Merge tag 'v3.10.103' into android-3.10.y
This is the 3.10.103 stable release
Conflicts:
drivers/input/joystick/xpad.c
fs/ext4/extents.c
net/ipv4/netfilter/arp_tables.c
net/ipv4/netfilter/ip_tables.c
net/ipv4/tcp_input.c
net/ipv6/netfilter/ip6_tables.c
net/socket.c
Change-Id: I293ede31fa94d55a377b7574db677858d53b4407
Signed-off-by: Greg Hackmann <ghackmann@google.com>
diff --git a/Documentation/ABI/obsolete/sysfs-block-zram b/Documentation/ABI/obsolete/sysfs-block-zram
new file mode 100644
index 0000000..720ea92
--- /dev/null
+++ b/Documentation/ABI/obsolete/sysfs-block-zram
@@ -0,0 +1,119 @@
+What: /sys/block/zram<id>/num_reads
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The num_reads file is read-only and specifies the number of
+ reads (failed or successful) done on this device.
+ Now accessible via zram<id>/stat node.
+
+What: /sys/block/zram<id>/num_writes
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The num_writes file is read-only and specifies the number of
+ writes (failed or successful) done on this device.
+ Now accessible via zram<id>/stat node.
+
+What: /sys/block/zram<id>/invalid_io
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The invalid_io file is read-only and specifies the number of
+ non-page-size-aligned I/O requests issued to this device.
+ Now accessible via zram<id>/io_stat node.
+
+What: /sys/block/zram<id>/failed_reads
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_reads file is read-only and specifies the number of
+ failed reads happened on this device.
+ Now accessible via zram<id>/io_stat node.
+
+What: /sys/block/zram<id>/failed_writes
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_writes file is read-only and specifies the number of
+ failed writes happened on this device.
+ Now accessible via zram<id>/io_stat node.
+
+What: /sys/block/zram<id>/notify_free
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The notify_free file is read-only. Depending on device usage
+ scenario it may account a) the number of pages freed because
+ of swap slot free notifications or b) the number of pages freed
+ because of REQ_DISCARD requests sent by bio. The former ones
+ are sent to a swap block device when a swap slot is freed, which
+ implies that this disk is being used as a swap disk. The latter
+ ones are sent by filesystem mounted with discard option,
+ whenever some data blocks are getting discarded.
+ Now accessible via zram<id>/io_stat node.
+
+What: /sys/block/zram<id>/zero_pages
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The zero_pages file is read-only and specifies number of zero
+ filled pages written to this disk. No memory is allocated for
+ such pages.
+ Now accessible via zram<id>/mm_stat node.
+
+What: /sys/block/zram<id>/orig_data_size
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The orig_data_size file is read-only and specifies uncompressed
+ size of data stored in this disk. This excludes zero-filled
+ pages (zero_pages) since no memory is allocated for them.
+ Unit: bytes
+ Now accessible via zram<id>/mm_stat node.
+
+What: /sys/block/zram<id>/compr_data_size
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The compr_data_size file is read-only and specifies compressed
+ size of data stored in this disk. So, compression ratio can be
+ calculated using orig_data_size and this statistic.
+ Unit: bytes
+ Now accessible via zram<id>/mm_stat node.
+
+What: /sys/block/zram<id>/mem_used_total
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The mem_used_total file is read-only and specifies the amount
+ of memory, including allocator fragmentation and metadata
+ overhead, allocated for this disk. So, allocator space
+ efficiency can be calculated using compr_data_size and this
+ statistic.
+ Unit: bytes
+ Now accessible via zram<id>/mm_stat node.
+
+What: /sys/block/zram<id>/mem_used_max
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The mem_used_max file is read/write and specifies the amount
+ of maximum memory zram have consumed to store compressed data.
+ For resetting the value, you should write "0". Otherwise,
+ you could see -EINVAL.
+ Unit: bytes
+ Downgraded to write-only node: so it's possible to set new
+ value only; its current value is stored in zram<id>/mm_stat
+ node.
+
+What: /sys/block/zram<id>/mem_limit
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The mem_limit file is read/write and specifies the maximum
+ amount of memory ZRAM can use to store the compressed data.
+ The limit could be changed in run time and "0" means disable
+ the limit. No limit is the initial state. Unit: bytes
+ Downgraded to write-only node: so it's possible to set new
+ value only; its current value is stored in zram<id>/mm_stat
+ node.
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index ec93fe3..2e69e83 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -5,20 +5,21 @@
The disksize file is read-write and specifies the disk size
which represents the limit on the *uncompressed* worth of data
that can be stored in this disk.
+ Unit: bytes
What: /sys/block/zram<id>/initstate
Date: August 2010
Contact: Nitin Gupta <ngupta@vflare.org>
Description:
- The disksize file is read-only and shows the initialization
+ The initstate file is read-only and shows the initialization
state of the device.
What: /sys/block/zram<id>/reset
Date: August 2010
Contact: Nitin Gupta <ngupta@vflare.org>
Description:
- The disksize file is write-only and allows resetting the
- device. The reset operation frees all the memory assocaited
+ The reset file is write-only and allows resetting the
+ device. The reset operation frees all the memory associated
with this device.
What: /sys/block/zram<id>/num_reads
@@ -42,24 +43,48 @@
The invalid_io file is read-only and specifies the number of
non-page-size-aligned I/O requests issued to this device.
+What: /sys/block/zram<id>/failed_reads
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_reads file is read-only and specifies the number of
+ failed reads happened on this device.
+
+What: /sys/block/zram<id>/failed_writes
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_writes file is read-only and specifies the number of
+ failed writes happened on this device.
+
+What: /sys/block/zram<id>/max_comp_streams
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The max_comp_streams file is read-write and specifies the
+ number of backend's zcomp_strm compression streams (number of
+ concurrent compress operations).
+
+What: /sys/block/zram<id>/comp_algorithm
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The comp_algorithm file is read-write and lets to show
+ available and selected compression algorithms, change
+ compression algorithm selection.
+
What: /sys/block/zram<id>/notify_free
Date: August 2010
Contact: Nitin Gupta <ngupta@vflare.org>
Description:
- The notify_free file is read-only and specifies the number of
- swap slot free notifications received by this device. These
- notifications are send to a swap block device when a swap slot
- is freed. This statistic is applicable only when this disk is
- being used as a swap disk.
-
-What: /sys/block/zram<id>/discard
-Date: August 2010
-Contact: Nitin Gupta <ngupta@vflare.org>
-Description:
- The discard file is read-only and specifies the number of
- discard requests received by this device. These requests
- provide information to block device regarding blocks which are
- no longer used by filesystem.
+ The notify_free file is read-only. Depending on device usage
+ scenario it may account a) the number of pages freed because
+ of swap slot free notifications or b) the number of pages freed
+ because of REQ_DISCARD requests sent by bio. The former ones
+ are sent to a swap block device when a swap slot is freed, which
+ implies that this disk is being used as a swap disk. The latter
+ ones are sent by filesystem mounted with discard option,
+ whenever some data blocks are getting discarded.
What: /sys/block/zram<id>/zero_pages
Date: August 2010
@@ -97,3 +122,47 @@
efficiency can be calculated using compr_data_size and this
statistic.
Unit: bytes
+
+What: /sys/block/zram<id>/mem_used_max
+Date: August 2014
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The mem_used_max file is read/write and specifies the amount
+ of maximum memory zram have consumed to store compressed data.
+ For resetting the value, you should write "0". Otherwise,
+ you could see -EINVAL.
+ Unit: bytes
+
+What: /sys/block/zram<id>/mem_limit
+Date: August 2014
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The mem_limit file is read/write and specifies the maximum
+ amount of memory ZRAM can use to store the compressed data. The
+ limit could be changed in run time and "0" means disable the
+ limit. No limit is the initial state. Unit: bytes
+
+What: /sys/block/zram<id>/compact
+Date: August 2015
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The compact file is write-only and trigger compaction for
+ allocator zrm uses. The allocator moves some objects so that
+ it could free fragment space.
+
+What: /sys/block/zram<id>/io_stat
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The io_stat file is read-only and accumulates device's I/O
+ statistics not accounted by block layer. For example,
+ failed_reads, failed_writes, etc. File format is similar to
+ block layer statistics file format.
+
+What: /sys/block/zram<id>/mm_stat
+Date: August 2015
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The mm_stat file is read-only and represents device's mm
+ statistics (orig_data_size, compr_data_size, etc.) in a format
+ similar to block layer statistics file format.
diff --git a/Documentation/ABI/testing/sysfs-class-dual-role-usb b/Documentation/ABI/testing/sysfs-class-dual-role-usb
new file mode 100644
index 0000000..a900fd7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-dual-role-usb
@@ -0,0 +1,71 @@
+What: /sys/class/dual_role_usb/.../
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ Provide a generic interface to monitor and change
+ the state of dual role usb ports. The name here
+ refers to the name mentioned in the
+ dual_role_phy_desc that is passed while registering
+ the dual_role_phy_intstance through
+ devm_dual_role_instance_register.
+
+What: /sys/class/dual_role_usb/.../supported_modes
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ This is a static node, once initialized this
+ is not expected to change during runtime. "dfp"
+ refers to "downstream facing port" i.e. port can
+ only act as host. "ufp" refers to "upstream
+ facing port" i.e. port can only act as device.
+ "dfp ufp" refers to "dual role port" i.e. the port
+ can either be a host port or a device port.
+
+What: /sys/class/dual_role_usb/.../mode
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The mode node refers to the current mode in which the
+ port is operating. "dfp" for host ports. "ufp" for device
+ ports and "none" when cable is not connected.
+
+ On devices where the USB mode is software-controllable,
+ userspace can change the mode by writing "dfp" or "ufp".
+ On devices where the USB mode is fixed in hardware,
+ this attribute is read-only.
+
+What: /sys/class/dual_role_usb/.../power_role
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The power_role node mentions whether the port
+ is "sink"ing or "source"ing power. "none" if
+ they are not connected.
+
+ On devices implementing USB Power Delivery,
+ userspace can control the power role by writing "sink" or
+ "source". On devices without USB-PD, this attribute is
+ read-only.
+
+What: /sys/class/dual_role_usb/.../data_role
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The data_role node mentions whether the port
+ is acting as "host" or "device" for USB data connection.
+ "none" if there is no active data link.
+
+ On devices implementing USB Power Delivery, userspace
+ can control the data role by writing "host" or "device".
+ On devices without USB-PD, this attribute is read-only
+
+What: /sys/class/dual_role_usb/.../powers_vconn
+Date: June 2015
+Contact: Badhri Jagan Sridharan<badhri@google.com>
+Description:
+ The powers_vconn node mentions whether the port
+ is supplying power for VCONN pin.
+
+ On devices with software control of VCONN,
+ userspace can disable the power supply to VCONN by writing "n",
+ or enable the power supply by writing "y".
diff --git a/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
new file mode 100644
index 0000000..acb19b9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
@@ -0,0 +1,16 @@
+What: /sys/kernel/wakeup_reasons/last_resume_reason
+Date: February 2014
+Contact: Ruchi Kandoi <kandoiruchi@google.com>
+Description:
+ The /sys/kernel/wakeup_reasons/last_resume_reason is
+ used to report wakeup reasons after system exited suspend.
+
+What: /sys/kernel/wakeup_reasons/last_suspend_time
+Date: March 2015
+Contact: jinqian <jinqian@google.com>
+Description:
+ The /sys/kernel/wakeup_reasons/last_suspend_time is
+ used to report time spent in last suspend cycle. It contains
+ two numbers (in seconds) separated by space. First number is
+ the time spent in suspend and resume processes. Second number
+ is the time spent in sleep state.
\ No newline at end of file
diff --git a/Documentation/android.txt b/Documentation/android.txt
new file mode 100644
index 0000000..0f40a78
--- /dev/null
+++ b/Documentation/android.txt
@@ -0,0 +1,121 @@
+ =============
+ A N D R O I D
+ =============
+
+Copyright (C) 2009 Google, Inc.
+Written by Mike Chan <mike@android.com>
+
+CONTENTS:
+---------
+
+1. Android
+ 1.1 Required enabled config options
+ 1.2 Required disabled config options
+ 1.3 Recommended enabled config options
+2. Contact
+
+
+1. Android
+==========
+
+Android (www.android.com) is an open source operating system for mobile devices.
+This document describes configurations needed to run the Android framework on
+top of the Linux kernel.
+
+To see a working defconfig look at msm_defconfig or goldfish_defconfig
+which can be found at http://android.git.kernel.org in kernel/common.git
+and kernel/msm.git
+
+
+1.1 Required enabled config options
+-----------------------------------
+After building a standard defconfig, ensure that these options are enabled in
+your .config or defconfig if they are not already. Based off the msm_defconfig.
+You should keep the rest of the default options enabled in the defconfig
+unless you know what you are doing.
+
+ANDROID_PARANOID_NETWORK
+ASHMEM
+CONFIG_FB_MODE_HELPERS
+CONFIG_FONT_8x16
+CONFIG_FONT_8x8
+CONFIG_YAFFS_SHORT_NAMES_IN_RAM
+DAB
+EARLYSUSPEND
+FB
+FB_CFB_COPYAREA
+FB_CFB_FILLRECT
+FB_CFB_IMAGEBLIT
+FB_DEFERRED_IO
+FB_TILEBLITTING
+HIGH_RES_TIMERS
+INOTIFY
+INOTIFY_USER
+INPUT_EVDEV
+INPUT_GPIO
+INPUT_MISC
+LEDS_CLASS
+LEDS_GPIO
+LOCK_KERNEL
+LkOGGER
+LOW_MEMORY_KILLER
+MISC_DEVICES
+NEW_LEDS
+NO_HZ
+POWER_SUPPLY
+PREEMPT
+RAMFS
+RTC_CLASS
+RTC_LIB
+SWITCH
+SWITCH_GPIO
+TMPFS
+UID_STAT
+UID16
+USB_FUNCTION
+USB_FUNCTION_ADB
+USER_WAKELOCK
+VIDEO_OUTPUT_CONTROL
+WAKELOCK
+YAFFS_AUTO_YAFFS2
+YAFFS_FS
+YAFFS_YAFFS1
+YAFFS_YAFFS2
+
+
+1.2 Required disabled config options
+------------------------------------
+CONFIG_YAFFS_DISABLE_LAZY_LOAD
+DNOTIFY
+
+
+1.3 Recommended enabled config options
+------------------------------
+ANDROID_PMEM
+PSTORE_CONSOLE
+PSTORE_RAM
+SCHEDSTATS
+DEBUG_PREEMPT
+DEBUG_MUTEXES
+DEBUG_SPINLOCK_SLEEP
+DEBUG_INFO
+FRAME_POINTER
+CPU_FREQ
+CPU_FREQ_TABLE
+CPU_FREQ_DEFAULT_GOV_ONDEMAND
+CPU_FREQ_GOV_ONDEMAND
+CRC_CCITT
+EMBEDDED
+INPUT_TOUCHSCREEN
+I2C
+I2C_BOARDINFO
+LOG_BUF_SHIFT=17
+SERIAL_CORE
+SERIAL_CORE_CONSOLE
+
+
+2. Contact
+==========
+website: http://android.git.kernel.org
+
+mailing-lists: android-kernel@googlegroups.com
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
new file mode 100644
index 0000000..d9995f1
--- /dev/null
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -0,0 +1,34 @@
+ Tagged virtual addresses in AArch64 Linux
+ =========================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date : 12 June 2013
+
+This document briefly describes the provision of tagged virtual
+addresses in the AArch64 translation system and their potential uses
+in AArch64 Linux.
+
+The kernel configures the translation tables so that translations made
+via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
+the virtual address ignored by the translation hardware. This frees up
+this byte for application use, with the following caveats:
+
+ (1) The kernel requires that all user addresses passed to EL1
+ are tagged with tag 0x00. This means that any syscall
+ parameters containing user virtual addresses *must* have
+ their top byte cleared before trapping to the kernel.
+
+ (2) Non-zero tags are not preserved when delivering signals.
+ This means that signal handlers in applications making use
+ of tags cannot rely on the tag information for user virtual
+ addresses being maintained for fields inside siginfo_t.
+ One exception to this rule is for signals raised in response
+ to watchpoint debug exceptions, where the tag information
+ will be preserved.
+
+ (3) Special care should be taken when using tagged pointers,
+ since it is likely that C compilers will not hazard two
+ virtual addresses differing only in the upper byte.
+
+The architecture prevents the use of a tagged PC, so the upper byte will
+be set to a sign-extension of bit 55 on exception return.
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index d18ecd8..52bda21 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -22,3 +22,9 @@
- Switching I/O schedulers at runtime
writeback_cache_control.txt
- Control of volatile write back caches
+mmc-max-speed.txt
+ - eMMC layer speed simulation, related to /sys/block/mmcblk*/
+ attributes:
+ max_read_speed
+ max_write_speed
+ cache_size
diff --git a/Documentation/block/mmc-max-speed.txt b/Documentation/block/mmc-max-speed.txt
new file mode 100644
index 0000000..3f052b9
--- /dev/null
+++ b/Documentation/block/mmc-max-speed.txt
@@ -0,0 +1,38 @@
+eMMC Block layer simulation speed controls in /sys/block/mmcblk*/
+===============================================
+
+Turned on with CONFIG_MMC_SIMULATE_MAX_SPEED which enables MMC device speed
+limiting. Used to test and simulate the behavior of the system when
+confronted with a slow MMC.
+
+Enables max_read_speed, max_write_speed and cache_size attributes and module
+default parameters to control the write or read maximum KB/second speed
+behaviors.
+
+NB: There is room for improving the algorithm for aspects tied directly to
+eMMC specific behavior. For instance, wear leveling and stalls from an
+exhausted erase pool. We would expect that if there was a need to provide
+similar speed simulation controls to other types of block devices, aspects of
+their behavior are modelled separately (e.g. head seek times, heat assist,
+shingling and rotational latency).
+
+/sys/block/mmcblk0/max_read_speed:
+
+Number of KB/second reads allowed to the block device. Used to test and
+simulate the behavior of the system when confronted with a slow reading MMC.
+Set to 0 or "off" to place no speed limit.
+
+/sys/block/mmcblk0/max_write_speed:
+
+Number of KB/second writes allowed to the block device. Used to test and
+simulate the behavior of the system when confronted with a slow writing MMC.
+Set to 0 or "off" to place no speed limit.
+
+/sys/block/mmcblk0/cache_size:
+
+Number of MB of high speed memory or high speed SLC cache expected on the
+eMMC device being simulated. Used to help simulate the write-back behavior
+more accurately. The assumption is the cache has no delay, but draws down
+in the background to the MLC/TLC primary store at the max_write_speed rate.
+Any write speed delays will show up when the cache is full, or when an I/O
+request to flush is issued.
diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
new file mode 100644
index 0000000..48a183e
--- /dev/null
+++ b/Documentation/blockdev/zram.txt
@@ -0,0 +1,189 @@
+zram: Compressed RAM based block devices
+----------------------------------------
+
+* Introduction
+
+The zram module creates RAM based block devices named /dev/zram<id>
+(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
+in memory itself. These disks allow very fast I/O and compression provides
+good amounts of memory savings. Some of the usecases include /tmp storage,
+use as swap disks, various caches under /var and maybe many more :)
+
+Statistics for individual zram devices are exported through sysfs nodes at
+/sys/block/zram<id>/
+
+* Usage
+
+Following shows a typical sequence of steps for using zram.
+
+1) Load Module:
+ modprobe zram num_devices=4
+ This creates 4 devices: /dev/zram{0,1,2,3}
+ (num_devices parameter is optional. Default: 1)
+
+2) Set max number of compression streams
+ Compression backend may use up to max_comp_streams compression streams,
+ thus allowing up to max_comp_streams concurrent compression operations.
+ By default, compression backend uses single compression stream.
+
+ Examples:
+ #show max compression streams number
+ cat /sys/block/zram0/max_comp_streams
+
+ #set max compression streams number to 3
+ echo 3 > /sys/block/zram0/max_comp_streams
+
+Note:
+In order to enable compression backend's multi stream support max_comp_streams
+must be initially set to desired concurrency level before ZRAM device
+initialisation. Once the device initialised as a single stream compression
+backend (max_comp_streams equals to 1), you will see error if you try to change
+the value of max_comp_streams because single stream compression backend
+implemented as a special case by lock overhead issue and does not support
+dynamic max_comp_streams. Only multi stream backend supports dynamic
+max_comp_streams adjustment.
+
+3) Select compression algorithm
+ Using comp_algorithm device attribute one can see available and
+ currently selected (shown in square brackets) compression algortithms,
+ change selected compression algorithm (once the device is initialised
+ there is no way to change compression algorithm).
+
+ Examples:
+ #show supported compression algorithms
+ cat /sys/block/zram0/comp_algorithm
+ lzo [lz4]
+
+ #select lzo compression algorithm
+ echo lzo > /sys/block/zram0/comp_algorithm
+
+4) Set Disksize
+ Set disk size by writing the value to sysfs node 'disksize'.
+ The value can be either in bytes or you can use mem suffixes.
+ Examples:
+ # Initialize /dev/zram0 with 50MB disksize
+ echo $((50*1024*1024)) > /sys/block/zram0/disksize
+
+ # Using mem suffixes
+ echo 256K > /sys/block/zram0/disksize
+ echo 512M > /sys/block/zram0/disksize
+ echo 1G > /sys/block/zram0/disksize
+
+Note:
+There is little point creating a zram of greater than twice the size of memory
+since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
+size of the disk when not in use so a huge zram is wasteful.
+
+5) Set memory limit: Optional
+ Set memory limit by writing the value to sysfs node 'mem_limit'.
+ The value can be either in bytes or you can use mem suffixes.
+ In addition, you could change the value in runtime.
+ Examples:
+ # limit /dev/zram0 with 50MB memory
+ echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
+
+ # Using mem suffixes
+ echo 256K > /sys/block/zram0/mem_limit
+ echo 512M > /sys/block/zram0/mem_limit
+ echo 1G > /sys/block/zram0/mem_limit
+
+ # To disable memory limit
+ echo 0 > /sys/block/zram0/mem_limit
+
+6) Activate:
+ mkswap /dev/zram0
+ swapon /dev/zram0
+
+ mkfs.ext4 /dev/zram1
+ mount /dev/zram1 /tmp
+
+7) Stats:
+Per-device statistics are exported as various nodes under /sys/block/zram<id>/
+
+A brief description of exported device attritbutes. For more details please
+read Documentation/ABI/testing/sysfs-block-zram.
+
+Name access description
+---- ------ -----------
+disksize RW show and set the device's disk size
+initstate RO shows the initialization state of the device
+reset WO trigger device reset
+num_reads RO the number of reads
+failed_reads RO the number of failed reads
+num_write RO the number of writes
+failed_writes RO the number of failed writes
+invalid_io RO the number of non-page-size-aligned I/O requests
+max_comp_streams RW the number of possible concurrent compress operations
+comp_algorithm RW show and change the compression algorithm
+notify_free RO the number of notifications to free pages (either
+ slot free notifications or REQ_DISCARD requests)
+zero_pages RO the number of zero filled pages written to this disk
+orig_data_size RO uncompressed size of data stored in this disk
+compr_data_size RO compressed size of data stored in this disk
+mem_used_total RO the amount of memory allocated for this disk
+mem_used_max RW the maximum amount memory zram have consumed to
+ store compressed data
+mem_limit RW the maximum amount of memory ZRAM can use to store
+ the compressed data
+num_migrated RO the number of objects migrated migrated by compaction
+
+
+WARNING
+=======
+per-stat sysfs attributes are considered to be deprecated.
+The basic strategy is:
+-- the existing RW nodes will be downgraded to WO nodes (in linux 4.11)
+-- deprecated RO sysfs nodes will eventually be removed (in linux 4.11)
+
+The list of deprecated attributes can be found here:
+Documentation/ABI/obsolete/sysfs-block-zram
+
+Basically, every attribute that has its own read accessible sysfs node
+(e.g. num_reads) *AND* is accessible via one of the stat files (zram<id>/stat
+or zram<id>/io_stat or zram<id>/mm_stat) is considered to be deprecated.
+
+User space is advised to use the following files to read the device statistics.
+
+File /sys/block/zram<id>/stat
+
+Represents block layer statistics. Read Documentation/block/stat.txt for
+details.
+
+File /sys/block/zram<id>/io_stat
+
+The stat file represents device's I/O statistics not accounted by block
+layer and, thus, not available in zram<id>/stat file. It consists of a
+single line of text and contains the following stats separated by
+whitespace:
+ failed_reads
+ failed_writes
+ invalid_io
+ notify_free
+
+File /sys/block/zram<id>/mm_stat
+
+The stat file represents device's mm statistics. It consists of a single
+line of text and contains the following stats separated by whitespace:
+ orig_data_size
+ compr_data_size
+ mem_used_total
+ mem_limit
+ mem_used_max
+ zero_pages
+ num_migrated
+
+8) Deactivate:
+ swapoff /dev/zram0
+ umount /dev/zram1
+
+9) Reset:
+ Write any positive value to 'reset' sysfs node
+ echo 1 > /sys/block/zram0/reset
+ echo 1 > /sys/block/zram1/reset
+
+ This frees all the memory allocated for the given device and
+ resets the disksize to zero. You must set the disksize again
+ before reusing the device.
+
+Nitin Gupta
+ngupta@vflare.org
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 638bf17..61dc0ec 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -598,6 +598,15 @@
be called for a newly-created cgroup if an error occurs after this
subsystem's create() method has been called for the new cgroup).
+int allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+(cgroup_mutex held by caller)
+
+Called prior to moving a task into a cgroup; if the subsystem
+returns an error, this will abort the attach operation. Used
+to extend the permission checks - if all subsystems in a cgroup
+return 0, the attach will be allowed to proceed, even if the
+default permission check (root or same user) fails.
+
int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
(cgroup_mutex held by caller)
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index 219970b..875eecb 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -28,6 +28,7 @@
2.3 Userspace
2.4 Ondemand
2.5 Conservative
+2.6 Interactive
3. The Governor Interface in the CPUfreq Core
@@ -218,6 +219,90 @@
speed. Load for frequency increase is still evaluated every
sampling rate.
+2.6 Interactive
+---------------
+
+The CPUfreq governor "interactive" is designed for latency-sensitive,
+interactive workloads. This governor sets the CPU speed depending on
+usage, similar to "ondemand" and "conservative" governors, but with a
+different set of configurable behaviors.
+
+The tuneable values for this governor are:
+
+target_loads: CPU load values used to adjust speed to influence the
+current CPU load toward that value. In general, the lower the target
+load, the more often the governor will raise CPU speeds to bring load
+below the target. The format is a single target load, optionally
+followed by pairs of CPU speeds and CPU loads to target at or above
+those speeds. Colons can be used between the speeds and associated
+target loads for readability. For example:
+
+ 85 1000000:90 1700000:99
+
+targets CPU load 85% below speed 1GHz, 90% at or above 1GHz, until
+1.7GHz and above, at which load 99% is targeted. If speeds are
+specified these must appear in ascending order. Higher target load
+values are typically specified for higher speeds, that is, target load
+values also usually appear in an ascending order. The default is
+target load 90% for all speeds.
+
+min_sample_time: The minimum amount of time to spend at the current
+frequency before ramping down. Default is 80000 uS.
+
+hispeed_freq: An intermediate "hi speed" at which to initially ramp
+when CPU load hits the value specified in go_hispeed_load. If load
+stays high for the amount of time specified in above_hispeed_delay,
+then speed may be bumped higher. Default is the maximum speed
+allowed by the policy at governor initialization time.
+
+go_hispeed_load: The CPU load at which to ramp to hispeed_freq.
+Default is 99%.
+
+above_hispeed_delay: When speed is at or above hispeed_freq, wait for
+this long before raising speed in response to continued high load.
+The format is a single delay value, optionally followed by pairs of
+CPU speeds and the delay to use at or above those speeds. Colons can
+be used between the speeds and associated delays for readability. For
+example:
+
+ 80000 1300000:200000 1500000:40000
+
+uses delay 80000 uS until CPU speed 1.3 GHz, at which speed delay
+200000 uS is used until speed 1.5 GHz, at which speed (and above)
+delay 40000 uS is used. If speeds are specified these must appear in
+ascending order. Default is 20000 uS.
+
+timer_rate: Sample rate for reevaluating CPU load when the CPU is not
+idle. A deferrable timer is used, such that the CPU will not be woken
+from idle to service this timer until something else needs to run.
+(The maximum time to allow deferring this timer when not running at
+minimum speed is configurable via timer_slack.) Default is 20000 uS.
+
+timer_slack: Maximum additional time to defer handling the governor
+sampling timer beyond timer_rate when running at speeds above the
+minimum. For platforms that consume additional power at idle when
+CPUs are running at speeds greater than minimum, this places an upper
+bound on how long the timer will be deferred prior to re-evaluating
+load and dropping speed. For example, if timer_rate is 20000uS and
+timer_slack is 10000uS then timers will be deferred for up to 30msec
+when not at lowest speed. A value of -1 means defer timers
+indefinitely at all speeds. Default is 80000 uS.
+
+boost: If non-zero, immediately boost speed of all CPUs to at least
+hispeed_freq until zero is written to this attribute. If zero, allow
+CPU speeds to drop below hispeed_freq according to load as usual.
+Default is zero.
+
+boostpulse: On each write, immediately boost speed of all CPUs to
+hispeed_freq for at least the period of time specified by
+boostpulse_duration, after which speeds are allowed to drop below
+hispeed_freq according to load as usual.
+
+boostpulse_duration: Length of time to hold CPU speed at hispeed_freq
+on a write to boostpulse, before allowing speed to drop according to
+load as usual. Default is 80000 uS.
+
+
3. The Governor Interface in the CPUfreq Core
=============================================
diff --git a/Documentation/device-mapper/boot.txt b/Documentation/device-mapper/boot.txt
new file mode 100644
index 0000000..adcaad5
--- /dev/null
+++ b/Documentation/device-mapper/boot.txt
@@ -0,0 +1,42 @@
+Boot time creation of mapped devices
+===================================
+
+It is possible to configure a device mapper device to act as the root
+device for your system in two ways.
+
+The first is to build an initial ramdisk which boots to a minimal
+userspace which configures the device, then pivot_root(8) in to it.
+
+For simple device mapper configurations, it is possible to boot directly
+using the following kernel command line:
+
+dm="<name> <uuid> <ro>,table line 1,...,table line n"
+
+name = the name to associate with the device
+ after boot, udev, if used, will use that name to label
+ the device node.
+uuid = may be 'none' or the UUID desired for the device.
+ro = may be "ro" or "rw". If "ro", the device and device table will be
+ marked read-only.
+
+Each table line may be as normal when using the dmsetup tool except for
+two variations:
+1. Any use of commas will be interpreted as a newline
+2. Quotation marks cannot be escaped and cannot be used without
+ terminating the dm= argument.
+
+Unless renamed by udev, the device node created will be dm-0 as the
+first minor number for the device-mapper is used during early creation.
+
+Example
+=======
+
+- Booting to a linear array made up of user-mode linux block devices:
+
+ dm="lroot none 0, 0 4096 linear 98:16 0, 4096 4096 linear 98:32 0" \
+ root=/dev/dm-0
+
+Will boot to a rw dm-linear target of 8192 sectors split across two
+block devices identified by their major:minor numbers. After boot, udev
+will rename this target to /dev/mapper/lroot (depending on the rules).
+No uuid was assigned.
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
index 9884681..3ee801b 100644
--- a/Documentation/device-mapper/verity.txt
+++ b/Documentation/device-mapper/verity.txt
@@ -11,6 +11,7 @@
<data_block_size> <hash_block_size>
<num_data_blocks> <hash_start_block>
<algorithm> <digest> <salt>
+ [<#opt_params> <opt_params>]
<version>
This is the type of the on-disk hash format.
@@ -62,6 +63,52 @@
<salt>
The hexadecimal encoding of the salt value.
+<#opt_params>
+ Number of optional parameters. If there are no optional parameters,
+ the optional paramaters section can be skipped or #opt_params can be zero.
+ Otherwise #opt_params is the number of following arguments.
+
+ Example of optional parameters section:
+ 1 ignore_corruption
+
+ignore_corruption
+ Log corrupted blocks, but allow read operations to proceed normally.
+
+restart_on_corruption
+ Restart the system when a corrupted block is discovered. This option is
+ not compatible with ignore_corruption and requires user space support to
+ avoid restart loops.
+
+ignore_zero_blocks
+ Do not verify blocks that are expected to contain zeroes and always return
+ zeroes instead. This may be useful if the partition contains unused blocks
+ that are not guaranteed to contain zeroes.
+
+use_fec_from_device
+ Use forward error correction (FEC) to recover from corruption if hash
+ verification fails. Use encoding data from the specified device. This
+ may be the same device where data and hash blocks reside, in which case
+ fec_start must be outside data and hash areas.
+
+ If the encoding data covers additional metadata, it must be accessible
+ on the hash device after the hash blocks.
+
+ Note: block sizes for data and hash devices must match.
+
+fec_roots
+ Number of generator roots. This equals to the number of parity bytes in
+ the encoding data. For example, in RS(M, N) encoding, the number of roots
+ is M-N.
+
+fec_blocks
+ The number of encoding data blocks on the FEC device. The block size for
+ the FEC device is <data_block_size>.
+
+fec_start
+ This is the offset, in <data_block_size> blocks, from the start of the
+ FEC device to the beginning of the encoding data.
+
+
Theory of operation
===================
@@ -125,7 +172,7 @@
The full specification of kernel parameters and on-disk metadata format
is available at the cryptsetup project's wiki page
- http://code.google.com/p/cryptsetup/wiki/DMVerity
+ https://gitlab.com/cryptsetup/cryptsetup/wikis/DMVerity
Status
======
@@ -142,7 +189,7 @@
A command line tool veritysetup is available to compute or verify
the hash tree or activate the kernel device. This is available from
-the cryptsetup upstream repository http://code.google.com/p/cryptsetup/
+the cryptsetup upstream repository https://gitlab.com/cryptsetup/cryptsetup/
(as a libcryptsetup extension).
Create hash on the device:
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 85aada2..458b57f 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -28,6 +28,7 @@
- cap-mmc-highspeed: MMC high-speed timing is supported
- cap-power-off-card: powering off the card is safe
- cap-sdio-irq: enable SDIO IRQ signalling on this interface
+- full-pwr-cycle: full power cycle of the card is supported
*NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 0706d32..cbbac3f 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -189,7 +189,7 @@
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
sector_t (*bmap)(struct address_space *, sector_t);
- int (*invalidatepage) (struct page *, unsigned long);
+ void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, int);
void (*freepage)(struct page *);
int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -310,8 +310,8 @@
keep it that way and don't breed new callers.
->invalidatepage() is called when the filesystem must attempt to drop
-some or all of the buffers from the page when it is being truncated. It
-returns zero on success. If ->invalidatepage is zero, the kernel uses
+some or all of the buffers from the page when it is being truncated. It
+returns zero on success. If ->invalidatepage is zero, the kernel uses
block_invalidatepage() instead.
->releasepage() is called when the kernel is about to try to drop the
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 4db22f6..85a4a03 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -445,3 +445,6 @@
[mandatory]
FS_REVAL_DOT is gone; if you used to have it, add ->d_weak_revalidate()
in your dentry operations instead.
+--
+[mandatory]
+ vfs_readdir() is gone; switch to iterate_dir() instead
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 954eab8..559a818 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -369,6 +369,8 @@
[stack:1001] = the stack of the thread with tid 1001
[vdso] = the "virtual dynamic shared object",
the kernel system call handler
+ [anon:<name>] = an anonymous mapping that has been
+ named by userspace
or if empty, the mapping is anonymous.
@@ -415,25 +417,34 @@
Referenced: 892 kB
Anonymous: 0 kB
Swap: 0 kB
+SwapPss: 0 kB
KernelPageSize: 4 kB
MMUPageSize: 4 kB
Locked: 374 kB
VmFlags: rd ex mr mw me de
+Name: name from userspace
the first of these lines shows the same information as is displayed for the
mapping in /proc/PID/maps. The remaining lines show the size of the mapping
(size), the amount of the mapping that is currently resident in RAM (RSS), the
process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping. Note that even a page which is part of a
-MAP_SHARED mapping, but has only a single pte mapped, i.e. is currently used
-by only one process, is accounted as private and not as shared. "Referenced"
-indicates the amount of memory currently marked as referenced or accessed.
+dirty private pages in the mapping.
+
+The "proportional set size" (PSS) of a process is the count of pages it has
+in memory, where each page is divided by the number of processes sharing it.
+So if a process has 1000 pages all to itself, and 1000 shared with one other
+process, its PSS will be 1500.
+Note that even a page which is part of a MAP_SHARED mapping, but has only
+a single pte mapped, i.e. is currently used by only one process, is accounted
+as private and not as shared.
+"Referenced" indicates the amount of memory currently marked as referenced or
+accessed.
"Anonymous" shows the amount of memory that does not belong to any file. Even
a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
and a page is modified, the file page is replaced by a private anonymous copy.
"Swap" shows how much would-be-anonymous memory is also used, but out on
swap.
-
+"SwapPss" shows proportional swap share of this mapping.
"VmFlags" field deserves a separate description. This member represents the kernel
flags associated with the particular virtual memory area in two letter encoded
manner. The codes are the following:
@@ -469,6 +480,9 @@
be present in all further kernel releases. Things get changed, the flags may
be vanished or the reverse -- new added.
+The "Name" field will only be present on a mapping that has been named by
+userspace, and will show the name passed in by userspace.
+
This file is only present if the CONFIG_MMU kernel configuration option is
enabled.
@@ -484,6 +498,10 @@
> echo 3 > /proc/PID/clear_refs
Any other value written to /proc/PID/clear_refs will have no effect.
+To reset the peak resident set size ("high water mark") to the process's
+current value:
+ > echo 5 > /proc/PID/clear_refs
+
The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
using /proc/kpageflags and number of times a page is mapped using
/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt
index 403c090..e5274f8 100644
--- a/Documentation/filesystems/squashfs.txt
+++ b/Documentation/filesystems/squashfs.txt
@@ -2,10 +2,10 @@
=======================
Squashfs is a compressed read-only filesystem for Linux.
-It uses zlib/lzo/xz compression to compress files, inodes and directories.
-Inodes in the system are very small and all blocks are packed to minimise
-data overhead. Block sizes greater than 4K are supported up to a maximum
-of 1Mbytes (default block size 128K).
+It uses zlib, lz4, lzo, or xz compression to compress files, inodes and
+directories. Inodes in the system are very small and all blocks are packed to
+minimise data overhead. Block sizes greater than 4K are supported up to a
+maximum of 1Mbytes (default block size 128K).
Squashfs is intended for general read-only filesystem use, for archival
use (i.e. in cases where a .tar.gz file may be used), and in constrained
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index bc4b06b..e445b95 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -549,7 +549,7 @@
-------------------------------
This describes how the VFS can manipulate mapping of a file to page cache in
-your filesystem. As of kernel 2.6.22, the following members are defined:
+your filesystem. The following members are defined:
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
@@ -566,7 +566,7 @@
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
sector_t (*bmap)(struct address_space *, sector_t);
- int (*invalidatepage) (struct page *, unsigned long);
+ void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, int);
void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -685,14 +685,14 @@
invalidatepage: If a page has PagePrivate set, then invalidatepage
will be called when part or all of the page is to be removed
from the address space. This generally corresponds to either a
- truncation or a complete invalidation of the address space
- (in the latter case 'offset' will always be 0).
- Any private data associated with the page should be updated
- to reflect this truncation. If offset is 0, then
- the private data should be released, because the page
- must be able to be completely discarded. This may be done by
- calling the ->releasepage function, but in this case the
- release MUST succeed.
+ truncation, punch hole or a complete invalidation of the address
+ space (in the latter case 'offset' will always be 0 and 'length'
+ will be PAGE_CACHE_SIZE). Any private data associated with the page
+ should be updated to reflect this truncation. If offset is 0 and
+ length is PAGE_CACHE_SIZE, then the private data should be released,
+ because the page must be able to be completely discarded. This may
+ be done by calling the ->releasepage function, but in this case the
+ release MUST succeed.
releasepage: releasepage is called on PagePrivate pages to indicate
that the page should be freed if possible. ->releasepage
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 98da831..1421989 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -46,6 +46,7 @@
BLACKFIN Blackfin architecture is enabled.
CLK Common clock infrastructure is enabled.
CMA Contiguous Memory Area support is enabled.
+ DM Device mapper support is enabled.
DRM Direct Rendering Management support is enabled.
DYNAMIC_DEBUG Build in debug messages and enable them at runtime
EDD BIOS Enhanced Disk Drive Services (EDD) is enabled
@@ -741,6 +742,11 @@
Disable PIN 1 of APIC timer
Can be useful to work around chipset bugs.
+ dm= [DM] Allows early creation of a device-mapper device.
+ See Documentation/device-mapper/boot.txt.
+
+ dmasound= [HW,OSS] Sound subsystem buffers
+
dma_debug=off If the kernel is compiled with DMA_API_DEBUG support,
this option disables the debugging code at boot.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a59ee43..b4ec119 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -22,6 +22,15 @@
min_pmtu - INTEGER
default 552 - minimum discovered Path MTU
+fwmark_reflect - BOOLEAN
+ Controls the fwmark of kernel-generated IPv4 reply packets that are not
+ associated with a socket for example, TCP RSTs or ICMP echo replies).
+ If unset, these packets have a fwmark of zero. If set, they have the
+ fwmark of the packet they are replying to. Similarly affects the fwmark
+ used by internal routing lookups triggered by incoming packets, such as
+ the ones used for Path MTU Discovery.
+ Default: 0
+
route/max_size - INTEGER
Maximum number of routes allowed in the kernel. Increase
this when using large numbers of interfaces and/or routes.
@@ -468,6 +477,16 @@
See include/net/tcp.h and the code for more details.
+tcp_fwmark_accept - BOOLEAN
+ If set, incoming connections to listening sockets that do not have a
+ socket mark will set the mark of the accepting socket to the fwmark of
+ the incoming SYN packet. This will cause all packets on that connection
+ (starting from the first SYNACK) to be sent with that fwmark. The
+ listening socket's mark is unchanged. Listening sockets that already
+ have a fwmark set via setsockopt(SOL_SOCKET, SO_MARK, ...) are
+ unaffected.
+ Default: 0
+
tcp_syn_retries - INTEGER
Number of times initial SYNs for an active TCP connection attempt
will be retransmitted. Should not be higher than 255. Default value
@@ -1093,6 +1112,15 @@
proxy_ndp - BOOLEAN
Do proxy ndp.
+fwmark_reflect - BOOLEAN
+ Controls the fwmark of kernel-generated IPv6 reply packets that are not
+ associated with a socket for example, TCP RSTs or ICMPv6 echo replies).
+ If unset, these packets have a fwmark of zero. If set, they have the
+ fwmark of the packet they are replying to. Similarly affects the fwmark
+ used by internal routing lookups triggered by incoming packets, such as
+ the ones used for Path MTU Discovery.
+ Default: 0
+
conf/interface/*:
Change special settings per interface.
@@ -1230,6 +1258,13 @@
routers are present.
Default: 3
+use_oif_addrs_only - BOOLEAN
+ When enabled, the candidate source addresses for destinations
+ routed via this interface are restricted to the set of addresses
+ configured on this interface (vis. RFC 6724, section 4).
+
+ Default: false
+
use_tempaddr - INTEGER
Preference for Privacy Extensions (RFC3041).
<= 0 : disable Privacy Extensions
@@ -1311,6 +1346,19 @@
1 - Generate unsolicited neighbour advertisements when device is brought
up or hardware address changes.
+optimistic_dad - BOOLEAN
+ Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
+ 0: disabled (default)
+ 1: enabled
+
+use_optimistic - BOOLEAN
+ If enabled, do not classify optimistic addresses as deprecated during
+ source address selection. Preferred addresses will still be chosen
+ before optimistic addresses, subject to other ranking in the source
+ address selection algorithm.
+ 0: disabled (default)
+ 1: enabled
+
icmp/*:
ratelimit - INTEGER
Limit the maximal rates for sending ICMPv6 packets.
diff --git a/Documentation/sync.txt b/Documentation/sync.txt
new file mode 100644
index 0000000..a2d05e7
--- /dev/null
+++ b/Documentation/sync.txt
@@ -0,0 +1,75 @@
+Motivation:
+
+In complicated DMA pipelines such as graphics (multimedia, camera, gpu, display)
+a consumer of a buffer needs to know when the producer has finished producing
+it. Likewise the producer needs to know when the consumer is finished with the
+buffer so it can reuse it. A particular buffer may be consumed by multiple
+consumers which will retain the buffer for different amounts of time. In
+addition, a consumer may consume multiple buffers atomically.
+The sync framework adds an API which allows synchronization between the
+producers and consumers in a generic way while also allowing platforms which
+have shared hardware synchronization primitives to exploit them.
+
+Goals:
+ * provide a generic API for expressing synchronization dependencies
+ * allow drivers to exploit hardware synchronization between hardware
+ blocks
+ * provide a userspace API that allows a compositor to manage
+ dependencies.
+ * provide rich telemetry data to allow debugging slowdowns and stalls of
+ the graphics pipeline.
+
+Objects:
+ * sync_timeline
+ * sync_pt
+ * sync_fence
+
+sync_timeline:
+
+A sync_timeline is an abstract monotonically increasing counter. In general,
+each driver/hardware block context will have one of these. They can be backed
+by the appropriate hardware or rely on the generic sw_sync implementation.
+Timelines are only ever created through their specific implementations
+(i.e. sw_sync.)
+
+sync_pt:
+
+A sync_pt is an abstract value which marks a point on a sync_timeline. Sync_pts
+have a single timeline parent. They have 3 states: active, signaled, and error.
+They start in active state and transition, once, to either signaled (when the
+timeline counter advances beyond the sync_pt’s value) or error state.
+
+sync_fence:
+
+Sync_fences are the primary primitives used by drivers to coordinate
+synchronization of their buffers. They are a collection of sync_pts which may
+or may not have the same timeline parent. A sync_pt can only exist in one fence
+and the fence's list of sync_pts is immutable once created. Fences can be
+waited on synchronously or asynchronously. Two fences can also be merged to
+create a third fence containing a copy of the two fences’ sync_pts. Fences are
+backed by file descriptors to allow userspace to coordinate the display pipeline
+dependencies.
+
+Use:
+
+A driver implementing sync support should have a work submission function which:
+ * takes a fence argument specifying when to begin work
+ * asynchronously queues that work to kick off when the fence is signaled
+ * returns a fence to indicate when its work will be done.
+ * signals the returned fence once the work is completed.
+
+Consider an imaginary display driver that has the following API:
+/*
+ * assumes buf is ready to be displayed.
+ * blocks until the buffer is on screen.
+ */
+ void display_buffer(struct dma_buf *buf);
+
+The new API will become:
+/*
+ * will display buf when fence is signaled.
+ * returns immediately with a fence that will signal when buf
+ * is no longer displayed.
+ */
+struct sync_fence* display_buffer(struct dma_buf *buf,
+ struct sync_fence *fence);
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 8d90c42..1065dad 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -51,6 +51,7 @@
- panic_on_oops
- panic_on_unrecovered_nmi
- panic_on_stackoverflow
+- perf_event_paranoid
- pid_max
- powersave-nap [ PPC only ]
- printk
@@ -464,6 +465,19 @@
==============================================================
+perf_event_paranoid:
+
+Controls use of the performance events system by unprivileged
+users (without CAP_SYS_ADMIN). The default value is 3 if
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 1 otherwise.
+
+ -1: Allow use of (almost) all events by all users
+>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
+>=1: Disallow CPU event access by users without CAP_SYS_ADMIN
+>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+>=3: Disallow all event access by users without CAP_SYS_ADMIN
+
+==============================================================
pid_max:
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index dcc75a9..c7539ec 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -29,6 +29,7 @@
- dirty_writeback_centisecs
- drop_caches
- extfrag_threshold
+- extra_free_kbytes
- hugepages_treat_as_movable
- hugetlb_shm_group
- laptop_mode
@@ -41,6 +42,8 @@
- min_slab_ratio
- min_unmapped_ratio
- mmap_min_addr
+- mmap_rnd_bits
+- mmap_rnd_compat_bits
- nr_hugepages
- nr_overcommit_hugepages
- nr_trim_pages (only if CONFIG_MMU=n)
@@ -198,6 +201,21 @@
==============================================================
+extra_free_kbytes
+
+This parameter tells the VM to keep extra free memory between the threshold
+where background reclaim (kswapd) kicks in, and the threshold where direct
+reclaim (by allocating processes) kicks in.
+
+This is useful for workloads that require low latency memory allocations
+and have a bounded burstiness in memory allocations, for example a
+realtime application that receives and transmits network traffic
+(causing in-kernel memory allocations) with a maximum total message burst
+size of 200MB may need 200MB of extra free memory to avoid direct reclaim
+related latencies.
+
+==============================================================
+
hugepages_treat_as_movable
This parameter is only useful when kernelcore= is specified at boot time to
@@ -439,6 +457,33 @@
==============================================================
+mmap_rnd_bits:
+
+This value can be used to select the number of bits to use to
+determine the random offset to the base address of vma regions
+resulting from mmap allocations on architectures which support
+tuning address space randomization. This value will be bounded
+by the architecture's minimum and maximum supported values.
+
+This value can be changed after boot using the
+/proc/sys/vm/mmap_rnd_bits tunable
+
+==============================================================
+
+mmap_rnd_compat_bits:
+
+This value can be used to select the number of bits to use to
+determine the random offset to the base address of vma regions
+resulting from mmap allocations for applications run in
+compatibility mode on architectures which support tuning address
+space randomization. This value will be bounded by the
+architecture's minimum and maximum supported values.
+
+This value can be changed after boot using the
+/proc/sys/vm/mmap_rnd_compat_bits tunable
+
+==============================================================
+
nr_hugepages
Change the minimum size of the hugepage pool.
diff --git a/Documentation/trace/events-power.txt b/Documentation/trace/events-power.txt
index e1498ff..2050400 100644
--- a/Documentation/trace/events-power.txt
+++ b/Documentation/trace/events-power.txt
@@ -25,6 +25,7 @@
cpu_idle "state=%lu cpu_id=%lu"
cpu_frequency "state=%lu cpu_id=%lu"
+cpu_frequency_limits "min=%lu max=%lu cpu_id=%lu"
A suspend event is used to indicate the system going in and out of the
suspend mode:
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index bfe8c29..29064c3 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -2013,6 +2013,35 @@
1) 1.449 us | }
+You can disable the hierarchical function call formatting and instead print a
+flat list of function entry and return events. This uses the format described
+in the Output Formatting section and respects all the trace options that
+control that formatting. Hierarchical formatting is the default.
+
+ hierachical: echo nofuncgraph-flat > trace_options
+ flat: echo funcgraph-flat > trace_options
+
+ ie:
+
+ # tracer: function_graph
+ #
+ # entries-in-buffer/entries-written: 68355/68355 #P:2
+ #
+ # _-----=> irqs-off
+ # / _----=> need-resched
+ # | / _---=> hardirq/softirq
+ # || / _--=> preempt-depth
+ # ||| / delay
+ # TASK-PID CPU# |||| TIMESTAMP FUNCTION
+ # | | | |||| | |
+ sh-1806 [001] d... 198.843443: graph_ent: func=_raw_spin_lock
+ sh-1806 [001] d... 198.843445: graph_ent: func=__raw_spin_lock
+ sh-1806 [001] d..1 198.843447: graph_ret: func=__raw_spin_lock
+ sh-1806 [001] d..1 198.843449: graph_ret: func=_raw_spin_lock
+ sh-1806 [001] d..1 198.843451: graph_ent: func=_raw_spin_unlock_irqrestore
+ sh-1806 [001] d... 198.843453: graph_ret: func=_raw_spin_unlock_irqrestore
+
+
You might find other useful features for this tracer in the
following "dynamic ftrace" section such as tracing only specific
functions or tasks.
diff --git a/Documentation/vm/zsmalloc.txt b/Documentation/vm/zsmalloc.txt
new file mode 100644
index 0000000..64ed63c
--- /dev/null
+++ b/Documentation/vm/zsmalloc.txt
@@ -0,0 +1,70 @@
+zsmalloc
+--------
+
+This allocator is designed for use with zram. Thus, the allocator is
+supposed to work well under low memory conditions. In particular, it
+never attempts higher order page allocation which is very likely to
+fail under memory pressure. On the other hand, if we just use single
+(0-order) pages, it would suffer from very high fragmentation --
+any object of size PAGE_SIZE/2 or larger would occupy an entire page.
+This was one of the major issues with its predecessor (xvmalloc).
+
+To overcome these issues, zsmalloc allocates a bunch of 0-order pages
+and links them together using various 'struct page' fields. These linked
+pages act as a single higher-order page i.e. an object can span 0-order
+page boundaries. The code refers to these linked pages as a single entity
+called zspage.
+
+For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE
+since this satisfies the requirements of all its current users (in the
+worst case, page is incompressible and is thus stored "as-is" i.e. in
+uncompressed form). For allocation requests larger than this size, failure
+is returned (see zs_malloc).
+
+Additionally, zs_malloc() does not return a dereferenceable pointer.
+Instead, it returns an opaque handle (unsigned long) which encodes actual
+location of the allocated object. The reason for this indirection is that
+zsmalloc does not keep zspages permanently mapped since that would cause
+issues on 32-bit systems where the VA region for kernel space mappings
+is very small. So, before using the allocating memory, the object has to
+be mapped using zs_map_object() to get a usable pointer and subsequently
+unmapped using zs_unmap_object().
+
+stat
+----
+
+With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via
+/sys/kernel/debug/zsmalloc/<user name>. Here is a sample of stat output:
+
+# cat /sys/kernel/debug/zsmalloc/zram0/classes
+
+ class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage
+ ..
+ ..
+ 9 176 0 1 186 129 8 4
+ 10 192 1 0 2880 2872 135 3
+ 11 208 0 1 819 795 42 2
+ 12 224 0 1 219 159 12 4
+ ..
+ ..
+
+
+class: index
+size: object size zspage stores
+almost_empty: the number of ZS_ALMOST_EMPTY zspages(see below)
+almost_full: the number of ZS_ALMOST_FULL zspages(see below)
+obj_allocated: the number of objects allocated
+obj_used: the number of objects allocated to the user
+pages_used: the number of pages allocated for the class
+pages_per_zspage: the number of 0-order pages to make a zspage
+
+We assign a zspage to ZS_ALMOST_EMPTY fullness group when:
+ n <= N / f, where
+n = number of allocated objects
+N = total number of objects zspage can store
+f = fullness_threshold_frac(ie, 4 at the moment)
+
+Similarly, we assign zspage to:
+ ZS_ALMOST_FULL when n > N / f
+ ZS_EMPTY when n == 0
+ ZS_FULL when n == N
diff --git a/MAINTAINERS b/MAINTAINERS
index 29d7d74..ba4458b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9188,6 +9188,13 @@
F: drivers/net/hamradio/*scc.c
F: drivers/net/hamradio/z8530.h
+ZBUD COMPRESSED PAGE ALLOCATOR
+M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/zbud.c
+F: include/linux/zbud.h
+
ZD1211RW WIRELESS DRIVER
M: Daniel Drake <dsd@gentoo.org>
M: Ulrich Kunitz <kune@deine-taler.de>
@@ -9210,6 +9217,21 @@
S: Maintained
F: drivers/tty/serial/zs.*
+ZSMALLOC COMPRESSED SLAB MEMORY ALLOCATOR
+M: Minchan Kim <minchan@kernel.org>
+M: Nitin Gupta <ngupta@vflare.org>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/zsmalloc.c
+F: include/linux/zsmalloc.h
+F: Documentation/vm/zsmalloc.txt
+
+ZSWAP COMPRESSED SWAP CACHING
+M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/zswap.c
+
THE REST
M: Linus Torvalds <torvalds@linux-foundation.org>
L: linux-kernel@vger.kernel.org
diff --git a/android/configs/README b/android/configs/README
new file mode 100644
index 0000000..8798731
--- /dev/null
+++ b/android/configs/README
@@ -0,0 +1,15 @@
+The files in this directory are meant to be used as a base for an Android
+kernel config. All devices should have the options in android-base.cfg enabled.
+While not mandatory, the options in android-recommended.cfg enable advanced
+Android features.
+
+Assuming you already have a minimalist defconfig for your device, a possible
+way to enable these options would be:
+
+ ARCH=<arch> scripts/kconfig/merge_config.sh <path_to>/<device>_defconfig android/configs/android-base.cfg android/configs/android-recommended.cfg
+
+This will generate a .config that can then be used to save a new defconfig or
+compile a new kernel with Android features enabled.
+
+Because there is no tool to consistently generate these config fragments,
+lets keep them alphabetically sorted instead of random.
diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg
new file mode 100644
index 0000000..13b622a
--- /dev/null
+++ b/android/configs/android-base.cfg
@@ -0,0 +1,155 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_DEVKMEM is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_MODULES is not set
+# CONFIG_OABI_COMPAT is not set
+# CONFIG_SYSVIPC is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ARMV7_COMPAT=y
+CONFIG_ASHMEM=y
+CONFIG_AUDIT=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_VERITY=y
+CONFIG_EMBEDDED=y
+CONFIG_FB=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET=y
+CONFIG_INET_ESP=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_TARGET_REJECT_SKERR=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_REJECT_SKERR=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_KEY=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_NAT=y
+CONFIG_NO_HZ=y
+CONFIG_PACKET=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PPP=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PREEMPT=y
+CONFIG_QUOTA=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_STAGING=y
+CONFIG_SWITCH=y
+CONFIG_SYNC=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_G_ANDROID=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_XFRM_USER=y
diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg
new file mode 100644
index 0000000..3d2ee5a
--- /dev/null
+++ b/android/configs/android-recommended.cfg
@@ -0,0 +1,133 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_NF_CONNTRACK_SIP is not set
+# CONFIG_PM_WAKELOCKS_GC is not set
+# CONFIG_VT is not set
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ASYMMETRIC_KEY_TYPE=y
+CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_CC_STACKPROTECTOR_STRONG=y
+CONFIG_COMPACTION=y
+CONFIG_DM_ANDROID_VERITY=y
+CONFIG_DM_UEVENT=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FUSE_FS=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HIDRAW=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_GPIO=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_KEYCHORD=y
+CONFIG_INPUT_KEYRESET=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_ION=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KEYS=y
+CONFIG_KSM=y
+CONFIG_LOGIG940_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGITECH_FF=y
+CONFIG_MD=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MSDOS_FS=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_PANTHERLORD_FF=y
+CONFIG_PERF_EVENTS=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+CONFIG_POWER_SUPPLY=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_PUBLIC_KEY_ALGO_RSA=y
+CONFIG_SCHEDSTATS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_SYSTEM_TRUSTED_KEYRING=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_TABLET_USB_WACOM=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_TASK_XACCT=y
+CONFIG_TIMER_STATS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UHID=y
+CONFIG_UID_STAT=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_USBNET=y
+CONFIG_VFAT_FS=y
+CONFIG_X509_CERTIFICATE_PARSER=y
diff --git a/arch/Kconfig b/arch/Kconfig
index 00e3702..6dbcfc4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -331,6 +331,7 @@
- secure_computing is called from a ptrace_event()-safe context
- secure_computing return value is checked and a return value of -1
results in the system call being skipped immediately.
+ - seccomp syscall wired up
config SECCOMP_FILTER
def_bool y
@@ -390,6 +391,74 @@
Some architectures generate an _ in front of C symbols; things like
module loading and assembly files need to know about this.
+config HAVE_ARCH_MMAP_RND_BITS
+ bool
+ help
+ An arch should select this symbol if it supports setting a variable
+ number of bits for use in establishing the base address for mmap
+ allocations, has MMU enabled and provides values for both:
+ - ARCH_MMAP_RND_BITS_MIN
+ - ARCH_MMAP_RND_BITS_MAX
+
+config ARCH_MMAP_RND_BITS_MIN
+ int
+
+config ARCH_MMAP_RND_BITS_MAX
+ int
+
+config ARCH_MMAP_RND_BITS_DEFAULT
+ int
+
+config ARCH_MMAP_RND_BITS
+ int "Number of bits to use for ASLR of mmap base address" if EXPERT
+ range ARCH_MMAP_RND_BITS_MIN ARCH_MMAP_RND_BITS_MAX
+ default ARCH_MMAP_RND_BITS_DEFAULT if ARCH_MMAP_RND_BITS_DEFAULT
+ default ARCH_MMAP_RND_BITS_MIN
+ depends on HAVE_ARCH_MMAP_RND_BITS
+ help
+ This value can be used to select the number of bits to use to
+ determine the random offset to the base address of vma regions
+ resulting from mmap allocations. This value will be bounded
+ by the architecture's minimum and maximum supported values.
+
+ This value can be changed after boot using the
+ /proc/sys/vm/mmap_rnd_bits tunable
+
+config HAVE_ARCH_MMAP_RND_COMPAT_BITS
+ bool
+ help
+ An arch should select this symbol if it supports running applications
+ in compatibility mode, supports setting a variable number of bits for
+ use in establishing the base address for mmap allocations, has MMU
+ enabled and provides values for both:
+ - ARCH_MMAP_RND_COMPAT_BITS_MIN
+ - ARCH_MMAP_RND_COMPAT_BITS_MAX
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+ int
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+ int
+
+config ARCH_MMAP_RND_COMPAT_BITS_DEFAULT
+ int
+
+config ARCH_MMAP_RND_COMPAT_BITS
+ int "Number of bits to use for ASLR of mmap base address for compatible applications" if EXPERT
+ range ARCH_MMAP_RND_COMPAT_BITS_MIN ARCH_MMAP_RND_COMPAT_BITS_MAX
+ default ARCH_MMAP_RND_COMPAT_BITS_DEFAULT if ARCH_MMAP_RND_COMPAT_BITS_DEFAULT
+ default ARCH_MMAP_RND_COMPAT_BITS_MIN
+ depends on HAVE_ARCH_MMAP_RND_COMPAT_BITS
+ help
+ This value can be used to select the number of bits to use to
+ determine the random offset to the base address of vma regions
+ resulting from mmap allocations for compatible applications This
+ value will be bounded by the architecture's minimum and maximum
+ supported values.
+
+ This value can be changed after boot using the
+ /proc/sys/vm/mmap_rnd_compat_bits tunable
+
#
# ABI hall of shame
#
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index b9e37ad6..1402fcc 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -96,6 +96,7 @@
};
struct osf_dirent_callback {
+ struct dir_context ctx;
struct osf_dirent __user *dirent;
long __user *basep;
unsigned int count;
@@ -146,17 +147,17 @@
{
int error;
struct fd arg = fdget(fd);
- struct osf_dirent_callback buf;
+ struct osf_dirent_callback buf = {
+ .ctx.actor = osf_filldir,
+ .dirent = dirent,
+ .basep = basep,
+ .count = count
+ };
if (!arg.file)
return -EBADF;
- buf.dirent = dirent;
- buf.basep = basep;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(arg.file, osf_filldir, &buf);
+ error = iterate_dir(arg.file, &buf.ctx);
if (error >= 0)
error = buf.error;
if (count != buf.count)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d419512..fd46f71 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -22,6 +22,7 @@
select HARDIRQS_SW_RESEND
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
select HAVE_ARCH_KGDB
+ select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_BPF_JIT
@@ -279,6 +280,14 @@
Select if you want MMU-based virtualised addressing space
support by paged memory management. If unsure, say 'Y'.
+config ARCH_MMAP_RND_BITS_MIN
+ default 8
+
+config ARCH_MMAP_RND_BITS_MAX
+ default 14 if PAGE_OFFSET=0x40000000
+ default 15 if PAGE_OFFSET=0x80000000
+ default 16
+
#
# The "ARM system type" choice list is ordered alphabetically by option
# text. Please add new entries in the option alphabetic order.
@@ -1820,6 +1829,15 @@
help
Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
+config ARM_FLUSH_CONSOLE_ON_RESTART
+ bool "Force flush the console on restart"
+ help
+ If the console is locked while the system is rebooted, the messages
+ in the temporary logbuffer would not have propogated to all the
+ console drivers. This option forces the console lock to be
+ released if it failed to be acquired, which will cause all the
+ pending messages to be flushed.
+
endmenu
menu "Boot options"
@@ -1849,6 +1867,21 @@
This was deprecated in 2001 and announced to live on for 5 years.
Some old boot loaders still use this way.
+config BUILD_ARM_APPENDED_DTB_IMAGE
+ bool "Build a concatenated zImage/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated zImage and list of
+ DTBs to be built by default (instead of a standalone zImage.)
+ The image will built in arch/arm/boot/zImage-dtb
+
+config BUILD_ARM_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated zImage-dtb.
+
# Compressed boot loader in ROM. Yes, we really want to ask about
# TEXT and BSS so we preserve their values in the config files.
config ZBOOT_ROM_TEXT
@@ -2198,6 +2231,13 @@
Say Y to include support code for NEON, the ARMv7 Advanced SIMD
Extension.
+config KERNEL_MODE_NEON
+ bool "Support for NEON in kernel mode"
+ default n
+ depends on NEON
+ help
+ Say Y to include support for NEON in kernel mode.
+
endmenu
menu "Userspace binary formats"
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 1d41908..a640f09 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -63,6 +63,27 @@
8 - SIGSEGV faults
16 - SIGBUS faults
+config DEBUG_RODATA
+ bool "Write protect kernel text section"
+ default n
+ depends on DEBUG_KERNEL && MMU
+ ---help---
+ Mark the kernel text section as write-protected in the pagetables,
+ in order to catch accidental (and incorrect) writes to such const
+ data. This will cause the size of the kernel, plus up to 4MB, to
+ be mapped as pages instead of sections, which will increase TLB
+ pressure.
+ If in doubt, say "N".
+
+config DEBUG_RODATA_TEST
+ bool "Testcase for the DEBUG_RODATA feature"
+ depends on DEBUG_RODATA
+ default n
+ ---help---
+ This option enables a testcase for the DEBUG_RODATA
+ feature.
+ If in doubt, say "N"
+
# These options are only for real kernel hackers who want to get their hands dirty.
config DEBUG_LL
bool "Kernel low-level debugging functions (read help!)"
@@ -669,6 +690,14 @@
kernel low-level debugging functions. Add earlyprintk to your
kernel parameters to enable this console.
+config EARLY_PRINTK_DIRECT
+ bool "Early printk direct"
+ depends on DEBUG_LL
+ help
+ Say Y here if you want to have an early console using the
+ kernel low-level debugging functions and EARLY_PRINTK is
+ not early enough.
+
config OC_ETM
bool "On-chip ETM and ETB"
depends on ARM_AMBA
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 7d4ce43..1a71484 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -272,6 +272,8 @@
# Default target when executing plain make
ifeq ($(CONFIG_XIP_KERNEL),y)
KBUILD_IMAGE := xipImage
+else ifeq ($(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE := zImage-dtb
else
KBUILD_IMAGE := zImage
endif
@@ -303,6 +305,9 @@
dtbs: scripts
$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) dtbs
+zImage-dtb: vmlinux scripts dtbs
+ $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
+
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arm/boot/.gitignore b/arch/arm/boot/.gitignore
index 3c79f85..ad7a025 100644
--- a/arch/arm/boot/.gitignore
+++ b/arch/arm/boot/.gitignore
@@ -4,3 +4,4 @@
bootpImage
uImage
*.dtb
+zImage-dtb
\ No newline at end of file
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 84aa2ca..65285bb 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -14,6 +14,7 @@
ifneq ($(MACHINE),)
include $(srctree)/$(MACHINE)/Makefile.boot
endif
+include $(srctree)/arch/arm/boot/dts/Makefile
# Note: the following conditions must always be true:
# ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET)
@@ -27,6 +28,14 @@
targets := Image zImage xipImage bootpImage uImage
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+
ifeq ($(CONFIG_XIP_KERNEL),y)
$(obj)/xipImage: vmlinux FORCE
@@ -55,6 +64,10 @@
$(call if_changed,objcopy)
@$(kecho) ' Kernel: $@ is ready'
+$(obj)/zImage-dtb: $(obj)/zImage $(DTB_OBJS) FORCE
+ $(call if_changed,cat)
+ @echo ' Kernel: $@ is ready'
+
endif
ifneq ($(LOADADDR),)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 032a8d9..a7cd673 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -717,6 +717,8 @@
bic r6, r6, #1 << 31 @ 32-bit translation system
bic r6, r6, #3 << 0 @ use only ttbr0
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
+ mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
mcrne p15, 0, r6, c2, c0, 2 @ load ttb control
#endif
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index f0895c5..b83cc50 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -210,13 +210,20 @@
wm8850-w70v2.dtb
dtb-$(CONFIG_ARCH_ZYNQ) += zynq-zc702.dtb
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+
targets += dtbs
-targets += $(dtb-y)
+targets += $(DTB_LIST)
endif
# *.dtb used to be generated in the directory above. Clean out the
# old build results so people don't accidentally use them.
-dtbs: $(addprefix $(obj)/, $(dtb-y))
+dtbs: $(addprefix $(obj)/, $(DTB_LIST))
$(Q)rm -f $(obj)/../*.dtb
clean-files := *.dtb
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 9353184..ce01364 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -17,3 +17,7 @@
config SHARP_SCOOP
bool
+
+config FIQ_GLUE
+ bool
+ select FIQ
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 48434cb..0a0821f 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -4,6 +4,7 @@
obj-y += firmware.o
+obj-$(CONFIG_FIQ_GLUE) += fiq_glue.o fiq_glue_setup.o
obj-$(CONFIG_ICST) += icst.o
obj-$(CONFIG_SA1111) += sa1111.o
obj-$(CONFIG_PCI_HOST_VIA82C505) += via82c505.o
diff --git a/arch/arm/common/fiq_glue.S b/arch/arm/common/fiq_glue.S
new file mode 100644
index 0000000..24b42ce
--- /dev/null
+++ b/arch/arm/common/fiq_glue.S
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+
+ .global fiq_glue_end
+
+ /* fiq stack: r0-r15,cpsr,spsr of interrupted mode */
+
+ENTRY(fiq_glue)
+ /* store pc, cpsr from previous mode, reserve space for spsr */
+ mrs r12, spsr
+ sub lr, lr, #4
+ subs r10, #1
+ bne nested_fiq
+
+ str r12, [sp, #-8]!
+ str lr, [sp, #-4]!
+
+ /* store r8-r14 from previous mode */
+ sub sp, sp, #(7 * 4)
+ stmia sp, {r8-r14}^
+ nop
+
+ /* store r0-r7 from previous mode */
+ stmfd sp!, {r0-r7}
+
+ /* setup func(data,regs) arguments */
+ mov r0, r9
+ mov r1, sp
+ mov r3, r8
+
+ mov r7, sp
+
+ /* Get sp and lr from non-user modes */
+ and r4, r12, #MODE_MASK
+ cmp r4, #USR_MODE
+ beq fiq_from_usr_mode
+
+ mov r7, sp
+ orr r4, r4, #(PSR_I_BIT | PSR_F_BIT)
+ msr cpsr_c, r4
+ str sp, [r7, #(4 * 13)]
+ str lr, [r7, #(4 * 14)]
+ mrs r5, spsr
+ str r5, [r7, #(4 * 17)]
+
+ cmp r4, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+ /* use fiq stack if we reenter this mode */
+ subne sp, r7, #(4 * 3)
+
+fiq_from_usr_mode:
+ msr cpsr_c, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+ mov r2, sp
+ sub sp, r7, #12
+ stmfd sp!, {r2, ip, lr}
+ /* call func(data,regs) */
+ blx r3
+ ldmfd sp, {r2, ip, lr}
+ mov sp, r2
+
+ /* restore/discard saved state */
+ cmp r4, #USR_MODE
+ beq fiq_from_usr_mode_exit
+
+ msr cpsr_c, r4
+ ldr sp, [r7, #(4 * 13)]
+ ldr lr, [r7, #(4 * 14)]
+ msr spsr_cxsf, r5
+
+fiq_from_usr_mode_exit:
+ msr cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+
+ ldmfd sp!, {r0-r7}
+ ldr lr, [sp, #(4 * 7)]
+ ldr r12, [sp, #(4 * 8)]
+ add sp, sp, #(10 * 4)
+exit_fiq:
+ msr spsr_cxsf, r12
+ add r10, #1
+ cmp r11, #0
+ moveqs pc, lr
+ bx r11 /* jump to custom fiq return function */
+
+nested_fiq:
+ orr r12, r12, #(PSR_F_BIT)
+ b exit_fiq
+
+fiq_glue_end:
+
+ENTRY(fiq_glue_setup) /* func, data, sp, smc call number */
+ stmfd sp!, {r4}
+ mrs r4, cpsr
+ msr cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+ movs r8, r0
+ mov r9, r1
+ mov sp, r2
+ mov r11, r3
+ moveq r10, #0
+ movne r10, #1
+ msr cpsr_c, r4
+ ldmfd sp!, {r4}
+ bx lr
+
diff --git a/arch/arm/common/fiq_glue_setup.c b/arch/arm/common/fiq_glue_setup.c
new file mode 100644
index 0000000..8cb1b61
--- /dev/null
+++ b/arch/arm/common/fiq_glue_setup.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/fiq.h>
+#include <asm/fiq_glue.h>
+
+extern unsigned char fiq_glue, fiq_glue_end;
+extern void fiq_glue_setup(void *func, void *data, void *sp,
+ fiq_return_handler_t fiq_return_handler);
+
+static struct fiq_handler fiq_debbuger_fiq_handler = {
+ .name = "fiq_glue",
+};
+DEFINE_PER_CPU(void *, fiq_stack);
+static struct fiq_glue_handler *current_handler;
+static fiq_return_handler_t fiq_return_handler;
+static DEFINE_MUTEX(fiq_glue_lock);
+
+static void fiq_glue_setup_helper(void *info)
+{
+ struct fiq_glue_handler *handler = info;
+ fiq_glue_setup(handler->fiq, handler,
+ __get_cpu_var(fiq_stack) + THREAD_START_SP,
+ fiq_return_handler);
+}
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler)
+{
+ int ret;
+ int cpu;
+
+ if (!handler || !handler->fiq)
+ return -EINVAL;
+
+ mutex_lock(&fiq_glue_lock);
+ if (fiq_stack) {
+ ret = -EBUSY;
+ goto err_busy;
+ }
+
+ for_each_possible_cpu(cpu) {
+ void *stack;
+ stack = (void *)__get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+ if (WARN_ON(!stack)) {
+ ret = -ENOMEM;
+ goto err_alloc_fiq_stack;
+ }
+ per_cpu(fiq_stack, cpu) = stack;
+ }
+
+ ret = claim_fiq(&fiq_debbuger_fiq_handler);
+ if (WARN_ON(ret))
+ goto err_claim_fiq;
+
+ current_handler = handler;
+ on_each_cpu(fiq_glue_setup_helper, handler, true);
+ set_fiq_handler(&fiq_glue, &fiq_glue_end - &fiq_glue);
+
+ mutex_unlock(&fiq_glue_lock);
+ return 0;
+
+err_claim_fiq:
+err_alloc_fiq_stack:
+ for_each_possible_cpu(cpu) {
+ __free_pages(per_cpu(fiq_stack, cpu), THREAD_SIZE_ORDER);
+ per_cpu(fiq_stack, cpu) = NULL;
+ }
+err_busy:
+ mutex_unlock(&fiq_glue_lock);
+ return ret;
+}
+
+static void fiq_glue_update_return_handler(void (*fiq_return)(void))
+{
+ fiq_return_handler = fiq_return;
+ if (current_handler)
+ on_each_cpu(fiq_glue_setup_helper, current_handler, true);
+}
+
+int fiq_glue_set_return_handler(void (*fiq_return)(void))
+{
+ int ret;
+
+ mutex_lock(&fiq_glue_lock);
+ if (fiq_return_handler) {
+ ret = -EBUSY;
+ goto err_busy;
+ }
+ fiq_glue_update_return_handler(fiq_return);
+ ret = 0;
+err_busy:
+ mutex_unlock(&fiq_glue_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(fiq_glue_set_return_handler);
+
+int fiq_glue_clear_return_handler(void (*fiq_return)(void))
+{
+ int ret;
+
+ mutex_lock(&fiq_glue_lock);
+ if (WARN_ON(fiq_return_handler != fiq_return)) {
+ ret = -EINVAL;
+ goto err_inval;
+ }
+ fiq_glue_update_return_handler(NULL);
+ ret = 0;
+err_inval:
+ mutex_unlock(&fiq_glue_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(fiq_glue_clear_return_handler);
+
+/**
+ * fiq_glue_resume - Restore fiqs after suspend or low power idle states
+ *
+ * This must be called before calling local_fiq_enable after returning from a
+ * power state where the fiq mode registers were lost. If a driver provided
+ * a resume hook when it registered the handler it will be called.
+ */
+
+void fiq_glue_resume(void)
+{
+ if (!current_handler)
+ return;
+ fiq_glue_setup(current_handler->fiq, current_handler,
+ __get_cpu_var(fiq_stack) + THREAD_START_SP,
+ fiq_return_handler);
+ if (current_handler->resume)
+ current_handler->resume(current_handler);
+}
+
diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig
index 2ba9e63..0baa4ec 100644
--- a/arch/arm/configs/versatile_defconfig
+++ b/arch/arm/configs/versatile_defconfig
@@ -65,6 +65,9 @@
CONFIG_MMC=y
CONFIG_MMC_ARMMMCI=m
CONFIG_EXT2_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS_ENCRYPTION=y
CONFIG_VFAT_FS=m
CONFIG_JFFS2_FS=y
CONFIG_CRAMFS=y
diff --git a/arch/arm/crypto/.gitignore b/arch/arm/crypto/.gitignore
new file mode 100644
index 0000000..6231d36
--- /dev/null
+++ b/arch/arm/crypto/.gitignore
@@ -0,0 +1 @@
+aesbs-core.S
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index a2c8385..2cee53b 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -3,7 +3,27 @@
#
obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
+obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
-aes-arm-y := aes-armv4.o aes_glue.o
-sha1-arm-y := sha1-armv4-large.o sha1_glue.o
+aes-arm-y := aes-armv4.o aes_glue.o
+aes-arm-bs-y := aesbs-core.o aesbs-glue.o
+sha1-arm-y := sha1-armv4-large.o sha1_glue.o
+sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
+sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
+sha256-arm-y := sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
+sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
+
+quiet_cmd_perl = PERL $@
+ cmd_perl = $(PERL) $(<) > $(@)
+
+$(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
+ $(call cmd,perl)
+
+$(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
+ $(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
index e73ec2a..0409b8f 100644
--- a/arch/arm/crypto/aes_glue.c
+++ b/arch/arm/crypto/aes_glue.c
@@ -6,22 +6,12 @@
#include <linux/crypto.h>
#include <crypto/aes.h>
-#define AES_MAXNR 14
+#include "aes_glue.h"
-typedef struct {
- unsigned int rd_key[4 *(AES_MAXNR + 1)];
- int rounds;
-} AES_KEY;
-
-struct AES_CTX {
- AES_KEY enc_key;
- AES_KEY dec_key;
-};
-
-asmlinkage void AES_encrypt(const u8 *in, u8 *out, AES_KEY *ctx);
-asmlinkage void AES_decrypt(const u8 *in, u8 *out, AES_KEY *ctx);
-asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
-asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
+EXPORT_SYMBOL(AES_encrypt);
+EXPORT_SYMBOL(AES_decrypt);
+EXPORT_SYMBOL(private_AES_set_encrypt_key);
+EXPORT_SYMBOL(private_AES_set_decrypt_key);
static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
@@ -81,7 +71,7 @@
.cipher = {
.cia_min_keysize = AES_MIN_KEY_SIZE,
.cia_max_keysize = AES_MAX_KEY_SIZE,
- .cia_setkey = aes_set_key,
+ .cia_setkey = aes_set_key,
.cia_encrypt = aes_encrypt,
.cia_decrypt = aes_decrypt
}
diff --git a/arch/arm/crypto/aes_glue.h b/arch/arm/crypto/aes_glue.h
new file mode 100644
index 0000000..cca3e51
--- /dev/null
+++ b/arch/arm/crypto/aes_glue.h
@@ -0,0 +1,19 @@
+
+#define AES_MAXNR 14
+
+struct AES_KEY {
+ unsigned int rd_key[4 * (AES_MAXNR + 1)];
+ int rounds;
+};
+
+struct AES_CTX {
+ struct AES_KEY enc_key;
+ struct AES_KEY dec_key;
+};
+
+asmlinkage void AES_encrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
+asmlinkage void AES_decrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
+asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey,
+ const int bits, struct AES_KEY *key);
+asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey,
+ const int bits, struct AES_KEY *key);
diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
new file mode 100644
index 0000000..71e5fc7
--- /dev/null
+++ b/arch/arm/crypto/aesbs-core.S_shipped
@@ -0,0 +1,2544 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Specific modes and adaptation for Linux kernel by Ard Biesheuvel
+@ <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is
+@ granted.
+@ ====================================================================
+
+@ Bit-sliced AES for ARM NEON
+@
+@ February 2012.
+@
+@ This implementation is direct adaptation of bsaes-x86_64 module for
+@ ARM NEON. Except that this module is endian-neutral [in sense that
+@ it can be compiled for either endianness] by courtesy of vld1.8's
+@ neutrality. Initial version doesn't implement interface to OpenSSL,
+@ only low-level primitives and unsupported entry points, just enough
+@ to collect performance results, which for Cortex-A8 core are:
+@
+@ encrypt 19.5 cycles per byte processed with 128-bit key
+@ decrypt 22.1 cycles per byte processed with 128-bit key
+@ key conv. 440 cycles per 128-bit key/0.18 of 8x block
+@
+@ Snapdragon S4 encrypts byte in 17.6 cycles and decrypts in 19.7,
+@ which is [much] worse than anticipated (for further details see
+@ http://www.openssl.org/~appro/Snapdragon-S4.html).
+@
+@ Cortex-A15 manages in 14.2/16.1 cycles [when integer-only code
+@ manages in 20.0 cycles].
+@
+@ When comparing to x86_64 results keep in mind that NEON unit is
+@ [mostly] single-issue and thus can't [fully] benefit from
+@ instruction-level parallelism. And when comparing to aes-armv4
+@ results keep in mind key schedule conversion overhead (see
+@ bsaes-x86_64.pl for further details)...
+@
+@ <appro@openssl.org>
+
+@ April-August 2013
+@
+@ Add CBC, CTR and XTS subroutines, adapt for kernel use.
+@
+@ <ard.biesheuvel@linaro.org>
+
+#ifndef __KERNEL__
+# include "arm_arch.h"
+
+# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
+# define VFP_ABI_POP vldmia sp!,{d8-d15}
+# define VFP_ABI_FRAME 0x40
+#else
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+# define VFP_ABI_FRAME 0
+# define BSAES_ASM_EXTENDED_KEY
+# define XTS_CHAIN_TWEAK
+# define __ARM_ARCH__ 7
+#endif
+
+#ifdef __thumb__
+# define adrl adr
+#endif
+
+#if __ARM_ARCH__>=7
+.text
+.syntax unified @ ARMv7-capable assembler is expected to handle this
+#ifdef __thumb2__
+.thumb
+#else
+.code 32
+#endif
+
+.fpu neon
+
+.type _bsaes_decrypt8,%function
+.align 4
+_bsaes_decrypt8:
+ adr r6,_bsaes_decrypt8
+ vldmia r4!, {q9} @ round 0 key
+ add r6,r6,#.LM0ISR-_bsaes_decrypt8
+
+ vldmia r6!, {q8} @ .LM0ISR
+ veor q10, q0, q9 @ xor with round0 key
+ veor q11, q1, q9
+ vtbl.8 d0, {q10}, d16
+ vtbl.8 d1, {q10}, d17
+ veor q12, q2, q9
+ vtbl.8 d2, {q11}, d16
+ vtbl.8 d3, {q11}, d17
+ veor q13, q3, q9
+ vtbl.8 d4, {q12}, d16
+ vtbl.8 d5, {q12}, d17
+ veor q14, q4, q9
+ vtbl.8 d6, {q13}, d16
+ vtbl.8 d7, {q13}, d17
+ veor q15, q5, q9
+ vtbl.8 d8, {q14}, d16
+ vtbl.8 d9, {q14}, d17
+ veor q10, q6, q9
+ vtbl.8 d10, {q15}, d16
+ vtbl.8 d11, {q15}, d17
+ veor q11, q7, q9
+ vtbl.8 d12, {q10}, d16
+ vtbl.8 d13, {q10}, d17
+ vtbl.8 d14, {q11}, d16
+ vtbl.8 d15, {q11}, d17
+ vmov.i8 q8,#0x55 @ compose .LBS0
+ vmov.i8 q9,#0x33 @ compose .LBS1
+ vshr.u64 q10, q6, #1
+ vshr.u64 q11, q4, #1
+ veor q10, q10, q7
+ veor q11, q11, q5
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #1
+ veor q5, q5, q11
+ vshl.u64 q11, q11, #1
+ veor q6, q6, q10
+ veor q4, q4, q11
+ vshr.u64 q10, q2, #1
+ vshr.u64 q11, q0, #1
+ veor q10, q10, q3
+ veor q11, q11, q1
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q3, q3, q10
+ vshl.u64 q10, q10, #1
+ veor q1, q1, q11
+ vshl.u64 q11, q11, #1
+ veor q2, q2, q10
+ veor q0, q0, q11
+ vmov.i8 q8,#0x0f @ compose .LBS2
+ vshr.u64 q10, q5, #2
+ vshr.u64 q11, q4, #2
+ veor q10, q10, q7
+ veor q11, q11, q6
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #2
+ veor q6, q6, q11
+ vshl.u64 q11, q11, #2
+ veor q5, q5, q10
+ veor q4, q4, q11
+ vshr.u64 q10, q1, #2
+ vshr.u64 q11, q0, #2
+ veor q10, q10, q3
+ veor q11, q11, q2
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q3, q3, q10
+ vshl.u64 q10, q10, #2
+ veor q2, q2, q11
+ vshl.u64 q11, q11, #2
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vshr.u64 q10, q3, #4
+ vshr.u64 q11, q2, #4
+ veor q10, q10, q7
+ veor q11, q11, q6
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #4
+ veor q6, q6, q11
+ vshl.u64 q11, q11, #4
+ veor q3, q3, q10
+ veor q2, q2, q11
+ vshr.u64 q10, q1, #4
+ vshr.u64 q11, q0, #4
+ veor q10, q10, q5
+ veor q11, q11, q4
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #4
+ veor q4, q4, q11
+ vshl.u64 q11, q11, #4
+ veor q1, q1, q10
+ veor q0, q0, q11
+ sub r5,r5,#1
+ b .Ldec_sbox
+.align 4
+.Ldec_loop:
+ vldmia r4!, {q8-q11}
+ veor q8, q8, q0
+ veor q9, q9, q1
+ vtbl.8 d0, {q8}, d24
+ vtbl.8 d1, {q8}, d25
+ vldmia r4!, {q8}
+ veor q10, q10, q2
+ vtbl.8 d2, {q9}, d24
+ vtbl.8 d3, {q9}, d25
+ vldmia r4!, {q9}
+ veor q11, q11, q3
+ vtbl.8 d4, {q10}, d24
+ vtbl.8 d5, {q10}, d25
+ vldmia r4!, {q10}
+ vtbl.8 d6, {q11}, d24
+ vtbl.8 d7, {q11}, d25
+ vldmia r4!, {q11}
+ veor q8, q8, q4
+ veor q9, q9, q5
+ vtbl.8 d8, {q8}, d24
+ vtbl.8 d9, {q8}, d25
+ veor q10, q10, q6
+ vtbl.8 d10, {q9}, d24
+ vtbl.8 d11, {q9}, d25
+ veor q11, q11, q7
+ vtbl.8 d12, {q10}, d24
+ vtbl.8 d13, {q10}, d25
+ vtbl.8 d14, {q11}, d24
+ vtbl.8 d15, {q11}, d25
+.Ldec_sbox:
+ veor q1, q1, q4
+ veor q3, q3, q4
+
+ veor q4, q4, q7
+ veor q1, q1, q6
+ veor q2, q2, q7
+ veor q6, q6, q4
+
+ veor q0, q0, q1
+ veor q2, q2, q5
+ veor q7, q7, q6
+ veor q3, q3, q0
+ veor q5, q5, q0
+ veor q1, q1, q3
+ veor q11, q3, q0
+ veor q10, q7, q4
+ veor q9, q1, q6
+ veor q13, q4, q0
+ vmov q8, q10
+ veor q12, q5, q2
+
+ vorr q10, q10, q9
+ veor q15, q11, q8
+ vand q14, q11, q12
+ vorr q11, q11, q12
+ veor q12, q12, q9
+ vand q8, q8, q9
+ veor q9, q6, q2
+ vand q15, q15, q12
+ vand q13, q13, q9
+ veor q9, q3, q7
+ veor q12, q1, q5
+ veor q11, q11, q13
+ veor q10, q10, q13
+ vand q13, q9, q12
+ vorr q9, q9, q12
+ veor q11, q11, q15
+ veor q8, q8, q13
+ veor q10, q10, q14
+ veor q9, q9, q15
+ veor q8, q8, q14
+ vand q12, q4, q6
+ veor q9, q9, q14
+ vand q13, q0, q2
+ vand q14, q7, q1
+ vorr q15, q3, q5
+ veor q11, q11, q12
+ veor q9, q9, q14
+ veor q8, q8, q15
+ veor q10, q10, q13
+
+ @ Inv_GF16 0, 1, 2, 3, s0, s1, s2, s3
+
+ @ new smaller inversion
+
+ vand q14, q11, q9
+ vmov q12, q8
+
+ veor q13, q10, q14
+ veor q15, q8, q14
+ veor q14, q8, q14 @ q14=q15
+
+ vbsl q13, q9, q8
+ vbsl q15, q11, q10
+ veor q11, q11, q10
+
+ vbsl q12, q13, q14
+ vbsl q8, q14, q13
+
+ vand q14, q12, q15
+ veor q9, q9, q8
+
+ veor q14, q14, q11
+ veor q12, q5, q2
+ veor q8, q1, q6
+ veor q10, q15, q14
+ vand q10, q10, q5
+ veor q5, q5, q1
+ vand q11, q1, q15
+ vand q5, q5, q14
+ veor q1, q11, q10
+ veor q5, q5, q11
+ veor q15, q15, q13
+ veor q14, q14, q9
+ veor q11, q15, q14
+ veor q10, q13, q9
+ vand q11, q11, q12
+ vand q10, q10, q2
+ veor q12, q12, q8
+ veor q2, q2, q6
+ vand q8, q8, q15
+ vand q6, q6, q13
+ vand q12, q12, q14
+ vand q2, q2, q9
+ veor q8, q8, q12
+ veor q2, q2, q6
+ veor q12, q12, q11
+ veor q6, q6, q10
+ veor q5, q5, q12
+ veor q2, q2, q12
+ veor q1, q1, q8
+ veor q6, q6, q8
+
+ veor q12, q3, q0
+ veor q8, q7, q4
+ veor q11, q15, q14
+ veor q10, q13, q9
+ vand q11, q11, q12
+ vand q10, q10, q0
+ veor q12, q12, q8
+ veor q0, q0, q4
+ vand q8, q8, q15
+ vand q4, q4, q13
+ vand q12, q12, q14
+ vand q0, q0, q9
+ veor q8, q8, q12
+ veor q0, q0, q4
+ veor q12, q12, q11
+ veor q4, q4, q10
+ veor q15, q15, q13
+ veor q14, q14, q9
+ veor q10, q15, q14
+ vand q10, q10, q3
+ veor q3, q3, q7
+ vand q11, q7, q15
+ vand q3, q3, q14
+ veor q7, q11, q10
+ veor q3, q3, q11
+ veor q3, q3, q12
+ veor q0, q0, q12
+ veor q7, q7, q8
+ veor q4, q4, q8
+ veor q1, q1, q7
+ veor q6, q6, q5
+
+ veor q4, q4, q1
+ veor q2, q2, q7
+ veor q5, q5, q7
+ veor q4, q4, q2
+ veor q7, q7, q0
+ veor q4, q4, q5
+ veor q3, q3, q6
+ veor q6, q6, q1
+ veor q3, q3, q4
+
+ veor q4, q4, q0
+ veor q7, q7, q3
+ subs r5,r5,#1
+ bcc .Ldec_done
+ @ multiplication by 0x05-0x00-0x04-0x00
+ vext.8 q8, q0, q0, #8
+ vext.8 q14, q3, q3, #8
+ vext.8 q15, q5, q5, #8
+ veor q8, q8, q0
+ vext.8 q9, q1, q1, #8
+ veor q14, q14, q3
+ vext.8 q10, q6, q6, #8
+ veor q15, q15, q5
+ vext.8 q11, q4, q4, #8
+ veor q9, q9, q1
+ vext.8 q12, q2, q2, #8
+ veor q10, q10, q6
+ vext.8 q13, q7, q7, #8
+ veor q11, q11, q4
+ veor q12, q12, q2
+ veor q13, q13, q7
+
+ veor q0, q0, q14
+ veor q1, q1, q14
+ veor q6, q6, q8
+ veor q2, q2, q10
+ veor q4, q4, q9
+ veor q1, q1, q15
+ veor q6, q6, q15
+ veor q2, q2, q14
+ veor q7, q7, q11
+ veor q4, q4, q14
+ veor q3, q3, q12
+ veor q2, q2, q15
+ veor q7, q7, q15
+ veor q5, q5, q13
+ vext.8 q8, q0, q0, #12 @ x0 <<< 32
+ vext.8 q9, q1, q1, #12
+ veor q0, q0, q8 @ x0 ^ (x0 <<< 32)
+ vext.8 q10, q6, q6, #12
+ veor q1, q1, q9
+ vext.8 q11, q4, q4, #12
+ veor q6, q6, q10
+ vext.8 q12, q2, q2, #12
+ veor q4, q4, q11
+ vext.8 q13, q7, q7, #12
+ veor q2, q2, q12
+ vext.8 q14, q3, q3, #12
+ veor q7, q7, q13
+ vext.8 q15, q5, q5, #12
+ veor q3, q3, q14
+
+ veor q9, q9, q0
+ veor q5, q5, q15
+ vext.8 q0, q0, q0, #8 @ (x0 ^ (x0 <<< 32)) <<< 64)
+ veor q10, q10, q1
+ veor q8, q8, q5
+ veor q9, q9, q5
+ vext.8 q1, q1, q1, #8
+ veor q13, q13, q2
+ veor q0, q0, q8
+ veor q14, q14, q7
+ veor q1, q1, q9
+ vext.8 q8, q2, q2, #8
+ veor q12, q12, q4
+ vext.8 q9, q7, q7, #8
+ veor q15, q15, q3
+ vext.8 q2, q4, q4, #8
+ veor q11, q11, q6
+ vext.8 q7, q5, q5, #8
+ veor q12, q12, q5
+ vext.8 q4, q3, q3, #8
+ veor q11, q11, q5
+ vext.8 q3, q6, q6, #8
+ veor q5, q9, q13
+ veor q11, q11, q2
+ veor q7, q7, q15
+ veor q6, q4, q14
+ veor q4, q8, q12
+ veor q2, q3, q10
+ vmov q3, q11
+ @ vmov q5, q9
+ vldmia r6, {q12} @ .LISR
+ ite eq @ Thumb2 thing, sanity check in ARM
+ addeq r6,r6,#0x10
+ bne .Ldec_loop
+ vldmia r6, {q12} @ .LISRM0
+ b .Ldec_loop
+.align 4
+.Ldec_done:
+ vmov.i8 q8,#0x55 @ compose .LBS0
+ vmov.i8 q9,#0x33 @ compose .LBS1
+ vshr.u64 q10, q3, #1
+ vshr.u64 q11, q2, #1
+ veor q10, q10, q5
+ veor q11, q11, q7
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #1
+ veor q7, q7, q11
+ vshl.u64 q11, q11, #1
+ veor q3, q3, q10
+ veor q2, q2, q11
+ vshr.u64 q10, q6, #1
+ vshr.u64 q11, q0, #1
+ veor q10, q10, q4
+ veor q11, q11, q1
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q4, q4, q10
+ vshl.u64 q10, q10, #1
+ veor q1, q1, q11
+ vshl.u64 q11, q11, #1
+ veor q6, q6, q10
+ veor q0, q0, q11
+ vmov.i8 q8,#0x0f @ compose .LBS2
+ vshr.u64 q10, q7, #2
+ vshr.u64 q11, q2, #2
+ veor q10, q10, q5
+ veor q11, q11, q3
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #2
+ veor q3, q3, q11
+ vshl.u64 q11, q11, #2
+ veor q7, q7, q10
+ veor q2, q2, q11
+ vshr.u64 q10, q1, #2
+ vshr.u64 q11, q0, #2
+ veor q10, q10, q4
+ veor q11, q11, q6
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q4, q4, q10
+ vshl.u64 q10, q10, #2
+ veor q6, q6, q11
+ vshl.u64 q11, q11, #2
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vshr.u64 q10, q4, #4
+ vshr.u64 q11, q6, #4
+ veor q10, q10, q5
+ veor q11, q11, q3
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #4
+ veor q3, q3, q11
+ vshl.u64 q11, q11, #4
+ veor q4, q4, q10
+ veor q6, q6, q11
+ vshr.u64 q10, q1, #4
+ vshr.u64 q11, q0, #4
+ veor q10, q10, q7
+ veor q11, q11, q2
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #4
+ veor q2, q2, q11
+ vshl.u64 q11, q11, #4
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vldmia r4, {q8} @ last round key
+ veor q6, q6, q8
+ veor q4, q4, q8
+ veor q2, q2, q8
+ veor q7, q7, q8
+ veor q3, q3, q8
+ veor q5, q5, q8
+ veor q0, q0, q8
+ veor q1, q1, q8
+ bx lr
+.size _bsaes_decrypt8,.-_bsaes_decrypt8
+
+.type _bsaes_const,%object
+.align 6
+_bsaes_const:
+.LM0ISR: @ InvShiftRows constants
+ .quad 0x0a0e0206070b0f03, 0x0004080c0d010509
+.LISR:
+ .quad 0x0504070602010003, 0x0f0e0d0c080b0a09
+.LISRM0:
+ .quad 0x01040b0e0205080f, 0x0306090c00070a0d
+.LM0SR: @ ShiftRows constants
+ .quad 0x0a0e02060f03070b, 0x0004080c05090d01
+.LSR:
+ .quad 0x0504070600030201, 0x0f0e0d0c0a09080b
+.LSRM0:
+ .quad 0x0304090e00050a0f, 0x01060b0c0207080d
+.LM0:
+ .quad 0x02060a0e03070b0f, 0x0004080c0105090d
+.LREVM0SR:
+ .quad 0x090d01050c000408, 0x03070b0f060a0e02
+.asciz "Bit-sliced AES for NEON, CRYPTOGAMS by <appro@openssl.org>"
+.align 6
+.size _bsaes_const,.-_bsaes_const
+
+.type _bsaes_encrypt8,%function
+.align 4
+_bsaes_encrypt8:
+ adr r6,_bsaes_encrypt8
+ vldmia r4!, {q9} @ round 0 key
+ sub r6,r6,#_bsaes_encrypt8-.LM0SR
+
+ vldmia r6!, {q8} @ .LM0SR
+_bsaes_encrypt8_alt:
+ veor q10, q0, q9 @ xor with round0 key
+ veor q11, q1, q9
+ vtbl.8 d0, {q10}, d16
+ vtbl.8 d1, {q10}, d17
+ veor q12, q2, q9
+ vtbl.8 d2, {q11}, d16
+ vtbl.8 d3, {q11}, d17
+ veor q13, q3, q9
+ vtbl.8 d4, {q12}, d16
+ vtbl.8 d5, {q12}, d17
+ veor q14, q4, q9
+ vtbl.8 d6, {q13}, d16
+ vtbl.8 d7, {q13}, d17
+ veor q15, q5, q9
+ vtbl.8 d8, {q14}, d16
+ vtbl.8 d9, {q14}, d17
+ veor q10, q6, q9
+ vtbl.8 d10, {q15}, d16
+ vtbl.8 d11, {q15}, d17
+ veor q11, q7, q9
+ vtbl.8 d12, {q10}, d16
+ vtbl.8 d13, {q10}, d17
+ vtbl.8 d14, {q11}, d16
+ vtbl.8 d15, {q11}, d17
+_bsaes_encrypt8_bitslice:
+ vmov.i8 q8,#0x55 @ compose .LBS0
+ vmov.i8 q9,#0x33 @ compose .LBS1
+ vshr.u64 q10, q6, #1
+ vshr.u64 q11, q4, #1
+ veor q10, q10, q7
+ veor q11, q11, q5
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #1
+ veor q5, q5, q11
+ vshl.u64 q11, q11, #1
+ veor q6, q6, q10
+ veor q4, q4, q11
+ vshr.u64 q10, q2, #1
+ vshr.u64 q11, q0, #1
+ veor q10, q10, q3
+ veor q11, q11, q1
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q3, q3, q10
+ vshl.u64 q10, q10, #1
+ veor q1, q1, q11
+ vshl.u64 q11, q11, #1
+ veor q2, q2, q10
+ veor q0, q0, q11
+ vmov.i8 q8,#0x0f @ compose .LBS2
+ vshr.u64 q10, q5, #2
+ vshr.u64 q11, q4, #2
+ veor q10, q10, q7
+ veor q11, q11, q6
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #2
+ veor q6, q6, q11
+ vshl.u64 q11, q11, #2
+ veor q5, q5, q10
+ veor q4, q4, q11
+ vshr.u64 q10, q1, #2
+ vshr.u64 q11, q0, #2
+ veor q10, q10, q3
+ veor q11, q11, q2
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q3, q3, q10
+ vshl.u64 q10, q10, #2
+ veor q2, q2, q11
+ vshl.u64 q11, q11, #2
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vshr.u64 q10, q3, #4
+ vshr.u64 q11, q2, #4
+ veor q10, q10, q7
+ veor q11, q11, q6
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #4
+ veor q6, q6, q11
+ vshl.u64 q11, q11, #4
+ veor q3, q3, q10
+ veor q2, q2, q11
+ vshr.u64 q10, q1, #4
+ vshr.u64 q11, q0, #4
+ veor q10, q10, q5
+ veor q11, q11, q4
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #4
+ veor q4, q4, q11
+ vshl.u64 q11, q11, #4
+ veor q1, q1, q10
+ veor q0, q0, q11
+ sub r5,r5,#1
+ b .Lenc_sbox
+.align 4
+.Lenc_loop:
+ vldmia r4!, {q8-q11}
+ veor q8, q8, q0
+ veor q9, q9, q1
+ vtbl.8 d0, {q8}, d24
+ vtbl.8 d1, {q8}, d25
+ vldmia r4!, {q8}
+ veor q10, q10, q2
+ vtbl.8 d2, {q9}, d24
+ vtbl.8 d3, {q9}, d25
+ vldmia r4!, {q9}
+ veor q11, q11, q3
+ vtbl.8 d4, {q10}, d24
+ vtbl.8 d5, {q10}, d25
+ vldmia r4!, {q10}
+ vtbl.8 d6, {q11}, d24
+ vtbl.8 d7, {q11}, d25
+ vldmia r4!, {q11}
+ veor q8, q8, q4
+ veor q9, q9, q5
+ vtbl.8 d8, {q8}, d24
+ vtbl.8 d9, {q8}, d25
+ veor q10, q10, q6
+ vtbl.8 d10, {q9}, d24
+ vtbl.8 d11, {q9}, d25
+ veor q11, q11, q7
+ vtbl.8 d12, {q10}, d24
+ vtbl.8 d13, {q10}, d25
+ vtbl.8 d14, {q11}, d24
+ vtbl.8 d15, {q11}, d25
+.Lenc_sbox:
+ veor q2, q2, q1
+ veor q5, q5, q6
+ veor q3, q3, q0
+ veor q6, q6, q2
+ veor q5, q5, q0
+
+ veor q6, q6, q3
+ veor q3, q3, q7
+ veor q7, q7, q5
+ veor q3, q3, q4
+ veor q4, q4, q5
+
+ veor q2, q2, q7
+ veor q3, q3, q1
+ veor q1, q1, q5
+ veor q11, q7, q4
+ veor q10, q1, q2
+ veor q9, q5, q3
+ veor q13, q2, q4
+ vmov q8, q10
+ veor q12, q6, q0
+
+ vorr q10, q10, q9
+ veor q15, q11, q8
+ vand q14, q11, q12
+ vorr q11, q11, q12
+ veor q12, q12, q9
+ vand q8, q8, q9
+ veor q9, q3, q0
+ vand q15, q15, q12
+ vand q13, q13, q9
+ veor q9, q7, q1
+ veor q12, q5, q6
+ veor q11, q11, q13
+ veor q10, q10, q13
+ vand q13, q9, q12
+ vorr q9, q9, q12
+ veor q11, q11, q15
+ veor q8, q8, q13
+ veor q10, q10, q14
+ veor q9, q9, q15
+ veor q8, q8, q14
+ vand q12, q2, q3
+ veor q9, q9, q14
+ vand q13, q4, q0
+ vand q14, q1, q5
+ vorr q15, q7, q6
+ veor q11, q11, q12
+ veor q9, q9, q14
+ veor q8, q8, q15
+ veor q10, q10, q13
+
+ @ Inv_GF16 0, 1, 2, 3, s0, s1, s2, s3
+
+ @ new smaller inversion
+
+ vand q14, q11, q9
+ vmov q12, q8
+
+ veor q13, q10, q14
+ veor q15, q8, q14
+ veor q14, q8, q14 @ q14=q15
+
+ vbsl q13, q9, q8
+ vbsl q15, q11, q10
+ veor q11, q11, q10
+
+ vbsl q12, q13, q14
+ vbsl q8, q14, q13
+
+ vand q14, q12, q15
+ veor q9, q9, q8
+
+ veor q14, q14, q11
+ veor q12, q6, q0
+ veor q8, q5, q3
+ veor q10, q15, q14
+ vand q10, q10, q6
+ veor q6, q6, q5
+ vand q11, q5, q15
+ vand q6, q6, q14
+ veor q5, q11, q10
+ veor q6, q6, q11
+ veor q15, q15, q13
+ veor q14, q14, q9
+ veor q11, q15, q14
+ veor q10, q13, q9
+ vand q11, q11, q12
+ vand q10, q10, q0
+ veor q12, q12, q8
+ veor q0, q0, q3
+ vand q8, q8, q15
+ vand q3, q3, q13
+ vand q12, q12, q14
+ vand q0, q0, q9
+ veor q8, q8, q12
+ veor q0, q0, q3
+ veor q12, q12, q11
+ veor q3, q3, q10
+ veor q6, q6, q12
+ veor q0, q0, q12
+ veor q5, q5, q8
+ veor q3, q3, q8
+
+ veor q12, q7, q4
+ veor q8, q1, q2
+ veor q11, q15, q14
+ veor q10, q13, q9
+ vand q11, q11, q12
+ vand q10, q10, q4
+ veor q12, q12, q8
+ veor q4, q4, q2
+ vand q8, q8, q15
+ vand q2, q2, q13
+ vand q12, q12, q14
+ vand q4, q4, q9
+ veor q8, q8, q12
+ veor q4, q4, q2
+ veor q12, q12, q11
+ veor q2, q2, q10
+ veor q15, q15, q13
+ veor q14, q14, q9
+ veor q10, q15, q14
+ vand q10, q10, q7
+ veor q7, q7, q1
+ vand q11, q1, q15
+ vand q7, q7, q14
+ veor q1, q11, q10
+ veor q7, q7, q11
+ veor q7, q7, q12
+ veor q4, q4, q12
+ veor q1, q1, q8
+ veor q2, q2, q8
+ veor q7, q7, q0
+ veor q1, q1, q6
+ veor q6, q6, q0
+ veor q4, q4, q7
+ veor q0, q0, q1
+
+ veor q1, q1, q5
+ veor q5, q5, q2
+ veor q2, q2, q3
+ veor q3, q3, q5
+ veor q4, q4, q5
+
+ veor q6, q6, q3
+ subs r5,r5,#1
+ bcc .Lenc_done
+ vext.8 q8, q0, q0, #12 @ x0 <<< 32
+ vext.8 q9, q1, q1, #12
+ veor q0, q0, q8 @ x0 ^ (x0 <<< 32)
+ vext.8 q10, q4, q4, #12
+ veor q1, q1, q9
+ vext.8 q11, q6, q6, #12
+ veor q4, q4, q10
+ vext.8 q12, q3, q3, #12
+ veor q6, q6, q11
+ vext.8 q13, q7, q7, #12
+ veor q3, q3, q12
+ vext.8 q14, q2, q2, #12
+ veor q7, q7, q13
+ vext.8 q15, q5, q5, #12
+ veor q2, q2, q14
+
+ veor q9, q9, q0
+ veor q5, q5, q15
+ vext.8 q0, q0, q0, #8 @ (x0 ^ (x0 <<< 32)) <<< 64)
+ veor q10, q10, q1
+ veor q8, q8, q5
+ veor q9, q9, q5
+ vext.8 q1, q1, q1, #8
+ veor q13, q13, q3
+ veor q0, q0, q8
+ veor q14, q14, q7
+ veor q1, q1, q9
+ vext.8 q8, q3, q3, #8
+ veor q12, q12, q6
+ vext.8 q9, q7, q7, #8
+ veor q15, q15, q2
+ vext.8 q3, q6, q6, #8
+ veor q11, q11, q4
+ vext.8 q7, q5, q5, #8
+ veor q12, q12, q5
+ vext.8 q6, q2, q2, #8
+ veor q11, q11, q5
+ vext.8 q2, q4, q4, #8
+ veor q5, q9, q13
+ veor q4, q8, q12
+ veor q3, q3, q11
+ veor q7, q7, q15
+ veor q6, q6, q14
+ @ vmov q4, q8
+ veor q2, q2, q10
+ @ vmov q5, q9
+ vldmia r6, {q12} @ .LSR
+ ite eq @ Thumb2 thing, samity check in ARM
+ addeq r6,r6,#0x10
+ bne .Lenc_loop
+ vldmia r6, {q12} @ .LSRM0
+ b .Lenc_loop
+.align 4
+.Lenc_done:
+ vmov.i8 q8,#0x55 @ compose .LBS0
+ vmov.i8 q9,#0x33 @ compose .LBS1
+ vshr.u64 q10, q2, #1
+ vshr.u64 q11, q3, #1
+ veor q10, q10, q5
+ veor q11, q11, q7
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #1
+ veor q7, q7, q11
+ vshl.u64 q11, q11, #1
+ veor q2, q2, q10
+ veor q3, q3, q11
+ vshr.u64 q10, q4, #1
+ vshr.u64 q11, q0, #1
+ veor q10, q10, q6
+ veor q11, q11, q1
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q6, q6, q10
+ vshl.u64 q10, q10, #1
+ veor q1, q1, q11
+ vshl.u64 q11, q11, #1
+ veor q4, q4, q10
+ veor q0, q0, q11
+ vmov.i8 q8,#0x0f @ compose .LBS2
+ vshr.u64 q10, q7, #2
+ vshr.u64 q11, q3, #2
+ veor q10, q10, q5
+ veor q11, q11, q2
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #2
+ veor q2, q2, q11
+ vshl.u64 q11, q11, #2
+ veor q7, q7, q10
+ veor q3, q3, q11
+ vshr.u64 q10, q1, #2
+ vshr.u64 q11, q0, #2
+ veor q10, q10, q6
+ veor q11, q11, q4
+ vand q10, q10, q9
+ vand q11, q11, q9
+ veor q6, q6, q10
+ vshl.u64 q10, q10, #2
+ veor q4, q4, q11
+ vshl.u64 q11, q11, #2
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vshr.u64 q10, q6, #4
+ vshr.u64 q11, q4, #4
+ veor q10, q10, q5
+ veor q11, q11, q2
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q5, q5, q10
+ vshl.u64 q10, q10, #4
+ veor q2, q2, q11
+ vshl.u64 q11, q11, #4
+ veor q6, q6, q10
+ veor q4, q4, q11
+ vshr.u64 q10, q1, #4
+ vshr.u64 q11, q0, #4
+ veor q10, q10, q7
+ veor q11, q11, q3
+ vand q10, q10, q8
+ vand q11, q11, q8
+ veor q7, q7, q10
+ vshl.u64 q10, q10, #4
+ veor q3, q3, q11
+ vshl.u64 q11, q11, #4
+ veor q1, q1, q10
+ veor q0, q0, q11
+ vldmia r4, {q8} @ last round key
+ veor q4, q4, q8
+ veor q6, q6, q8
+ veor q3, q3, q8
+ veor q7, q7, q8
+ veor q2, q2, q8
+ veor q5, q5, q8
+ veor q0, q0, q8
+ veor q1, q1, q8
+ bx lr
+.size _bsaes_encrypt8,.-_bsaes_encrypt8
+.type _bsaes_key_convert,%function
+.align 4
+_bsaes_key_convert:
+ adr r6,_bsaes_key_convert
+ vld1.8 {q7}, [r4]! @ load round 0 key
+ sub r6,r6,#_bsaes_key_convert-.LM0
+ vld1.8 {q15}, [r4]! @ load round 1 key
+
+ vmov.i8 q8, #0x01 @ bit masks
+ vmov.i8 q9, #0x02
+ vmov.i8 q10, #0x04
+ vmov.i8 q11, #0x08
+ vmov.i8 q12, #0x10
+ vmov.i8 q13, #0x20
+ vldmia r6, {q14} @ .LM0
+
+#ifdef __ARMEL__
+ vrev32.8 q7, q7
+ vrev32.8 q15, q15
+#endif
+ sub r5,r5,#1
+ vstmia r12!, {q7} @ save round 0 key
+ b .Lkey_loop
+
+.align 4
+.Lkey_loop:
+ vtbl.8 d14,{q15},d28
+ vtbl.8 d15,{q15},d29
+ vmov.i8 q6, #0x40
+ vmov.i8 q15, #0x80
+
+ vtst.8 q0, q7, q8
+ vtst.8 q1, q7, q9
+ vtst.8 q2, q7, q10
+ vtst.8 q3, q7, q11
+ vtst.8 q4, q7, q12
+ vtst.8 q5, q7, q13
+ vtst.8 q6, q7, q6
+ vtst.8 q7, q7, q15
+ vld1.8 {q15}, [r4]! @ load next round key
+ vmvn q0, q0 @ "pnot"
+ vmvn q1, q1
+ vmvn q5, q5
+ vmvn q6, q6
+#ifdef __ARMEL__
+ vrev32.8 q15, q15
+#endif
+ subs r5,r5,#1
+ vstmia r12!,{q0-q7} @ write bit-sliced round key
+ bne .Lkey_loop
+
+ vmov.i8 q7,#0x63 @ compose .L63
+ @ don't save last round key
+ bx lr
+.size _bsaes_key_convert,.-_bsaes_key_convert
+.extern AES_cbc_encrypt
+.extern AES_decrypt
+
+.global bsaes_cbc_encrypt
+.type bsaes_cbc_encrypt,%function
+.align 5
+bsaes_cbc_encrypt:
+#ifndef __KERNEL__
+ cmp r2, #128
+#ifndef __thumb__
+ blo AES_cbc_encrypt
+#else
+ bhs 1f
+ b AES_cbc_encrypt
+1:
+#endif
+#endif
+
+ @ it is up to the caller to make sure we are called with enc == 0
+
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr}
+ VFP_ABI_PUSH
+ ldr r8, [ip] @ IV is 1st arg on the stack
+ mov r2, r2, lsr#4 @ len in 16 byte blocks
+ sub sp, #0x10 @ scratch space to carry over the IV
+ mov r9, sp @ save sp
+
+ ldr r10, [r3, #240] @ get # of rounds
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, r10, lsl#7 @ 128 bytes per inner round key
+ add r12, #96 @ sifze of bit-slices key schedule
+
+ @ populate the key schedule
+ mov r4, r3 @ pass key
+ mov r5, r10 @ pass # of rounds
+ mov sp, r12 @ sp is sp
+ bl _bsaes_key_convert
+ vldmia sp, {q6}
+ vstmia r12, {q15} @ save last round key
+ veor q7, q7, q6 @ fix up round 0 key
+ vstmia sp, {q7}
+#else
+ ldr r12, [r3, #244]
+ eors r12, #1
+ beq 0f
+
+ @ populate the key schedule
+ str r12, [r3, #244]
+ mov r4, r3 @ pass key
+ mov r5, r10 @ pass # of rounds
+ add r12, r3, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, r3, #248
+ vldmia r4, {q6}
+ vstmia r12, {q15} @ save last round key
+ veor q7, q7, q6 @ fix up round 0 key
+ vstmia r4, {q7}
+
+.align 2
+0:
+#endif
+
+ vld1.8 {q15}, [r8] @ load IV
+ b .Lcbc_dec_loop
+
+.align 4
+.Lcbc_dec_loop:
+ subs r2, r2, #0x8
+ bmi .Lcbc_dec_loop_finish
+
+ vld1.8 {q0-q1}, [r0]! @ load input
+ vld1.8 {q2-q3}, [r0]!
+#ifndef BSAES_ASM_EXTENDED_KEY
+ mov r4, sp @ pass the key
+#else
+ add r4, r3, #248
+#endif
+ vld1.8 {q4-q5}, [r0]!
+ mov r5, r10
+ vld1.8 {q6-q7}, [r0]
+ sub r0, r0, #0x60
+ vstmia r9, {q15} @ put aside IV
+
+ bl _bsaes_decrypt8
+
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q10-q11}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vld1.8 {q12-q13}, [r0]!
+ veor q4, q4, q10
+ veor q2, q2, q11
+ vld1.8 {q14-q15}, [r0]!
+ veor q7, q7, q12
+ vst1.8 {q0-q1}, [r1]! @ write output
+ veor q3, q3, q13
+ vst1.8 {q6}, [r1]!
+ veor q5, q5, q14
+ vst1.8 {q4}, [r1]!
+ vst1.8 {q2}, [r1]!
+ vst1.8 {q7}, [r1]!
+ vst1.8 {q3}, [r1]!
+ vst1.8 {q5}, [r1]!
+
+ b .Lcbc_dec_loop
+
+.Lcbc_dec_loop_finish:
+ adds r2, r2, #8
+ beq .Lcbc_dec_done
+
+ vld1.8 {q0}, [r0]! @ load input
+ cmp r2, #2
+ blo .Lcbc_dec_one
+ vld1.8 {q1}, [r0]!
+#ifndef BSAES_ASM_EXTENDED_KEY
+ mov r4, sp @ pass the key
+#else
+ add r4, r3, #248
+#endif
+ mov r5, r10
+ vstmia r9, {q15} @ put aside IV
+ beq .Lcbc_dec_two
+ vld1.8 {q2}, [r0]!
+ cmp r2, #4
+ blo .Lcbc_dec_three
+ vld1.8 {q3}, [r0]!
+ beq .Lcbc_dec_four
+ vld1.8 {q4}, [r0]!
+ cmp r2, #6
+ blo .Lcbc_dec_five
+ vld1.8 {q5}, [r0]!
+ beq .Lcbc_dec_six
+ vld1.8 {q6}, [r0]!
+ sub r0, r0, #0x70
+
+ bl _bsaes_decrypt8
+
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q10-q11}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vld1.8 {q12-q13}, [r0]!
+ veor q4, q4, q10
+ veor q2, q2, q11
+ vld1.8 {q15}, [r0]!
+ veor q7, q7, q12
+ vst1.8 {q0-q1}, [r1]! @ write output
+ veor q3, q3, q13
+ vst1.8 {q6}, [r1]!
+ vst1.8 {q4}, [r1]!
+ vst1.8 {q2}, [r1]!
+ vst1.8 {q7}, [r1]!
+ vst1.8 {q3}, [r1]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_six:
+ sub r0, r0, #0x60
+ bl _bsaes_decrypt8
+ vldmia r9,{q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q10-q11}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vld1.8 {q12}, [r0]!
+ veor q4, q4, q10
+ veor q2, q2, q11
+ vld1.8 {q15}, [r0]!
+ veor q7, q7, q12
+ vst1.8 {q0-q1}, [r1]! @ write output
+ vst1.8 {q6}, [r1]!
+ vst1.8 {q4}, [r1]!
+ vst1.8 {q2}, [r1]!
+ vst1.8 {q7}, [r1]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_five:
+ sub r0, r0, #0x50
+ bl _bsaes_decrypt8
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q10-q11}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vld1.8 {q15}, [r0]!
+ veor q4, q4, q10
+ vst1.8 {q0-q1}, [r1]! @ write output
+ veor q2, q2, q11
+ vst1.8 {q6}, [r1]!
+ vst1.8 {q4}, [r1]!
+ vst1.8 {q2}, [r1]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_four:
+ sub r0, r0, #0x40
+ bl _bsaes_decrypt8
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q10}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vld1.8 {q15}, [r0]!
+ veor q4, q4, q10
+ vst1.8 {q0-q1}, [r1]! @ write output
+ vst1.8 {q6}, [r1]!
+ vst1.8 {q4}, [r1]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_three:
+ sub r0, r0, #0x30
+ bl _bsaes_decrypt8
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8-q9}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q15}, [r0]!
+ veor q1, q1, q8
+ veor q6, q6, q9
+ vst1.8 {q0-q1}, [r1]! @ write output
+ vst1.8 {q6}, [r1]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_two:
+ sub r0, r0, #0x20
+ bl _bsaes_decrypt8
+ vldmia r9, {q14} @ reload IV
+ vld1.8 {q8}, [r0]! @ reload input
+ veor q0, q0, q14 @ ^= IV
+ vld1.8 {q15}, [r0]! @ reload input
+ veor q1, q1, q8
+ vst1.8 {q0-q1}, [r1]! @ write output
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_one:
+ sub r0, r0, #0x10
+ mov r10, r1 @ save original out pointer
+ mov r1, r9 @ use the iv scratch space as out buffer
+ mov r2, r3
+ vmov q4,q15 @ just in case ensure that IV
+ vmov q5,q0 @ and input are preserved
+ bl AES_decrypt
+ vld1.8 {q0}, [r9,:64] @ load result
+ veor q0, q0, q4 @ ^= IV
+ vmov q15, q5 @ q5 holds input
+ vst1.8 {q0}, [r10] @ write output
+
+.Lcbc_dec_done:
+#ifndef BSAES_ASM_EXTENDED_KEY
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+.Lcbc_dec_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r9
+ bne .Lcbc_dec_bzero
+#endif
+
+ mov sp, r9
+ add sp, #0x10 @ add sp,r9,#0x10 is no good for thumb
+ vst1.8 {q15}, [r8] @ return IV
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc}
+.size bsaes_cbc_encrypt,.-bsaes_cbc_encrypt
+.extern AES_encrypt
+.global bsaes_ctr32_encrypt_blocks
+.type bsaes_ctr32_encrypt_blocks,%function
+.align 5
+bsaes_ctr32_encrypt_blocks:
+ cmp r2, #8 @ use plain AES for
+ blo .Lctr_enc_short @ small sizes
+
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr}
+ VFP_ABI_PUSH
+ ldr r8, [ip] @ ctr is 1st arg on the stack
+ sub sp, sp, #0x10 @ scratch space to carry over the ctr
+ mov r9, sp @ save sp
+
+ ldr r10, [r3, #240] @ get # of rounds
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, r10, lsl#7 @ 128 bytes per inner round key
+ add r12, #96 @ size of bit-sliced key schedule
+
+ @ populate the key schedule
+ mov r4, r3 @ pass key
+ mov r5, r10 @ pass # of rounds
+ mov sp, r12 @ sp is sp
+ bl _bsaes_key_convert
+ veor q7,q7,q15 @ fix up last round key
+ vstmia r12, {q7} @ save last round key
+
+ vld1.8 {q0}, [r8] @ load counter
+ add r8, r6, #.LREVM0SR-.LM0 @ borrow r8
+ vldmia sp, {q4} @ load round0 key
+#else
+ ldr r12, [r3, #244]
+ eors r12, #1
+ beq 0f
+
+ @ populate the key schedule
+ str r12, [r3, #244]
+ mov r4, r3 @ pass key
+ mov r5, r10 @ pass # of rounds
+ add r12, r3, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ veor q7,q7,q15 @ fix up last round key
+ vstmia r12, {q7} @ save last round key
+
+.align 2
+0: add r12, r3, #248
+ vld1.8 {q0}, [r8] @ load counter
+ adrl r8, .LREVM0SR @ borrow r8
+ vldmia r12, {q4} @ load round0 key
+ sub sp, #0x10 @ place for adjusted round0 key
+#endif
+
+ vmov.i32 q8,#1 @ compose 1<<96
+ veor q9,q9,q9
+ vrev32.8 q0,q0
+ vext.8 q8,q9,q8,#4
+ vrev32.8 q4,q4
+ vadd.u32 q9,q8,q8 @ compose 2<<96
+ vstmia sp, {q4} @ save adjusted round0 key
+ b .Lctr_enc_loop
+
+.align 4
+.Lctr_enc_loop:
+ vadd.u32 q10, q8, q9 @ compose 3<<96
+ vadd.u32 q1, q0, q8 @ +1
+ vadd.u32 q2, q0, q9 @ +2
+ vadd.u32 q3, q0, q10 @ +3
+ vadd.u32 q4, q1, q10
+ vadd.u32 q5, q2, q10
+ vadd.u32 q6, q3, q10
+ vadd.u32 q7, q4, q10
+ vadd.u32 q10, q5, q10 @ next counter
+
+ @ Borrow prologue from _bsaes_encrypt8 to use the opportunity
+ @ to flip byte order in 32-bit counter
+
+ vldmia sp, {q9} @ load round0 key
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x10 @ pass next round key
+#else
+ add r4, r3, #264
+#endif
+ vldmia r8, {q8} @ .LREVM0SR
+ mov r5, r10 @ pass rounds
+ vstmia r9, {q10} @ save next counter
+ sub r6, r8, #.LREVM0SR-.LSR @ pass constants
+
+ bl _bsaes_encrypt8_alt
+
+ subs r2, r2, #8
+ blo .Lctr_enc_loop_done
+
+ vld1.8 {q8-q9}, [r0]! @ load input
+ vld1.8 {q10-q11}, [r0]!
+ veor q0, q8
+ veor q1, q9
+ vld1.8 {q12-q13}, [r0]!
+ veor q4, q10
+ veor q6, q11
+ vld1.8 {q14-q15}, [r0]!
+ veor q3, q12
+ vst1.8 {q0-q1}, [r1]! @ write output
+ veor q7, q13
+ veor q2, q14
+ vst1.8 {q4}, [r1]!
+ veor q5, q15
+ vst1.8 {q6}, [r1]!
+ vmov.i32 q8, #1 @ compose 1<<96
+ vst1.8 {q3}, [r1]!
+ veor q9, q9, q9
+ vst1.8 {q7}, [r1]!
+ vext.8 q8, q9, q8, #4
+ vst1.8 {q2}, [r1]!
+ vadd.u32 q9,q8,q8 @ compose 2<<96
+ vst1.8 {q5}, [r1]!
+ vldmia r9, {q0} @ load counter
+
+ bne .Lctr_enc_loop
+ b .Lctr_enc_done
+
+.align 4
+.Lctr_enc_loop_done:
+ add r2, r2, #8
+ vld1.8 {q8}, [r0]! @ load input
+ veor q0, q8
+ vst1.8 {q0}, [r1]! @ write output
+ cmp r2, #2
+ blo .Lctr_enc_done
+ vld1.8 {q9}, [r0]!
+ veor q1, q9
+ vst1.8 {q1}, [r1]!
+ beq .Lctr_enc_done
+ vld1.8 {q10}, [r0]!
+ veor q4, q10
+ vst1.8 {q4}, [r1]!
+ cmp r2, #4
+ blo .Lctr_enc_done
+ vld1.8 {q11}, [r0]!
+ veor q6, q11
+ vst1.8 {q6}, [r1]!
+ beq .Lctr_enc_done
+ vld1.8 {q12}, [r0]!
+ veor q3, q12
+ vst1.8 {q3}, [r1]!
+ cmp r2, #6
+ blo .Lctr_enc_done
+ vld1.8 {q13}, [r0]!
+ veor q7, q13
+ vst1.8 {q7}, [r1]!
+ beq .Lctr_enc_done
+ vld1.8 {q14}, [r0]
+ veor q2, q14
+ vst1.8 {q2}, [r1]!
+
+.Lctr_enc_done:
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifndef BSAES_ASM_EXTENDED_KEY
+.Lctr_enc_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r9
+ bne .Lctr_enc_bzero
+#else
+ vstmia sp, {q0-q1}
+#endif
+
+ mov sp, r9
+ add sp, #0x10 @ add sp,r9,#0x10 is no good for thumb
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.align 4
+.Lctr_enc_short:
+ ldr ip, [sp] @ ctr pointer is passed on stack
+ stmdb sp!, {r4-r8, lr}
+
+ mov r4, r0 @ copy arguments
+ mov r5, r1
+ mov r6, r2
+ mov r7, r3
+ ldr r8, [ip, #12] @ load counter LSW
+ vld1.8 {q1}, [ip] @ load whole counter value
+#ifdef __ARMEL__
+ rev r8, r8
+#endif
+ sub sp, sp, #0x10
+ vst1.8 {q1}, [sp,:64] @ copy counter value
+ sub sp, sp, #0x10
+
+.Lctr_enc_short_loop:
+ add r0, sp, #0x10 @ input counter value
+ mov r1, sp @ output on the stack
+ mov r2, r7 @ key
+
+ bl AES_encrypt
+
+ vld1.8 {q0}, [r4]! @ load input
+ vld1.8 {q1}, [sp,:64] @ load encrypted counter
+ add r8, r8, #1
+#ifdef __ARMEL__
+ rev r0, r8
+ str r0, [sp, #0x1c] @ next counter value
+#else
+ str r8, [sp, #0x1c] @ next counter value
+#endif
+ veor q0,q0,q1
+ vst1.8 {q0}, [r5]! @ store output
+ subs r6, r6, #1
+ bne .Lctr_enc_short_loop
+
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+ vstmia sp!, {q0-q1}
+
+ ldmia sp!, {r4-r8, pc}
+.size bsaes_ctr32_encrypt_blocks,.-bsaes_ctr32_encrypt_blocks
+.globl bsaes_xts_encrypt
+.type bsaes_xts_encrypt,%function
+.align 4
+bsaes_xts_encrypt:
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr} @ 0x20
+ VFP_ABI_PUSH
+ mov r6, sp @ future r3
+
+ mov r7, r0
+ mov r8, r1
+ mov r9, r2
+ mov r10, r3
+
+ sub r0, sp, #0x10 @ 0x10
+ bic r0, #0xf @ align at 16 bytes
+ mov sp, r0
+
+#ifdef XTS_CHAIN_TWEAK
+ ldr r0, [ip] @ pointer to input tweak
+#else
+ @ generate initial tweak
+ ldr r0, [ip, #4] @ iv[]
+ mov r1, sp
+ ldr r2, [ip, #0] @ key2
+ bl AES_encrypt
+ mov r0,sp @ pointer to initial tweak
+#endif
+
+ ldr r1, [r10, #240] @ get # of rounds
+ mov r3, r6
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, r1, lsl#7 @ 128 bytes per inner round key
+ @ add r12, #96 @ size of bit-sliced key schedule
+ sub r12, #48 @ place for tweak[9]
+
+ @ populate the key schedule
+ mov r4, r10 @ pass key
+ mov r5, r1 @ pass # of rounds
+ mov sp, r12
+ add r12, #0x90 @ pass key schedule
+ bl _bsaes_key_convert
+ veor q7, q7, q15 @ fix up last round key
+ vstmia r12, {q7} @ save last round key
+#else
+ ldr r12, [r10, #244]
+ eors r12, #1
+ beq 0f
+
+ str r12, [r10, #244]
+ mov r4, r10 @ pass key
+ mov r5, r1 @ pass # of rounds
+ add r12, r10, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ veor q7, q7, q15 @ fix up last round key
+ vstmia r12, {q7}
+
+.align 2
+0: sub sp, #0x90 @ place for tweak[9]
+#endif
+
+ vld1.8 {q8}, [r0] @ initial tweak
+ adr r2, .Lxts_magic
+
+ subs r9, #0x80
+ blo .Lxts_enc_short
+ b .Lxts_enc_loop
+
+.align 4
+.Lxts_enc_loop:
+ vldmia r2, {q5} @ load XTS magic
+ vshr.s64 q6, q8, #63
+ mov r0, sp
+ vand q6, q6, q5
+ vadd.u64 q9, q8, q8
+ vst1.64 {q8}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q9, #63
+ veor q9, q9, q6
+ vand q7, q7, q5
+ vadd.u64 q10, q9, q9
+ vst1.64 {q9}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q10, #63
+ veor q10, q10, q7
+ vand q6, q6, q5
+ vld1.8 {q0}, [r7]!
+ vadd.u64 q11, q10, q10
+ vst1.64 {q10}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q11, #63
+ veor q11, q11, q6
+ vand q7, q7, q5
+ vld1.8 {q1}, [r7]!
+ veor q0, q0, q8
+ vadd.u64 q12, q11, q11
+ vst1.64 {q11}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q12, #63
+ veor q12, q12, q7
+ vand q6, q6, q5
+ vld1.8 {q2}, [r7]!
+ veor q1, q1, q9
+ vadd.u64 q13, q12, q12
+ vst1.64 {q12}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q13, #63
+ veor q13, q13, q6
+ vand q7, q7, q5
+ vld1.8 {q3}, [r7]!
+ veor q2, q2, q10
+ vadd.u64 q14, q13, q13
+ vst1.64 {q13}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q14, #63
+ veor q14, q14, q7
+ vand q6, q6, q5
+ vld1.8 {q4}, [r7]!
+ veor q3, q3, q11
+ vadd.u64 q15, q14, q14
+ vst1.64 {q14}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q15, #63
+ veor q15, q15, q6
+ vand q7, q7, q5
+ vld1.8 {q5}, [r7]!
+ veor q4, q4, q12
+ vadd.u64 q8, q15, q15
+ vst1.64 {q15}, [r0,:128]!
+ vswp d15,d14
+ veor q8, q8, q7
+ vst1.64 {q8}, [r0,:128] @ next round tweak
+
+ vld1.8 {q6-q7}, [r7]!
+ veor q5, q5, q13
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q6, q6, q14
+ mov r5, r1 @ pass rounds
+ veor q7, q7, q15
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q6, q11
+ vld1.64 {q14-q15}, [r0,:128]!
+ veor q10, q3, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ veor q12, q2, q14
+ vst1.8 {q10-q11}, [r8]!
+ veor q13, q5, q15
+ vst1.8 {q12-q13}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+
+ subs r9, #0x80
+ bpl .Lxts_enc_loop
+
+.Lxts_enc_short:
+ adds r9, #0x70
+ bmi .Lxts_enc_done
+
+ vldmia r2, {q5} @ load XTS magic
+ vshr.s64 q7, q8, #63
+ mov r0, sp
+ vand q7, q7, q5
+ vadd.u64 q9, q8, q8
+ vst1.64 {q8}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q9, #63
+ veor q9, q9, q7
+ vand q6, q6, q5
+ vadd.u64 q10, q9, q9
+ vst1.64 {q9}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q10, #63
+ veor q10, q10, q6
+ vand q7, q7, q5
+ vld1.8 {q0}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_1
+ vadd.u64 q11, q10, q10
+ vst1.64 {q10}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q11, #63
+ veor q11, q11, q7
+ vand q6, q6, q5
+ vld1.8 {q1}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_2
+ veor q0, q0, q8
+ vadd.u64 q12, q11, q11
+ vst1.64 {q11}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q12, #63
+ veor q12, q12, q6
+ vand q7, q7, q5
+ vld1.8 {q2}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_3
+ veor q1, q1, q9
+ vadd.u64 q13, q12, q12
+ vst1.64 {q12}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q13, #63
+ veor q13, q13, q7
+ vand q6, q6, q5
+ vld1.8 {q3}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_4
+ veor q2, q2, q10
+ vadd.u64 q14, q13, q13
+ vst1.64 {q13}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q14, #63
+ veor q14, q14, q6
+ vand q7, q7, q5
+ vld1.8 {q4}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_5
+ veor q3, q3, q11
+ vadd.u64 q15, q14, q14
+ vst1.64 {q14}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q15, #63
+ veor q15, q15, q7
+ vand q6, q6, q5
+ vld1.8 {q5}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_enc_6
+ veor q4, q4, q12
+ sub r9, #0x10
+ vst1.64 {q15}, [r0,:128] @ next round tweak
+
+ vld1.8 {q6}, [r7]!
+ veor q5, q5, q13
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q6, q6, q14
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q6, q11
+ vld1.64 {q14}, [r0,:128]!
+ veor q10, q3, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ veor q12, q2, q14
+ vst1.8 {q10-q11}, [r8]!
+ vst1.8 {q12}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_6:
+ vst1.64 {q14}, [r0,:128] @ next round tweak
+
+ veor q4, q4, q12
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q5, q5, q13
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q6, q11
+ veor q10, q3, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ vst1.8 {q10-q11}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+
+@ put this in range for both ARM and Thumb mode adr instructions
+.align 5
+.Lxts_magic:
+ .quad 1, 0x87
+
+.align 5
+.Lxts_enc_5:
+ vst1.64 {q13}, [r0,:128] @ next round tweak
+
+ veor q3, q3, q11
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q4, q4, q12
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q6, q11
+ veor q10, q3, q12
+ vst1.8 {q8-q9}, [r8]!
+ vst1.8 {q10}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_4:
+ vst1.64 {q12}, [r0,:128] @ next round tweak
+
+ veor q2, q2, q10
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q3, q3, q11
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q6, q11
+ vst1.8 {q8-q9}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_3:
+ vst1.64 {q11}, [r0,:128] @ next round tweak
+
+ veor q1, q1, q9
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q2, q2, q10
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ veor q8, q4, q10
+ vst1.8 {q0-q1}, [r8]!
+ vst1.8 {q8}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_2:
+ vst1.64 {q10}, [r0,:128] @ next round tweak
+
+ veor q0, q0, q8
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q1, q1, q9
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ vst1.8 {q0-q1}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_1:
+ mov r0, sp
+ veor q0, q8
+ mov r1, sp
+ vst1.8 {q0}, [sp,:128]
+ mov r2, r10
+ mov r4, r3 @ preserve fp
+
+ bl AES_encrypt
+
+ vld1.8 {q0}, [sp,:128]
+ veor q0, q0, q8
+ vst1.8 {q0}, [r8]!
+ mov r3, r4
+
+ vmov q8, q9 @ next round tweak
+
+.Lxts_enc_done:
+#ifndef XTS_CHAIN_TWEAK
+ adds r9, #0x10
+ beq .Lxts_enc_ret
+ sub r6, r8, #0x10
+
+.Lxts_enc_steal:
+ ldrb r0, [r7], #1
+ ldrb r1, [r8, #-0x10]
+ strb r0, [r8, #-0x10]
+ strb r1, [r8], #1
+
+ subs r9, #1
+ bhi .Lxts_enc_steal
+
+ vld1.8 {q0}, [r6]
+ mov r0, sp
+ veor q0, q0, q8
+ mov r1, sp
+ vst1.8 {q0}, [sp,:128]
+ mov r2, r10
+ mov r4, r3 @ preserve fp
+
+ bl AES_encrypt
+
+ vld1.8 {q0}, [sp,:128]
+ veor q0, q0, q8
+ vst1.8 {q0}, [r6]
+ mov r3, r4
+#endif
+
+.Lxts_enc_ret:
+ bic r0, r3, #0xf
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifdef XTS_CHAIN_TWEAK
+ ldr r1, [r3, #0x20+VFP_ABI_FRAME] @ chain tweak
+#endif
+.Lxts_enc_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r0
+ bne .Lxts_enc_bzero
+
+ mov sp, r3
+#ifdef XTS_CHAIN_TWEAK
+ vst1.8 {q8}, [r1]
+#endif
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.size bsaes_xts_encrypt,.-bsaes_xts_encrypt
+
+.globl bsaes_xts_decrypt
+.type bsaes_xts_decrypt,%function
+.align 4
+bsaes_xts_decrypt:
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr} @ 0x20
+ VFP_ABI_PUSH
+ mov r6, sp @ future r3
+
+ mov r7, r0
+ mov r8, r1
+ mov r9, r2
+ mov r10, r3
+
+ sub r0, sp, #0x10 @ 0x10
+ bic r0, #0xf @ align at 16 bytes
+ mov sp, r0
+
+#ifdef XTS_CHAIN_TWEAK
+ ldr r0, [ip] @ pointer to input tweak
+#else
+ @ generate initial tweak
+ ldr r0, [ip, #4] @ iv[]
+ mov r1, sp
+ ldr r2, [ip, #0] @ key2
+ bl AES_encrypt
+ mov r0, sp @ pointer to initial tweak
+#endif
+
+ ldr r1, [r10, #240] @ get # of rounds
+ mov r3, r6
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, r1, lsl#7 @ 128 bytes per inner round key
+ @ add r12, #96 @ size of bit-sliced key schedule
+ sub r12, #48 @ place for tweak[9]
+
+ @ populate the key schedule
+ mov r4, r10 @ pass key
+ mov r5, r1 @ pass # of rounds
+ mov sp, r12
+ add r12, #0x90 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, sp, #0x90
+ vldmia r4, {q6}
+ vstmia r12, {q15} @ save last round key
+ veor q7, q7, q6 @ fix up round 0 key
+ vstmia r4, {q7}
+#else
+ ldr r12, [r10, #244]
+ eors r12, #1
+ beq 0f
+
+ str r12, [r10, #244]
+ mov r4, r10 @ pass key
+ mov r5, r1 @ pass # of rounds
+ add r12, r10, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, r10, #248
+ vldmia r4, {q6}
+ vstmia r12, {q15} @ save last round key
+ veor q7, q7, q6 @ fix up round 0 key
+ vstmia r4, {q7}
+
+.align 2
+0: sub sp, #0x90 @ place for tweak[9]
+#endif
+ vld1.8 {q8}, [r0] @ initial tweak
+ adr r2, .Lxts_magic
+
+ tst r9, #0xf @ if not multiple of 16
+ it ne @ Thumb2 thing, sanity check in ARM
+ subne r9, #0x10 @ subtract another 16 bytes
+ subs r9, #0x80
+
+ blo .Lxts_dec_short
+ b .Lxts_dec_loop
+
+.align 4
+.Lxts_dec_loop:
+ vldmia r2, {q5} @ load XTS magic
+ vshr.s64 q6, q8, #63
+ mov r0, sp
+ vand q6, q6, q5
+ vadd.u64 q9, q8, q8
+ vst1.64 {q8}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q9, #63
+ veor q9, q9, q6
+ vand q7, q7, q5
+ vadd.u64 q10, q9, q9
+ vst1.64 {q9}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q10, #63
+ veor q10, q10, q7
+ vand q6, q6, q5
+ vld1.8 {q0}, [r7]!
+ vadd.u64 q11, q10, q10
+ vst1.64 {q10}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q11, #63
+ veor q11, q11, q6
+ vand q7, q7, q5
+ vld1.8 {q1}, [r7]!
+ veor q0, q0, q8
+ vadd.u64 q12, q11, q11
+ vst1.64 {q11}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q12, #63
+ veor q12, q12, q7
+ vand q6, q6, q5
+ vld1.8 {q2}, [r7]!
+ veor q1, q1, q9
+ vadd.u64 q13, q12, q12
+ vst1.64 {q12}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q13, #63
+ veor q13, q13, q6
+ vand q7, q7, q5
+ vld1.8 {q3}, [r7]!
+ veor q2, q2, q10
+ vadd.u64 q14, q13, q13
+ vst1.64 {q13}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q14, #63
+ veor q14, q14, q7
+ vand q6, q6, q5
+ vld1.8 {q4}, [r7]!
+ veor q3, q3, q11
+ vadd.u64 q15, q14, q14
+ vst1.64 {q14}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q15, #63
+ veor q15, q15, q6
+ vand q7, q7, q5
+ vld1.8 {q5}, [r7]!
+ veor q4, q4, q12
+ vadd.u64 q8, q15, q15
+ vst1.64 {q15}, [r0,:128]!
+ vswp d15,d14
+ veor q8, q8, q7
+ vst1.64 {q8}, [r0,:128] @ next round tweak
+
+ vld1.8 {q6-q7}, [r7]!
+ veor q5, q5, q13
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q6, q6, q14
+ mov r5, r1 @ pass rounds
+ veor q7, q7, q15
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q4, q11
+ vld1.64 {q14-q15}, [r0,:128]!
+ veor q10, q2, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ veor q12, q3, q14
+ vst1.8 {q10-q11}, [r8]!
+ veor q13, q5, q15
+ vst1.8 {q12-q13}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+
+ subs r9, #0x80
+ bpl .Lxts_dec_loop
+
+.Lxts_dec_short:
+ adds r9, #0x70
+ bmi .Lxts_dec_done
+
+ vldmia r2, {q5} @ load XTS magic
+ vshr.s64 q7, q8, #63
+ mov r0, sp
+ vand q7, q7, q5
+ vadd.u64 q9, q8, q8
+ vst1.64 {q8}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q9, #63
+ veor q9, q9, q7
+ vand q6, q6, q5
+ vadd.u64 q10, q9, q9
+ vst1.64 {q9}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q10, #63
+ veor q10, q10, q6
+ vand q7, q7, q5
+ vld1.8 {q0}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_1
+ vadd.u64 q11, q10, q10
+ vst1.64 {q10}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q11, #63
+ veor q11, q11, q7
+ vand q6, q6, q5
+ vld1.8 {q1}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_2
+ veor q0, q0, q8
+ vadd.u64 q12, q11, q11
+ vst1.64 {q11}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q12, #63
+ veor q12, q12, q6
+ vand q7, q7, q5
+ vld1.8 {q2}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_3
+ veor q1, q1, q9
+ vadd.u64 q13, q12, q12
+ vst1.64 {q12}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q13, #63
+ veor q13, q13, q7
+ vand q6, q6, q5
+ vld1.8 {q3}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_4
+ veor q2, q2, q10
+ vadd.u64 q14, q13, q13
+ vst1.64 {q13}, [r0,:128]!
+ vswp d13,d12
+ vshr.s64 q7, q14, #63
+ veor q14, q14, q6
+ vand q7, q7, q5
+ vld1.8 {q4}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_5
+ veor q3, q3, q11
+ vadd.u64 q15, q14, q14
+ vst1.64 {q14}, [r0,:128]!
+ vswp d15,d14
+ vshr.s64 q6, q15, #63
+ veor q15, q15, q7
+ vand q6, q6, q5
+ vld1.8 {q5}, [r7]!
+ subs r9, #0x10
+ bmi .Lxts_dec_6
+ veor q4, q4, q12
+ sub r9, #0x10
+ vst1.64 {q15}, [r0,:128] @ next round tweak
+
+ vld1.8 {q6}, [r7]!
+ veor q5, q5, q13
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q6, q6, q14
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q4, q11
+ vld1.64 {q14}, [r0,:128]!
+ veor q10, q2, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ veor q12, q3, q14
+ vst1.8 {q10-q11}, [r8]!
+ vst1.8 {q12}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_6:
+ vst1.64 {q14}, [r0,:128] @ next round tweak
+
+ veor q4, q4, q12
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q5, q5, q13
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12-q13}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q4, q11
+ veor q10, q2, q12
+ vst1.8 {q8-q9}, [r8]!
+ veor q11, q7, q13
+ vst1.8 {q10-q11}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_5:
+ vst1.64 {q13}, [r0,:128] @ next round tweak
+
+ veor q3, q3, q11
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q4, q4, q12
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ vld1.64 {q12}, [r0,:128]!
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q4, q11
+ veor q10, q2, q12
+ vst1.8 {q8-q9}, [r8]!
+ vst1.8 {q10}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_4:
+ vst1.64 {q12}, [r0,:128] @ next round tweak
+
+ veor q2, q2, q10
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q3, q3, q11
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10-q11}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ veor q9, q4, q11
+ vst1.8 {q8-q9}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_3:
+ vst1.64 {q11}, [r0,:128] @ next round tweak
+
+ veor q1, q1, q9
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q2, q2, q10
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ vld1.64 {q10}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ veor q8, q6, q10
+ vst1.8 {q0-q1}, [r8]!
+ vst1.8 {q8}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_2:
+ vst1.64 {q10}, [r0,:128] @ next round tweak
+
+ veor q0, q0, q8
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, r10, #248 @ pass key schedule
+#endif
+ veor q1, q1, q9
+ mov r5, r1 @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {q8-q9}, [r0,:128]!
+ veor q0, q0, q8
+ veor q1, q1, q9
+ vst1.8 {q0-q1}, [r8]!
+
+ vld1.64 {q8}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_1:
+ mov r0, sp
+ veor q0, q8
+ mov r1, sp
+ vst1.8 {q0}, [sp,:128]
+ mov r2, r10
+ mov r4, r3 @ preserve fp
+ mov r5, r2 @ preserve magic
+
+ bl AES_decrypt
+
+ vld1.8 {q0}, [sp,:128]
+ veor q0, q0, q8
+ vst1.8 {q0}, [r8]!
+ mov r3, r4
+ mov r2, r5
+
+ vmov q8, q9 @ next round tweak
+
+.Lxts_dec_done:
+#ifndef XTS_CHAIN_TWEAK
+ adds r9, #0x10
+ beq .Lxts_dec_ret
+
+ @ calculate one round of extra tweak for the stolen ciphertext
+ vldmia r2, {q5}
+ vshr.s64 q6, q8, #63
+ vand q6, q6, q5
+ vadd.u64 q9, q8, q8
+ vswp d13,d12
+ veor q9, q9, q6
+
+ @ perform the final decryption with the last tweak value
+ vld1.8 {q0}, [r7]!
+ mov r0, sp
+ veor q0, q0, q9
+ mov r1, sp
+ vst1.8 {q0}, [sp,:128]
+ mov r2, r10
+ mov r4, r3 @ preserve fp
+
+ bl AES_decrypt
+
+ vld1.8 {q0}, [sp,:128]
+ veor q0, q0, q9
+ vst1.8 {q0}, [r8]
+
+ mov r6, r8
+.Lxts_dec_steal:
+ ldrb r1, [r8]
+ ldrb r0, [r7], #1
+ strb r1, [r8, #0x10]
+ strb r0, [r8], #1
+
+ subs r9, #1
+ bhi .Lxts_dec_steal
+
+ vld1.8 {q0}, [r6]
+ mov r0, sp
+ veor q0, q8
+ mov r1, sp
+ vst1.8 {q0}, [sp,:128]
+ mov r2, r10
+
+ bl AES_decrypt
+
+ vld1.8 {q0}, [sp,:128]
+ veor q0, q0, q8
+ vst1.8 {q0}, [r6]
+ mov r3, r4
+#endif
+
+.Lxts_dec_ret:
+ bic r0, r3, #0xf
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifdef XTS_CHAIN_TWEAK
+ ldr r1, [r3, #0x20+VFP_ABI_FRAME] @ chain tweak
+#endif
+.Lxts_dec_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r0
+ bne .Lxts_dec_bzero
+
+ mov sp, r3
+#ifdef XTS_CHAIN_TWEAK
+ vst1.8 {q8}, [r1]
+#endif
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.size bsaes_xts_decrypt,.-bsaes_xts_decrypt
+#endif
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
new file mode 100644
index 0000000..15468fb
--- /dev/null
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -0,0 +1,434 @@
+/*
+ * linux/arch/arm/crypto/aesbs-glue.c - glue code for NEON bit sliced AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+
+#include "aes_glue.h"
+
+#define BIT_SLICED_KEY_MAXSIZE (128 * (AES_MAXNR - 1) + 2 * AES_BLOCK_SIZE)
+
+struct BS_KEY {
+ struct AES_KEY rk;
+ int converted;
+ u8 __aligned(8) bs[BIT_SLICED_KEY_MAXSIZE];
+} __aligned(8);
+
+asmlinkage void bsaes_enc_key_convert(u8 out[], struct AES_KEY const *in);
+asmlinkage void bsaes_dec_key_convert(u8 out[], struct AES_KEY const *in);
+
+asmlinkage void bsaes_cbc_encrypt(u8 const in[], u8 out[], u32 bytes,
+ struct BS_KEY *key, u8 iv[]);
+
+asmlinkage void bsaes_ctr32_encrypt_blocks(u8 const in[], u8 out[], u32 blocks,
+ struct BS_KEY *key, u8 const iv[]);
+
+asmlinkage void bsaes_xts_encrypt(u8 const in[], u8 out[], u32 bytes,
+ struct BS_KEY *key, u8 tweak[]);
+
+asmlinkage void bsaes_xts_decrypt(u8 const in[], u8 out[], u32 bytes,
+ struct BS_KEY *key, u8 tweak[]);
+
+struct aesbs_cbc_ctx {
+ struct AES_KEY enc;
+ struct BS_KEY dec;
+};
+
+struct aesbs_ctr_ctx {
+ struct BS_KEY enc;
+};
+
+struct aesbs_xts_ctx {
+ struct BS_KEY enc;
+ struct BS_KEY dec;
+ struct AES_KEY twkey;
+};
+
+static int aesbs_cbc_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+ int bits = key_len * 8;
+
+ if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc)) {
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+ ctx->dec.rk = ctx->enc;
+ private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
+ ctx->dec.converted = 0;
+ return 0;
+}
+
+static int aesbs_ctr_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+ int bits = key_len * 8;
+
+ if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+ ctx->enc.converted = 0;
+ return 0;
+}
+
+static int aesbs_xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+ int bits = key_len * 4;
+
+ if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+ ctx->dec.rk = ctx->enc.rk;
+ private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
+ private_AES_set_encrypt_key(in_key + key_len / 2, bits, &ctx->twkey);
+ ctx->enc.converted = ctx->dec.converted = 0;
+ return 0;
+}
+
+static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ while (walk.nbytes) {
+ u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
+ u8 *src = walk.src.virt.addr;
+
+ if (walk.dst.virt.addr == walk.src.virt.addr) {
+ u8 *iv = walk.iv;
+
+ do {
+ crypto_xor(src, iv, AES_BLOCK_SIZE);
+ AES_encrypt(src, src, &ctx->enc);
+ iv = src;
+ src += AES_BLOCK_SIZE;
+ } while (--blocks);
+ memcpy(walk.iv, iv, AES_BLOCK_SIZE);
+ } else {
+ u8 *dst = walk.dst.virt.addr;
+
+ do {
+ crypto_xor(walk.iv, src, AES_BLOCK_SIZE);
+ AES_encrypt(walk.iv, dst, &ctx->enc);
+ memcpy(walk.iv, dst, AES_BLOCK_SIZE);
+ src += AES_BLOCK_SIZE;
+ dst += AES_BLOCK_SIZE;
+ } while (--blocks);
+ }
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+ while ((walk.nbytes / AES_BLOCK_SIZE) >= 8) {
+ kernel_neon_begin();
+ bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+ walk.nbytes, &ctx->dec, walk.iv);
+ kernel_neon_end();
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ while (walk.nbytes) {
+ u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
+ u8 *dst = walk.dst.virt.addr;
+ u8 *src = walk.src.virt.addr;
+ u8 bk[2][AES_BLOCK_SIZE];
+ u8 *iv = walk.iv;
+
+ do {
+ if (walk.dst.virt.addr == walk.src.virt.addr)
+ memcpy(bk[blocks & 1], src, AES_BLOCK_SIZE);
+
+ AES_decrypt(src, dst, &ctx->dec.rk);
+ crypto_xor(dst, iv, AES_BLOCK_SIZE);
+
+ if (walk.dst.virt.addr == walk.src.virt.addr)
+ iv = bk[blocks & 1];
+ else
+ iv = src;
+
+ dst += AES_BLOCK_SIZE;
+ src += AES_BLOCK_SIZE;
+ } while (--blocks);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static void inc_be128_ctr(__be32 ctr[], u32 addend)
+{
+ int i;
+
+ for (i = 3; i >= 0; i--, addend = 1) {
+ u32 n = be32_to_cpu(ctr[i]) + addend;
+
+ ctr[i] = cpu_to_be32(n);
+ if (n >= addend)
+ break;
+ }
+}
+
+static int aesbs_ctr_encrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst, struct scatterlist *src,
+ unsigned int nbytes)
+{
+ struct aesbs_ctr_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ u32 blocks;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+ while ((blocks = walk.nbytes / AES_BLOCK_SIZE)) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+ __be32 *ctr = (__be32 *)walk.iv;
+ u32 headroom = UINT_MAX - be32_to_cpu(ctr[3]);
+
+ /* avoid 32 bit counter overflow in the NEON code */
+ if (unlikely(headroom < blocks)) {
+ blocks = headroom + 1;
+ tail = walk.nbytes - blocks * AES_BLOCK_SIZE;
+ }
+ kernel_neon_begin();
+ bsaes_ctr32_encrypt_blocks(walk.src.virt.addr,
+ walk.dst.virt.addr, blocks,
+ &ctx->enc, walk.iv);
+ kernel_neon_end();
+ inc_be128_ctr(ctr, blocks);
+
+ nbytes -= blocks * AES_BLOCK_SIZE;
+ if (nbytes && nbytes == tail && nbytes <= AES_BLOCK_SIZE)
+ break;
+
+ err = blkcipher_walk_done(desc, &walk, tail);
+ }
+ if (walk.nbytes) {
+ u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 ks[AES_BLOCK_SIZE];
+
+ AES_encrypt(walk.iv, ks, &ctx->enc.rk);
+ if (tdst != tsrc)
+ memcpy(tdst, tsrc, nbytes);
+ crypto_xor(tdst, ks, nbytes);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ return err;
+}
+
+static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+ /* generate the initial tweak */
+ AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
+
+ while (walk.nbytes) {
+ kernel_neon_begin();
+ bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+ walk.nbytes, &ctx->enc, walk.iv);
+ kernel_neon_end();
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
+
+ /* generate the initial tweak */
+ AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
+
+ while (walk.nbytes) {
+ kernel_neon_begin();
+ bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
+ walk.nbytes, &ctx->dec, walk.iv);
+ kernel_neon_end();
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static struct crypto_alg aesbs_algs[] = { {
+ .cra_name = "__cbc-aes-neonbs",
+ .cra_driver_name = "__driver-cbc-aes-neonbs",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct aesbs_cbc_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_cbc_set_key,
+ .encrypt = aesbs_cbc_encrypt,
+ .decrypt = aesbs_cbc_decrypt,
+ },
+}, {
+ .cra_name = "__ctr-aes-neonbs",
+ .cra_driver_name = "__driver-ctr-aes-neonbs",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct aesbs_ctr_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_ctr_set_key,
+ .encrypt = aesbs_ctr_encrypt,
+ .decrypt = aesbs_ctr_encrypt,
+ },
+}, {
+ .cra_name = "__xts-aes-neonbs",
+ .cra_driver_name = "__driver-xts-aes-neonbs",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct aesbs_xts_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_xts_set_key,
+ .encrypt = aesbs_xts_encrypt,
+ .decrypt = aesbs_xts_decrypt,
+ },
+}, {
+ .cra_name = "cbc(aes)",
+ .cra_driver_name = "cbc-aes-neonbs",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = __ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "ctr(aes)",
+ .cra_driver_name = "ctr-aes-neonbs",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "xts(aes)",
+ .cra_driver_name = "xts-aes-neonbs",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+} };
+
+static int __init aesbs_mod_init(void)
+{
+ if (!cpu_has_neon())
+ return -ENODEV;
+
+ return crypto_register_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
+}
+
+static void __exit aesbs_mod_exit(void)
+{
+ crypto_unregister_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
+}
+
+module_init(aesbs_mod_init);
+module_exit(aesbs_mod_exit);
+
+MODULE_DESCRIPTION("Bit sliced AES in CBC/CTR/XTS modes using NEON");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
new file mode 100644
index 0000000..be068db
--- /dev/null
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -0,0 +1,2467 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Specific modes and adaptation for Linux kernel by Ard Biesheuvel
+# <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is
+# granted.
+# ====================================================================
+
+# Bit-sliced AES for ARM NEON
+#
+# February 2012.
+#
+# This implementation is direct adaptation of bsaes-x86_64 module for
+# ARM NEON. Except that this module is endian-neutral [in sense that
+# it can be compiled for either endianness] by courtesy of vld1.8's
+# neutrality. Initial version doesn't implement interface to OpenSSL,
+# only low-level primitives and unsupported entry points, just enough
+# to collect performance results, which for Cortex-A8 core are:
+#
+# encrypt 19.5 cycles per byte processed with 128-bit key
+# decrypt 22.1 cycles per byte processed with 128-bit key
+# key conv. 440 cycles per 128-bit key/0.18 of 8x block
+#
+# Snapdragon S4 encrypts byte in 17.6 cycles and decrypts in 19.7,
+# which is [much] worse than anticipated (for further details see
+# http://www.openssl.org/~appro/Snapdragon-S4.html).
+#
+# Cortex-A15 manages in 14.2/16.1 cycles [when integer-only code
+# manages in 20.0 cycles].
+#
+# When comparing to x86_64 results keep in mind that NEON unit is
+# [mostly] single-issue and thus can't [fully] benefit from
+# instruction-level parallelism. And when comparing to aes-armv4
+# results keep in mind key schedule conversion overhead (see
+# bsaes-x86_64.pl for further details)...
+#
+# <appro@openssl.org>
+
+# April-August 2013
+#
+# Add CBC, CTR and XTS subroutines, adapt for kernel use.
+#
+# <ard.biesheuvel@linaro.org>
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+my ($inp,$out,$len,$key)=("r0","r1","r2","r3");
+my @XMM=map("q$_",(0..15));
+
+{
+my ($key,$rounds,$const)=("r4","r5","r6");
+
+sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; }
+sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; }
+
+sub Sbox {
+# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb
+# output in lsb > [b0, b1, b4, b6, b3, b7, b2, b5] < msb
+my @b=@_[0..7];
+my @t=@_[8..11];
+my @s=@_[12..15];
+ &InBasisChange (@b);
+ &Inv_GF256 (@b[6,5,0,3,7,1,4,2],@t,@s);
+ &OutBasisChange (@b[7,1,4,2,6,5,0,3]);
+}
+
+sub InBasisChange {
+# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb
+# output in lsb > [b6, b5, b0, b3, b7, b1, b4, b2] < msb
+my @b=@_[0..7];
+$code.=<<___;
+ veor @b[2], @b[2], @b[1]
+ veor @b[5], @b[5], @b[6]
+ veor @b[3], @b[3], @b[0]
+ veor @b[6], @b[6], @b[2]
+ veor @b[5], @b[5], @b[0]
+
+ veor @b[6], @b[6], @b[3]
+ veor @b[3], @b[3], @b[7]
+ veor @b[7], @b[7], @b[5]
+ veor @b[3], @b[3], @b[4]
+ veor @b[4], @b[4], @b[5]
+
+ veor @b[2], @b[2], @b[7]
+ veor @b[3], @b[3], @b[1]
+ veor @b[1], @b[1], @b[5]
+___
+}
+
+sub OutBasisChange {
+# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb
+# output in lsb > [b6, b1, b2, b4, b7, b0, b3, b5] < msb
+my @b=@_[0..7];
+$code.=<<___;
+ veor @b[0], @b[0], @b[6]
+ veor @b[1], @b[1], @b[4]
+ veor @b[4], @b[4], @b[6]
+ veor @b[2], @b[2], @b[0]
+ veor @b[6], @b[6], @b[1]
+
+ veor @b[1], @b[1], @b[5]
+ veor @b[5], @b[5], @b[3]
+ veor @b[3], @b[3], @b[7]
+ veor @b[7], @b[7], @b[5]
+ veor @b[2], @b[2], @b[5]
+
+ veor @b[4], @b[4], @b[7]
+___
+}
+
+sub InvSbox {
+# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb
+# output in lsb > [b0, b1, b6, b4, b2, b7, b3, b5] < msb
+my @b=@_[0..7];
+my @t=@_[8..11];
+my @s=@_[12..15];
+ &InvInBasisChange (@b);
+ &Inv_GF256 (@b[5,1,2,6,3,7,0,4],@t,@s);
+ &InvOutBasisChange (@b[3,7,0,4,5,1,2,6]);
+}
+
+sub InvInBasisChange { # OutBasisChange in reverse (with twist)
+my @b=@_[5,1,2,6,3,7,0,4];
+$code.=<<___
+ veor @b[1], @b[1], @b[7]
+ veor @b[4], @b[4], @b[7]
+
+ veor @b[7], @b[7], @b[5]
+ veor @b[1], @b[1], @b[3]
+ veor @b[2], @b[2], @b[5]
+ veor @b[3], @b[3], @b[7]
+
+ veor @b[6], @b[6], @b[1]
+ veor @b[2], @b[2], @b[0]
+ veor @b[5], @b[5], @b[3]
+ veor @b[4], @b[4], @b[6]
+ veor @b[0], @b[0], @b[6]
+ veor @b[1], @b[1], @b[4]
+___
+}
+
+sub InvOutBasisChange { # InBasisChange in reverse
+my @b=@_[2,5,7,3,6,1,0,4];
+$code.=<<___;
+ veor @b[1], @b[1], @b[5]
+ veor @b[2], @b[2], @b[7]
+
+ veor @b[3], @b[3], @b[1]
+ veor @b[4], @b[4], @b[5]
+ veor @b[7], @b[7], @b[5]
+ veor @b[3], @b[3], @b[4]
+ veor @b[5], @b[5], @b[0]
+ veor @b[3], @b[3], @b[7]
+ veor @b[6], @b[6], @b[2]
+ veor @b[2], @b[2], @b[1]
+ veor @b[6], @b[6], @b[3]
+
+ veor @b[3], @b[3], @b[0]
+ veor @b[5], @b[5], @b[6]
+___
+}
+
+sub Mul_GF4 {
+#;*************************************************************
+#;* Mul_GF4: Input x0-x1,y0-y1 Output x0-x1 Temp t0 (8) *
+#;*************************************************************
+my ($x0,$x1,$y0,$y1,$t0,$t1)=@_;
+$code.=<<___;
+ veor $t0, $y0, $y1
+ vand $t0, $t0, $x0
+ veor $x0, $x0, $x1
+ vand $t1, $x1, $y0
+ vand $x0, $x0, $y1
+ veor $x1, $t1, $t0
+ veor $x0, $x0, $t1
+___
+}
+
+sub Mul_GF4_N { # not used, see next subroutine
+# multiply and scale by N
+my ($x0,$x1,$y0,$y1,$t0)=@_;
+$code.=<<___;
+ veor $t0, $y0, $y1
+ vand $t0, $t0, $x0
+ veor $x0, $x0, $x1
+ vand $x1, $x1, $y0
+ vand $x0, $x0, $y1
+ veor $x1, $x1, $x0
+ veor $x0, $x0, $t0
+___
+}
+
+sub Mul_GF4_N_GF4 {
+# interleaved Mul_GF4_N and Mul_GF4
+my ($x0,$x1,$y0,$y1,$t0,
+ $x2,$x3,$y2,$y3,$t1)=@_;
+$code.=<<___;
+ veor $t0, $y0, $y1
+ veor $t1, $y2, $y3
+ vand $t0, $t0, $x0
+ vand $t1, $t1, $x2
+ veor $x0, $x0, $x1
+ veor $x2, $x2, $x3
+ vand $x1, $x1, $y0
+ vand $x3, $x3, $y2
+ vand $x0, $x0, $y1
+ vand $x2, $x2, $y3
+ veor $x1, $x1, $x0
+ veor $x2, $x2, $x3
+ veor $x0, $x0, $t0
+ veor $x3, $x3, $t1
+___
+}
+sub Mul_GF16_2 {
+my @x=@_[0..7];
+my @y=@_[8..11];
+my @t=@_[12..15];
+$code.=<<___;
+ veor @t[0], @x[0], @x[2]
+ veor @t[1], @x[1], @x[3]
+___
+ &Mul_GF4 (@x[0], @x[1], @y[0], @y[1], @t[2..3]);
+$code.=<<___;
+ veor @y[0], @y[0], @y[2]
+ veor @y[1], @y[1], @y[3]
+___
+ Mul_GF4_N_GF4 (@t[0], @t[1], @y[0], @y[1], @t[3],
+ @x[2], @x[3], @y[2], @y[3], @t[2]);
+$code.=<<___;
+ veor @x[0], @x[0], @t[0]
+ veor @x[2], @x[2], @t[0]
+ veor @x[1], @x[1], @t[1]
+ veor @x[3], @x[3], @t[1]
+
+ veor @t[0], @x[4], @x[6]
+ veor @t[1], @x[5], @x[7]
+___
+ &Mul_GF4_N_GF4 (@t[0], @t[1], @y[0], @y[1], @t[3],
+ @x[6], @x[7], @y[2], @y[3], @t[2]);
+$code.=<<___;
+ veor @y[0], @y[0], @y[2]
+ veor @y[1], @y[1], @y[3]
+___
+ &Mul_GF4 (@x[4], @x[5], @y[0], @y[1], @t[2..3]);
+$code.=<<___;
+ veor @x[4], @x[4], @t[0]
+ veor @x[6], @x[6], @t[0]
+ veor @x[5], @x[5], @t[1]
+ veor @x[7], @x[7], @t[1]
+___
+}
+sub Inv_GF256 {
+#;********************************************************************
+#;* Inv_GF256: Input x0-x7 Output x0-x7 Temp t0-t3,s0-s3 (144) *
+#;********************************************************************
+my @x=@_[0..7];
+my @t=@_[8..11];
+my @s=@_[12..15];
+# direct optimizations from hardware
+$code.=<<___;
+ veor @t[3], @x[4], @x[6]
+ veor @t[2], @x[5], @x[7]
+ veor @t[1], @x[1], @x[3]
+ veor @s[1], @x[7], @x[6]
+ vmov @t[0], @t[2]
+ veor @s[0], @x[0], @x[2]
+
+ vorr @t[2], @t[2], @t[1]
+ veor @s[3], @t[3], @t[0]
+ vand @s[2], @t[3], @s[0]
+ vorr @t[3], @t[3], @s[0]
+ veor @s[0], @s[0], @t[1]
+ vand @t[0], @t[0], @t[1]
+ veor @t[1], @x[3], @x[2]
+ vand @s[3], @s[3], @s[0]
+ vand @s[1], @s[1], @t[1]
+ veor @t[1], @x[4], @x[5]
+ veor @s[0], @x[1], @x[0]
+ veor @t[3], @t[3], @s[1]
+ veor @t[2], @t[2], @s[1]
+ vand @s[1], @t[1], @s[0]
+ vorr @t[1], @t[1], @s[0]
+ veor @t[3], @t[3], @s[3]
+ veor @t[0], @t[0], @s[1]
+ veor @t[2], @t[2], @s[2]
+ veor @t[1], @t[1], @s[3]
+ veor @t[0], @t[0], @s[2]
+ vand @s[0], @x[7], @x[3]
+ veor @t[1], @t[1], @s[2]
+ vand @s[1], @x[6], @x[2]
+ vand @s[2], @x[5], @x[1]
+ vorr @s[3], @x[4], @x[0]
+ veor @t[3], @t[3], @s[0]
+ veor @t[1], @t[1], @s[2]
+ veor @t[0], @t[0], @s[3]
+ veor @t[2], @t[2], @s[1]
+
+ @ Inv_GF16 \t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3
+
+ @ new smaller inversion
+
+ vand @s[2], @t[3], @t[1]
+ vmov @s[0], @t[0]
+
+ veor @s[1], @t[2], @s[2]
+ veor @s[3], @t[0], @s[2]
+ veor @s[2], @t[0], @s[2] @ @s[2]=@s[3]
+
+ vbsl @s[1], @t[1], @t[0]
+ vbsl @s[3], @t[3], @t[2]
+ veor @t[3], @t[3], @t[2]
+
+ vbsl @s[0], @s[1], @s[2]
+ vbsl @t[0], @s[2], @s[1]
+
+ vand @s[2], @s[0], @s[3]
+ veor @t[1], @t[1], @t[0]
+
+ veor @s[2], @s[2], @t[3]
+___
+# output in s3, s2, s1, t1
+
+# Mul_GF16_2 \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \t2, \t3, \t0, \t1, \s0, \s1, \s2, \s3
+
+# Mul_GF16_2 \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
+ &Mul_GF16_2(@x,@s[3,2,1],@t[1],@s[0],@t[0,2,3]);
+
+### output msb > [x3,x2,x1,x0,x7,x6,x5,x4] < lsb
+}
+
+# AES linear components
+
+sub ShiftRows {
+my @x=@_[0..7];
+my @t=@_[8..11];
+my $mask=pop;
+$code.=<<___;
+ vldmia $key!, {@t[0]-@t[3]}
+ veor @t[0], @t[0], @x[0]
+ veor @t[1], @t[1], @x[1]
+ vtbl.8 `&Dlo(@x[0])`, {@t[0]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[0])`, {@t[0]}, `&Dhi($mask)`
+ vldmia $key!, {@t[0]}
+ veor @t[2], @t[2], @x[2]
+ vtbl.8 `&Dlo(@x[1])`, {@t[1]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[1])`, {@t[1]}, `&Dhi($mask)`
+ vldmia $key!, {@t[1]}
+ veor @t[3], @t[3], @x[3]
+ vtbl.8 `&Dlo(@x[2])`, {@t[2]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[2])`, {@t[2]}, `&Dhi($mask)`
+ vldmia $key!, {@t[2]}
+ vtbl.8 `&Dlo(@x[3])`, {@t[3]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[3])`, {@t[3]}, `&Dhi($mask)`
+ vldmia $key!, {@t[3]}
+ veor @t[0], @t[0], @x[4]
+ veor @t[1], @t[1], @x[5]
+ vtbl.8 `&Dlo(@x[4])`, {@t[0]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[4])`, {@t[0]}, `&Dhi($mask)`
+ veor @t[2], @t[2], @x[6]
+ vtbl.8 `&Dlo(@x[5])`, {@t[1]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[5])`, {@t[1]}, `&Dhi($mask)`
+ veor @t[3], @t[3], @x[7]
+ vtbl.8 `&Dlo(@x[6])`, {@t[2]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[6])`, {@t[2]}, `&Dhi($mask)`
+ vtbl.8 `&Dlo(@x[7])`, {@t[3]}, `&Dlo($mask)`
+ vtbl.8 `&Dhi(@x[7])`, {@t[3]}, `&Dhi($mask)`
+___
+}
+
+sub MixColumns {
+# modified to emit output in order suitable for feeding back to aesenc[last]
+my @x=@_[0..7];
+my @t=@_[8..15];
+my $inv=@_[16]; # optional
+$code.=<<___;
+ vext.8 @t[0], @x[0], @x[0], #12 @ x0 <<< 32
+ vext.8 @t[1], @x[1], @x[1], #12
+ veor @x[0], @x[0], @t[0] @ x0 ^ (x0 <<< 32)
+ vext.8 @t[2], @x[2], @x[2], #12
+ veor @x[1], @x[1], @t[1]
+ vext.8 @t[3], @x[3], @x[3], #12
+ veor @x[2], @x[2], @t[2]
+ vext.8 @t[4], @x[4], @x[4], #12
+ veor @x[3], @x[3], @t[3]
+ vext.8 @t[5], @x[5], @x[5], #12
+ veor @x[4], @x[4], @t[4]
+ vext.8 @t[6], @x[6], @x[6], #12
+ veor @x[5], @x[5], @t[5]
+ vext.8 @t[7], @x[7], @x[7], #12
+ veor @x[6], @x[6], @t[6]
+
+ veor @t[1], @t[1], @x[0]
+ veor @x[7], @x[7], @t[7]
+ vext.8 @x[0], @x[0], @x[0], #8 @ (x0 ^ (x0 <<< 32)) <<< 64)
+ veor @t[2], @t[2], @x[1]
+ veor @t[0], @t[0], @x[7]
+ veor @t[1], @t[1], @x[7]
+ vext.8 @x[1], @x[1], @x[1], #8
+ veor @t[5], @t[5], @x[4]
+ veor @x[0], @x[0], @t[0]
+ veor @t[6], @t[6], @x[5]
+ veor @x[1], @x[1], @t[1]
+ vext.8 @t[0], @x[4], @x[4], #8
+ veor @t[4], @t[4], @x[3]
+ vext.8 @t[1], @x[5], @x[5], #8
+ veor @t[7], @t[7], @x[6]
+ vext.8 @x[4], @x[3], @x[3], #8
+ veor @t[3], @t[3], @x[2]
+ vext.8 @x[5], @x[7], @x[7], #8
+ veor @t[4], @t[4], @x[7]
+ vext.8 @x[3], @x[6], @x[6], #8
+ veor @t[3], @t[3], @x[7]
+ vext.8 @x[6], @x[2], @x[2], #8
+ veor @x[7], @t[1], @t[5]
+___
+$code.=<<___ if (!$inv);
+ veor @x[2], @t[0], @t[4]
+ veor @x[4], @x[4], @t[3]
+ veor @x[5], @x[5], @t[7]
+ veor @x[3], @x[3], @t[6]
+ @ vmov @x[2], @t[0]
+ veor @x[6], @x[6], @t[2]
+ @ vmov @x[7], @t[1]
+___
+$code.=<<___ if ($inv);
+ veor @t[3], @t[3], @x[4]
+ veor @x[5], @x[5], @t[7]
+ veor @x[2], @x[3], @t[6]
+ veor @x[3], @t[0], @t[4]
+ veor @x[4], @x[6], @t[2]
+ vmov @x[6], @t[3]
+ @ vmov @x[7], @t[1]
+___
+}
+
+sub InvMixColumns_orig {
+my @x=@_[0..7];
+my @t=@_[8..15];
+
+$code.=<<___;
+ @ multiplication by 0x0e
+ vext.8 @t[7], @x[7], @x[7], #12
+ vmov @t[2], @x[2]
+ veor @x[2], @x[2], @x[5] @ 2 5
+ veor @x[7], @x[7], @x[5] @ 7 5
+ vext.8 @t[0], @x[0], @x[0], #12
+ vmov @t[5], @x[5]
+ veor @x[5], @x[5], @x[0] @ 5 0 [1]
+ veor @x[0], @x[0], @x[1] @ 0 1
+ vext.8 @t[1], @x[1], @x[1], #12
+ veor @x[1], @x[1], @x[2] @ 1 25
+ veor @x[0], @x[0], @x[6] @ 01 6 [2]
+ vext.8 @t[3], @x[3], @x[3], #12
+ veor @x[1], @x[1], @x[3] @ 125 3 [4]
+ veor @x[2], @x[2], @x[0] @ 25 016 [3]
+ veor @x[3], @x[3], @x[7] @ 3 75
+ veor @x[7], @x[7], @x[6] @ 75 6 [0]
+ vext.8 @t[6], @x[6], @x[6], #12
+ vmov @t[4], @x[4]
+ veor @x[6], @x[6], @x[4] @ 6 4
+ veor @x[4], @x[4], @x[3] @ 4 375 [6]
+ veor @x[3], @x[3], @x[7] @ 375 756=36
+ veor @x[6], @x[6], @t[5] @ 64 5 [7]
+ veor @x[3], @x[3], @t[2] @ 36 2
+ vext.8 @t[5], @t[5], @t[5], #12
+ veor @x[3], @x[3], @t[4] @ 362 4 [5]
+___
+ my @y = @x[7,5,0,2,1,3,4,6];
+$code.=<<___;
+ @ multiplication by 0x0b
+ veor @y[1], @y[1], @y[0]
+ veor @y[0], @y[0], @t[0]
+ vext.8 @t[2], @t[2], @t[2], #12
+ veor @y[1], @y[1], @t[1]
+ veor @y[0], @y[0], @t[5]
+ vext.8 @t[4], @t[4], @t[4], #12
+ veor @y[1], @y[1], @t[6]
+ veor @y[0], @y[0], @t[7]
+ veor @t[7], @t[7], @t[6] @ clobber t[7]
+
+ veor @y[3], @y[3], @t[0]
+ veor @y[1], @y[1], @y[0]
+ vext.8 @t[0], @t[0], @t[0], #12
+ veor @y[2], @y[2], @t[1]
+ veor @y[4], @y[4], @t[1]
+ vext.8 @t[1], @t[1], @t[1], #12
+ veor @y[2], @y[2], @t[2]
+ veor @y[3], @y[3], @t[2]
+ veor @y[5], @y[5], @t[2]
+ veor @y[2], @y[2], @t[7]
+ vext.8 @t[2], @t[2], @t[2], #12
+ veor @y[3], @y[3], @t[3]
+ veor @y[6], @y[6], @t[3]
+ veor @y[4], @y[4], @t[3]
+ veor @y[7], @y[7], @t[4]
+ vext.8 @t[3], @t[3], @t[3], #12
+ veor @y[5], @y[5], @t[4]
+ veor @y[7], @y[7], @t[7]
+ veor @t[7], @t[7], @t[5] @ clobber t[7] even more
+ veor @y[3], @y[3], @t[5]
+ veor @y[4], @y[4], @t[4]
+
+ veor @y[5], @y[5], @t[7]
+ vext.8 @t[4], @t[4], @t[4], #12
+ veor @y[6], @y[6], @t[7]
+ veor @y[4], @y[4], @t[7]
+
+ veor @t[7], @t[7], @t[5]
+ vext.8 @t[5], @t[5], @t[5], #12
+
+ @ multiplication by 0x0d
+ veor @y[4], @y[4], @y[7]
+ veor @t[7], @t[7], @t[6] @ restore t[7]
+ veor @y[7], @y[7], @t[4]
+ vext.8 @t[6], @t[6], @t[6], #12
+ veor @y[2], @y[2], @t[0]
+ veor @y[7], @y[7], @t[5]
+ vext.8 @t[7], @t[7], @t[7], #12
+ veor @y[2], @y[2], @t[2]
+
+ veor @y[3], @y[3], @y[1]
+ veor @y[1], @y[1], @t[1]
+ veor @y[0], @y[0], @t[0]
+ veor @y[3], @y[3], @t[0]
+ veor @y[1], @y[1], @t[5]
+ veor @y[0], @y[0], @t[5]
+ vext.8 @t[0], @t[0], @t[0], #12
+ veor @y[1], @y[1], @t[7]
+ veor @y[0], @y[0], @t[6]
+ veor @y[3], @y[3], @y[1]
+ veor @y[4], @y[4], @t[1]
+ vext.8 @t[1], @t[1], @t[1], #12
+
+ veor @y[7], @y[7], @t[7]
+ veor @y[4], @y[4], @t[2]
+ veor @y[5], @y[5], @t[2]
+ veor @y[2], @y[2], @t[6]
+ veor @t[6], @t[6], @t[3] @ clobber t[6]
+ vext.8 @t[2], @t[2], @t[2], #12
+ veor @y[4], @y[4], @y[7]
+ veor @y[3], @y[3], @t[6]
+
+ veor @y[6], @y[6], @t[6]
+ veor @y[5], @y[5], @t[5]
+ vext.8 @t[5], @t[5], @t[5], #12
+ veor @y[6], @y[6], @t[4]
+ vext.8 @t[4], @t[4], @t[4], #12
+ veor @y[5], @y[5], @t[6]
+ veor @y[6], @y[6], @t[7]
+ vext.8 @t[7], @t[7], @t[7], #12
+ veor @t[6], @t[6], @t[3] @ restore t[6]
+ vext.8 @t[3], @t[3], @t[3], #12
+
+ @ multiplication by 0x09
+ veor @y[4], @y[4], @y[1]
+ veor @t[1], @t[1], @y[1] @ t[1]=y[1]
+ veor @t[0], @t[0], @t[5] @ clobber t[0]
+ vext.8 @t[6], @t[6], @t[6], #12
+ veor @t[1], @t[1], @t[5]
+ veor @y[3], @y[3], @t[0]
+ veor @t[0], @t[0], @y[0] @ t[0]=y[0]
+ veor @t[1], @t[1], @t[6]
+ veor @t[6], @t[6], @t[7] @ clobber t[6]
+ veor @y[4], @y[4], @t[1]
+ veor @y[7], @y[7], @t[4]
+ veor @y[6], @y[6], @t[3]
+ veor @y[5], @y[5], @t[2]
+ veor @t[4], @t[4], @y[4] @ t[4]=y[4]
+ veor @t[3], @t[3], @y[3] @ t[3]=y[3]
+ veor @t[5], @t[5], @y[5] @ t[5]=y[5]
+ veor @t[2], @t[2], @y[2] @ t[2]=y[2]
+ veor @t[3], @t[3], @t[7]
+ veor @XMM[5], @t[5], @t[6]
+ veor @XMM[6], @t[6], @y[6] @ t[6]=y[6]
+ veor @XMM[2], @t[2], @t[6]
+ veor @XMM[7], @t[7], @y[7] @ t[7]=y[7]
+
+ vmov @XMM[0], @t[0]
+ vmov @XMM[1], @t[1]
+ @ vmov @XMM[2], @t[2]
+ vmov @XMM[3], @t[3]
+ vmov @XMM[4], @t[4]
+ @ vmov @XMM[5], @t[5]
+ @ vmov @XMM[6], @t[6]
+ @ vmov @XMM[7], @t[7]
+___
+}
+
+sub InvMixColumns {
+my @x=@_[0..7];
+my @t=@_[8..15];
+
+# Thanks to Jussi Kivilinna for providing pointer to
+#
+# | 0e 0b 0d 09 | | 02 03 01 01 | | 05 00 04 00 |
+# | 09 0e 0b 0d | = | 01 02 03 01 | x | 00 05 00 04 |
+# | 0d 09 0e 0b | | 01 01 02 03 | | 04 00 05 00 |
+# | 0b 0d 09 0e | | 03 01 01 02 | | 00 04 00 05 |
+
+$code.=<<___;
+ @ multiplication by 0x05-0x00-0x04-0x00
+ vext.8 @t[0], @x[0], @x[0], #8
+ vext.8 @t[6], @x[6], @x[6], #8
+ vext.8 @t[7], @x[7], @x[7], #8
+ veor @t[0], @t[0], @x[0]
+ vext.8 @t[1], @x[1], @x[1], #8
+ veor @t[6], @t[6], @x[6]
+ vext.8 @t[2], @x[2], @x[2], #8
+ veor @t[7], @t[7], @x[7]
+ vext.8 @t[3], @x[3], @x[3], #8
+ veor @t[1], @t[1], @x[1]
+ vext.8 @t[4], @x[4], @x[4], #8
+ veor @t[2], @t[2], @x[2]
+ vext.8 @t[5], @x[5], @x[5], #8
+ veor @t[3], @t[3], @x[3]
+ veor @t[4], @t[4], @x[4]
+ veor @t[5], @t[5], @x[5]
+
+ veor @x[0], @x[0], @t[6]
+ veor @x[1], @x[1], @t[6]
+ veor @x[2], @x[2], @t[0]
+ veor @x[4], @x[4], @t[2]
+ veor @x[3], @x[3], @t[1]
+ veor @x[1], @x[1], @t[7]
+ veor @x[2], @x[2], @t[7]
+ veor @x[4], @x[4], @t[6]
+ veor @x[5], @x[5], @t[3]
+ veor @x[3], @x[3], @t[6]
+ veor @x[6], @x[6], @t[4]
+ veor @x[4], @x[4], @t[7]
+ veor @x[5], @x[5], @t[7]
+ veor @x[7], @x[7], @t[5]
+___
+ &MixColumns (@x,@t,1); # flipped 2<->3 and 4<->6
+}
+
+sub swapmove {
+my ($a,$b,$n,$mask,$t)=@_;
+$code.=<<___;
+ vshr.u64 $t, $b, #$n
+ veor $t, $t, $a
+ vand $t, $t, $mask
+ veor $a, $a, $t
+ vshl.u64 $t, $t, #$n
+ veor $b, $b, $t
+___
+}
+sub swapmove2x {
+my ($a0,$b0,$a1,$b1,$n,$mask,$t0,$t1)=@_;
+$code.=<<___;
+ vshr.u64 $t0, $b0, #$n
+ vshr.u64 $t1, $b1, #$n
+ veor $t0, $t0, $a0
+ veor $t1, $t1, $a1
+ vand $t0, $t0, $mask
+ vand $t1, $t1, $mask
+ veor $a0, $a0, $t0
+ vshl.u64 $t0, $t0, #$n
+ veor $a1, $a1, $t1
+ vshl.u64 $t1, $t1, #$n
+ veor $b0, $b0, $t0
+ veor $b1, $b1, $t1
+___
+}
+
+sub bitslice {
+my @x=reverse(@_[0..7]);
+my ($t0,$t1,$t2,$t3)=@_[8..11];
+$code.=<<___;
+ vmov.i8 $t0,#0x55 @ compose .LBS0
+ vmov.i8 $t1,#0x33 @ compose .LBS1
+___
+ &swapmove2x(@x[0,1,2,3],1,$t0,$t2,$t3);
+ &swapmove2x(@x[4,5,6,7],1,$t0,$t2,$t3);
+$code.=<<___;
+ vmov.i8 $t0,#0x0f @ compose .LBS2
+___
+ &swapmove2x(@x[0,2,1,3],2,$t1,$t2,$t3);
+ &swapmove2x(@x[4,6,5,7],2,$t1,$t2,$t3);
+
+ &swapmove2x(@x[0,4,1,5],4,$t0,$t2,$t3);
+ &swapmove2x(@x[2,6,3,7],4,$t0,$t2,$t3);
+}
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+
+# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
+# define VFP_ABI_POP vldmia sp!,{d8-d15}
+# define VFP_ABI_FRAME 0x40
+#else
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+# define VFP_ABI_FRAME 0
+# define BSAES_ASM_EXTENDED_KEY
+# define XTS_CHAIN_TWEAK
+# define __ARM_ARCH__ 7
+#endif
+
+#ifdef __thumb__
+# define adrl adr
+#endif
+
+#if __ARM_ARCH__>=7
+.text
+.syntax unified @ ARMv7-capable assembler is expected to handle this
+#ifdef __thumb2__
+.thumb
+#else
+.code 32
+#endif
+
+.fpu neon
+
+.type _bsaes_decrypt8,%function
+.align 4
+_bsaes_decrypt8:
+ adr $const,_bsaes_decrypt8
+ vldmia $key!, {@XMM[9]} @ round 0 key
+ add $const,$const,#.LM0ISR-_bsaes_decrypt8
+
+ vldmia $const!, {@XMM[8]} @ .LM0ISR
+ veor @XMM[10], @XMM[0], @XMM[9] @ xor with round0 key
+ veor @XMM[11], @XMM[1], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[0])`, {@XMM[10]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[0])`, {@XMM[10]}, `&Dhi(@XMM[8])`
+ veor @XMM[12], @XMM[2], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[1])`, {@XMM[11]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[1])`, {@XMM[11]}, `&Dhi(@XMM[8])`
+ veor @XMM[13], @XMM[3], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[2])`, {@XMM[12]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[2])`, {@XMM[12]}, `&Dhi(@XMM[8])`
+ veor @XMM[14], @XMM[4], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[3])`, {@XMM[13]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[3])`, {@XMM[13]}, `&Dhi(@XMM[8])`
+ veor @XMM[15], @XMM[5], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[4])`, {@XMM[14]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[4])`, {@XMM[14]}, `&Dhi(@XMM[8])`
+ veor @XMM[10], @XMM[6], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[5])`, {@XMM[15]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[5])`, {@XMM[15]}, `&Dhi(@XMM[8])`
+ veor @XMM[11], @XMM[7], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[6])`, {@XMM[10]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[6])`, {@XMM[10]}, `&Dhi(@XMM[8])`
+ vtbl.8 `&Dlo(@XMM[7])`, {@XMM[11]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[7])`, {@XMM[11]}, `&Dhi(@XMM[8])`
+___
+ &bitslice (@XMM[0..7, 8..11]);
+$code.=<<___;
+ sub $rounds,$rounds,#1
+ b .Ldec_sbox
+.align 4
+.Ldec_loop:
+___
+ &ShiftRows (@XMM[0..7, 8..12]);
+$code.=".Ldec_sbox:\n";
+ &InvSbox (@XMM[0..7, 8..15]);
+$code.=<<___;
+ subs $rounds,$rounds,#1
+ bcc .Ldec_done
+___
+ &InvMixColumns (@XMM[0,1,6,4,2,7,3,5, 8..15]);
+$code.=<<___;
+ vldmia $const, {@XMM[12]} @ .LISR
+ ite eq @ Thumb2 thing, sanity check in ARM
+ addeq $const,$const,#0x10
+ bne .Ldec_loop
+ vldmia $const, {@XMM[12]} @ .LISRM0
+ b .Ldec_loop
+.align 4
+.Ldec_done:
+___
+ &bitslice (@XMM[0,1,6,4,2,7,3,5, 8..11]);
+$code.=<<___;
+ vldmia $key, {@XMM[8]} @ last round key
+ veor @XMM[6], @XMM[6], @XMM[8]
+ veor @XMM[4], @XMM[4], @XMM[8]
+ veor @XMM[2], @XMM[2], @XMM[8]
+ veor @XMM[7], @XMM[7], @XMM[8]
+ veor @XMM[3], @XMM[3], @XMM[8]
+ veor @XMM[5], @XMM[5], @XMM[8]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ veor @XMM[1], @XMM[1], @XMM[8]
+ bx lr
+.size _bsaes_decrypt8,.-_bsaes_decrypt8
+
+.type _bsaes_const,%object
+.align 6
+_bsaes_const:
+.LM0ISR: @ InvShiftRows constants
+ .quad 0x0a0e0206070b0f03, 0x0004080c0d010509
+.LISR:
+ .quad 0x0504070602010003, 0x0f0e0d0c080b0a09
+.LISRM0:
+ .quad 0x01040b0e0205080f, 0x0306090c00070a0d
+.LM0SR: @ ShiftRows constants
+ .quad 0x0a0e02060f03070b, 0x0004080c05090d01
+.LSR:
+ .quad 0x0504070600030201, 0x0f0e0d0c0a09080b
+.LSRM0:
+ .quad 0x0304090e00050a0f, 0x01060b0c0207080d
+.LM0:
+ .quad 0x02060a0e03070b0f, 0x0004080c0105090d
+.LREVM0SR:
+ .quad 0x090d01050c000408, 0x03070b0f060a0e02
+.asciz "Bit-sliced AES for NEON, CRYPTOGAMS by <appro\@openssl.org>"
+.align 6
+.size _bsaes_const,.-_bsaes_const
+
+.type _bsaes_encrypt8,%function
+.align 4
+_bsaes_encrypt8:
+ adr $const,_bsaes_encrypt8
+ vldmia $key!, {@XMM[9]} @ round 0 key
+ sub $const,$const,#_bsaes_encrypt8-.LM0SR
+
+ vldmia $const!, {@XMM[8]} @ .LM0SR
+_bsaes_encrypt8_alt:
+ veor @XMM[10], @XMM[0], @XMM[9] @ xor with round0 key
+ veor @XMM[11], @XMM[1], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[0])`, {@XMM[10]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[0])`, {@XMM[10]}, `&Dhi(@XMM[8])`
+ veor @XMM[12], @XMM[2], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[1])`, {@XMM[11]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[1])`, {@XMM[11]}, `&Dhi(@XMM[8])`
+ veor @XMM[13], @XMM[3], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[2])`, {@XMM[12]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[2])`, {@XMM[12]}, `&Dhi(@XMM[8])`
+ veor @XMM[14], @XMM[4], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[3])`, {@XMM[13]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[3])`, {@XMM[13]}, `&Dhi(@XMM[8])`
+ veor @XMM[15], @XMM[5], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[4])`, {@XMM[14]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[4])`, {@XMM[14]}, `&Dhi(@XMM[8])`
+ veor @XMM[10], @XMM[6], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[5])`, {@XMM[15]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[5])`, {@XMM[15]}, `&Dhi(@XMM[8])`
+ veor @XMM[11], @XMM[7], @XMM[9]
+ vtbl.8 `&Dlo(@XMM[6])`, {@XMM[10]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[6])`, {@XMM[10]}, `&Dhi(@XMM[8])`
+ vtbl.8 `&Dlo(@XMM[7])`, {@XMM[11]}, `&Dlo(@XMM[8])`
+ vtbl.8 `&Dhi(@XMM[7])`, {@XMM[11]}, `&Dhi(@XMM[8])`
+_bsaes_encrypt8_bitslice:
+___
+ &bitslice (@XMM[0..7, 8..11]);
+$code.=<<___;
+ sub $rounds,$rounds,#1
+ b .Lenc_sbox
+.align 4
+.Lenc_loop:
+___
+ &ShiftRows (@XMM[0..7, 8..12]);
+$code.=".Lenc_sbox:\n";
+ &Sbox (@XMM[0..7, 8..15]);
+$code.=<<___;
+ subs $rounds,$rounds,#1
+ bcc .Lenc_done
+___
+ &MixColumns (@XMM[0,1,4,6,3,7,2,5, 8..15]);
+$code.=<<___;
+ vldmia $const, {@XMM[12]} @ .LSR
+ ite eq @ Thumb2 thing, samity check in ARM
+ addeq $const,$const,#0x10
+ bne .Lenc_loop
+ vldmia $const, {@XMM[12]} @ .LSRM0
+ b .Lenc_loop
+.align 4
+.Lenc_done:
+___
+ # output in lsb > [t0, t1, t4, t6, t3, t7, t2, t5] < msb
+ &bitslice (@XMM[0,1,4,6,3,7,2,5, 8..11]);
+$code.=<<___;
+ vldmia $key, {@XMM[8]} @ last round key
+ veor @XMM[4], @XMM[4], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[8]
+ veor @XMM[3], @XMM[3], @XMM[8]
+ veor @XMM[7], @XMM[7], @XMM[8]
+ veor @XMM[2], @XMM[2], @XMM[8]
+ veor @XMM[5], @XMM[5], @XMM[8]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ veor @XMM[1], @XMM[1], @XMM[8]
+ bx lr
+.size _bsaes_encrypt8,.-_bsaes_encrypt8
+___
+}
+{
+my ($out,$inp,$rounds,$const)=("r12","r4","r5","r6");
+
+sub bitslice_key {
+my @x=reverse(@_[0..7]);
+my ($bs0,$bs1,$bs2,$t2,$t3)=@_[8..12];
+
+ &swapmove (@x[0,1],1,$bs0,$t2,$t3);
+$code.=<<___;
+ @ &swapmove(@x[2,3],1,$t0,$t2,$t3);
+ vmov @x[2], @x[0]
+ vmov @x[3], @x[1]
+___
+ #&swapmove2x(@x[4,5,6,7],1,$t0,$t2,$t3);
+
+ &swapmove2x (@x[0,2,1,3],2,$bs1,$t2,$t3);
+$code.=<<___;
+ @ &swapmove2x(@x[4,6,5,7],2,$t1,$t2,$t3);
+ vmov @x[4], @x[0]
+ vmov @x[6], @x[2]
+ vmov @x[5], @x[1]
+ vmov @x[7], @x[3]
+___
+ &swapmove2x (@x[0,4,1,5],4,$bs2,$t2,$t3);
+ &swapmove2x (@x[2,6,3,7],4,$bs2,$t2,$t3);
+}
+
+$code.=<<___;
+.type _bsaes_key_convert,%function
+.align 4
+_bsaes_key_convert:
+ adr $const,_bsaes_key_convert
+ vld1.8 {@XMM[7]}, [$inp]! @ load round 0 key
+ sub $const,$const,#_bsaes_key_convert-.LM0
+ vld1.8 {@XMM[15]}, [$inp]! @ load round 1 key
+
+ vmov.i8 @XMM[8], #0x01 @ bit masks
+ vmov.i8 @XMM[9], #0x02
+ vmov.i8 @XMM[10], #0x04
+ vmov.i8 @XMM[11], #0x08
+ vmov.i8 @XMM[12], #0x10
+ vmov.i8 @XMM[13], #0x20
+ vldmia $const, {@XMM[14]} @ .LM0
+
+#ifdef __ARMEL__
+ vrev32.8 @XMM[7], @XMM[7]
+ vrev32.8 @XMM[15], @XMM[15]
+#endif
+ sub $rounds,$rounds,#1
+ vstmia $out!, {@XMM[7]} @ save round 0 key
+ b .Lkey_loop
+
+.align 4
+.Lkey_loop:
+ vtbl.8 `&Dlo(@XMM[7])`,{@XMM[15]},`&Dlo(@XMM[14])`
+ vtbl.8 `&Dhi(@XMM[7])`,{@XMM[15]},`&Dhi(@XMM[14])`
+ vmov.i8 @XMM[6], #0x40
+ vmov.i8 @XMM[15], #0x80
+
+ vtst.8 @XMM[0], @XMM[7], @XMM[8]
+ vtst.8 @XMM[1], @XMM[7], @XMM[9]
+ vtst.8 @XMM[2], @XMM[7], @XMM[10]
+ vtst.8 @XMM[3], @XMM[7], @XMM[11]
+ vtst.8 @XMM[4], @XMM[7], @XMM[12]
+ vtst.8 @XMM[5], @XMM[7], @XMM[13]
+ vtst.8 @XMM[6], @XMM[7], @XMM[6]
+ vtst.8 @XMM[7], @XMM[7], @XMM[15]
+ vld1.8 {@XMM[15]}, [$inp]! @ load next round key
+ vmvn @XMM[0], @XMM[0] @ "pnot"
+ vmvn @XMM[1], @XMM[1]
+ vmvn @XMM[5], @XMM[5]
+ vmvn @XMM[6], @XMM[6]
+#ifdef __ARMEL__
+ vrev32.8 @XMM[15], @XMM[15]
+#endif
+ subs $rounds,$rounds,#1
+ vstmia $out!,{@XMM[0]-@XMM[7]} @ write bit-sliced round key
+ bne .Lkey_loop
+
+ vmov.i8 @XMM[7],#0x63 @ compose .L63
+ @ don't save last round key
+ bx lr
+.size _bsaes_key_convert,.-_bsaes_key_convert
+___
+}
+
+if (0) { # following four functions are unsupported interface
+ # used for benchmarking...
+$code.=<<___;
+.globl bsaes_enc_key_convert
+.type bsaes_enc_key_convert,%function
+.align 4
+bsaes_enc_key_convert:
+ stmdb sp!,{r4-r6,lr}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+
+ ldr r5,[$inp,#240] @ pass rounds
+ mov r4,$inp @ pass key
+ mov r12,$out @ pass key schedule
+ bl _bsaes_key_convert
+ veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key
+ vstmia r12, {@XMM[7]} @ save last round key
+
+ vldmia sp!,{d8-d15}
+ ldmia sp!,{r4-r6,pc}
+.size bsaes_enc_key_convert,.-bsaes_enc_key_convert
+
+.globl bsaes_encrypt_128
+.type bsaes_encrypt_128,%function
+.align 4
+bsaes_encrypt_128:
+ stmdb sp!,{r4-r6,lr}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+.Lenc128_loop:
+ vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input
+ vld1.8 {@XMM[2]-@XMM[3]}, [$inp]!
+ mov r4,$key @ pass the key
+ vld1.8 {@XMM[4]-@XMM[5]}, [$inp]!
+ mov r5,#10 @ pass rounds
+ vld1.8 {@XMM[6]-@XMM[7]}, [$inp]!
+
+ bl _bsaes_encrypt8
+
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[3]}, [$out]!
+ vst1.8 {@XMM[7]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ subs $len,$len,#0x80
+ vst1.8 {@XMM[5]}, [$out]!
+ bhi .Lenc128_loop
+
+ vldmia sp!,{d8-d15}
+ ldmia sp!,{r4-r6,pc}
+.size bsaes_encrypt_128,.-bsaes_encrypt_128
+
+.globl bsaes_dec_key_convert
+.type bsaes_dec_key_convert,%function
+.align 4
+bsaes_dec_key_convert:
+ stmdb sp!,{r4-r6,lr}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+
+ ldr r5,[$inp,#240] @ pass rounds
+ mov r4,$inp @ pass key
+ mov r12,$out @ pass key schedule
+ bl _bsaes_key_convert
+ vldmia $out, {@XMM[6]}
+ vstmia r12, {@XMM[15]} @ save last round key
+ veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key
+ vstmia $out, {@XMM[7]}
+
+ vldmia sp!,{d8-d15}
+ ldmia sp!,{r4-r6,pc}
+.size bsaes_dec_key_convert,.-bsaes_dec_key_convert
+
+.globl bsaes_decrypt_128
+.type bsaes_decrypt_128,%function
+.align 4
+bsaes_decrypt_128:
+ stmdb sp!,{r4-r6,lr}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+.Ldec128_loop:
+ vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input
+ vld1.8 {@XMM[2]-@XMM[3]}, [$inp]!
+ mov r4,$key @ pass the key
+ vld1.8 {@XMM[4]-@XMM[5]}, [$inp]!
+ mov r5,#10 @ pass rounds
+ vld1.8 {@XMM[6]-@XMM[7]}, [$inp]!
+
+ bl _bsaes_decrypt8
+
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ vst1.8 {@XMM[7]}, [$out]!
+ vst1.8 {@XMM[3]}, [$out]!
+ subs $len,$len,#0x80
+ vst1.8 {@XMM[5]}, [$out]!
+ bhi .Ldec128_loop
+
+ vldmia sp!,{d8-d15}
+ ldmia sp!,{r4-r6,pc}
+.size bsaes_decrypt_128,.-bsaes_decrypt_128
+___
+}
+{
+my ($inp,$out,$len,$key, $ivp,$fp,$rounds)=map("r$_",(0..3,8..10));
+my ($keysched)=("sp");
+
+$code.=<<___;
+.extern AES_cbc_encrypt
+.extern AES_decrypt
+
+.global bsaes_cbc_encrypt
+.type bsaes_cbc_encrypt,%function
+.align 5
+bsaes_cbc_encrypt:
+#ifndef __KERNEL__
+ cmp $len, #128
+#ifndef __thumb__
+ blo AES_cbc_encrypt
+#else
+ bhs 1f
+ b AES_cbc_encrypt
+1:
+#endif
+#endif
+
+ @ it is up to the caller to make sure we are called with enc == 0
+
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr}
+ VFP_ABI_PUSH
+ ldr $ivp, [ip] @ IV is 1st arg on the stack
+ mov $len, $len, lsr#4 @ len in 16 byte blocks
+ sub sp, #0x10 @ scratch space to carry over the IV
+ mov $fp, sp @ save sp
+
+ ldr $rounds, [$key, #240] @ get # of rounds
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key
+ add r12, #`128-32` @ sifze of bit-slices key schedule
+
+ @ populate the key schedule
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ mov sp, r12 @ sp is $keysched
+ bl _bsaes_key_convert
+ vldmia $keysched, {@XMM[6]}
+ vstmia r12, {@XMM[15]} @ save last round key
+ veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key
+ vstmia $keysched, {@XMM[7]}
+#else
+ ldr r12, [$key, #244]
+ eors r12, #1
+ beq 0f
+
+ @ populate the key schedule
+ str r12, [$key, #244]
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ add r12, $key, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, $key, #248
+ vldmia r4, {@XMM[6]}
+ vstmia r12, {@XMM[15]} @ save last round key
+ veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key
+ vstmia r4, {@XMM[7]}
+
+.align 2
+0:
+#endif
+
+ vld1.8 {@XMM[15]}, [$ivp] @ load IV
+ b .Lcbc_dec_loop
+
+.align 4
+.Lcbc_dec_loop:
+ subs $len, $len, #0x8
+ bmi .Lcbc_dec_loop_finish
+
+ vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input
+ vld1.8 {@XMM[2]-@XMM[3]}, [$inp]!
+#ifndef BSAES_ASM_EXTENDED_KEY
+ mov r4, $keysched @ pass the key
+#else
+ add r4, $key, #248
+#endif
+ vld1.8 {@XMM[4]-@XMM[5]}, [$inp]!
+ mov r5, $rounds
+ vld1.8 {@XMM[6]-@XMM[7]}, [$inp]
+ sub $inp, $inp, #0x60
+ vstmia $fp, {@XMM[15]} @ put aside IV
+
+ bl _bsaes_decrypt8
+
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[10]-@XMM[11]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vld1.8 {@XMM[12]-@XMM[13]}, [$inp]!
+ veor @XMM[4], @XMM[4], @XMM[10]
+ veor @XMM[2], @XMM[2], @XMM[11]
+ vld1.8 {@XMM[14]-@XMM[15]}, [$inp]!
+ veor @XMM[7], @XMM[7], @XMM[12]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ veor @XMM[3], @XMM[3], @XMM[13]
+ vst1.8 {@XMM[6]}, [$out]!
+ veor @XMM[5], @XMM[5], @XMM[14]
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ vst1.8 {@XMM[7]}, [$out]!
+ vst1.8 {@XMM[3]}, [$out]!
+ vst1.8 {@XMM[5]}, [$out]!
+
+ b .Lcbc_dec_loop
+
+.Lcbc_dec_loop_finish:
+ adds $len, $len, #8
+ beq .Lcbc_dec_done
+
+ vld1.8 {@XMM[0]}, [$inp]! @ load input
+ cmp $len, #2
+ blo .Lcbc_dec_one
+ vld1.8 {@XMM[1]}, [$inp]!
+#ifndef BSAES_ASM_EXTENDED_KEY
+ mov r4, $keysched @ pass the key
+#else
+ add r4, $key, #248
+#endif
+ mov r5, $rounds
+ vstmia $fp, {@XMM[15]} @ put aside IV
+ beq .Lcbc_dec_two
+ vld1.8 {@XMM[2]}, [$inp]!
+ cmp $len, #4
+ blo .Lcbc_dec_three
+ vld1.8 {@XMM[3]}, [$inp]!
+ beq .Lcbc_dec_four
+ vld1.8 {@XMM[4]}, [$inp]!
+ cmp $len, #6
+ blo .Lcbc_dec_five
+ vld1.8 {@XMM[5]}, [$inp]!
+ beq .Lcbc_dec_six
+ vld1.8 {@XMM[6]}, [$inp]!
+ sub $inp, $inp, #0x70
+
+ bl _bsaes_decrypt8
+
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[10]-@XMM[11]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vld1.8 {@XMM[12]-@XMM[13]}, [$inp]!
+ veor @XMM[4], @XMM[4], @XMM[10]
+ veor @XMM[2], @XMM[2], @XMM[11]
+ vld1.8 {@XMM[15]}, [$inp]!
+ veor @XMM[7], @XMM[7], @XMM[12]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ veor @XMM[3], @XMM[3], @XMM[13]
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ vst1.8 {@XMM[7]}, [$out]!
+ vst1.8 {@XMM[3]}, [$out]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_six:
+ sub $inp, $inp, #0x60
+ bl _bsaes_decrypt8
+ vldmia $fp,{@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[10]-@XMM[11]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vld1.8 {@XMM[12]}, [$inp]!
+ veor @XMM[4], @XMM[4], @XMM[10]
+ veor @XMM[2], @XMM[2], @XMM[11]
+ vld1.8 {@XMM[15]}, [$inp]!
+ veor @XMM[7], @XMM[7], @XMM[12]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ vst1.8 {@XMM[7]}, [$out]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_five:
+ sub $inp, $inp, #0x50
+ bl _bsaes_decrypt8
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[10]-@XMM[11]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vld1.8 {@XMM[15]}, [$inp]!
+ veor @XMM[4], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ veor @XMM[2], @XMM[2], @XMM[11]
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[4]}, [$out]!
+ vst1.8 {@XMM[2]}, [$out]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_four:
+ sub $inp, $inp, #0x40
+ bl _bsaes_decrypt8
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[10]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vld1.8 {@XMM[15]}, [$inp]!
+ veor @XMM[4], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ vst1.8 {@XMM[6]}, [$out]!
+ vst1.8 {@XMM[4]}, [$out]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_three:
+ sub $inp, $inp, #0x30
+ bl _bsaes_decrypt8
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[15]}, [$inp]!
+ veor @XMM[1], @XMM[1], @XMM[8]
+ veor @XMM[6], @XMM[6], @XMM[9]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ vst1.8 {@XMM[6]}, [$out]!
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_two:
+ sub $inp, $inp, #0x20
+ bl _bsaes_decrypt8
+ vldmia $fp, {@XMM[14]} @ reload IV
+ vld1.8 {@XMM[8]}, [$inp]! @ reload input
+ veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV
+ vld1.8 {@XMM[15]}, [$inp]! @ reload input
+ veor @XMM[1], @XMM[1], @XMM[8]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ b .Lcbc_dec_done
+.align 4
+.Lcbc_dec_one:
+ sub $inp, $inp, #0x10
+ mov $rounds, $out @ save original out pointer
+ mov $out, $fp @ use the iv scratch space as out buffer
+ mov r2, $key
+ vmov @XMM[4],@XMM[15] @ just in case ensure that IV
+ vmov @XMM[5],@XMM[0] @ and input are preserved
+ bl AES_decrypt
+ vld1.8 {@XMM[0]}, [$fp,:64] @ load result
+ veor @XMM[0], @XMM[0], @XMM[4] @ ^= IV
+ vmov @XMM[15], @XMM[5] @ @XMM[5] holds input
+ vst1.8 {@XMM[0]}, [$rounds] @ write output
+
+.Lcbc_dec_done:
+#ifndef BSAES_ASM_EXTENDED_KEY
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+.Lcbc_dec_bzero: @ wipe key schedule [if any]
+ vstmia $keysched!, {q0-q1}
+ cmp $keysched, $fp
+ bne .Lcbc_dec_bzero
+#endif
+
+ mov sp, $fp
+ add sp, #0x10 @ add sp,$fp,#0x10 is no good for thumb
+ vst1.8 {@XMM[15]}, [$ivp] @ return IV
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc}
+.size bsaes_cbc_encrypt,.-bsaes_cbc_encrypt
+___
+}
+{
+my ($inp,$out,$len,$key, $ctr,$fp,$rounds)=(map("r$_",(0..3,8..10)));
+my $const = "r6"; # shared with _bsaes_encrypt8_alt
+my $keysched = "sp";
+
+$code.=<<___;
+.extern AES_encrypt
+.global bsaes_ctr32_encrypt_blocks
+.type bsaes_ctr32_encrypt_blocks,%function
+.align 5
+bsaes_ctr32_encrypt_blocks:
+ cmp $len, #8 @ use plain AES for
+ blo .Lctr_enc_short @ small sizes
+
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr}
+ VFP_ABI_PUSH
+ ldr $ctr, [ip] @ ctr is 1st arg on the stack
+ sub sp, sp, #0x10 @ scratch space to carry over the ctr
+ mov $fp, sp @ save sp
+
+ ldr $rounds, [$key, #240] @ get # of rounds
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key
+ add r12, #`128-32` @ size of bit-sliced key schedule
+
+ @ populate the key schedule
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ mov sp, r12 @ sp is $keysched
+ bl _bsaes_key_convert
+ veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key
+ vstmia r12, {@XMM[7]} @ save last round key
+
+ vld1.8 {@XMM[0]}, [$ctr] @ load counter
+ add $ctr, $const, #.LREVM0SR-.LM0 @ borrow $ctr
+ vldmia $keysched, {@XMM[4]} @ load round0 key
+#else
+ ldr r12, [$key, #244]
+ eors r12, #1
+ beq 0f
+
+ @ populate the key schedule
+ str r12, [$key, #244]
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ add r12, $key, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key
+ vstmia r12, {@XMM[7]} @ save last round key
+
+.align 2
+0: add r12, $key, #248
+ vld1.8 {@XMM[0]}, [$ctr] @ load counter
+ adrl $ctr, .LREVM0SR @ borrow $ctr
+ vldmia r12, {@XMM[4]} @ load round0 key
+ sub sp, #0x10 @ place for adjusted round0 key
+#endif
+
+ vmov.i32 @XMM[8],#1 @ compose 1<<96
+ veor @XMM[9],@XMM[9],@XMM[9]
+ vrev32.8 @XMM[0],@XMM[0]
+ vext.8 @XMM[8],@XMM[9],@XMM[8],#4
+ vrev32.8 @XMM[4],@XMM[4]
+ vadd.u32 @XMM[9],@XMM[8],@XMM[8] @ compose 2<<96
+ vstmia $keysched, {@XMM[4]} @ save adjusted round0 key
+ b .Lctr_enc_loop
+
+.align 4
+.Lctr_enc_loop:
+ vadd.u32 @XMM[10], @XMM[8], @XMM[9] @ compose 3<<96
+ vadd.u32 @XMM[1], @XMM[0], @XMM[8] @ +1
+ vadd.u32 @XMM[2], @XMM[0], @XMM[9] @ +2
+ vadd.u32 @XMM[3], @XMM[0], @XMM[10] @ +3
+ vadd.u32 @XMM[4], @XMM[1], @XMM[10]
+ vadd.u32 @XMM[5], @XMM[2], @XMM[10]
+ vadd.u32 @XMM[6], @XMM[3], @XMM[10]
+ vadd.u32 @XMM[7], @XMM[4], @XMM[10]
+ vadd.u32 @XMM[10], @XMM[5], @XMM[10] @ next counter
+
+ @ Borrow prologue from _bsaes_encrypt8 to use the opportunity
+ @ to flip byte order in 32-bit counter
+
+ vldmia $keysched, {@XMM[9]} @ load round0 key
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, $keysched, #0x10 @ pass next round key
+#else
+ add r4, $key, #`248+16`
+#endif
+ vldmia $ctr, {@XMM[8]} @ .LREVM0SR
+ mov r5, $rounds @ pass rounds
+ vstmia $fp, {@XMM[10]} @ save next counter
+ sub $const, $ctr, #.LREVM0SR-.LSR @ pass constants
+
+ bl _bsaes_encrypt8_alt
+
+ subs $len, $len, #8
+ blo .Lctr_enc_loop_done
+
+ vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ load input
+ vld1.8 {@XMM[10]-@XMM[11]}, [$inp]!
+ veor @XMM[0], @XMM[8]
+ veor @XMM[1], @XMM[9]
+ vld1.8 {@XMM[12]-@XMM[13]}, [$inp]!
+ veor @XMM[4], @XMM[10]
+ veor @XMM[6], @XMM[11]
+ vld1.8 {@XMM[14]-@XMM[15]}, [$inp]!
+ veor @XMM[3], @XMM[12]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output
+ veor @XMM[7], @XMM[13]
+ veor @XMM[2], @XMM[14]
+ vst1.8 {@XMM[4]}, [$out]!
+ veor @XMM[5], @XMM[15]
+ vst1.8 {@XMM[6]}, [$out]!
+ vmov.i32 @XMM[8], #1 @ compose 1<<96
+ vst1.8 {@XMM[3]}, [$out]!
+ veor @XMM[9], @XMM[9], @XMM[9]
+ vst1.8 {@XMM[7]}, [$out]!
+ vext.8 @XMM[8], @XMM[9], @XMM[8], #4
+ vst1.8 {@XMM[2]}, [$out]!
+ vadd.u32 @XMM[9],@XMM[8],@XMM[8] @ compose 2<<96
+ vst1.8 {@XMM[5]}, [$out]!
+ vldmia $fp, {@XMM[0]} @ load counter
+
+ bne .Lctr_enc_loop
+ b .Lctr_enc_done
+
+.align 4
+.Lctr_enc_loop_done:
+ add $len, $len, #8
+ vld1.8 {@XMM[8]}, [$inp]! @ load input
+ veor @XMM[0], @XMM[8]
+ vst1.8 {@XMM[0]}, [$out]! @ write output
+ cmp $len, #2
+ blo .Lctr_enc_done
+ vld1.8 {@XMM[9]}, [$inp]!
+ veor @XMM[1], @XMM[9]
+ vst1.8 {@XMM[1]}, [$out]!
+ beq .Lctr_enc_done
+ vld1.8 {@XMM[10]}, [$inp]!
+ veor @XMM[4], @XMM[10]
+ vst1.8 {@XMM[4]}, [$out]!
+ cmp $len, #4
+ blo .Lctr_enc_done
+ vld1.8 {@XMM[11]}, [$inp]!
+ veor @XMM[6], @XMM[11]
+ vst1.8 {@XMM[6]}, [$out]!
+ beq .Lctr_enc_done
+ vld1.8 {@XMM[12]}, [$inp]!
+ veor @XMM[3], @XMM[12]
+ vst1.8 {@XMM[3]}, [$out]!
+ cmp $len, #6
+ blo .Lctr_enc_done
+ vld1.8 {@XMM[13]}, [$inp]!
+ veor @XMM[7], @XMM[13]
+ vst1.8 {@XMM[7]}, [$out]!
+ beq .Lctr_enc_done
+ vld1.8 {@XMM[14]}, [$inp]
+ veor @XMM[2], @XMM[14]
+ vst1.8 {@XMM[2]}, [$out]!
+
+.Lctr_enc_done:
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifndef BSAES_ASM_EXTENDED_KEY
+.Lctr_enc_bzero: @ wipe key schedule [if any]
+ vstmia $keysched!, {q0-q1}
+ cmp $keysched, $fp
+ bne .Lctr_enc_bzero
+#else
+ vstmia $keysched, {q0-q1}
+#endif
+
+ mov sp, $fp
+ add sp, #0x10 @ add sp,$fp,#0x10 is no good for thumb
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.align 4
+.Lctr_enc_short:
+ ldr ip, [sp] @ ctr pointer is passed on stack
+ stmdb sp!, {r4-r8, lr}
+
+ mov r4, $inp @ copy arguments
+ mov r5, $out
+ mov r6, $len
+ mov r7, $key
+ ldr r8, [ip, #12] @ load counter LSW
+ vld1.8 {@XMM[1]}, [ip] @ load whole counter value
+#ifdef __ARMEL__
+ rev r8, r8
+#endif
+ sub sp, sp, #0x10
+ vst1.8 {@XMM[1]}, [sp,:64] @ copy counter value
+ sub sp, sp, #0x10
+
+.Lctr_enc_short_loop:
+ add r0, sp, #0x10 @ input counter value
+ mov r1, sp @ output on the stack
+ mov r2, r7 @ key
+
+ bl AES_encrypt
+
+ vld1.8 {@XMM[0]}, [r4]! @ load input
+ vld1.8 {@XMM[1]}, [sp,:64] @ load encrypted counter
+ add r8, r8, #1
+#ifdef __ARMEL__
+ rev r0, r8
+ str r0, [sp, #0x1c] @ next counter value
+#else
+ str r8, [sp, #0x1c] @ next counter value
+#endif
+ veor @XMM[0],@XMM[0],@XMM[1]
+ vst1.8 {@XMM[0]}, [r5]! @ store output
+ subs r6, r6, #1
+ bne .Lctr_enc_short_loop
+
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+ vstmia sp!, {q0-q1}
+
+ ldmia sp!, {r4-r8, pc}
+.size bsaes_ctr32_encrypt_blocks,.-bsaes_ctr32_encrypt_blocks
+___
+}
+{
+######################################################################
+# void bsaes_xts_[en|de]crypt(const char *inp,char *out,size_t len,
+# const AES_KEY *key1, const AES_KEY *key2,
+# const unsigned char iv[16]);
+#
+my ($inp,$out,$len,$key,$rounds,$magic,$fp)=(map("r$_",(7..10,1..3)));
+my $const="r6"; # returned by _bsaes_key_convert
+my $twmask=@XMM[5];
+my @T=@XMM[6..7];
+
+$code.=<<___;
+.globl bsaes_xts_encrypt
+.type bsaes_xts_encrypt,%function
+.align 4
+bsaes_xts_encrypt:
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr} @ 0x20
+ VFP_ABI_PUSH
+ mov r6, sp @ future $fp
+
+ mov $inp, r0
+ mov $out, r1
+ mov $len, r2
+ mov $key, r3
+
+ sub r0, sp, #0x10 @ 0x10
+ bic r0, #0xf @ align at 16 bytes
+ mov sp, r0
+
+#ifdef XTS_CHAIN_TWEAK
+ ldr r0, [ip] @ pointer to input tweak
+#else
+ @ generate initial tweak
+ ldr r0, [ip, #4] @ iv[]
+ mov r1, sp
+ ldr r2, [ip, #0] @ key2
+ bl AES_encrypt
+ mov r0,sp @ pointer to initial tweak
+#endif
+
+ ldr $rounds, [$key, #240] @ get # of rounds
+ mov $fp, r6
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key
+ @ add r12, #`128-32` @ size of bit-sliced key schedule
+ sub r12, #`32+16` @ place for tweak[9]
+
+ @ populate the key schedule
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ mov sp, r12
+ add r12, #0x90 @ pass key schedule
+ bl _bsaes_key_convert
+ veor @XMM[7], @XMM[7], @XMM[15] @ fix up last round key
+ vstmia r12, {@XMM[7]} @ save last round key
+#else
+ ldr r12, [$key, #244]
+ eors r12, #1
+ beq 0f
+
+ str r12, [$key, #244]
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ add r12, $key, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ veor @XMM[7], @XMM[7], @XMM[15] @ fix up last round key
+ vstmia r12, {@XMM[7]}
+
+.align 2
+0: sub sp, #0x90 @ place for tweak[9]
+#endif
+
+ vld1.8 {@XMM[8]}, [r0] @ initial tweak
+ adr $magic, .Lxts_magic
+
+ subs $len, #0x80
+ blo .Lxts_enc_short
+ b .Lxts_enc_loop
+
+.align 4
+.Lxts_enc_loop:
+ vldmia $magic, {$twmask} @ load XTS magic
+ vshr.s64 @T[0], @XMM[8], #63
+ mov r0, sp
+ vand @T[0], @T[0], $twmask
+___
+for($i=9;$i<16;$i++) {
+$code.=<<___;
+ vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1]
+ vst1.64 {@XMM[$i-1]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ vshr.s64 @T[1], @XMM[$i], #63
+ veor @XMM[$i], @XMM[$i], @T[0]
+ vand @T[1], @T[1], $twmask
+___
+ @T=reverse(@T);
+
+$code.=<<___ if ($i>=10);
+ vld1.8 {@XMM[$i-10]}, [$inp]!
+___
+$code.=<<___ if ($i>=11);
+ veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3]
+___
+}
+$code.=<<___;
+ vadd.u64 @XMM[8], @XMM[15], @XMM[15]
+ vst1.64 {@XMM[15]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ veor @XMM[8], @XMM[8], @T[0]
+ vst1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+
+ vld1.8 {@XMM[6]-@XMM[7]}, [$inp]!
+ veor @XMM[5], @XMM[5], @XMM[13]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[6], @XMM[6], @XMM[14]
+ mov r5, $rounds @ pass rounds
+ veor @XMM[7], @XMM[7], @XMM[15]
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[6], @XMM[11]
+ vld1.64 {@XMM[14]-@XMM[15]}, [r0,:128]!
+ veor @XMM[10], @XMM[3], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ veor @XMM[12], @XMM[2], @XMM[14]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+ veor @XMM[13], @XMM[5], @XMM[15]
+ vst1.8 {@XMM[12]-@XMM[13]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+
+ subs $len, #0x80
+ bpl .Lxts_enc_loop
+
+.Lxts_enc_short:
+ adds $len, #0x70
+ bmi .Lxts_enc_done
+
+ vldmia $magic, {$twmask} @ load XTS magic
+ vshr.s64 @T[0], @XMM[8], #63
+ mov r0, sp
+ vand @T[0], @T[0], $twmask
+___
+for($i=9;$i<16;$i++) {
+$code.=<<___;
+ vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1]
+ vst1.64 {@XMM[$i-1]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ vshr.s64 @T[1], @XMM[$i], #63
+ veor @XMM[$i], @XMM[$i], @T[0]
+ vand @T[1], @T[1], $twmask
+___
+ @T=reverse(@T);
+
+$code.=<<___ if ($i>=10);
+ vld1.8 {@XMM[$i-10]}, [$inp]!
+ subs $len, #0x10
+ bmi .Lxts_enc_`$i-9`
+___
+$code.=<<___ if ($i>=11);
+ veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3]
+___
+}
+$code.=<<___;
+ sub $len, #0x10
+ vst1.64 {@XMM[15]}, [r0,:128] @ next round tweak
+
+ vld1.8 {@XMM[6]}, [$inp]!
+ veor @XMM[5], @XMM[5], @XMM[13]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[6], @XMM[6], @XMM[14]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[6], @XMM[11]
+ vld1.64 {@XMM[14]}, [r0,:128]!
+ veor @XMM[10], @XMM[3], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ veor @XMM[12], @XMM[2], @XMM[14]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+ vst1.8 {@XMM[12]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_6:
+ vst1.64 {@XMM[14]}, [r0,:128] @ next round tweak
+
+ veor @XMM[4], @XMM[4], @XMM[12]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[5], @XMM[5], @XMM[13]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[6], @XMM[11]
+ veor @XMM[10], @XMM[3], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+
+@ put this in range for both ARM and Thumb mode adr instructions
+.align 5
+.Lxts_magic:
+ .quad 1, 0x87
+
+.align 5
+.Lxts_enc_5:
+ vst1.64 {@XMM[13]}, [r0,:128] @ next round tweak
+
+ veor @XMM[3], @XMM[3], @XMM[11]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[4], @XMM[4], @XMM[12]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[6], @XMM[11]
+ veor @XMM[10], @XMM[3], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ vst1.8 {@XMM[10]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_4:
+ vst1.64 {@XMM[12]}, [r0,:128] @ next round tweak
+
+ veor @XMM[2], @XMM[2], @XMM[10]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[3], @XMM[3], @XMM[11]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[6], @XMM[11]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_3:
+ vst1.64 {@XMM[11]}, [r0,:128] @ next round tweak
+
+ veor @XMM[1], @XMM[1], @XMM[9]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[2], @XMM[2], @XMM[10]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]!
+ vld1.64 {@XMM[10]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[4], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ vst1.8 {@XMM[8]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_2:
+ vst1.64 {@XMM[10]}, [r0,:128] @ next round tweak
+
+ veor @XMM[0], @XMM[0], @XMM[8]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[1], @XMM[1], @XMM[9]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_encrypt8
+
+ vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_enc_done
+.align 4
+.Lxts_enc_1:
+ mov r0, sp
+ veor @XMM[0], @XMM[8]
+ mov r1, sp
+ vst1.8 {@XMM[0]}, [sp,:128]
+ mov r2, $key
+ mov r4, $fp @ preserve fp
+
+ bl AES_encrypt
+
+ vld1.8 {@XMM[0]}, [sp,:128]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ vst1.8 {@XMM[0]}, [$out]!
+ mov $fp, r4
+
+ vmov @XMM[8], @XMM[9] @ next round tweak
+
+.Lxts_enc_done:
+#ifndef XTS_CHAIN_TWEAK
+ adds $len, #0x10
+ beq .Lxts_enc_ret
+ sub r6, $out, #0x10
+
+.Lxts_enc_steal:
+ ldrb r0, [$inp], #1
+ ldrb r1, [$out, #-0x10]
+ strb r0, [$out, #-0x10]
+ strb r1, [$out], #1
+
+ subs $len, #1
+ bhi .Lxts_enc_steal
+
+ vld1.8 {@XMM[0]}, [r6]
+ mov r0, sp
+ veor @XMM[0], @XMM[0], @XMM[8]
+ mov r1, sp
+ vst1.8 {@XMM[0]}, [sp,:128]
+ mov r2, $key
+ mov r4, $fp @ preserve fp
+
+ bl AES_encrypt
+
+ vld1.8 {@XMM[0]}, [sp,:128]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ vst1.8 {@XMM[0]}, [r6]
+ mov $fp, r4
+#endif
+
+.Lxts_enc_ret:
+ bic r0, $fp, #0xf
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifdef XTS_CHAIN_TWEAK
+ ldr r1, [$fp, #0x20+VFP_ABI_FRAME] @ chain tweak
+#endif
+.Lxts_enc_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r0
+ bne .Lxts_enc_bzero
+
+ mov sp, $fp
+#ifdef XTS_CHAIN_TWEAK
+ vst1.8 {@XMM[8]}, [r1]
+#endif
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.size bsaes_xts_encrypt,.-bsaes_xts_encrypt
+
+.globl bsaes_xts_decrypt
+.type bsaes_xts_decrypt,%function
+.align 4
+bsaes_xts_decrypt:
+ mov ip, sp
+ stmdb sp!, {r4-r10, lr} @ 0x20
+ VFP_ABI_PUSH
+ mov r6, sp @ future $fp
+
+ mov $inp, r0
+ mov $out, r1
+ mov $len, r2
+ mov $key, r3
+
+ sub r0, sp, #0x10 @ 0x10
+ bic r0, #0xf @ align at 16 bytes
+ mov sp, r0
+
+#ifdef XTS_CHAIN_TWEAK
+ ldr r0, [ip] @ pointer to input tweak
+#else
+ @ generate initial tweak
+ ldr r0, [ip, #4] @ iv[]
+ mov r1, sp
+ ldr r2, [ip, #0] @ key2
+ bl AES_encrypt
+ mov r0, sp @ pointer to initial tweak
+#endif
+
+ ldr $rounds, [$key, #240] @ get # of rounds
+ mov $fp, r6
+#ifndef BSAES_ASM_EXTENDED_KEY
+ @ allocate the key schedule on the stack
+ sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key
+ @ add r12, #`128-32` @ size of bit-sliced key schedule
+ sub r12, #`32+16` @ place for tweak[9]
+
+ @ populate the key schedule
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ mov sp, r12
+ add r12, #0x90 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, sp, #0x90
+ vldmia r4, {@XMM[6]}
+ vstmia r12, {@XMM[15]} @ save last round key
+ veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key
+ vstmia r4, {@XMM[7]}
+#else
+ ldr r12, [$key, #244]
+ eors r12, #1
+ beq 0f
+
+ str r12, [$key, #244]
+ mov r4, $key @ pass key
+ mov r5, $rounds @ pass # of rounds
+ add r12, $key, #248 @ pass key schedule
+ bl _bsaes_key_convert
+ add r4, $key, #248
+ vldmia r4, {@XMM[6]}
+ vstmia r12, {@XMM[15]} @ save last round key
+ veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key
+ vstmia r4, {@XMM[7]}
+
+.align 2
+0: sub sp, #0x90 @ place for tweak[9]
+#endif
+ vld1.8 {@XMM[8]}, [r0] @ initial tweak
+ adr $magic, .Lxts_magic
+
+ tst $len, #0xf @ if not multiple of 16
+ it ne @ Thumb2 thing, sanity check in ARM
+ subne $len, #0x10 @ subtract another 16 bytes
+ subs $len, #0x80
+
+ blo .Lxts_dec_short
+ b .Lxts_dec_loop
+
+.align 4
+.Lxts_dec_loop:
+ vldmia $magic, {$twmask} @ load XTS magic
+ vshr.s64 @T[0], @XMM[8], #63
+ mov r0, sp
+ vand @T[0], @T[0], $twmask
+___
+for($i=9;$i<16;$i++) {
+$code.=<<___;
+ vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1]
+ vst1.64 {@XMM[$i-1]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ vshr.s64 @T[1], @XMM[$i], #63
+ veor @XMM[$i], @XMM[$i], @T[0]
+ vand @T[1], @T[1], $twmask
+___
+ @T=reverse(@T);
+
+$code.=<<___ if ($i>=10);
+ vld1.8 {@XMM[$i-10]}, [$inp]!
+___
+$code.=<<___ if ($i>=11);
+ veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3]
+___
+}
+$code.=<<___;
+ vadd.u64 @XMM[8], @XMM[15], @XMM[15]
+ vst1.64 {@XMM[15]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ veor @XMM[8], @XMM[8], @T[0]
+ vst1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+
+ vld1.8 {@XMM[6]-@XMM[7]}, [$inp]!
+ veor @XMM[5], @XMM[5], @XMM[13]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[6], @XMM[6], @XMM[14]
+ mov r5, $rounds @ pass rounds
+ veor @XMM[7], @XMM[7], @XMM[15]
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[4], @XMM[11]
+ vld1.64 {@XMM[14]-@XMM[15]}, [r0,:128]!
+ veor @XMM[10], @XMM[2], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ veor @XMM[12], @XMM[3], @XMM[14]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+ veor @XMM[13], @XMM[5], @XMM[15]
+ vst1.8 {@XMM[12]-@XMM[13]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+
+ subs $len, #0x80
+ bpl .Lxts_dec_loop
+
+.Lxts_dec_short:
+ adds $len, #0x70
+ bmi .Lxts_dec_done
+
+ vldmia $magic, {$twmask} @ load XTS magic
+ vshr.s64 @T[0], @XMM[8], #63
+ mov r0, sp
+ vand @T[0], @T[0], $twmask
+___
+for($i=9;$i<16;$i++) {
+$code.=<<___;
+ vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1]
+ vst1.64 {@XMM[$i-1]}, [r0,:128]!
+ vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")`
+ vshr.s64 @T[1], @XMM[$i], #63
+ veor @XMM[$i], @XMM[$i], @T[0]
+ vand @T[1], @T[1], $twmask
+___
+ @T=reverse(@T);
+
+$code.=<<___ if ($i>=10);
+ vld1.8 {@XMM[$i-10]}, [$inp]!
+ subs $len, #0x10
+ bmi .Lxts_dec_`$i-9`
+___
+$code.=<<___ if ($i>=11);
+ veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3]
+___
+}
+$code.=<<___;
+ sub $len, #0x10
+ vst1.64 {@XMM[15]}, [r0,:128] @ next round tweak
+
+ vld1.8 {@XMM[6]}, [$inp]!
+ veor @XMM[5], @XMM[5], @XMM[13]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[6], @XMM[6], @XMM[14]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[4], @XMM[11]
+ vld1.64 {@XMM[14]}, [r0,:128]!
+ veor @XMM[10], @XMM[2], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ veor @XMM[12], @XMM[3], @XMM[14]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+ vst1.8 {@XMM[12]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_6:
+ vst1.64 {@XMM[14]}, [r0,:128] @ next round tweak
+
+ veor @XMM[4], @XMM[4], @XMM[12]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[5], @XMM[5], @XMM[13]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[4], @XMM[11]
+ veor @XMM[10], @XMM[2], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ veor @XMM[11], @XMM[7], @XMM[13]
+ vst1.8 {@XMM[10]-@XMM[11]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_5:
+ vst1.64 {@XMM[13]}, [r0,:128] @ next round tweak
+
+ veor @XMM[3], @XMM[3], @XMM[11]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[4], @XMM[4], @XMM[12]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ vld1.64 {@XMM[12]}, [r0,:128]!
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[4], @XMM[11]
+ veor @XMM[10], @XMM[2], @XMM[12]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+ vst1.8 {@XMM[10]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_4:
+ vst1.64 {@XMM[12]}, [r0,:128] @ next round tweak
+
+ veor @XMM[2], @XMM[2], @XMM[10]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[3], @XMM[3], @XMM[11]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]!
+ vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ veor @XMM[9], @XMM[4], @XMM[11]
+ vst1.8 {@XMM[8]-@XMM[9]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_3:
+ vst1.64 {@XMM[11]}, [r0,:128] @ next round tweak
+
+ veor @XMM[1], @XMM[1], @XMM[9]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[2], @XMM[2], @XMM[10]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]!
+ vld1.64 {@XMM[10]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ veor @XMM[8], @XMM[6], @XMM[10]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+ vst1.8 {@XMM[8]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_2:
+ vst1.64 {@XMM[10]}, [r0,:128] @ next round tweak
+
+ veor @XMM[0], @XMM[0], @XMM[8]
+#ifndef BSAES_ASM_EXTENDED_KEY
+ add r4, sp, #0x90 @ pass key schedule
+#else
+ add r4, $key, #248 @ pass key schedule
+#endif
+ veor @XMM[1], @XMM[1], @XMM[9]
+ mov r5, $rounds @ pass rounds
+ mov r0, sp
+
+ bl _bsaes_decrypt8
+
+ vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]!
+ veor @XMM[0], @XMM[0], @XMM[ 8]
+ veor @XMM[1], @XMM[1], @XMM[ 9]
+ vst1.8 {@XMM[0]-@XMM[1]}, [$out]!
+
+ vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak
+ b .Lxts_dec_done
+.align 4
+.Lxts_dec_1:
+ mov r0, sp
+ veor @XMM[0], @XMM[8]
+ mov r1, sp
+ vst1.8 {@XMM[0]}, [sp,:128]
+ mov r2, $key
+ mov r4, $fp @ preserve fp
+ mov r5, $magic @ preserve magic
+
+ bl AES_decrypt
+
+ vld1.8 {@XMM[0]}, [sp,:128]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ vst1.8 {@XMM[0]}, [$out]!
+ mov $fp, r4
+ mov $magic, r5
+
+ vmov @XMM[8], @XMM[9] @ next round tweak
+
+.Lxts_dec_done:
+#ifndef XTS_CHAIN_TWEAK
+ adds $len, #0x10
+ beq .Lxts_dec_ret
+
+ @ calculate one round of extra tweak for the stolen ciphertext
+ vldmia $magic, {$twmask}
+ vshr.s64 @XMM[6], @XMM[8], #63
+ vand @XMM[6], @XMM[6], $twmask
+ vadd.u64 @XMM[9], @XMM[8], @XMM[8]
+ vswp `&Dhi("@XMM[6]")`,`&Dlo("@XMM[6]")`
+ veor @XMM[9], @XMM[9], @XMM[6]
+
+ @ perform the final decryption with the last tweak value
+ vld1.8 {@XMM[0]}, [$inp]!
+ mov r0, sp
+ veor @XMM[0], @XMM[0], @XMM[9]
+ mov r1, sp
+ vst1.8 {@XMM[0]}, [sp,:128]
+ mov r2, $key
+ mov r4, $fp @ preserve fp
+
+ bl AES_decrypt
+
+ vld1.8 {@XMM[0]}, [sp,:128]
+ veor @XMM[0], @XMM[0], @XMM[9]
+ vst1.8 {@XMM[0]}, [$out]
+
+ mov r6, $out
+.Lxts_dec_steal:
+ ldrb r1, [$out]
+ ldrb r0, [$inp], #1
+ strb r1, [$out, #0x10]
+ strb r0, [$out], #1
+
+ subs $len, #1
+ bhi .Lxts_dec_steal
+
+ vld1.8 {@XMM[0]}, [r6]
+ mov r0, sp
+ veor @XMM[0], @XMM[8]
+ mov r1, sp
+ vst1.8 {@XMM[0]}, [sp,:128]
+ mov r2, $key
+
+ bl AES_decrypt
+
+ vld1.8 {@XMM[0]}, [sp,:128]
+ veor @XMM[0], @XMM[0], @XMM[8]
+ vst1.8 {@XMM[0]}, [r6]
+ mov $fp, r4
+#endif
+
+.Lxts_dec_ret:
+ bic r0, $fp, #0xf
+ vmov.i32 q0, #0
+ vmov.i32 q1, #0
+#ifdef XTS_CHAIN_TWEAK
+ ldr r1, [$fp, #0x20+VFP_ABI_FRAME] @ chain tweak
+#endif
+.Lxts_dec_bzero: @ wipe key schedule [if any]
+ vstmia sp!, {q0-q1}
+ cmp sp, r0
+ bne .Lxts_dec_bzero
+
+ mov sp, $fp
+#ifdef XTS_CHAIN_TWEAK
+ vst1.8 {@XMM[8]}, [r1]
+#endif
+ VFP_ABI_POP
+ ldmia sp!, {r4-r10, pc} @ return
+
+.size bsaes_xts_decrypt,.-bsaes_xts_decrypt
+___
+}
+$code.=<<___;
+#endif
+___
+
+$code =~ s/\`([^\`]*)\`/eval($1)/gem;
+
+open SELF,$0;
+while(<SELF>) {
+ next if (/^#!/);
+ last if (!s/^#/@/ and !/^$/);
+ print;
+}
+close SELF;
+
+print $code;
+
+close STDOUT;
diff --git a/arch/arm/crypto/sha1-armv7-neon.S b/arch/arm/crypto/sha1-armv7-neon.S
new file mode 100644
index 0000000..50013c0
--- /dev/null
+++ b/arch/arm/crypto/sha1-armv7-neon.S
@@ -0,0 +1,634 @@
+/* sha1-armv7-neon.S - ARM/NEON accelerated SHA-1 transform function
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code 32
+.fpu neon
+
+.text
+
+
+/* Context structure */
+
+#define state_h0 0
+#define state_h1 4
+#define state_h2 8
+#define state_h3 12
+#define state_h4 16
+
+
+/* Constants */
+
+#define K1 0x5A827999
+#define K2 0x6ED9EBA1
+#define K3 0x8F1BBCDC
+#define K4 0xCA62C1D6
+.align 4
+.LK_VEC:
+.LK1: .long K1, K1, K1, K1
+.LK2: .long K2, K2, K2, K2
+.LK3: .long K3, K3, K3, K3
+.LK4: .long K4, K4, K4, K4
+
+
+/* Register macros */
+
+#define RSTATE r0
+#define RDATA r1
+#define RNBLKS r2
+#define ROLDSTACK r3
+#define RWK lr
+
+#define _a r4
+#define _b r5
+#define _c r6
+#define _d r7
+#define _e r8
+
+#define RT0 r9
+#define RT1 r10
+#define RT2 r11
+#define RT3 r12
+
+#define W0 q0
+#define W1 q1
+#define W2 q2
+#define W3 q3
+#define W4 q4
+#define W5 q5
+#define W6 q6
+#define W7 q7
+
+#define tmp0 q8
+#define tmp1 q9
+#define tmp2 q10
+#define tmp3 q11
+
+#define qK1 q12
+#define qK2 q13
+#define qK3 q14
+#define qK4 q15
+
+
+/* Round function macros. */
+
+#define WK_offs(i) (((i) & 15) * 4)
+
+#define _R_F1(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ ldr RT3, [sp, WK_offs(i)]; \
+ pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ bic RT0, d, b; \
+ add e, e, a, ror #(32 - 5); \
+ and RT1, c, b; \
+ pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ add RT0, RT0, RT3; \
+ add e, e, RT1; \
+ ror b, #(32 - 30); \
+ pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ add e, e, RT0;
+
+#define _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ ldr RT3, [sp, WK_offs(i)]; \
+ pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ eor RT0, d, b; \
+ add e, e, a, ror #(32 - 5); \
+ eor RT0, RT0, c; \
+ pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ add e, e, RT3; \
+ ror b, #(32 - 30); \
+ pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ add e, e, RT0; \
+
+#define _R_F3(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ ldr RT3, [sp, WK_offs(i)]; \
+ pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ eor RT0, b, c; \
+ and RT1, b, c; \
+ add e, e, a, ror #(32 - 5); \
+ pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ and RT0, RT0, d; \
+ add RT1, RT1, RT3; \
+ add e, e, RT0; \
+ ror b, #(32 - 30); \
+ pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+ add e, e, RT1;
+
+#define _R_F4(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define _R(a,b,c,d,e,f,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ _R_##f(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define R(a,b,c,d,e,f,i) \
+ _R_##f(a,b,c,d,e,i,dummy,dummy,dummy,i16,\
+ W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define dummy(...)
+
+
+/* Input expansion macros. */
+
+/********* Precalc macros for rounds 0-15 *************************************/
+
+#define W_PRECALC_00_15() \
+ add RWK, sp, #(WK_offs(0)); \
+ \
+ vld1.32 {tmp0, tmp1}, [RDATA]!; \
+ vrev32.8 W0, tmp0; /* big => little */ \
+ vld1.32 {tmp2, tmp3}, [RDATA]!; \
+ vadd.u32 tmp0, W0, curK; \
+ vrev32.8 W7, tmp1; /* big => little */ \
+ vrev32.8 W6, tmp2; /* big => little */ \
+ vadd.u32 tmp1, W7, curK; \
+ vrev32.8 W5, tmp3; /* big => little */ \
+ vadd.u32 tmp2, W6, curK; \
+ vst1.32 {tmp0, tmp1}, [RWK]!; \
+ vadd.u32 tmp3, W5, curK; \
+ vst1.32 {tmp2, tmp3}, [RWK]; \
+
+#define WPRECALC_00_15_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vld1.32 {tmp0, tmp1}, [RDATA]!; \
+
+#define WPRECALC_00_15_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ add RWK, sp, #(WK_offs(0)); \
+
+#define WPRECALC_00_15_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vrev32.8 W0, tmp0; /* big => little */ \
+
+#define WPRECALC_00_15_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vld1.32 {tmp2, tmp3}, [RDATA]!; \
+
+#define WPRECALC_00_15_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp0, W0, curK; \
+
+#define WPRECALC_00_15_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vrev32.8 W7, tmp1; /* big => little */ \
+
+#define WPRECALC_00_15_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vrev32.8 W6, tmp2; /* big => little */ \
+
+#define WPRECALC_00_15_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp1, W7, curK; \
+
+#define WPRECALC_00_15_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vrev32.8 W5, tmp3; /* big => little */ \
+
+#define WPRECALC_00_15_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp2, W6, curK; \
+
+#define WPRECALC_00_15_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vst1.32 {tmp0, tmp1}, [RWK]!; \
+
+#define WPRECALC_00_15_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp3, W5, curK; \
+
+#define WPRECALC_00_15_12(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vst1.32 {tmp2, tmp3}, [RWK]; \
+
+
+/********* Precalc macros for rounds 16-31 ************************************/
+
+#define WPRECALC_16_31_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor tmp0, tmp0; \
+ vext.8 W, W_m16, W_m12, #8; \
+
+#define WPRECALC_16_31_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ add RWK, sp, #(WK_offs(i)); \
+ vext.8 tmp0, W_m04, tmp0, #4; \
+
+#define WPRECALC_16_31_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor tmp0, tmp0, W_m16; \
+ veor.32 W, W, W_m08; \
+
+#define WPRECALC_16_31_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor tmp1, tmp1; \
+ veor W, W, tmp0; \
+
+#define WPRECALC_16_31_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vshl.u32 tmp0, W, #1; \
+
+#define WPRECALC_16_31_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vext.8 tmp1, tmp1, W, #(16-12); \
+ vshr.u32 W, W, #31; \
+
+#define WPRECALC_16_31_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vorr tmp0, tmp0, W; \
+ vshr.u32 W, tmp1, #30; \
+
+#define WPRECALC_16_31_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vshl.u32 tmp1, tmp1, #2; \
+
+#define WPRECALC_16_31_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor tmp0, tmp0, W; \
+
+#define WPRECALC_16_31_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor W, tmp0, tmp1; \
+
+#define WPRECALC_16_31_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp0, W, curK; \
+
+#define WPRECALC_16_31_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vst1.32 {tmp0}, [RWK];
+
+
+/********* Precalc macros for rounds 32-79 ************************************/
+
+#define WPRECALC_32_79_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor W, W_m28; \
+
+#define WPRECALC_32_79_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vext.8 tmp0, W_m08, W_m04, #8; \
+
+#define WPRECALC_32_79_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor W, W_m16; \
+
+#define WPRECALC_32_79_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ veor W, tmp0; \
+
+#define WPRECALC_32_79_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ add RWK, sp, #(WK_offs(i&~3)); \
+
+#define WPRECALC_32_79_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vshl.u32 tmp1, W, #2; \
+
+#define WPRECALC_32_79_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vshr.u32 tmp0, W, #30; \
+
+#define WPRECALC_32_79_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vorr W, tmp0, tmp1; \
+
+#define WPRECALC_32_79_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vadd.u32 tmp0, W, curK; \
+
+#define WPRECALC_32_79_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+ vst1.32 {tmp0}, [RWK];
+
+
+/*
+ * Transform nblks*64 bytes (nblks*16 32-bit words) at DATA.
+ *
+ * unsigned int
+ * sha1_transform_neon (void *ctx, const unsigned char *data,
+ * unsigned int nblks)
+ */
+.align 3
+ENTRY(sha1_transform_neon)
+ /* input:
+ * r0: ctx, CTX
+ * r1: data (64*nblks bytes)
+ * r2: nblks
+ */
+
+ cmp RNBLKS, #0;
+ beq .Ldo_nothing;
+
+ push {r4-r12, lr};
+ /*vpush {q4-q7};*/
+
+ adr RT3, .LK_VEC;
+
+ mov ROLDSTACK, sp;
+
+ /* Align stack. */
+ sub RT0, sp, #(16*4);
+ and RT0, #(~(16-1));
+ mov sp, RT0;
+
+ vld1.32 {qK1-qK2}, [RT3]!; /* Load K1,K2 */
+
+ /* Get the values of the chaining variables. */
+ ldm RSTATE, {_a-_e};
+
+ vld1.32 {qK3-qK4}, [RT3]; /* Load K3,K4 */
+
+#undef curK
+#define curK qK1
+ /* Precalc 0-15. */
+ W_PRECALC_00_15();
+
+.Loop:
+ /* Transform 0-15 + Precalc 16-31. */
+ _R( _a, _b, _c, _d, _e, F1, 0,
+ WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 16,
+ W4, W5, W6, W7, W0, _, _, _ );
+ _R( _e, _a, _b, _c, _d, F1, 1,
+ WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 16,
+ W4, W5, W6, W7, W0, _, _, _ );
+ _R( _d, _e, _a, _b, _c, F1, 2,
+ WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 16,
+ W4, W5, W6, W7, W0, _, _, _ );
+ _R( _c, _d, _e, _a, _b, F1, 3,
+ WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,16,
+ W4, W5, W6, W7, W0, _, _, _ );
+
+#undef curK
+#define curK qK2
+ _R( _b, _c, _d, _e, _a, F1, 4,
+ WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 20,
+ W3, W4, W5, W6, W7, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F1, 5,
+ WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 20,
+ W3, W4, W5, W6, W7, _, _, _ );
+ _R( _e, _a, _b, _c, _d, F1, 6,
+ WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 20,
+ W3, W4, W5, W6, W7, _, _, _ );
+ _R( _d, _e, _a, _b, _c, F1, 7,
+ WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,20,
+ W3, W4, W5, W6, W7, _, _, _ );
+
+ _R( _c, _d, _e, _a, _b, F1, 8,
+ WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 24,
+ W2, W3, W4, W5, W6, _, _, _ );
+ _R( _b, _c, _d, _e, _a, F1, 9,
+ WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 24,
+ W2, W3, W4, W5, W6, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F1, 10,
+ WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 24,
+ W2, W3, W4, W5, W6, _, _, _ );
+ _R( _e, _a, _b, _c, _d, F1, 11,
+ WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,24,
+ W2, W3, W4, W5, W6, _, _, _ );
+
+ _R( _d, _e, _a, _b, _c, F1, 12,
+ WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 28,
+ W1, W2, W3, W4, W5, _, _, _ );
+ _R( _c, _d, _e, _a, _b, F1, 13,
+ WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 28,
+ W1, W2, W3, W4, W5, _, _, _ );
+ _R( _b, _c, _d, _e, _a, F1, 14,
+ WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 28,
+ W1, W2, W3, W4, W5, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F1, 15,
+ WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,28,
+ W1, W2, W3, W4, W5, _, _, _ );
+
+ /* Transform 16-63 + Precalc 32-79. */
+ _R( _e, _a, _b, _c, _d, F1, 16,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 32,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _d, _e, _a, _b, _c, F1, 17,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 32,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _c, _d, _e, _a, _b, F1, 18,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 32,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _b, _c, _d, _e, _a, F1, 19,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 32,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+
+ _R( _a, _b, _c, _d, _e, F2, 20,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 36,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _e, _a, _b, _c, _d, F2, 21,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 36,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _d, _e, _a, _b, _c, F2, 22,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 36,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _c, _d, _e, _a, _b, F2, 23,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 36,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+
+#undef curK
+#define curK qK3
+ _R( _b, _c, _d, _e, _a, F2, 24,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 40,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _a, _b, _c, _d, _e, F2, 25,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 40,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _e, _a, _b, _c, _d, F2, 26,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 40,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _d, _e, _a, _b, _c, F2, 27,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 40,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+
+ _R( _c, _d, _e, _a, _b, F2, 28,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 44,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _b, _c, _d, _e, _a, F2, 29,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 44,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _a, _b, _c, _d, _e, F2, 30,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 44,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _e, _a, _b, _c, _d, F2, 31,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 44,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+
+ _R( _d, _e, _a, _b, _c, F2, 32,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 48,
+ W4, W5, W6, W7, W0, W1, W2, W3);
+ _R( _c, _d, _e, _a, _b, F2, 33,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 48,
+ W4, W5, W6, W7, W0, W1, W2, W3);
+ _R( _b, _c, _d, _e, _a, F2, 34,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 48,
+ W4, W5, W6, W7, W0, W1, W2, W3);
+ _R( _a, _b, _c, _d, _e, F2, 35,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 48,
+ W4, W5, W6, W7, W0, W1, W2, W3);
+
+ _R( _e, _a, _b, _c, _d, F2, 36,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 52,
+ W3, W4, W5, W6, W7, W0, W1, W2);
+ _R( _d, _e, _a, _b, _c, F2, 37,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 52,
+ W3, W4, W5, W6, W7, W0, W1, W2);
+ _R( _c, _d, _e, _a, _b, F2, 38,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 52,
+ W3, W4, W5, W6, W7, W0, W1, W2);
+ _R( _b, _c, _d, _e, _a, F2, 39,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 52,
+ W3, W4, W5, W6, W7, W0, W1, W2);
+
+ _R( _a, _b, _c, _d, _e, F3, 40,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 56,
+ W2, W3, W4, W5, W6, W7, W0, W1);
+ _R( _e, _a, _b, _c, _d, F3, 41,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 56,
+ W2, W3, W4, W5, W6, W7, W0, W1);
+ _R( _d, _e, _a, _b, _c, F3, 42,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 56,
+ W2, W3, W4, W5, W6, W7, W0, W1);
+ _R( _c, _d, _e, _a, _b, F3, 43,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 56,
+ W2, W3, W4, W5, W6, W7, W0, W1);
+
+#undef curK
+#define curK qK4
+ _R( _b, _c, _d, _e, _a, F3, 44,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 60,
+ W1, W2, W3, W4, W5, W6, W7, W0);
+ _R( _a, _b, _c, _d, _e, F3, 45,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 60,
+ W1, W2, W3, W4, W5, W6, W7, W0);
+ _R( _e, _a, _b, _c, _d, F3, 46,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 60,
+ W1, W2, W3, W4, W5, W6, W7, W0);
+ _R( _d, _e, _a, _b, _c, F3, 47,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 60,
+ W1, W2, W3, W4, W5, W6, W7, W0);
+
+ _R( _c, _d, _e, _a, _b, F3, 48,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 64,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _b, _c, _d, _e, _a, F3, 49,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 64,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _a, _b, _c, _d, _e, F3, 50,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 64,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+ _R( _e, _a, _b, _c, _d, F3, 51,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 64,
+ W0, W1, W2, W3, W4, W5, W6, W7);
+
+ _R( _d, _e, _a, _b, _c, F3, 52,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 68,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _c, _d, _e, _a, _b, F3, 53,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 68,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _b, _c, _d, _e, _a, F3, 54,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 68,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+ _R( _a, _b, _c, _d, _e, F3, 55,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 68,
+ W7, W0, W1, W2, W3, W4, W5, W6);
+
+ _R( _e, _a, _b, _c, _d, F3, 56,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 72,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _d, _e, _a, _b, _c, F3, 57,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 72,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _c, _d, _e, _a, _b, F3, 58,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 72,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+ _R( _b, _c, _d, _e, _a, F3, 59,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 72,
+ W6, W7, W0, W1, W2, W3, W4, W5);
+
+ subs RNBLKS, #1;
+
+ _R( _a, _b, _c, _d, _e, F4, 60,
+ WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 76,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _e, _a, _b, _c, _d, F4, 61,
+ WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 76,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _d, _e, _a, _b, _c, F4, 62,
+ WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 76,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+ _R( _c, _d, _e, _a, _b, F4, 63,
+ WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 76,
+ W5, W6, W7, W0, W1, W2, W3, W4);
+
+ beq .Lend;
+
+ /* Transform 64-79 + Precalc 0-15 of next block. */
+#undef curK
+#define curK qK1
+ _R( _b, _c, _d, _e, _a, F4, 64,
+ WPRECALC_00_15_0, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F4, 65,
+ WPRECALC_00_15_1, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _e, _a, _b, _c, _d, F4, 66,
+ WPRECALC_00_15_2, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _d, _e, _a, _b, _c, F4, 67,
+ WPRECALC_00_15_3, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+ _R( _c, _d, _e, _a, _b, F4, 68,
+ dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _b, _c, _d, _e, _a, F4, 69,
+ dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F4, 70,
+ WPRECALC_00_15_4, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _e, _a, _b, _c, _d, F4, 71,
+ WPRECALC_00_15_5, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+ _R( _d, _e, _a, _b, _c, F4, 72,
+ dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _c, _d, _e, _a, _b, F4, 73,
+ dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _b, _c, _d, _e, _a, F4, 74,
+ WPRECALC_00_15_6, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _a, _b, _c, _d, _e, F4, 75,
+ WPRECALC_00_15_7, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+ _R( _e, _a, _b, _c, _d, F4, 76,
+ WPRECALC_00_15_8, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _d, _e, _a, _b, _c, F4, 77,
+ WPRECALC_00_15_9, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _c, _d, _e, _a, _b, F4, 78,
+ WPRECALC_00_15_10, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+ _R( _b, _c, _d, _e, _a, F4, 79,
+ WPRECALC_00_15_11, dummy, WPRECALC_00_15_12, _, _, _, _, _, _, _, _, _ );
+
+ /* Update the chaining variables. */
+ ldm RSTATE, {RT0-RT3};
+ add _a, RT0;
+ ldr RT0, [RSTATE, #state_h4];
+ add _b, RT1;
+ add _c, RT2;
+ add _d, RT3;
+ add _e, RT0;
+ stm RSTATE, {_a-_e};
+
+ b .Loop;
+
+.Lend:
+ /* Transform 64-79 */
+ R( _b, _c, _d, _e, _a, F4, 64 );
+ R( _a, _b, _c, _d, _e, F4, 65 );
+ R( _e, _a, _b, _c, _d, F4, 66 );
+ R( _d, _e, _a, _b, _c, F4, 67 );
+ R( _c, _d, _e, _a, _b, F4, 68 );
+ R( _b, _c, _d, _e, _a, F4, 69 );
+ R( _a, _b, _c, _d, _e, F4, 70 );
+ R( _e, _a, _b, _c, _d, F4, 71 );
+ R( _d, _e, _a, _b, _c, F4, 72 );
+ R( _c, _d, _e, _a, _b, F4, 73 );
+ R( _b, _c, _d, _e, _a, F4, 74 );
+ R( _a, _b, _c, _d, _e, F4, 75 );
+ R( _e, _a, _b, _c, _d, F4, 76 );
+ R( _d, _e, _a, _b, _c, F4, 77 );
+ R( _c, _d, _e, _a, _b, F4, 78 );
+ R( _b, _c, _d, _e, _a, F4, 79 );
+
+ mov sp, ROLDSTACK;
+
+ /* Update the chaining variables. */
+ ldm RSTATE, {RT0-RT3};
+ add _a, RT0;
+ ldr RT0, [RSTATE, #state_h4];
+ add _b, RT1;
+ add _c, RT2;
+ add _d, RT3;
+ /*vpop {q4-q7};*/
+ add _e, RT0;
+ stm RSTATE, {_a-_e};
+
+ pop {r4-r12, pc};
+
+.Ldo_nothing:
+ bx lr
+ENDPROC(sha1_transform_neon)
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index ace4cd6..e31b044 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -23,32 +23,27 @@
#include <linux/types.h>
#include <crypto/sha.h>
#include <asm/byteorder.h>
+#include <asm/crypto/sha1.h>
-struct SHA1_CTX {
- uint32_t h0,h1,h2,h3,h4;
- u64 count;
- u8 data[SHA1_BLOCK_SIZE];
-};
-asmlinkage void sha1_block_data_order(struct SHA1_CTX *digest,
+asmlinkage void sha1_block_data_order(u32 *digest,
const unsigned char *data, unsigned int rounds);
static int sha1_init(struct shash_desc *desc)
{
- struct SHA1_CTX *sctx = shash_desc_ctx(desc);
- memset(sctx, 0, sizeof(*sctx));
- sctx->h0 = SHA1_H0;
- sctx->h1 = SHA1_H1;
- sctx->h2 = SHA1_H2;
- sctx->h3 = SHA1_H3;
- sctx->h4 = SHA1_H4;
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha1_state){
+ .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+ };
+
return 0;
}
-static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
- unsigned int len, unsigned int partial)
+static int __sha1_update(struct sha1_state *sctx, const u8 *data,
+ unsigned int len, unsigned int partial)
{
unsigned int done = 0;
@@ -56,43 +51,44 @@
if (partial) {
done = SHA1_BLOCK_SIZE - partial;
- memcpy(sctx->data + partial, data, done);
- sha1_block_data_order(sctx, sctx->data, 1);
+ memcpy(sctx->buffer + partial, data, done);
+ sha1_block_data_order(sctx->state, sctx->buffer, 1);
}
if (len - done >= SHA1_BLOCK_SIZE) {
const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
- sha1_block_data_order(sctx, data + done, rounds);
+ sha1_block_data_order(sctx->state, data + done, rounds);
done += rounds * SHA1_BLOCK_SIZE;
}
- memcpy(sctx->data, data + done, len - done);
+ memcpy(sctx->buffer, data + done, len - done);
return 0;
}
-static int sha1_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
+int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
{
- struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+ struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
int res;
/* Handle the fast case right here */
if (partial + len < SHA1_BLOCK_SIZE) {
sctx->count += len;
- memcpy(sctx->data + partial, data, len);
+ memcpy(sctx->buffer + partial, data, len);
return 0;
}
res = __sha1_update(sctx, data, len, partial);
return res;
}
+EXPORT_SYMBOL_GPL(sha1_update_arm);
/* Add padding and return the message digest. */
static int sha1_final(struct shash_desc *desc, u8 *out)
{
- struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+ struct sha1_state *sctx = shash_desc_ctx(desc);
unsigned int i, index, padlen;
__be32 *dst = (__be32 *)out;
__be64 bits;
@@ -106,7 +102,7 @@
/* We need to fill a whole block for __sha1_update() */
if (padlen <= 56) {
sctx->count += padlen;
- memcpy(sctx->data + index, padding, padlen);
+ memcpy(sctx->buffer + index, padding, padlen);
} else {
__sha1_update(sctx, padding, padlen, index);
}
@@ -114,7 +110,7 @@
/* Store state in digest */
for (i = 0; i < 5; i++)
- dst[i] = cpu_to_be32(((u32 *)sctx)[i]);
+ dst[i] = cpu_to_be32(sctx->state[i]);
/* Wipe context */
memset(sctx, 0, sizeof(*sctx));
@@ -124,7 +120,7 @@
static int sha1_export(struct shash_desc *desc, void *out)
{
- struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+ struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(out, sctx, sizeof(*sctx));
return 0;
}
@@ -132,7 +128,7 @@
static int sha1_import(struct shash_desc *desc, const void *in)
{
- struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+ struct sha1_state *sctx = shash_desc_ctx(desc);
memcpy(sctx, in, sizeof(*sctx));
return 0;
}
@@ -141,12 +137,12 @@
static struct shash_alg alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_init,
- .update = sha1_update,
+ .update = sha1_update_arm,
.final = sha1_final,
.export = sha1_export,
.import = sha1_import,
- .descsize = sizeof(struct SHA1_CTX),
- .statesize = sizeof(struct SHA1_CTX),
+ .descsize = sizeof(struct sha1_state),
+ .statesize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name= "sha1-asm",
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
new file mode 100644
index 0000000..6f1b411
--- /dev/null
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -0,0 +1,197 @@
+/*
+ * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
+ * ARM NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha1_generic.c and sha1_ssse3_glue.c:
+ * Copyright (c) Alan Smithee.
+ * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
+ * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
+ * Copyright (c) Mathias Krause <minipli@googlemail.com>
+ * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/crypto/sha1.h>
+
+
+asmlinkage void sha1_transform_neon(void *state_h, const char *data,
+ unsigned int rounds);
+
+
+static int sha1_neon_init(struct shash_desc *desc)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha1_state){
+ .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+ };
+
+ return 0;
+}
+
+static int __sha1_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len, unsigned int partial)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int done = 0;
+
+ sctx->count += len;
+
+ if (partial) {
+ done = SHA1_BLOCK_SIZE - partial;
+ memcpy(sctx->buffer + partial, data, done);
+ sha1_transform_neon(sctx->state, sctx->buffer, 1);
+ }
+
+ if (len - done >= SHA1_BLOCK_SIZE) {
+ const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
+
+ sha1_transform_neon(sctx->state, data + done, rounds);
+ done += rounds * SHA1_BLOCK_SIZE;
+ }
+
+ memcpy(sctx->buffer, data + done, len - done);
+
+ return 0;
+}
+
+static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+ int res;
+
+ /* Handle the fast case right here */
+ if (partial + len < SHA1_BLOCK_SIZE) {
+ sctx->count += len;
+ memcpy(sctx->buffer + partial, data, len);
+
+ return 0;
+ }
+
+ if (!may_use_simd()) {
+ res = sha1_update_arm(desc, data, len);
+ } else {
+ kernel_neon_begin();
+ res = __sha1_neon_update(desc, data, len, partial);
+ kernel_neon_end();
+ }
+
+ return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha1_neon_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int i, index, padlen;
+ __be32 *dst = (__be32 *)out;
+ __be64 bits;
+ static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+ bits = cpu_to_be64(sctx->count << 3);
+
+ /* Pad out to 56 mod 64 and append length */
+ index = sctx->count % SHA1_BLOCK_SIZE;
+ padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index);
+ if (!may_use_simd()) {
+ sha1_update_arm(desc, padding, padlen);
+ sha1_update_arm(desc, (const u8 *)&bits, sizeof(bits));
+ } else {
+ kernel_neon_begin();
+ /* We need to fill a whole block for __sha1_neon_update() */
+ if (padlen <= 56) {
+ sctx->count += padlen;
+ memcpy(sctx->buffer + index, padding, padlen);
+ } else {
+ __sha1_neon_update(desc, padding, padlen, index);
+ }
+ __sha1_neon_update(desc, (const u8 *)&bits, sizeof(bits), 56);
+ kernel_neon_end();
+ }
+
+ /* Store state in digest */
+ for (i = 0; i < 5; i++)
+ dst[i] = cpu_to_be32(sctx->state[i]);
+
+ /* Wipe context */
+ memset(sctx, 0, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha1_neon_export(struct shash_desc *desc, void *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(out, sctx, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha1_neon_import(struct shash_desc *desc, const void *in)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(sctx, in, sizeof(*sctx));
+
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .digestsize = SHA1_DIGEST_SIZE,
+ .init = sha1_neon_init,
+ .update = sha1_neon_update,
+ .final = sha1_neon_final,
+ .export = sha1_neon_export,
+ .import = sha1_neon_import,
+ .descsize = sizeof(struct sha1_state),
+ .statesize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-neon",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init sha1_neon_mod_init(void)
+{
+ if (!cpu_has_neon())
+ return -ENODEV;
+
+ return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_neon_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_init(sha1_neon_mod_init);
+module_exit(sha1_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
+MODULE_ALIAS("sha1");
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
new file mode 100644
index 0000000..fac0533
--- /dev/null
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -0,0 +1,716 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA256 block procedure for ARMv4. May 2007.
+
+# Performance is ~2x better than gcc 3.4 generated code and in "abso-
+# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
+# byte [on single-issue Xscale PXA250 core].
+
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 22% improvement on
+# Cortex A8 core and ~20 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 16%
+# improvement on Cortex A8 core and ~15.4 cycles per processed byte.
+
+# September 2013.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process one
+# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
+# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
+# code (meaning that latter performs sub-optimally, nothing was done
+# about it).
+
+# May 2014.
+#
+# Add ARMv8 code path performing at 2.0 cpb on Apple A7.
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0"; $t0="r0";
+$inp="r1"; $t4="r1";
+$len="r2"; $t1="r2";
+$T1="r3"; $t3="r3";
+$A="r4";
+$B="r5";
+$C="r6";
+$D="r7";
+$E="r8";
+$F="r9";
+$G="r10";
+$H="r11";
+@V=($A,$B,$C,$D,$E,$F,$G,$H);
+$t2="r12";
+$Ktbl="r14";
+
+@Sigma0=( 2,13,22);
+@Sigma1=( 6,11,25);
+@sigma0=( 7,18, 3);
+@sigma1=(17,19,10);
+
+sub BODY_00_15 {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___ if ($i<16);
+#if __ARM_ARCH__>=7
+ @ ldr $t1,[$inp],#4 @ $i
+# if $i==15
+ str $inp,[sp,#17*4] @ make room for $t4
+# endif
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+# ifndef __ARMEB__
+ rev $t1,$t1
+# endif
+#else
+ @ ldrb $t1,[$inp,#3] @ $i
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ ldrb $t2,[$inp,#2]
+ ldrb $t0,[$inp,#1]
+ orr $t1,$t1,$t2,lsl#8
+ ldrb $t2,[$inp],#4
+ orr $t1,$t1,$t0,lsl#16
+# if $i==15
+ str $inp,[sp,#17*4] @ make room for $t4
+# endif
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+ orr $t1,$t1,$t2,lsl#24
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+#endif
+___
+$code.=<<___;
+ ldr $t2,[$Ktbl],#4 @ *K256++
+ add $h,$h,$t1 @ h+=X[i]
+ str $t1,[sp,#`$i%16`*4]
+ eor $t1,$f,$g
+ add $h,$h,$t0,ror#$Sigma1[0] @ h+=Sigma1(e)
+ and $t1,$t1,$e
+ add $h,$h,$t2 @ h+=K256[i]
+ eor $t1,$t1,$g @ Ch(e,f,g)
+ eor $t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]`
+ add $h,$h,$t1 @ h+=Ch(e,f,g)
+#if $i==31
+ and $t2,$t2,#0xff
+ cmp $t2,#0xf2 @ done?
+#endif
+#if $i<15
+# if __ARM_ARCH__>=7
+ ldr $t1,[$inp],#4 @ prefetch
+# else
+ ldrb $t1,[$inp,#3]
+# endif
+ eor $t2,$a,$b @ a^b, b^c in next round
+#else
+ ldr $t1,[sp,#`($i+2)%16`*4] @ from future BODY_16_xx
+ eor $t2,$a,$b @ a^b, b^c in next round
+ ldr $t4,[sp,#`($i+15)%16`*4] @ from future BODY_16_xx
+#endif
+ eor $t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]` @ Sigma0(a)
+ and $t3,$t3,$t2 @ (b^c)&=(a^b)
+ add $d,$d,$h @ d+=h
+ eor $t3,$t3,$b @ Maj(a,b,c)
+ add $h,$h,$t0,ror#$Sigma0[0] @ h+=Sigma0(a)
+ @ add $h,$h,$t3 @ h+=Maj(a,b,c)
+___
+ ($t2,$t3)=($t3,$t2);
+}
+
+sub BODY_16_XX {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___;
+ @ ldr $t1,[sp,#`($i+1)%16`*4] @ $i
+ @ ldr $t4,[sp,#`($i+14)%16`*4]
+ mov $t0,$t1,ror#$sigma0[0]
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ mov $t2,$t4,ror#$sigma1[0]
+ eor $t0,$t0,$t1,ror#$sigma0[1]
+ eor $t2,$t2,$t4,ror#$sigma1[1]
+ eor $t0,$t0,$t1,lsr#$sigma0[2] @ sigma0(X[i+1])
+ ldr $t1,[sp,#`($i+0)%16`*4]
+ eor $t2,$t2,$t4,lsr#$sigma1[2] @ sigma1(X[i+14])
+ ldr $t4,[sp,#`($i+9)%16`*4]
+
+ add $t2,$t2,$t0
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` @ from BODY_00_15
+ add $t1,$t1,$t2
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+ add $t1,$t1,$t4 @ X[i]
+___
+ &BODY_00_15(@_);
+}
+
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code 32
+#else
+.syntax unified
+# ifdef __thumb2__
+# define adrl adr
+.thumb
+# else
+.code 32
+# endif
+#endif
+
+.type K256,%object
+.align 5
+K256:
+.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+.size K256,.-K256
+.word 0 @ terminator
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word OPENSSL_armcap_P-sha256_block_data_order
+#endif
+.align 5
+
+.global sha256_block_data_order
+.type sha256_block_data_order,%function
+sha256_block_data_order:
+#if __ARM_ARCH__<7
+ sub r3,pc,#8 @ sha256_block_data_order
+#else
+ adr r3,sha256_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ ldr r12,.LOPENSSL_armcap
+ ldr r12,[r3,r12] @ OPENSSL_armcap_P
+ tst r12,#ARMV8_SHA256
+ bne .LARMv8
+ tst r12,#ARMV7_NEON
+ bne .LNEON
+#endif
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+ stmdb sp!,{$ctx,$inp,$len,r4-r11,lr}
+ ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H}
+ sub $Ktbl,r3,#256+32 @ K256
+ sub sp,sp,#16*4 @ alloca(X[16])
+.Loop:
+# if __ARM_ARCH__>=7
+ ldr $t1,[$inp],#4
+# else
+ ldrb $t1,[$inp,#3]
+# endif
+ eor $t3,$B,$C @ magic
+ eor $t2,$t2,$t2
+___
+for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=".Lrounds_16_xx:\n";
+for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+#if __ARM_ARCH__>=7
+ ite eq @ Thumb2 thing, sanity check in ARM
+#endif
+ ldreq $t3,[sp,#16*4] @ pull ctx
+ bne .Lrounds_16_xx
+
+ add $A,$A,$t2 @ h+=Maj(a,b,c) from the past
+ ldr $t0,[$t3,#0]
+ ldr $t1,[$t3,#4]
+ ldr $t2,[$t3,#8]
+ add $A,$A,$t0
+ ldr $t0,[$t3,#12]
+ add $B,$B,$t1
+ ldr $t1,[$t3,#16]
+ add $C,$C,$t2
+ ldr $t2,[$t3,#20]
+ add $D,$D,$t0
+ ldr $t0,[$t3,#24]
+ add $E,$E,$t1
+ ldr $t1,[$t3,#28]
+ add $F,$F,$t2
+ ldr $inp,[sp,#17*4] @ pull inp
+ ldr $t2,[sp,#18*4] @ pull inp+len
+ add $G,$G,$t0
+ add $H,$H,$t1
+ stmia $t3,{$A,$B,$C,$D,$E,$F,$G,$H}
+ cmp $inp,$t2
+ sub $Ktbl,$Ktbl,#256 @ rewind Ktbl
+ bne .Loop
+
+ add sp,sp,#`16+3`*4 @ destroy frame
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r4-r11,pc}
+#else
+ ldmia sp!,{r4-r11,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size sha256_block_data_order,.-sha256_block_data_order
+___
+######################################################################
+# NEON stuff
+#
+{{{
+my @X=map("q$_",(0..3));
+my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25");
+my $Xfer=$t4;
+my $j=0;
+
+sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; }
+sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; }
+
+sub AUTOLOAD() # thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+ my $arg = pop;
+ $arg = "#$arg" if ($arg*1 eq $arg);
+ $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+sub Xupdate()
+{ use integer;
+ my $body = shift;
+ my @insns = (&$body,&$body,&$body,&$body);
+ my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+ &vext_8 ($T0,@X[0],@X[1],4); # X[1..4]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vext_8 ($T1,@X[2],@X[3],4); # X[9..12]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T2,$T0,$sigma0[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += X[9..12]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T1,$T0,$sigma0[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T2,$T0,32-$sigma0[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T3,$T0,$sigma0[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T1,$T1,$T2);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T3,$T0,32-$sigma0[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T1,$T1,$T3); # sigma0(X[1..4])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T5,&Dhi(@X[3]),$sigma1[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += sigma0(X[1..4])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4); # sigma1(X[14..15])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T5,&Dlo(@X[0]),$sigma1[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vld1_32 ("{$T0}","[$Ktbl,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4); # sigma1(X[16..17])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 ($T0,$T0,@X[0]);
+ while($#insns>=2) { eval(shift(@insns)); }
+ &vst1_32 ("{$T0}","[$Xfer,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+
+ push(@X,shift(@X)); # "rotate" X[]
+}
+
+sub Xpreload()
+{ use integer;
+ my $body = shift;
+ my @insns = (&$body,&$body,&$body,&$body);
+ my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vld1_32 ("{$T0}","[$Ktbl,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vrev32_8 (@X[0],@X[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 ($T0,$T0,@X[0]);
+ foreach (@insns) { eval; } # remaining instructions
+ &vst1_32 ("{$T0}","[$Xfer,:128]!");
+
+ push(@X,shift(@X)); # "rotate" X[]
+}
+
+sub body_00_15 () {
+ (
+ '($a,$b,$c,$d,$e,$f,$g,$h)=@V;'.
+ '&add ($h,$h,$t1)', # h+=X[i]+K[i]
+ '&eor ($t1,$f,$g)',
+ '&eor ($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))',
+ '&add ($a,$a,$t2)', # h+=Maj(a,b,c) from the past
+ '&and ($t1,$t1,$e)',
+ '&eor ($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))', # Sigma1(e)
+ '&eor ($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))',
+ '&eor ($t1,$t1,$g)', # Ch(e,f,g)
+ '&add ($h,$h,$t2,"ror#$Sigma1[0]")', # h+=Sigma1(e)
+ '&eor ($t2,$a,$b)', # a^b, b^c in next round
+ '&eor ($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))', # Sigma0(a)
+ '&add ($h,$h,$t1)', # h+=Ch(e,f,g)
+ '&ldr ($t1,sprintf "[sp,#%d]",4*(($j+1)&15)) if (($j&15)!=15);'.
+ '&ldr ($t1,"[$Ktbl]") if ($j==15);'.
+ '&ldr ($t1,"[sp,#64]") if ($j==31)',
+ '&and ($t3,$t3,$t2)', # (b^c)&=(a^b)
+ '&add ($d,$d,$h)', # d+=h
+ '&add ($h,$h,$t0,"ror#$Sigma0[0]");'. # h+=Sigma0(a)
+ '&eor ($t3,$t3,$b)', # Maj(a,b,c)
+ '$j++; unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);'
+ )
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
+.fpu neon
+
+.global sha256_block_data_order_neon
+.type sha256_block_data_order_neon,%function
+.align 4
+sha256_block_data_order_neon:
+.LNEON:
+ stmdb sp!,{r4-r12,lr}
+
+ sub $H,sp,#16*4+16
+ adrl $Ktbl,K256
+ bic $H,$H,#15 @ align for 128-bit stores
+ mov $t2,sp
+ mov sp,$H @ alloca
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+
+ vld1.8 {@X[0]},[$inp]!
+ vld1.8 {@X[1]},[$inp]!
+ vld1.8 {@X[2]},[$inp]!
+ vld1.8 {@X[3]},[$inp]!
+ vld1.32 {$T0},[$Ktbl,:128]!
+ vld1.32 {$T1},[$Ktbl,:128]!
+ vld1.32 {$T2},[$Ktbl,:128]!
+ vld1.32 {$T3},[$Ktbl,:128]!
+ vrev32.8 @X[0],@X[0] @ yes, even on
+ str $ctx,[sp,#64]
+ vrev32.8 @X[1],@X[1] @ big-endian
+ str $inp,[sp,#68]
+ mov $Xfer,sp
+ vrev32.8 @X[2],@X[2]
+ str $len,[sp,#72]
+ vrev32.8 @X[3],@X[3]
+ str $t2,[sp,#76] @ save original sp
+ vadd.i32 $T0,$T0,@X[0]
+ vadd.i32 $T1,$T1,@X[1]
+ vst1.32 {$T0},[$Xfer,:128]!
+ vadd.i32 $T2,$T2,@X[2]
+ vst1.32 {$T1},[$Xfer,:128]!
+ vadd.i32 $T3,$T3,@X[3]
+ vst1.32 {$T2},[$Xfer,:128]!
+ vst1.32 {$T3},[$Xfer,:128]!
+
+ ldmia $ctx,{$A-$H}
+ sub $Xfer,$Xfer,#64
+ ldr $t1,[sp,#0]
+ eor $t2,$t2,$t2
+ eor $t3,$B,$C
+ b .L_00_48
+
+.align 4
+.L_00_48:
+___
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+$code.=<<___;
+ teq $t1,#0 @ check for K256 terminator
+ ldr $t1,[sp,#0]
+ sub $Xfer,$Xfer,#64
+ bne .L_00_48
+
+ ldr $inp,[sp,#68]
+ ldr $t0,[sp,#72]
+ sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl
+ teq $inp,$t0
+ it eq
+ subeq $inp,$inp,#64 @ avoid SEGV
+ vld1.8 {@X[0]},[$inp]! @ load next input block
+ vld1.8 {@X[1]},[$inp]!
+ vld1.8 {@X[2]},[$inp]!
+ vld1.8 {@X[3]},[$inp]!
+ it ne
+ strne $inp,[sp,#68]
+ mov $Xfer,sp
+___
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+$code.=<<___;
+ ldr $t0,[$t1,#0]
+ add $A,$A,$t2 @ h+=Maj(a,b,c) from the past
+ ldr $t2,[$t1,#4]
+ ldr $t3,[$t1,#8]
+ ldr $t4,[$t1,#12]
+ add $A,$A,$t0 @ accumulate
+ ldr $t0,[$t1,#16]
+ add $B,$B,$t2
+ ldr $t2,[$t1,#20]
+ add $C,$C,$t3
+ ldr $t3,[$t1,#24]
+ add $D,$D,$t4
+ ldr $t4,[$t1,#28]
+ add $E,$E,$t0
+ str $A,[$t1],#4
+ add $F,$F,$t2
+ str $B,[$t1],#4
+ add $G,$G,$t3
+ str $C,[$t1],#4
+ add $H,$H,$t4
+ str $D,[$t1],#4
+ stmia $t1,{$E-$H}
+
+ ittte ne
+ movne $Xfer,sp
+ ldrne $t1,[sp,#0]
+ eorne $t2,$t2,$t2
+ ldreq sp,[sp,#76] @ restore original sp
+ itt ne
+ eorne $t3,$B,$C
+ bne .L_00_48
+
+ ldmia sp!,{r4-r12,pc}
+.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+___
+}}}
+######################################################################
+# ARMv8 stuff
+#
+{{{
+my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2));
+my @MSG=map("q$_",(8..11));
+my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15));
+my $Ktbl="r3";
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# ifdef __thumb2__
+# define INST(a,b,c,d) .byte c,d|0xc,a,b
+# else
+# define INST(a,b,c,d) .byte a,b,c,d
+# endif
+
+.type sha256_block_data_order_armv8,%function
+.align 5
+sha256_block_data_order_armv8:
+.LARMv8:
+ vld1.32 {$ABCD,$EFGH},[$ctx]
+# ifdef __thumb2__
+ adr $Ktbl,.LARMv8
+ sub $Ktbl,$Ktbl,#.LARMv8-K256
+# else
+ adrl $Ktbl,K256
+# endif
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+
+.Loop_v8:
+ vld1.8 {@MSG[0]-@MSG[1]},[$inp]!
+ vld1.8 {@MSG[2]-@MSG[3]},[$inp]!
+ vld1.32 {$W0},[$Ktbl]!
+ vrev32.8 @MSG[0],@MSG[0]
+ vrev32.8 @MSG[1],@MSG[1]
+ vrev32.8 @MSG[2],@MSG[2]
+ vrev32.8 @MSG[3],@MSG[3]
+ vmov $ABCD_SAVE,$ABCD @ offload
+ vmov $EFGH_SAVE,$EFGH
+ teq $inp,$len
+___
+for($i=0;$i<12;$i++) {
+$code.=<<___;
+ vld1.32 {$W1},[$Ktbl]!
+ vadd.i32 $W0,$W0,@MSG[0]
+ sha256su0 @MSG[0],@MSG[1]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+ sha256su1 @MSG[0],@MSG[2],@MSG[3]
+___
+ ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG));
+}
+$code.=<<___;
+ vld1.32 {$W1},[$Ktbl]!
+ vadd.i32 $W0,$W0,@MSG[0]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+
+ vld1.32 {$W0},[$Ktbl]!
+ vadd.i32 $W1,$W1,@MSG[1]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W1
+ sha256h2 $EFGH,$abcd,$W1
+
+ vld1.32 {$W1},[$Ktbl]
+ vadd.i32 $W0,$W0,@MSG[2]
+ sub $Ktbl,$Ktbl,#256-16 @ rewind
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+
+ vadd.i32 $W1,$W1,@MSG[3]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W1
+ sha256h2 $EFGH,$abcd,$W1
+
+ vadd.i32 $ABCD,$ABCD,$ABCD_SAVE
+ vadd.i32 $EFGH,$EFGH,$EFGH_SAVE
+ it ne
+ bne .Loop_v8
+
+ vst1.32 {$ABCD,$EFGH},[$ctx]
+
+ ret @ bx lr
+.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
+#endif
+___
+}}}
+$code.=<<___;
+.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align 2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm OPENSSL_armcap_P,4,4
+#endif
+___
+
+open SELF,$0;
+while(<SELF>) {
+ next if (/^#!/);
+ last if (!s/^#/@/ and !/^$/);
+ print;
+}
+close SELF;
+
+{ my %opcode = (
+ "sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40,
+ "sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 );
+
+ sub unsha256 {
+ my ($mnemonic,$arg)=@_;
+
+ if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) {
+ my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19)
+ |(($2&7)<<17)|(($2&8)<<4)
+ |(($3&7)<<1) |(($3&8)<<2);
+ # since ARMv7 instructions are always encoded little-endian.
+ # correct solution is to use .inst directive, but older
+ # assemblers don't implement it:-(
+ sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s",
+ $word&0xff,($word>>8)&0xff,
+ ($word>>16)&0xff,($word>>24)&0xff,
+ $mnemonic,$arg;
+ }
+ }
+}
+
+foreach (split($/,$code)) {
+
+ s/\`([^\`]*)\`/eval $1/geo;
+
+ s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo;
+
+ s/\bret\b/bx lr/go or
+ s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4
+
+ print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
new file mode 100644
index 0000000..555a1a8
--- /dev/null
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -0,0 +1,2808 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA256 block procedure for ARMv4. May 2007.
+
+@ Performance is ~2x better than gcc 3.4 generated code and in "abso-
+@ lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
+@ byte [on single-issue Xscale PXA250 core].
+
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 22% improvement on
+@ Cortex A8 core and ~20 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 16%
+@ improvement on Cortex A8 core and ~15.4 cycles per processed byte.
+
+@ September 2013.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process one
+@ byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
+@ S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
+@ code (meaning that latter performs sub-optimally, nothing was done
+@ about it).
+
+@ May 2014.
+@
+@ Add ARMv8 code path performing at 2.0 cpb on Apple A7.
+
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code 32
+#else
+.syntax unified
+# ifdef __thumb2__
+# define adrl adr
+.thumb
+# else
+.code 32
+# endif
+#endif
+
+.type K256,%object
+.align 5
+K256:
+.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+.size K256,.-K256
+.word 0 @ terminator
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word OPENSSL_armcap_P-sha256_block_data_order
+#endif
+.align 5
+
+.global sha256_block_data_order
+.type sha256_block_data_order,%function
+sha256_block_data_order:
+#if __ARM_ARCH__<7
+ sub r3,pc,#8 @ sha256_block_data_order
+#else
+ adr r3,sha256_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ ldr r12,.LOPENSSL_armcap
+ ldr r12,[r3,r12] @ OPENSSL_armcap_P
+ tst r12,#ARMV8_SHA256
+ bne .LARMv8
+ tst r12,#ARMV7_NEON
+ bne .LNEON
+#endif
+ add r2,r1,r2,lsl#6 @ len to point at the end of inp
+ stmdb sp!,{r0,r1,r2,r4-r11,lr}
+ ldmia r0,{r4,r5,r6,r7,r8,r9,r10,r11}
+ sub r14,r3,#256+32 @ K256
+ sub sp,sp,#16*4 @ alloca(X[16])
+.Loop:
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r5,r6 @ magic
+ eor r12,r12,r12
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 0
+# if 0==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r8,r8,ror#5
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 0
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 0==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r8,r8,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r11,r11,r2 @ h+=X[i]
+ str r2,[sp,#0*4]
+ eor r2,r9,r10
+ add r11,r11,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r8
+ add r11,r11,r12 @ h+=K256[i]
+ eor r2,r2,r10 @ Ch(e,f,g)
+ eor r0,r4,r4,ror#11
+ add r11,r11,r2 @ h+=Ch(e,f,g)
+#if 0==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 0<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r4,r5 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#2*4] @ from future BODY_16_xx
+ eor r12,r4,r5 @ a^b, b^c in next round
+ ldr r1,[sp,#15*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r4,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r7,r7,r11 @ d+=h
+ eor r3,r3,r5 @ Maj(a,b,c)
+ add r11,r11,r0,ror#2 @ h+=Sigma0(a)
+ @ add r11,r11,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 1
+# if 1==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r7,r7,ror#5
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 1
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 1==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r7,r7,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r10,r10,r2 @ h+=X[i]
+ str r2,[sp,#1*4]
+ eor r2,r8,r9
+ add r10,r10,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r7
+ add r10,r10,r3 @ h+=K256[i]
+ eor r2,r2,r9 @ Ch(e,f,g)
+ eor r0,r11,r11,ror#11
+ add r10,r10,r2 @ h+=Ch(e,f,g)
+#if 1==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 1<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r11,r4 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#3*4] @ from future BODY_16_xx
+ eor r3,r11,r4 @ a^b, b^c in next round
+ ldr r1,[sp,#0*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r11,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r6,r6,r10 @ d+=h
+ eor r12,r12,r4 @ Maj(a,b,c)
+ add r10,r10,r0,ror#2 @ h+=Sigma0(a)
+ @ add r10,r10,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 2
+# if 2==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 2
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 2==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r6,r6,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r9,r9,r2 @ h+=X[i]
+ str r2,[sp,#2*4]
+ eor r2,r7,r8
+ add r9,r9,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r6
+ add r9,r9,r12 @ h+=K256[i]
+ eor r2,r2,r8 @ Ch(e,f,g)
+ eor r0,r10,r10,ror#11
+ add r9,r9,r2 @ h+=Ch(e,f,g)
+#if 2==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 2<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r10,r11 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#4*4] @ from future BODY_16_xx
+ eor r12,r10,r11 @ a^b, b^c in next round
+ ldr r1,[sp,#1*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r10,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r5,r5,r9 @ d+=h
+ eor r3,r3,r11 @ Maj(a,b,c)
+ add r9,r9,r0,ror#2 @ h+=Sigma0(a)
+ @ add r9,r9,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 3
+# if 3==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r5,r5,ror#5
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 3
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 3==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r5,r5,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r8,r8,r2 @ h+=X[i]
+ str r2,[sp,#3*4]
+ eor r2,r6,r7
+ add r8,r8,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r5
+ add r8,r8,r3 @ h+=K256[i]
+ eor r2,r2,r7 @ Ch(e,f,g)
+ eor r0,r9,r9,ror#11
+ add r8,r8,r2 @ h+=Ch(e,f,g)
+#if 3==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 3<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r9,r10 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#5*4] @ from future BODY_16_xx
+ eor r3,r9,r10 @ a^b, b^c in next round
+ ldr r1,[sp,#2*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r9,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r4,r4,r8 @ d+=h
+ eor r12,r12,r10 @ Maj(a,b,c)
+ add r8,r8,r0,ror#2 @ h+=Sigma0(a)
+ @ add r8,r8,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 4
+# if 4==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r4,r4,ror#5
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 4
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 4==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r4,r4,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r7,r7,r2 @ h+=X[i]
+ str r2,[sp,#4*4]
+ eor r2,r5,r6
+ add r7,r7,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r4
+ add r7,r7,r12 @ h+=K256[i]
+ eor r2,r2,r6 @ Ch(e,f,g)
+ eor r0,r8,r8,ror#11
+ add r7,r7,r2 @ h+=Ch(e,f,g)
+#if 4==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 4<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r8,r9 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#6*4] @ from future BODY_16_xx
+ eor r12,r8,r9 @ a^b, b^c in next round
+ ldr r1,[sp,#3*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r8,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r11,r11,r7 @ d+=h
+ eor r3,r3,r9 @ Maj(a,b,c)
+ add r7,r7,r0,ror#2 @ h+=Sigma0(a)
+ @ add r7,r7,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 5
+# if 5==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r11,r11,ror#5
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 5
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 5==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r11,r11,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r6,r6,r2 @ h+=X[i]
+ str r2,[sp,#5*4]
+ eor r2,r4,r5
+ add r6,r6,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r11
+ add r6,r6,r3 @ h+=K256[i]
+ eor r2,r2,r5 @ Ch(e,f,g)
+ eor r0,r7,r7,ror#11
+ add r6,r6,r2 @ h+=Ch(e,f,g)
+#if 5==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 5<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r7,r8 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#7*4] @ from future BODY_16_xx
+ eor r3,r7,r8 @ a^b, b^c in next round
+ ldr r1,[sp,#4*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r7,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r10,r10,r6 @ d+=h
+ eor r12,r12,r8 @ Maj(a,b,c)
+ add r6,r6,r0,ror#2 @ h+=Sigma0(a)
+ @ add r6,r6,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 6
+# if 6==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 6
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 6==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r10,r10,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r5,r5,r2 @ h+=X[i]
+ str r2,[sp,#6*4]
+ eor r2,r11,r4
+ add r5,r5,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r10
+ add r5,r5,r12 @ h+=K256[i]
+ eor r2,r2,r4 @ Ch(e,f,g)
+ eor r0,r6,r6,ror#11
+ add r5,r5,r2 @ h+=Ch(e,f,g)
+#if 6==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 6<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r6,r7 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#8*4] @ from future BODY_16_xx
+ eor r12,r6,r7 @ a^b, b^c in next round
+ ldr r1,[sp,#5*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r6,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r9,r9,r5 @ d+=h
+ eor r3,r3,r7 @ Maj(a,b,c)
+ add r5,r5,r0,ror#2 @ h+=Sigma0(a)
+ @ add r5,r5,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 7
+# if 7==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r9,r9,ror#5
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 7
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 7==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r9,r9,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r4,r4,r2 @ h+=X[i]
+ str r2,[sp,#7*4]
+ eor r2,r10,r11
+ add r4,r4,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r9
+ add r4,r4,r3 @ h+=K256[i]
+ eor r2,r2,r11 @ Ch(e,f,g)
+ eor r0,r5,r5,ror#11
+ add r4,r4,r2 @ h+=Ch(e,f,g)
+#if 7==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 7<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r5,r6 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#9*4] @ from future BODY_16_xx
+ eor r3,r5,r6 @ a^b, b^c in next round
+ ldr r1,[sp,#6*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r5,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r8,r8,r4 @ d+=h
+ eor r12,r12,r6 @ Maj(a,b,c)
+ add r4,r4,r0,ror#2 @ h+=Sigma0(a)
+ @ add r4,r4,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 8
+# if 8==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r8,r8,ror#5
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 8
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 8==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r8,r8,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r11,r11,r2 @ h+=X[i]
+ str r2,[sp,#8*4]
+ eor r2,r9,r10
+ add r11,r11,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r8
+ add r11,r11,r12 @ h+=K256[i]
+ eor r2,r2,r10 @ Ch(e,f,g)
+ eor r0,r4,r4,ror#11
+ add r11,r11,r2 @ h+=Ch(e,f,g)
+#if 8==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 8<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r4,r5 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#10*4] @ from future BODY_16_xx
+ eor r12,r4,r5 @ a^b, b^c in next round
+ ldr r1,[sp,#7*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r4,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r7,r7,r11 @ d+=h
+ eor r3,r3,r5 @ Maj(a,b,c)
+ add r11,r11,r0,ror#2 @ h+=Sigma0(a)
+ @ add r11,r11,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 9
+# if 9==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r7,r7,ror#5
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 9
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 9==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r7,r7,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r10,r10,r2 @ h+=X[i]
+ str r2,[sp,#9*4]
+ eor r2,r8,r9
+ add r10,r10,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r7
+ add r10,r10,r3 @ h+=K256[i]
+ eor r2,r2,r9 @ Ch(e,f,g)
+ eor r0,r11,r11,ror#11
+ add r10,r10,r2 @ h+=Ch(e,f,g)
+#if 9==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 9<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r11,r4 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#11*4] @ from future BODY_16_xx
+ eor r3,r11,r4 @ a^b, b^c in next round
+ ldr r1,[sp,#8*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r11,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r6,r6,r10 @ d+=h
+ eor r12,r12,r4 @ Maj(a,b,c)
+ add r10,r10,r0,ror#2 @ h+=Sigma0(a)
+ @ add r10,r10,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 10
+# if 10==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 10
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 10==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r6,r6,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r9,r9,r2 @ h+=X[i]
+ str r2,[sp,#10*4]
+ eor r2,r7,r8
+ add r9,r9,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r6
+ add r9,r9,r12 @ h+=K256[i]
+ eor r2,r2,r8 @ Ch(e,f,g)
+ eor r0,r10,r10,ror#11
+ add r9,r9,r2 @ h+=Ch(e,f,g)
+#if 10==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 10<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r10,r11 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#12*4] @ from future BODY_16_xx
+ eor r12,r10,r11 @ a^b, b^c in next round
+ ldr r1,[sp,#9*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r10,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r5,r5,r9 @ d+=h
+ eor r3,r3,r11 @ Maj(a,b,c)
+ add r9,r9,r0,ror#2 @ h+=Sigma0(a)
+ @ add r9,r9,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 11
+# if 11==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r5,r5,ror#5
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 11
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 11==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r5,r5,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r8,r8,r2 @ h+=X[i]
+ str r2,[sp,#11*4]
+ eor r2,r6,r7
+ add r8,r8,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r5
+ add r8,r8,r3 @ h+=K256[i]
+ eor r2,r2,r7 @ Ch(e,f,g)
+ eor r0,r9,r9,ror#11
+ add r8,r8,r2 @ h+=Ch(e,f,g)
+#if 11==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 11<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r9,r10 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#13*4] @ from future BODY_16_xx
+ eor r3,r9,r10 @ a^b, b^c in next round
+ ldr r1,[sp,#10*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r9,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r4,r4,r8 @ d+=h
+ eor r12,r12,r10 @ Maj(a,b,c)
+ add r8,r8,r0,ror#2 @ h+=Sigma0(a)
+ @ add r8,r8,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 12
+# if 12==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r4,r4,ror#5
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 12
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 12==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r4,r4,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r7,r7,r2 @ h+=X[i]
+ str r2,[sp,#12*4]
+ eor r2,r5,r6
+ add r7,r7,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r4
+ add r7,r7,r12 @ h+=K256[i]
+ eor r2,r2,r6 @ Ch(e,f,g)
+ eor r0,r8,r8,ror#11
+ add r7,r7,r2 @ h+=Ch(e,f,g)
+#if 12==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 12<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r8,r9 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#14*4] @ from future BODY_16_xx
+ eor r12,r8,r9 @ a^b, b^c in next round
+ ldr r1,[sp,#11*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r8,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r11,r11,r7 @ d+=h
+ eor r3,r3,r9 @ Maj(a,b,c)
+ add r7,r7,r0,ror#2 @ h+=Sigma0(a)
+ @ add r7,r7,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 13
+# if 13==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r11,r11,ror#5
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 13
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 13==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r11,r11,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r6,r6,r2 @ h+=X[i]
+ str r2,[sp,#13*4]
+ eor r2,r4,r5
+ add r6,r6,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r11
+ add r6,r6,r3 @ h+=K256[i]
+ eor r2,r2,r5 @ Ch(e,f,g)
+ eor r0,r7,r7,ror#11
+ add r6,r6,r2 @ h+=Ch(e,f,g)
+#if 13==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 13<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r7,r8 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#15*4] @ from future BODY_16_xx
+ eor r3,r7,r8 @ a^b, b^c in next round
+ ldr r1,[sp,#12*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r7,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r10,r10,r6 @ d+=h
+ eor r12,r12,r8 @ Maj(a,b,c)
+ add r6,r6,r0,ror#2 @ h+=Sigma0(a)
+ @ add r6,r6,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 14
+# if 14==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 14
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ ldrb r12,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r12,lsl#8
+ ldrb r12,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 14==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r10,r10,ror#5
+ orr r2,r2,r12,lsl#24
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+#endif
+ ldr r12,[r14],#4 @ *K256++
+ add r5,r5,r2 @ h+=X[i]
+ str r2,[sp,#14*4]
+ eor r2,r11,r4
+ add r5,r5,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r10
+ add r5,r5,r12 @ h+=K256[i]
+ eor r2,r2,r4 @ Ch(e,f,g)
+ eor r0,r6,r6,ror#11
+ add r5,r5,r2 @ h+=Ch(e,f,g)
+#if 14==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 14<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r6,r7 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#0*4] @ from future BODY_16_xx
+ eor r12,r6,r7 @ a^b, b^c in next round
+ ldr r1,[sp,#13*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r6,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r9,r9,r5 @ d+=h
+ eor r3,r3,r7 @ Maj(a,b,c)
+ add r5,r5,r0,ror#2 @ h+=Sigma0(a)
+ @ add r5,r5,r3 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ @ ldr r2,[r1],#4 @ 15
+# if 15==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r9,r9,ror#5
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+# ifndef __ARMEB__
+ rev r2,r2
+# endif
+#else
+ @ ldrb r2,[r1,#3] @ 15
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ ldrb r3,[r1,#2]
+ ldrb r0,[r1,#1]
+ orr r2,r2,r3,lsl#8
+ ldrb r3,[r1],#4
+ orr r2,r2,r0,lsl#16
+# if 15==15
+ str r1,[sp,#17*4] @ make room for r1
+# endif
+ eor r0,r9,r9,ror#5
+ orr r2,r2,r3,lsl#24
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+#endif
+ ldr r3,[r14],#4 @ *K256++
+ add r4,r4,r2 @ h+=X[i]
+ str r2,[sp,#15*4]
+ eor r2,r10,r11
+ add r4,r4,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r9
+ add r4,r4,r3 @ h+=K256[i]
+ eor r2,r2,r11 @ Ch(e,f,g)
+ eor r0,r5,r5,ror#11
+ add r4,r4,r2 @ h+=Ch(e,f,g)
+#if 15==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 15<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r5,r6 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#1*4] @ from future BODY_16_xx
+ eor r3,r5,r6 @ a^b, b^c in next round
+ ldr r1,[sp,#14*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r5,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r8,r8,r4 @ d+=h
+ eor r12,r12,r6 @ Maj(a,b,c)
+ add r4,r4,r0,ror#2 @ h+=Sigma0(a)
+ @ add r4,r4,r12 @ h+=Maj(a,b,c)
+.Lrounds_16_xx:
+ @ ldr r2,[sp,#1*4] @ 16
+ @ ldr r1,[sp,#14*4]
+ mov r0,r2,ror#7
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#0*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#9*4]
+
+ add r12,r12,r0
+ eor r0,r8,r8,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r11,r11,r2 @ h+=X[i]
+ str r2,[sp,#0*4]
+ eor r2,r9,r10
+ add r11,r11,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r8
+ add r11,r11,r12 @ h+=K256[i]
+ eor r2,r2,r10 @ Ch(e,f,g)
+ eor r0,r4,r4,ror#11
+ add r11,r11,r2 @ h+=Ch(e,f,g)
+#if 16==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 16<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r4,r5 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#2*4] @ from future BODY_16_xx
+ eor r12,r4,r5 @ a^b, b^c in next round
+ ldr r1,[sp,#15*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r4,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r7,r7,r11 @ d+=h
+ eor r3,r3,r5 @ Maj(a,b,c)
+ add r11,r11,r0,ror#2 @ h+=Sigma0(a)
+ @ add r11,r11,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#2*4] @ 17
+ @ ldr r1,[sp,#15*4]
+ mov r0,r2,ror#7
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#1*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#10*4]
+
+ add r3,r3,r0
+ eor r0,r7,r7,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r10,r10,r2 @ h+=X[i]
+ str r2,[sp,#1*4]
+ eor r2,r8,r9
+ add r10,r10,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r7
+ add r10,r10,r3 @ h+=K256[i]
+ eor r2,r2,r9 @ Ch(e,f,g)
+ eor r0,r11,r11,ror#11
+ add r10,r10,r2 @ h+=Ch(e,f,g)
+#if 17==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 17<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r11,r4 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#3*4] @ from future BODY_16_xx
+ eor r3,r11,r4 @ a^b, b^c in next round
+ ldr r1,[sp,#0*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r11,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r6,r6,r10 @ d+=h
+ eor r12,r12,r4 @ Maj(a,b,c)
+ add r10,r10,r0,ror#2 @ h+=Sigma0(a)
+ @ add r10,r10,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#3*4] @ 18
+ @ ldr r1,[sp,#0*4]
+ mov r0,r2,ror#7
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#2*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#11*4]
+
+ add r12,r12,r0
+ eor r0,r6,r6,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r9,r9,r2 @ h+=X[i]
+ str r2,[sp,#2*4]
+ eor r2,r7,r8
+ add r9,r9,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r6
+ add r9,r9,r12 @ h+=K256[i]
+ eor r2,r2,r8 @ Ch(e,f,g)
+ eor r0,r10,r10,ror#11
+ add r9,r9,r2 @ h+=Ch(e,f,g)
+#if 18==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 18<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r10,r11 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#4*4] @ from future BODY_16_xx
+ eor r12,r10,r11 @ a^b, b^c in next round
+ ldr r1,[sp,#1*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r10,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r5,r5,r9 @ d+=h
+ eor r3,r3,r11 @ Maj(a,b,c)
+ add r9,r9,r0,ror#2 @ h+=Sigma0(a)
+ @ add r9,r9,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#4*4] @ 19
+ @ ldr r1,[sp,#1*4]
+ mov r0,r2,ror#7
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#3*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#12*4]
+
+ add r3,r3,r0
+ eor r0,r5,r5,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r8,r8,r2 @ h+=X[i]
+ str r2,[sp,#3*4]
+ eor r2,r6,r7
+ add r8,r8,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r5
+ add r8,r8,r3 @ h+=K256[i]
+ eor r2,r2,r7 @ Ch(e,f,g)
+ eor r0,r9,r9,ror#11
+ add r8,r8,r2 @ h+=Ch(e,f,g)
+#if 19==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 19<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r9,r10 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#5*4] @ from future BODY_16_xx
+ eor r3,r9,r10 @ a^b, b^c in next round
+ ldr r1,[sp,#2*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r9,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r4,r4,r8 @ d+=h
+ eor r12,r12,r10 @ Maj(a,b,c)
+ add r8,r8,r0,ror#2 @ h+=Sigma0(a)
+ @ add r8,r8,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#5*4] @ 20
+ @ ldr r1,[sp,#2*4]
+ mov r0,r2,ror#7
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#4*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#13*4]
+
+ add r12,r12,r0
+ eor r0,r4,r4,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r7,r7,r2 @ h+=X[i]
+ str r2,[sp,#4*4]
+ eor r2,r5,r6
+ add r7,r7,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r4
+ add r7,r7,r12 @ h+=K256[i]
+ eor r2,r2,r6 @ Ch(e,f,g)
+ eor r0,r8,r8,ror#11
+ add r7,r7,r2 @ h+=Ch(e,f,g)
+#if 20==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 20<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r8,r9 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#6*4] @ from future BODY_16_xx
+ eor r12,r8,r9 @ a^b, b^c in next round
+ ldr r1,[sp,#3*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r8,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r11,r11,r7 @ d+=h
+ eor r3,r3,r9 @ Maj(a,b,c)
+ add r7,r7,r0,ror#2 @ h+=Sigma0(a)
+ @ add r7,r7,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#6*4] @ 21
+ @ ldr r1,[sp,#3*4]
+ mov r0,r2,ror#7
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#5*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#14*4]
+
+ add r3,r3,r0
+ eor r0,r11,r11,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r6,r6,r2 @ h+=X[i]
+ str r2,[sp,#5*4]
+ eor r2,r4,r5
+ add r6,r6,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r11
+ add r6,r6,r3 @ h+=K256[i]
+ eor r2,r2,r5 @ Ch(e,f,g)
+ eor r0,r7,r7,ror#11
+ add r6,r6,r2 @ h+=Ch(e,f,g)
+#if 21==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 21<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r7,r8 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#7*4] @ from future BODY_16_xx
+ eor r3,r7,r8 @ a^b, b^c in next round
+ ldr r1,[sp,#4*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r7,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r10,r10,r6 @ d+=h
+ eor r12,r12,r8 @ Maj(a,b,c)
+ add r6,r6,r0,ror#2 @ h+=Sigma0(a)
+ @ add r6,r6,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#7*4] @ 22
+ @ ldr r1,[sp,#4*4]
+ mov r0,r2,ror#7
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#6*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#15*4]
+
+ add r12,r12,r0
+ eor r0,r10,r10,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r5,r5,r2 @ h+=X[i]
+ str r2,[sp,#6*4]
+ eor r2,r11,r4
+ add r5,r5,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r10
+ add r5,r5,r12 @ h+=K256[i]
+ eor r2,r2,r4 @ Ch(e,f,g)
+ eor r0,r6,r6,ror#11
+ add r5,r5,r2 @ h+=Ch(e,f,g)
+#if 22==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 22<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r6,r7 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#8*4] @ from future BODY_16_xx
+ eor r12,r6,r7 @ a^b, b^c in next round
+ ldr r1,[sp,#5*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r6,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r9,r9,r5 @ d+=h
+ eor r3,r3,r7 @ Maj(a,b,c)
+ add r5,r5,r0,ror#2 @ h+=Sigma0(a)
+ @ add r5,r5,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#8*4] @ 23
+ @ ldr r1,[sp,#5*4]
+ mov r0,r2,ror#7
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#7*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#0*4]
+
+ add r3,r3,r0
+ eor r0,r9,r9,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r4,r4,r2 @ h+=X[i]
+ str r2,[sp,#7*4]
+ eor r2,r10,r11
+ add r4,r4,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r9
+ add r4,r4,r3 @ h+=K256[i]
+ eor r2,r2,r11 @ Ch(e,f,g)
+ eor r0,r5,r5,ror#11
+ add r4,r4,r2 @ h+=Ch(e,f,g)
+#if 23==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 23<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r5,r6 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#9*4] @ from future BODY_16_xx
+ eor r3,r5,r6 @ a^b, b^c in next round
+ ldr r1,[sp,#6*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r5,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r8,r8,r4 @ d+=h
+ eor r12,r12,r6 @ Maj(a,b,c)
+ add r4,r4,r0,ror#2 @ h+=Sigma0(a)
+ @ add r4,r4,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#9*4] @ 24
+ @ ldr r1,[sp,#6*4]
+ mov r0,r2,ror#7
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#8*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#1*4]
+
+ add r12,r12,r0
+ eor r0,r8,r8,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r8,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r11,r11,r2 @ h+=X[i]
+ str r2,[sp,#8*4]
+ eor r2,r9,r10
+ add r11,r11,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r8
+ add r11,r11,r12 @ h+=K256[i]
+ eor r2,r2,r10 @ Ch(e,f,g)
+ eor r0,r4,r4,ror#11
+ add r11,r11,r2 @ h+=Ch(e,f,g)
+#if 24==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 24<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r4,r5 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#10*4] @ from future BODY_16_xx
+ eor r12,r4,r5 @ a^b, b^c in next round
+ ldr r1,[sp,#7*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r4,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r7,r7,r11 @ d+=h
+ eor r3,r3,r5 @ Maj(a,b,c)
+ add r11,r11,r0,ror#2 @ h+=Sigma0(a)
+ @ add r11,r11,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#10*4] @ 25
+ @ ldr r1,[sp,#7*4]
+ mov r0,r2,ror#7
+ add r11,r11,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#9*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#2*4]
+
+ add r3,r3,r0
+ eor r0,r7,r7,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r7,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r10,r10,r2 @ h+=X[i]
+ str r2,[sp,#9*4]
+ eor r2,r8,r9
+ add r10,r10,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r7
+ add r10,r10,r3 @ h+=K256[i]
+ eor r2,r2,r9 @ Ch(e,f,g)
+ eor r0,r11,r11,ror#11
+ add r10,r10,r2 @ h+=Ch(e,f,g)
+#if 25==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 25<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r11,r4 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#11*4] @ from future BODY_16_xx
+ eor r3,r11,r4 @ a^b, b^c in next round
+ ldr r1,[sp,#8*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r11,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r6,r6,r10 @ d+=h
+ eor r12,r12,r4 @ Maj(a,b,c)
+ add r10,r10,r0,ror#2 @ h+=Sigma0(a)
+ @ add r10,r10,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#11*4] @ 26
+ @ ldr r1,[sp,#8*4]
+ mov r0,r2,ror#7
+ add r10,r10,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#10*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#3*4]
+
+ add r12,r12,r0
+ eor r0,r6,r6,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r6,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r9,r9,r2 @ h+=X[i]
+ str r2,[sp,#10*4]
+ eor r2,r7,r8
+ add r9,r9,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r6
+ add r9,r9,r12 @ h+=K256[i]
+ eor r2,r2,r8 @ Ch(e,f,g)
+ eor r0,r10,r10,ror#11
+ add r9,r9,r2 @ h+=Ch(e,f,g)
+#if 26==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 26<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r10,r11 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#12*4] @ from future BODY_16_xx
+ eor r12,r10,r11 @ a^b, b^c in next round
+ ldr r1,[sp,#9*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r10,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r5,r5,r9 @ d+=h
+ eor r3,r3,r11 @ Maj(a,b,c)
+ add r9,r9,r0,ror#2 @ h+=Sigma0(a)
+ @ add r9,r9,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#12*4] @ 27
+ @ ldr r1,[sp,#9*4]
+ mov r0,r2,ror#7
+ add r9,r9,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#11*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#4*4]
+
+ add r3,r3,r0
+ eor r0,r5,r5,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r5,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r8,r8,r2 @ h+=X[i]
+ str r2,[sp,#11*4]
+ eor r2,r6,r7
+ add r8,r8,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r5
+ add r8,r8,r3 @ h+=K256[i]
+ eor r2,r2,r7 @ Ch(e,f,g)
+ eor r0,r9,r9,ror#11
+ add r8,r8,r2 @ h+=Ch(e,f,g)
+#if 27==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 27<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r9,r10 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#13*4] @ from future BODY_16_xx
+ eor r3,r9,r10 @ a^b, b^c in next round
+ ldr r1,[sp,#10*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r9,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r4,r4,r8 @ d+=h
+ eor r12,r12,r10 @ Maj(a,b,c)
+ add r8,r8,r0,ror#2 @ h+=Sigma0(a)
+ @ add r8,r8,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#13*4] @ 28
+ @ ldr r1,[sp,#10*4]
+ mov r0,r2,ror#7
+ add r8,r8,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#12*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#5*4]
+
+ add r12,r12,r0
+ eor r0,r4,r4,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r4,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r7,r7,r2 @ h+=X[i]
+ str r2,[sp,#12*4]
+ eor r2,r5,r6
+ add r7,r7,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r4
+ add r7,r7,r12 @ h+=K256[i]
+ eor r2,r2,r6 @ Ch(e,f,g)
+ eor r0,r8,r8,ror#11
+ add r7,r7,r2 @ h+=Ch(e,f,g)
+#if 28==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 28<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r8,r9 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#14*4] @ from future BODY_16_xx
+ eor r12,r8,r9 @ a^b, b^c in next round
+ ldr r1,[sp,#11*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r8,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r11,r11,r7 @ d+=h
+ eor r3,r3,r9 @ Maj(a,b,c)
+ add r7,r7,r0,ror#2 @ h+=Sigma0(a)
+ @ add r7,r7,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#14*4] @ 29
+ @ ldr r1,[sp,#11*4]
+ mov r0,r2,ror#7
+ add r7,r7,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#13*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#6*4]
+
+ add r3,r3,r0
+ eor r0,r11,r11,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r11,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r6,r6,r2 @ h+=X[i]
+ str r2,[sp,#13*4]
+ eor r2,r4,r5
+ add r6,r6,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r11
+ add r6,r6,r3 @ h+=K256[i]
+ eor r2,r2,r5 @ Ch(e,f,g)
+ eor r0,r7,r7,ror#11
+ add r6,r6,r2 @ h+=Ch(e,f,g)
+#if 29==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 29<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r7,r8 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#15*4] @ from future BODY_16_xx
+ eor r3,r7,r8 @ a^b, b^c in next round
+ ldr r1,[sp,#12*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r7,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r10,r10,r6 @ d+=h
+ eor r12,r12,r8 @ Maj(a,b,c)
+ add r6,r6,r0,ror#2 @ h+=Sigma0(a)
+ @ add r6,r6,r12 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#15*4] @ 30
+ @ ldr r1,[sp,#12*4]
+ mov r0,r2,ror#7
+ add r6,r6,r12 @ h+=Maj(a,b,c) from the past
+ mov r12,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r12,r12,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#14*4]
+ eor r12,r12,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#7*4]
+
+ add r12,r12,r0
+ eor r0,r10,r10,ror#5 @ from BODY_00_15
+ add r2,r2,r12
+ eor r0,r0,r10,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r12,[r14],#4 @ *K256++
+ add r5,r5,r2 @ h+=X[i]
+ str r2,[sp,#14*4]
+ eor r2,r11,r4
+ add r5,r5,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r10
+ add r5,r5,r12 @ h+=K256[i]
+ eor r2,r2,r4 @ Ch(e,f,g)
+ eor r0,r6,r6,ror#11
+ add r5,r5,r2 @ h+=Ch(e,f,g)
+#if 30==31
+ and r12,r12,#0xff
+ cmp r12,#0xf2 @ done?
+#endif
+#if 30<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r12,r6,r7 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#0*4] @ from future BODY_16_xx
+ eor r12,r6,r7 @ a^b, b^c in next round
+ ldr r1,[sp,#13*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r6,ror#20 @ Sigma0(a)
+ and r3,r3,r12 @ (b^c)&=(a^b)
+ add r9,r9,r5 @ d+=h
+ eor r3,r3,r7 @ Maj(a,b,c)
+ add r5,r5,r0,ror#2 @ h+=Sigma0(a)
+ @ add r5,r5,r3 @ h+=Maj(a,b,c)
+ @ ldr r2,[sp,#0*4] @ 31
+ @ ldr r1,[sp,#13*4]
+ mov r0,r2,ror#7
+ add r5,r5,r3 @ h+=Maj(a,b,c) from the past
+ mov r3,r1,ror#17
+ eor r0,r0,r2,ror#18
+ eor r3,r3,r1,ror#19
+ eor r0,r0,r2,lsr#3 @ sigma0(X[i+1])
+ ldr r2,[sp,#15*4]
+ eor r3,r3,r1,lsr#10 @ sigma1(X[i+14])
+ ldr r1,[sp,#8*4]
+
+ add r3,r3,r0
+ eor r0,r9,r9,ror#5 @ from BODY_00_15
+ add r2,r2,r3
+ eor r0,r0,r9,ror#19 @ Sigma1(e)
+ add r2,r2,r1 @ X[i]
+ ldr r3,[r14],#4 @ *K256++
+ add r4,r4,r2 @ h+=X[i]
+ str r2,[sp,#15*4]
+ eor r2,r10,r11
+ add r4,r4,r0,ror#6 @ h+=Sigma1(e)
+ and r2,r2,r9
+ add r4,r4,r3 @ h+=K256[i]
+ eor r2,r2,r11 @ Ch(e,f,g)
+ eor r0,r5,r5,ror#11
+ add r4,r4,r2 @ h+=Ch(e,f,g)
+#if 31==31
+ and r3,r3,#0xff
+ cmp r3,#0xf2 @ done?
+#endif
+#if 31<15
+# if __ARM_ARCH__>=7
+ ldr r2,[r1],#4 @ prefetch
+# else
+ ldrb r2,[r1,#3]
+# endif
+ eor r3,r5,r6 @ a^b, b^c in next round
+#else
+ ldr r2,[sp,#1*4] @ from future BODY_16_xx
+ eor r3,r5,r6 @ a^b, b^c in next round
+ ldr r1,[sp,#14*4] @ from future BODY_16_xx
+#endif
+ eor r0,r0,r5,ror#20 @ Sigma0(a)
+ and r12,r12,r3 @ (b^c)&=(a^b)
+ add r8,r8,r4 @ d+=h
+ eor r12,r12,r6 @ Maj(a,b,c)
+ add r4,r4,r0,ror#2 @ h+=Sigma0(a)
+ @ add r4,r4,r12 @ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+ ite eq @ Thumb2 thing, sanity check in ARM
+#endif
+ ldreq r3,[sp,#16*4] @ pull ctx
+ bne .Lrounds_16_xx
+
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ ldr r0,[r3,#0]
+ ldr r2,[r3,#4]
+ ldr r12,[r3,#8]
+ add r4,r4,r0
+ ldr r0,[r3,#12]
+ add r5,r5,r2
+ ldr r2,[r3,#16]
+ add r6,r6,r12
+ ldr r12,[r3,#20]
+ add r7,r7,r0
+ ldr r0,[r3,#24]
+ add r8,r8,r2
+ ldr r2,[r3,#28]
+ add r9,r9,r12
+ ldr r1,[sp,#17*4] @ pull inp
+ ldr r12,[sp,#18*4] @ pull inp+len
+ add r10,r10,r0
+ add r11,r11,r2
+ stmia r3,{r4,r5,r6,r7,r8,r9,r10,r11}
+ cmp r1,r12
+ sub r14,r14,#256 @ rewind Ktbl
+ bne .Loop
+
+ add sp,sp,#19*4 @ destroy frame
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r4-r11,pc}
+#else
+ ldmia sp!,{r4-r11,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ .word 0xe12fff1e @ interoperable with Thumb ISA:-)
+#endif
+.size sha256_block_data_order,.-sha256_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
+.fpu neon
+
+.global sha256_block_data_order_neon
+.type sha256_block_data_order_neon,%function
+.align 4
+sha256_block_data_order_neon:
+.LNEON:
+ stmdb sp!,{r4-r12,lr}
+
+ sub r11,sp,#16*4+16
+ adrl r14,K256
+ bic r11,r11,#15 @ align for 128-bit stores
+ mov r12,sp
+ mov sp,r11 @ alloca
+ add r2,r1,r2,lsl#6 @ len to point at the end of inp
+
+ vld1.8 {q0},[r1]!
+ vld1.8 {q1},[r1]!
+ vld1.8 {q2},[r1]!
+ vld1.8 {q3},[r1]!
+ vld1.32 {q8},[r14,:128]!
+ vld1.32 {q9},[r14,:128]!
+ vld1.32 {q10},[r14,:128]!
+ vld1.32 {q11},[r14,:128]!
+ vrev32.8 q0,q0 @ yes, even on
+ str r0,[sp,#64]
+ vrev32.8 q1,q1 @ big-endian
+ str r1,[sp,#68]
+ mov r1,sp
+ vrev32.8 q2,q2
+ str r2,[sp,#72]
+ vrev32.8 q3,q3
+ str r12,[sp,#76] @ save original sp
+ vadd.i32 q8,q8,q0
+ vadd.i32 q9,q9,q1
+ vst1.32 {q8},[r1,:128]!
+ vadd.i32 q10,q10,q2
+ vst1.32 {q9},[r1,:128]!
+ vadd.i32 q11,q11,q3
+ vst1.32 {q10},[r1,:128]!
+ vst1.32 {q11},[r1,:128]!
+
+ ldmia r0,{r4-r11}
+ sub r1,r1,#64
+ ldr r2,[sp,#0]
+ eor r12,r12,r12
+ eor r3,r5,r6
+ b .L_00_48
+
+.align 4
+.L_00_48:
+ vext.8 q8,q0,q1,#4
+ add r11,r11,r2
+ eor r2,r9,r10
+ eor r0,r8,r8,ror#5
+ vext.8 q9,q2,q3,#4
+ add r4,r4,r12
+ and r2,r2,r8
+ eor r12,r0,r8,ror#19
+ vshr.u32 q10,q8,#7
+ eor r0,r4,r4,ror#11
+ eor r2,r2,r10
+ vadd.i32 q0,q0,q9
+ add r11,r11,r12,ror#6
+ eor r12,r4,r5
+ vshr.u32 q9,q8,#3
+ eor r0,r0,r4,ror#20
+ add r11,r11,r2
+ vsli.32 q10,q8,#25
+ ldr r2,[sp,#4]
+ and r3,r3,r12
+ vshr.u32 q11,q8,#18
+ add r7,r7,r11
+ add r11,r11,r0,ror#2
+ eor r3,r3,r5
+ veor q9,q9,q10
+ add r10,r10,r2
+ vsli.32 q11,q8,#14
+ eor r2,r8,r9
+ eor r0,r7,r7,ror#5
+ vshr.u32 d24,d7,#17
+ add r11,r11,r3
+ and r2,r2,r7
+ veor q9,q9,q11
+ eor r3,r0,r7,ror#19
+ eor r0,r11,r11,ror#11
+ vsli.32 d24,d7,#15
+ eor r2,r2,r9
+ add r10,r10,r3,ror#6
+ vshr.u32 d25,d7,#10
+ eor r3,r11,r4
+ eor r0,r0,r11,ror#20
+ vadd.i32 q0,q0,q9
+ add r10,r10,r2
+ ldr r2,[sp,#8]
+ veor d25,d25,d24
+ and r12,r12,r3
+ add r6,r6,r10
+ vshr.u32 d24,d7,#19
+ add r10,r10,r0,ror#2
+ eor r12,r12,r4
+ vsli.32 d24,d7,#13
+ add r9,r9,r2
+ eor r2,r7,r8
+ veor d25,d25,d24
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12
+ vadd.i32 d0,d0,d25
+ and r2,r2,r6
+ eor r12,r0,r6,ror#19
+ vshr.u32 d24,d0,#17
+ eor r0,r10,r10,ror#11
+ eor r2,r2,r8
+ vsli.32 d24,d0,#15
+ add r9,r9,r12,ror#6
+ eor r12,r10,r11
+ vshr.u32 d25,d0,#10
+ eor r0,r0,r10,ror#20
+ add r9,r9,r2
+ veor d25,d25,d24
+ ldr r2,[sp,#12]
+ and r3,r3,r12
+ vshr.u32 d24,d0,#19
+ add r5,r5,r9
+ add r9,r9,r0,ror#2
+ eor r3,r3,r11
+ vld1.32 {q8},[r14,:128]!
+ add r8,r8,r2
+ vsli.32 d24,d0,#13
+ eor r2,r6,r7
+ eor r0,r5,r5,ror#5
+ veor d25,d25,d24
+ add r9,r9,r3
+ and r2,r2,r5
+ vadd.i32 d1,d1,d25
+ eor r3,r0,r5,ror#19
+ eor r0,r9,r9,ror#11
+ vadd.i32 q8,q8,q0
+ eor r2,r2,r7
+ add r8,r8,r3,ror#6
+ eor r3,r9,r10
+ eor r0,r0,r9,ror#20
+ add r8,r8,r2
+ ldr r2,[sp,#16]
+ and r12,r12,r3
+ add r4,r4,r8
+ vst1.32 {q8},[r1,:128]!
+ add r8,r8,r0,ror#2
+ eor r12,r12,r10
+ vext.8 q8,q1,q2,#4
+ add r7,r7,r2
+ eor r2,r5,r6
+ eor r0,r4,r4,ror#5
+ vext.8 q9,q3,q0,#4
+ add r8,r8,r12
+ and r2,r2,r4
+ eor r12,r0,r4,ror#19
+ vshr.u32 q10,q8,#7
+ eor r0,r8,r8,ror#11
+ eor r2,r2,r6
+ vadd.i32 q1,q1,q9
+ add r7,r7,r12,ror#6
+ eor r12,r8,r9
+ vshr.u32 q9,q8,#3
+ eor r0,r0,r8,ror#20
+ add r7,r7,r2
+ vsli.32 q10,q8,#25
+ ldr r2,[sp,#20]
+ and r3,r3,r12
+ vshr.u32 q11,q8,#18
+ add r11,r11,r7
+ add r7,r7,r0,ror#2
+ eor r3,r3,r9
+ veor q9,q9,q10
+ add r6,r6,r2
+ vsli.32 q11,q8,#14
+ eor r2,r4,r5
+ eor r0,r11,r11,ror#5
+ vshr.u32 d24,d1,#17
+ add r7,r7,r3
+ and r2,r2,r11
+ veor q9,q9,q11
+ eor r3,r0,r11,ror#19
+ eor r0,r7,r7,ror#11
+ vsli.32 d24,d1,#15
+ eor r2,r2,r5
+ add r6,r6,r3,ror#6
+ vshr.u32 d25,d1,#10
+ eor r3,r7,r8
+ eor r0,r0,r7,ror#20
+ vadd.i32 q1,q1,q9
+ add r6,r6,r2
+ ldr r2,[sp,#24]
+ veor d25,d25,d24
+ and r12,r12,r3
+ add r10,r10,r6
+ vshr.u32 d24,d1,#19
+ add r6,r6,r0,ror#2
+ eor r12,r12,r8
+ vsli.32 d24,d1,#13
+ add r5,r5,r2
+ eor r2,r11,r4
+ veor d25,d25,d24
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12
+ vadd.i32 d2,d2,d25
+ and r2,r2,r10
+ eor r12,r0,r10,ror#19
+ vshr.u32 d24,d2,#17
+ eor r0,r6,r6,ror#11
+ eor r2,r2,r4
+ vsli.32 d24,d2,#15
+ add r5,r5,r12,ror#6
+ eor r12,r6,r7
+ vshr.u32 d25,d2,#10
+ eor r0,r0,r6,ror#20
+ add r5,r5,r2
+ veor d25,d25,d24
+ ldr r2,[sp,#28]
+ and r3,r3,r12
+ vshr.u32 d24,d2,#19
+ add r9,r9,r5
+ add r5,r5,r0,ror#2
+ eor r3,r3,r7
+ vld1.32 {q8},[r14,:128]!
+ add r4,r4,r2
+ vsli.32 d24,d2,#13
+ eor r2,r10,r11
+ eor r0,r9,r9,ror#5
+ veor d25,d25,d24
+ add r5,r5,r3
+ and r2,r2,r9
+ vadd.i32 d3,d3,d25
+ eor r3,r0,r9,ror#19
+ eor r0,r5,r5,ror#11
+ vadd.i32 q8,q8,q1
+ eor r2,r2,r11
+ add r4,r4,r3,ror#6
+ eor r3,r5,r6
+ eor r0,r0,r5,ror#20
+ add r4,r4,r2
+ ldr r2,[sp,#32]
+ and r12,r12,r3
+ add r8,r8,r4
+ vst1.32 {q8},[r1,:128]!
+ add r4,r4,r0,ror#2
+ eor r12,r12,r6
+ vext.8 q8,q2,q3,#4
+ add r11,r11,r2
+ eor r2,r9,r10
+ eor r0,r8,r8,ror#5
+ vext.8 q9,q0,q1,#4
+ add r4,r4,r12
+ and r2,r2,r8
+ eor r12,r0,r8,ror#19
+ vshr.u32 q10,q8,#7
+ eor r0,r4,r4,ror#11
+ eor r2,r2,r10
+ vadd.i32 q2,q2,q9
+ add r11,r11,r12,ror#6
+ eor r12,r4,r5
+ vshr.u32 q9,q8,#3
+ eor r0,r0,r4,ror#20
+ add r11,r11,r2
+ vsli.32 q10,q8,#25
+ ldr r2,[sp,#36]
+ and r3,r3,r12
+ vshr.u32 q11,q8,#18
+ add r7,r7,r11
+ add r11,r11,r0,ror#2
+ eor r3,r3,r5
+ veor q9,q9,q10
+ add r10,r10,r2
+ vsli.32 q11,q8,#14
+ eor r2,r8,r9
+ eor r0,r7,r7,ror#5
+ vshr.u32 d24,d3,#17
+ add r11,r11,r3
+ and r2,r2,r7
+ veor q9,q9,q11
+ eor r3,r0,r7,ror#19
+ eor r0,r11,r11,ror#11
+ vsli.32 d24,d3,#15
+ eor r2,r2,r9
+ add r10,r10,r3,ror#6
+ vshr.u32 d25,d3,#10
+ eor r3,r11,r4
+ eor r0,r0,r11,ror#20
+ vadd.i32 q2,q2,q9
+ add r10,r10,r2
+ ldr r2,[sp,#40]
+ veor d25,d25,d24
+ and r12,r12,r3
+ add r6,r6,r10
+ vshr.u32 d24,d3,#19
+ add r10,r10,r0,ror#2
+ eor r12,r12,r4
+ vsli.32 d24,d3,#13
+ add r9,r9,r2
+ eor r2,r7,r8
+ veor d25,d25,d24
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12
+ vadd.i32 d4,d4,d25
+ and r2,r2,r6
+ eor r12,r0,r6,ror#19
+ vshr.u32 d24,d4,#17
+ eor r0,r10,r10,ror#11
+ eor r2,r2,r8
+ vsli.32 d24,d4,#15
+ add r9,r9,r12,ror#6
+ eor r12,r10,r11
+ vshr.u32 d25,d4,#10
+ eor r0,r0,r10,ror#20
+ add r9,r9,r2
+ veor d25,d25,d24
+ ldr r2,[sp,#44]
+ and r3,r3,r12
+ vshr.u32 d24,d4,#19
+ add r5,r5,r9
+ add r9,r9,r0,ror#2
+ eor r3,r3,r11
+ vld1.32 {q8},[r14,:128]!
+ add r8,r8,r2
+ vsli.32 d24,d4,#13
+ eor r2,r6,r7
+ eor r0,r5,r5,ror#5
+ veor d25,d25,d24
+ add r9,r9,r3
+ and r2,r2,r5
+ vadd.i32 d5,d5,d25
+ eor r3,r0,r5,ror#19
+ eor r0,r9,r9,ror#11
+ vadd.i32 q8,q8,q2
+ eor r2,r2,r7
+ add r8,r8,r3,ror#6
+ eor r3,r9,r10
+ eor r0,r0,r9,ror#20
+ add r8,r8,r2
+ ldr r2,[sp,#48]
+ and r12,r12,r3
+ add r4,r4,r8
+ vst1.32 {q8},[r1,:128]!
+ add r8,r8,r0,ror#2
+ eor r12,r12,r10
+ vext.8 q8,q3,q0,#4
+ add r7,r7,r2
+ eor r2,r5,r6
+ eor r0,r4,r4,ror#5
+ vext.8 q9,q1,q2,#4
+ add r8,r8,r12
+ and r2,r2,r4
+ eor r12,r0,r4,ror#19
+ vshr.u32 q10,q8,#7
+ eor r0,r8,r8,ror#11
+ eor r2,r2,r6
+ vadd.i32 q3,q3,q9
+ add r7,r7,r12,ror#6
+ eor r12,r8,r9
+ vshr.u32 q9,q8,#3
+ eor r0,r0,r8,ror#20
+ add r7,r7,r2
+ vsli.32 q10,q8,#25
+ ldr r2,[sp,#52]
+ and r3,r3,r12
+ vshr.u32 q11,q8,#18
+ add r11,r11,r7
+ add r7,r7,r0,ror#2
+ eor r3,r3,r9
+ veor q9,q9,q10
+ add r6,r6,r2
+ vsli.32 q11,q8,#14
+ eor r2,r4,r5
+ eor r0,r11,r11,ror#5
+ vshr.u32 d24,d5,#17
+ add r7,r7,r3
+ and r2,r2,r11
+ veor q9,q9,q11
+ eor r3,r0,r11,ror#19
+ eor r0,r7,r7,ror#11
+ vsli.32 d24,d5,#15
+ eor r2,r2,r5
+ add r6,r6,r3,ror#6
+ vshr.u32 d25,d5,#10
+ eor r3,r7,r8
+ eor r0,r0,r7,ror#20
+ vadd.i32 q3,q3,q9
+ add r6,r6,r2
+ ldr r2,[sp,#56]
+ veor d25,d25,d24
+ and r12,r12,r3
+ add r10,r10,r6
+ vshr.u32 d24,d5,#19
+ add r6,r6,r0,ror#2
+ eor r12,r12,r8
+ vsli.32 d24,d5,#13
+ add r5,r5,r2
+ eor r2,r11,r4
+ veor d25,d25,d24
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12
+ vadd.i32 d6,d6,d25
+ and r2,r2,r10
+ eor r12,r0,r10,ror#19
+ vshr.u32 d24,d6,#17
+ eor r0,r6,r6,ror#11
+ eor r2,r2,r4
+ vsli.32 d24,d6,#15
+ add r5,r5,r12,ror#6
+ eor r12,r6,r7
+ vshr.u32 d25,d6,#10
+ eor r0,r0,r6,ror#20
+ add r5,r5,r2
+ veor d25,d25,d24
+ ldr r2,[sp,#60]
+ and r3,r3,r12
+ vshr.u32 d24,d6,#19
+ add r9,r9,r5
+ add r5,r5,r0,ror#2
+ eor r3,r3,r7
+ vld1.32 {q8},[r14,:128]!
+ add r4,r4,r2
+ vsli.32 d24,d6,#13
+ eor r2,r10,r11
+ eor r0,r9,r9,ror#5
+ veor d25,d25,d24
+ add r5,r5,r3
+ and r2,r2,r9
+ vadd.i32 d7,d7,d25
+ eor r3,r0,r9,ror#19
+ eor r0,r5,r5,ror#11
+ vadd.i32 q8,q8,q3
+ eor r2,r2,r11
+ add r4,r4,r3,ror#6
+ eor r3,r5,r6
+ eor r0,r0,r5,ror#20
+ add r4,r4,r2
+ ldr r2,[r14]
+ and r12,r12,r3
+ add r8,r8,r4
+ vst1.32 {q8},[r1,:128]!
+ add r4,r4,r0,ror#2
+ eor r12,r12,r6
+ teq r2,#0 @ check for K256 terminator
+ ldr r2,[sp,#0]
+ sub r1,r1,#64
+ bne .L_00_48
+
+ ldr r1,[sp,#68]
+ ldr r0,[sp,#72]
+ sub r14,r14,#256 @ rewind r14
+ teq r1,r0
+ it eq
+ subeq r1,r1,#64 @ avoid SEGV
+ vld1.8 {q0},[r1]! @ load next input block
+ vld1.8 {q1},[r1]!
+ vld1.8 {q2},[r1]!
+ vld1.8 {q3},[r1]!
+ it ne
+ strne r1,[sp,#68]
+ mov r1,sp
+ add r11,r11,r2
+ eor r2,r9,r10
+ eor r0,r8,r8,ror#5
+ add r4,r4,r12
+ vld1.32 {q8},[r14,:128]!
+ and r2,r2,r8
+ eor r12,r0,r8,ror#19
+ eor r0,r4,r4,ror#11
+ eor r2,r2,r10
+ vrev32.8 q0,q0
+ add r11,r11,r12,ror#6
+ eor r12,r4,r5
+ eor r0,r0,r4,ror#20
+ add r11,r11,r2
+ vadd.i32 q8,q8,q0
+ ldr r2,[sp,#4]
+ and r3,r3,r12
+ add r7,r7,r11
+ add r11,r11,r0,ror#2
+ eor r3,r3,r5
+ add r10,r10,r2
+ eor r2,r8,r9
+ eor r0,r7,r7,ror#5
+ add r11,r11,r3
+ and r2,r2,r7
+ eor r3,r0,r7,ror#19
+ eor r0,r11,r11,ror#11
+ eor r2,r2,r9
+ add r10,r10,r3,ror#6
+ eor r3,r11,r4
+ eor r0,r0,r11,ror#20
+ add r10,r10,r2
+ ldr r2,[sp,#8]
+ and r12,r12,r3
+ add r6,r6,r10
+ add r10,r10,r0,ror#2
+ eor r12,r12,r4
+ add r9,r9,r2
+ eor r2,r7,r8
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12
+ and r2,r2,r6
+ eor r12,r0,r6,ror#19
+ eor r0,r10,r10,ror#11
+ eor r2,r2,r8
+ add r9,r9,r12,ror#6
+ eor r12,r10,r11
+ eor r0,r0,r10,ror#20
+ add r9,r9,r2
+ ldr r2,[sp,#12]
+ and r3,r3,r12
+ add r5,r5,r9
+ add r9,r9,r0,ror#2
+ eor r3,r3,r11
+ add r8,r8,r2
+ eor r2,r6,r7
+ eor r0,r5,r5,ror#5
+ add r9,r9,r3
+ and r2,r2,r5
+ eor r3,r0,r5,ror#19
+ eor r0,r9,r9,ror#11
+ eor r2,r2,r7
+ add r8,r8,r3,ror#6
+ eor r3,r9,r10
+ eor r0,r0,r9,ror#20
+ add r8,r8,r2
+ ldr r2,[sp,#16]
+ and r12,r12,r3
+ add r4,r4,r8
+ add r8,r8,r0,ror#2
+ eor r12,r12,r10
+ vst1.32 {q8},[r1,:128]!
+ add r7,r7,r2
+ eor r2,r5,r6
+ eor r0,r4,r4,ror#5
+ add r8,r8,r12
+ vld1.32 {q8},[r14,:128]!
+ and r2,r2,r4
+ eor r12,r0,r4,ror#19
+ eor r0,r8,r8,ror#11
+ eor r2,r2,r6
+ vrev32.8 q1,q1
+ add r7,r7,r12,ror#6
+ eor r12,r8,r9
+ eor r0,r0,r8,ror#20
+ add r7,r7,r2
+ vadd.i32 q8,q8,q1
+ ldr r2,[sp,#20]
+ and r3,r3,r12
+ add r11,r11,r7
+ add r7,r7,r0,ror#2
+ eor r3,r3,r9
+ add r6,r6,r2
+ eor r2,r4,r5
+ eor r0,r11,r11,ror#5
+ add r7,r7,r3
+ and r2,r2,r11
+ eor r3,r0,r11,ror#19
+ eor r0,r7,r7,ror#11
+ eor r2,r2,r5
+ add r6,r6,r3,ror#6
+ eor r3,r7,r8
+ eor r0,r0,r7,ror#20
+ add r6,r6,r2
+ ldr r2,[sp,#24]
+ and r12,r12,r3
+ add r10,r10,r6
+ add r6,r6,r0,ror#2
+ eor r12,r12,r8
+ add r5,r5,r2
+ eor r2,r11,r4
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12
+ and r2,r2,r10
+ eor r12,r0,r10,ror#19
+ eor r0,r6,r6,ror#11
+ eor r2,r2,r4
+ add r5,r5,r12,ror#6
+ eor r12,r6,r7
+ eor r0,r0,r6,ror#20
+ add r5,r5,r2
+ ldr r2,[sp,#28]
+ and r3,r3,r12
+ add r9,r9,r5
+ add r5,r5,r0,ror#2
+ eor r3,r3,r7
+ add r4,r4,r2
+ eor r2,r10,r11
+ eor r0,r9,r9,ror#5
+ add r5,r5,r3
+ and r2,r2,r9
+ eor r3,r0,r9,ror#19
+ eor r0,r5,r5,ror#11
+ eor r2,r2,r11
+ add r4,r4,r3,ror#6
+ eor r3,r5,r6
+ eor r0,r0,r5,ror#20
+ add r4,r4,r2
+ ldr r2,[sp,#32]
+ and r12,r12,r3
+ add r8,r8,r4
+ add r4,r4,r0,ror#2
+ eor r12,r12,r6
+ vst1.32 {q8},[r1,:128]!
+ add r11,r11,r2
+ eor r2,r9,r10
+ eor r0,r8,r8,ror#5
+ add r4,r4,r12
+ vld1.32 {q8},[r14,:128]!
+ and r2,r2,r8
+ eor r12,r0,r8,ror#19
+ eor r0,r4,r4,ror#11
+ eor r2,r2,r10
+ vrev32.8 q2,q2
+ add r11,r11,r12,ror#6
+ eor r12,r4,r5
+ eor r0,r0,r4,ror#20
+ add r11,r11,r2
+ vadd.i32 q8,q8,q2
+ ldr r2,[sp,#36]
+ and r3,r3,r12
+ add r7,r7,r11
+ add r11,r11,r0,ror#2
+ eor r3,r3,r5
+ add r10,r10,r2
+ eor r2,r8,r9
+ eor r0,r7,r7,ror#5
+ add r11,r11,r3
+ and r2,r2,r7
+ eor r3,r0,r7,ror#19
+ eor r0,r11,r11,ror#11
+ eor r2,r2,r9
+ add r10,r10,r3,ror#6
+ eor r3,r11,r4
+ eor r0,r0,r11,ror#20
+ add r10,r10,r2
+ ldr r2,[sp,#40]
+ and r12,r12,r3
+ add r6,r6,r10
+ add r10,r10,r0,ror#2
+ eor r12,r12,r4
+ add r9,r9,r2
+ eor r2,r7,r8
+ eor r0,r6,r6,ror#5
+ add r10,r10,r12
+ and r2,r2,r6
+ eor r12,r0,r6,ror#19
+ eor r0,r10,r10,ror#11
+ eor r2,r2,r8
+ add r9,r9,r12,ror#6
+ eor r12,r10,r11
+ eor r0,r0,r10,ror#20
+ add r9,r9,r2
+ ldr r2,[sp,#44]
+ and r3,r3,r12
+ add r5,r5,r9
+ add r9,r9,r0,ror#2
+ eor r3,r3,r11
+ add r8,r8,r2
+ eor r2,r6,r7
+ eor r0,r5,r5,ror#5
+ add r9,r9,r3
+ and r2,r2,r5
+ eor r3,r0,r5,ror#19
+ eor r0,r9,r9,ror#11
+ eor r2,r2,r7
+ add r8,r8,r3,ror#6
+ eor r3,r9,r10
+ eor r0,r0,r9,ror#20
+ add r8,r8,r2
+ ldr r2,[sp,#48]
+ and r12,r12,r3
+ add r4,r4,r8
+ add r8,r8,r0,ror#2
+ eor r12,r12,r10
+ vst1.32 {q8},[r1,:128]!
+ add r7,r7,r2
+ eor r2,r5,r6
+ eor r0,r4,r4,ror#5
+ add r8,r8,r12
+ vld1.32 {q8},[r14,:128]!
+ and r2,r2,r4
+ eor r12,r0,r4,ror#19
+ eor r0,r8,r8,ror#11
+ eor r2,r2,r6
+ vrev32.8 q3,q3
+ add r7,r7,r12,ror#6
+ eor r12,r8,r9
+ eor r0,r0,r8,ror#20
+ add r7,r7,r2
+ vadd.i32 q8,q8,q3
+ ldr r2,[sp,#52]
+ and r3,r3,r12
+ add r11,r11,r7
+ add r7,r7,r0,ror#2
+ eor r3,r3,r9
+ add r6,r6,r2
+ eor r2,r4,r5
+ eor r0,r11,r11,ror#5
+ add r7,r7,r3
+ and r2,r2,r11
+ eor r3,r0,r11,ror#19
+ eor r0,r7,r7,ror#11
+ eor r2,r2,r5
+ add r6,r6,r3,ror#6
+ eor r3,r7,r8
+ eor r0,r0,r7,ror#20
+ add r6,r6,r2
+ ldr r2,[sp,#56]
+ and r12,r12,r3
+ add r10,r10,r6
+ add r6,r6,r0,ror#2
+ eor r12,r12,r8
+ add r5,r5,r2
+ eor r2,r11,r4
+ eor r0,r10,r10,ror#5
+ add r6,r6,r12
+ and r2,r2,r10
+ eor r12,r0,r10,ror#19
+ eor r0,r6,r6,ror#11
+ eor r2,r2,r4
+ add r5,r5,r12,ror#6
+ eor r12,r6,r7
+ eor r0,r0,r6,ror#20
+ add r5,r5,r2
+ ldr r2,[sp,#60]
+ and r3,r3,r12
+ add r9,r9,r5
+ add r5,r5,r0,ror#2
+ eor r3,r3,r7
+ add r4,r4,r2
+ eor r2,r10,r11
+ eor r0,r9,r9,ror#5
+ add r5,r5,r3
+ and r2,r2,r9
+ eor r3,r0,r9,ror#19
+ eor r0,r5,r5,ror#11
+ eor r2,r2,r11
+ add r4,r4,r3,ror#6
+ eor r3,r5,r6
+ eor r0,r0,r5,ror#20
+ add r4,r4,r2
+ ldr r2,[sp,#64]
+ and r12,r12,r3
+ add r8,r8,r4
+ add r4,r4,r0,ror#2
+ eor r12,r12,r6
+ vst1.32 {q8},[r1,:128]!
+ ldr r0,[r2,#0]
+ add r4,r4,r12 @ h+=Maj(a,b,c) from the past
+ ldr r12,[r2,#4]
+ ldr r3,[r2,#8]
+ ldr r1,[r2,#12]
+ add r4,r4,r0 @ accumulate
+ ldr r0,[r2,#16]
+ add r5,r5,r12
+ ldr r12,[r2,#20]
+ add r6,r6,r3
+ ldr r3,[r2,#24]
+ add r7,r7,r1
+ ldr r1,[r2,#28]
+ add r8,r8,r0
+ str r4,[r2],#4
+ add r9,r9,r12
+ str r5,[r2],#4
+ add r10,r10,r3
+ str r6,[r2],#4
+ add r11,r11,r1
+ str r7,[r2],#4
+ stmia r2,{r8-r11}
+
+ ittte ne
+ movne r1,sp
+ ldrne r2,[sp,#0]
+ eorne r12,r12,r12
+ ldreq sp,[sp,#76] @ restore original sp
+ itt ne
+ eorne r3,r5,r6
+ bne .L_00_48
+
+ ldmia sp!,{r4-r12,pc}
+.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# ifdef __thumb2__
+# define INST(a,b,c,d) .byte c,d|0xc,a,b
+# else
+# define INST(a,b,c,d) .byte a,b,c,d
+# endif
+
+.type sha256_block_data_order_armv8,%function
+.align 5
+sha256_block_data_order_armv8:
+.LARMv8:
+ vld1.32 {q0,q1},[r0]
+# ifdef __thumb2__
+ adr r3,.LARMv8
+ sub r3,r3,#.LARMv8-K256
+# else
+ adrl r3,K256
+# endif
+ add r2,r1,r2,lsl#6 @ len to point at the end of inp
+
+.Loop_v8:
+ vld1.8 {q8-q9},[r1]!
+ vld1.8 {q10-q11},[r1]!
+ vld1.32 {q12},[r3]!
+ vrev32.8 q8,q8
+ vrev32.8 q9,q9
+ vrev32.8 q10,q10
+ vrev32.8 q11,q11
+ vmov q14,q0 @ offload
+ vmov q15,q1
+ teq r1,r2
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ INST(0xe2,0x03,0xfa,0xf3) @ sha256su0 q8,q9
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe6,0x0c,0x64,0xf3) @ sha256su1 q8,q10,q11
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ INST(0xe4,0x23,0xfa,0xf3) @ sha256su0 q9,q10
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe0,0x2c,0x66,0xf3) @ sha256su1 q9,q11,q8
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q10
+ INST(0xe6,0x43,0xfa,0xf3) @ sha256su0 q10,q11
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+ INST(0xe2,0x4c,0x60,0xf3) @ sha256su1 q10,q8,q9
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q11
+ INST(0xe0,0x63,0xfa,0xf3) @ sha256su0 q11,q8
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+ INST(0xe4,0x6c,0x62,0xf3) @ sha256su1 q11,q9,q10
+ vld1.32 {q13},[r3]!
+ vadd.i32 q12,q12,q8
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+
+ vld1.32 {q12},[r3]!
+ vadd.i32 q13,q13,q9
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+
+ vld1.32 {q13},[r3]
+ vadd.i32 q12,q12,q10
+ sub r3,r3,#256-16 @ rewind
+ vmov q2,q0
+ INST(0x68,0x0c,0x02,0xf3) @ sha256h q0,q1,q12
+ INST(0x68,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q12
+
+ vadd.i32 q13,q13,q11
+ vmov q2,q0
+ INST(0x6a,0x0c,0x02,0xf3) @ sha256h q0,q1,q13
+ INST(0x6a,0x2c,0x14,0xf3) @ sha256h2 q1,q2,q13
+
+ vadd.i32 q0,q0,q14
+ vadd.i32 q1,q1,q15
+ it ne
+ bne .Loop_v8
+
+ vst1.32 {q0,q1},[r0]
+
+ bx lr @ bx lr
+.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
+#endif
+.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>"
+.align 2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
new file mode 100644
index 0000000..0d6fc43
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.c
@@ -0,0 +1,246 @@
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using optimized ARM assembler and NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha256_ssse3_glue.c:
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
+ unsigned int num_blks);
+
+
+int sha256_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ sctx->state[0] = SHA256_H0;
+ sctx->state[1] = SHA256_H1;
+ sctx->state[2] = SHA256_H2;
+ sctx->state[3] = SHA256_H3;
+ sctx->state[4] = SHA256_H4;
+ sctx->state[5] = SHA256_H5;
+ sctx->state[6] = SHA256_H6;
+ sctx->state[7] = SHA256_H7;
+ sctx->count = 0;
+
+ return 0;
+}
+
+int sha224_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ sctx->state[0] = SHA224_H0;
+ sctx->state[1] = SHA224_H1;
+ sctx->state[2] = SHA224_H2;
+ sctx->state[3] = SHA224_H3;
+ sctx->state[4] = SHA224_H4;
+ sctx->state[5] = SHA224_H5;
+ sctx->state[6] = SHA224_H6;
+ sctx->state[7] = SHA224_H7;
+ sctx->count = 0;
+
+ return 0;
+}
+
+int __sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len,
+ unsigned int partial)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int done = 0;
+
+ sctx->count += len;
+
+ if (partial) {
+ done = SHA256_BLOCK_SIZE - partial;
+ memcpy(sctx->buf + partial, data, done);
+ sha256_block_data_order(sctx->state, sctx->buf, 1);
+ }
+
+ if (len - done >= SHA256_BLOCK_SIZE) {
+ const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;
+
+ sha256_block_data_order(sctx->state, data + done, rounds);
+ done += rounds * SHA256_BLOCK_SIZE;
+ }
+
+ memcpy(sctx->buf, data + done, len - done);
+
+ return 0;
+}
+
+int sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+ /* Handle the fast case right here */
+ if (partial + len < SHA256_BLOCK_SIZE) {
+ sctx->count += len;
+ memcpy(sctx->buf + partial, data, len);
+
+ return 0;
+ }
+
+ return __sha256_update(desc, data, len, partial);
+}
+
+/* Add padding and return the message digest. */
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int i, index, padlen;
+ __be32 *dst = (__be32 *)out;
+ __be64 bits;
+ static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+ /* save number of bits */
+ bits = cpu_to_be64(sctx->count << 3);
+
+ /* Pad out to 56 mod 64 and append length */
+ index = sctx->count % SHA256_BLOCK_SIZE;
+ padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);
+
+ /* We need to fill a whole block for __sha256_update */
+ if (padlen <= 56) {
+ sctx->count += padlen;
+ memcpy(sctx->buf + index, padding, padlen);
+ } else {
+ __sha256_update(desc, padding, padlen, index);
+ }
+ __sha256_update(desc, (const u8 *)&bits, sizeof(bits), 56);
+
+ /* Store state in digest */
+ for (i = 0; i < 8; i++)
+ dst[i] = cpu_to_be32(sctx->state[i]);
+
+ /* Wipe context */
+ memset(sctx, 0, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+ u8 D[SHA256_DIGEST_SIZE];
+
+ sha256_final(desc, D);
+
+ memcpy(out, D, SHA224_DIGEST_SIZE);
+ memset(D, 0, SHA256_DIGEST_SIZE);
+
+ return 0;
+}
+
+int sha256_export(struct shash_desc *desc, void *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(out, sctx, sizeof(*sctx));
+
+ return 0;
+}
+
+int sha256_import(struct shash_desc *desc, const void *in)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(sctx, in, sizeof(*sctx));
+
+ return 0;
+}
+
+static struct shash_alg algs[] = { {
+ .digestsize = SHA256_DIGEST_SIZE,
+ .init = sha256_init,
+ .update = sha256_update,
+ .final = sha256_final,
+ .export = sha256_export,
+ .import = sha256_import,
+ .descsize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-asm",
+ .cra_priority = 150,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .digestsize = SHA224_DIGEST_SIZE,
+ .init = sha224_init,
+ .update = sha256_update,
+ .final = sha224_final,
+ .export = sha256_export,
+ .import = sha256_import,
+ .descsize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-asm",
+ .cra_priority = 150,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha256_mod_init(void)
+{
+ int res = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+
+ if (res < 0)
+ return res;
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+ res = crypto_register_shashes(sha256_neon_algs,
+ ARRAY_SIZE(sha256_neon_algs));
+
+ if (res < 0)
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+ }
+
+ return res;
+}
+
+static void __exit sha256_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+ crypto_unregister_shashes(sha256_neon_algs,
+ ARRAY_SIZE(sha256_neon_algs));
+}
+
+module_init(sha256_mod_init);
+module_exit(sha256_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm (ARM), including NEON");
+
+MODULE_ALIAS("sha256");
diff --git a/arch/arm/crypto/sha256_glue.h b/arch/arm/crypto/sha256_glue.h
new file mode 100644
index 0000000..0312f4f
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.h
@@ -0,0 +1,23 @@
+#ifndef _CRYPTO_SHA256_GLUE_H
+#define _CRYPTO_SHA256_GLUE_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern struct shash_alg sha256_neon_algs[2];
+
+extern int sha256_init(struct shash_desc *desc);
+
+extern int sha224_init(struct shash_desc *desc);
+
+extern int __sha256_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len, unsigned int partial);
+
+extern int sha256_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+extern int sha256_export(struct shash_desc *desc, void *out);
+
+extern int sha256_import(struct shash_desc *desc, const void *in);
+
+#endif /* _CRYPTO_SHA256_GLUE_H */
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
new file mode 100644
index 0000000..3ff0a7f
--- /dev/null
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -0,0 +1,172 @@
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha512_neon_glue.c:
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order_neon(u32 *digest, const void *data,
+ unsigned int num_blks);
+
+
+static int __sha256_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len, unsigned int partial)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int done = 0;
+
+ sctx->count += len;
+
+ if (partial) {
+ done = SHA256_BLOCK_SIZE - partial;
+ memcpy(sctx->buf + partial, data, done);
+ sha256_block_data_order_neon(sctx->state, sctx->buf, 1);
+ }
+
+ if (len - done >= SHA256_BLOCK_SIZE) {
+ const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;
+
+ sha256_block_data_order_neon(sctx->state, data + done, rounds);
+ done += rounds * SHA256_BLOCK_SIZE;
+ }
+
+ memcpy(sctx->buf, data + done, len - done);
+
+ return 0;
+}
+
+static int sha256_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+ int res;
+
+ /* Handle the fast case right here */
+ if (partial + len < SHA256_BLOCK_SIZE) {
+ sctx->count += len;
+ memcpy(sctx->buf + partial, data, len);
+
+ return 0;
+ }
+
+ if (!may_use_simd()) {
+ res = __sha256_update(desc, data, len, partial);
+ } else {
+ kernel_neon_begin();
+ res = __sha256_neon_update(desc, data, len, partial);
+ kernel_neon_end();
+ }
+
+ return res;
+}
+
+/* Add padding and return the message digest. */
+static int sha256_neon_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int i, index, padlen;
+ __be32 *dst = (__be32 *)out;
+ __be64 bits;
+ static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+ /* save number of bits */
+ bits = cpu_to_be64(sctx->count << 3);
+
+ /* Pad out to 56 mod 64 and append length */
+ index = sctx->count % SHA256_BLOCK_SIZE;
+ padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);
+
+ if (!may_use_simd()) {
+ sha256_update(desc, padding, padlen);
+ sha256_update(desc, (const u8 *)&bits, sizeof(bits));
+ } else {
+ kernel_neon_begin();
+ /* We need to fill a whole block for __sha256_neon_update() */
+ if (padlen <= 56) {
+ sctx->count += padlen;
+ memcpy(sctx->buf + index, padding, padlen);
+ } else {
+ __sha256_neon_update(desc, padding, padlen, index);
+ }
+ __sha256_neon_update(desc, (const u8 *)&bits,
+ sizeof(bits), 56);
+ kernel_neon_end();
+ }
+
+ /* Store state in digest */
+ for (i = 0; i < 8; i++)
+ dst[i] = cpu_to_be32(sctx->state[i]);
+
+ /* Wipe context */
+ memset(sctx, 0, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha224_neon_final(struct shash_desc *desc, u8 *out)
+{
+ u8 D[SHA256_DIGEST_SIZE];
+
+ sha256_neon_final(desc, D);
+
+ memcpy(out, D, SHA224_DIGEST_SIZE);
+ memset(D, 0, SHA256_DIGEST_SIZE);
+
+ return 0;
+}
+
+struct shash_alg sha256_neon_algs[] = { {
+ .digestsize = SHA256_DIGEST_SIZE,
+ .init = sha256_init,
+ .update = sha256_neon_update,
+ .final = sha256_neon_final,
+ .export = sha256_export,
+ .import = sha256_import,
+ .descsize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-neon",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .digestsize = SHA224_DIGEST_SIZE,
+ .init = sha224_init,
+ .update = sha256_neon_update,
+ .final = sha224_neon_final,
+ .export = sha256_export,
+ .import = sha256_import,
+ .descsize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-neon",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
new file mode 100644
index 0000000..fe99472
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv7-neon.S
@@ -0,0 +1,455 @@
+/* sha512-armv7-neon.S - ARM/NEON assembly implementation of SHA-512 transform
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code 32
+.fpu neon
+
+.text
+
+/* structure of SHA512_CONTEXT */
+#define hd_a 0
+#define hd_b ((hd_a) + 8)
+#define hd_c ((hd_b) + 8)
+#define hd_d ((hd_c) + 8)
+#define hd_e ((hd_d) + 8)
+#define hd_f ((hd_e) + 8)
+#define hd_g ((hd_f) + 8)
+
+/* register macros */
+#define RK %r2
+
+#define RA d0
+#define RB d1
+#define RC d2
+#define RD d3
+#define RE d4
+#define RF d5
+#define RG d6
+#define RH d7
+
+#define RT0 d8
+#define RT1 d9
+#define RT2 d10
+#define RT3 d11
+#define RT4 d12
+#define RT5 d13
+#define RT6 d14
+#define RT7 d15
+
+#define RT01q q4
+#define RT23q q5
+#define RT45q q6
+#define RT67q q7
+
+#define RW0 d16
+#define RW1 d17
+#define RW2 d18
+#define RW3 d19
+#define RW4 d20
+#define RW5 d21
+#define RW6 d22
+#define RW7 d23
+#define RW8 d24
+#define RW9 d25
+#define RW10 d26
+#define RW11 d27
+#define RW12 d28
+#define RW13 d29
+#define RW14 d30
+#define RW15 d31
+
+#define RW01q q8
+#define RW23q q9
+#define RW45q q10
+#define RW67q q11
+#define RW89q q12
+#define RW1011q q13
+#define RW1213q q14
+#define RW1415q q15
+
+/***********************************************************************
+ * ARM assembly implementation of sha512 transform
+ ***********************************************************************/
+#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
+ rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
+ /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+ vshr.u64 RT2, re, #14; \
+ vshl.u64 RT3, re, #64 - 14; \
+ interleave_op(arg1); \
+ vshr.u64 RT4, re, #18; \
+ vshl.u64 RT5, re, #64 - 18; \
+ vld1.64 {RT0}, [RK]!; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, re, #41; \
+ vshl.u64 RT5, re, #64 - 41; \
+ vadd.u64 RT0, RT0, rw0; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vmov.64 RT7, re; \
+ veor.64 RT1, RT2, RT3; \
+ vbsl.64 RT7, rf, rg; \
+ \
+ vadd.u64 RT1, RT1, rh; \
+ vshr.u64 RT2, ra, #28; \
+ vshl.u64 RT3, ra, #64 - 28; \
+ vadd.u64 RT1, RT1, RT0; \
+ vshr.u64 RT4, ra, #34; \
+ vshl.u64 RT5, ra, #64 - 34; \
+ vadd.u64 RT1, RT1, RT7; \
+ \
+ /* h = Sum0 (a) + Maj (a, b, c); */ \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, ra, #39; \
+ vshl.u64 RT5, ra, #64 - 39; \
+ veor.64 RT0, ra, rb; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vbsl.64 RT0, rc, rb; \
+ vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+ veor.64 rh, RT2, RT3; \
+ \
+ /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+ vshr.u64 RT2, rd, #14; \
+ vshl.u64 RT3, rd, #64 - 14; \
+ vadd.u64 rh, rh, RT0; \
+ vshr.u64 RT4, rd, #18; \
+ vshl.u64 RT5, rd, #64 - 18; \
+ vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+ vld1.64 {RT0}, [RK]!; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, rd, #41; \
+ vshl.u64 RT5, rd, #64 - 41; \
+ vadd.u64 RT0, RT0, rw1; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vmov.64 RT7, rd; \
+ veor.64 RT1, RT2, RT3; \
+ vbsl.64 RT7, re, rf; \
+ \
+ vadd.u64 RT1, RT1, rg; \
+ vshr.u64 RT2, rh, #28; \
+ vshl.u64 RT3, rh, #64 - 28; \
+ vadd.u64 RT1, RT1, RT0; \
+ vshr.u64 RT4, rh, #34; \
+ vshl.u64 RT5, rh, #64 - 34; \
+ vadd.u64 RT1, RT1, RT7; \
+ \
+ /* g = Sum0 (h) + Maj (h, a, b); */ \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, rh, #39; \
+ vshl.u64 RT5, rh, #64 - 39; \
+ veor.64 RT0, rh, ra; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vbsl.64 RT0, rb, ra; \
+ vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+ veor.64 rg, RT2, RT3; \
+ \
+ /* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
+ /* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
+ \
+ /**** S0(w[1:2]) */ \
+ \
+ /* w[0:1] += w[9:10] */ \
+ /* RT23q = rw1:rw2 */ \
+ vext.u64 RT23q, rw01q, rw23q, #1; \
+ vadd.u64 rw0, rw9; \
+ vadd.u64 rg, rg, RT0; \
+ vadd.u64 rw1, rw10;\
+ vadd.u64 rg, rg, RT1; /* g+=t1; */ \
+ \
+ vshr.u64 RT45q, RT23q, #1; \
+ vshl.u64 RT67q, RT23q, #64 - 1; \
+ vshr.u64 RT01q, RT23q, #8; \
+ veor.u64 RT45q, RT45q, RT67q; \
+ vshl.u64 RT67q, RT23q, #64 - 8; \
+ veor.u64 RT45q, RT45q, RT01q; \
+ vshr.u64 RT01q, RT23q, #7; \
+ veor.u64 RT45q, RT45q, RT67q; \
+ \
+ /**** S1(w[14:15]) */ \
+ vshr.u64 RT23q, rw1415q, #6; \
+ veor.u64 RT01q, RT01q, RT45q; \
+ vshr.u64 RT45q, rw1415q, #19; \
+ vshl.u64 RT67q, rw1415q, #64 - 19; \
+ veor.u64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT45q, rw1415q, #61; \
+ veor.u64 RT23q, RT23q, RT67q; \
+ vshl.u64 RT67q, rw1415q, #64 - 61; \
+ veor.u64 RT23q, RT23q, RT45q; \
+ vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
+ veor.u64 RT01q, RT23q, RT67q;
+#define vadd_RT01q(rw01q) \
+ /* w[0:1] += S(w[14:15]) */ \
+ vadd.u64 rw01q, RT01q;
+
+#define dummy(_) /*_*/
+
+#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
+ interleave_op1, arg1, interleave_op2, arg2) \
+ /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+ vshr.u64 RT2, re, #14; \
+ vshl.u64 RT3, re, #64 - 14; \
+ interleave_op1(arg1); \
+ vshr.u64 RT4, re, #18; \
+ vshl.u64 RT5, re, #64 - 18; \
+ interleave_op2(arg2); \
+ vld1.64 {RT0}, [RK]!; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, re, #41; \
+ vshl.u64 RT5, re, #64 - 41; \
+ vadd.u64 RT0, RT0, rw0; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vmov.64 RT7, re; \
+ veor.64 RT1, RT2, RT3; \
+ vbsl.64 RT7, rf, rg; \
+ \
+ vadd.u64 RT1, RT1, rh; \
+ vshr.u64 RT2, ra, #28; \
+ vshl.u64 RT3, ra, #64 - 28; \
+ vadd.u64 RT1, RT1, RT0; \
+ vshr.u64 RT4, ra, #34; \
+ vshl.u64 RT5, ra, #64 - 34; \
+ vadd.u64 RT1, RT1, RT7; \
+ \
+ /* h = Sum0 (a) + Maj (a, b, c); */ \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, ra, #39; \
+ vshl.u64 RT5, ra, #64 - 39; \
+ veor.64 RT0, ra, rb; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vbsl.64 RT0, rc, rb; \
+ vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+ veor.64 rh, RT2, RT3; \
+ \
+ /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+ vshr.u64 RT2, rd, #14; \
+ vshl.u64 RT3, rd, #64 - 14; \
+ vadd.u64 rh, rh, RT0; \
+ vshr.u64 RT4, rd, #18; \
+ vshl.u64 RT5, rd, #64 - 18; \
+ vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+ vld1.64 {RT0}, [RK]!; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, rd, #41; \
+ vshl.u64 RT5, rd, #64 - 41; \
+ vadd.u64 RT0, RT0, rw1; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vmov.64 RT7, rd; \
+ veor.64 RT1, RT2, RT3; \
+ vbsl.64 RT7, re, rf; \
+ \
+ vadd.u64 RT1, RT1, rg; \
+ vshr.u64 RT2, rh, #28; \
+ vshl.u64 RT3, rh, #64 - 28; \
+ vadd.u64 RT1, RT1, RT0; \
+ vshr.u64 RT4, rh, #34; \
+ vshl.u64 RT5, rh, #64 - 34; \
+ vadd.u64 RT1, RT1, RT7; \
+ \
+ /* g = Sum0 (h) + Maj (h, a, b); */ \
+ veor.64 RT23q, RT23q, RT45q; \
+ vshr.u64 RT4, rh, #39; \
+ vshl.u64 RT5, rh, #64 - 39; \
+ veor.64 RT0, rh, ra; \
+ veor.64 RT23q, RT23q, RT45q; \
+ vbsl.64 RT0, rb, ra; \
+ vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+ veor.64 rg, RT2, RT3;
+#define vadd_rg_RT0(rg) \
+ vadd.u64 rg, rg, RT0;
+#define vadd_rg_RT1(rg) \
+ vadd.u64 rg, rg, RT1; /* g+=t1; */
+
+.align 3
+ENTRY(sha512_transform_neon)
+ /* Input:
+ * %r0: SHA512_CONTEXT
+ * %r1: data
+ * %r2: u64 k[] constants
+ * %r3: nblks
+ */
+ push {%lr};
+
+ mov %lr, #0;
+
+ /* Load context to d0-d7 */
+ vld1.64 {RA-RD}, [%r0]!;
+ vld1.64 {RE-RH}, [%r0];
+ sub %r0, #(4*8);
+
+ /* Load input to w[16], d16-d31 */
+ /* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
+ vld1.64 {RW0-RW3}, [%r1]!;
+ vld1.64 {RW4-RW7}, [%r1]!;
+ vld1.64 {RW8-RW11}, [%r1]!;
+ vld1.64 {RW12-RW15}, [%r1]!;
+#ifdef __ARMEL__
+ /* byteswap */
+ vrev64.8 RW01q, RW01q;
+ vrev64.8 RW23q, RW23q;
+ vrev64.8 RW45q, RW45q;
+ vrev64.8 RW67q, RW67q;
+ vrev64.8 RW89q, RW89q;
+ vrev64.8 RW1011q, RW1011q;
+ vrev64.8 RW1213q, RW1213q;
+ vrev64.8 RW1415q, RW1415q;
+#endif
+
+ /* EABI says that d8-d15 must be preserved by callee. */
+ /*vpush {RT0-RT7};*/
+
+.Loop:
+ rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+ RW23q, RW1415q, RW9, RW10, dummy, _);
+ b .Lenter_rounds;
+
+.Loop_rounds:
+ rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+ RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
+.Lenter_rounds:
+ rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
+ RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
+ rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
+ RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
+ rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
+ RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
+ rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
+ RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
+ rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
+ RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
+ add %lr, #16;
+ rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
+ RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
+ cmp %lr, #64;
+ rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
+ RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
+ bne .Loop_rounds;
+
+ subs %r3, #1;
+
+ rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
+ vadd_RT01q, RW1415q, dummy, _);
+ rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
+ vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+ beq .Lhandle_tail;
+ vld1.64 {RW0-RW3}, [%r1]!;
+ rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+ vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+ rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+ vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+ vrev64.8 RW01q, RW01q;
+ vrev64.8 RW23q, RW23q;
+#endif
+ vld1.64 {RW4-RW7}, [%r1]!;
+ rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+ vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+ rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+ vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+#ifdef __ARMEL__
+ vrev64.8 RW45q, RW45q;
+ vrev64.8 RW67q, RW67q;
+#endif
+ vld1.64 {RW8-RW11}, [%r1]!;
+ rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+ vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+ rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+ vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+ vrev64.8 RW89q, RW89q;
+ vrev64.8 RW1011q, RW1011q;
+#endif
+ vld1.64 {RW12-RW15}, [%r1]!;
+ vadd_rg_RT0(RA);
+ vadd_rg_RT1(RA);
+
+ /* Load context */
+ vld1.64 {RT0-RT3}, [%r0]!;
+ vld1.64 {RT4-RT7}, [%r0];
+ sub %r0, #(4*8);
+
+#ifdef __ARMEL__
+ vrev64.8 RW1213q, RW1213q;
+ vrev64.8 RW1415q, RW1415q;
+#endif
+
+ vadd.u64 RA, RT0;
+ vadd.u64 RB, RT1;
+ vadd.u64 RC, RT2;
+ vadd.u64 RD, RT3;
+ vadd.u64 RE, RT4;
+ vadd.u64 RF, RT5;
+ vadd.u64 RG, RT6;
+ vadd.u64 RH, RT7;
+
+ /* Store the first half of context */
+ vst1.64 {RA-RD}, [%r0]!;
+ sub RK, $(8*80);
+ vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+ mov %lr, #0;
+ sub %r0, #(4*8);
+
+ b .Loop;
+
+.Lhandle_tail:
+ rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+ vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+ rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+ vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+ rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+ vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+ rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+ vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+ rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+ vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+ rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+ vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+
+ /* Load context to d16-d23 */
+ vld1.64 {RW0-RW3}, [%r0]!;
+ vadd_rg_RT0(RA);
+ vld1.64 {RW4-RW7}, [%r0];
+ vadd_rg_RT1(RA);
+ sub %r0, #(4*8);
+
+ vadd.u64 RA, RW0;
+ vadd.u64 RB, RW1;
+ vadd.u64 RC, RW2;
+ vadd.u64 RD, RW3;
+ vadd.u64 RE, RW4;
+ vadd.u64 RF, RW5;
+ vadd.u64 RG, RW6;
+ vadd.u64 RH, RW7;
+
+ /* Store the first half of context */
+ vst1.64 {RA-RD}, [%r0]!;
+
+ /* Clear used registers */
+ /* d16-d31 */
+ veor.u64 RW01q, RW01q;
+ veor.u64 RW23q, RW23q;
+ veor.u64 RW45q, RW45q;
+ veor.u64 RW67q, RW67q;
+ vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+ veor.u64 RW89q, RW89q;
+ veor.u64 RW1011q, RW1011q;
+ veor.u64 RW1213q, RW1213q;
+ veor.u64 RW1415q, RW1415q;
+ /* d8-d15 */
+ /*vpop {RT0-RT7};*/
+ /* d0-d7 (q0-q3) */
+ veor.u64 %q0, %q0;
+ veor.u64 %q1, %q1;
+ veor.u64 %q2, %q2;
+ veor.u64 %q3, %q3;
+
+ pop {%pc};
+ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
new file mode 100644
index 0000000..0d2758f
--- /dev/null
+++ b/arch/arm/crypto/sha512_neon_glue.c
@@ -0,0 +1,305 @@
+/*
+ * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha512_ssse3_glue.c:
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+
+static const u64 sha512_k[] = {
+ 0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
+ 0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
+ 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
+ 0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
+ 0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
+ 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
+ 0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
+ 0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
+ 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
+ 0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
+ 0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
+ 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
+ 0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
+ 0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
+ 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
+ 0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
+ 0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
+ 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
+ 0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
+ 0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
+ 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
+ 0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
+ 0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
+ 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
+ 0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
+ 0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
+ 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
+ 0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
+ 0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
+ 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
+ 0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
+ 0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
+ 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
+ 0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
+ 0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
+ 0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
+ 0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
+ 0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
+ 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
+ 0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
+};
+
+
+asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
+ const u64 k[], unsigned int num_blks);
+
+
+static int sha512_neon_init(struct shash_desc *desc)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ sctx->state[0] = SHA512_H0;
+ sctx->state[1] = SHA512_H1;
+ sctx->state[2] = SHA512_H2;
+ sctx->state[3] = SHA512_H3;
+ sctx->state[4] = SHA512_H4;
+ sctx->state[5] = SHA512_H5;
+ sctx->state[6] = SHA512_H6;
+ sctx->state[7] = SHA512_H7;
+ sctx->count[0] = sctx->count[1] = 0;
+
+ return 0;
+}
+
+static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len, unsigned int partial)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+ unsigned int done = 0;
+
+ sctx->count[0] += len;
+ if (sctx->count[0] < len)
+ sctx->count[1]++;
+
+ if (partial) {
+ done = SHA512_BLOCK_SIZE - partial;
+ memcpy(sctx->buf + partial, data, done);
+ sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
+ }
+
+ if (len - done >= SHA512_BLOCK_SIZE) {
+ const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
+
+ sha512_transform_neon(sctx->state, data + done, sha512_k,
+ rounds);
+
+ done += rounds * SHA512_BLOCK_SIZE;
+ }
+
+ memcpy(sctx->buf, data + done, len - done);
+
+ return 0;
+}
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
+ int res;
+
+ /* Handle the fast case right here */
+ if (partial + len < SHA512_BLOCK_SIZE) {
+ sctx->count[0] += len;
+ if (sctx->count[0] < len)
+ sctx->count[1]++;
+ memcpy(sctx->buf + partial, data, len);
+
+ return 0;
+ }
+
+ if (!may_use_simd()) {
+ res = crypto_sha512_update(desc, data, len);
+ } else {
+ kernel_neon_begin();
+ res = __sha512_neon_update(desc, data, len, partial);
+ kernel_neon_end();
+ }
+
+ return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+ unsigned int i, index, padlen;
+ __be64 *dst = (__be64 *)out;
+ __be64 bits[2];
+ static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
+
+ /* save number of bits */
+ bits[1] = cpu_to_be64(sctx->count[0] << 3);
+ bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
+
+ /* Pad out to 112 mod 128 and append length */
+ index = sctx->count[0] & 0x7f;
+ padlen = (index < 112) ? (112 - index) : ((128+112) - index);
+
+ if (!may_use_simd()) {
+ crypto_sha512_update(desc, padding, padlen);
+ crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
+ } else {
+ kernel_neon_begin();
+ /* We need to fill a whole block for __sha512_neon_update() */
+ if (padlen <= 112) {
+ sctx->count[0] += padlen;
+ if (sctx->count[0] < padlen)
+ sctx->count[1]++;
+ memcpy(sctx->buf + index, padding, padlen);
+ } else {
+ __sha512_neon_update(desc, padding, padlen, index);
+ }
+ __sha512_neon_update(desc, (const u8 *)&bits,
+ sizeof(bits), 112);
+ kernel_neon_end();
+ }
+
+ /* Store state in digest */
+ for (i = 0; i < 8; i++)
+ dst[i] = cpu_to_be64(sctx->state[i]);
+
+ /* Wipe context */
+ memset(sctx, 0, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha512_neon_export(struct shash_desc *desc, void *out)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(out, sctx, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha512_neon_import(struct shash_desc *desc, const void *in)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ memcpy(sctx, in, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha384_neon_init(struct shash_desc *desc)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ sctx->state[0] = SHA384_H0;
+ sctx->state[1] = SHA384_H1;
+ sctx->state[2] = SHA384_H2;
+ sctx->state[3] = SHA384_H3;
+ sctx->state[4] = SHA384_H4;
+ sctx->state[5] = SHA384_H5;
+ sctx->state[6] = SHA384_H6;
+ sctx->state[7] = SHA384_H7;
+
+ sctx->count[0] = sctx->count[1] = 0;
+
+ return 0;
+}
+
+static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
+{
+ u8 D[SHA512_DIGEST_SIZE];
+
+ sha512_neon_final(desc, D);
+
+ memcpy(hash, D, SHA384_DIGEST_SIZE);
+ memset(D, 0, SHA512_DIGEST_SIZE);
+
+ return 0;
+}
+
+static struct shash_alg algs[] = { {
+ .digestsize = SHA512_DIGEST_SIZE,
+ .init = sha512_neon_init,
+ .update = sha512_neon_update,
+ .final = sha512_neon_final,
+ .export = sha512_neon_export,
+ .import = sha512_neon_import,
+ .descsize = sizeof(struct sha512_state),
+ .statesize = sizeof(struct sha512_state),
+ .base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "sha512-neon",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .digestsize = SHA384_DIGEST_SIZE,
+ .init = sha384_neon_init,
+ .update = sha512_neon_update,
+ .final = sha384_neon_final,
+ .export = sha512_neon_export,
+ .import = sha512_neon_import,
+ .descsize = sizeof(struct sha512_state),
+ .statesize = sizeof(struct sha512_state),
+ .base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "sha384-neon",
+ .cra_priority = 250,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA384_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha512_neon_mod_init(void)
+{
+ if (!cpu_has_neon())
+ return -ENODEV;
+
+ return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_neon_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha512_neon_mod_init);
+module_exit(sha512_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
+
+MODULE_ALIAS("sha512");
+MODULE_ALIAS("sha384");
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index d3db398..6577b8a 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -24,6 +24,7 @@
generic-y += serial.h
generic-y += shmbuf.h
generic-y += siginfo.h
+generic-y += simd.h
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 8dcd9c7..b00ef07 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -59,6 +59,21 @@
#define smp_wmb() dmb()
#endif
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index a25e62d..36324ec 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -16,6 +16,7 @@
#include <asm/shmparam.h>
#include <asm/cachetype.h>
#include <asm/outercache.h>
+#include <asm/rodata.h>
#define CACHE_COLOUR(vaddr) ((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
diff --git a/arch/arm/include/asm/crypto/sha1.h b/arch/arm/include/asm/crypto/sha1.h
new file mode 100644
index 0000000..75e6a41
--- /dev/null
+++ b/arch/arm/include/asm/crypto/sha1.h
@@ -0,0 +1,10 @@
+#ifndef ASM_ARM_CRYPTO_SHA1_H
+#define ASM_ARM_CRYPTO_SHA1_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+#endif
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index ce6e306..051b726 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@
typedef struct user_fp elf_fpregset_t;
-#define EM_ARM 40
-
#define EF_ARM_EABI_MASK 0xff000000
#define EF_ARM_EABI_UNKNOWN 0x00000000
#define EF_ARM_EABI_VER1 0x01000000
diff --git a/arch/arm/include/asm/fiq_glue.h b/arch/arm/include/asm/fiq_glue.h
new file mode 100644
index 0000000..a9e244f9
--- /dev/null
+++ b/arch/arm/include/asm/fiq_glue.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_FIQ_GLUE_H
+#define __ASM_FIQ_GLUE_H
+
+struct fiq_glue_handler {
+ void (*fiq)(struct fiq_glue_handler *h, void *regs, void *svc_sp);
+ void (*resume)(struct fiq_glue_handler *h);
+};
+typedef void (*fiq_return_handler_t)(void);
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler);
+int fiq_glue_set_return_handler(fiq_return_handler_t fiq_return);
+int fiq_glue_clear_return_handler(fiq_return_handler_t fiq_return);
+
+#ifdef CONFIG_FIQ_GLUE
+void fiq_glue_resume(void);
+#else
+static inline void fiq_glue_resume(void) {}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 2740c2a..3d7351c 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
-#define NR_IPI 6
+#define NR_IPI 7
typedef struct {
unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 3b2c40b..0ca0f5a 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -66,6 +66,7 @@
#define L2X0_STNDBY_MODE_EN (1 << 0)
/* Registers shifts and masks */
+#define L2X0_CACHE_ID_REV_MASK (0x3f)
#define L2X0_CACHE_ID_PART_MASK (0xf << 6)
#define L2X0_CACHE_ID_PART_L210 (1 << 6)
#define L2X0_CACHE_ID_PART_L310 (3 << 6)
@@ -106,6 +107,8 @@
#define L2X0_WAY_SIZE_SHIFT 3
+#define REV_PL310_R2P0 4
+
#ifndef __ASSEMBLY__
extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
#if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
index 0cf7a6b..4aee45d 100644
--- a/arch/arm/include/asm/hardware/coresight.h
+++ b/arch/arm/include/asm/hardware/coresight.h
@@ -17,15 +17,23 @@
#define TRACER_ACCESSED_BIT 0
#define TRACER_RUNNING_BIT 1
#define TRACER_CYCLE_ACC_BIT 2
+#define TRACER_TRACE_DATA_BIT 3
+#define TRACER_TIMESTAMP_BIT 4
+#define TRACER_BRANCHOUTPUT_BIT 5
+#define TRACER_RETURN_STACK_BIT 6
#define TRACER_ACCESSED BIT(TRACER_ACCESSED_BIT)
#define TRACER_RUNNING BIT(TRACER_RUNNING_BIT)
#define TRACER_CYCLE_ACC BIT(TRACER_CYCLE_ACC_BIT)
+#define TRACER_TRACE_DATA BIT(TRACER_TRACE_DATA_BIT)
+#define TRACER_TIMESTAMP BIT(TRACER_TIMESTAMP_BIT)
+#define TRACER_BRANCHOUTPUT BIT(TRACER_BRANCHOUTPUT_BIT)
+#define TRACER_RETURN_STACK BIT(TRACER_RETURN_STACK_BIT)
#define TRACER_TIMEOUT 10000
-#define etm_writel(t, v, x) \
- (__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
+#define etm_writel(t, id, v, x) \
+ (__raw_writel((v), (t)->etm_regs[(id)] + (x)))
+#define etm_readl(t, id, x) (__raw_readl((t)->etm_regs[(id)] + (x)))
/* CoreSight Management Registers */
#define CSMR_LOCKACCESS 0xfb0
@@ -43,7 +51,7 @@
#define ETMCTRL_POWERDOWN 1
#define ETMCTRL_PROGRAM (1 << 10)
#define ETMCTRL_PORTSEL (1 << 11)
-#define ETMCTRL_DO_CONTEXTID (3 << 14)
+#define ETMCTRL_CONTEXTIDSIZE(x) (((x) & 3) << 14)
#define ETMCTRL_PORTMASK1 (7 << 4)
#define ETMCTRL_PORTMASK2 (1 << 21)
#define ETMCTRL_PORTMASK (ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
@@ -55,9 +63,12 @@
#define ETMCTRL_DATA_DO_BOTH (ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
#define ETMCTRL_BRANCH_OUTPUT (1 << 8)
#define ETMCTRL_CYCLEACCURATE (1 << 12)
+#define ETMCTRL_TIMESTAMP_EN (1 << 28)
+#define ETMCTRL_RETURN_STACK_EN (1 << 29)
/* ETM configuration code register */
#define ETMR_CONFCODE (0x04)
+#define ETMCCR_ETMIDR_PRESENT BIT(31)
/* ETM trace start/stop resource control register */
#define ETMR_TRACESSCTRL (0x18)
@@ -113,10 +124,25 @@
#define ETMR_TRACEENCTRL 0x24
#define ETMTE_INCLEXCL BIT(24)
#define ETMR_TRACEENEVT 0x20
-#define ETMCTRL_OPTS (ETMCTRL_DO_CPRT | \
- ETMCTRL_DATA_DO_ADDR | \
- ETMCTRL_BRANCH_OUTPUT | \
- ETMCTRL_DO_CONTEXTID)
+
+#define ETMR_VIEWDATAEVT 0x30
+#define ETMR_VIEWDATACTRL1 0x34
+#define ETMR_VIEWDATACTRL2 0x38
+#define ETMR_VIEWDATACTRL3 0x3c
+#define ETMVDC3_EXCLONLY BIT(16)
+
+#define ETMCTRL_OPTS (ETMCTRL_DO_CPRT)
+
+#define ETMR_ID 0x1e4
+#define ETMIDR_VERSION(x) (((x) >> 4) & 0xff)
+#define ETMIDR_VERSION_3_1 0x21
+#define ETMIDR_VERSION_PFT_1_0 0x30
+
+#define ETMR_CCE 0x1e8
+#define ETMCCER_RETURN_STACK_IMPLEMENTED BIT(23)
+#define ETMCCER_TIMESTAMPING_IMPLEMENTED BIT(22)
+
+#define ETMR_TRACEIDR 0x200
/* ETM management registers, "ETM Architecture", 3.5.24 */
#define ETMMR_OSLAR 0x300
@@ -140,14 +166,16 @@
#define ETBFF_TRIGIN BIT(8)
#define ETBFF_TRIGEVT BIT(9)
#define ETBFF_TRIGFL BIT(10)
+#define ETBFF_STOPFL BIT(12)
#define etb_writel(t, v, x) \
(__raw_writel((v), (t)->etb_regs + (x)))
#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
-#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etm_unlock(t) \
- do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
+#define etm_lock(t, id) \
+ do { etm_writel((t), (id), 0, CSMR_LOCKACCESS); } while (0)
+#define etm_unlock(t, id) \
+ do { etm_writel((t), (id), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
#define etb_unlock(t) \
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 53c15de..809203a 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -35,6 +35,9 @@
extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
#endif
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+
#endif
#endif
diff --git a/arch/arm/include/asm/mach/mmc.h b/arch/arm/include/asm/mach/mmc.h
new file mode 100644
index 0000000..bca864a
--- /dev/null
+++ b/arch/arm/include/asm/mach/mmc.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm/include/asm/mach/mmc.h
+ */
+#ifndef ASMARM_MACH_MMC_H
+#define ASMARM_MACH_MMC_H
+
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+
+struct embedded_sdio_data {
+ struct sdio_cis cis;
+ struct sdio_cccr cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+};
+
+struct mmc_platform_data {
+ unsigned int ocr_mask; /* available voltages */
+ int built_in; /* built-in device flag */
+ int card_present; /* card detect state */
+ u32 (*translate_vdd)(struct device *, unsigned int);
+ unsigned int (*status)(struct device *);
+ struct embedded_sdio_data *embedded_sdio;
+ int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id);
+};
+
+#endif
diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h
new file mode 100644
index 0000000..8f730fe
--- /dev/null
+++ b/arch/arm/include/asm/neon.h
@@ -0,0 +1,36 @@
+/*
+ * linux/arch/arm/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/hwcap.h>
+
+#define cpu_has_neon() (!!(elf_hwcap & HWCAP_NEON))
+
+#ifdef __ARM_NEON__
+
+/*
+ * If you are affected by the BUILD_BUG below, it probably means that you are
+ * using NEON code /and/ calling the kernel_neon_begin() function from the same
+ * compilation unit. To prevent issues that may arise from GCC reordering or
+ * generating(1) NEON instructions outside of these begin/end functions, the
+ * only supported way of using NEON code in the kernel is by isolating it in a
+ * separate compilation unit, and calling it from another unit from inside a
+ * kernel_neon_begin/kernel_neon_end pair.
+ *
+ * (1) Current GCC (4.7) might generate NEON instructions at O3 level if
+ * -mpfu=neon is set.
+ */
+
+#define kernel_neon_begin() \
+ BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code")
+
+#else
+void kernel_neon_begin(void);
+#endif
+void kernel_neon_end(void);
diff --git a/arch/arm/include/asm/rodata.h b/arch/arm/include/asm/rodata.h
new file mode 100644
index 0000000..8c8add8
--- /dev/null
+++ b/arch/arm/include/asm/rodata.h
@@ -0,0 +1,32 @@
+/*
+ * arch/arm/include/asm/rodata.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASMARM_RODATA_H
+#define _ASMARM_RODATA_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_DEBUG_RODATA
+
+int set_memory_rw(unsigned long virt, int numpages);
+int set_memory_ro(unsigned long virt, int numpages);
+
+void mark_rodata_ro(void);
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
+#endif
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d3a22be..c5aa088 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -81,6 +81,8 @@
extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+extern void smp_send_all_cpu_backtrace(void);
+
struct smp_operations {
#ifdef CONFIG_SMP
/*
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 73ddd72..ed805f1 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -103,8 +103,7 @@
memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(struct task_struct *task,
- struct pt_regs *regs)
+static inline int syscall_get_arch(void)
{
/* ARM tasks don't change audit architectures on the fly. */
return AUDIT_ARCH_ARM;
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index cbd6197..4387624 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,7 @@
#include <uapi/asm/unistd.h>
-#define __NR_syscalls (380)
+#define __NR_syscalls (384)
#define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0)
#define __ARCH_WANT_STAT64
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index af33b44..17407c9 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -406,6 +406,12 @@
#define __NR_process_vm_writev (__NR_SYSCALL_BASE+377)
#define __NR_kcmp (__NR_SYSCALL_BASE+378)
#define __NR_finit_module (__NR_SYSCALL_BASE+379)
+/* Reserve for later
+#define __NR_sched_setattr (__NR_SYSCALL_BASE+380)
+#define __NR_sched_getattr (__NR_SYSCALL_BASE+381)
+#define __NR_renameat2 (__NR_SYSCALL_BASE+382)
+*/
+#define __NR_seccomp (__NR_SYSCALL_BASE+383)
/*
* This may need to be greater than __NR_last_syscall+1 in order to
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index c6ca7e3..725f844 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -389,6 +389,11 @@
CALL(sys_process_vm_writev)
CALL(sys_kcmp)
CALL(sys_finit_module)
+/* 380 */ CALL(sys_ni_syscall) /* reserved sys_sched_setattr */
+ CALL(sys_ni_syscall) /* reserved sys_sched_getattr */
+ CALL(sys_ni_syscall) /* reserved sys_renameat2 */
+ CALL(sys_seccomp)
+
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 8ff0ecd..7db3247 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/types.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <linux/sysrq.h>
#include <linux/device.h>
#include <linux/clk.h>
@@ -37,26 +38,37 @@
struct tracectx {
unsigned int etb_bufsz;
void __iomem *etb_regs;
- void __iomem *etm_regs;
+ void __iomem **etm_regs;
+ int etm_regs_count;
unsigned long flags;
int ncmppairs;
int etm_portsz;
+ int etm_contextid_size;
+ u32 etb_fc;
+ unsigned long range_start;
+ unsigned long range_end;
+ unsigned long data_range_start;
+ unsigned long data_range_end;
+ bool dump_initial_etb;
struct device *dev;
struct clk *emu_clk;
struct mutex mutex;
};
-static struct tracectx tracer;
+static struct tracectx tracer = {
+ .range_start = (unsigned long)_stext,
+ .range_end = (unsigned long)_etext,
+};
static inline bool trace_isrunning(struct tracectx *t)
{
return !!(t->flags & TRACER_RUNNING);
}
-static int etm_setup_address_range(struct tracectx *t, int n,
+static int etm_setup_address_range(struct tracectx *t, int id, int n,
unsigned long start, unsigned long end, int exclude, int data)
{
- u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \
+ u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_IGNSECURITY |
ETMAAT_NOVALCMP;
if (n < 1 || n > t->ncmppairs)
@@ -72,95 +84,185 @@
flags |= ETMAAT_IEXEC;
/* first comparator for the range */
- etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2));
- etm_writel(t, start, ETMR_COMP_VAL(n * 2));
+ etm_writel(t, id, flags, ETMR_COMP_ACC_TYPE(n * 2));
+ etm_writel(t, id, start, ETMR_COMP_VAL(n * 2));
/* second comparator is right next to it */
- etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
- etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1));
+ etm_writel(t, id, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
+ etm_writel(t, id, end, ETMR_COMP_VAL(n * 2 + 1));
- flags = exclude ? ETMTE_INCLEXCL : 0;
- etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL);
+ if (data) {
+ flags = exclude ? ETMVDC3_EXCLONLY : 0;
+ if (exclude)
+ n += 8;
+ etm_writel(t, id, flags | BIT(n), ETMR_VIEWDATACTRL3);
+ } else {
+ flags = exclude ? ETMTE_INCLEXCL : 0;
+ etm_writel(t, id, flags | (1 << n), ETMR_TRACEENCTRL);
+ }
return 0;
}
+static int trace_start_etm(struct tracectx *t, int id)
+{
+ u32 v;
+ unsigned long timeout = TRACER_TIMEOUT;
+
+ v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
+ v |= ETMCTRL_CONTEXTIDSIZE(t->etm_contextid_size);
+
+ if (t->flags & TRACER_CYCLE_ACC)
+ v |= ETMCTRL_CYCLEACCURATE;
+
+ if (t->flags & TRACER_BRANCHOUTPUT)
+ v |= ETMCTRL_BRANCH_OUTPUT;
+
+ if (t->flags & TRACER_TRACE_DATA)
+ v |= ETMCTRL_DATA_DO_ADDR;
+
+ if (t->flags & TRACER_TIMESTAMP)
+ v |= ETMCTRL_TIMESTAMP_EN;
+
+ if (t->flags & TRACER_RETURN_STACK)
+ v |= ETMCTRL_RETURN_STACK_EN;
+
+ etm_unlock(t, id);
+
+ etm_writel(t, id, v, ETMR_CTRL);
+
+ while (!(etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
+ ;
+ if (!timeout) {
+ dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
+ etm_lock(t, id);
+ return -EFAULT;
+ }
+
+ if (t->range_start || t->range_end)
+ etm_setup_address_range(t, id, 1,
+ t->range_start, t->range_end, 0, 0);
+ else
+ etm_writel(t, id, ETMTE_INCLEXCL, ETMR_TRACEENCTRL);
+
+ etm_writel(t, id, 0, ETMR_TRACEENCTRL2);
+ etm_writel(t, id, 0, ETMR_TRACESSCTRL);
+ etm_writel(t, id, 0x6f, ETMR_TRACEENEVT);
+
+ etm_writel(t, id, 0, ETMR_VIEWDATACTRL1);
+ etm_writel(t, id, 0, ETMR_VIEWDATACTRL2);
+
+ if (t->data_range_start || t->data_range_end)
+ etm_setup_address_range(t, id, 2, t->data_range_start,
+ t->data_range_end, 0, 1);
+ else
+ etm_writel(t, id, ETMVDC3_EXCLONLY, ETMR_VIEWDATACTRL3);
+
+ etm_writel(t, id, 0x6f, ETMR_VIEWDATAEVT);
+
+ v &= ~ETMCTRL_PROGRAM;
+ v |= ETMCTRL_PORTSEL;
+
+ etm_writel(t, id, v, ETMR_CTRL);
+
+ timeout = TRACER_TIMEOUT;
+ while (etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
+ ;
+ if (!timeout) {
+ dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
+ etm_lock(t, id);
+ return -EFAULT;
+ }
+
+ etm_lock(t, id);
+ return 0;
+}
+
static int trace_start(struct tracectx *t)
{
- u32 v;
- unsigned long timeout = TRACER_TIMEOUT;
+ int ret;
+ int id;
+ u32 etb_fc = t->etb_fc;
etb_unlock(t);
- etb_writel(t, 0, ETBR_FORMATTERCTRL);
+ t->dump_initial_etb = false;
+ etb_writel(t, 0, ETBR_WRITEADDR);
+ etb_writel(t, etb_fc, ETBR_FORMATTERCTRL);
etb_writel(t, 1, ETBR_CTRL);
etb_lock(t);
- /* configure etm */
- v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
-
- if (t->flags & TRACER_CYCLE_ACC)
- v |= ETMCTRL_CYCLEACCURATE;
-
- etm_unlock(t);
-
- etm_writel(t, v, ETMR_CTRL);
-
- while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
- etm_lock(t);
- return -EFAULT;
+ /* configure etm(s) */
+ for (id = 0; id < t->etm_regs_count; id++) {
+ ret = trace_start_etm(t, id);
+ if (ret)
+ return ret;
}
- etm_setup_address_range(t, 1, (unsigned long)_stext,
- (unsigned long)_etext, 0, 0);
- etm_writel(t, 0, ETMR_TRACEENCTRL2);
- etm_writel(t, 0, ETMR_TRACESSCTRL);
- etm_writel(t, 0x6f, ETMR_TRACEENEVT);
-
- v &= ~ETMCTRL_PROGRAM;
- v |= ETMCTRL_PORTSEL;
-
- etm_writel(t, v, ETMR_CTRL);
-
- timeout = TRACER_TIMEOUT;
- while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
- etm_lock(t);
- return -EFAULT;
- }
-
- etm_lock(t);
-
t->flags |= TRACER_RUNNING;
return 0;
}
-static int trace_stop(struct tracectx *t)
+static int trace_stop_etm(struct tracectx *t, int id)
{
unsigned long timeout = TRACER_TIMEOUT;
- etm_unlock(t);
+ etm_unlock(t, id);
- etm_writel(t, 0x440, ETMR_CTRL);
- while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
+ etm_writel(t, id, 0x440, ETMR_CTRL);
+ while (!(etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
;
if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
- etm_lock(t);
+ dev_err(t->dev,
+ "etm%d: Waiting for progbit to assert timed out\n",
+ id);
+ etm_lock(t, id);
return -EFAULT;
}
- etm_lock(t);
+ etm_lock(t, id);
+ return 0;
+}
+
+static int trace_power_down_etm(struct tracectx *t, int id)
+{
+ unsigned long timeout = TRACER_TIMEOUT;
+ etm_unlock(t, id);
+ while (!(etm_readl(t, id, ETMR_STATUS) & ETMST_PROGBIT) && --timeout)
+ ;
+ if (!timeout) {
+ dev_err(t->dev, "etm%d: Waiting for status progbit to assert timed out\n",
+ id);
+ etm_lock(t, id);
+ return -EFAULT;
+ }
+
+ etm_writel(t, id, 0x441, ETMR_CTRL);
+
+ etm_lock(t, id);
+ return 0;
+}
+
+static int trace_stop(struct tracectx *t)
+{
+ int id;
+ unsigned long timeout = TRACER_TIMEOUT;
+ u32 etb_fc = t->etb_fc;
+
+ for (id = 0; id < t->etm_regs_count; id++)
+ trace_stop_etm(t, id);
+
+ for (id = 0; id < t->etm_regs_count; id++)
+ trace_power_down_etm(t, id);
etb_unlock(t);
- etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
+ if (etb_fc) {
+ etb_fc |= ETBFF_STOPFL;
+ etb_writel(t, t->etb_fc, ETBR_FORMATTERCTRL);
+ }
+ etb_writel(t, etb_fc | ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
timeout = TRACER_TIMEOUT;
while (etb_readl(t, ETBR_FORMATTERCTRL) &
@@ -185,24 +287,15 @@
static int etb_getdatalen(struct tracectx *t)
{
u32 v;
- int rp, wp;
+ int wp;
v = etb_readl(t, ETBR_STATUS);
if (v & 1)
return t->etb_bufsz;
- rp = etb_readl(t, ETBR_READADDR);
wp = etb_readl(t, ETBR_WRITEADDR);
-
- if (rp > wp) {
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_WRITEADDR);
-
- return 0;
- }
-
- return wp - rp;
+ return wp;
}
/* sysrq+v will always stop the running trace and leave it at that */
@@ -235,21 +328,18 @@
printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM)));
printk(KERN_INFO "\n--- ETB buffer end ---\n");
- /* deassert the overflow bit */
- etb_writel(t, 1, ETBR_CTRL);
- etb_writel(t, 0, ETBR_CTRL);
-
- etb_writel(t, 0, ETBR_TRIGGERCOUNT);
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_WRITEADDR);
-
etb_lock(t);
}
static void sysrq_etm_dump(int key)
{
+ if (!mutex_trylock(&tracer.mutex)) {
+ printk(KERN_INFO "Tracing hardware busy\n");
+ return;
+ }
dev_dbg(tracer.dev, "Dumping ETB buffer\n");
etm_dump();
+ mutex_unlock(&tracer.mutex);
}
static struct sysrq_key_op sysrq_etm_op = {
@@ -276,6 +366,10 @@
struct tracectx *t = file->private_data;
u32 first = 0;
u32 *buf;
+ int wpos;
+ int skip;
+ long wlength;
+ loff_t pos = *ppos;
mutex_lock(&t->mutex);
@@ -287,31 +381,39 @@
etb_unlock(t);
total = etb_getdatalen(t);
+ if (total == 0 && t->dump_initial_etb)
+ total = t->etb_bufsz;
if (total == t->etb_bufsz)
first = etb_readl(t, ETBR_WRITEADDR);
+ if (pos > total * 4) {
+ skip = 0;
+ wpos = total;
+ } else {
+ skip = (int)pos % 4;
+ wpos = (int)pos / 4;
+ }
+ total -= wpos;
+ first = (first + wpos) % t->etb_bufsz;
+
etb_writel(t, first, ETBR_READADDR);
- length = min(total * 4, (int)len);
- buf = vmalloc(length);
+ wlength = min(total, DIV_ROUND_UP(skip + (int)len, 4));
+ length = min(total * 4 - skip, (int)len);
+ buf = vmalloc(wlength * 4);
- dev_dbg(t->dev, "ETB buffer length: %d\n", total);
+ dev_dbg(t->dev, "ETB read %ld bytes to %lld from %ld words at %d\n",
+ length, pos, wlength, first);
+ dev_dbg(t->dev, "ETB buffer length: %d\n", total + wpos);
dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS));
- for (i = 0; i < length / 4; i++)
+ for (i = 0; i < wlength; i++)
buf[i] = etb_readl(t, ETBR_READMEM);
- /* the only way to deassert overflow bit in ETB status is this */
- etb_writel(t, 1, ETBR_CTRL);
- etb_writel(t, 0, ETBR_CTRL);
-
- etb_writel(t, 0, ETBR_WRITEADDR);
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-
etb_lock(t);
- length -= copy_to_user(data, buf, length);
+ length -= copy_to_user(data, (u8 *)buf + skip, length);
vfree(buf);
+ *ppos = pos + length;
out:
mutex_unlock(&t->mutex);
@@ -348,28 +450,17 @@
if (ret)
goto out;
+ mutex_lock(&t->mutex);
t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
if (!t->etb_regs) {
ret = -ENOMEM;
goto out_release;
}
+ t->dev = &dev->dev;
+ t->dump_initial_etb = true;
amba_set_drvdata(dev, t);
- etb_miscdev.parent = &dev->dev;
-
- ret = misc_register(&etb_miscdev);
- if (ret)
- goto out_unmap;
-
- t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
- if (IS_ERR(t->emu_clk)) {
- dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
- return -EFAULT;
- }
-
- clk_enable(t->emu_clk);
-
etb_unlock(t);
t->etb_bufsz = etb_readl(t, ETBR_DEPTH);
dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz);
@@ -378,6 +469,20 @@
etb_writel(t, 0, ETBR_CTRL);
etb_writel(t, 0x1000, ETBR_FORMATTERCTRL);
etb_lock(t);
+ mutex_unlock(&t->mutex);
+
+ etb_miscdev.parent = &dev->dev;
+
+ ret = misc_register(&etb_miscdev);
+ if (ret)
+ goto out_unmap;
+
+ /* Get optional clock. Currently used to select clock source on omap3 */
+ t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
+ if (IS_ERR(t->emu_clk))
+ dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
+ else
+ clk_enable(t->emu_clk);
dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n");
@@ -385,10 +490,13 @@
return ret;
out_unmap:
+ mutex_lock(&t->mutex);
amba_set_drvdata(dev, NULL);
iounmap(t->etb_regs);
+ t->etb_regs = NULL;
out_release:
+ mutex_unlock(&t->mutex);
amba_release_regions(dev);
return ret;
@@ -403,8 +511,10 @@
iounmap(t->etb_regs);
t->etb_regs = NULL;
- clk_disable(t->emu_clk);
- clk_put(t->emu_clk);
+ if (!IS_ERR(t->emu_clk)) {
+ clk_disable(t->emu_clk);
+ clk_put(t->emu_clk);
+ }
amba_release_regions(dev);
@@ -448,7 +558,10 @@
return -EINVAL;
mutex_lock(&tracer.mutex);
- ret = value ? trace_start(&tracer) : trace_stop(&tracer);
+ if (!tracer.etb_regs)
+ ret = -ENODEV;
+ else
+ ret = value ? trace_start(&tracer) : trace_stop(&tracer);
mutex_unlock(&tracer.mutex);
return ret ? : n;
@@ -463,36 +576,50 @@
{
u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st;
int datalen;
+ int id;
+ int ret;
- etb_unlock(&tracer);
- datalen = etb_getdatalen(&tracer);
- etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
- etb_ra = etb_readl(&tracer, ETBR_READADDR);
- etb_st = etb_readl(&tracer, ETBR_STATUS);
- etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
- etb_lock(&tracer);
+ mutex_lock(&tracer.mutex);
+ if (tracer.etb_regs) {
+ etb_unlock(&tracer);
+ datalen = etb_getdatalen(&tracer);
+ etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
+ etb_ra = etb_readl(&tracer, ETBR_READADDR);
+ etb_st = etb_readl(&tracer, ETBR_STATUS);
+ etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
+ etb_lock(&tracer);
+ } else {
+ etb_wa = etb_ra = etb_st = etb_fc = ~0;
+ datalen = -1;
+ }
- etm_unlock(&tracer);
- etm_ctrl = etm_readl(&tracer, ETMR_CTRL);
- etm_st = etm_readl(&tracer, ETMR_STATUS);
- etm_lock(&tracer);
-
- return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
+ ret = sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
"ETBR_WRITEADDR:\t%08x\n"
"ETBR_READADDR:\t%08x\n"
"ETBR_STATUS:\t%08x\n"
- "ETBR_FORMATTERCTRL:\t%08x\n"
- "ETMR_CTRL:\t%08x\n"
- "ETMR_STATUS:\t%08x\n",
+ "ETBR_FORMATTERCTRL:\t%08x\n",
datalen,
tracer.ncmppairs,
etb_wa,
etb_ra,
etb_st,
- etb_fc,
+ etb_fc
+ );
+
+ for (id = 0; id < tracer.etm_regs_count; id++) {
+ etm_unlock(&tracer, id);
+ etm_ctrl = etm_readl(&tracer, id, ETMR_CTRL);
+ etm_st = etm_readl(&tracer, id, ETMR_STATUS);
+ etm_lock(&tracer, id);
+ ret += sprintf(buf + ret, "ETMR_CTRL:\t%08x\n"
+ "ETMR_STATUS:\t%08x\n",
etm_ctrl,
etm_st
);
+ }
+ mutex_unlock(&tracer.mutex);
+
+ return ret;
}
static struct kobj_attribute trace_info_attr =
@@ -531,42 +658,260 @@
static struct kobj_attribute trace_mode_attr =
__ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store);
+static ssize_t trace_contextid_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ /* 0: No context id tracing, 1: One byte, 2: Two bytes, 3: Four bytes */
+ return sprintf(buf, "%d\n", (1 << tracer.etm_contextid_size) >> 1);
+}
+
+static ssize_t trace_contextid_size_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned int contextid_size;
+
+ if (sscanf(buf, "%u", &contextid_size) != 1)
+ return -EINVAL;
+
+ if (contextid_size == 3 || contextid_size > 4)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ tracer.etm_contextid_size = fls(contextid_size);
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+static struct kobj_attribute trace_contextid_size_attr =
+ __ATTR(trace_contextid_size, 0644,
+ trace_contextid_size_show, trace_contextid_size_store);
+
+static ssize_t trace_branch_output_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_BRANCHOUTPUT));
+}
+
+static ssize_t trace_branch_output_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned int branch_output;
+
+ if (sscanf(buf, "%u", &branch_output) != 1)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ if (branch_output) {
+ tracer.flags |= TRACER_BRANCHOUTPUT;
+ /* Branch broadcasting is incompatible with the return stack */
+ tracer.flags &= ~TRACER_RETURN_STACK;
+ } else {
+ tracer.flags &= ~TRACER_BRANCHOUTPUT;
+ }
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+static struct kobj_attribute trace_branch_output_attr =
+ __ATTR(trace_branch_output, 0644,
+ trace_branch_output_show, trace_branch_output_store);
+
+static ssize_t trace_return_stack_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_RETURN_STACK));
+}
+
+static ssize_t trace_return_stack_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned int return_stack;
+
+ if (sscanf(buf, "%u", &return_stack) != 1)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ if (return_stack) {
+ tracer.flags |= TRACER_RETURN_STACK;
+ /* Return stack is incompatible with branch broadcasting */
+ tracer.flags &= ~TRACER_BRANCHOUTPUT;
+ } else {
+ tracer.flags &= ~TRACER_RETURN_STACK;
+ }
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+static struct kobj_attribute trace_return_stack_attr =
+ __ATTR(trace_return_stack, 0644,
+ trace_return_stack_show, trace_return_stack_store);
+
+static ssize_t trace_timestamp_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_TIMESTAMP));
+}
+
+static ssize_t trace_timestamp_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned int timestamp;
+
+ if (sscanf(buf, "%u", ×tamp) != 1)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ if (timestamp)
+ tracer.flags |= TRACER_TIMESTAMP;
+ else
+ tracer.flags &= ~TRACER_TIMESTAMP;
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+static struct kobj_attribute trace_timestamp_attr =
+ __ATTR(trace_timestamp, 0644,
+ trace_timestamp_show, trace_timestamp_store);
+
+static ssize_t trace_range_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%08lx %08lx\n",
+ tracer.range_start, tracer.range_end);
+}
+
+static ssize_t trace_range_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned long range_start, range_end;
+
+ if (sscanf(buf, "%lx %lx", &range_start, &range_end) != 2)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ tracer.range_start = range_start;
+ tracer.range_end = range_end;
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+
+static struct kobj_attribute trace_range_attr =
+ __ATTR(trace_range, 0644, trace_range_show, trace_range_store);
+
+static ssize_t trace_data_range_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ unsigned long range_start;
+ u64 range_end;
+ mutex_lock(&tracer.mutex);
+ range_start = tracer.data_range_start;
+ range_end = tracer.data_range_end;
+ if (!range_end && (tracer.flags & TRACER_TRACE_DATA))
+ range_end = 0x100000000ULL;
+ mutex_unlock(&tracer.mutex);
+ return sprintf(buf, "%08lx %08llx\n", range_start, range_end);
+}
+
+static ssize_t trace_data_range_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ unsigned long range_start;
+ u64 range_end;
+
+ if (sscanf(buf, "%lx %llx", &range_start, &range_end) != 2)
+ return -EINVAL;
+
+ mutex_lock(&tracer.mutex);
+ tracer.data_range_start = range_start;
+ tracer.data_range_end = (unsigned long)range_end;
+ if (range_end)
+ tracer.flags |= TRACER_TRACE_DATA;
+ else
+ tracer.flags &= ~TRACER_TRACE_DATA;
+ mutex_unlock(&tracer.mutex);
+
+ return n;
+}
+
+
+static struct kobj_attribute trace_data_range_attr =
+ __ATTR(trace_data_range, 0644,
+ trace_data_range_show, trace_data_range_store);
+
static int etm_probe(struct amba_device *dev, const struct amba_id *id)
{
struct tracectx *t = &tracer;
int ret = 0;
+ void __iomem **new_regs;
+ int new_count;
+ u32 etmccr;
+ u32 etmidr;
+ u32 etmccer = 0;
+ u8 etm_version = 0;
- if (t->etm_regs) {
- dev_dbg(&dev->dev, "ETM already initialized\n");
- ret = -EBUSY;
+ mutex_lock(&t->mutex);
+ new_count = t->etm_regs_count + 1;
+ new_regs = krealloc(t->etm_regs,
+ sizeof(t->etm_regs[0]) * new_count, GFP_KERNEL);
+
+ if (!new_regs) {
+ dev_dbg(&dev->dev, "Failed to allocate ETM register array\n");
+ ret = -ENOMEM;
goto out;
}
+ t->etm_regs = new_regs;
ret = amba_request_regions(dev, NULL);
if (ret)
goto out;
- t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
- if (!t->etm_regs) {
+ t->etm_regs[t->etm_regs_count] =
+ ioremap_nocache(dev->res.start, resource_size(&dev->res));
+ if (!t->etm_regs[t->etm_regs_count]) {
ret = -ENOMEM;
goto out_release;
}
- amba_set_drvdata(dev, t);
+ amba_set_drvdata(dev, t->etm_regs[t->etm_regs_count]);
- mutex_init(&t->mutex);
- t->dev = &dev->dev;
- t->flags = TRACER_CYCLE_ACC;
+ t->flags = TRACER_CYCLE_ACC | TRACER_TRACE_DATA | TRACER_BRANCHOUTPUT;
t->etm_portsz = 1;
+ t->etm_contextid_size = 3;
- etm_unlock(t);
- (void)etm_readl(t, ETMMR_PDSR);
+ etm_unlock(t, t->etm_regs_count);
+ (void)etm_readl(t, t->etm_regs_count, ETMMR_PDSR);
/* dummy first read */
- (void)etm_readl(&tracer, ETMMR_OSSRR);
+ (void)etm_readl(&tracer, t->etm_regs_count, ETMMR_OSSRR);
- t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
- etm_writel(t, 0x440, ETMR_CTRL);
- etm_lock(t);
+ etmccr = etm_readl(t, t->etm_regs_count, ETMR_CONFCODE);
+ t->ncmppairs = etmccr & 0xf;
+ if (etmccr & ETMCCR_ETMIDR_PRESENT) {
+ etmidr = etm_readl(t, t->etm_regs_count, ETMR_ID);
+ etm_version = ETMIDR_VERSION(etmidr);
+ if (etm_version >= ETMIDR_VERSION_3_1)
+ etmccer = etm_readl(t, t->etm_regs_count, ETMR_CCE);
+ }
+ etm_writel(t, t->etm_regs_count, 0x441, ETMR_CTRL);
+ etm_writel(t, t->etm_regs_count, new_count, ETMR_TRACEIDR);
+ etm_lock(t, t->etm_regs_count);
ret = sysfs_create_file(&dev->dev.kobj,
&trace_running_attr.attr);
@@ -582,35 +927,100 @@
if (ret)
dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n");
- dev_dbg(t->dev, "ETM AMBA driver initialized.\n");
+ ret = sysfs_create_file(&dev->dev.kobj,
+ &trace_contextid_size_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev,
+ "Failed to create trace_contextid_size in sysfs\n");
+
+ ret = sysfs_create_file(&dev->dev.kobj,
+ &trace_branch_output_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev,
+ "Failed to create trace_branch_output in sysfs\n");
+
+ if (etmccer & ETMCCER_RETURN_STACK_IMPLEMENTED) {
+ ret = sysfs_create_file(&dev->dev.kobj,
+ &trace_return_stack_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev,
+ "Failed to create trace_return_stack in sysfs\n");
+ }
+
+ if (etmccer & ETMCCER_TIMESTAMPING_IMPLEMENTED) {
+ ret = sysfs_create_file(&dev->dev.kobj,
+ &trace_timestamp_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev,
+ "Failed to create trace_timestamp in sysfs\n");
+ }
+
+ ret = sysfs_create_file(&dev->dev.kobj, &trace_range_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev, "Failed to create trace_range in sysfs\n");
+
+ if (etm_version < ETMIDR_VERSION_PFT_1_0) {
+ ret = sysfs_create_file(&dev->dev.kobj,
+ &trace_data_range_attr.attr);
+ if (ret)
+ dev_dbg(&dev->dev,
+ "Failed to create trace_data_range in sysfs\n");
+ } else {
+ tracer.flags &= ~TRACER_TRACE_DATA;
+ }
+
+ dev_dbg(&dev->dev, "ETM AMBA driver initialized.\n");
+
+ /* Enable formatter if there are multiple trace sources */
+ if (new_count > 1)
+ t->etb_fc = ETBFF_ENFCONT | ETBFF_ENFTC;
+
+ t->etm_regs_count = new_count;
out:
+ mutex_unlock(&t->mutex);
return ret;
out_unmap:
amba_set_drvdata(dev, NULL);
- iounmap(t->etm_regs);
+ iounmap(t->etm_regs[t->etm_regs_count]);
out_release:
amba_release_regions(dev);
+ mutex_unlock(&t->mutex);
return ret;
}
static int etm_remove(struct amba_device *dev)
{
- struct tracectx *t = amba_get_drvdata(dev);
-
- amba_set_drvdata(dev, NULL);
-
- iounmap(t->etm_regs);
- t->etm_regs = NULL;
-
- amba_release_regions(dev);
+ int i;
+ struct tracectx *t = &tracer;
+ void __iomem *etm_regs = amba_get_drvdata(dev);
sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr);
sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr);
sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr);
+ sysfs_remove_file(&dev->dev.kobj, &trace_range_attr.attr);
+ sysfs_remove_file(&dev->dev.kobj, &trace_data_range_attr.attr);
+
+ amba_set_drvdata(dev, NULL);
+
+ mutex_lock(&t->mutex);
+ for (i = 0; i < t->etm_regs_count; i++)
+ if (t->etm_regs[i] == etm_regs)
+ break;
+ for (; i < t->etm_regs_count - 1; i++)
+ t->etm_regs[i] = t->etm_regs[i + 1];
+ t->etm_regs_count--;
+ if (!t->etm_regs_count) {
+ kfree(t->etm_regs);
+ t->etm_regs = NULL;
+ }
+ mutex_unlock(&t->mutex);
+
+ iounmap(etm_regs);
+ amba_release_regions(dev);
return 0;
}
@@ -620,6 +1030,10 @@
.id = 0x0003b921,
.mask = 0x0007ffff,
},
+ {
+ .id = 0x0003b950,
+ .mask = 0x0007ffff,
+ },
{ 0, 0 },
};
@@ -637,6 +1051,8 @@
{
int retval;
+ mutex_init(&tracer.mutex);
+
retval = amba_driver_register(&etb_driver);
if (retval) {
printk(KERN_ERR "Failed to register etb\n");
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 34e5664..6a740a9 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -13,6 +13,7 @@
*/
#include <linux/ftrace.h>
+#include <linux/module.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
@@ -63,6 +64,20 @@
}
#endif
+int ftrace_arch_code_modify_prepare(void)
+{
+ set_kernel_text_rw();
+ set_all_modules_text_rw();
+ return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+ set_all_modules_text_ro();
+ set_kernel_text_ro();
+ return 0;
+}
+
static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
{
return arm_gen_branch_link(pc, addr);
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 778c2f7..b321c8f 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -144,6 +144,8 @@
static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
{
+ if (user_mode(regs))
+ return -1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return 0;
@@ -151,6 +153,8 @@
static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
{
+ if (user_mode(regs))
+ return -1;
compiled_break = 1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index ac4c2e5..978002e 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -32,6 +32,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/cpuidle.h>
#include <linux/leds.h>
+#include <linux/console.h>
#include <asm/cacheflush.h>
#include <asm/idmap.h>
@@ -57,9 +58,46 @@
"ARM" , "Thumb" , "Jazelle", "ThumbEE"
};
+#ifdef CONFIG_SMP
+void arch_trigger_all_cpu_backtrace(void)
+{
+ smp_send_all_cpu_backtrace();
+}
+#else
+void arch_trigger_all_cpu_backtrace(void)
+{
+ dump_stack();
+}
+#endif
+
extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
typedef void (*phys_reset_t)(unsigned long);
+#ifdef CONFIG_ARM_FLUSH_CONSOLE_ON_RESTART
+void arm_machine_flush_console(void)
+{
+ printk("\n");
+ pr_emerg("Restarting %s\n", linux_banner);
+ if (console_trylock()) {
+ console_unlock();
+ return;
+ }
+
+ mdelay(50);
+
+ local_irq_disable();
+ if (!console_trylock())
+ pr_emerg("arm_restart: Console was locked! Busting\n");
+ else
+ pr_emerg("arm_restart: Console was locked!\n");
+ console_unlock();
+}
+#else
+void arm_machine_flush_console(void)
+{
+}
+#endif
+
/*
* A temporary stack to use for CPU reset. This is static so that we
* don't clobber it with the identity mapping. When running with this
@@ -147,6 +185,7 @@
void arch_cpu_idle_enter(void)
{
+ idle_notifier_call_chain(IDLE_START);
ledtrig_cpu(CPU_LED_IDLE_START);
#ifdef CONFIG_PL310_ERRATA_769419
wmb();
@@ -156,6 +195,7 @@
void arch_cpu_idle_exit(void)
{
ledtrig_cpu(CPU_LED_IDLE_END);
+ idle_notifier_call_chain(IDLE_END);
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -195,6 +235,16 @@
*/
void machine_shutdown(void)
{
+#ifdef CONFIG_SMP
+ /*
+ * Disable preemption so we're guaranteed to
+ * run to power off or reboot and prevent
+ * the possibility of switching to another
+ * thread that might wind up blocking on
+ * one of the stopped CPUs.
+ */
+ preempt_disable();
+#endif
disable_nonboot_cpus();
}
@@ -240,6 +290,10 @@
{
smp_send_stop();
+ /* Flush the console to make sure all the relevant messages make it
+ * out to the console drivers */
+ arm_machine_flush_console();
+
arm_pm_restart(reboot_mode, cmd);
/* Give a grace period for failure to restart of 1s */
@@ -251,6 +305,77 @@
while (1);
}
+/*
+ * dump a block of kernel memory from around the given address
+ */
+static void show_data(unsigned long addr, int nbytes, const char *name)
+{
+ int i, j;
+ int nlines;
+ u32 *p;
+
+ /*
+ * don't attempt to dump non-kernel addresses or
+ * values that are probably just small negative numbers
+ */
+ if (addr < PAGE_OFFSET || addr > -256UL)
+ return;
+
+ printk("\n%s: %#lx:\n", name, addr);
+
+ /*
+ * round address down to a 32 bit boundary
+ * and always dump a multiple of 32 bytes
+ */
+ p = (u32 *)(addr & ~(sizeof(u32) - 1));
+ nbytes += (addr & (sizeof(u32) - 1));
+ nlines = (nbytes + 31) / 32;
+
+
+ for (i = 0; i < nlines; i++) {
+ /*
+ * just display low 16 bits of address to keep
+ * each line of the dump < 80 characters
+ */
+ printk("%04lx ", (unsigned long)p & 0xffff);
+ for (j = 0; j < 8; j++) {
+ u32 data;
+ if (probe_kernel_address(p, data)) {
+ printk(" ********");
+ } else {
+ printk(" %08x", data);
+ }
+ ++p;
+ }
+ printk("\n");
+ }
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+ mm_segment_t fs;
+
+ fs = get_fs();
+ set_fs(KERNEL_DS);
+ show_data(regs->ARM_pc - nbytes, nbytes * 2, "PC");
+ show_data(regs->ARM_lr - nbytes, nbytes * 2, "LR");
+ show_data(regs->ARM_sp - nbytes, nbytes * 2, "SP");
+ show_data(regs->ARM_ip - nbytes, nbytes * 2, "IP");
+ show_data(regs->ARM_fp - nbytes, nbytes * 2, "FP");
+ show_data(regs->ARM_r0 - nbytes, nbytes * 2, "R0");
+ show_data(regs->ARM_r1 - nbytes, nbytes * 2, "R1");
+ show_data(regs->ARM_r2 - nbytes, nbytes * 2, "R2");
+ show_data(regs->ARM_r3 - nbytes, nbytes * 2, "R3");
+ show_data(regs->ARM_r4 - nbytes, nbytes * 2, "R4");
+ show_data(regs->ARM_r5 - nbytes, nbytes * 2, "R5");
+ show_data(regs->ARM_r6 - nbytes, nbytes * 2, "R6");
+ show_data(regs->ARM_r7 - nbytes, nbytes * 2, "R7");
+ show_data(regs->ARM_r8 - nbytes, nbytes * 2, "R8");
+ show_data(regs->ARM_r9 - nbytes, nbytes * 2, "R9");
+ show_data(regs->ARM_r10 - nbytes, nbytes * 2, "R10");
+ set_fs(fs);
+}
+
void __show_regs(struct pt_regs *regs)
{
unsigned long flags;
@@ -307,6 +432,8 @@
printk("Control: %08x%s\n", ctrl, buf);
}
#endif
+
+ show_extra_register_data(regs, 128);
}
void show_regs(struct pt_regs * regs)
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 4e2110d..fe8c5ec 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -916,7 +916,7 @@
PTRACE_SYSCALL_EXIT,
};
-static int tracehook_report_syscall(struct pt_regs *regs,
+static void tracehook_report_syscall(struct pt_regs *regs,
enum ptrace_syscall_dir dir)
{
unsigned long ip;
@@ -934,7 +934,6 @@
current_thread_info()->syscall = -1;
regs->ARM_ip = ip;
- return current_thread_info()->syscall;
}
asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
@@ -946,7 +945,9 @@
return -1;
if (test_thread_flag(TIF_SYSCALL_TRACE))
- scno = tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+ tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+ scno = current_thread_info()->syscall;
if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
trace_sys_enter(regs, scno);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5919eb4..0c96b2d 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -66,6 +66,7 @@
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
+ IPI_CPU_BACKTRACE,
};
static DECLARE_COMPLETION(cpu_running);
@@ -463,6 +464,7 @@
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_CPU_BACKTRACE, "CPU backtrace"),
};
void show_ipi_list(struct seq_file *p, int prec)
@@ -588,6 +590,58 @@
cpu_relax();
}
+static cpumask_t backtrace_mask;
+static DEFINE_RAW_SPINLOCK(backtrace_lock);
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+void smp_send_all_cpu_backtrace(void)
+{
+ unsigned int this_cpu = smp_processor_id();
+ int i;
+
+ if (test_and_set_bit(0, &backtrace_flag))
+ /*
+ * If there is already a trigger_all_cpu_backtrace() in progress
+ * (backtrace_flag == 1), don't output double cpu dump infos.
+ */
+ return;
+
+ cpumask_copy(&backtrace_mask, cpu_online_mask);
+ cpu_clear(this_cpu, backtrace_mask);
+
+ pr_info("Backtrace for cpu %d (current):\n", this_cpu);
+ dump_stack();
+
+ pr_info("\nsending IPI to all other CPUs:\n");
+ smp_cross_call(&backtrace_mask, IPI_CPU_BACKTRACE);
+
+ /* Wait for up to 10 seconds for all other CPUs to do the backtrace */
+ for (i = 0; i < 10 * 1000; i++) {
+ if (cpumask_empty(&backtrace_mask))
+ break;
+ mdelay(1);
+ }
+
+ clear_bit(0, &backtrace_flag);
+ smp_mb__after_clear_bit();
+}
+
+/*
+ * ipi_cpu_backtrace - handle IPI from smp_send_all_cpu_backtrace()
+ */
+static void ipi_cpu_backtrace(unsigned int cpu, struct pt_regs *regs)
+{
+ if (cpu_isset(cpu, backtrace_mask)) {
+ raw_spin_lock(&backtrace_lock);
+ pr_warning("IPI backtrace for cpu %d\n", cpu);
+ show_regs(regs);
+ raw_spin_unlock(&backtrace_lock);
+ cpu_clear(cpu, backtrace_mask);
+ }
+}
+
/*
* Main handler for inter-processor interrupts
*/
@@ -638,6 +692,10 @@
irq_exit();
break;
+ case IPI_CPU_BACKTRACE:
+ ipi_cpu_backtrace(cpu, regs);
+ break;
+
default:
printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
cpu, ipinr);
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 9e51be9..8045a48 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -7,6 +7,7 @@
obj-$(CONFIG_MMU) += fault-armv.o flush.o idmap.o ioremap.o \
mmap.o pgd.o mmu.o
+obj-$(CONFIG_DEBUG_RODATA) += rodata.o
ifneq ($(CONFIG_MMU),y)
obj-y += nommu.o
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c465fac..90a130f 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -33,6 +33,9 @@
static DEFINE_RAW_SPINLOCK(l2x0_lock);
static u32 l2x0_way_mask; /* Bitmask of active ways */
static u32 l2x0_size;
+static u32 l2x0_cache_id;
+static unsigned int l2x0_sets;
+static unsigned int l2x0_ways;
static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
/* Aurora don't have the cache ID register available, so we have to
@@ -49,6 +52,13 @@
static bool of_init = false;
+static inline bool is_pl310_rev(int rev)
+{
+ return (l2x0_cache_id &
+ (L2X0_CACHE_ID_PART_MASK | L2X0_CACHE_ID_REV_MASK)) ==
+ (L2X0_CACHE_ID_PART_L310 | rev);
+}
+
static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
{
/* wait for cache operation by line or way to complete */
@@ -137,6 +147,23 @@
raw_spin_unlock_irqrestore(&l2x0_lock, flags);
}
+#ifdef CONFIG_PL310_ERRATA_727915
+static void l2x0_for_each_set_way(void __iomem *reg)
+{
+ int set;
+ int way;
+ unsigned long flags;
+
+ for (way = 0; way < l2x0_ways; way++) {
+ raw_spin_lock_irqsave(&l2x0_lock, flags);
+ for (set = 0; set < l2x0_sets; set++)
+ writel_relaxed((way << 28) | (set << 5), reg);
+ cache_sync();
+ raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+ }
+}
+#endif
+
static void __l2x0_flush_all(void)
{
debug_writel(0x03);
@@ -150,6 +177,13 @@
{
unsigned long flags;
+#ifdef CONFIG_PL310_ERRATA_727915
+ if (is_pl310_rev(REV_PL310_R2P0)) {
+ l2x0_for_each_set_way(l2x0_base + L2X0_CLEAN_INV_LINE_IDX);
+ return;
+ }
+#endif
+
/* clean all ways */
raw_spin_lock_irqsave(&l2x0_lock, flags);
__l2x0_flush_all();
@@ -160,11 +194,20 @@
{
unsigned long flags;
+#ifdef CONFIG_PL310_ERRATA_727915
+ if (is_pl310_rev(REV_PL310_R2P0)) {
+ l2x0_for_each_set_way(l2x0_base + L2X0_CLEAN_LINE_IDX);
+ return;
+ }
+#endif
+
/* clean all ways */
raw_spin_lock_irqsave(&l2x0_lock, flags);
+ debug_writel(0x03);
writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY);
cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask);
cache_sync();
+ debug_writel(0x00);
raw_spin_unlock_irqrestore(&l2x0_lock, flags);
}
@@ -323,65 +366,64 @@
void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
{
u32 aux;
- u32 cache_id;
u32 way_size = 0;
- int ways;
int way_size_shift = L2X0_WAY_SIZE_SHIFT;
const char *type;
l2x0_base = base;
if (cache_id_part_number_from_dt)
- cache_id = cache_id_part_number_from_dt;
+ l2x0_cache_id = cache_id_part_number_from_dt;
else
- cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
+ l2x0_cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
aux &= aux_mask;
aux |= aux_val;
/* Determine the number of ways */
- switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
+ switch (l2x0_cache_id & L2X0_CACHE_ID_PART_MASK) {
case L2X0_CACHE_ID_PART_L310:
if (aux & (1 << 16))
- ways = 16;
+ l2x0_ways = 16;
else
- ways = 8;
+ l2x0_ways = 8;
type = "L310";
#ifdef CONFIG_PL310_ERRATA_753970
/* Unmapped register. */
sync_reg_offset = L2X0_DUMMY_REG;
#endif
- if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0)
+ if ((l2x0_cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0)
outer_cache.set_debug = pl310_set_debug;
break;
case L2X0_CACHE_ID_PART_L210:
- ways = (aux >> 13) & 0xf;
+ l2x0_ways = (aux >> 13) & 0xf;
type = "L210";
break;
case AURORA_CACHE_ID:
sync_reg_offset = AURORA_SYNC_REG;
- ways = (aux >> 13) & 0xf;
- ways = 2 << ((ways + 1) >> 2);
+ l2x0_ways = (aux >> 13) & 0xf;
+ l2x0_ways = 2 << ((l2x0_ways + 1) >> 2);
way_size_shift = AURORA_WAY_SIZE_SHIFT;
type = "Aurora";
break;
default:
/* Assume unknown chips have 8 ways */
- ways = 8;
+ l2x0_ways = 8;
type = "L2x0 series";
break;
}
- l2x0_way_mask = (1 << ways) - 1;
+ l2x0_way_mask = (1 << l2x0_ways) - 1;
/*
* L2 cache Size = Way size * Number of ways
*/
way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
- way_size = 1 << (way_size + way_size_shift);
+ way_size = SZ_1K << (way_size + way_size_shift);
- l2x0_size = ways * way_size * SZ_1K;
+ l2x0_size = l2x0_ways * way_size;
+ l2x0_sets = way_size / CACHE_LINE_SIZE;
/*
* Check if l2x0 controller is already enabled.
@@ -390,7 +432,7 @@
*/
if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
/* Make sure that I&D is not locked down when starting */
- l2x0_unlock(cache_id);
+ l2x0_unlock(l2x0_cache_id);
/* l2x0 controller is disabled */
writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
@@ -419,7 +461,7 @@
printk(KERN_INFO "%s cache controller enabled\n", type);
printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
- ways, cache_id, aux, l2x0_size);
+ l2x0_ways, l2x0_cache_id, aux, l2x0_size);
}
#ifdef CONFIG_OF
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index d8fd4d4..7a3d3d8 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -270,6 +270,11 @@
* - end - virtual end address of region
*/
ENTRY(v6_dma_flush_range)
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+ sub r2, r1, r0
+ cmp r2, #CONFIG_CACHE_FLUSH_RANGE_LIMIT
+ bhi v6_dma_flush_dcache_all
+#endif
#ifdef CONFIG_DMA_CACHE_RWFO
ldrb r2, [r0] @ read for ownership
strb r2, [r0] @ write for ownership
@@ -292,6 +297,18 @@
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mov pc, lr
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+v6_dma_flush_dcache_all:
+ mov r0, #0
+#ifdef HARVARD_CACHE
+ mcr p15, 0, r0, c7, c14, 0 @ D cache clean+invalidate
+#else
+ mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate
+#endif
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mov pc, lr
+#endif
+
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 160da6d..2abb8bb 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -274,10 +274,10 @@
local_irq_enable();
/*
- * If we're in an interrupt or have no user
+ * If we're in an interrupt, or have no irqs, or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || irqs_disabled() || !mm)
goto no_context;
if (user_mode(regs))
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 5ef506c..0a23581 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -173,10 +173,9 @@
{
unsigned long random_factor = 0UL;
- /* 8 bits of randomness in 20 address space bits */
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE))
- random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT;
+ random_factor = (get_random_long() & ((1UL << mmap_rnd_bits) - 1)) << PAGE_SHIFT;
if (mmap_is_legacy()) {
mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4c7d5cd..a4e5cd5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -605,11 +605,25 @@
return early_alloc_aligned(sz, sz);
}
-static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
+static pte_t * __init early_pte_alloc(pmd_t *pmd)
+{
+ if (pmd_none(*pmd) || pmd_bad(*pmd))
+ return early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
+ return pmd_page_vaddr(*pmd);
+}
+
+static void __init early_pte_install(pmd_t *pmd, pte_t *pte, unsigned long prot)
+{
+ __pmd_populate(pmd, __pa(pte), prot);
+ BUG_ON(pmd_bad(*pmd));
+}
+
+static pte_t * __init early_pte_alloc_and_install(pmd_t *pmd,
+ unsigned long addr, unsigned long prot)
{
if (pmd_none(*pmd)) {
- pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
- __pmd_populate(pmd, __pa(pte), prot);
+ pte_t *pte = early_pte_alloc(pmd);
+ early_pte_install(pmd, pte, prot);
}
BUG_ON(pmd_bad(*pmd));
return pte_offset_kernel(pmd, addr);
@@ -619,11 +633,17 @@
unsigned long end, unsigned long pfn,
const struct mem_type *type)
{
- pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
+ pte_t *start_pte = early_pte_alloc(pmd);
+ pte_t *pte = start_pte + pte_index(addr);
+
+ /* If replacing a section mapping, the whole section must be replaced */
+ BUG_ON(!pmd_none(*pmd) && pmd_bad(*pmd) && ((addr | end) & ~PMD_MASK));
+
do {
set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), 0);
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
+ early_pte_install(pmd, start_pte, type->prot_l1);
}
static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
@@ -655,7 +675,8 @@
static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
unsigned long end, phys_addr_t phys,
- const struct mem_type *type)
+ const struct mem_type *type,
+ bool force_pages)
{
pmd_t *pmd = pmd_offset(pud, addr);
unsigned long next;
@@ -672,7 +693,8 @@
* aligned to a section boundary.
*/
if (type->prot_sect &&
- ((addr | next | phys) & ~SECTION_MASK) == 0) {
+ ((addr | next | phys) & ~SECTION_MASK) == 0 &&
+ !force_pages) {
__map_init_section(pmd, addr, next, phys, type);
} else {
alloc_init_pte(pmd, addr, next,
@@ -686,14 +708,15 @@
static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
unsigned long end, phys_addr_t phys,
- const struct mem_type *type)
+ const struct mem_type *type,
+ bool force_pages)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
do {
next = pud_addr_end(addr, end);
- alloc_init_pmd(pud, addr, next, phys, type);
+ alloc_init_pmd(pud, addr, next, phys, type, force_pages);
phys += next - addr;
} while (pud++, addr = next, addr != end);
}
@@ -767,7 +790,7 @@
* offsets, and we take full advantage of sections and
* supersections.
*/
-static void __init create_mapping(struct map_desc *md)
+static void __init create_mapping(struct map_desc *md, bool force_pages)
{
unsigned long addr, length, end;
phys_addr_t phys;
@@ -817,7 +840,7 @@
do {
unsigned long next = pgd_addr_end(addr, end);
- alloc_init_pud(pgd, addr, next, phys, type);
+ alloc_init_pud(pgd, addr, next, phys, type, force_pages);
phys += next - addr;
addr = next;
@@ -839,7 +862,7 @@
svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm));
for (md = io_desc; nr; md++, nr--) {
- create_mapping(md);
+ create_mapping(md, false);
vm = &svm->vm;
vm->addr = (void *)(md->virtual & PAGE_MASK);
@@ -960,7 +983,7 @@
map.virtual &= PAGE_MASK;
map.length = PAGE_SIZE;
map.type = MT_DEVICE;
- create_mapping(&map);
+ create_mapping(&map, false);
}
#endif
@@ -1005,6 +1028,28 @@
struct membank *bank = &meminfo.bank[j];
*bank = meminfo.bank[i];
+#ifdef CONFIG_SPARSEMEM
+ if (pfn_to_section_nr(bank_pfn_start(bank)) !=
+ pfn_to_section_nr(bank_pfn_end(bank) - 1)) {
+ phys_addr_t sz;
+ unsigned long start_pfn = bank_pfn_start(bank);
+ unsigned long end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
+ sz = ((phys_addr_t)(end_pfn - start_pfn) << PAGE_SHIFT);
+
+ if (meminfo.nr_banks >= NR_BANKS) {
+ pr_crit("NR_BANKS too low, ignoring %lld bytes of memory\n",
+ (unsigned long long)(bank->size - sz));
+ } else {
+ memmove(bank + 1, bank,
+ (meminfo.nr_banks - i) * sizeof(*bank));
+ meminfo.nr_banks++;
+ bank[1].size -= sz;
+ bank[1].start = __pfn_to_phys(end_pfn);
+ }
+ bank->size = sz;
+ }
+#endif
+
if (bank->start > ULONG_MAX)
highmem = 1;
@@ -1202,7 +1247,7 @@
map.virtual = MODULES_VADDR;
map.length = ((unsigned long)_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK;
map.type = MT_ROM;
- create_mapping(&map);
+ create_mapping(&map, false);
#endif
/*
@@ -1213,14 +1258,14 @@
map.virtual = FLUSH_BASE;
map.length = SZ_1M;
map.type = MT_CACHECLEAN;
- create_mapping(&map);
+ create_mapping(&map, false);
#endif
#ifdef FLUSH_BASE_MINICACHE
map.pfn = __phys_to_pfn(FLUSH_BASE_PHYS + SZ_1M);
map.virtual = FLUSH_BASE_MINICACHE;
map.length = SZ_1M;
map.type = MT_MINICLEAN;
- create_mapping(&map);
+ create_mapping(&map, false);
#endif
/*
@@ -1236,13 +1281,13 @@
#else
map.type = MT_LOW_VECTORS;
#endif
- create_mapping(&map);
+ create_mapping(&map, false);
if (!vectors_high()) {
map.virtual = 0;
map.length = PAGE_SIZE * 2;
map.type = MT_LOW_VECTORS;
- create_mapping(&map);
+ create_mapping(&map, false);
}
/* Now create a kernel read-only mapping */
@@ -1250,7 +1295,7 @@
map.virtual = 0xffff0000 + PAGE_SIZE;
map.length = PAGE_SIZE;
map.type = MT_LOW_VECTORS;
- create_mapping(&map);
+ create_mapping(&map, false);
/*
* Ask the machine support to map in the statically mapped devices.
@@ -1275,20 +1320,23 @@
static void __init kmap_init(void)
{
#ifdef CONFIG_HIGHMEM
- pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE),
+ pkmap_page_table = early_pte_alloc_and_install(pmd_off_k(PKMAP_BASE),
PKMAP_BASE, _PAGE_KERNEL_TABLE);
#endif
}
+
static void __init map_lowmem(void)
{
struct memblock_region *reg;
+ phys_addr_t start;
+ phys_addr_t end;
+ struct map_desc map;
/* Map all the lowmem memory banks. */
for_each_memblock(memory, reg) {
- phys_addr_t start = reg->base;
- phys_addr_t end = start + reg->size;
- struct map_desc map;
+ start = reg->base;
+ end = start + reg->size;
if (end > arm_lowmem_limit)
end = arm_lowmem_limit;
@@ -1300,8 +1348,20 @@
map.length = end - start;
map.type = MT_MEMORY;
- create_mapping(&map);
+ create_mapping(&map, false);
}
+
+#ifdef CONFIG_DEBUG_RODATA
+ start = __pa(_stext) & PMD_MASK;
+ end = ALIGN(__pa(__end_rodata), PMD_SIZE);
+
+ map.pfn = __phys_to_pfn(start);
+ map.virtual = __phys_to_virt(start);
+ map.length = end - start;
+ map.type = MT_MEMORY;
+
+ create_mapping(&map, true);
+#endif
}
/*
diff --git a/arch/arm/mm/rodata.c b/arch/arm/mm/rodata.c
new file mode 100644
index 0000000..9a8eb84
--- /dev/null
+++ b/arch/arm/mm/rodata.c
@@ -0,0 +1,159 @@
+/*
+ * linux/arch/arm/mm/rodata.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * Based on x86 implementation in arch/x86/mm/init_32.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+
+#include <asm/cache.h>
+#include <asm/pgtable.h>
+#include <asm/rodata.h>
+#include <asm/sections.h>
+#include <asm/tlbflush.h>
+
+#include "mm.h"
+
+static int kernel_set_to_readonly __read_mostly;
+
+#ifdef CONFIG_DEBUG_RODATA_TEST
+static const int rodata_test_data = 0xC3;
+
+static noinline void rodata_test(void)
+{
+ int result;
+
+ pr_info("%s: attempting to write to read-only section:\n", __func__);
+
+ if (*(volatile int *)&rodata_test_data != 0xC3) {
+ pr_err("read only data changed before test\n");
+ return;
+ }
+
+ /*
+ * Attempt to to write to rodata_test_data, trapping the expected
+ * data abort. If the trap executed, result will be 1. If it didn't,
+ * result will be 0xFF.
+ */
+ asm volatile(
+ "0: str %[zero], [%[rodata_test_data]]\n"
+ " mov %[result], #0xFF\n"
+ " b 2f\n"
+ "1: mov %[result], #1\n"
+ "2:\n"
+
+ /* Exception fixup - if store at label 0 faults, jumps to 1 */
+ ".pushsection __ex_table, \"a\"\n"
+ " .long 0b, 1b\n"
+ ".popsection\n"
+
+ : [result] "=r" (result)
+ : [rodata_test_data] "r" (&rodata_test_data), [zero] "r" (0)
+ : "memory"
+ );
+
+ if (result == 1)
+ pr_info("write to read-only section trapped, success\n");
+ else
+ pr_err("write to read-only section NOT trapped, test failed\n");
+
+ if (*(volatile int *)&rodata_test_data != 0xC3)
+ pr_err("read only data changed during write\n");
+}
+#else
+static inline void rodata_test(void) { }
+#endif
+
+static int set_page_attributes(unsigned long virt, int numpages,
+ pte_t (*f)(pte_t))
+{
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long start = virt;
+ unsigned long end = virt + (numpages << PAGE_SHIFT);
+ unsigned long pmd_end;
+
+ while (virt < end) {
+ pmd = pmd_off_k(virt);
+ pmd_end = min(ALIGN(virt + 1, PMD_SIZE), end);
+
+ if ((pmd_val(*pmd) & PMD_TYPE_MASK) != PMD_TYPE_TABLE) {
+ pr_err("%s: pmd %p=%08lx for %08lx not page table\n",
+ __func__, pmd, pmd_val(*pmd), virt);
+ virt = pmd_end;
+ continue;
+ }
+
+ while (virt < pmd_end) {
+ pte = pte_offset_kernel(pmd, virt);
+ set_pte_ext(pte, f(*pte), 0);
+ virt += PAGE_SIZE;
+ }
+ }
+
+ flush_tlb_kernel_range(start, end);
+
+ return 0;
+}
+
+int set_memory_ro(unsigned long virt, int numpages)
+{
+ return set_page_attributes(virt, numpages, pte_wrprotect);
+}
+EXPORT_SYMBOL(set_memory_ro);
+
+int set_memory_rw(unsigned long virt, int numpages)
+{
+ return set_page_attributes(virt, numpages, pte_mkwrite);
+}
+EXPORT_SYMBOL(set_memory_rw);
+
+void set_kernel_text_rw(void)
+{
+ unsigned long start = PAGE_ALIGN((unsigned long)_text);
+ unsigned long size = PAGE_ALIGN((unsigned long)__end_rodata) - start;
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_debug("Set kernel text: %lx - %lx to read-write\n",
+ start, start + size);
+
+ set_memory_rw(start, size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+ unsigned long start = PAGE_ALIGN((unsigned long)_text);
+ unsigned long size = PAGE_ALIGN((unsigned long)__end_rodata) - start;
+
+ if (!kernel_set_to_readonly)
+ return;
+
+ pr_info_once("Write protecting the kernel text section %lx - %lx\n",
+ start, start + size);
+
+ pr_debug("Set kernel text: %lx - %lx to read only\n",
+ start, start + size);
+
+ set_memory_ro(start, size >> PAGE_SHIFT);
+}
+
+void mark_rodata_ro(void)
+{
+ kernel_set_to_readonly = 1;
+
+ set_kernel_text_ro();
+
+ rodata_test();
+}
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 5dfbb0b..452fb3a 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/user.h>
+#include <linux/export.h>
#include <asm/cp15.h>
#include <asm/cputype.h>
@@ -648,6 +649,52 @@
return NOTIFY_OK;
}
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+ struct thread_info *thread = current_thread_info();
+ unsigned int cpu;
+ u32 fpexc;
+
+ /*
+ * Kernel mode NEON is only allowed outside of interrupt context
+ * with preemption disabled. This will make sure that the kernel
+ * mode NEON register contents never need to be preserved.
+ */
+ BUG_ON(in_interrupt());
+ cpu = get_cpu();
+
+ fpexc = fmrx(FPEXC) | FPEXC_EN;
+ fmxr(FPEXC, fpexc);
+
+ /*
+ * Save the userland NEON/VFP state. Under UP,
+ * the owner could be a task other than 'current'
+ */
+ if (vfp_state_in_hw(cpu, thread))
+ vfp_save_state(&thread->vfpstate, fpexc);
+#ifndef CONFIG_SMP
+ else if (vfp_current_hw_state[cpu] != NULL)
+ vfp_save_state(vfp_current_hw_state[cpu], fpexc);
+#endif
+ vfp_current_hw_state[cpu] = NULL;
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+ /* Disable the NEON/VFP unit. */
+ fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+ put_cpu();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
/*
* VFP support code initialisation.
*/
@@ -731,4 +778,4 @@
return 0;
}
-late_initcall(vfp_init);
+core_initcall(vfp_init);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 661ccf8..883a903 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -8,15 +8,22 @@
select ARM_AMBA
select ARM_ARCH_TIMER
select ARM_GIC
+ select AUDIT_ARCH_COMPAT_GENERIC
select CLONE_BACKWARDS
select COMMON_CLK
select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+ select GENERIC_CPU_AUTOPROBE
select GENERIC_IOMAP
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL
select HARDIRQS_SW_RESEND
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_MMAP_RND_BITS
+ select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+ select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
@@ -53,6 +60,27 @@
config NO_IOPORT
def_bool y
+config ARCH_MMAP_RND_BITS_MIN
+ default 14 if ARM64_64K_PAGES
+ default 18
+
+# max bits determined by the following formula:
+# VA_BITS - PAGE_SHIFT - 3
+# VA_BITS is always 39
+config ARCH_MMAP_RND_BITS_MAX
+ default 20 if ARM64_64K_PAGES
+ default 24
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+ default 11
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+ default 16
+
+config ILLEGAL_POINTER_VALUE
+ hex
+ default 0xdead000000000000
+
config STACKTRACE_SUPPORT
def_bool y
@@ -155,6 +183,31 @@
depends on SMP
default "4"
+config SWP_EMULATE
+ bool "Emulate SWP/SWPB instructions"
+ help
+ ARMv6 architecture deprecates use of the SWP/SWPB instructions. ARMv8
+ oblosetes the use of SWP/SWPB instructions. ARMv7 multiprocessing
+ extensions introduce the ability to disable these instructions,
+ triggering an undefined instruction exception when executed. Say Y
+ here to enable software emulation of these instructions for userspace
+ (not kernel) using LDREX/STREX. Also creates /proc/cpu/swp_emulation
+ for statistics.
+
+ In some older versions of glibc [<=2.8] SWP is used during futex
+ trylock() operations with the assumption that the code will not
+ be preempted. This invalid assumption may be more likely to fail
+ with SWP emulation enabled, leading to deadlock of the user
+ application.
+
+ NOTE: when accessing uncached shared regions, LDREX/STREX rely
+ on an external transaction monitoring block called a global
+ monitor to maintain update atomicity. If your system does not
+ implement a global monitor, this option can cause programs that
+ perform SWP operations to uncached memory to deadlock.
+
+ If unsure, say Y.
+
source kernel/Kconfig.preempt
config HZ
@@ -185,8 +238,33 @@
Enable hardware performance counter support for perf events. If
disabled, perf events will use software events only.
+config ARMV7_COMPAT
+ bool "Kernel support for ARMv7 applications"
+ depends on COMPAT
+ select SWP_EMULATE
+ help
+ This option enables features that allow that ran on an ARMv7 or older
+ processor to continue functioning.
+
+ If you want to execute ARMv7 applications, say Y
+
+
source "mm/Kconfig"
+config SECCOMP
+ bool "Enable seccomp to safely compute untrusted bytecode"
+ ---help---
+ This kernel feature is useful for number crunching applications
+ that may need to compute untrusted bytecode during their
+ execution. By using pipes or other transports made available to
+ the process as file descriptors supporting the read/write
+ syscalls, it's possible to isolate those applications in
+ their own address space using seccomp. Once seccomp is
+ enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+ and the task is only allowed to execute a few safe syscalls
+ defined by each seccomp mode.
+
+
endmenu
menu "Boot options"
@@ -199,6 +277,23 @@
entering them here. As a minimum, you should specify the the
root device (e.g. root=/dev/nfs).
+choice
+ prompt "Kernel command line type" if CMDLINE != ""
+ default CMDLINE_FROM_BOOTLOADER
+
+config CMDLINE_FROM_BOOTLOADER
+ bool "Use bootloader kernel arguments if available"
+ help
+ Uses the command-line options passed by the boot loader. If
+ the boot loader doesn't provide any, the default kernel command
+ string provided in CMDLINE will be used.
+
+config CMDLINE_EXTEND
+ bool "Extend bootloader kernel arguments"
+ help
+ The command-line arguments provided by the boot loader will be
+ appended to the default kernel command string.
+
config CMDLINE_FORCE
bool "Always use the default kernel command string"
help
@@ -206,6 +301,22 @@
loader passes other arguments to the kernel.
This is useful if you cannot or don't want to change the
command-line options your boot loader passes to the kernel.
+endchoice
+
+config BUILD_ARM64_APPENDED_DTB_IMAGE
+ bool "Build a concatenated Image.gz/dtb by default"
+ depends on OF
+ help
+ Enabling this option will cause a concatenated Image.gz and list of
+ DTBs to be built by default (instead of a standalone Image.gz.)
+ The image will built in arch/arm64/boot/Image.gz-dtb
+
+config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES
+ string "Default dtb names"
+ depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+ help
+ Space separated list of names of dtbs to append when
+ building a concatenated Image.gz-dtb.
endmenu
@@ -245,5 +356,8 @@
source "security/Kconfig"
source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
source "lib/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index c95c5cb..2b27721 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -20,6 +20,7 @@
KBUILD_DEFCONFIG := defconfig
KBUILD_CFLAGS += -mgeneral-regs-only
+KBUILD_CFLAGS += -fno-pic
KBUILD_CPPFLAGS += -mlittle-endian
AS += -EL
LD += -EL
@@ -37,11 +38,17 @@
export TEXT_OFFSET GZFLAGS
core-y += arch/arm64/kernel/ arch/arm64/mm/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
libs-y := arch/arm64/lib/ $(libs-y)
libs-y += $(LIBGCC)
# Default target when executing plain make
+ifeq ($(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE := Image.gz-dtb
+else
KBUILD_IMAGE := Image.gz
+endif
+
KBUILD_DTBS := dtbs
all: $(KBUILD_IMAGE) $(KBUILD_DTBS)
@@ -60,6 +67,9 @@
dtbs: scripts
$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+Image.gz-dtb: vmlinux scripts dtbs
+ $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore
index 8dab0bb..eb35511 100644
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@@ -1,2 +1,3 @@
Image
Image.gz
+Image.gz-dtb
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 5a0e3ab..df51984 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -14,14 +14,27 @@
# Based on the ia64 boot/Makefile.
#
+include $(srctree)/arch/arm64/boot/dts/Makefile
+
targets := Image Image.gz
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+
$(obj)/Image: vmlinux FORCE
$(call if_changed,objcopy)
$(obj)/Image.gz: $(obj)/Image FORCE
$(call if_changed,gzip)
+$(obj)/Image.gz-dtb: $(obj)/Image.gz $(DTB_OBJS) FORCE
+ $(call if_changed,cat)
+
install: $(obj)/Image
$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
$(obj)/Image System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 68457e9..d58ea71 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,8 +1,15 @@
dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
targets += dtbs
-targets += $(dtb-y)
-dtbs: $(addprefix $(obj)/, $(dtb-y))
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+targets += $(DTB_LIST)
-clean-files := *.dtb
+dtbs: $(addprefix $(obj)/, $(DTB_LIST))
+
+clean-files := dts/*.dtb *.dtb
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 8d9696ad..8fd6e02 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -67,9 +67,16 @@
# CONFIG_USB_SUPPORT is not set
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+# CONFIG_EXT3_FS is not set
# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_USE_FOR_EXT23=y
+# CONFIG_EXT4_FS_POSIX_ACL is not set
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS_ENCRYPTION=y
+CONFIG_FS_ENCRYPTION=y
+# CONFIG_EXT4_DEBUG is not set
CONFIG_FUSE_FS=y
CONFIG_CUSE=y
CONFIG_VFAT_FS=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 0000000..a38b02c
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,52 @@
+
+menuconfig ARM64_CRYPTO
+ bool "ARM64 Accelerated Cryptographic Algorithms"
+ depends on ARM64
+ help
+ Say Y here to choose from a selection of cryptographic algorithms
+ implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+ tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_SHA2_ARM64_CE
+ tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_GHASH_ARM64_CE
+ tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64_CE
+ tristate "AES core cipher using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+
+config CRYPTO_AES_ARM64_CE_CCM
+ tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_AES_ARM64_CE
+ select CRYPTO_AEAD
+
+config CRYPTO_AES_ARM64_CE_BLK
+ tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_AES_ARM64_CE
+ select CRYPTO_ABLK_HELPER
+
+config CRYPTO_AES_ARM64_NEON_BLK
+ tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_AES
+ select CRYPTO_ABLK_HELPER
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 0000000..a3f935f
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,38 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-neon.o := -DINTERLEAVE=4
+
+CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+ $(call if_changed_rule,cc_o_c)
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 0000000..432e484
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,222 @@
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ /*
+ * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+ * u32 *macp, u8 const rk[], u32 rounds);
+ */
+ENTRY(ce_aes_ccm_auth_data)
+ ldr w8, [x3] /* leftover from prev round? */
+ ld1 {v0.2d}, [x0] /* load mac */
+ cbz w8, 1f
+ sub w8, w8, #16
+ eor v1.16b, v1.16b, v1.16b
+0: ldrb w7, [x1], #1 /* get 1 byte of input */
+ subs w2, w2, #1
+ add w8, w8, #1
+ ins v1.b[0], w7
+ ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */
+ beq 8f /* out of input? */
+ cbnz w8, 0b
+ eor v0.16b, v0.16b, v1.16b
+1: ld1 {v3.2d}, [x4] /* load first round key */
+ prfm pldl1strm, [x1]
+ cmp w5, #12 /* which key size? */
+ add x6, x4, #16
+ sub w7, w5, #2 /* modified # of rounds */
+ bmi 2f
+ bne 5f
+ mov v5.16b, v3.16b
+ b 4f
+2: mov v4.16b, v3.16b
+ ld1 {v5.2d}, [x6], #16 /* load 2nd round key */
+3: aese v0.16b, v4.16b
+ aesmc v0.16b, v0.16b
+4: ld1 {v3.2d}, [x6], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aesmc v0.16b, v0.16b
+5: ld1 {v4.2d}, [x6], #16 /* load next round key */
+ subs w7, w7, #3
+ aese v0.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ ld1 {v5.2d}, [x6], #16 /* load next round key */
+ bpl 3b
+ aese v0.16b, v4.16b
+ subs w2, w2, #16 /* last data? */
+ eor v0.16b, v0.16b, v5.16b /* final round */
+ bmi 6f
+ ld1 {v1.16b}, [x1], #16 /* load next input block */
+ eor v0.16b, v0.16b, v1.16b /* xor with mac */
+ bne 1b
+6: st1 {v0.2d}, [x0] /* store mac */
+ beq 10f
+ adds w2, w2, #16
+ beq 10f
+ mov w8, w2
+7: ldrb w7, [x1], #1
+ umov w6, v0.b[0]
+ eor w6, w6, w7
+ strb w6, [x0], #1
+ subs w2, w2, #1
+ beq 10f
+ ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */
+ b 7b
+8: mov w7, w8
+ add w8, w8, #16
+9: ext v1.16b, v1.16b, v1.16b, #1
+ adds w7, w7, #1
+ bne 9b
+ eor v0.16b, v0.16b, v1.16b
+ st1 {v0.2d}, [x0]
+10: str w8, [x3]
+ ret
+ENDPROC(ce_aes_ccm_auth_data)
+
+ /*
+ * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+ * u32 rounds);
+ */
+ENTRY(ce_aes_ccm_final)
+ ld1 {v3.2d}, [x2], #16 /* load first round key */
+ ld1 {v0.2d}, [x0] /* load mac */
+ cmp w3, #12 /* which key size? */
+ sub w3, w3, #2 /* modified # of rounds */
+ ld1 {v1.2d}, [x1] /* load 1st ctriv */
+ bmi 0f
+ bne 3f
+ mov v5.16b, v3.16b
+ b 2f
+0: mov v4.16b, v3.16b
+1: ld1 {v5.2d}, [x2], #16 /* load next round key */
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+2: ld1 {v3.2d}, [x2], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aese v1.16b, v5.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+3: ld1 {v4.2d}, [x2], #16 /* load next round key */
+ subs w3, w3, #3
+ aese v0.16b, v3.16b
+ aese v1.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+ bpl 1b
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ /* final round key cancels out */
+ eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */
+ st1 {v0.2d}, [x0] /* store result */
+ ret
+ENDPROC(ce_aes_ccm_final)
+
+ .macro aes_ccm_do_crypt,enc
+ ldr x8, [x6, #8] /* load lower ctr */
+ ld1 {v0.2d}, [x5] /* load mac */
+ rev x8, x8 /* keep swabbed ctr in reg */
+0: /* outer loop */
+ ld1 {v1.1d}, [x6] /* load upper ctr */
+ prfm pldl1strm, [x1]
+ add x8, x8, #1
+ rev x9, x8
+ cmp w4, #12 /* which key size? */
+ sub w7, w4, #2 /* get modified # of rounds */
+ ins v1.d[1], x9 /* no carry in lower ctr */
+ ld1 {v3.2d}, [x3] /* load first round key */
+ add x10, x3, #16
+ bmi 1f
+ bne 4f
+ mov v5.16b, v3.16b
+ b 3f
+1: mov v4.16b, v3.16b
+ ld1 {v5.2d}, [x10], #16 /* load 2nd round key */
+2: /* inner loop: 3 rounds, 2x interleaved */
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+3: ld1 {v3.2d}, [x10], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aese v1.16b, v5.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+4: ld1 {v4.2d}, [x10], #16 /* load next round key */
+ subs w7, w7, #3
+ aese v0.16b, v3.16b
+ aese v1.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+ ld1 {v5.2d}, [x10], #16 /* load next round key */
+ bpl 2b
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ subs w2, w2, #16
+ bmi 6f /* partial block? */
+ ld1 {v2.16b}, [x1], #16 /* load next input block */
+ .if \enc == 1
+ eor v2.16b, v2.16b, v5.16b /* final round enc+mac */
+ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */
+ .else
+ eor v2.16b, v2.16b, v1.16b /* xor with crypted ctr */
+ eor v1.16b, v2.16b, v5.16b /* final round enc */
+ .endif
+ eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
+ st1 {v1.16b}, [x0], #16 /* write output block */
+ bne 0b
+ rev x8, x8
+ st1 {v0.2d}, [x5] /* store mac */
+ str x8, [x6, #8] /* store lsb end of ctr (BE) */
+5: ret
+
+6: eor v0.16b, v0.16b, v5.16b /* final round mac */
+ eor v1.16b, v1.16b, v5.16b /* final round enc */
+ st1 {v0.2d}, [x5] /* store mac */
+ add w2, w2, #16 /* process partial tail block */
+7: ldrb w9, [x1], #1 /* get 1 byte of input */
+ umov w6, v1.b[0] /* get top crypted ctr byte */
+ umov w7, v0.b[0] /* get top mac byte */
+ .if \enc == 1
+ eor w7, w7, w9
+ eor w9, w9, w6
+ .else
+ eor w9, w9, w6
+ eor w7, w7, w9
+ .endif
+ strb w9, [x0], #1 /* store out byte */
+ strb w7, [x5], #1 /* store mac byte */
+ subs w2, w2, #1
+ beq 5b
+ ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */
+ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */
+ b 7b
+ .endm
+
+ /*
+ * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+ * u8 const rk[], u32 rounds, u8 mac[],
+ * u8 ctr[]);
+ * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+ * u8 const rk[], u32 rounds, u8 mac[],
+ * u8 ctr[]);
+ */
+ENTRY(ce_aes_ccm_encrypt)
+ aes_ccm_do_crypt 1
+ENDPROC(ce_aes_ccm_encrypt)
+
+ENTRY(ce_aes_ccm_decrypt)
+ aes_ccm_do_crypt 0
+ENDPROC(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 0000000..0ac73b8
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,299 @@
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+ u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+ u32 const rk[], u32 rounds, u8 mac[],
+ u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+ u32 const rk[], u32 rounds, u8 mac[],
+ u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+ u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+ int ret;
+
+ ret = ce_aes_expandkey(ctx, in_key, key_len);
+ if (!ret)
+ return 0;
+
+ tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ if ((authsize & 1) || authsize < 4)
+ return -EINVAL;
+ return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ __be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+ u32 l = req->iv[0] + 1;
+
+ /* verify that CCM dimension 'L' is set correctly in the IV */
+ if (l < 2 || l > 8)
+ return -EINVAL;
+
+ /* verify that msglen can in fact be represented in L bytes */
+ if (l < 4 && msglen >> (8 * l))
+ return -EOVERFLOW;
+
+ /*
+ * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+ * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+ */
+ n[0] = 0;
+ n[1] = cpu_to_be32(msglen);
+
+ memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+ /*
+ * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+ * - bits 0..2 : max # of bytes required to represent msglen, minus 1
+ * (already set by caller)
+ * - bits 3..5 : size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+ * - bit 6 : indicates presence of authenticate-only data
+ */
+ maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+ if (req->assoclen)
+ maciv[0] |= 0x40;
+
+ memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+ return 0;
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+ struct scatter_walk walk;
+ u32 len = req->assoclen;
+ u32 macp = 0;
+
+ /* prepend the AAD with a length tag */
+ if (len < 0xff00) {
+ ltag.l = cpu_to_be16(len);
+ ltag.len = 2;
+ } else {
+ ltag.l = cpu_to_be16(0xfffe);
+ put_unaligned_be32(len, <ag.h);
+ ltag.len = 6;
+ }
+
+ ce_aes_ccm_auth_data(mac, (u8 *)<ag, ltag.len, &macp, ctx->key_enc,
+ num_rounds(ctx));
+ scatterwalk_start(&walk, req->assoc);
+
+ do {
+ u32 n = scatterwalk_clamp(&walk, len);
+ u8 *p;
+
+ if (!n) {
+ scatterwalk_start(&walk, sg_next(walk.sg));
+ n = scatterwalk_clamp(&walk, len);
+ }
+ p = scatterwalk_map(&walk);
+ ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
+ num_rounds(ctx));
+ len -= n;
+
+ scatterwalk_unmap(p);
+ scatterwalk_advance(&walk, n);
+ scatterwalk_done(&walk, 0, len);
+ } while (len);
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ struct blkcipher_desc desc = { .info = req->iv };
+ struct blkcipher_walk walk;
+ u8 __aligned(8) mac[AES_BLOCK_SIZE];
+ u8 buf[AES_BLOCK_SIZE];
+ u32 len = req->cryptlen;
+ int err;
+
+ err = ccm_init_mac(req, mac, len);
+ if (err)
+ return err;
+
+ kernel_neon_begin_partial(6);
+
+ if (req->assoclen)
+ ccm_calculate_auth_mac(req, mac);
+
+ /* preserve the original iv for the final round */
+ memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+ blkcipher_walk_init(&walk, req->dst, req->src, len);
+ err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+ AES_BLOCK_SIZE);
+
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ if (walk.nbytes == len)
+ tail = 0;
+
+ ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
+
+ len -= walk.nbytes - tail;
+ err = blkcipher_walk_done(&desc, &walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+ kernel_neon_end();
+
+ if (err)
+ return err;
+
+ /* copy authtag to end of dst */
+ scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+ crypto_aead_authsize(aead), 1);
+
+ return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ unsigned int authsize = crypto_aead_authsize(aead);
+ struct blkcipher_desc desc = { .info = req->iv };
+ struct blkcipher_walk walk;
+ u8 __aligned(8) mac[AES_BLOCK_SIZE];
+ u8 buf[AES_BLOCK_SIZE];
+ u32 len = req->cryptlen - authsize;
+ int err;
+
+ err = ccm_init_mac(req, mac, len);
+ if (err)
+ return err;
+
+ kernel_neon_begin_partial(6);
+
+ if (req->assoclen)
+ ccm_calculate_auth_mac(req, mac);
+
+ /* preserve the original iv for the final round */
+ memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+ blkcipher_walk_init(&walk, req->dst, req->src, len);
+ err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+ AES_BLOCK_SIZE);
+
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ if (walk.nbytes == len)
+ tail = 0;
+
+ ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
+
+ len -= walk.nbytes - tail;
+ err = blkcipher_walk_done(&desc, &walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+ kernel_neon_end();
+
+ if (err)
+ return err;
+
+ /* compare calculated auth tag with the stored one */
+ scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+ authsize, 0);
+
+ if (memcmp(mac, buf, authsize))
+ return -EBADMSG;
+ return 0;
+}
+
+static struct crypto_alg ccm_aes_alg = {
+ .cra_name = "ccm(aes)",
+ .cra_driver_name = "ccm-aes-ce",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_AEAD,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_aead_type,
+ .cra_module = THIS_MODULE,
+ .cra_aead = {
+ .ivsize = AES_BLOCK_SIZE,
+ .maxauthsize = AES_BLOCK_SIZE,
+ .setkey = ccm_setkey,
+ .setauthsize = ccm_setauthsize,
+ .encrypt = ccm_encrypt,
+ .decrypt = ccm_decrypt,
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_AES))
+ return -ENODEV;
+ return crypto_register_alg(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 0000000..47acc16
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,265 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+ u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct aes_block *out = (struct aes_block *)dst;
+ struct aes_block const *in = (struct aes_block *)src;
+ void *dummy0;
+ int dummy1;
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]], #16 ;"
+ " cmp %w[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aese v0.16b, v2.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aese v0.16b, v3.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %w[rounds], %w[rounds], #3 ;"
+ " aese v0.16b, v1.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aese v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=Q"(*out),
+ [key] "=r"(dummy0),
+ [rounds] "=r"(dummy1)
+ : [in] "Q"(*in),
+ "1"(ctx->key_enc),
+ "2"(num_rounds(ctx) - 2)
+ : "cc");
+
+ kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct aes_block *out = (struct aes_block *)dst;
+ struct aes_block const *in = (struct aes_block *)src;
+ void *dummy0;
+ int dummy1;
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]], #16 ;"
+ " cmp %w[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aesd v0.16b, v2.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aesd v0.16b, v3.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %w[rounds], %w[rounds], #3 ;"
+ " aesd v0.16b, v1.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aesd v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=Q"(*out),
+ [key] "=r"(dummy0),
+ [rounds] "=r"(dummy1)
+ : [in] "Q"(*in),
+ "1"(ctx->key_dec),
+ "2"(num_rounds(ctx) - 2)
+ : "cc");
+
+ kernel_neon_end();
+}
+
+/*
+ * aes_sub() - use the aese instruction to perform the AES sbox substitution
+ * on each byte in 'input'
+ */
+static u32 aes_sub(u32 input)
+{
+ u32 ret;
+
+ __asm__("dup v1.4s, %w[in] ;"
+ "movi v0.16b, #0 ;"
+ "aese v0.16b, v1.16b ;"
+ "umov %w[out], v0.4s[0] ;"
+
+ : [out] "=r"(ret)
+ : [in] "r"(input)
+ : "v0","v1");
+
+ return ret;
+}
+
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ unsigned int key_len)
+{
+ /*
+ * The AES key schedule round constants
+ */
+ static u8 const rcon[] = {
+ 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
+ };
+
+ u32 kwords = key_len / sizeof(u32);
+ struct aes_block *key_enc, *key_dec;
+ int i, j;
+
+ if (key_len != AES_KEYSIZE_128 &&
+ key_len != AES_KEYSIZE_192 &&
+ key_len != AES_KEYSIZE_256)
+ return -EINVAL;
+
+ memcpy(ctx->key_enc, in_key, key_len);
+ ctx->key_length = key_len;
+
+ kernel_neon_begin_partial(2);
+ for (i = 0; i < sizeof(rcon); i++) {
+ u32 *rki = ctx->key_enc + (i * kwords);
+ u32 *rko = rki + kwords;
+
+ rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+ rko[1] = rko[0] ^ rki[1];
+ rko[2] = rko[1] ^ rki[2];
+ rko[3] = rko[2] ^ rki[3];
+
+ if (key_len == AES_KEYSIZE_192) {
+ if (i >= 7)
+ break;
+ rko[4] = rko[3] ^ rki[4];
+ rko[5] = rko[4] ^ rki[5];
+ } else if (key_len == AES_KEYSIZE_256) {
+ if (i >= 6)
+ break;
+ rko[4] = aes_sub(rko[3]) ^ rki[4];
+ rko[5] = rko[4] ^ rki[5];
+ rko[6] = rko[5] ^ rki[6];
+ rko[7] = rko[6] ^ rki[7];
+ }
+ }
+
+ /*
+ * Generate the decryption keys for the Equivalent Inverse Cipher.
+ * This involves reversing the order of the round keys, and applying
+ * the Inverse Mix Columns transformation on all but the first and
+ * the last one.
+ */
+ key_enc = (struct aes_block *)ctx->key_enc;
+ key_dec = (struct aes_block *)ctx->key_dec;
+ j = num_rounds(ctx);
+
+ key_dec[0] = key_enc[j];
+ for (i = 1, j--; j > 0; i++, j--)
+ __asm__("ld1 {v0.16b}, %[in] ;"
+ "aesimc v1.16b, v0.16b ;"
+ "st1 {v1.16b}, %[out] ;"
+
+ : [out] "=Q"(key_dec[i])
+ : [in] "Q"(key_enc[j])
+ : "v0","v1");
+ key_dec[i] = key_enc[0];
+
+ kernel_neon_end();
+ return 0;
+}
+EXPORT_SYMBOL(ce_aes_expandkey);
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int ret;
+
+ ret = ce_aes_expandkey(ctx, in_key, key_len);
+ if (!ret)
+ return 0;
+
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+EXPORT_SYMBOL(ce_aes_setkey);
+
+static struct crypto_alg aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-ce",
+ .cra_priority = 299,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_cipher = {
+ .cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = ce_aes_setkey,
+ .cia_encrypt = aes_cipher_encrypt,
+ .cia_decrypt = aes_cipher_decrypt
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce-setkey.h b/arch/arm64/crypto/aes-ce-setkey.h
new file mode 100644
index 0000000..f08a647
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-setkey.h
@@ -0,0 +1,5 @@
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len);
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ unsigned int key_len);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 0000000..685a18f
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,133 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ * Crypto Extensions
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func) ENTRY(ce_ ## func)
+#define AES_ENDPROC(func) ENDPROC(ce_ ## func)
+
+ .arch armv8-a+crypto
+
+ /* preload all round keys */
+ .macro load_round_keys, rounds, rk
+ cmp \rounds, #12
+ blo 2222f /* 128 bits */
+ beq 1111f /* 192 bits */
+ ld1 {v17.16b-v18.16b}, [\rk], #32
+1111: ld1 {v19.16b-v20.16b}, [\rk], #32
+2222: ld1 {v21.16b-v24.16b}, [\rk], #64
+ ld1 {v25.16b-v28.16b}, [\rk], #64
+ ld1 {v29.16b-v31.16b}, [\rk]
+ .endm
+
+ /* prepare for encryption with key in rk[] */
+ .macro enc_prepare, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ /* prepare for encryption (again) but with new key in rk[] */
+ .macro enc_switch_key, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ /* prepare for decryption with key in rk[] */
+ .macro dec_prepare, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ .macro do_enc_Nx, de, mc, k, i0, i1, i2, i3
+ aes\de \i0\().16b, \k\().16b
+ .ifnb \i1
+ aes\de \i1\().16b, \k\().16b
+ .ifnb \i3
+ aes\de \i2\().16b, \k\().16b
+ aes\de \i3\().16b, \k\().16b
+ .endif
+ .endif
+ aes\mc \i0\().16b, \i0\().16b
+ .ifnb \i1
+ aes\mc \i1\().16b, \i1\().16b
+ .ifnb \i3
+ aes\mc \i2\().16b, \i2\().16b
+ aes\mc \i3\().16b, \i3\().16b
+ .endif
+ .endif
+ .endm
+
+ /* up to 4 interleaved encryption rounds with the same round key */
+ .macro round_Nx, enc, k, i0, i1, i2, i3
+ .ifc \enc, e
+ do_enc_Nx e, mc, \k, \i0, \i1, \i2, \i3
+ .else
+ do_enc_Nx d, imc, \k, \i0, \i1, \i2, \i3
+ .endif
+ .endm
+
+ /* up to 4 interleaved final rounds */
+ .macro fin_round_Nx, de, k, k2, i0, i1, i2, i3
+ aes\de \i0\().16b, \k\().16b
+ .ifnb \i1
+ aes\de \i1\().16b, \k\().16b
+ .ifnb \i3
+ aes\de \i2\().16b, \k\().16b
+ aes\de \i3\().16b, \k\().16b
+ .endif
+ .endif
+ eor \i0\().16b, \i0\().16b, \k2\().16b
+ .ifnb \i1
+ eor \i1\().16b, \i1\().16b, \k2\().16b
+ .ifnb \i3
+ eor \i2\().16b, \i2\().16b, \k2\().16b
+ eor \i3\().16b, \i3\().16b, \k2\().16b
+ .endif
+ .endif
+ .endm
+
+ /* up to 4 interleaved blocks */
+ .macro do_block_Nx, enc, rounds, i0, i1, i2, i3
+ cmp \rounds, #12
+ blo 2222f /* 128 bits */
+ beq 1111f /* 192 bits */
+ round_Nx \enc, v17, \i0, \i1, \i2, \i3
+ round_Nx \enc, v18, \i0, \i1, \i2, \i3
+1111: round_Nx \enc, v19, \i0, \i1, \i2, \i3
+ round_Nx \enc, v20, \i0, \i1, \i2, \i3
+2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+ round_Nx \enc, \key, \i0, \i1, \i2, \i3
+ .endr
+ fin_round_Nx \enc, v30, v31, \i0, \i1, \i2, \i3
+ .endm
+
+ .macro encrypt_block, in, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \in
+ .endm
+
+ .macro encrypt_block2x, i0, i1, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \i0, \i1
+ .endm
+
+ .macro encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \i0, \i1, \i2, \i3
+ .endm
+
+ .macro decrypt_block, in, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \in
+ .endm
+
+ .macro decrypt_block2x, i0, i1, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \i0, \i1
+ .endm
+
+ .macro decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \i0, \i1, \i2, \i3
+ .endm
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 0000000..801aae3
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,452 @@
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+
+#include "aes-ce-setkey.h"
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE "ce"
+#define PRIO 300
+#define aes_setkey ce_aes_setkey
+#define aes_expandkey ce_aes_expandkey
+#define aes_ecb_encrypt ce_aes_ecb_encrypt
+#define aes_ecb_decrypt ce_aes_ecb_decrypt
+#define aes_cbc_encrypt ce_aes_cbc_encrypt
+#define aes_cbc_decrypt ce_aes_cbc_decrypt
+#define aes_ctr_encrypt ce_aes_ctr_encrypt
+#define aes_xts_encrypt ce_aes_xts_encrypt
+#define aes_xts_decrypt ce_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE "neon"
+#define PRIO 200
+#define aes_setkey crypto_aes_set_key
+#define aes_expandkey crypto_aes_expand_key
+#define aes_ecb_encrypt neon_aes_ecb_encrypt
+#define aes_ecb_decrypt neon_aes_ecb_decrypt
+#define aes_cbc_encrypt neon_aes_cbc_encrypt
+#define aes_cbc_decrypt neon_aes_cbc_decrypt
+#define aes_ctr_encrypt neon_aes_ctr_encrypt
+#define aes_xts_encrypt neon_aes_xts_encrypt
+#define aes_xts_decrypt neon_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+MODULE_ALIAS("ecb(aes)");
+MODULE_ALIAS("cbc(aes)");
+MODULE_ALIAS("ctr(aes)");
+MODULE_ALIAS("xts(aes)");
+#endif
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, int first);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, int first);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int first);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int first);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 ctr[], int first);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+ int rounds, int blocks, u8 const rk2[], u8 iv[],
+ int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+ int rounds, int blocks, u8 const rk2[], u8 iv[],
+ int first);
+
+struct crypto_aes_xts_ctx {
+ struct crypto_aes_ctx key1;
+ struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+ int ret;
+
+ ret = aes_expandkey(&ctx->key1, in_key, key_len / 2);
+ if (!ret)
+ ret = aes_expandkey(&ctx->key2, &in_key[key_len / 2],
+ key_len / 2);
+ if (!ret)
+ return 0;
+
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_dec, rounds, blocks, first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+ first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_dec, rounds, blocks, walk.iv,
+ first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+ first = 1;
+ kernel_neon_begin();
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+ first);
+ first = 0;
+ nbytes -= blocks * AES_BLOCK_SIZE;
+ if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+ break;
+ err = blkcipher_walk_done(desc, &walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (nbytes) {
+ u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+ /*
+ * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+ * to tell aes_ctr_encrypt() to only read half a block.
+ */
+ blocks = (nbytes <= 8) ? -1 : 1;
+
+ aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+ blocks, walk.iv, first);
+ memcpy(tdst, tail, nbytes);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key1.key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key1.key_enc, rounds, blocks,
+ (u8 *)ctx->key2.key_enc, walk.iv, first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key1.key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key1.key_dec, rounds, blocks,
+ (u8 *)ctx->key2.key_enc, walk.iv, first);
+ err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+ .cra_name = "__ecb-aes-" MODE,
+ .cra_driver_name = "__driver-ecb-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aes_setkey,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+ },
+}, {
+ .cra_name = "__cbc-aes-" MODE,
+ .cra_driver_name = "__driver-cbc-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aes_setkey,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ },
+}, {
+ .cra_name = "__ctr-aes-" MODE,
+ .cra_driver_name = "__driver-ctr-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aes_setkey,
+ .encrypt = ctr_encrypt,
+ .decrypt = ctr_encrypt,
+ },
+}, {
+ .cra_name = "__xts-aes-" MODE,
+ .cra_driver_name = "__driver-xts-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = xts_set_key,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ },
+}, {
+ .cra_name = "ecb(aes)",
+ .cra_driver_name = "ecb-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "cbc(aes)",
+ .cra_driver_name = "cbc-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "ctr(aes)",
+ .cra_driver_name = "ctr-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "xts(aes)",
+ .cra_driver_name = "xts-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+} };
+
+static int __init aes_init(void)
+{
+ return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+ crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 0000000..f6e372c
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,532 @@
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+ .text
+ .align 4
+
+/*
+ * There are several ways to instantiate this code:
+ * - no interleave, all inline
+ * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
+ * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
+ * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
+ * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
+ *
+ * Macros imported by this code:
+ * - enc_prepare - setup NEON registers for encryption
+ * - dec_prepare - setup NEON registers for decryption
+ * - enc_switch_key - change to new key after having prepared for encryption
+ * - encrypt_block - encrypt a single block
+ * - decrypt block - decrypt a single block
+ * - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ * - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ */
+
+#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
+#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp
+#define FRAME_POP ldp x29, x30, [sp],#16
+
+#if INTERLEAVE == 2
+
+aes_encrypt_block2x:
+ encrypt_block2x v0, v1, w3, x2, x6, w7
+ ret
+ENDPROC(aes_encrypt_block2x)
+
+aes_decrypt_block2x:
+ decrypt_block2x v0, v1, w3, x2, x6, w7
+ ret
+ENDPROC(aes_decrypt_block2x)
+
+#elif INTERLEAVE == 4
+
+aes_encrypt_block4x:
+ encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ ret
+ENDPROC(aes_encrypt_block4x)
+
+aes_decrypt_block4x:
+ decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ ret
+ENDPROC(aes_decrypt_block4x)
+
+#else
+#error INTERLEAVE should equal 2 or 4
+#endif
+
+ .macro do_encrypt_block2x
+ bl aes_encrypt_block2x
+ .endm
+
+ .macro do_decrypt_block2x
+ bl aes_decrypt_block2x
+ .endm
+
+ .macro do_encrypt_block4x
+ bl aes_encrypt_block4x
+ .endm
+
+ .macro do_decrypt_block4x
+ bl aes_decrypt_block4x
+ .endm
+
+#else
+#define FRAME_PUSH
+#define FRAME_POP
+
+ .macro do_encrypt_block2x
+ encrypt_block2x v0, v1, w3, x2, x6, w7
+ .endm
+
+ .macro do_decrypt_block2x
+ decrypt_block2x v0, v1, w3, x2, x6, w7
+ .endm
+
+ .macro do_encrypt_block4x
+ encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ .endm
+
+ .macro do_decrypt_block4x
+ decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ .endm
+
+#endif
+
+ /*
+ * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, int first)
+ * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, int first)
+ */
+
+AES_ENTRY(aes_ecb_encrypt)
+ FRAME_PUSH
+ cbz w5, .LecbencloopNx
+
+ enc_prepare w3, x2, x5
+
+.LecbencloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lecbenc1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
+ do_encrypt_block2x
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ do_encrypt_block4x
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LecbencloopNx
+.Lecbenc1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lecbencout
+#endif
+.Lecbencloop:
+ ld1 {v0.16b}, [x1], #16 /* get next pt block */
+ encrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lecbencloop
+.Lecbencout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ecb_encrypt)
+
+
+AES_ENTRY(aes_ecb_decrypt)
+ FRAME_PUSH
+ cbz w5, .LecbdecloopNx
+
+ dec_prepare w3, x2, x5
+
+.LecbdecloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lecbdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ do_decrypt_block2x
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ do_decrypt_block4x
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LecbdecloopNx
+.Lecbdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lecbdecout
+#endif
+.Lecbdecloop:
+ ld1 {v0.16b}, [x1], #16 /* get next ct block */
+ decrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lecbdecloop
+.Lecbdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ecb_decrypt)
+
+
+ /*
+ * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int first)
+ * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int first)
+ */
+
+AES_ENTRY(aes_cbc_encrypt)
+ cbz w6, .Lcbcencloop
+
+ ld1 {v0.16b}, [x5] /* get iv */
+ enc_prepare w3, x2, x5
+
+.Lcbcencloop:
+ ld1 {v1.16b}, [x1], #16 /* get next pt block */
+ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */
+ encrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lcbcencloop
+ ret
+AES_ENDPROC(aes_cbc_encrypt)
+
+
+AES_ENTRY(aes_cbc_decrypt)
+ FRAME_PUSH
+ cbz w6, .LcbcdecloopNx
+
+ ld1 {v7.16b}, [x5] /* get iv */
+ dec_prepare w3, x2, x5
+
+.LcbcdecloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lcbcdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ mov v2.16b, v0.16b
+ mov v3.16b, v1.16b
+ do_decrypt_block2x
+ eor v0.16b, v0.16b, v7.16b
+ eor v1.16b, v1.16b, v2.16b
+ mov v7.16b, v3.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ mov v4.16b, v0.16b
+ mov v5.16b, v1.16b
+ mov v6.16b, v2.16b
+ do_decrypt_block4x
+ sub x1, x1, #16
+ eor v0.16b, v0.16b, v7.16b
+ eor v1.16b, v1.16b, v4.16b
+ ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */
+ eor v2.16b, v2.16b, v5.16b
+ eor v3.16b, v3.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LcbcdecloopNx
+.Lcbcdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lcbcdecout
+#endif
+.Lcbcdecloop:
+ ld1 {v1.16b}, [x1], #16 /* get next ct block */
+ mov v0.16b, v1.16b /* ...and copy to v0 */
+ decrypt_block v0, w3, x2, x5, w6
+ eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
+ mov v7.16b, v1.16b /* ct is next iv */
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lcbcdecloop
+.Lcbcdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_cbc_decrypt)
+
+
+ /*
+ * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 ctr[], int first)
+ */
+
+AES_ENTRY(aes_ctr_encrypt)
+ FRAME_PUSH
+ cbnz w6, .Lctrfirst /* 1st time around? */
+ umov x5, v4.d[1] /* keep swabbed ctr in reg */
+ rev x5, x5
+#if INTERLEAVE >= 2
+ cmn w5, w4 /* 32 bit overflow? */
+ bcs .Lctrinc
+ add x5, x5, #1 /* increment BE ctr */
+ b .LctrincNx
+#else
+ b .Lctrinc
+#endif
+.Lctrfirst:
+ enc_prepare w3, x2, x6
+ ld1 {v4.16b}, [x5]
+ umov x5, v4.d[1] /* keep swabbed ctr in reg */
+ rev x5, x5
+#if INTERLEAVE >= 2
+ cmn w5, w4 /* 32 bit overflow? */
+ bcs .Lctrloop
+.LctrloopNx:
+ subs w4, w4, #INTERLEAVE
+ bmi .Lctr1x
+#if INTERLEAVE == 2
+ mov v0.8b, v4.8b
+ mov v1.8b, v4.8b
+ rev x7, x5
+ add x5, x5, #1
+ ins v0.d[1], x7
+ rev x7, x5
+ add x5, x5, #1
+ ins v1.d[1], x7
+ ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */
+ do_encrypt_block2x
+ eor v0.16b, v0.16b, v2.16b
+ eor v1.16b, v1.16b, v3.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
+ dup v7.4s, w5
+ mov v0.16b, v4.16b
+ add v7.4s, v7.4s, v8.4s
+ mov v1.16b, v4.16b
+ rev32 v8.16b, v7.16b
+ mov v2.16b, v4.16b
+ mov v3.16b, v4.16b
+ mov v1.s[3], v8.s[0]
+ mov v2.s[3], v8.s[1]
+ mov v3.s[3], v8.s[2]
+ ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */
+ do_encrypt_block4x
+ eor v0.16b, v5.16b, v0.16b
+ ld1 {v5.16b}, [x1], #16 /* get 1 input block */
+ eor v1.16b, v6.16b, v1.16b
+ eor v2.16b, v7.16b, v2.16b
+ eor v3.16b, v5.16b, v3.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ add x5, x5, #INTERLEAVE
+#endif
+ cbz w4, .LctroutNx
+.LctrincNx:
+ rev x7, x5
+ ins v4.d[1], x7
+ b .LctrloopNx
+.LctroutNx:
+ sub x5, x5, #1
+ rev x7, x5
+ ins v4.d[1], x7
+ b .Lctrout
+.Lctr1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lctrout
+#endif
+.Lctrloop:
+ mov v0.16b, v4.16b
+ encrypt_block v0, w3, x2, x6, w7
+ subs w4, w4, #1
+ bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
+ ld1 {v3.16b}, [x1], #16
+ eor v3.16b, v0.16b, v3.16b
+ st1 {v3.16b}, [x0], #16
+ beq .Lctrout
+.Lctrinc:
+ adds x5, x5, #1 /* increment BE ctr */
+ rev x7, x5
+ ins v4.d[1], x7
+ bcc .Lctrloop /* no overflow? */
+ umov x7, v4.d[0] /* load upper word of ctr */
+ rev x7, x7 /* ... to handle the carry */
+ add x7, x7, #1
+ rev x7, x7
+ ins v4.d[0], x7
+ b .Lctrloop
+.Lctrhalfblock:
+ ld1 {v3.8b}, [x1]
+ eor v3.8b, v0.8b, v3.8b
+ st1 {v3.8b}, [x0]
+.Lctrout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ctr_encrypt)
+ .ltorg
+
+
+ /*
+ * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+ * int blocks, u8 const rk2[], u8 iv[], int first)
+ * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+ * int blocks, u8 const rk2[], u8 iv[], int first)
+ */
+
+ .macro next_tweak, out, in, const, tmp
+ sshr \tmp\().2d, \in\().2d, #63
+ and \tmp\().16b, \tmp\().16b, \const\().16b
+ add \out\().2d, \in\().2d, \in\().2d
+ ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+ eor \out\().16b, \out\().16b, \tmp\().16b
+ .endm
+
+.Lxts_mul_x:
+ .word 1, 0, 0x87, 0
+
+AES_ENTRY(aes_xts_encrypt)
+ FRAME_PUSH
+ cbz w7, .LxtsencloopNx
+
+ ld1 {v4.16b}, [x6]
+ enc_prepare w3, x5, x6
+ encrypt_block v4, w3, x5, x6, w7 /* first tweak */
+ enc_switch_key w3, x2, x6
+ ldr q7, .Lxts_mul_x
+ b .LxtsencNx
+
+.LxtsencloopNx:
+ ldr q7, .Lxts_mul_x
+ next_tweak v4, v4, v7, v8
+.LxtsencNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lxtsenc1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ do_encrypt_block2x
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+ cbz w4, .LxtsencoutNx
+ next_tweak v4, v5, v7, v8
+ b .LxtsencNx
+.LxtsencoutNx:
+ mov v4.16b, v5.16b
+ b .Lxtsencout
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ next_tweak v6, v5, v7, v8
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ next_tweak v7, v6, v7, v8
+ eor v3.16b, v3.16b, v7.16b
+ do_encrypt_block4x
+ eor v3.16b, v3.16b, v7.16b
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ mov v4.16b, v7.16b
+ cbz w4, .Lxtsencout
+ b .LxtsencloopNx
+#endif
+.Lxtsenc1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lxtsencout
+#endif
+.Lxtsencloop:
+ ld1 {v1.16b}, [x1], #16
+ eor v0.16b, v1.16b, v4.16b
+ encrypt_block v0, w3, x2, x6, w7
+ eor v0.16b, v0.16b, v4.16b
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ beq .Lxtsencout
+ next_tweak v4, v4, v7, v8
+ b .Lxtsencloop
+.Lxtsencout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_xts_encrypt)
+
+
+AES_ENTRY(aes_xts_decrypt)
+ FRAME_PUSH
+ cbz w7, .LxtsdecloopNx
+
+ ld1 {v4.16b}, [x6]
+ enc_prepare w3, x5, x6
+ encrypt_block v4, w3, x5, x6, w7 /* first tweak */
+ dec_prepare w3, x2, x6
+ ldr q7, .Lxts_mul_x
+ b .LxtsdecNx
+
+.LxtsdecloopNx:
+ ldr q7, .Lxts_mul_x
+ next_tweak v4, v4, v7, v8
+.LxtsdecNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lxtsdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ do_decrypt_block2x
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+ cbz w4, .LxtsdecoutNx
+ next_tweak v4, v5, v7, v8
+ b .LxtsdecNx
+.LxtsdecoutNx:
+ mov v4.16b, v5.16b
+ b .Lxtsdecout
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ next_tweak v6, v5, v7, v8
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ next_tweak v7, v6, v7, v8
+ eor v3.16b, v3.16b, v7.16b
+ do_decrypt_block4x
+ eor v3.16b, v3.16b, v7.16b
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ mov v4.16b, v7.16b
+ cbz w4, .Lxtsdecout
+ b .LxtsdecloopNx
+#endif
+.Lxtsdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lxtsdecout
+#endif
+.Lxtsdecloop:
+ ld1 {v1.16b}, [x1], #16
+ eor v0.16b, v1.16b, v4.16b
+ decrypt_block v0, w3, x2, x6, w7
+ eor v0.16b, v0.16b, v4.16b
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ beq .Lxtsdecout
+ next_tweak v4, v4, v7, v8
+ b .Lxtsdecloop
+.Lxtsdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 0000000..b93170e
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func) ENTRY(neon_ ## func)
+#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
+
+ /* multiply by polynomial 'x' in GF(2^8) */
+ .macro mul_by_x, out, in, temp, const
+ sshr \temp, \in, #7
+ add \out, \in, \in
+ and \temp, \temp, \const
+ eor \out, \out, \temp
+ .endm
+
+ /* preload the entire Sbox */
+ .macro prepare, sbox, shiftrows, temp
+ adr \temp, \sbox
+ movi v12.16b, #0x40
+ ldr q13, \shiftrows
+ movi v14.16b, #0x1b
+ ld1 {v16.16b-v19.16b}, [\temp], #64
+ ld1 {v20.16b-v23.16b}, [\temp], #64
+ ld1 {v24.16b-v27.16b}, [\temp], #64
+ ld1 {v28.16b-v31.16b}, [\temp]
+ .endm
+
+ /* do preload for encryption */
+ .macro enc_prepare, ignore0, ignore1, temp
+ prepare .LForward_Sbox, .LForward_ShiftRows, \temp
+ .endm
+
+ .macro enc_switch_key, ignore0, ignore1, temp
+ /* do nothing */
+ .endm
+
+ /* do preload for decryption */
+ .macro dec_prepare, ignore0, ignore1, temp
+ prepare .LReverse_Sbox, .LReverse_ShiftRows, \temp
+ .endm
+
+ /* apply SubBytes transformation using the the preloaded Sbox */
+ .macro sub_bytes, in
+ sub v9.16b, \in\().16b, v12.16b
+ tbl \in\().16b, {v16.16b-v19.16b}, \in\().16b
+ sub v10.16b, v9.16b, v12.16b
+ tbx \in\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v11.16b, v10.16b, v12.16b
+ tbx \in\().16b, {v24.16b-v27.16b}, v10.16b
+ tbx \in\().16b, {v28.16b-v31.16b}, v11.16b
+ .endm
+
+ /* apply MixColumns transformation */
+ .macro mix_columns, in
+ mul_by_x v10.16b, \in\().16b, v9.16b, v14.16b
+ rev32 v8.8h, \in\().8h
+ eor \in\().16b, v10.16b, \in\().16b
+ shl v9.4s, v8.4s, #24
+ shl v11.4s, \in\().4s, #24
+ sri v9.4s, v8.4s, #8
+ sri v11.4s, \in\().4s, #8
+ eor v9.16b, v9.16b, v8.16b
+ eor v10.16b, v10.16b, v9.16b
+ eor \in\().16b, v10.16b, v11.16b
+ .endm
+
+ /* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+ .macro inv_mix_columns, in
+ mul_by_x v11.16b, \in\().16b, v10.16b, v14.16b
+ mul_by_x v11.16b, v11.16b, v10.16b, v14.16b
+ eor \in\().16b, \in\().16b, v11.16b
+ rev32 v11.8h, v11.8h
+ eor \in\().16b, \in\().16b, v11.16b
+ mix_columns \in
+ .endm
+
+ .macro do_block, enc, in, rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
+ tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */
+ sub_bytes \in
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns \in
+ .else
+ inv_mix_columns \in
+ .endif
+ b 1111b
+2222: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro encrypt_block, in, rounds, rk, rkp, i
+ do_block 1, \in, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block, in, rounds, rk, rkp, i
+ do_block 0, \in, \rounds, \rk, \rkp, \i
+ .endm
+
+ /*
+ * Interleaved versions: functionally equivalent to the
+ * ones above, but applied to 2 or 4 AES states in parallel.
+ */
+
+ .macro sub_bytes_2x, in0, in1
+ sub v8.16b, \in0\().16b, v12.16b
+ sub v9.16b, \in1\().16b, v12.16b
+ tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+ tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+ sub v10.16b, v8.16b, v12.16b
+ sub v11.16b, v9.16b, v12.16b
+ tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
+ tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v8.16b, v10.16b, v12.16b
+ sub v9.16b, v11.16b, v12.16b
+ tbx \in0\().16b, {v24.16b-v27.16b}, v10.16b
+ tbx \in1\().16b, {v24.16b-v27.16b}, v11.16b
+ tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
+ tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
+ .endm
+
+ .macro sub_bytes_4x, in0, in1, in2, in3
+ sub v8.16b, \in0\().16b, v12.16b
+ tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+ sub v9.16b, \in1\().16b, v12.16b
+ tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+ sub v10.16b, \in2\().16b, v12.16b
+ tbl \in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+ sub v11.16b, \in3\().16b, v12.16b
+ tbl \in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+ tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
+ tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v8.16b, v8.16b, v12.16b
+ tbx \in2\().16b, {v20.16b-v23.16b}, v10.16b
+ sub v9.16b, v9.16b, v12.16b
+ tbx \in3\().16b, {v20.16b-v23.16b}, v11.16b
+ sub v10.16b, v10.16b, v12.16b
+ tbx \in0\().16b, {v24.16b-v27.16b}, v8.16b
+ sub v11.16b, v11.16b, v12.16b
+ tbx \in1\().16b, {v24.16b-v27.16b}, v9.16b
+ sub v8.16b, v8.16b, v12.16b
+ tbx \in2\().16b, {v24.16b-v27.16b}, v10.16b
+ sub v9.16b, v9.16b, v12.16b
+ tbx \in3\().16b, {v24.16b-v27.16b}, v11.16b
+ sub v10.16b, v10.16b, v12.16b
+ tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
+ sub v11.16b, v11.16b, v12.16b
+ tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
+ tbx \in2\().16b, {v28.16b-v31.16b}, v10.16b
+ tbx \in3\().16b, {v28.16b-v31.16b}, v11.16b
+ .endm
+
+ .macro mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+ sshr \tmp0\().16b, \in0\().16b, #7
+ add \out0\().16b, \in0\().16b, \in0\().16b
+ sshr \tmp1\().16b, \in1\().16b, #7
+ and \tmp0\().16b, \tmp0\().16b, \const\().16b
+ add \out1\().16b, \in1\().16b, \in1\().16b
+ and \tmp1\().16b, \tmp1\().16b, \const\().16b
+ eor \out0\().16b, \out0\().16b, \tmp0\().16b
+ eor \out1\().16b, \out1\().16b, \tmp1\().16b
+ .endm
+
+ .macro mix_columns_2x, in0, in1
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ rev32 v10.8h, \in0\().8h
+ rev32 v11.8h, \in1\().8h
+ eor \in0\().16b, v8.16b, \in0\().16b
+ eor \in1\().16b, v9.16b, \in1\().16b
+ shl v12.4s, v10.4s, #24
+ shl v13.4s, v11.4s, #24
+ eor v8.16b, v8.16b, v10.16b
+ sri v12.4s, v10.4s, #8
+ shl v10.4s, \in0\().4s, #24
+ eor v9.16b, v9.16b, v11.16b
+ sri v13.4s, v11.4s, #8
+ shl v11.4s, \in1\().4s, #24
+ sri v10.4s, \in0\().4s, #8
+ eor \in0\().16b, v8.16b, v12.16b
+ sri v11.4s, \in1\().4s, #8
+ eor \in1\().16b, v9.16b, v13.16b
+ eor \in0\().16b, v10.16b, \in0\().16b
+ eor \in1\().16b, v11.16b, \in1\().16b
+ .endm
+
+ .macro inv_mix_cols_2x, in0, in1
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ mul_by_x_2x v8, v9, v8, v9, v10, v11, v14
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ rev32 v8.8h, v8.8h
+ rev32 v9.8h, v9.8h
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ mix_columns_2x \in0, \in1
+ .endm
+
+ .macro inv_mix_cols_4x, in0, in1, in2, in3
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ mul_by_x_2x v10, v11, \in2, \in3, v12, v13, v14
+ mul_by_x_2x v8, v9, v8, v9, v12, v13, v14
+ mul_by_x_2x v10, v11, v10, v11, v12, v13, v14
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ eor \in2\().16b, \in2\().16b, v10.16b
+ eor \in3\().16b, \in3\().16b, v11.16b
+ rev32 v8.8h, v8.8h
+ rev32 v9.8h, v9.8h
+ rev32 v10.8h, v10.8h
+ rev32 v11.8h, v11.8h
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ eor \in2\().16b, \in2\().16b, v10.16b
+ eor \in3\().16b, \in3\().16b, v11.16b
+ mix_columns_2x \in0, \in1
+ mix_columns_2x \in2, \in3
+ .endm
+
+ .macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ sub_bytes_2x \in0, \in1
+ tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
+ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns_2x \in0, \in1
+ ldr q13, .LForward_ShiftRows
+ .else
+ inv_mix_cols_2x \in0, \in1
+ ldr q13, .LReverse_ShiftRows
+ .endif
+ movi v12.16b, #0x40
+ b 1111b
+2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
+ eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
+ sub_bytes_4x \in0, \in1, \in2, \in3
+ tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
+ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
+ tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */
+ tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns_2x \in0, \in1
+ mix_columns_2x \in2, \in3
+ ldr q13, .LForward_ShiftRows
+ .else
+ inv_mix_cols_4x \in0, \in1, \in2, \in3
+ ldr q13, .LReverse_ShiftRows
+ .endif
+ movi v12.16b, #0x40
+ b 1111b
+2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
+ eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro encrypt_block2x, in0, in1, rounds, rk, rkp, i
+ do_block_2x 1, \in0, \in1, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block2x, in0, in1, rounds, rk, rkp, i
+ do_block_2x 0, \in0, \in1, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+ do_block_4x 1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+ do_block_4x 0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+ .endm
+
+#include "aes-modes.S"
+
+ .text
+ .align 4
+.LForward_ShiftRows:
+ .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
+ .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+
+.LReverse_ShiftRows:
+ .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
+ .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+
+.LForward_Sbox:
+ .byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+ .byte 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+ .byte 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+ .byte 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+ .byte 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+ .byte 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+ .byte 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+ .byte 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+ .byte 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+ .byte 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+ .byte 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+ .byte 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+ .byte 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+ .byte 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+ .byte 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+ .byte 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+ .byte 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+ .byte 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+ .byte 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+ .byte 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+ .byte 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+ .byte 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+ .byte 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+ .byte 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+ .byte 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+ .byte 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+ .byte 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+ .byte 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+ .byte 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+ .byte 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+ .byte 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+ .byte 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.LReverse_Sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+ .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 0000000..dc45701
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,79 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ SHASH .req v0
+ SHASH2 .req v1
+ T1 .req v2
+ T2 .req v3
+ MASK .req v4
+ XL .req v5
+ XM .req v6
+ XH .req v7
+ IN1 .req v7
+
+ .text
+ .arch armv8-a+crypto
+
+ /*
+ * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ * struct ghash_key const *k, const char *head)
+ */
+ENTRY(pmull_ghash_update)
+ ld1 {SHASH.16b}, [x3]
+ ld1 {XL.16b}, [x1]
+ movi MASK.16b, #0xe1
+ ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
+ shl MASK.2d, MASK.2d, #57
+ eor SHASH2.16b, SHASH2.16b, SHASH.16b
+
+ /* do the head block first, if supplied */
+ cbz x4, 0f
+ ld1 {T1.2d}, [x4]
+ b 1f
+
+0: ld1 {T1.2d}, [x2], #16
+ sub w0, w0, #1
+
+1: /* multiply XL by SHASH in GF(2^128) */
+CPU_LE( rev64 T1.16b, T1.16b )
+
+ ext T2.16b, XL.16b, XL.16b, #8
+ ext IN1.16b, T1.16b, T1.16b, #8
+ eor T1.16b, T1.16b, T2.16b
+ eor XL.16b, XL.16b, IN1.16b
+
+ pmull2 XH.1q, SHASH.2d, XL.2d // a1 * b1
+ eor T1.16b, T1.16b, XL.16b
+ pmull XL.1q, SHASH.1d, XL.1d // a0 * b0
+ pmull XM.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0)
+
+ ext T1.16b, XL.16b, XH.16b, #8
+ eor T2.16b, XL.16b, XH.16b
+ eor XM.16b, XM.16b, T1.16b
+ eor XM.16b, XM.16b, T2.16b
+ pmull T2.1q, XL.1d, MASK.1d
+
+ mov XH.d[0], XM.d[1]
+ mov XM.d[1], XL.d[0]
+
+ eor XL.16b, XM.16b, T2.16b
+ ext T2.16b, XL.16b, XL.16b, #8
+ pmull XL.1q, XL.1d, MASK.1d
+ eor T2.16b, T2.16b, XH.16b
+ eor XL.16b, XL.16b, T2.16b
+
+ cbnz w0, 0b
+
+ st1 {XL.16b}, [x1]
+ ret
+ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 0000000..833ec1e
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,156 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+#define GHASH_BLOCK_SIZE 16
+#define GHASH_DIGEST_SIZE 16
+
+struct ghash_key {
+ u64 a;
+ u64 b;
+};
+
+struct ghash_desc_ctx {
+ u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+ u8 buf[GHASH_BLOCK_SIZE];
+ u32 count;
+};
+
+asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k, const char *head);
+
+static int ghash_init(struct shash_desc *desc)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+ unsigned int len)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ ctx->count += len;
+
+ if ((partial + len) >= GHASH_BLOCK_SIZE) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+ int blocks;
+
+ if (partial) {
+ int p = GHASH_BLOCK_SIZE - partial;
+
+ memcpy(ctx->buf + partial, src, p);
+ src += p;
+ len -= p;
+ }
+
+ blocks = len / GHASH_BLOCK_SIZE;
+ len %= GHASH_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(8);
+ pmull_ghash_update(blocks, ctx->digest, src, key,
+ partial ? ctx->buf : NULL);
+ kernel_neon_end();
+ src += blocks * GHASH_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(ctx->buf + partial, src, len);
+ return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ if (partial) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+ memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+ kernel_neon_begin_partial(8);
+ pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
+ kernel_neon_end();
+ }
+ put_unaligned_be64(ctx->digest[1], dst);
+ put_unaligned_be64(ctx->digest[0], dst + 8);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+ const u8 *inkey, unsigned int keylen)
+{
+ struct ghash_key *key = crypto_shash_ctx(tfm);
+ u64 a, b;
+
+ if (keylen != GHASH_BLOCK_SIZE) {
+ crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+
+ /* perform multiplication by 'x' in GF(2^128) */
+ b = get_unaligned_be64(inkey);
+ a = get_unaligned_be64(inkey + 8);
+
+ key->a = (a << 1) | (b >> 63);
+ key->b = (b << 1) | (a >> 63);
+
+ if (b >> 63)
+ key->b ^= 0xc200000000000000UL;
+
+ return 0;
+}
+
+static struct shash_alg ghash_alg = {
+ .digestsize = GHASH_DIGEST_SIZE,
+ .init = ghash_init,
+ .update = ghash_update,
+ .final = ghash_final,
+ .setkey = ghash_setkey,
+ .descsize = sizeof(struct ghash_desc_ctx),
+ .base = {
+ .cra_name = "ghash",
+ .cra_driver_name = "ghash-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = GHASH_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct ghash_key),
+ .cra_module = THIS_MODULE,
+ },
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+ return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+ crypto_unregister_shash(&ghash_alg);
+}
+
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 0000000..09d57d9
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ k0 .req v0
+ k1 .req v1
+ k2 .req v2
+ k3 .req v3
+
+ t0 .req v4
+ t1 .req v5
+
+ dga .req q6
+ dgav .req v6
+ dgb .req s7
+ dgbv .req v7
+
+ dg0q .req q12
+ dg0s .req s12
+ dg0v .req v12
+ dg1s .req s13
+ dg1v .req v13
+ dg2s .req s14
+
+ .macro add_only, op, ev, rc, s0, dg1
+ .ifc \ev, ev
+ add t1.4s, v\s0\().4s, \rc\().4s
+ sha1h dg2s, dg0s
+ .ifnb \dg1
+ sha1\op dg0q, \dg1, t0.4s
+ .else
+ sha1\op dg0q, dg1s, t0.4s
+ .endif
+ .else
+ .ifnb \s0
+ add t0.4s, v\s0\().4s, \rc\().4s
+ .endif
+ sha1h dg1s, dg0s
+ sha1\op dg0q, dg2s, t1.4s
+ .endif
+ .endm
+
+ .macro add_update, op, ev, rc, s0, s1, s2, s3, dg1
+ sha1su0 v\s0\().4s, v\s1\().4s, v\s2\().4s
+ add_only \op, \ev, \rc, \s1, \dg1
+ sha1su1 v\s0\().4s, v\s3\().4s
+ .endm
+
+ /*
+ * The SHA1 round constants
+ */
+ .align 4
+.Lsha1_rcon:
+ .word 0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+ /*
+ * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head, long bytes)
+ */
+ENTRY(sha1_ce_transform)
+ /* load round constants */
+ adr x6, .Lsha1_rcon
+ ld1r {k0.4s}, [x6], #4
+ ld1r {k1.4s}, [x6], #4
+ ld1r {k2.4s}, [x6], #4
+ ld1r {k3.4s}, [x6]
+
+ /* load state */
+ ldr dga, [x2]
+ ldr dgb, [x2, #16]
+
+ /* load partial state (if supplied) */
+ cbz x3, 0f
+ ld1 {v8.4s-v11.4s}, [x3]
+ b 1f
+
+ /* load input */
+0: ld1 {v8.4s-v11.4s}, [x1], #64
+ sub w0, w0, #1
+
+1:
+CPU_LE( rev32 v8.16b, v8.16b )
+CPU_LE( rev32 v9.16b, v9.16b )
+CPU_LE( rev32 v10.16b, v10.16b )
+CPU_LE( rev32 v11.16b, v11.16b )
+
+2: add t0.4s, v8.4s, k0.4s
+ mov dg0v.16b, dgav.16b
+
+ add_update c, ev, k0, 8, 9, 10, 11, dgb
+ add_update c, od, k0, 9, 10, 11, 8
+ add_update c, ev, k0, 10, 11, 8, 9
+ add_update c, od, k0, 11, 8, 9, 10
+ add_update c, ev, k1, 8, 9, 10, 11
+
+ add_update p, od, k1, 9, 10, 11, 8
+ add_update p, ev, k1, 10, 11, 8, 9
+ add_update p, od, k1, 11, 8, 9, 10
+ add_update p, ev, k1, 8, 9, 10, 11
+ add_update p, od, k2, 9, 10, 11, 8
+
+ add_update m, ev, k2, 10, 11, 8, 9
+ add_update m, od, k2, 11, 8, 9, 10
+ add_update m, ev, k2, 8, 9, 10, 11
+ add_update m, od, k2, 9, 10, 11, 8
+ add_update m, ev, k3, 10, 11, 8, 9
+
+ add_update p, od, k3, 11, 8, 9, 10
+ add_only p, ev, k3, 9
+ add_only p, od, k3, 10
+ add_only p, ev, k3, 11
+ add_only p, od
+
+ /* update state */
+ add dgbv.2s, dgbv.2s, dg1v.2s
+ add dgav.4s, dgav.4s, dg0v.4s
+
+ cbnz w0, 0b
+
+ /*
+ * Final block: add padding and total bit count.
+ * Skip if we have no total byte count in x4. In that case, the input
+ * size was not a round multiple of the block size, and the padding is
+ * handled by the C code.
+ */
+ cbz x4, 3f
+ movi v9.2d, #0
+ mov x8, #0x80000000
+ movi v10.2d, #0
+ ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ fmov d8, x8
+ mov x4, #0
+ mov v11.d[0], xzr
+ mov v11.d[1], x7
+ b 2b
+
+ /* store new state */
+3: str dga, [x2]
+ str dgb, [x2, #16]
+ ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 0000000..6fe83f3
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha1_state){
+ .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+ };
+ return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+ sctx->count += len;
+
+ if ((partial + len) >= SHA1_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA1_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buffer + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA1_BLOCK_SIZE;
+ len %= SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buffer : NULL, 0);
+ kernel_neon_end();
+
+ data += blocks * SHA1_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buffer + partial, data, len);
+ return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+ static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ u32 padlen = SHA1_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+ sha1_update(desc, padding, padlen);
+ sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int blocks;
+ int i;
+
+ if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+ sha1_update(desc, data, len);
+ return sha1_final(desc, out);
+ }
+
+ /*
+ * Use a fast path if the input is a multiple of 64 bytes. In
+ * this case, there is no need to copy data around, and we can
+ * perform the entire digest calculation in a single invocation
+ * of sha1_ce_transform()
+ */
+ blocks = len / SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+ kernel_neon_end();
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .init = sha1_init,
+ .update = sha1_update,
+ .final = sha1_final,
+ .finup = sha1_finup,
+ .export = sha1_export,
+ .import = sha1_import,
+ .descsize = sizeof(struct sha1_state),
+ .digestsize = SHA1_DIGEST_SIZE,
+ .statesize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+ return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 0000000..7f29fc0
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,156 @@
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ dga .req q20
+ dgav .req v20
+ dgb .req q21
+ dgbv .req v21
+
+ t0 .req v22
+ t1 .req v23
+
+ dg0q .req q24
+ dg0v .req v24
+ dg1q .req q25
+ dg1v .req v25
+ dg2q .req q26
+ dg2v .req v26
+
+ .macro add_only, ev, rc, s0
+ mov dg2v.16b, dg0v.16b
+ .ifeq \ev
+ add t1.4s, v\s0\().4s, \rc\().4s
+ sha256h dg0q, dg1q, t0.4s
+ sha256h2 dg1q, dg2q, t0.4s
+ .else
+ .ifnb \s0
+ add t0.4s, v\s0\().4s, \rc\().4s
+ .endif
+ sha256h dg0q, dg1q, t1.4s
+ sha256h2 dg1q, dg2q, t1.4s
+ .endif
+ .endm
+
+ .macro add_update, ev, rc, s0, s1, s2, s3
+ sha256su0 v\s0\().4s, v\s1\().4s
+ add_only \ev, \rc, \s1
+ sha256su1 v\s0\().4s, v\s2\().4s, v\s3\().4s
+ .endm
+
+ /*
+ * The SHA-256 round constants
+ */
+ .align 4
+.Lsha2_rcon:
+ .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+ .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+ .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+ .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+ .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+ .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+ .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+ .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+ .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+ .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+ .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+ .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+ .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+ .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+ .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+ .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+ /*
+ * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head, long bytes)
+ */
+ENTRY(sha2_ce_transform)
+ /* load round constants */
+ adr x8, .Lsha2_rcon
+ ld1 { v0.4s- v3.4s}, [x8], #64
+ ld1 { v4.4s- v7.4s}, [x8], #64
+ ld1 { v8.4s-v11.4s}, [x8], #64
+ ld1 {v12.4s-v15.4s}, [x8]
+
+ /* load state */
+ ldp dga, dgb, [x2]
+
+ /* load partial input (if supplied) */
+ cbz x3, 0f
+ ld1 {v16.4s-v19.4s}, [x3]
+ b 1f
+
+ /* load input */
+0: ld1 {v16.4s-v19.4s}, [x1], #64
+ sub w0, w0, #1
+
+1:
+CPU_LE( rev32 v16.16b, v16.16b )
+CPU_LE( rev32 v17.16b, v17.16b )
+CPU_LE( rev32 v18.16b, v18.16b )
+CPU_LE( rev32 v19.16b, v19.16b )
+
+2: add t0.4s, v16.4s, v0.4s
+ mov dg0v.16b, dgav.16b
+ mov dg1v.16b, dgbv.16b
+
+ add_update 0, v1, 16, 17, 18, 19
+ add_update 1, v2, 17, 18, 19, 16
+ add_update 0, v3, 18, 19, 16, 17
+ add_update 1, v4, 19, 16, 17, 18
+
+ add_update 0, v5, 16, 17, 18, 19
+ add_update 1, v6, 17, 18, 19, 16
+ add_update 0, v7, 18, 19, 16, 17
+ add_update 1, v8, 19, 16, 17, 18
+
+ add_update 0, v9, 16, 17, 18, 19
+ add_update 1, v10, 17, 18, 19, 16
+ add_update 0, v11, 18, 19, 16, 17
+ add_update 1, v12, 19, 16, 17, 18
+
+ add_only 0, v13, 17
+ add_only 1, v14, 18
+ add_only 0, v15, 19
+ add_only 1
+
+ /* update state */
+ add dgav.4s, dgav.4s, dg0v.4s
+ add dgbv.4s, dgbv.4s, dg1v.4s
+
+ /* handled all input blocks? */
+ cbnz w0, 0b
+
+ /*
+ * Final block: add padding and total bit count.
+ * Skip if we have no total byte count in x4. In that case, the input
+ * size was not a round multiple of the block size, and the padding is
+ * handled by the C code.
+ */
+ cbz x4, 3f
+ movi v17.2d, #0
+ mov x8, #0x80000000
+ movi v18.2d, #0
+ ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ fmov d16, x8
+ mov x4, #0
+ mov v19.d[0], xzr
+ mov v19.d[1], x7
+ b 2b
+
+ /* store new state */
+3: stp dga, dgb, [x2]
+ ret
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 0000000..c294e67
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,255 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head, long bytes);
+
+static int sha224_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+ SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+ SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+ sctx->count += len;
+
+ if ((partial + len) >= SHA256_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA256_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buf + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA256_BLOCK_SIZE;
+ len %= SHA256_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(28);
+ sha2_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buf : NULL, 0);
+ kernel_neon_end();
+
+ data += blocks * SHA256_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buf + partial, data, len);
+ return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+ static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ u32 padlen = SHA256_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+ sha2_update(desc, padding, padlen);
+ sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static void sha2_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ int blocks;
+
+ if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
+ sha2_update(desc, data, len);
+ sha2_final(desc);
+ return;
+ }
+
+ /*
+ * Use a fast path if the input is a multiple of 64 bytes. In
+ * this case, there is no need to copy data around, and we can
+ * perform the entire digest calculation in a single invocation
+ * of sha2_ce_transform()
+ */
+ blocks = len / SHA256_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(28);
+ sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+ kernel_neon_end();
+ data += blocks * SHA256_BLOCK_SIZE;
+}
+
+static int sha224_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_finup(desc, data, len);
+
+ for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha256_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_finup(desc, data, len);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg algs[] = { {
+ .init = sha224_init,
+ .update = sha2_update,
+ .final = sha224_final,
+ .finup = sha224_finup,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA224_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha256_init,
+ .update = sha2_update,
+ .final = sha256_final,
+ .finup = sha256_finup,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA256_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+ return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 79a642d..fb6e0c4 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -36,6 +36,7 @@
generic-y += sembuf.h
generic-y += serial.h
generic-y += shmbuf.h
+generic-y += simd.h
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index d4a6333..78e20ba 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -35,10 +35,60 @@
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#else
+
#define smp_mb() asm volatile("dmb ish" : : : "memory")
#define smp_rmb() asm volatile("dmb ishld" : : : "memory")
#define smp_wmb() asm volatile("dmb ishst" : : : "memory")
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 4: \
+ asm volatile ("stlr %w1, %0" \
+ : "=Q" (*p) : "r" (v) : "memory"); \
+ break; \
+ case 8: \
+ asm volatile ("stlr %1, %0" \
+ : "=Q" (*p) : "r" (v) : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 4: \
+ asm volatile ("ldar %w0, %1" \
+ : "=r" (___p1) : "Q" (*p) : "memory"); \
+ break; \
+ case 8: \
+ asm volatile ("ldar %0, %1" \
+ : "=r" (___p1) : "Q" (*p) : "memory"); \
+ break; \
+ } \
+ ___p1; \
+})
+
#endif
#define read_barrier_depends() do { } while(0)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 8a8ce0e..a8b44ca 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -158,17 +158,23 @@
return ret;
}
-#define cmpxchg(ptr,o,n) \
- ((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \
- (unsigned long)(o), \
- (unsigned long)(n), \
- sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
+ sizeof(*(ptr))); \
+ __ret; \
+})
-#define cmpxchg_local(ptr,o,n) \
- ((__typeof__(*(ptr)))__cmpxchg((ptr), \
- (unsigned long)(o), \
- (unsigned long)(n), \
- sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ __ret; \
+})
#define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n))
#define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index c30a548..a203e97 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -191,6 +191,13 @@
compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */
int _fd;
} _sigpoll;
+
+ /* SIGSYS */
+ struct {
+ compat_uptr_t _call_addr; /* calling user insn */
+ int _syscall; /* triggering system call number */
+ unsigned int _arch; /* AUDIT_ARCH_* of syscall */
+ } _sigsys;
} _sifields;
} compat_siginfo_t;
@@ -214,7 +221,7 @@
return (u32)(unsigned long)uptr;
}
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
static inline void __user *arch_compat_alloc_user_space(long len)
{
@@ -291,11 +298,6 @@
#else /* !CONFIG_COMPAT */
-static inline int is_compat_task(void)
-{
- return 0;
-}
-
static inline int is_compat_thread(struct thread_info *thread)
{
return 0;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 0000000..cd4ac05
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap))
+#define cpu_feature(x) ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+ return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index be9b5ca..76b7b3c 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -16,23 +16,13 @@
#ifndef __ASM_CPUTYPE_H
#define __ASM_CPUTYPE_H
-#define ID_MIDR_EL1 "midr_el1"
-#define ID_MPIDR_EL1 "mpidr_el1"
-#define ID_CTR_EL0 "ctr_el0"
-
-#define ID_AA64PFR0_EL1 "id_aa64pfr0_el1"
-#define ID_AA64DFR0_EL1 "id_aa64dfr0_el1"
-#define ID_AA64AFR0_EL1 "id_aa64afr0_el1"
-#define ID_AA64ISAR0_EL1 "id_aa64isar0_el1"
-#define ID_AA64MMFR0_EL1 "id_aa64mmfr0_el1"
-
#define INVALID_HWID ULONG_MAX
#define MPIDR_HWID_BITMASK 0xff00ffffff
#define read_cpuid(reg) ({ \
u64 __val; \
- asm("mrs %0, " reg : "=r" (__val)); \
+ asm("mrs %0, " #reg : "=r" (__val)); \
__val; \
})
@@ -51,12 +41,12 @@
*/
static inline u32 __attribute_const__ read_cpuid_id(void)
{
- return read_cpuid(ID_MIDR_EL1);
+ return read_cpuid(MIDR_EL1);
}
static inline u64 __attribute_const__ read_cpuid_mpidr(void)
{
- return read_cpuid(ID_MPIDR_EL1);
+ return read_cpuid(MPIDR_EL1);
}
static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
@@ -71,7 +61,7 @@
static inline u32 __attribute_const__ read_cpuid_cachetype(void)
{
- return read_cpuid(ID_CTR_EL0);
+ return read_cpuid(CTR_EL0);
}
void cpuinfo_store_cpu(void);
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7eaa0b3..ef8235c 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -83,6 +83,15 @@
}
#endif
+#ifdef CONFIG_COMPAT
+int aarch32_break_handler(struct pt_regs *regs);
+#else
+static int aarch32_break_handler(struct pt_regs *regs)
+{
+ return -EFAULT;
+}
+#endif
+
#endif /* __ASSEMBLY */
#endif /* __KERNEL__ */
#endif /* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index fe32c0e..e7fa87f 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@
typedef elf_greg_t elf_gregset_t[ELF_NGREG];
typedef struct user_fpsimd_state elf_fpregset_t;
-#define EM_AARCH64 183
-
/*
* AArch64 static relocation types.
*/
@@ -151,7 +149,6 @@
#define arch_randomize_brk arch_randomize_brk
#ifdef CONFIG_COMPAT
-#define EM_ARM 40
#define COMPAT_ELF_PLATFORM ("v8l")
#define COMPAT_ELF_ET_DYN_BASE (randomize_et_dyn(2 * TASK_SIZE_32 / 3))
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index c43b4ac..50f559f 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,8 +37,21 @@
u32 fpcr;
};
};
+ /* the id of the last cpu to have restored this state */
+ unsigned int cpu;
};
+/*
+ * Struct for stacking the bottom 'n' FP/SIMD registers.
+ */
+struct fpsimd_partial_state {
+ u32 fpsr;
+ u32 fpcr;
+ u32 num_regs;
+ __uint128_t vregs[32];
+};
+
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/* Masks for extracting the FPSR and FPCR from the FPSCR */
#define VFP_FPSCR_STAT_MASK 0xf800009f
@@ -58,6 +71,16 @@
extern void fpsimd_thread_switch(struct task_struct *next);
extern void fpsimd_flush_thread(void);
+extern void fpsimd_preserve_current_state(void);
+extern void fpsimd_restore_current_state(void);
+extern void fpsimd_update_current_state(struct fpsimd_state *state);
+
+extern void fpsimd_flush_task_state(struct task_struct *target);
+
+extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
+ u32 num_regs);
+extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+
#endif
#endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index bbec599..768414d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -62,3 +62,38 @@
ldr w\tmpnr, [\state, #16 * 2 + 4]
msr fpcr, x\tmpnr
.endm
+
+.altmacro
+.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
+ mrs x\tmpnr1, fpsr
+ str w\numnr, [\state, #8]
+ mrs x\tmpnr2, fpcr
+ stp w\tmpnr1, w\tmpnr2, [\state]
+ adr x\tmpnr1, 0f
+ add \state, \state, x\numnr, lsl #4
+ sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
+ br x\tmpnr1
+ .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+ .irp qb, %(qa + 1)
+ stp q\qa, q\qb, [\state, # -16 * \qa - 16]
+ .endr
+ .endr
+0:
+.endm
+
+.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
+ ldp w\tmpnr1, w\tmpnr2, [\state]
+ msr fpsr, x\tmpnr1
+ msr fpcr, x\tmpnr2
+ adr x\tmpnr1, 0f
+ ldr w\tmpnr2, [\state, #8]
+ add \state, \state, x\tmpnr2, lsl #4
+ sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
+ br x\tmpnr1
+ .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+ .irp qb, %(qa + 1)
+ ldp q\qa, q\qb, [\state, # -16 * \qa - 16]
+ .endr
+ .endr
+0:
+.endm
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6d4482f..024c461 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,13 @@
#define COMPAT_HWCAP_IDIVA (1 << 17)
#define COMPAT_HWCAP_IDIVT (1 << 18)
#define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_EVTSTRM (1 << 21)
+
+#define COMPAT_HWCAP2_AES (1 << 0)
+#define COMPAT_HWCAP2_PMULL (1 << 1)
+#define COMPAT_HWCAP2_SHA1 (1 << 2)
+#define COMPAT_HWCAP2_SHA2 (1 << 3)
+#define COMPAT_HWCAP2_CRC32 (1 << 4)
#ifndef __ASSEMBLY__
/*
@@ -37,12 +44,13 @@
* instruction set this cpu supports.
*/
#define ELF_HWCAP (elf_hwcap)
-#define COMPAT_ELF_HWCAP (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
- COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
- COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
- COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
- COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
-extern unsigned int elf_hwcap;
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP (compat_elf_hwcap)
+#define COMPAT_ELF_HWCAP2 (compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
+#endif
+
+extern unsigned long elf_hwcap;
#endif
#endif
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
new file mode 100644
index 0000000..13ce4cc
--- /dev/null
+++ b/arch/arm64/include/asm/neon.h
@@ -0,0 +1,18 @@
+/*
+ * linux/arch/arm64/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+
+#define cpu_has_neon() (1)
+
+#define kernel_neon_begin() kernel_neon_begin_partial(32)
+
+void kernel_neon_begin_partial(u32 num_regs);
+void kernel_neon_end(void);
diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h
new file mode 100644
index 0000000..fd189a5
--- /dev/null
+++ b/arch/arm64/include/asm/opcodes.h
@@ -0,0 +1,231 @@
+/*
+ * Copied from arch/arm/include/asm/opcodes.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARM_OPCODES_H
+#define __ASM_ARM_OPCODES_H
+
+#ifndef __ASSEMBLY__
+#include <linux/linkage.h>
+extern asmlinkage unsigned int arm_check_condition(u32 opcode, u64 psr);
+#endif
+
+#define ARM_OPCODE_CONDTEST_FAIL 0
+#define ARM_OPCODE_CONDTEST_PASS 1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
+
+
+/*
+ * Assembler opcode byteswap helpers.
+ * These are only intended for use by this header: don't use them directly,
+ * because they will be suboptimal in most cases.
+ */
+#define ___asm_opcode_swab32(x) ( \
+ (((x) << 24) & 0xFF000000) \
+ | (((x) << 8) & 0x00FF0000) \
+ | (((x) >> 8) & 0x0000FF00) \
+ | (((x) >> 24) & 0x000000FF) \
+)
+#define ___asm_opcode_swab16(x) ( \
+ (((x) << 8) & 0xFF00) \
+ | (((x) >> 8) & 0x00FF) \
+)
+#define ___asm_opcode_swahb32(x) ( \
+ (((x) << 8) & 0xFF00FF00) \
+ | (((x) >> 8) & 0x00FF00FF) \
+)
+#define ___asm_opcode_swahw32(x) ( \
+ (((x) << 16) & 0xFFFF0000) \
+ | (((x) >> 16) & 0x0000FFFF) \
+)
+#define ___asm_opcode_identity32(x) ((x) & 0xFFFFFFFF)
+#define ___asm_opcode_identity16(x) ((x) & 0xFFFF)
+
+
+/*
+ * Opcode byteswap helpers
+ *
+ * These macros help with converting instructions between a canonical integer
+ * format and in-memory representation, in an endianness-agnostic manner.
+ *
+ * __mem_to_opcode_*() convert from in-memory representation to canonical form.
+ * __opcode_to_mem_*() convert from canonical form to in-memory representation.
+ *
+ *
+ * Canonical instruction representation:
+ *
+ * ARM: 0xKKLLMMNN
+ * Thumb 16-bit: 0x0000KKLL, where KK < 0xE8
+ * Thumb 32-bit: 0xKKLLMMNN, where KK >= 0xE8
+ *
+ * There is no way to distinguish an ARM instruction in canonical representation
+ * from a Thumb instruction (just as these cannot be distinguished in memory).
+ * Where this distinction is important, it needs to be tracked separately.
+ *
+ * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not
+ * represent any valid Thumb-2 instruction. For this range,
+ * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false.
+ *
+ * The ___asm variants are intended only for use by this header, in situations
+ * involving inline assembler. For .S files, the normal __opcode_*() macros
+ * should do the right thing.
+ */
+#ifdef __ASSEMBLY__
+
+#define ___opcode_swab32(x) ___asm_opcode_swab32(x)
+#define ___opcode_swab16(x) ___asm_opcode_swab16(x)
+#define ___opcode_swahb32(x) ___asm_opcode_swahb32(x)
+#define ___opcode_swahw32(x) ___asm_opcode_swahw32(x)
+#define ___opcode_identity32(x) ___asm_opcode_identity32(x)
+#define ___opcode_identity16(x) ___asm_opcode_identity16(x)
+
+#else /* ! __ASSEMBLY__ */
+
+#include <linux/types.h>
+#include <linux/swab.h>
+
+#define ___opcode_swab32(x) swab32(x)
+#define ___opcode_swab16(x) swab16(x)
+#define ___opcode_swahb32(x) swahb32(x)
+#define ___opcode_swahw32(x) swahw32(x)
+#define ___opcode_identity32(x) ((u32)(x))
+#define ___opcode_identity16(x) ((u16)(x))
+
+#endif /* ! __ASSEMBLY__ */
+
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+
+#define __opcode_to_mem_arm(x) ___opcode_swab32(x)
+#define __opcode_to_mem_thumb16(x) ___opcode_swab16(x)
+#define __opcode_to_mem_thumb32(x) ___opcode_swahb32(x)
+#define ___asm_opcode_to_mem_arm(x) ___asm_opcode_swab32(x)
+#define ___asm_opcode_to_mem_thumb16(x) ___asm_opcode_swab16(x)
+#define ___asm_opcode_to_mem_thumb32(x) ___asm_opcode_swahb32(x)
+
+#else /* ! CONFIG_CPU_ENDIAN_BE8 */
+
+#define __opcode_to_mem_arm(x) ___opcode_identity32(x)
+#define __opcode_to_mem_thumb16(x) ___opcode_identity16(x)
+#define ___asm_opcode_to_mem_arm(x) ___asm_opcode_identity32(x)
+#define ___asm_opcode_to_mem_thumb16(x) ___asm_opcode_identity16(x)
+#ifndef CONFIG_CPU_ENDIAN_BE32
+/*
+ * On BE32 systems, using 32-bit accesses to store Thumb instructions will not
+ * work in all cases, due to alignment constraints. For now, a correct
+ * version is not provided for BE32.
+ */
+#define __opcode_to_mem_thumb32(x) ___opcode_swahw32(x)
+#define ___asm_opcode_to_mem_thumb32(x) ___asm_opcode_swahw32(x)
+#endif
+
+#endif /* ! CONFIG_CPU_ENDIAN_BE8 */
+
+#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x)
+#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x)
+#ifndef CONFIG_CPU_ENDIAN_BE32
+#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x)
+#endif
+
+/* Operations specific to Thumb opcodes */
+
+/* Instruction size checks: */
+#define __opcode_is_thumb32(x) ( \
+ ((x) & 0xF8000000) == 0xE8000000 \
+ || ((x) & 0xF0000000) == 0xF0000000 \
+)
+#define __opcode_is_thumb16(x) ( \
+ ((x) & 0xFFFF0000) == 0 \
+ && !(((x) & 0xF800) == 0xE800 || ((x) & 0xF000) == 0xF000) \
+)
+
+/* Operations to construct or split 32-bit Thumb instructions: */
+#define __opcode_thumb32_first(x) (___opcode_identity16((x) >> 16))
+#define __opcode_thumb32_second(x) (___opcode_identity16(x))
+#define __opcode_thumb32_compose(first, second) ( \
+ (___opcode_identity32(___opcode_identity16(first)) << 16) \
+ | ___opcode_identity32(___opcode_identity16(second)) \
+)
+#define ___asm_opcode_thumb32_first(x) (___asm_opcode_identity16((x) >> 16))
+#define ___asm_opcode_thumb32_second(x) (___asm_opcode_identity16(x))
+#define ___asm_opcode_thumb32_compose(first, second) ( \
+ (___asm_opcode_identity32(___asm_opcode_identity16(first)) << 16) \
+ | ___asm_opcode_identity32(___asm_opcode_identity16(second)) \
+)
+
+/*
+ * Opcode injection helpers
+ *
+ * In rare cases it is necessary to assemble an opcode which the
+ * assembler does not support directly, or which would normally be
+ * rejected because of the CFLAGS or AFLAGS used to build the affected
+ * file.
+ *
+ * Before using these macros, consider carefully whether it is feasible
+ * instead to change the build flags for your file, or whether it really
+ * makes sense to support old assembler versions when building that
+ * particular kernel feature.
+ *
+ * The macros defined here should only be used where there is no viable
+ * alternative.
+ *
+ *
+ * __inst_arm(x): emit the specified ARM opcode
+ * __inst_thumb16(x): emit the specified 16-bit Thumb opcode
+ * __inst_thumb32(x): emit the specified 32-bit Thumb opcode
+ *
+ * __inst_arm_thumb16(arm, thumb): emit either the specified arm or
+ * 16-bit Thumb opcode, depending on whether an ARM or Thumb-2
+ * kernel is being built
+ *
+ * __inst_arm_thumb32(arm, thumb): emit either the specified arm or
+ * 32-bit Thumb opcode, depending on whether an ARM or Thumb-2
+ * kernel is being built
+ *
+ *
+ * Note that using these macros directly is poor practice. Instead, you
+ * should use them to define human-readable wrapper macros to encode the
+ * instructions that you care about. In code which might run on ARMv7 or
+ * above, you can usually use the __inst_arm_thumb{16,32} macros to
+ * specify the ARM and Thumb alternatives at the same time. This ensures
+ * that the correct opcode gets emitted depending on the instruction set
+ * used for the kernel build.
+ *
+ * Look at opcodes-virt.h for an example of how to use these macros.
+ */
+#include <linux/stringify.h>
+
+#define __inst_arm(x) ___inst_arm(___asm_opcode_to_mem_arm(x))
+#define __inst_thumb32(x) ___inst_thumb32( \
+ ___asm_opcode_to_mem_thumb16(___asm_opcode_thumb32_first(x)), \
+ ___asm_opcode_to_mem_thumb16(___asm_opcode_thumb32_second(x)) \
+)
+#define __inst_thumb16(x) ___inst_thumb16(___asm_opcode_to_mem_thumb16(x))
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define __inst_arm_thumb16(arm_opcode, thumb_opcode) \
+ __inst_thumb16(thumb_opcode)
+#define __inst_arm_thumb32(arm_opcode, thumb_opcode) \
+ __inst_thumb32(thumb_opcode)
+#else
+#define __inst_arm_thumb16(arm_opcode, thumb_opcode) __inst_arm(arm_opcode)
+#define __inst_arm_thumb32(arm_opcode, thumb_opcode) __inst_arm(arm_opcode)
+#endif
+
+/* Helpers for the helpers. Don't use these directly. */
+#ifdef __ASSEMBLY__
+#define ___inst_arm(x) .long x
+#define ___inst_thumb16(x) .short x
+#define ___inst_thumb32(first, second) .short first, second
+#else
+#define ___inst_arm(x) ".long " __stringify(x) "\n\t"
+#define ___inst_thumb16(x) ".short " __stringify(x) "\n\t"
+#define ___inst_thumb32(first, second) \
+ ".short " __stringify(first) ", " __stringify(second) "\n\t"
+#endif
+
+#endif /* __ASM_ARM_OPCODES_H */
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h
index 4489615..4e94424 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-3level-types.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
#define __ASM_PGTABLE_3LEVEL_TYPES_H
+#include <asm/types.h>
+
typedef u64 pteval_t;
typedef u64 pmdval_t;
typedef u64 pgdval_t;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 75fd13d..7eeed1a 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -92,5 +92,6 @@
#define TCR_TG1_64K (UL(1) << 30)
#define TCR_IPS_40BIT (UL(2) << 32)
#define TCR_ASID16 (UL(1) << 36)
+#define TCR_TBI0 (UL(1) << 37)
#endif
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ab239b2..3b7bb03 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -131,8 +131,8 @@
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
-#define KSTK_EIP(tsk) task_pt_regs(tsk)->pc
-#define KSTK_ESP(tsk) task_pt_regs(tsk)->sp
+#define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk))
/*
* Prefetching support
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 7257c36..33d3001 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -60,6 +60,15 @@
#define COMPAT_PT_TEXT_ADDR 0x10000
#define COMPAT_PT_DATA_ADDR 0x10004
#define COMPAT_PT_TEXT_END_ADDR 0x10008
+
+/*
+ * used to skip a system call when tracer changes its number to -1
+ * with ptrace(PTRACE_SET_SYSCALL)
+ */
+#define RET_SKIP_SYSCALL -1
+#define RET_SKIP_SYSCALL_TRACE -2
+#define IS_SKIP_SYSCALL(no) ((int)(no & 0xffffffff) == -1)
+
#ifndef __ASSEMBLY__
/* sizeof(struct user) for AArch32 */
@@ -131,7 +140,12 @@
(!((regs)->pstate & PSR_F_BIT))
#define user_stack_pointer(regs) \
- ((regs)->sp)
+ (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+ return regs->regs[0];
+}
/*
* Are the current registers suitable for user mode? (used to maintain
@@ -171,7 +185,13 @@
#define profile_pc(regs) instruction_pointer(regs)
#endif
-extern int aarch32_break_trap(struct pt_regs *regs);
+/*
+ * True if instr is a 32-bit thumb instruction. This works if instr
+ * is the first or only half-word of a thumb instruction. It also works
+ * when instr holds all 32-bits of a wide thumb instruction if stored
+ * in the form (first_half<<16)|(second_half)
+ */
+#define is_wide_instruction(instr) ((unsigned)(instr) >= 0xe800)
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h
new file mode 100644
index 0000000..bec3a43
--- /dev/null
+++ b/arch/arm64/include/asm/seccomp.h
@@ -0,0 +1,25 @@
+/*
+ * arch/arm64/include/asm/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi <at> linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#ifdef CONFIG_COMPAT
+#define __NR_seccomp_read_32 __NR_compat_read
+#define __NR_seccomp_write_32 __NR_compat_write
+#define __NR_seccomp_exit_32 __NR_compat_exit
+#define __NR_seccomp_sigreturn_32 __NR_compat_rt_sigreturn
+#endif /* CONFIG_COMPAT */
+
+#include <asm-generic/seccomp.h>
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 70ba9d4..35cfb7e 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -16,6 +16,8 @@
#ifndef __ASM_SYSCALL_H
#define __ASM_SYSCALL_H
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
#include <linux/err.h>
@@ -104,4 +106,16 @@
memcpy(®s->regs[i], args, n * sizeof(args[0]));
}
+/*
+ * We don't care about endianness (__AUDIT_ARCH_LE bit) here because
+ * AArch64 has the same system calls both on little- and big- endian.
+ */
+static inline int syscall_get_arch(void)
+{
+ if (is_compat_task())
+ return AUDIT_ARCH_ARM;
+
+ return AUDIT_ARCH_AARCH64;
+}
+
#endif /* __ASM_SYSCALL_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 23a3c47..c09cbf6 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -97,6 +97,9 @@
/*
* thread information flags:
* TIF_SYSCALL_TRACE - syscall trace active
+ * TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace
+ * TIF_SYSCALL_AUDIT - syscall auditing
+ * TIF_SECOMP - syscall secure computing
* TIF_SIGPENDING - signal pending
* TIF_NEED_RESCHED - rescheduling necessary
* TIF_NOTIFY_RESUME - callback before returning to user
@@ -106,7 +109,11 @@
#define TIF_SIGPENDING 0
#define TIF_NEED_RESCHED 1
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
+#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
#define TIF_SYSCALL_TRACE 8
+#define TIF_SYSCALL_AUDIT 9
+#define TIF_SYSCALL_TRACEPOINT 10
+#define TIF_SECCOMP 11
#define TIF_POLLING_NRFLAG 16
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_FREEZE 19
@@ -118,10 +125,18 @@
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_32BIT (1 << TIF_32BIT)
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- _TIF_NOTIFY_RESUME)
+ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+
+#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
#endif /* __KERNEL__ */
#endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 10ca8ff..75f51ea 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -18,6 +18,19 @@
#ifndef __ASM_TRAP_H
#define __ASM_TRAP_H
+#include <linux/list.h>
+
+struct undef_hook {
+ struct list_head node;
+ u32 instr_mask;
+ u32 instr_val;
+ u32 pstate_mask;
+ u32 pstate_val;
+ int (*fn)(struct pt_regs *regs, unsigned int instr);
+};
+
+void register_undef_hook(struct undef_hook *hook);
+
static inline int in_exception_text(unsigned long ptr)
{
extern char __exception_text_start[];
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217..2a3957f 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -25,6 +25,26 @@
#define __ARCH_WANT_COMPAT_SYS_SENDFILE
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
+
+/*
+ * Compat syscall numbers used by the AArch64 kernel.
+ */
+#define __NR_compat_restart_syscall 0
+#define __NR_compat_exit 1
+#define __NR_compat_read 3
+#define __NR_compat_write 4
+#define __NR_compat_sigreturn 119
+#define __NR_compat_rt_sigreturn 173
+
+/*
+ * The following SVCs are ARM private.
+ */
+#define __ARM_NR_COMPAT_BASE 0x0f0000
+#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
+#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
+
+#define __NR_compat_syscalls 384
#endif
+
#define __ARCH_WANT_SYS_CLONE
#include <uapi/asm/unistd.h>
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 58125bf..76d0945 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -21,399 +21,771 @@
#define __SYSCALL(x, y)
#endif
-__SYSCALL(0, sys_restart_syscall)
-__SYSCALL(1, sys_exit)
-__SYSCALL(2, sys_fork)
-__SYSCALL(3, sys_read)
-__SYSCALL(4, sys_write)
-__SYSCALL(5, compat_sys_open)
-__SYSCALL(6, sys_close)
-__SYSCALL(7, sys_ni_syscall) /* 7 was sys_waitpid */
-__SYSCALL(8, sys_creat)
-__SYSCALL(9, sys_link)
-__SYSCALL(10, sys_unlink)
-__SYSCALL(11, compat_sys_execve)
-__SYSCALL(12, sys_chdir)
-__SYSCALL(13, sys_ni_syscall) /* 13 was sys_time */
-__SYSCALL(14, sys_mknod)
-__SYSCALL(15, sys_chmod)
-__SYSCALL(16, sys_lchown16)
-__SYSCALL(17, sys_ni_syscall) /* 17 was sys_break */
-__SYSCALL(18, sys_ni_syscall) /* 18 was sys_stat */
-__SYSCALL(19, compat_sys_lseek)
-__SYSCALL(20, sys_getpid)
-__SYSCALL(21, compat_sys_mount)
-__SYSCALL(22, sys_ni_syscall) /* 22 was sys_umount */
-__SYSCALL(23, sys_setuid16)
-__SYSCALL(24, sys_getuid16)
-__SYSCALL(25, sys_ni_syscall) /* 25 was sys_stime */
-__SYSCALL(26, compat_sys_ptrace)
-__SYSCALL(27, sys_ni_syscall) /* 27 was sys_alarm */
-__SYSCALL(28, sys_ni_syscall) /* 28 was sys_fstat */
-__SYSCALL(29, sys_pause)
-__SYSCALL(30, sys_ni_syscall) /* 30 was sys_utime */
-__SYSCALL(31, sys_ni_syscall) /* 31 was sys_stty */
-__SYSCALL(32, sys_ni_syscall) /* 32 was sys_gtty */
-__SYSCALL(33, sys_access)
-__SYSCALL(34, sys_nice)
-__SYSCALL(35, sys_ni_syscall) /* 35 was sys_ftime */
-__SYSCALL(36, sys_sync)
-__SYSCALL(37, sys_kill)
-__SYSCALL(38, sys_rename)
-__SYSCALL(39, sys_mkdir)
-__SYSCALL(40, sys_rmdir)
-__SYSCALL(41, sys_dup)
-__SYSCALL(42, sys_pipe)
-__SYSCALL(43, compat_sys_times)
-__SYSCALL(44, sys_ni_syscall) /* 44 was sys_prof */
-__SYSCALL(45, sys_brk)
-__SYSCALL(46, sys_setgid16)
-__SYSCALL(47, sys_getgid16)
-__SYSCALL(48, sys_ni_syscall) /* 48 was sys_signal */
-__SYSCALL(49, sys_geteuid16)
-__SYSCALL(50, sys_getegid16)
-__SYSCALL(51, sys_acct)
-__SYSCALL(52, sys_umount)
-__SYSCALL(53, sys_ni_syscall) /* 53 was sys_lock */
-__SYSCALL(54, compat_sys_ioctl)
-__SYSCALL(55, compat_sys_fcntl)
-__SYSCALL(56, sys_ni_syscall) /* 56 was sys_mpx */
-__SYSCALL(57, sys_setpgid)
-__SYSCALL(58, sys_ni_syscall) /* 58 was sys_ulimit */
-__SYSCALL(59, sys_ni_syscall) /* 59 was sys_olduname */
-__SYSCALL(60, sys_umask)
-__SYSCALL(61, sys_chroot)
-__SYSCALL(62, compat_sys_ustat)
-__SYSCALL(63, sys_dup2)
-__SYSCALL(64, sys_getppid)
-__SYSCALL(65, sys_getpgrp)
-__SYSCALL(66, sys_setsid)
-__SYSCALL(67, compat_sys_sigaction)
-__SYSCALL(68, sys_ni_syscall) /* 68 was sys_sgetmask */
-__SYSCALL(69, sys_ni_syscall) /* 69 was sys_ssetmask */
-__SYSCALL(70, sys_setreuid16)
-__SYSCALL(71, sys_setregid16)
-__SYSCALL(72, sys_sigsuspend)
-__SYSCALL(73, compat_sys_sigpending)
-__SYSCALL(74, sys_sethostname)
-__SYSCALL(75, compat_sys_setrlimit)
-__SYSCALL(76, sys_ni_syscall) /* 76 was compat_sys_getrlimit */
-__SYSCALL(77, compat_sys_getrusage)
-__SYSCALL(78, compat_sys_gettimeofday)
-__SYSCALL(79, compat_sys_settimeofday)
-__SYSCALL(80, sys_getgroups16)
-__SYSCALL(81, sys_setgroups16)
-__SYSCALL(82, sys_ni_syscall) /* 82 was compat_sys_select */
-__SYSCALL(83, sys_symlink)
-__SYSCALL(84, sys_ni_syscall) /* 84 was sys_lstat */
-__SYSCALL(85, sys_readlink)
-__SYSCALL(86, sys_uselib)
-__SYSCALL(87, sys_swapon)
-__SYSCALL(88, sys_reboot)
-__SYSCALL(89, sys_ni_syscall) /* 89 was sys_readdir */
-__SYSCALL(90, sys_ni_syscall) /* 90 was sys_mmap */
-__SYSCALL(91, sys_munmap)
-__SYSCALL(92, compat_sys_truncate)
-__SYSCALL(93, compat_sys_ftruncate)
-__SYSCALL(94, sys_fchmod)
-__SYSCALL(95, sys_fchown16)
-__SYSCALL(96, sys_getpriority)
-__SYSCALL(97, sys_setpriority)
-__SYSCALL(98, sys_ni_syscall) /* 98 was sys_profil */
-__SYSCALL(99, compat_sys_statfs)
-__SYSCALL(100, compat_sys_fstatfs)
-__SYSCALL(101, sys_ni_syscall) /* 101 was sys_ioperm */
-__SYSCALL(102, sys_ni_syscall) /* 102 was sys_socketcall */
-__SYSCALL(103, sys_syslog)
-__SYSCALL(104, compat_sys_setitimer)
-__SYSCALL(105, compat_sys_getitimer)
-__SYSCALL(106, compat_sys_newstat)
-__SYSCALL(107, compat_sys_newlstat)
-__SYSCALL(108, compat_sys_newfstat)
-__SYSCALL(109, sys_ni_syscall) /* 109 was sys_uname */
-__SYSCALL(110, sys_ni_syscall) /* 110 was sys_iopl */
-__SYSCALL(111, sys_vhangup)
-__SYSCALL(112, sys_ni_syscall) /* 112 was sys_idle */
-__SYSCALL(113, sys_ni_syscall) /* 113 was sys_syscall */
-__SYSCALL(114, compat_sys_wait4)
-__SYSCALL(115, sys_swapoff)
-__SYSCALL(116, compat_sys_sysinfo)
-__SYSCALL(117, sys_ni_syscall) /* 117 was sys_ipc */
-__SYSCALL(118, sys_fsync)
-__SYSCALL(119, compat_sys_sigreturn_wrapper)
-__SYSCALL(120, sys_clone)
-__SYSCALL(121, sys_setdomainname)
-__SYSCALL(122, sys_newuname)
-__SYSCALL(123, sys_ni_syscall) /* 123 was sys_modify_ldt */
-__SYSCALL(124, compat_sys_adjtimex)
-__SYSCALL(125, sys_mprotect)
-__SYSCALL(126, compat_sys_sigprocmask)
-__SYSCALL(127, sys_ni_syscall) /* 127 was sys_create_module */
-__SYSCALL(128, sys_init_module)
-__SYSCALL(129, sys_delete_module)
-__SYSCALL(130, sys_ni_syscall) /* 130 was sys_get_kernel_syms */
-__SYSCALL(131, sys_quotactl)
-__SYSCALL(132, sys_getpgid)
-__SYSCALL(133, sys_fchdir)
-__SYSCALL(134, sys_bdflush)
-__SYSCALL(135, sys_sysfs)
-__SYSCALL(136, sys_personality)
-__SYSCALL(137, sys_ni_syscall) /* 137 was sys_afs_syscall */
-__SYSCALL(138, sys_setfsuid16)
-__SYSCALL(139, sys_setfsgid16)
-__SYSCALL(140, sys_llseek)
-__SYSCALL(141, compat_sys_getdents)
-__SYSCALL(142, compat_sys_select)
-__SYSCALL(143, sys_flock)
-__SYSCALL(144, sys_msync)
-__SYSCALL(145, compat_sys_readv)
-__SYSCALL(146, compat_sys_writev)
-__SYSCALL(147, sys_getsid)
-__SYSCALL(148, sys_fdatasync)
-__SYSCALL(149, compat_sys_sysctl)
-__SYSCALL(150, sys_mlock)
-__SYSCALL(151, sys_munlock)
-__SYSCALL(152, sys_mlockall)
-__SYSCALL(153, sys_munlockall)
-__SYSCALL(154, sys_sched_setparam)
-__SYSCALL(155, sys_sched_getparam)
-__SYSCALL(156, sys_sched_setscheduler)
-__SYSCALL(157, sys_sched_getscheduler)
-__SYSCALL(158, sys_sched_yield)
-__SYSCALL(159, sys_sched_get_priority_max)
-__SYSCALL(160, sys_sched_get_priority_min)
-__SYSCALL(161, compat_sys_sched_rr_get_interval)
-__SYSCALL(162, compat_sys_nanosleep)
-__SYSCALL(163, sys_mremap)
-__SYSCALL(164, sys_setresuid16)
-__SYSCALL(165, sys_getresuid16)
-__SYSCALL(166, sys_ni_syscall) /* 166 was sys_vm86 */
-__SYSCALL(167, sys_ni_syscall) /* 167 was sys_query_module */
-__SYSCALL(168, sys_poll)
-__SYSCALL(169, sys_ni_syscall)
-__SYSCALL(170, sys_setresgid16)
-__SYSCALL(171, sys_getresgid16)
-__SYSCALL(172, sys_prctl)
-__SYSCALL(173, compat_sys_rt_sigreturn_wrapper)
-__SYSCALL(174, compat_sys_rt_sigaction)
-__SYSCALL(175, compat_sys_rt_sigprocmask)
-__SYSCALL(176, compat_sys_rt_sigpending)
-__SYSCALL(177, compat_sys_rt_sigtimedwait)
-__SYSCALL(178, compat_sys_rt_sigqueueinfo)
-__SYSCALL(179, compat_sys_rt_sigsuspend)
-__SYSCALL(180, compat_sys_pread64_wrapper)
-__SYSCALL(181, compat_sys_pwrite64_wrapper)
-__SYSCALL(182, sys_chown16)
-__SYSCALL(183, sys_getcwd)
-__SYSCALL(184, sys_capget)
-__SYSCALL(185, sys_capset)
-__SYSCALL(186, compat_sys_sigaltstack)
-__SYSCALL(187, compat_sys_sendfile)
-__SYSCALL(188, sys_ni_syscall) /* 188 reserved */
-__SYSCALL(189, sys_ni_syscall) /* 189 reserved */
-__SYSCALL(190, sys_vfork)
-__SYSCALL(191, compat_sys_getrlimit) /* SuS compliant getrlimit */
-__SYSCALL(192, sys_mmap_pgoff)
-__SYSCALL(193, compat_sys_truncate64_wrapper)
-__SYSCALL(194, compat_sys_ftruncate64_wrapper)
-__SYSCALL(195, sys_stat64)
-__SYSCALL(196, sys_lstat64)
-__SYSCALL(197, sys_fstat64)
-__SYSCALL(198, sys_lchown)
-__SYSCALL(199, sys_getuid)
-__SYSCALL(200, sys_getgid)
-__SYSCALL(201, sys_geteuid)
-__SYSCALL(202, sys_getegid)
-__SYSCALL(203, sys_setreuid)
-__SYSCALL(204, sys_setregid)
-__SYSCALL(205, sys_getgroups)
-__SYSCALL(206, sys_setgroups)
-__SYSCALL(207, sys_fchown)
-__SYSCALL(208, sys_setresuid)
-__SYSCALL(209, sys_getresuid)
-__SYSCALL(210, sys_setresgid)
-__SYSCALL(211, sys_getresgid)
-__SYSCALL(212, sys_chown)
-__SYSCALL(213, sys_setuid)
-__SYSCALL(214, sys_setgid)
-__SYSCALL(215, sys_setfsuid)
-__SYSCALL(216, sys_setfsgid)
-__SYSCALL(217, compat_sys_getdents64)
-__SYSCALL(218, sys_pivot_root)
-__SYSCALL(219, sys_mincore)
-__SYSCALL(220, sys_madvise)
-__SYSCALL(221, compat_sys_fcntl64)
-__SYSCALL(222, sys_ni_syscall) /* 222 for tux */
-__SYSCALL(223, sys_ni_syscall) /* 223 is unused */
-__SYSCALL(224, sys_gettid)
-__SYSCALL(225, compat_sys_readahead_wrapper)
-__SYSCALL(226, sys_setxattr)
-__SYSCALL(227, sys_lsetxattr)
-__SYSCALL(228, sys_fsetxattr)
-__SYSCALL(229, sys_getxattr)
-__SYSCALL(230, sys_lgetxattr)
-__SYSCALL(231, sys_fgetxattr)
-__SYSCALL(232, sys_listxattr)
-__SYSCALL(233, sys_llistxattr)
-__SYSCALL(234, sys_flistxattr)
-__SYSCALL(235, sys_removexattr)
-__SYSCALL(236, sys_lremovexattr)
-__SYSCALL(237, sys_fremovexattr)
-__SYSCALL(238, sys_tkill)
-__SYSCALL(239, sys_sendfile64)
-__SYSCALL(240, compat_sys_futex)
-__SYSCALL(241, compat_sys_sched_setaffinity)
-__SYSCALL(242, compat_sys_sched_getaffinity)
-__SYSCALL(243, compat_sys_io_setup)
-__SYSCALL(244, sys_io_destroy)
-__SYSCALL(245, compat_sys_io_getevents)
-__SYSCALL(246, compat_sys_io_submit)
-__SYSCALL(247, sys_io_cancel)
-__SYSCALL(248, sys_exit_group)
-__SYSCALL(249, compat_sys_lookup_dcookie)
-__SYSCALL(250, sys_epoll_create)
-__SYSCALL(251, sys_epoll_ctl)
-__SYSCALL(252, sys_epoll_wait)
-__SYSCALL(253, sys_remap_file_pages)
-__SYSCALL(254, sys_ni_syscall) /* 254 for set_thread_area */
-__SYSCALL(255, sys_ni_syscall) /* 255 for get_thread_area */
-__SYSCALL(256, sys_set_tid_address)
-__SYSCALL(257, compat_sys_timer_create)
-__SYSCALL(258, compat_sys_timer_settime)
-__SYSCALL(259, compat_sys_timer_gettime)
-__SYSCALL(260, sys_timer_getoverrun)
-__SYSCALL(261, sys_timer_delete)
-__SYSCALL(262, compat_sys_clock_settime)
-__SYSCALL(263, compat_sys_clock_gettime)
-__SYSCALL(264, compat_sys_clock_getres)
-__SYSCALL(265, compat_sys_clock_nanosleep)
-__SYSCALL(266, compat_sys_statfs64_wrapper)
-__SYSCALL(267, compat_sys_fstatfs64_wrapper)
-__SYSCALL(268, sys_tgkill)
-__SYSCALL(269, compat_sys_utimes)
-__SYSCALL(270, compat_sys_fadvise64_64_wrapper)
-__SYSCALL(271, sys_pciconfig_iobase)
-__SYSCALL(272, sys_pciconfig_read)
-__SYSCALL(273, sys_pciconfig_write)
-__SYSCALL(274, compat_sys_mq_open)
-__SYSCALL(275, sys_mq_unlink)
-__SYSCALL(276, compat_sys_mq_timedsend)
-__SYSCALL(277, compat_sys_mq_timedreceive)
-__SYSCALL(278, compat_sys_mq_notify)
-__SYSCALL(279, compat_sys_mq_getsetattr)
-__SYSCALL(280, compat_sys_waitid)
-__SYSCALL(281, sys_socket)
-__SYSCALL(282, sys_bind)
-__SYSCALL(283, sys_connect)
-__SYSCALL(284, sys_listen)
-__SYSCALL(285, sys_accept)
-__SYSCALL(286, sys_getsockname)
-__SYSCALL(287, sys_getpeername)
-__SYSCALL(288, sys_socketpair)
-__SYSCALL(289, sys_send)
-__SYSCALL(290, sys_sendto)
-__SYSCALL(291, compat_sys_recv)
-__SYSCALL(292, compat_sys_recvfrom)
-__SYSCALL(293, sys_shutdown)
-__SYSCALL(294, compat_sys_setsockopt)
-__SYSCALL(295, compat_sys_getsockopt)
-__SYSCALL(296, compat_sys_sendmsg)
-__SYSCALL(297, compat_sys_recvmsg)
-__SYSCALL(298, sys_semop)
-__SYSCALL(299, sys_semget)
-__SYSCALL(300, compat_sys_semctl)
-__SYSCALL(301, compat_sys_msgsnd)
-__SYSCALL(302, compat_sys_msgrcv)
-__SYSCALL(303, sys_msgget)
-__SYSCALL(304, compat_sys_msgctl)
-__SYSCALL(305, compat_sys_shmat)
-__SYSCALL(306, sys_shmdt)
-__SYSCALL(307, sys_shmget)
-__SYSCALL(308, compat_sys_shmctl)
-__SYSCALL(309, sys_add_key)
-__SYSCALL(310, sys_request_key)
-__SYSCALL(311, compat_sys_keyctl)
-__SYSCALL(312, compat_sys_semtimedop)
-__SYSCALL(313, sys_ni_syscall)
-__SYSCALL(314, sys_ioprio_set)
-__SYSCALL(315, sys_ioprio_get)
-__SYSCALL(316, sys_inotify_init)
-__SYSCALL(317, sys_inotify_add_watch)
-__SYSCALL(318, sys_inotify_rm_watch)
-__SYSCALL(319, compat_sys_mbind)
-__SYSCALL(320, compat_sys_get_mempolicy)
-__SYSCALL(321, compat_sys_set_mempolicy)
-__SYSCALL(322, compat_sys_openat)
-__SYSCALL(323, sys_mkdirat)
-__SYSCALL(324, sys_mknodat)
-__SYSCALL(325, sys_fchownat)
-__SYSCALL(326, compat_sys_futimesat)
-__SYSCALL(327, sys_fstatat64)
-__SYSCALL(328, sys_unlinkat)
-__SYSCALL(329, sys_renameat)
-__SYSCALL(330, sys_linkat)
-__SYSCALL(331, sys_symlinkat)
-__SYSCALL(332, sys_readlinkat)
-__SYSCALL(333, sys_fchmodat)
-__SYSCALL(334, sys_faccessat)
-__SYSCALL(335, compat_sys_pselect6)
-__SYSCALL(336, compat_sys_ppoll)
-__SYSCALL(337, sys_unshare)
-__SYSCALL(338, compat_sys_set_robust_list)
-__SYSCALL(339, compat_sys_get_robust_list)
-__SYSCALL(340, sys_splice)
-__SYSCALL(341, compat_sys_sync_file_range2_wrapper)
-__SYSCALL(342, sys_tee)
-__SYSCALL(343, compat_sys_vmsplice)
-__SYSCALL(344, compat_sys_move_pages)
-__SYSCALL(345, sys_getcpu)
-__SYSCALL(346, compat_sys_epoll_pwait)
-__SYSCALL(347, compat_sys_kexec_load)
-__SYSCALL(348, compat_sys_utimensat)
-__SYSCALL(349, compat_sys_signalfd)
-__SYSCALL(350, sys_timerfd_create)
-__SYSCALL(351, sys_eventfd)
-__SYSCALL(352, compat_sys_fallocate_wrapper)
-__SYSCALL(353, compat_sys_timerfd_settime)
-__SYSCALL(354, compat_sys_timerfd_gettime)
-__SYSCALL(355, compat_sys_signalfd4)
-__SYSCALL(356, sys_eventfd2)
-__SYSCALL(357, sys_epoll_create1)
-__SYSCALL(358, sys_dup3)
-__SYSCALL(359, sys_pipe2)
-__SYSCALL(360, sys_inotify_init1)
-__SYSCALL(361, compat_sys_preadv)
-__SYSCALL(362, compat_sys_pwritev)
-__SYSCALL(363, compat_sys_rt_tgsigqueueinfo)
-__SYSCALL(364, sys_perf_event_open)
-__SYSCALL(365, compat_sys_recvmmsg)
-__SYSCALL(366, sys_accept4)
-__SYSCALL(367, sys_fanotify_init)
-__SYSCALL(368, compat_sys_fanotify_mark)
-__SYSCALL(369, sys_prlimit64)
-__SYSCALL(370, sys_name_to_handle_at)
-__SYSCALL(371, compat_sys_open_by_handle_at)
-__SYSCALL(372, compat_sys_clock_adjtime)
-__SYSCALL(373, sys_syncfs)
-__SYSCALL(374, compat_sys_sendmmsg)
-__SYSCALL(375, sys_setns)
-__SYSCALL(376, compat_sys_process_vm_readv)
-__SYSCALL(377, compat_sys_process_vm_writev)
-__SYSCALL(378, sys_ni_syscall) /* 378 for kcmp */
-
-#define __NR_compat_syscalls 379
-
-/*
- * Compat syscall numbers used by the AArch64 kernel.
- */
-#define __NR_compat_restart_syscall 0
-#define __NR_compat_sigreturn 119
-#define __NR_compat_rt_sigreturn 173
-
-
-/*
- * The following SVCs are ARM private.
- */
-#define __ARM_NR_COMPAT_BASE 0x0f0000
-#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
-#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
+#define __NR_restart_syscall 0
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_exit 1
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_fork 2
+__SYSCALL(__NR_fork, sys_fork)
+#define __NR_read 3
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 4
+__SYSCALL(__NR_write, sys_write)
+#define __NR_open 5
+__SYSCALL(__NR_open, compat_sys_open)
+#define __NR_close 6
+__SYSCALL(__NR_close, sys_close)
+ /* 7 was sys_waitpid */
+__SYSCALL(7, sys_ni_syscall)
+#define __NR_creat 8
+__SYSCALL(__NR_creat, sys_creat)
+#define __NR_link 9
+__SYSCALL(__NR_link, sys_link)
+#define __NR_unlink 10
+__SYSCALL(__NR_unlink, sys_unlink)
+#define __NR_execve 11
+__SYSCALL(__NR_execve, compat_sys_execve)
+#define __NR_chdir 12
+__SYSCALL(__NR_chdir, sys_chdir)
+ /* 13 was sys_time */
+__SYSCALL(13, sys_ni_syscall)
+#define __NR_mknod 14
+__SYSCALL(__NR_mknod, sys_mknod)
+#define __NR_chmod 15
+__SYSCALL(__NR_chmod, sys_chmod)
+#define __NR_lchown 16
+__SYSCALL(__NR_lchown, sys_lchown16)
+ /* 17 was sys_break */
+__SYSCALL(17, sys_ni_syscall)
+ /* 18 was sys_stat */
+__SYSCALL(18, sys_ni_syscall)
+#define __NR_lseek 19
+__SYSCALL(__NR_lseek, compat_sys_lseek)
+#define __NR_getpid 20
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_mount 21
+__SYSCALL(__NR_mount, compat_sys_mount)
+ /* 22 was sys_umount */
+__SYSCALL(22, sys_ni_syscall)
+#define __NR_setuid 23
+__SYSCALL(__NR_setuid, sys_setuid16)
+#define __NR_getuid 24
+__SYSCALL(__NR_getuid, sys_getuid16)
+ /* 25 was sys_stime */
+__SYSCALL(25, sys_ni_syscall)
+#define __NR_ptrace 26
+__SYSCALL(__NR_ptrace, compat_sys_ptrace)
+ /* 27 was sys_alarm */
+__SYSCALL(27, sys_ni_syscall)
+ /* 28 was sys_fstat */
+__SYSCALL(28, sys_ni_syscall)
+#define __NR_pause 29
+__SYSCALL(__NR_pause, sys_pause)
+ /* 30 was sys_utime */
+__SYSCALL(30, sys_ni_syscall)
+ /* 31 was sys_stty */
+__SYSCALL(31, sys_ni_syscall)
+ /* 32 was sys_gtty */
+__SYSCALL(32, sys_ni_syscall)
+#define __NR_access 33
+__SYSCALL(__NR_access, sys_access)
+#define __NR_nice 34
+__SYSCALL(__NR_nice, sys_nice)
+ /* 35 was sys_ftime */
+__SYSCALL(35, sys_ni_syscall)
+#define __NR_sync 36
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_kill 37
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_rename 38
+__SYSCALL(__NR_rename, sys_rename)
+#define __NR_mkdir 39
+__SYSCALL(__NR_mkdir, sys_mkdir)
+#define __NR_rmdir 40
+__SYSCALL(__NR_rmdir, sys_rmdir)
+#define __NR_dup 41
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_pipe 42
+__SYSCALL(__NR_pipe, sys_pipe)
+#define __NR_times 43
+__SYSCALL(__NR_times, compat_sys_times)
+ /* 44 was sys_prof */
+__SYSCALL(44, sys_ni_syscall)
+#define __NR_brk 45
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_setgid 46
+__SYSCALL(__NR_setgid, sys_setgid16)
+#define __NR_getgid 47
+__SYSCALL(__NR_getgid, sys_getgid16)
+ /* 48 was sys_signal */
+__SYSCALL(48, sys_ni_syscall)
+#define __NR_geteuid 49
+__SYSCALL(__NR_geteuid, sys_geteuid16)
+#define __NR_getegid 50
+__SYSCALL(__NR_getegid, sys_getegid16)
+#define __NR_acct 51
+__SYSCALL(__NR_acct, sys_acct)
+#define __NR_umount2 52
+__SYSCALL(__NR_umount2, sys_umount)
+ /* 53 was sys_lock */
+__SYSCALL(53, sys_ni_syscall)
+#define __NR_ioctl 54
+__SYSCALL(__NR_ioctl, compat_sys_ioctl)
+#define __NR_fcntl 55
+__SYSCALL(__NR_fcntl, compat_sys_fcntl)
+ /* 56 was sys_mpx */
+__SYSCALL(56, sys_ni_syscall)
+#define __NR_setpgid 57
+__SYSCALL(__NR_setpgid, sys_setpgid)
+ /* 58 was sys_ulimit */
+__SYSCALL(58, sys_ni_syscall)
+ /* 59 was sys_olduname */
+__SYSCALL(59, sys_ni_syscall)
+#define __NR_umask 60
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_chroot 61
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_ustat 62
+__SYSCALL(__NR_ustat, compat_sys_ustat)
+#define __NR_dup2 63
+__SYSCALL(__NR_dup2, sys_dup2)
+#define __NR_getppid 64
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getpgrp 65
+__SYSCALL(__NR_getpgrp, sys_getpgrp)
+#define __NR_setsid 66
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_sigaction 67
+__SYSCALL(__NR_sigaction, compat_sys_sigaction)
+ /* 68 was sys_sgetmask */
+__SYSCALL(68, sys_ni_syscall)
+ /* 69 was sys_ssetmask */
+__SYSCALL(69, sys_ni_syscall)
+#define __NR_setreuid 70
+__SYSCALL(__NR_setreuid, sys_setreuid16)
+#define __NR_setregid 71
+__SYSCALL(__NR_setregid, sys_setregid16)
+#define __NR_sigsuspend 72
+__SYSCALL(__NR_sigsuspend, sys_sigsuspend)
+#define __NR_sigpending 73
+__SYSCALL(__NR_sigpending, compat_sys_sigpending)
+#define __NR_sethostname 74
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setrlimit 75
+__SYSCALL(__NR_setrlimit, compat_sys_setrlimit)
+ /* 76 was compat_sys_getrlimit */
+__SYSCALL(76, sys_ni_syscall)
+#define __NR_getrusage 77
+__SYSCALL(__NR_getrusage, compat_sys_getrusage)
+#define __NR_gettimeofday 78
+__SYSCALL(__NR_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 79
+__SYSCALL(__NR_settimeofday, compat_sys_settimeofday)
+#define __NR_getgroups 80
+__SYSCALL(__NR_getgroups, sys_getgroups16)
+#define __NR_setgroups 81
+__SYSCALL(__NR_setgroups, sys_setgroups16)
+ /* 82 was compat_sys_select */
+__SYSCALL(82, sys_ni_syscall)
+#define __NR_symlink 83
+__SYSCALL(__NR_symlink, sys_symlink)
+ /* 84 was sys_lstat */
+__SYSCALL(84, sys_ni_syscall)
+#define __NR_readlink 85
+__SYSCALL(__NR_readlink, sys_readlink)
+#define __NR_uselib 86
+__SYSCALL(__NR_uselib, sys_uselib)
+#define __NR_swapon 87
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_reboot 88
+__SYSCALL(__NR_reboot, sys_reboot)
+ /* 89 was sys_readdir */
+__SYSCALL(89, sys_ni_syscall)
+ /* 90 was sys_mmap */
+__SYSCALL(90, sys_ni_syscall)
+#define __NR_munmap 91
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_truncate 92
+__SYSCALL(__NR_truncate, compat_sys_truncate)
+#define __NR_ftruncate 93
+__SYSCALL(__NR_ftruncate, compat_sys_ftruncate)
+#define __NR_fchmod 94
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchown 95
+__SYSCALL(__NR_fchown, sys_fchown16)
+#define __NR_getpriority 96
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_setpriority 97
+__SYSCALL(__NR_setpriority, sys_setpriority)
+ /* 98 was sys_profil */
+__SYSCALL(98, sys_ni_syscall)
+#define __NR_statfs 99
+__SYSCALL(__NR_statfs, compat_sys_statfs)
+#define __NR_fstatfs 100
+__SYSCALL(__NR_fstatfs, compat_sys_fstatfs)
+ /* 101 was sys_ioperm */
+__SYSCALL(101, sys_ni_syscall)
+ /* 102 was sys_socketcall */
+__SYSCALL(102, sys_ni_syscall)
+#define __NR_syslog 103
+__SYSCALL(__NR_syslog, sys_syslog)
+#define __NR_setitimer 104
+__SYSCALL(__NR_setitimer, compat_sys_setitimer)
+#define __NR_getitimer 105
+__SYSCALL(__NR_getitimer, compat_sys_getitimer)
+#define __NR_stat 106
+__SYSCALL(__NR_stat, compat_sys_newstat)
+#define __NR_lstat 107
+__SYSCALL(__NR_lstat, compat_sys_newlstat)
+#define __NR_fstat 108
+__SYSCALL(__NR_fstat, compat_sys_newfstat)
+ /* 109 was sys_uname */
+__SYSCALL(109, sys_ni_syscall)
+ /* 110 was sys_iopl */
+__SYSCALL(110, sys_ni_syscall)
+#define __NR_vhangup 111
+__SYSCALL(__NR_vhangup, sys_vhangup)
+ /* 112 was sys_idle */
+__SYSCALL(112, sys_ni_syscall)
+ /* 113 was sys_syscall */
+__SYSCALL(113, sys_ni_syscall)
+#define __NR_wait4 114
+__SYSCALL(__NR_wait4, compat_sys_wait4)
+#define __NR_swapoff 115
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_sysinfo 116
+__SYSCALL(__NR_sysinfo, compat_sys_sysinfo)
+ /* 117 was sys_ipc */
+__SYSCALL(117, sys_ni_syscall)
+#define __NR_fsync 118
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_sigreturn 119
+__SYSCALL(__NR_sigreturn, compat_sys_sigreturn_wrapper)
+#define __NR_clone 120
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_setdomainname 121
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_uname 122
+__SYSCALL(__NR_uname, sys_newuname)
+ /* 123 was sys_modify_ldt */
+__SYSCALL(123, sys_ni_syscall)
+#define __NR_adjtimex 124
+__SYSCALL(__NR_adjtimex, compat_sys_adjtimex)
+#define __NR_mprotect 125
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_sigprocmask 126
+__SYSCALL(__NR_sigprocmask, compat_sys_sigprocmask)
+ /* 127 was sys_create_module */
+__SYSCALL(127, sys_ni_syscall)
+#define __NR_init_module 128
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 129
+__SYSCALL(__NR_delete_module, sys_delete_module)
+ /* 130 was sys_get_kernel_syms */
+__SYSCALL(130, sys_ni_syscall)
+#define __NR_quotactl 131
+__SYSCALL(__NR_quotactl, sys_quotactl)
+#define __NR_getpgid 132
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_fchdir 133
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_bdflush 134
+__SYSCALL(__NR_bdflush, sys_bdflush)
+#define __NR_sysfs 135
+__SYSCALL(__NR_sysfs, sys_sysfs)
+#define __NR_personality 136
+__SYSCALL(__NR_personality, sys_personality)
+ /* 137 was sys_afs_syscall */
+__SYSCALL(137, sys_ni_syscall)
+#define __NR_setfsuid 138
+__SYSCALL(__NR_setfsuid, sys_setfsuid16)
+#define __NR_setfsgid 139
+__SYSCALL(__NR_setfsgid, sys_setfsgid16)
+#define __NR__llseek 140
+__SYSCALL(__NR__llseek, sys_llseek)
+#define __NR_getdents 141
+__SYSCALL(__NR_getdents, compat_sys_getdents)
+#define __NR__newselect 142
+__SYSCALL(__NR__newselect, compat_sys_select)
+#define __NR_flock 143
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_msync 144
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_readv 145
+__SYSCALL(__NR_readv, compat_sys_readv)
+#define __NR_writev 146
+__SYSCALL(__NR_writev, compat_sys_writev)
+#define __NR_getsid 147
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_fdatasync 148
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#define __NR__sysctl 149
+__SYSCALL(__NR__sysctl, compat_sys_sysctl)
+#define __NR_mlock 150
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 151
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 152
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 153
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_sched_setparam 154
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_getparam 155
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setscheduler 156
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 157
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_yield 158
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 159
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 160
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 161
+__SYSCALL(__NR_sched_rr_get_interval, compat_sys_sched_rr_get_interval)
+#define __NR_nanosleep 162
+__SYSCALL(__NR_nanosleep, compat_sys_nanosleep)
+#define __NR_mremap 163
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_setresuid 164
+__SYSCALL(__NR_setresuid, sys_setresuid16)
+#define __NR_getresuid 165
+__SYSCALL(__NR_getresuid, sys_getresuid16)
+ /* 166 was sys_vm86 */
+__SYSCALL(166, sys_ni_syscall)
+ /* 167 was sys_query_module */
+__SYSCALL(167, sys_ni_syscall)
+#define __NR_poll 168
+__SYSCALL(__NR_poll, sys_poll)
+#define __NR_nfsservctl 169
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+#define __NR_setresgid 170
+__SYSCALL(__NR_setresgid, sys_setresgid16)
+#define __NR_getresgid 171
+__SYSCALL(__NR_getresgid, sys_getresgid16)
+#define __NR_prctl 172
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_rt_sigreturn 173
+__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn_wrapper)
+#define __NR_rt_sigaction 174
+__SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 175
+__SYSCALL(__NR_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 176
+__SYSCALL(__NR_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 177
+__SYSCALL(__NR_rt_sigtimedwait, compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 178
+__SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigsuspend 179
+__SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_pread64 180
+__SYSCALL(__NR_pread64, compat_sys_pread64_wrapper)
+#define __NR_pwrite64 181
+__SYSCALL(__NR_pwrite64, compat_sys_pwrite64_wrapper)
+#define __NR_chown 182
+__SYSCALL(__NR_chown, sys_chown16)
+#define __NR_getcwd 183
+__SYSCALL(__NR_getcwd, sys_getcwd)
+#define __NR_capget 184
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 185
+__SYSCALL(__NR_capset, sys_capset)
+#define __NR_sigaltstack 186
+__SYSCALL(__NR_sigaltstack, compat_sys_sigaltstack)
+#define __NR_sendfile 187
+__SYSCALL(__NR_sendfile, compat_sys_sendfile)
+ /* 188 reserved */
+__SYSCALL(188, sys_ni_syscall)
+ /* 189 reserved */
+__SYSCALL(189, sys_ni_syscall)
+#define __NR_vfork 190
+__SYSCALL(__NR_vfork, sys_vfork)
+#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
+__SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit) /* SuS compliant getrlimit */
+#define __NR_mmap2 192
+__SYSCALL(__NR_mmap2, sys_mmap_pgoff)
+#define __NR_truncate64 193
+__SYSCALL(__NR_truncate64, compat_sys_truncate64_wrapper)
+#define __NR_ftruncate64 194
+__SYSCALL(__NR_ftruncate64, compat_sys_ftruncate64_wrapper)
+#define __NR_stat64 195
+__SYSCALL(__NR_stat64, sys_stat64)
+#define __NR_lstat64 196
+__SYSCALL(__NR_lstat64, sys_lstat64)
+#define __NR_fstat64 197
+__SYSCALL(__NR_fstat64, sys_fstat64)
+#define __NR_lchown32 198
+__SYSCALL(__NR_lchown32, sys_lchown)
+#define __NR_getuid32 199
+__SYSCALL(__NR_getuid32, sys_getuid)
+#define __NR_getgid32 200
+__SYSCALL(__NR_getgid32, sys_getgid)
+#define __NR_geteuid32 201
+__SYSCALL(__NR_geteuid32, sys_geteuid)
+#define __NR_getegid32 202
+__SYSCALL(__NR_getegid32, sys_getegid)
+#define __NR_setreuid32 203
+__SYSCALL(__NR_setreuid32, sys_setreuid)
+#define __NR_setregid32 204
+__SYSCALL(__NR_setregid32, sys_setregid)
+#define __NR_getgroups32 205
+__SYSCALL(__NR_getgroups32, sys_getgroups)
+#define __NR_setgroups32 206
+__SYSCALL(__NR_setgroups32, sys_setgroups)
+#define __NR_fchown32 207
+__SYSCALL(__NR_fchown32, sys_fchown)
+#define __NR_setresuid32 208
+__SYSCALL(__NR_setresuid32, sys_setresuid)
+#define __NR_getresuid32 209
+__SYSCALL(__NR_getresuid32, sys_getresuid)
+#define __NR_setresgid32 210
+__SYSCALL(__NR_setresgid32, sys_setresgid)
+#define __NR_getresgid32 211
+__SYSCALL(__NR_getresgid32, sys_getresgid)
+#define __NR_chown32 212
+__SYSCALL(__NR_chown32, sys_chown)
+#define __NR_setuid32 213
+__SYSCALL(__NR_setuid32, sys_setuid)
+#define __NR_setgid32 214
+__SYSCALL(__NR_setgid32, sys_setgid)
+#define __NR_setfsuid32 215
+__SYSCALL(__NR_setfsuid32, sys_setfsuid)
+#define __NR_setfsgid32 216
+__SYSCALL(__NR_setfsgid32, sys_setfsgid)
+#define __NR_getdents64 217
+__SYSCALL(__NR_getdents64, compat_sys_getdents64)
+#define __NR_pivot_root 218
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+#define __NR_mincore 219
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 220
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_fcntl64 221
+__SYSCALL(__NR_fcntl64, compat_sys_fcntl64)
+ /* 222 for tux */
+__SYSCALL(222, sys_ni_syscall)
+ /* 223 is unused */
+__SYSCALL(223, sys_ni_syscall)
+#define __NR_gettid 224
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_readahead 225
+__SYSCALL(__NR_readahead, compat_sys_readahead_wrapper)
+#define __NR_setxattr 226
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 227
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 228
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 229
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 230
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 231
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 232
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 233
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 234
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 235
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 236
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 237
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_tkill 238
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_sendfile64 239
+__SYSCALL(__NR_sendfile64, sys_sendfile64)
+#define __NR_futex 240
+__SYSCALL(__NR_futex, compat_sys_futex)
+#define __NR_sched_setaffinity 241
+__SYSCALL(__NR_sched_setaffinity, compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 242
+__SYSCALL(__NR_sched_getaffinity, compat_sys_sched_getaffinity)
+#define __NR_io_setup 243
+__SYSCALL(__NR_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 244
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_getevents 245
+__SYSCALL(__NR_io_getevents, compat_sys_io_getevents)
+#define __NR_io_submit 246
+__SYSCALL(__NR_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 247
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_exit_group 248
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_lookup_dcookie 249
+__SYSCALL(__NR_lookup_dcookie, compat_sys_lookup_dcookie)
+#define __NR_epoll_create 250
+__SYSCALL(__NR_epoll_create, sys_epoll_create)
+#define __NR_epoll_ctl 251
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_wait 252
+__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
+#define __NR_remap_file_pages 253
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+ /* 254 for set_thread_area */
+__SYSCALL(254, sys_ni_syscall)
+ /* 255 for get_thread_area */
+__SYSCALL(255, sys_ni_syscall)
+#define __NR_set_tid_address 256
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_timer_create 257
+__SYSCALL(__NR_timer_create, compat_sys_timer_create)
+#define __NR_timer_settime 258
+__SYSCALL(__NR_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_gettime 259
+__SYSCALL(__NR_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 260
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_delete 261
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 262
+__SYSCALL(__NR_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 263
+__SYSCALL(__NR_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 264
+__SYSCALL(__NR_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 265
+__SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep)
+#define __NR_statfs64 266
+__SYSCALL(__NR_statfs64, compat_sys_statfs64_wrapper)
+#define __NR_fstatfs64 267
+__SYSCALL(__NR_fstatfs64, compat_sys_fstatfs64_wrapper)
+#define __NR_tgkill 268
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_utimes 269
+__SYSCALL(__NR_utimes, compat_sys_utimes)
+#define __NR_arm_fadvise64_64 270
+__SYSCALL(__NR_arm_fadvise64_64, compat_sys_fadvise64_64_wrapper)
+#define __NR_pciconfig_iobase 271
+__SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase)
+#define __NR_pciconfig_read 272
+__SYSCALL(__NR_pciconfig_read, sys_pciconfig_read)
+#define __NR_pciconfig_write 273
+__SYSCALL(__NR_pciconfig_write, sys_pciconfig_write)
+#define __NR_mq_open 274
+__SYSCALL(__NR_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 275
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 276
+__SYSCALL(__NR_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 277
+__SYSCALL(__NR_mq_timedreceive, compat_sys_mq_timedreceive)
+#define __NR_mq_notify 278
+__SYSCALL(__NR_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 279
+__SYSCALL(__NR_mq_getsetattr, compat_sys_mq_getsetattr)
+#define __NR_waitid 280
+__SYSCALL(__NR_waitid, compat_sys_waitid)
+#define __NR_socket 281
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_bind 282
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_connect 283
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_listen 284
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 285
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_getsockname 286
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 287
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_socketpair 288
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_send 289
+__SYSCALL(__NR_send, sys_send)
+#define __NR_sendto 290
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recv 291
+__SYSCALL(__NR_recv, compat_sys_recv)
+#define __NR_recvfrom 292
+__SYSCALL(__NR_recvfrom, compat_sys_recvfrom)
+#define __NR_shutdown 293
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_setsockopt 294
+__SYSCALL(__NR_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 295
+__SYSCALL(__NR_getsockopt, compat_sys_getsockopt)
+#define __NR_sendmsg 296
+__SYSCALL(__NR_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 297
+__SYSCALL(__NR_recvmsg, compat_sys_recvmsg)
+#define __NR_semop 298
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_semget 299
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 300
+__SYSCALL(__NR_semctl, compat_sys_semctl)
+#define __NR_msgsnd 301
+__SYSCALL(__NR_msgsnd, compat_sys_msgsnd)
+#define __NR_msgrcv 302
+__SYSCALL(__NR_msgrcv, compat_sys_msgrcv)
+#define __NR_msgget 303
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 304
+__SYSCALL(__NR_msgctl, compat_sys_msgctl)
+#define __NR_shmat 305
+__SYSCALL(__NR_shmat, compat_sys_shmat)
+#define __NR_shmdt 306
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_shmget 307
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 308
+__SYSCALL(__NR_shmctl, compat_sys_shmctl)
+#define __NR_add_key 309
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 310
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 311
+__SYSCALL(__NR_keyctl, compat_sys_keyctl)
+#define __NR_semtimedop 312
+__SYSCALL(__NR_semtimedop, compat_sys_semtimedop)
+#define __NR_vserver 313
+__SYSCALL(__NR_vserver, sys_ni_syscall)
+#define __NR_ioprio_set 314
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 315
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_inotify_init 316
+__SYSCALL(__NR_inotify_init, sys_inotify_init)
+#define __NR_inotify_add_watch 317
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 318
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_mbind 319
+__SYSCALL(__NR_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 320
+__SYSCALL(__NR_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 321
+__SYSCALL(__NR_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_openat 322
+__SYSCALL(__NR_openat, compat_sys_openat)
+#define __NR_mkdirat 323
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat 324
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat 325
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat 326
+__SYSCALL(__NR_futimesat, compat_sys_futimesat)
+#define __NR_fstatat64 327
+__SYSCALL(__NR_fstatat64, sys_fstatat64)
+#define __NR_unlinkat 328
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat 329
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat 330
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat 331
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat 332
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat 333
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat 334
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_pselect6 335
+__SYSCALL(__NR_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 336
+__SYSCALL(__NR_ppoll, compat_sys_ppoll)
+#define __NR_unshare 337
+__SYSCALL(__NR_unshare, sys_unshare)
+#define __NR_set_robust_list 338
+__SYSCALL(__NR_set_robust_list, compat_sys_set_robust_list)
+#define __NR_get_robust_list 339
+__SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list)
+#define __NR_splice 340
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_sync_file_range2 341
+__SYSCALL(__NR_sync_file_range2, compat_sys_sync_file_range2_wrapper)
+#define __NR_tee 342
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_vmsplice 343
+__SYSCALL(__NR_vmsplice, compat_sys_vmsplice)
+#define __NR_move_pages 344
+__SYSCALL(__NR_move_pages, compat_sys_move_pages)
+#define __NR_getcpu 345
+__SYSCALL(__NR_getcpu, sys_getcpu)
+#define __NR_epoll_pwait 346
+__SYSCALL(__NR_epoll_pwait, compat_sys_epoll_pwait)
+#define __NR_kexec_load 347
+__SYSCALL(__NR_kexec_load, compat_sys_kexec_load)
+#define __NR_utimensat 348
+__SYSCALL(__NR_utimensat, compat_sys_utimensat)
+#define __NR_signalfd 349
+__SYSCALL(__NR_signalfd, compat_sys_signalfd)
+#define __NR_timerfd_create 350
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_eventfd 351
+__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate 352
+__SYSCALL(__NR_fallocate, compat_sys_fallocate_wrapper)
+#define __NR_timerfd_settime 353
+__SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 354
+__SYSCALL(__NR_timerfd_gettime, compat_sys_timerfd_gettime)
+#define __NR_signalfd4 355
+__SYSCALL(__NR_signalfd4, compat_sys_signalfd4)
+#define __NR_eventfd2 356
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1 357
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_dup3 358
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2 359
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_inotify_init1 360
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv 361
+__SYSCALL(__NR_preadv, compat_sys_preadv)
+#define __NR_pwritev 362
+__SYSCALL(__NR_pwritev, compat_sys_pwritev)
+#define __NR_rt_tgsigqueueinfo 363
+__SYSCALL(__NR_rt_tgsigqueueinfo, compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 364
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_recvmmsg 365
+__SYSCALL(__NR_recvmmsg, compat_sys_recvmmsg)
+#define __NR_accept4 366
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_fanotify_init 367
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 368
+__SYSCALL(__NR_fanotify_mark, compat_sys_fanotify_mark)
+#define __NR_prlimit64 369
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_name_to_handle_at 370
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 371
+__SYSCALL(__NR_open_by_handle_at, compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 372
+__SYSCALL(__NR_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 373
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_sendmmsg 374
+__SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg)
+#define __NR_setns 375
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_process_vm_readv 376
+__SYSCALL(__NR_process_vm_readv, compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 377
+__SYSCALL(__NR_process_vm_writev, compat_sys_process_vm_writev)
+#define __NR_kcmp 378
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 379
+__SYSCALL(__NR_finit_module, sys_finit_module)
+/* #define __NR_sched_setattr 380 */
+__SYSCALL(380, sys_ni_syscall)
+/* #define __NR_sched_getattr 381 */
+__SYSCALL(381, sys_ni_syscall)
+/* #define __NR_renameat2 382 */
+__SYSCALL(382, sys_ni_syscall)
+#define __NR_seccomp 383
+__SYSCALL(__NR_seccomp, sys_seccomp)
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index eea4975..73cf0f5 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -21,6 +21,11 @@
*/
#define HWCAP_FP (1 << 0)
#define HWCAP_ASIMD (1 << 1)
-
+#define HWCAP_EVTSTRM (1 << 2)
+#define HWCAP_AES (1 << 3)
+#define HWCAP_PMULL (1 << 4)
+#define HWCAP_SHA1 (1 << 5)
+#define HWCAP_SHA2 (1 << 6)
+#define HWCAP_CRC32 (1 << 7)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 6913643..49c6174 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -23,6 +23,7 @@
#include <asm/hwcap.h>
+#define PTRACE_SET_SYSCALL 23
/*
* PSR bits
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564..3e67066 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,15 +9,18 @@
arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \
entry-fpsimd.o process.o ptrace.o setup.o signal.o \
sys.o stacktrace.o time.o traps.o io.o vdso.o \
- hyp-stub.o psci.o
+ hyp-stub.o psci.o opcodes.o
-arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
+arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
sys_compat.o
arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o
arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o smp_psci.o
arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o
arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o
+
+obj-$(CONFIG_SWP_EMULATE) += swp_emulate.o
obj-y += $(arm64-obj-y) vdso/
obj-m += $(arm64-obj-m)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index f4726dc..1be679a 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -24,6 +24,7 @@
#include <linux/init.h>
#include <linux/ptrace.h>
#include <linux/stat.h>
+#include <linux/uaccess.h>
#include <asm/debug-monitors.h>
#include <asm/local.h>
@@ -144,7 +145,7 @@
unsigned long action, void *data)
{
int cpu = (unsigned long)data;
- if (action == CPU_ONLINE)
+ if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
smp_call_function_single(cpu, clear_os_lock, NULL, 1);
return NOTIFY_OK;
}
@@ -226,13 +227,74 @@
return 0;
}
-static int __init single_step_init(void)
+static int brk_handler(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ siginfo_t info;
+
+ if (!user_mode(regs))
+ return -EFAULT;
+
+ info = (siginfo_t) {
+ .si_signo = SIGTRAP,
+ .si_errno = 0,
+ .si_code = TRAP_BRKPT,
+ .si_addr = (void __user *)instruction_pointer(regs),
+ };
+
+ force_sig_info(SIGTRAP, &info, current);
+ return 0;
+}
+
+int aarch32_break_handler(struct pt_regs *regs)
+{
+ siginfo_t info;
+ unsigned int instr;
+ bool bp = false;
+ void __user *pc = (void __user *)instruction_pointer(regs);
+
+ if (!compat_user_mode(regs))
+ return -EFAULT;
+
+ if (compat_thumb_mode(regs)) {
+ /* get 16-bit Thumb instruction */
+ get_user(instr, (u16 __user *)pc);
+ if (instr == AARCH32_BREAK_THUMB2_LO) {
+ /* get second half of 32-bit Thumb-2 instruction */
+ get_user(instr, (u16 __user *)(pc + 2));
+ bp = instr == AARCH32_BREAK_THUMB2_HI;
+ } else {
+ bp = instr == AARCH32_BREAK_THUMB;
+ }
+ } else {
+ /* 32-bit ARM instruction */
+ get_user(instr, (u32 __user *)pc);
+ bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
+ }
+
+ if (!bp)
+ return -EFAULT;
+
+ info = (siginfo_t) {
+ .si_signo = SIGTRAP,
+ .si_errno = 0,
+ .si_code = TRAP_BRKPT,
+ .si_addr = pc,
+ };
+
+ force_sig_info(SIGTRAP, &info, current);
+ return 0;
+}
+
+static int __init debug_traps_init(void)
{
hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
TRAP_HWBKPT, "single-step handler");
+ hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
+ TRAP_BRKPT, "ptrace BRK handler");
return 0;
}
-arch_initcall(single_step_init);
+arch_initcall(debug_traps_init);
/* Re-enable single step for syscall restarting. */
void user_rewind_single_step(struct task_struct *task)
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6..d358cca 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,3 +41,27 @@
fpsimd_restore x0, 8
ret
ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Save the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_save_partial_state)
+ fpsimd_save_partial x0, 1, 8, 9
+ ret
+ENDPROC(fpsimd_load_partial_state)
+
+/*
+ * Load the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_load_partial_state)
+ fpsimd_restore_partial x0, 8, 9
+ ret
+ENDPROC(fpsimd_load_partial_state)
+
+#endif
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7cd589e..5abd0ca 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -25,9 +25,9 @@
#include <asm/asm-offsets.h>
#include <asm/errno.h>
#include <asm/esr.h>
+#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/unistd.h>
-#include <asm/unistd32.h>
/*
* Bad Abort numbers
@@ -422,6 +422,7 @@
* Data abort handling
*/
mrs x0, far_el1
+ bic x0, x0, #(0xff << 56)
disable_step x1
isb
enable_dbg
@@ -585,7 +586,7 @@
str x0, [sp, #S_X0] // returned x0
work_pending:
tbnz x1, #TIF_NEED_RESCHED, work_resched
- /* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */
+ /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
ldr x2, [sp, #S_PSTATE]
mov x0, sp // 'regs'
tst x2, #PSR_MODE_MASK // user mode regs?
@@ -640,8 +641,9 @@
enable_irq
get_thread_info tsk
- ldr x16, [tsk, #TI_FLAGS] // check for syscall tracing
- tbnz x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls?
+ ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks
+ tst x16, #_TIF_SYSCALL_WORK
+ b.ne __sys_trace
adr lr, ret_fast_syscall // return address
cmp scno, sc_nr // check upper syscall limit
b.hs ni_sys
@@ -657,10 +659,13 @@
* switches, and waiting for our parent to respond.
*/
__sys_trace:
- mov x1, sp
- mov w0, #0 // trace entry
- bl syscall_trace
+ mov x0, sp
+ bl syscall_trace_enter
adr lr, __sys_trace_return // return address
+ cmp w0, #RET_SKIP_SYSCALL_TRACE // skip syscall and tracing?
+ b.eq ret_to_user
+ cmp w0, #RET_SKIP_SYSCALL // skip syscall?
+ b.eq __sys_trace_return_skipped
uxtw scno, w0 // syscall number (possibly new)
mov x1, sp // pointer to regs
cmp scno, sc_nr // check upper syscall limit
@@ -674,9 +679,9 @@
__sys_trace_return:
str x0, [sp] // save returned x0
- mov x1, sp
- mov w0, #1 // trace exit
- bl syscall_trace
+__sys_trace_return_skipped: // x0 already in regs[0]
+ mov x0, sp
+ bl syscall_trace_exit
b ret_to_user
/*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 2fa308e..093bee2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -33,6 +33,60 @@
#define FPEXC_IDF (1 << 7)
/*
+ * In order to reduce the number of times the FPSIMD state is needlessly saved
+ * and restored, we need to keep track of two things:
+ * (a) for each task, we need to remember which CPU was the last one to have
+ * the task's FPSIMD state loaded into its FPSIMD registers;
+ * (b) for each CPU, we need to remember which task's userland FPSIMD state has
+ * been loaded into its FPSIMD registers most recently, or whether it has
+ * been used to perform kernel mode NEON in the meantime.
+ *
+ * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to
+ * the id of the current CPU everytime the state is loaded onto a CPU. For (b),
+ * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
+ * address of the userland FPSIMD state of the task that was loaded onto the CPU
+ * the most recently, or NULL if kernel mode NEON has been performed after that.
+ *
+ * With this in place, we no longer have to restore the next FPSIMD state right
+ * when switching between tasks. Instead, we can defer this check to userland
+ * resume, at which time we verify whether the CPU's fpsimd_last_state and the
+ * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we
+ * can omit the FPSIMD restore.
+ *
+ * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
+ * indicate whether or not the userland FPSIMD state of the current task is
+ * present in the registers. The flag is set unless the FPSIMD registers of this
+ * CPU currently contain the most recent userland FPSIMD state of the current
+ * task.
+ *
+ * For a certain task, the sequence may look something like this:
+ * - the task gets scheduled in; if both the task's fpsimd_state.cpu field
+ * contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
+ * variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
+ * cleared, otherwise it is set;
+ *
+ * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
+ * userland FPSIMD state is copied from memory to the registers, the task's
+ * fpsimd_state.cpu field is set to the id of the current CPU, the current
+ * CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
+ * TIF_FOREIGN_FPSTATE flag is cleared;
+ *
+ * - the task executes an ordinary syscall; upon return to userland, the
+ * TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
+ * restored;
+ *
+ * - the task executes a syscall which executes some NEON instructions; this is
+ * preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
+ * register contents to memory, clears the fpsimd_last_state per-cpu variable
+ * and sets the TIF_FOREIGN_FPSTATE flag;
+ *
+ * - the task gets preempted after kernel_neon_end() is called; as we have not
+ * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
+ * whatever is in the FPSIMD registers is not saved to memory, but discarded.
+ */
+static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+
+/*
* Trapped FP/ASIMD access.
*/
void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
@@ -70,22 +124,177 @@
void fpsimd_thread_switch(struct task_struct *next)
{
- /* check if not kernel threads */
- if (current->mm)
+ /*
+ * Save the current FPSIMD state to memory, but only if whatever is in
+ * the registers is in fact the most recent userland FPSIMD state of
+ * 'current'.
+ */
+ if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
fpsimd_save_state(¤t->thread.fpsimd_state);
- if (next->mm)
- fpsimd_load_state(&next->thread.fpsimd_state);
+
+ if (next->mm) {
+ /*
+ * If we are switching to a task whose most recent userland
+ * FPSIMD state is already in the registers of *this* cpu,
+ * we can skip loading the state from memory. Otherwise, set
+ * the TIF_FOREIGN_FPSTATE flag so the state will be loaded
+ * upon the next return to userland.
+ */
+ struct fpsimd_state *st = &next->thread.fpsimd_state;
+
+ if (__this_cpu_read(fpsimd_last_state) == st
+ && st->cpu == smp_processor_id())
+ clear_ti_thread_flag(task_thread_info(next),
+ TIF_FOREIGN_FPSTATE);
+ else
+ set_ti_thread_flag(task_thread_info(next),
+ TIF_FOREIGN_FPSTATE);
+ }
}
void fpsimd_flush_thread(void)
{
- preempt_disable();
memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
- fpsimd_load_state(¤t->thread.fpsimd_state);
+ set_thread_flag(TIF_FOREIGN_FPSTATE);
+}
+
+/*
+ * Save the userland FPSIMD state of 'current' to memory, but only if the state
+ * currently held in the registers does in fact belong to 'current'
+ */
+void fpsimd_preserve_current_state(void)
+{
+ preempt_disable();
+ if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_save_state(¤t->thread.fpsimd_state);
preempt_enable();
}
/*
+ * Load the userland FPSIMD state of 'current' from memory, but only if the
+ * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
+ * state of 'current'
+ */
+void fpsimd_restore_current_state(void)
+{
+ preempt_disable();
+ if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+ struct fpsimd_state *st = ¤t->thread.fpsimd_state;
+
+ fpsimd_load_state(st);
+ this_cpu_write(fpsimd_last_state, st);
+ st->cpu = smp_processor_id();
+ }
+ preempt_enable();
+}
+
+/*
+ * Load an updated userland FPSIMD state for 'current' from memory and set the
+ * flag that indicates that the FPSIMD register contents are the most recent
+ * FPSIMD state of 'current'
+ */
+void fpsimd_update_current_state(struct fpsimd_state *state)
+{
+ preempt_disable();
+ fpsimd_load_state(state);
+ if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+ struct fpsimd_state *st = ¤t->thread.fpsimd_state;
+
+ this_cpu_write(fpsimd_last_state, st);
+ st->cpu = smp_processor_id();
+ }
+ preempt_enable();
+}
+
+/*
+ * Invalidate live CPU copies of task t's FPSIMD state
+ */
+void fpsimd_flush_task_state(struct task_struct *t)
+{
+ t->thread.fpsimd_state.cpu = NR_CPUS;
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
+static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin_partial(u32 num_regs)
+{
+ if (in_interrupt()) {
+ struct fpsimd_partial_state *s = this_cpu_ptr(
+ in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+
+ BUG_ON(num_regs > 32);
+ fpsimd_save_partial_state(s, roundup(num_regs, 2));
+ } else {
+ /*
+ * Save the userland FPSIMD state if we have one and if we
+ * haven't done so already. Clear fpsimd_last_state to indicate
+ * that there is no longer userland FPSIMD state in the
+ * registers.
+ */
+ preempt_disable();
+ if (current->mm &&
+ !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_save_state(¤t->thread.fpsimd_state);
+ this_cpu_write(fpsimd_last_state, NULL);
+ }
+}
+EXPORT_SYMBOL(kernel_neon_begin_partial);
+
+void kernel_neon_end(void)
+{
+ if (in_interrupt()) {
+ struct fpsimd_partial_state *s = this_cpu_ptr(
+ in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+ fpsimd_load_partial_state(s);
+ } else {
+ preempt_enable();
+ }
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
+#ifdef CONFIG_CPU_PM
+static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
+ unsigned long cmd, void *v)
+{
+ switch (cmd) {
+ case CPU_PM_ENTER:
+ if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_save_state(¤t->thread.fpsimd_state);
+ this_cpu_write(fpsimd_last_state, NULL);
+ break;
+ case CPU_PM_EXIT:
+ if (current->mm)
+ set_thread_flag(TIF_FOREIGN_FPSTATE);
+ break;
+ case CPU_PM_ENTER_FAILED:
+ default:
+ return NOTIFY_DONE;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_pm_notifier_block = {
+ .notifier_call = fpsimd_cpu_pm_notifier,
+};
+
+static void fpsimd_pm_init(void)
+{
+ cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
+}
+
+#else
+static inline void fpsimd_pm_init(void) { }
+#endif /* CONFIG_CPU_PM */
+
+/*
* FP/SIMD support code initialisation.
*/
static int __init fpsimd_init(void)
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 5ab825c..eda4d05 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,13 +20,13 @@
#define pr_fmt(fmt) "hw-breakpoint: " fmt
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/smp.h>
-#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
@@ -826,7 +826,7 @@
void *hcpu)
{
int cpu = (long)hcpu;
- if (action == CPU_ONLINE)
+ if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
smp_call_function_single(cpu, reset_ctrl_regs, NULL, 1);
return NOTIFY_OK;
}
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 8b69ecb..2f5b3ff 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -27,6 +27,9 @@
*
* See Documentation/arm/kernel_user_helpers.txt for formal definitions.
*/
+
+#include <asm/unistd.h>
+
.align 5
.globl __kuser_helper_start
__kuser_helper_start:
diff --git a/arch/arm64/kernel/opcodes.c b/arch/arm64/kernel/opcodes.c
new file mode 100644
index 0000000..ceb5a04
--- /dev/null
+++ b/arch/arm64/kernel/opcodes.c
@@ -0,0 +1,72 @@
+/*
+ * Copied from linux/arch/arm/kernel/opcodes.c
+ *
+ * A32 condition code lookup feature moved from nwfpe/fpopcode.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <asm/opcodes.h>
+
+#define ARM_OPCODE_CONDITION_UNCOND 0xf
+
+/*
+ * condition code lookup table
+ * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
+ *
+ * bit position in short is condition code: NZCV
+ */
+static const unsigned short cc_map[16] = {
+ 0xF0F0, /* EQ == Z set */
+ 0x0F0F, /* NE */
+ 0xCCCC, /* CS == C set */
+ 0x3333, /* CC */
+ 0xFF00, /* MI == N set */
+ 0x00FF, /* PL */
+ 0xAAAA, /* VS == V set */
+ 0x5555, /* VC */
+ 0x0C0C, /* HI == C set && Z clear */
+ 0xF3F3, /* LS == C clear || Z set */
+ 0xAA55, /* GE == (N==V) */
+ 0x55AA, /* LT == (N!=V) */
+ 0x0A05, /* GT == (!Z && (N==V)) */
+ 0xF5FA, /* LE == (Z || (N!=V)) */
+ 0xFFFF, /* AL always */
+ 0 /* NV */
+};
+
+/*
+ * Returns:
+ * ARM_OPCODE_CONDTEST_FAIL - if condition fails
+ * ARM_OPCODE_CONDTEST_PASS - if condition passes (including AL)
+ * ARM_OPCODE_CONDTEST_UNCOND - if NV condition, or separate unconditional
+ * opcode space from v5 onwards
+ *
+ * Code that tests whether a conditional instruction would pass its condition
+ * check should check that return value == ARM_OPCODE_CONDTEST_PASS.
+ *
+ * Code that tests if a condition means that the instruction would be executed
+ * (regardless of conditional or unconditional) should instead check that the
+ * return value != ARM_OPCODE_CONDTEST_FAIL.
+ */
+asmlinkage unsigned int arm_check_condition(u32 opcode, u64 psr)
+{
+ u32 cc_bits = opcode >> 28;
+ u32 psr_cond = (u32)(psr & 0xffffffff) >> 28;
+ unsigned int ret;
+
+ if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
+ if ((cc_map[cc_bits] >> (psr_cond)) & 1)
+ ret = ARM_OPCODE_CONDTEST_PASS;
+ else
+ ret = ARM_OPCODE_CONDTEST_FAIL;
+ } else {
+ ret = ARM_OPCODE_CONDTEST_UNCOND;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arm_check_condition);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0860fc3..78259d0 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -20,6 +20,7 @@
#include <stdarg.h>
+#include <linux/compat.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/kernel.h>
@@ -141,6 +142,70 @@
while (1);
}
+/*
+ * dump a block of kernel memory from around the given address
+ */
+static void show_data(unsigned long addr, int nbytes, const char *name)
+{
+ int i, j;
+ int nlines;
+ u32 *p;
+
+ /*
+ * don't attempt to dump non-kernel addresses or
+ * values that are probably just small negative numbers
+ */
+ if (addr < PAGE_OFFSET || addr > -256UL)
+ return;
+
+ printk("\n%s: %#lx:\n", name, addr);
+
+ /*
+ * round address down to a 32 bit boundary
+ * and always dump a multiple of 32 bytes
+ */
+ p = (u32 *)(addr & ~(sizeof(u32) - 1));
+ nbytes += (addr & (sizeof(u32) - 1));
+ nlines = (nbytes + 31) / 32;
+
+
+ for (i = 0; i < nlines; i++) {
+ /*
+ * just display low 16 bits of address to keep
+ * each line of the dump < 80 characters
+ */
+ printk("%04lx ", (unsigned long)p & 0xffff);
+ for (j = 0; j < 8; j++) {
+ u32 data;
+ if (probe_kernel_address(p, data)) {
+ printk(" ********");
+ } else {
+ printk(" %08x", data);
+ }
+ ++p;
+ }
+ printk("\n");
+ }
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+ mm_segment_t fs;
+ unsigned int i;
+
+ fs = get_fs();
+ set_fs(KERNEL_DS);
+ show_data(regs->pc - nbytes, nbytes * 2, "PC");
+ show_data(regs->regs[30] - nbytes, nbytes * 2, "LR");
+ show_data(regs->sp - nbytes, nbytes * 2, "SP");
+ for (i = 0; i < 30; i++) {
+ char name[4];
+ snprintf(name, sizeof(name), "X%u", i);
+ show_data(regs->regs[i] - nbytes, nbytes * 2, name);
+ }
+ set_fs(fs);
+}
+
void __show_regs(struct pt_regs *regs)
{
int i;
@@ -156,6 +221,8 @@
if (i % 2 == 0)
printk("\n");
}
+ if (!user_mode(regs))
+ show_extra_register_data(regs, 128);
printk("\n");
}
@@ -202,7 +269,7 @@
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- fpsimd_save_state(¤t->thread.fpsimd_state);
+ fpsimd_preserve_current_state();
*dst = *src;
return 0;
}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index dfad98f..8027b1d 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,12 +19,15 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/audit.h>
+#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
+#include <linux/seccomp.h>
#include <linux/security.h>
#include <linux/init.h>
#include <linux/signal.h>
@@ -38,6 +41,7 @@
#include <asm/compat.h>
#include <asm/debug-monitors.h>
#include <asm/pgtable.h>
+#include <asm/syscall.h>
#include <asm/traps.h>
#include <asm/system_misc.h>
@@ -59,28 +63,6 @@
user_disable_single_step(child);
}
-/*
- * Handle hitting a breakpoint.
- */
-static int ptrace_break(struct pt_regs *regs)
-{
- siginfo_t info = {
- .si_signo = SIGTRAP,
- .si_errno = 0,
- .si_code = TRAP_BRKPT,
- .si_addr = (void __user *)instruction_pointer(regs),
- };
-
- force_sig_info(SIGTRAP, &info, current);
- return 0;
-}
-
-static int arm64_break_trap(unsigned long addr, unsigned int esr,
- struct pt_regs *regs)
-{
- return ptrace_break(regs);
-}
-
#ifdef CONFIG_HAVE_HW_BREAKPOINT
/*
* Handle hitting a HW-breakpoint.
@@ -546,6 +528,7 @@
return ret;
target->thread.fpsimd_state.user_fpsimd = newstate;
+ fpsimd_flush_task_state(target);
return ret;
}
@@ -795,6 +778,7 @@
uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
}
+ fpsimd_flush_task_state(target);
return ret;
}
@@ -822,33 +806,6 @@
.regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets)
};
-int aarch32_break_trap(struct pt_regs *regs)
-{
- unsigned int instr;
- bool bp = false;
- void __user *pc = (void __user *)instruction_pointer(regs);
-
- if (compat_thumb_mode(regs)) {
- /* get 16-bit Thumb instruction */
- get_user(instr, (u16 __user *)pc);
- if (instr == AARCH32_BREAK_THUMB2_LO) {
- /* get second half of 32-bit Thumb-2 instruction */
- get_user(instr, (u16 __user *)(pc + 2));
- bp = instr == AARCH32_BREAK_THUMB2_HI;
- } else {
- bp = instr == AARCH32_BREAK_THUMB;
- }
- } else {
- /* 32-bit ARM instruction */
- get_user(instr, (u32 __user *)pc);
- bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
- }
-
- if (bp)
- return ptrace_break(regs);
- return 1;
-}
-
static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off,
compat_ulong_t __user *ret)
{
@@ -1117,48 +1074,87 @@
long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
- return ptrace_request(child, request, addr, data);
-}
+ int ret;
-
-static int __init ptrace_break_init(void)
-{
- hook_debug_fault_code(DBG_ESR_EVT_BRK, arm64_break_trap, SIGTRAP,
- TRAP_BRKPT, "ptrace BRK handler");
- return 0;
-}
-core_initcall(ptrace_break_init);
-
-
-asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
-{
- unsigned long saved_reg;
-
- if (!test_thread_flag(TIF_SYSCALL_TRACE))
- return regs->syscallno;
-
- if (is_compat_task()) {
- /* AArch32 uses ip (r12) for scratch */
- saved_reg = regs->regs[12];
- regs->regs[12] = dir;
- } else {
- /*
- * Save X7. X7 is used to denote syscall entry/exit:
- * X7 = 0 -> entry, = 1 -> exit
- */
- saved_reg = regs->regs[7];
- regs->regs[7] = dir;
+ switch (request) {
+ case PTRACE_SET_SYSCALL:
+ task_pt_regs(child)->syscallno = data;
+ ret = 0;
+ break;
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
}
- if (dir)
+ return ret;
+}
+
+enum ptrace_syscall_dir {
+ PTRACE_SYSCALL_ENTER = 0,
+ PTRACE_SYSCALL_EXIT,
+};
+
+static void tracehook_report_syscall(struct pt_regs *regs,
+ enum ptrace_syscall_dir dir)
+{
+ int regno;
+ unsigned long saved_reg;
+
+ /*
+ * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
+ * used to denote syscall entry/exit:
+ */
+ regno = (is_compat_task() ? 12 : 7);
+ saved_reg = regs->regs[regno];
+ regs->regs[regno] = dir;
+
+ if (dir == PTRACE_SYSCALL_EXIT)
tracehook_report_syscall_exit(regs, 0);
else if (tracehook_report_syscall_entry(regs))
regs->syscallno = ~0UL;
- if (is_compat_task())
- regs->regs[12] = saved_reg;
- else
- regs->regs[7] = saved_reg;
+ regs->regs[regno] = saved_reg;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+ unsigned int saved_syscallno = regs->syscallno;
+
+ /* Do the secure computing check first; failures should be fast. */
+ if (secure_computing(regs->syscallno) == -1)
+ return RET_SKIP_SYSCALL_TRACE;
+
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+ if (IS_SKIP_SYSCALL(regs->syscallno)) {
+ /*
+ * RESTRICTION: we can't modify a return value of user
+ * issued syscall(-1) here. In order to ease this flavor,
+ * we need to treat whatever value in x0 as a return value,
+ * but this might result in a bogus value being returned.
+ */
+ /*
+ * NOTE: syscallno may also be set to -1 if fatal signal is
+ * detected in tracehook_report_syscall_entry(), but since
+ * a value set to x0 here is not used in this case, we may
+ * neglect the case.
+ */
+ if (!test_thread_flag(TIF_SYSCALL_TRACE) ||
+ (IS_SKIP_SYSCALL(saved_syscallno)))
+ regs->regs[0] = -ENOSYS;
+ }
+
+ audit_syscall_entry(syscall_get_arch(), regs->syscallno,
+ regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]);
return regs->syscallno;
}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+ audit_syscall_exit(regs);
+
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 7cc551d..aae66b0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -58,9 +58,20 @@
unsigned int processor_id;
EXPORT_SYMBOL(processor_id);
-unsigned int elf_hwcap __read_mostly;
+unsigned long elf_hwcap __read_mostly;
EXPORT_SYMBOL_GPL(elf_hwcap);
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP_DEFAULT \
+ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
+ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
+ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
+ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
+ COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
+#endif
+
static const char *cpu_name;
static const char *machine_name;
phys_addr_t __fdt_pointer __initdata;
@@ -114,6 +125,7 @@
static void __init setup_processor(void)
{
struct cpu_info *cpu_info;
+ u64 features, block;
/*
* locate processor in the list of supported processor
@@ -134,6 +146,69 @@
sprintf(init_utsname()->machine, "aarch64");
elf_hwcap = 0;
+
+ /*
+ * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
+ * The blocks we test below represent incremental functionality
+ * for non-negative values. Negative values are reserved.
+ */
+ features = read_cpuid(ID_AA64ISAR0_EL1);
+ block = (features >> 4) & 0xf;
+ if (!(block & 0x8)) {
+ switch (block) {
+ default:
+ case 2:
+ elf_hwcap |= HWCAP_PMULL;
+ case 1:
+ elf_hwcap |= HWCAP_AES;
+ case 0:
+ break;
+ }
+ }
+
+ block = (features >> 8) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_SHA1;
+
+ block = (features >> 12) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_SHA2;
+
+ block = (features >> 16) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+ /*
+ * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+ * the Aarch32 32-bit execution state.
+ */
+ features = read_cpuid(ID_ISAR5_EL1);
+ block = (features >> 4) & 0xf;
+ if (!(block & 0x8)) {
+ switch (block) {
+ default:
+ case 2:
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+ case 1:
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+ case 0:
+ break;
+ }
+ }
+
+ block = (features >> 8) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+ block = (features >> 12) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+ block = (features >> 16) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
}
static void __init setup_machine_fdt(phys_addr_t dt_phys)
@@ -323,6 +398,12 @@
static const char *hwcap_str[] = {
"fp",
"asimd",
+ "evtstrm",
+ "aes",
+ "pmull",
+ "sha1",
+ "sha2",
+ "crc32",
NULL
};
@@ -351,6 +432,15 @@
"lpae",
"evtstrm"
};
+
+static const char *compat_hwcap2_str[] = {
+ "aes",
+ "pmull",
+ "sha1",
+ "sha2",
+ "crc32",
+ NULL
+};
#endif /* CONFIG_COMPAT */
static int c_show(struct seq_file *m, void *v)
@@ -385,6 +475,10 @@
for (j = 0; compat_hwcap_str[j]; j++)
if (COMPAT_ELF_HWCAP & (1 << j))
seq_printf(m, " %s", compat_hwcap_str[j]);
+
+ for (j = 0; compat_hwcap2_str[j]; j++)
+ if (compat_elf_hwcap2 & (1 << j))
+ seq_printf(m, " %s", compat_hwcap2_str[j]);
#endif /* CONFIG_COMPAT */
} else {
for (j = 0; hwcap_str[j]; j++)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 890a591..182b6fc 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/personality.h>
@@ -25,7 +26,6 @@
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
-#include <asm/compat.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
@@ -51,7 +51,7 @@
int err;
/* dump the hardware registers to the fpsimd_state structure */
- fpsimd_save_state(fpsimd);
+ fpsimd_preserve_current_state();
/* copy the FP and status/control registers */
err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
@@ -86,11 +86,8 @@
__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
/* load the hardware registers from the fpsimd_state structure */
- if (!err) {
- preempt_disable();
- fpsimd_load_state(&fpsimd);
- preempt_enable();
- }
+ if (!err)
+ fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
@@ -416,4 +413,8 @@
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
}
+
+ if (thread_flags & _TIF_FOREIGN_FPSTATE)
+ fpsimd_restore_current_state();
+
}
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1e60acc..ec6cac5 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -26,7 +26,7 @@
#include <asm/fpsimd.h>
#include <asm/signal32.h>
#include <asm/uaccess.h>
-#include <asm/unistd32.h>
+#include <asm/unistd.h>
struct compat_sigcontext {
/* We always set these two fields to 0 */
@@ -211,6 +211,14 @@
err |= __put_user(from->si_uid, &to->si_uid);
err |= __put_user(from->si_int, &to->si_int);
break;
+#ifdef __ARCH_SIGSYS
+ case __SI_SYS:
+ err |= __put_user((compat_uptr_t)(unsigned long)
+ from->si_call_addr, &to->si_call_addr);
+ err |= __put_user(from->si_syscall, &to->si_syscall);
+ err |= __put_user(from->si_arch, &to->si_arch);
+ break;
+#endif
default: /* this is just in case for now ... */
err |= __put_user(from->si_pid, &to->si_pid);
err |= __put_user(from->si_uid, &to->si_uid);
@@ -263,7 +271,7 @@
* Note that this also saves V16-31, which aren't visible
* in AArch32.
*/
- fpsimd_save_state(fpsimd);
+ fpsimd_preserve_current_state();
/* Place structure header on the stack */
__put_user_error(magic, &frame->magic, err);
@@ -333,11 +341,8 @@
* We don't need to touch the exception register, so
* reload the hardware state.
*/
- if (!err) {
- preempt_disable();
- fpsimd_load_state(&fpsimd);
- preempt_enable();
- }
+ if (!err)
+ fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
diff --git a/arch/arm64/kernel/swp_emulate.c b/arch/arm64/kernel/swp_emulate.c
new file mode 100644
index 0000000..508fd2e
--- /dev/null
+++ b/arch/arm64/kernel/swp_emulate.c
@@ -0,0 +1,223 @@
+/*
+ * Derived from from linux/arch/arm/kernel/swp_emulate.c
+ *
+ * Copyright (C) 2009 ARM Limited
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ * store-exclusive for processors that have them disabled (or future ones that
+ * might not implement them).
+ *
+ * Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ * Where: Rt = destination
+ * Rt2 = source
+ * Rn = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/perf_event.h>
+
+#include <asm/opcodes.h>
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+#include <asm/system_misc.h>
+#include <linux/debugfs.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+
+static int swpb(u8 in, u8 *out, u8 *addr)
+{
+ u8 _out;
+ int res;
+ int err;
+
+ do {
+ __asm__ __volatile__(
+ "0: ldxrb %w1, %4\n"
+ "1: stxrb %w0, %w3, %4\n"
+ " mov %w2, #0\n"
+ "2:\n"
+ " .section .fixup,\"ax\"\n"
+ " .align 2\n"
+ "3: mov %w2, %5\n"
+ " b 2b\n"
+ " .previous\n"
+ " .section __ex_table,\"a\"\n"
+ " .align 3\n"
+ " .quad 0b, 3b\n"
+ " .quad 1b, 3b\n"
+ " .previous"
+ : "=&r" (res), "=r" (_out), "=r" (err)
+ : "r" (in), "Q" (*addr), "i" (-EFAULT)
+ : "cc", "memory");
+ } while (err == 0 && res != 0);
+
+ if (err == 0)
+ *out = _out;
+ return err;
+}
+
+static int swp(u32 in, u32 *out, u32 *addr)
+{
+ u32 _out;
+ int res;
+ int err = 0;
+
+ do {
+ __asm__ __volatile__(
+ "0: ldxr %w1, %4\n"
+ "1: stxr %w0, %w3, %4\n"
+ " mov %w2, #0\n"
+ "2:\n"
+ " .section .fixup,\"ax\"\n"
+ " .align 2\n"
+ "3: mov %w2, %5\n"
+ " b 2b\n"
+ " .previous\n"
+ " .section __ex_table,\"a\"\n"
+ " .align 3\n"
+ " .quad 0b, 3b\n"
+ " .quad 1b, 3b\n"
+ " .previous"
+ : "=&r" (res), "=r" (_out), "=r" (err)
+ : "r" (in), "Q" (*addr), "i" (-EFAULT)
+ : "cc", "memory");
+ } while (err == 0 && res != 0);
+
+ if (err == 0)
+ *out = _out;
+ return err;
+}
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+ (((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET 16
+#define RT_OFFSET 12
+#define RT2_OFFSET 0
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+static pid_t previous_pid;
+
+u64 swpb_count = 0;
+u64 swp_count = 0;
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+ u32 destreg, data, type;
+ uintptr_t address;
+ unsigned int res = 0;
+ int err;
+ u32 temp32;
+ u8 temp8;
+
+ perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
+
+ res = arm_check_condition(instr, regs->pstate);
+ switch (res) {
+ case ARM_OPCODE_CONDTEST_PASS:
+ break;
+ case ARM_OPCODE_CONDTEST_FAIL:
+ /* Condition failed - return to next instruction */
+ regs->pc += 4;
+ return 0;
+ case ARM_OPCODE_CONDTEST_UNCOND:
+ /* If unconditional encoding - not a SWP, undef */
+ return -EFAULT;
+ default:
+ return -EINVAL;
+ }
+
+ if (current->pid != previous_pid) {
+ pr_warn("\"%s\" (%ld) uses obsolete SWP{B} instruction\n",
+ current->comm, (unsigned long)current->pid);
+ previous_pid = current->pid;
+ }
+
+ address = regs->regs[EXTRACT_REG_NUM(instr, RN_OFFSET)] & 0xffffffff;
+ data = regs->regs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+ destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+ type = instr & TYPE_SWPB;
+
+ /* Check access in reasonable access range for both SWP and SWPB */
+ if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+ pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+ (void *)address);
+ res = -EFAULT;
+ }
+ if (type == TYPE_SWPB) {
+ err = swpb((u8) data, &temp8, (u8 *) address);
+ if (err)
+ return err;
+ regs->regs[destreg] = temp8;
+ regs->pc += 4;
+ swpb_count++;
+ } else if (address & 0x3) {
+ /* SWP to unaligned address not permitted */
+ pr_debug("SWP instruction on unaligned pointer!\n");
+ return -EFAULT;
+ } else {
+ err = swp((u32) data, &temp32, (u32 *) address);
+ if (err)
+ return err;
+ regs->regs[destreg] = temp32;
+ regs->pc += 4;
+ swp_count++;
+ }
+
+ return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+ .instr_mask = 0x0fb00ff0,
+ .instr_val = 0x01000090,
+ .pstate_mask = COMPAT_PSR_MODE_MASK | COMPAT_PSR_T_BIT,
+ .pstate_val = COMPAT_PSR_MODE_USR,
+ .fn = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+ struct dentry *dir;
+ dir = debugfs_create_dir("swp_emulate", NULL);
+ debugfs_create_u64("swp_count", S_IRUGO | S_IWUSR, dir, &swp_count);
+ debugfs_create_u64("swpb_count", S_IRUGO | S_IWUSR, dir, &swpb_count);
+
+ pr_notice("Registering SWP/SWPB emulation handler\n");
+ register_undef_hook(&swp_hook);
+
+
+ return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 7803992..dc47e53 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -26,7 +26,7 @@
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
-#include <asm/unistd32.h>
+#include <asm/unistd.h>
static inline void
do_compat_cache_op(unsigned long start, unsigned long end, int flags)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f30852d..0da4769 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -3,6 +3,7 @@
*
* Copyright (C) 1995-2009 Russell King
* Copyright (C) 2012 ARM Ltd.
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -32,6 +33,7 @@
#include <linux/syscalls.h>
#include <asm/atomic.h>
+#include <asm/debug-monitors.h>
#include <asm/traps.h>
#include <asm/stacktrace.h>
#include <asm/exception.h>
@@ -256,17 +258,58 @@
die(str, regs, err);
}
+static LIST_HEAD(undef_hook);
+
+void register_undef_hook(struct undef_hook *hook)
+{
+ list_add(&hook->node, &undef_hook);
+}
+
+static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
+{
+ struct undef_hook *hook;
+ int (*fn)(struct pt_regs *regs, unsigned int instr) = NULL;
+
+ list_for_each_entry(hook, &undef_hook, node)
+ if ((instr & hook->instr_mask) == hook->instr_val &&
+ (regs->pstate & hook->pstate_mask) == hook->pstate_val)
+ fn = hook->fn;
+
+ return fn ? fn(regs, instr) : 1;
+}
+
asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
{
+ u32 instr;
siginfo_t info;
void __user *pc = (void __user *)instruction_pointer(regs);
-#ifdef CONFIG_COMPAT
/* check for AArch32 breakpoint instructions */
- if (compat_user_mode(regs) && aarch32_break_trap(regs) == 0)
+ if (!aarch32_break_handler(regs))
return;
-#endif
+ if (user_mode(regs)) {
+ if (compat_thumb_mode(regs)) {
+ if (get_user(instr, (u16 __user *)pc))
+ goto die_sig;
+ if (is_wide_instruction(instr)) {
+ u32 instr2;
+ if (get_user(instr2, (u16 __user *)pc+1))
+ goto die_sig;
+ instr <<= 16;
+ instr |= instr2;
+ }
+ } else if (get_user(instr, (u32 __user *)pc)) {
+ goto die_sig;
+ }
+ } else {
+ /* kernel mode */
+ instr = *((u32 *)pc);
+ }
+ if (call_undef_hook(regs, instr) == 0)
+ return;
+
+die_sig:
if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
printk_ratelimit()) {
pr_info("%s[%d]: undefined instruction: pc=%p\n",
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 5c55166..b016660 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -109,9 +109,11 @@
}
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+#define PFN_MASK ((1UL << (64 - PAGE_SHIFT)) - 1)
+
int pfn_valid(unsigned long pfn)
{
- return memblock_is_memory(pfn << PAGE_SHIFT);
+ return (pfn & PFN_MASK) == pfn && memblock_is_memory(pfn << PAGE_SHIFT);
}
EXPORT_SYMBOL(pfn_valid);
#endif
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 8aaf073..83c3df2 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -51,9 +51,14 @@
{
unsigned long rnd = 0;
- if (current->flags & PF_RANDOMIZE)
- rnd = (long)get_random_int() & STACK_RND_MASK;
-
+ if (current->flags & PF_RANDOMIZE) {
+#ifdef CONFIG_COMPAT
+ if (test_thread_flag(TIF_32BIT))
+ rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
+ else
+#endif
+ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
+ }
return rnd << PAGE_SHIFT;
}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index f84fcf7..25929f6 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -147,7 +147,7 @@
* both user and kernel.
*/
ldr x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
- TCR_ASID16 | (1 << 31)
+ TCR_ASID16 | TCR_TBI0 | (1 << 31)
#ifdef CONFIG_ARM64_64K_PAGES
orr x10, x10, TCR_TG0_64K
orr x10, x10, TCR_TG1_64K
@@ -156,6 +156,20 @@
ret // return to head.S
ENDPROC(__cpu_setup)
+#ifdef CONFIG_ARMV7_COMPAT
+ /*
+ * n n T
+ * U E WT T UD US IHBS
+ * CE0 XWHW CZ ME TEEA S
+ * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
+ * 0011 0... 1101 ..0. ..0. 10.. .... .... < hardware reserved
+ * .... .100 .... 01.1 11.1 ..01 0011 1101 < software settings
+ */
+ .type crval, #object
+crval:
+ .word 0x030802e2 // clear
+ .word 0x0405d03d // set
+#else
/*
* n n T
* U E WT T UD US IHBS
@@ -168,3 +182,4 @@
crval:
.word 0x030802e2 // clear
.word 0x0405d11d // set
+#endif
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index 60576e0..d0a69aa 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -45,14 +45,37 @@
# define smp_rmb() rmb()
# define smp_wmb() wmb()
# define smp_read_barrier_depends() read_barrier_depends()
+
#else
+
# define smp_mb() barrier()
# define smp_rmb() barrier()
# define smp_wmb() barrier()
# define smp_read_barrier_depends() do { } while(0)
+
#endif
/*
+ * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
+ * need for asm trickery!
+ */
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
+/*
* XXX check on this ---I suspect what Linus really wants here is
* acquire vs release semantics but we can't discuss this stuff with
* Linus just yet. Grrr...
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index e355a4c..2d6f0de 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -85,4 +85,19 @@
#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#endif /* _ASM_METAG_BARRIER_H */
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 314ab55..52c5b61 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -180,4 +180,19 @@
#define nudge_writes() mb()
#endif
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#endif /* __ASM_BARRIER_H */
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 7e5fe27..358820b 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -147,7 +147,7 @@
unsigned long random_factor = 0UL;
if (current->flags & PF_RANDOMIZE) {
- random_factor = get_random_int();
+ random_factor = get_random_long();
random_factor = random_factor << PAGE_SHIFT;
if (TASK_IS_32BIT_ADDR)
random_factor &= 0xfffffful;
@@ -168,7 +168,7 @@
static inline unsigned long brk_rnd(void)
{
- unsigned long rnd = get_random_int();
+ unsigned long rnd = get_random_long();
rnd = rnd << PAGE_SHIFT;
/* 8MB for 32bit, 256MB for 64bit */
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 838b479..88d0962 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -60,6 +60,7 @@
};
struct getdents_callback {
+ struct dir_context ctx;
struct hpux_dirent __user *current_dir;
struct hpux_dirent __user *previous;
int count;
@@ -110,24 +111,23 @@
{
struct fd arg;
struct hpux_dirent __user * lastdirent;
- struct getdents_callback buf;
+ struct getdents_callback buf = {
+ .ctx.actor = filldir,
+ .current_dir = dirent,
+ .count = count
+ };
int error;
arg = fdget(fd);
if (!arg.file)
return -EBADF;
- buf.current_dir = dirent;
- buf.previous = NULL;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(arg.file, filldir, &buf);
+ error = iterate_dir(arg.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
- if (put_user(arg.file->f_pos, &lastdirent->d_off))
+ if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index ae78225..f89da80 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -45,11 +45,15 @@
# define SMPWMB eieio
#endif
+#define __lwsync() __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
#define smp_mb() mb()
-#define smp_rmb() __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_rmb() __lwsync()
#define smp_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
#define smp_read_barrier_depends() read_barrier_depends()
#else
+#define __lwsync() barrier()
+
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
@@ -65,4 +69,19 @@
#define data_barrier(x) \
asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ __lwsync(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ __lwsync(); \
+ ___p1; \
+})
+
#endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a5e339806..51ab67e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1460,9 +1460,9 @@
/* 8MB for 32bit, 1GB for 64bit */
if (is_32bit_task())
- rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+ rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT)));
else
- rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+ rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT)));
return rnd << PAGE_SHIFT;
}
diff --git a/arch/powerpc/mm/mmap_64.c b/arch/powerpc/mm/mmap_64.c
index 67a42ed..2803d90 100644
--- a/arch/powerpc/mm/mmap_64.c
+++ b/arch/powerpc/mm/mmap_64.c
@@ -60,9 +60,9 @@
if (current->flags & PF_RANDOMIZE) {
/* 8MB for 32bit, 1GB for 64bit */
if (is_32bit_task())
- rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+ rnd = get_random_long() % (1<<(23-PAGE_SHIFT));
else
- rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+ rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT));
}
return rnd << PAGE_SHIFT;
}
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 16760ee..578680f 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -32,4 +32,19 @@
#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
#endif /* __ASM_BARRIER_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 749313b..25b4b1f 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -89,11 +89,10 @@
regs->orig_gpr2 = args[0];
}
-static inline int syscall_get_arch(struct task_struct *task,
- struct pt_regs *regs)
+static inline int syscall_get_arch(void)
{
#ifdef CONFIG_COMPAT
- if (test_tsk_thread_flag(task, TIF_31BIT))
+ if (test_tsk_thread_flag(current, TIF_31BIT))
return AUDIT_ARCH_S390;
#endif
return sizeof(long) == 8 ? AUDIT_ARCH_S390X : AUDIT_ARCH_S390;
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 95d4598..b5aad96 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -53,4 +53,19 @@
#define smp_read_barrier_depends() do { } while(0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
#endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 666510b..c2c11c7 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -265,7 +265,7 @@
unsigned long rnd = 0UL;
if (current->flags & PF_RANDOMIZE) {
- unsigned long val = get_random_int();
+ unsigned long val = get_random_long();
if (test_thread_flag(TIF_32BIT))
rnd = (val % (1UL << (23UL-PAGE_SHIFT)));
else
diff --git a/arch/um/include/shared/frame_kern.h b/arch/um/include/shared/frame_kern.h
index e584e40..f2ca570 100644
--- a/arch/um/include/shared/frame_kern.h
+++ b/arch/um/include/shared/frame_kern.h
@@ -6,13 +6,13 @@
#ifndef __FRAME_KERN_H_
#define __FRAME_KERN_H_
-extern int setup_signal_stack_sc(unsigned long stack_top, int sig,
+extern int setup_signal_stack_sc(unsigned long stack_top, int sig,
struct k_sigaction *ka,
- struct pt_regs *regs,
+ struct pt_regs *regs,
sigset_t *mask);
-extern int setup_signal_stack_si(unsigned long stack_top, int sig,
+extern int setup_signal_stack_si(unsigned long stack_top, int sig,
struct k_sigaction *ka,
- struct pt_regs *regs, siginfo_t *info,
+ struct pt_regs *regs, struct siginfo *info,
sigset_t *mask);
#endif
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 3e831b3..f57e02e 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -19,7 +19,7 @@
* OK, we're invoking a handler
*/
static void handle_signal(struct pt_regs *regs, unsigned long signr,
- struct k_sigaction *ka, siginfo_t *info)
+ struct k_sigaction *ka, struct siginfo *info)
{
sigset_t *oldset = sigmask_to_save();
int singlestep = 0;
@@ -71,7 +71,7 @@
static int kern_do_signal(struct pt_regs *regs)
{
struct k_sigaction ka_copy;
- siginfo_t info;
+ struct siginfo info;
int sig, handled_sig = 0;
while ((sig = get_signal_to_deliver(&info, &ka_copy, regs, NULL)) > 0) {
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 9d9f1b4..905924b 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -25,7 +25,7 @@
[SIGIO] = sigio_handler,
[SIGVTALRM] = timer_handler };
-static void sig_handler_common(int sig, siginfo_t *si, mcontext_t *mc)
+static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
{
struct uml_pt_regs r;
int save_errno = errno;
@@ -61,7 +61,7 @@
static int signals_enabled;
static unsigned int signals_pending;
-void sig_handler(int sig, siginfo_t *si, mcontext_t *mc)
+void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
{
int enabled;
@@ -120,7 +120,7 @@
panic("enabling signal stack failed, errno = %d\n", errno);
}
-static void (*handlers[_NSIG])(int sig, siginfo_t *si, mcontext_t *mc) = {
+static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = {
[SIGSEGV] = sig_handler,
[SIGBUS] = sig_handler,
[SIGILL] = sig_handler,
@@ -162,7 +162,7 @@
while ((sig = ffs(pending)) != 0){
sig--;
pending &= ~(1 << sig);
- (*handlers[sig])(sig, si, mc);
+ (*handlers[sig])(sig, (struct siginfo *)si, mc);
}
/*
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 4625949..908579f 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -409,7 +409,7 @@
if (WIFSTOPPED(status)) {
int sig = WSTOPSIG(status);
- ptrace(PTRACE_GETSIGINFO, pid, 0, &si);
+ ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si);
switch (sig) {
case SIGSEGV:
@@ -417,7 +417,7 @@
!ptrace_faultinfo) {
get_skas_faultinfo(pid,
®s->faultinfo);
- (*sig_info[SIGSEGV])(SIGSEGV, &si,
+ (*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
regs);
}
else handle_segv(pid, regs);
@@ -426,14 +426,14 @@
handle_trap(pid, regs, local_using_sysemu);
break;
case SIGTRAP:
- relay_signal(SIGTRAP, &si, regs);
+ relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
break;
case SIGVTALRM:
now = os_nsecs();
if (now < nsecs)
break;
block_signals();
- (*sig_info[sig])(sig, &si, regs);
+ (*sig_info[sig])(sig, (struct siginfo *)&si, regs);
unblock_signals();
nsecs = timer.it_value.tv_sec *
UM_NSEC_PER_SEC +
@@ -447,7 +447,7 @@
case SIGFPE:
case SIGWINCH:
block_signals();
- (*sig_info[sig])(sig, &si, regs);
+ (*sig_info[sig])(sig, (struct siginfo *)&si, regs);
unblock_signals();
break;
default:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 105ae30..c3754f4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -99,6 +99,8 @@
select DCACHE_WORD_ACCESS
select GENERIC_SMP_IDLE_THREAD
select ARCH_WANT_IPC_PARSE_VERSION if X86_32
+ select HAVE_ARCH_MMAP_RND_BITS if MMU
+ select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT
select HAVE_ARCH_SECCOMP_FILTER
select BUILDTIME_EXTABLE_SORT
select GENERIC_CMOS_UPDATE
@@ -149,6 +151,20 @@
config MMU
def_bool y
+config ARCH_MMAP_RND_BITS_MIN
+ default 28 if 64BIT
+ default 8
+
+config ARCH_MMAP_RND_BITS_MAX
+ default 32 if 64BIT
+ default 16
+
+config ARCH_MMAP_RND_COMPAT_BITS_MIN
+ default 8
+
+config ARCH_MMAP_RND_COMPAT_BITS_MAX
+ default 16
+
config SBUS
bool
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 9444708..590eea2 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,311 +1,2958 @@
# CONFIG_64BIT is not set
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_X86_32=y
+CONFIG_X86=y
+CONFIG_INSTRUCTION_DECODER=y
+CONFIG_OUTPUT_FORMAT="elf32-i386"
+CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_MMU=y
+CONFIG_NEED_SG_DMA_LENGTH=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_ARCH_HAS_CPU_RELAX=y
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
+CONFIG_ARCH_HAS_CPU_AUTOPROBE=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
+CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+# CONFIG_ZONE_DMA32 is not set
+# CONFIG_AUDIT_ARCH is not set
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
+CONFIG_X86_32_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_32_LAZY_GS=y
+CONFIG_ARCH_HWEIGHT_CFLAGS="-fcall-saved-ecx -fcall-saved-edx"
+CONFIG_ARCH_CPU_PROBE_RELEASE=y
+CONFIG_ARCH_SUPPORTS_UPROBES=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_IRQ_WORK=y
+CONFIG_BUILDTIME_EXTABLE_SORT=y
+
+#
+# General setup
+#
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_CROSS_COMPILE=""
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_HAVE_KERNEL_XZ=y
+CONFIG_HAVE_KERNEL_LZO=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
+# CONFIG_KERNEL_XZ is not set
+# CONFIG_KERNEL_LZO is not set
+CONFIG_DEFAULT_HOSTNAME="(none)"
+CONFIG_SWAP=y
CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
+CONFIG_FHANDLE=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_AUDIT_WATCH=y
+CONFIG_AUDIT_TREE=y
+# CONFIG_AUDIT_LOGINUID_IMMUTABLE is not set
+CONFIG_HAVE_GENERIC_HARDIRQS=y
+
+#
+# IRQ subsystem
+#
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_IRQ_SHOW=y
+CONFIG_GENERIC_PENDING_IRQ=y
+CONFIG_IRQ_DOMAIN=y
+# CONFIG_IRQ_DOMAIN_DEBUG is not set
+CONFIG_IRQ_FORCED_THREADING=y
+CONFIG_SPARSE_IRQ=y
+CONFIG_CLOCKSOURCE_WATCHDOG=y
+CONFIG_KTIME_SCALAR=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
+CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
+CONFIG_GENERIC_CMOS_UPDATE=y
+
+#
+# Timers subsystem
+#
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ_COMMON=y
+# CONFIG_HZ_PERIODIC is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+
+#
+# CPU/Task time and stats accounting
+#
+CONFIG_TICK_CPU_ACCOUNTING=y
+# CONFIG_IRQ_TIME_ACCOUNTING is not set
CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
+
+#
+# RCU Subsystem
+#
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+CONFIG_RCU_STALL_COMMON=y
+CONFIG_RCU_FANOUT=32
+CONFIG_RCU_FANOUT_LEAF=16
+# CONFIG_RCU_FANOUT_EXACT is not set
+CONFIG_RCU_FAST_NO_HZ=y
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_RCU_NOCB_CPU is not set
+# CONFIG_IKCONFIG is not set
CONFIG_LOG_BUF_SHIFT=18
+CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
+CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
+CONFIG_ARCH_WANTS_PROT_NUMA_PROT_NONE=y
CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_DEVICE=y
CONFIG_CPUSETS=y
+CONFIG_PROC_PID_CPUSET=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_SCHED=y
+# CONFIG_MEMCG is not set
+# CONFIG_CGROUP_HUGETLB is not set
+# CONFIG_CGROUP_PERF is not set
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_BLK_CGROUP is not set
+# CONFIG_CHECKPOINT_RESTORE is not set
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+# CONFIG_USER_NS is not set
+CONFIG_PID_NS=y
+# CONFIG_NET_NS is not set
+CONFIG_UIDGID_CONVERTED=y
+# CONFIG_UIDGID_STRICT_TYPE_CHECKS is not set
+# CONFIG_SCHED_AUTOGROUP is not set
+# CONFIG_SYSFS_DEPRECATED is not set
+CONFIG_RELAY=y
CONFIG_BLK_DEV_INITRD=y
-# CONFIG_COMPAT_BRK is not set
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_XZ=y
+CONFIG_RD_LZO=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_HAVE_UID16=y
+CONFIG_SYSCTL_EXCEPTION_TRACE=y
+CONFIG_HOTPLUG=y
+CONFIG_HAVE_PCSPKR_PLATFORM=y
+CONFIG_PANIC_TIMEOUT=0
+# CONFIG_EXPERT is not set
+CONFIG_UID16=y
+# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_KALLSYMS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_PCSPKR_PLATFORM=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_PCI_QUIRKS=y
+# CONFIG_EMBEDDED is not set
+CONFIG_HAVE_PERF_EVENTS=y
+
+#
+# Kernel Performance Events And Counters
+#
+CONFIG_PERF_EVENTS=y
+# CONFIG_DEBUG_PERF_USE_VMALLOC is not set
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_COMPAT_BRK=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
CONFIG_PROFILING=y
+CONFIG_TRACEPOINTS=y
+# CONFIG_OPROFILE is not set
+CONFIG_HAVE_OPROFILE=y
+CONFIG_OPROFILE_NMI_TIMER=y
CONFIG_KPROBES=y
+# CONFIG_JUMP_LABEL is not set
+CONFIG_OPTPROBES=y
+CONFIG_KPROBES_ON_FTRACE=y
+# CONFIG_HAVE_64BIT_ALIGNED_ACCESS is not set
+CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
+CONFIG_ARCH_USE_BUILTIN_BSWAP=y
+CONFIG_KRETPROBES=y
+CONFIG_USER_RETURN_NOTIFIER=y
+CONFIG_HAVE_IOREMAP_PROT=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_OPTPROBES=y
+CONFIG_HAVE_KPROBES_ON_FTRACE=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_ATTRS=y
+CONFIG_HAVE_DMA_CONTIGUOUS=y
+CONFIG_GENERIC_SMP_IDLE_THREAD=y
+CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+CONFIG_HAVE_HW_BREAKPOINT=y
+CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
+CONFIG_HAVE_USER_RETURN_NOTIFIER=y
+CONFIG_HAVE_PERF_EVENTS_NMI=y
+CONFIG_HAVE_PERF_REGS=y
+CONFIG_HAVE_PERF_USER_STACK_DUMP=y
+CONFIG_HAVE_ARCH_JUMP_LABEL=y
+CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
+CONFIG_HAVE_CMPXCHG_LOCAL=y
+CONFIG_HAVE_CMPXCHG_DOUBLE=y
+CONFIG_ARCH_WANT_IPC_PARSE_VERSION=y
+CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
+CONFIG_SECCOMP_FILTER=y
+CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
+CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
+CONFIG_MODULES_USE_ELF_REL=y
+CONFIG_CLONE_BACKWARDS=y
+CONFIG_OLD_SIGSUSPEND3=y
+CONFIG_OLD_SIGACTION=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_GCOV_KERNEL is not set
+# CONFIG_GCOV_TOOLCHAIN_IS_ANDROID is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
+# CONFIG_MODVERSIONS is not set
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_MODULE_SIG is not set
+CONFIG_STOP_MACHINE=y
+CONFIG_BLOCK=y
+CONFIG_LBDAF=y
+CONFIG_BLK_DEV_BSG=y
+# CONFIG_BLK_DEV_BSGLIB is not set
+CONFIG_BLK_DEV_INTEGRITY=y
+
+#
+# Partition Types
+#
CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
+# CONFIG_ACORN_PARTITION is not set
+# CONFIG_OSF_PARTITION is not set
+# CONFIG_AMIGA_PARTITION is not set
+CONFIG_ATARI_PARTITION=y
CONFIG_MAC_PARTITION=y
+CONFIG_MSDOS_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_LDM_PARTITION=y
+# CONFIG_LDM_DEBUG is not set
CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
+# CONFIG_KARMA_PARTITION is not set
CONFIG_EFI_PARTITION=y
+CONFIG_SYSV68_PARTITION=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_PREEMPT_NOTIFIERS=y
+CONFIG_UNINLINE_SPIN_UNLOCK=y
+CONFIG_FREEZER=y
+
+#
+# Processor type and features
+#
+CONFIG_ZONE_DMA=y
CONFIG_SMP=y
+CONFIG_X86_MPPARSE=y
+# CONFIG_X86_BIGSMP is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
+# CONFIG_X86_GOLDFISH is not set
+# CONFIG_X86_WANT_INTEL_MID is not set
+# CONFIG_X86_RDC321X is not set
+# CONFIG_X86_32_NON_STANDARD is not set
+CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y
+# CONFIG_X86_32_IRIS is not set
+# CONFIG_SCHED_OMIT_FRAME_POINTER is not set
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
+# CONFIG_PARAVIRT_DEBUG is not set
+# CONFIG_PARAVIRT_SPINLOCKS is not set
+# CONFIG_XEN is not set
+# CONFIG_XEN_PRIVILEGED_GUEST is not set
+# CONFIG_KVM_GUEST is not set
+CONFIG_LGUEST_GUEST=y
+# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set
+CONFIG_NO_BOOTMEM=y
+# CONFIG_MEMTEST is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMII is not set
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUMM is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MEFFICEON is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MELAN is not set
+# CONFIG_MGEODEGX1 is not set
+# CONFIG_MGEODE_LX is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+# CONFIG_MVIAC7 is not set
+CONFIG_MCORE2=y
+# CONFIG_MATOM is not set
CONFIG_X86_GENERIC=y
+CONFIG_X86_INTERNODE_CACHE_SHIFT=6
+CONFIG_X86_L1_CACHE_SHIFT=6
+CONFIG_X86_INTEL_USERCOPY=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
+CONFIG_X86_CMPXCHG64=y
+CONFIG_X86_CMOV=y
+CONFIG_X86_MINIMUM_CPU_FAMILY=5
+CONFIG_X86_DEBUGCTLMSR=y
+CONFIG_CPU_SUP_INTEL=y
+CONFIG_CPU_SUP_AMD=y
+CONFIG_CPU_SUP_CENTAUR=y
+CONFIG_CPU_SUP_TRANSMETA_32=y
CONFIG_HPET_TIMER=y
+CONFIG_DMI=y
+CONFIG_NR_CPUS=8
CONFIG_SCHED_SMT=y
+CONFIG_SCHED_MC=y
+# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
-CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
+# CONFIG_PREEMPT is not set
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+# CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS is not set
CONFIG_X86_MCE=y
+CONFIG_X86_MCE_INTEL=y
+CONFIG_X86_MCE_AMD=y
+# CONFIG_X86_ANCIENT_MCE is not set
+CONFIG_X86_MCE_THRESHOLD=y
+# CONFIG_X86_MCE_INJECT is not set
+CONFIG_X86_THERMAL_VECTOR=y
+CONFIG_VM86=y
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
CONFIG_X86_REBOOTFIXUPS=y
-CONFIG_MICROCODE=y
-CONFIG_MICROCODE_AMD=y
-CONFIG_X86_MSR=y
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
CONFIG_X86_CPUID=y
+# CONFIG_NOHIGHMEM is not set
+# CONFIG_HIGHMEM4G is not set
+CONFIG_HIGHMEM64G=y
+CONFIG_PAGE_OFFSET=0xC0000000
+CONFIG_HIGHMEM=y
+CONFIG_X86_PAE=y
+CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
+CONFIG_ARCH_DMA_ADDR_T_64BIT=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_ILLEGAL_POINTER_VALUE=0
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_SPARSEMEM_STATIC=y
+CONFIG_HAVE_MEMBLOCK=y
+CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
+CONFIG_ARCH_DISCARD_MEMBLOCK=y
+# CONFIG_HAVE_BOOTMEM_INFO_NODE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=999999
+# CONFIG_COMPACTION is not set
+CONFIG_PHYS_ADDR_T_64BIT=y
+CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
+CONFIG_MMU_NOTIFIER=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
+CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
+# CONFIG_MEMORY_FAILURE is not set
+# CONFIG_TRANSPARENT_HUGEPAGE is not set
+CONFIG_CROSS_MEMORY_ATTACH=y
+# CONFIG_CLEANCACHE is not set
+# CONFIG_FRONTSWAP is not set
CONFIG_HIGHPTE=y
-CONFIG_X86_CHECK_BIOS_CORRUPTION=y
+# CONFIG_X86_CHECK_BIOS_CORRUPTION is not set
+CONFIG_X86_RESERVE_LOW=64
+# CONFIG_MATH_EMULATION is not set
+CONFIG_MTRR=y
# CONFIG_MTRR_SANITIZER is not set
-CONFIG_EFI=y
-CONFIG_HZ_1000=y
+CONFIG_X86_PAT=y
+CONFIG_ARCH_USES_PG_UNCACHED=y
+CONFIG_ARCH_RANDOM=y
+CONFIG_X86_SMAP=y
+CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
+# CONFIG_HZ_100 is not set
+# CONFIG_HZ_250 is not set
+CONFIG_HZ_300=y
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=300
+CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
-# CONFIG_COMPAT_VDSO is not set
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
-CONFIG_PM_TRACE_RTC=y
-CONFIG_ACPI_PROCFS=y
-CONFIG_ACPI_DOCK=y
+CONFIG_PHYSICAL_START=0x100000
+CONFIG_RELOCATABLE=y
+CONFIG_X86_NEED_RELOCS=y
+CONFIG_PHYSICAL_ALIGN=0x100000
+CONFIG_HOTPLUG_CPU=y
+# CONFIG_BOOTPARAM_HOTPLUG_CPU0 is not set
+# CONFIG_DEBUG_HOTPLUG_CPU0 is not set
+CONFIG_COMPAT_VDSO=y
+# CONFIG_CMDLINE_BOOL is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+
+#
+# Power management and ACPI options
+#
+# CONFIG_SUSPEND is not set
+# CONFIG_HAS_WAKELOCK is not set
+# CONFIG_WAKELOCK is not set
+# CONFIG_HIBERNATION is not set
+# CONFIG_PM_RUNTIME is not set
+# CONFIG_SUSPEND_TIME is not set
+# CONFIG_ACPI is not set
+# CONFIG_SFI is not set
+
+#
+# CPU Frequency scaling
+#
CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_COMMON=y
+CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_STAT_DETAILS=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-CONFIG_X86_ACPI_CPUFREQ=y
+# CONFIG_CPU_FREQ_GOV_INTERACTIVE is not set
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+
+#
+# x86 CPU frequency scaling drivers
+#
+# CONFIG_X86_INTEL_PSTATE is not set
+# CONFIG_X86_POWERNOW_K6 is not set
+# CONFIG_X86_POWERNOW_K7 is not set
+# CONFIG_X86_GX_SUSPMOD is not set
+# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
+# CONFIG_X86_SPEEDSTEP_ICH is not set
+# CONFIG_X86_SPEEDSTEP_SMI is not set
+# CONFIG_X86_P4_CLOCKMOD is not set
+# CONFIG_X86_CPUFREQ_NFORCE2 is not set
+# CONFIG_X86_LONGRUN is not set
+
+#
+# shared options
+#
+# CONFIG_X86_SPEEDSTEP_LIB is not set
+CONFIG_CPU_IDLE=y
+# CONFIG_CPU_IDLE_MULTIPLE_DRIVERS is not set
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
+# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
+CONFIG_INTEL_IDLE=y
+
+#
+# Bus options (PCI etc.)
+#
+CONFIG_PCI=y
+# CONFIG_PCI_GOBIOS is not set
+# CONFIG_PCI_GOMMCONFIG is not set
+# CONFIG_PCI_GODIRECT is not set
+CONFIG_PCI_GOANY=y
+CONFIG_PCI_BIOS=y
+CONFIG_PCI_DIRECT=y
+CONFIG_PCI_DOMAINS=y
CONFIG_PCIEPORTBUS=y
+# CONFIG_HOTPLUG_PCI_PCIE is not set
+CONFIG_PCIEAER=y
+# CONFIG_PCIE_ECRC is not set
+# CONFIG_PCIEAER_INJECT is not set
+CONFIG_PCIEASPM=y
+# CONFIG_PCIEASPM_DEBUG is not set
+CONFIG_PCIEASPM_DEFAULT=y
+# CONFIG_PCIEASPM_POWERSAVE is not set
+# CONFIG_PCIEASPM_PERFORMANCE is not set
+CONFIG_ARCH_SUPPORTS_MSI=y
CONFIG_PCI_MSI=y
+# CONFIG_PCI_DEBUG is not set
+# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
+# CONFIG_PCI_STUB is not set
+CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
+# CONFIG_PCI_PRI is not set
+# CONFIG_PCI_PASID is not set
+CONFIG_PCI_LABEL=y
+
+#
+# PCIE Host Controller Drivers
+#
+CONFIG_ISA_DMA_API=y
+CONFIG_ISA=y
+CONFIG_EISA=y
+CONFIG_EISA_VLB_PRIMING=y
+CONFIG_EISA_PCI_EISA=y
+CONFIG_EISA_VIRTUAL_ROOT=y
+CONFIG_EISA_NAMES=y
+# CONFIG_SCx200 is not set
+# CONFIG_ALIX is not set
+# CONFIG_NET5501 is not set
+# CONFIG_GEOS is not set
+CONFIG_AMD_NB=y
CONFIG_PCCARD=y
+# CONFIG_PCMCIA is not set
+CONFIG_CARDBUS=y
+
+#
+# PC-card bridges
+#
CONFIG_YENTA=y
+CONFIG_YENTA_O2=y
+CONFIG_YENTA_RICOH=y
+CONFIG_YENTA_TI=y
+CONFIG_YENTA_ENE_TUNE=y
+CONFIG_YENTA_TOSHIBA=y
+CONFIG_PCMCIA_PROBE=y
CONFIG_HOTPLUG_PCI=y
-CONFIG_BINFMT_MISC=y
+# CONFIG_HOTPLUG_PCI_COMPAQ is not set
+# CONFIG_HOTPLUG_PCI_IBM is not set
+CONFIG_HOTPLUG_PCI_CPCI=y
+# CONFIG_HOTPLUG_PCI_CPCI_ZT5550 is not set
+# CONFIG_HOTPLUG_PCI_CPCI_GENERIC is not set
+CONFIG_HOTPLUG_PCI_SHPC=y
+# CONFIG_RAPIDIO is not set
+
+#
+# Executable file formats / Emulations
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_SCRIPT=y
+CONFIG_HAVE_AOUT=y
+# CONFIG_BINFMT_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+CONFIG_COREDUMP=y
+CONFIG_HAVE_ATOMIC_IOMAP=y
+CONFIG_HAVE_TEXT_POKE_SMP=y
CONFIG_NET=y
+
+#
+# Networking options
+#
CONFIG_PACKET=y
+# CONFIG_PACKET_DIAG is not set
CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
+# CONFIG_UNIX_DIAG is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_ALGO=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+# CONFIG_NET_KEY_MIGRATE is not set
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
+# CONFIG_IP_FIB_TRIE_STATS is not set
CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_ROUTE_MULTIPATH=y
CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
+# CONFIG_IP_PNP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE_DEMUX is not set
+# CONFIG_NET_IP_TUNNEL is not set
CONFIG_IP_MROUTE=y
+# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
+# CONFIG_ARPD is not set
CONFIG_SYN_COOKIES=y
+# CONFIG_NET_IPVTI is not set
+# CONFIG_INET_AH is not set
+CONFIG_INET_ESP=y
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+# CONFIG_INET_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+CONFIG_INET_XFRM_MODE_TUNNEL=y
# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_DIAG is not set
-CONFIG_TCP_CONG_ADVANCED=y
-# CONFIG_TCP_CONG_BIC is not set
-# CONFIG_TCP_CONG_WESTWOOD is not set
-# CONFIG_TCP_CONG_HTCP is not set
+CONFIG_INET_LRO=y
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_INET_UDP_DIAG is not set
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
CONFIG_TCP_MD5SIG=y
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_NETLABEL=y
+# CONFIG_IPV6 is not set
+# CONFIG_NETLABEL is not set
+# CONFIG_ANDROID_PARANOID_NETWORK is not set
+# CONFIG_NET_ACTIVITY_STATS is not set
+CONFIG_NETWORK_SECMARK=y
+# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NF_CONNTRACK=y
-CONFIG_NF_CONNTRACK_FTP=y
-CONFIG_NF_CONNTRACK_IRC=y
-CONFIG_NF_CONNTRACK_SIP=y
-CONFIG_NF_CT_NETLINK=y
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
-CONFIG_NETFILTER_XT_TARGET_NFLOG=y
-CONFIG_NETFILTER_XT_TARGET_SECMARK=y
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
-CONFIG_NETFILTER_XT_MATCH_POLICY=y
-CONFIG_NETFILTER_XT_MATCH_STATE=y
-CONFIG_NF_CONNTRACK_IPV4=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
+
+#
+# Core Netfilter Configuration
+#
+# CONFIG_NETFILTER_NETLINK_ACCT is not set
+# CONFIG_NETFILTER_NETLINK_QUEUE is not set
+# CONFIG_NETFILTER_NETLINK_LOG is not set
+# CONFIG_NF_CONNTRACK is not set
+CONFIG_NETFILTER_XTABLES=y
+
+#
+# Xtables combined modules
+#
+# CONFIG_NETFILTER_XT_MARK is not set
+
+#
+# Xtables targets
+#
+# CONFIG_NETFILTER_XT_TARGET_AUDIT is not set
+# CONFIG_NETFILTER_XT_TARGET_CLASSIFY is not set
+# CONFIG_NETFILTER_XT_TARGET_HMARK is not set
+# CONFIG_NETFILTER_XT_TARGET_IDLETIMER is not set
+# CONFIG_NETFILTER_XT_TARGET_LOG is not set
+# CONFIG_NETFILTER_XT_TARGET_MARK is not set
+# CONFIG_NETFILTER_XT_TARGET_NFLOG is not set
+# CONFIG_NETFILTER_XT_TARGET_NFQUEUE is not set
+# CONFIG_NETFILTER_XT_TARGET_RATEEST is not set
+# CONFIG_NETFILTER_XT_TARGET_TEE is not set
+# CONFIG_NETFILTER_XT_TARGET_SECMARK is not set
+# CONFIG_NETFILTER_XT_TARGET_TCPMSS is not set
+
+#
+# Xtables matches
+#
+# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set
+# CONFIG_NETFILTER_XT_MATCH_BPF is not set
+# CONFIG_NETFILTER_XT_MATCH_COMMENT is not set
+# CONFIG_NETFILTER_XT_MATCH_CPU is not set
+# CONFIG_NETFILTER_XT_MATCH_DCCP is not set
+# CONFIG_NETFILTER_XT_MATCH_DEVGROUP is not set
+# CONFIG_NETFILTER_XT_MATCH_DSCP is not set
+# CONFIG_NETFILTER_XT_MATCH_ECN is not set
+# CONFIG_NETFILTER_XT_MATCH_ESP is not set
+# CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set
+# CONFIG_NETFILTER_XT_MATCH_HL is not set
+# CONFIG_NETFILTER_XT_MATCH_IPRANGE is not set
+# CONFIG_NETFILTER_XT_MATCH_LENGTH is not set
+# CONFIG_NETFILTER_XT_MATCH_LIMIT is not set
+# CONFIG_NETFILTER_XT_MATCH_MAC is not set
+# CONFIG_NETFILTER_XT_MATCH_MARK is not set
+# CONFIG_NETFILTER_XT_MATCH_MULTIPORT is not set
+# CONFIG_NETFILTER_XT_MATCH_NFACCT is not set
+# CONFIG_NETFILTER_XT_MATCH_OWNER is not set
+# CONFIG_NETFILTER_XT_MATCH_POLICY is not set
+# CONFIG_NETFILTER_XT_MATCH_PKTTYPE is not set
+# CONFIG_NETFILTER_XT_MATCH_QUOTA is not set
+# CONFIG_NETFILTER_XT_MATCH_QUOTA2 is not set
+# CONFIG_NETFILTER_XT_MATCH_RATEEST is not set
+# CONFIG_NETFILTER_XT_MATCH_REALM is not set
+# CONFIG_NETFILTER_XT_MATCH_RECENT is not set
+# CONFIG_NETFILTER_XT_MATCH_SCTP is not set
+# CONFIG_NETFILTER_XT_MATCH_STATISTIC is not set
+# CONFIG_NETFILTER_XT_MATCH_STRING is not set
+# CONFIG_NETFILTER_XT_MATCH_TCPMSS is not set
+# CONFIG_NETFILTER_XT_MATCH_TIME is not set
+# CONFIG_NETFILTER_XT_MATCH_U32 is not set
+# CONFIG_IP_VS is not set
+
+#
+# IP: Netfilter Configuration
+#
+# CONFIG_NF_DEFRAG_IPV4 is not set
CONFIG_IP_NF_IPTABLES=y
+# CONFIG_IP_NF_MATCH_AH is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
CONFIG_IP_NF_FILTER=y
-CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_ULOG=y
-CONFIG_NF_NAT=y
-CONFIG_IP_NF_TARGET_MASQUERADE=y
-CONFIG_IP_NF_MANGLE=y
-CONFIG_NF_CONNTRACK_IPV6=y
-CONFIG_IP6_NF_IPTABLES=y
-CONFIG_IP6_NF_MATCH_IPV6HEADER=y
-CONFIG_IP6_NF_FILTER=y
-CONFIG_IP6_NF_TARGET_REJECT=y
-CONFIG_IP6_NF_MANGLE=y
+# CONFIG_IP_NF_TARGET_REJECT is not set
+# CONFIG_IP_NF_TARGET_ULOG is not set
+# CONFIG_IP_NF_MANGLE is not set
+# CONFIG_IP_NF_RAW is not set
+# CONFIG_IP_NF_SECURITY is not set
+# CONFIG_IP_NF_ARPTABLES is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
+# CONFIG_TIPC is not set
+CONFIG_ATM=y
+CONFIG_ATM_CLIP=y
+# CONFIG_ATM_CLIP_NO_ICMP is not set
+# CONFIG_ATM_LANE is not set
+# CONFIG_ATM_BR2684 is not set
+# CONFIG_L2TP is not set
+# CONFIG_BRIDGE is not set
+CONFIG_HAVE_NET_DSA=y
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_PHONET is not set
+# CONFIG_MHI is not set
+# CONFIG_IEEE802154 is not set
CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+# CONFIG_NET_SCH_CBQ is not set
+# CONFIG_NET_SCH_HTB is not set
+# CONFIG_NET_SCH_HFSC is not set
+# CONFIG_NET_SCH_ATM is not set
+# CONFIG_NET_SCH_PRIO is not set
+# CONFIG_NET_SCH_MULTIQ is not set
+# CONFIG_NET_SCH_RED is not set
+# CONFIG_NET_SCH_SFB is not set
+# CONFIG_NET_SCH_SFQ is not set
+# CONFIG_NET_SCH_TEQL is not set
+# CONFIG_NET_SCH_TBF is not set
+# CONFIG_NET_SCH_GRED is not set
+# CONFIG_NET_SCH_DSMARK is not set
+# CONFIG_NET_SCH_NETEM is not set
+# CONFIG_NET_SCH_DRR is not set
+# CONFIG_NET_SCH_MQPRIO is not set
+# CONFIG_NET_SCH_CHOKE is not set
+# CONFIG_NET_SCH_QFQ is not set
+# CONFIG_NET_SCH_CODEL is not set
+# CONFIG_NET_SCH_FQ_CODEL is not set
+# CONFIG_NET_SCH_INGRESS is not set
+# CONFIG_NET_SCH_PLUG is not set
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+# CONFIG_NET_CLS_BASIC is not set
+# CONFIG_NET_CLS_TCINDEX is not set
+# CONFIG_NET_CLS_ROUTE4 is not set
+# CONFIG_NET_CLS_FW is not set
+# CONFIG_NET_CLS_U32 is not set
+# CONFIG_NET_CLS_RSVP is not set
+# CONFIG_NET_CLS_RSVP6 is not set
+# CONFIG_NET_CLS_FLOW is not set
+# CONFIG_NET_CLS_CGROUP is not set
CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+# CONFIG_NET_EMATCH_CMP is not set
+# CONFIG_NET_EMATCH_NBYTE is not set
+# CONFIG_NET_EMATCH_U32 is not set
+# CONFIG_NET_EMATCH_META is not set
+# CONFIG_NET_EMATCH_TEXT is not set
CONFIG_NET_CLS_ACT=y
-CONFIG_HAMRADIO=y
-CONFIG_CFG80211=y
-CONFIG_MAC80211=y
-CONFIG_MAC80211_LEDS=y
-CONFIG_RFKILL=y
+# CONFIG_NET_ACT_POLICE is not set
+# CONFIG_NET_ACT_GACT is not set
+# CONFIG_NET_ACT_MIRRED is not set
+# CONFIG_NET_ACT_IPT is not set
+# CONFIG_NET_ACT_NAT is not set
+# CONFIG_NET_ACT_PEDIT is not set
+# CONFIG_NET_ACT_SIMP is not set
+# CONFIG_NET_ACT_SKBEDIT is not set
+# CONFIG_NET_ACT_CSUM is not set
+CONFIG_NET_SCH_FIFO=y
+# CONFIG_DCB is not set
+CONFIG_DNS_RESOLVER=y
+# CONFIG_BATMAN_ADV is not set
+# CONFIG_OPENVSWITCH is not set
+# CONFIG_VSOCKETS is not set
+# CONFIG_NETLINK_MMAP is not set
+# CONFIG_NETLINK_DIAG is not set
+# CONFIG_RMNET_DATA is not set
+# CONFIG_NETPRIO_CGROUP is not set
+CONFIG_BQL=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+CONFIG_FIB_RULES=y
+# CONFIG_WIRELESS is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
+# CONFIG_CEPH_LIB is not set
+# CONFIG_NFC is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEBUG_DEVRES=y
-CONFIG_CONNECTOR=y
+CONFIG_DEVTMPFS=y
+# CONFIG_DEVTMPFS_MOUNT is not set
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+CONFIG_FW_LOADER_USER_HELPER=y
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_GENERIC_CPU_DEVICES is not set
+CONFIG_HAVE_CPU_AUTOPROBE=y
+# CONFIG_DMA_SHARED_BUFFER is not set
+# CONFIG_CMA is not set
+
+#
+# Bus devices
+#
+# CONFIG_CONNECTOR is not set
+# CONFIG_MTD is not set
+CONFIG_PARPORT=y
+CONFIG_PARPORT_PC=y
+# CONFIG_PARPORT_SERIAL is not set
+CONFIG_PARPORT_PC_FIFO=y
+# CONFIG_PARPORT_PC_SUPERIO is not set
+# CONFIG_PARPORT_GSC is not set
+# CONFIG_PARPORT_AX88796 is not set
+CONFIG_PARPORT_1284=y
+CONFIG_PNP=y
+CONFIG_PNP_DEBUG_MESSAGES=y
+
+#
+# Protocols
+#
+CONFIG_ISAPNP=y
+CONFIG_PNPBIOS=y
+CONFIG_PNPBIOS_PROC_FS=y
+# CONFIG_PNPACPI is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_PARIDE is not set
+# CONFIG_BLK_DEV_PCIESSD_MTIP32XX is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
+# CONFIG_BLK_DEV_CRYPTOLOOP is not set
+# CONFIG_BLK_DEV_DRBD is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_NVME is not set
+# CONFIG_BLK_DEV_SX8 is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=65536
+# CONFIG_BLK_DEV_XIP is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+CONFIG_VIRTIO_BLK=y
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_BLK_DEV_RBD is not set
+# CONFIG_BLK_DEV_RSXX is not set
+
+#
+# Misc devices
+#
+# CONFIG_SENSORS_LIS3LV02D is not set
+# CONFIG_AD525X_DPOT is not set
+# CONFIG_DUMMY_IRQ is not set
+# CONFIG_IBM_ASM is not set
+# CONFIG_PHANTOM is not set
+# CONFIG_INTEL_MID_PTI is not set
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+# CONFIG_ICS932S401 is not set
+# CONFIG_ATMEL_SSC is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_KERNEL_DEBUGGER_CORE is not set
+# CONFIG_HP_ILO is not set
+# CONFIG_APDS9802ALS is not set
+# CONFIG_ISL29003 is not set
+# CONFIG_ISL29020 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_SENSORS_BH1780 is not set
+# CONFIG_SENSORS_BH1770 is not set
+# CONFIG_SENSORS_APDS990X is not set
+# CONFIG_HMC6352 is not set
+# CONFIG_SENSORS_NCT1008 is not set
+# CONFIG_DS1682 is not set
+# CONFIG_UID_STAT is not set
+# CONFIG_VMWARE_BALLOON is not set
+# CONFIG_BMP085_I2C is not set
+# CONFIG_PCH_PHUB is not set
+# CONFIG_USB_SWITCH_FSA9480 is not set
+# CONFIG_SRAM is not set
+# CONFIG_BCM4329_RFKILL is not set
+# CONFIG_TEGRA_CRYPTO_DEV is not set
+# CONFIG_APANIC is not set
+CONFIG_APANIC_PLABEL="kpanic"
+# CONFIG_THERM_EST is not set
+# CONFIG_FAN_THERM_EST is not set
+# CONFIG_BLUEDROID_PM is not set
+CONFIG_CPULOAD_MONITOR=y
+# CONFIG_MODS is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_LEGACY is not set
+# CONFIG_EEPROM_MAX6875 is not set
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
+
+#
+# Texas Instruments shared transport line discipline
+#
+# CONFIG_ST_GPS is not set
+# CONFIG_SENSORS_LIS3_I2C is not set
+
+#
+# Altera FPGA firmware download module
+#
+# CONFIG_ALTERA_STAPL is not set
+# CONFIG_INTEL_MEI is not set
+# CONFIG_INTEL_MEI_ME is not set
+# CONFIG_VMWARE_VMCI is not set
+# CONFIG_ISSP is not set
+# CONFIG_GPS is not set
+# CONFIG_HTC_HEADSET_MGR is not set
+# CONFIG_HEADSET_DEBUG_UART is not set
+
+#
+# Qualcomm Modem Drivers
+#
+CONFIG_HAVE_IDE=y
+CONFIG_IDE=y
+
+#
+# Please see Documentation/ide/ide.txt for help/info on IDE drives
+#
+CONFIG_IDE_ATAPI=y
+# CONFIG_BLK_DEV_IDE_SATA is not set
+CONFIG_IDE_GD=y
+CONFIG_IDE_GD_ATA=y
+# CONFIG_IDE_GD_ATAPI is not set
+# CONFIG_BLK_DEV_DELKIN is not set
+CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+CONFIG_IDE_PROC_FS=y
+
+#
+# IDE chipset support/bugfixes
+#
+# CONFIG_IDE_GENERIC is not set
+# CONFIG_BLK_DEV_PLATFORM is not set
+# CONFIG_BLK_DEV_CMD640 is not set
+# CONFIG_BLK_DEV_IDEPNP is not set
+
+#
+# PCI IDE chipsets support
+#
+# CONFIG_BLK_DEV_GENERIC is not set
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_RZ1000 is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_CS5535 is not set
+# CONFIG_BLK_DEV_CS5536 is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_JMICRON is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_IT8172 is not set
+# CONFIG_BLK_DEV_IT8213 is not set
+# CONFIG_BLK_DEV_IT821X is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SIS5513 is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_BLK_DEV_TC86C001 is not set
+
+#
+# Other IDE chipsets support
+#
+
+#
+# Note: most of these also require special kernel boot parameters
+#
+# CONFIG_BLK_DEV_4DRIVES is not set
+# CONFIG_BLK_DEV_ALI14XX is not set
+# CONFIG_BLK_DEV_DTC2278 is not set
+# CONFIG_BLK_DEV_HT6560B is not set
+# CONFIG_BLK_DEV_QD65XX is not set
+# CONFIG_BLK_DEV_UMC8672 is not set
+# CONFIG_BLK_DEV_IDEDMA is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI_MOD=y
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
+# CONFIG_SCSI_TGT is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
CONFIG_BLK_DEV_SD=y
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
CONFIG_BLK_DEV_SR=y
CONFIG_BLK_DEV_SR_VENDOR=y
CONFIG_CHR_DEV_SG=y
+# CONFIG_CHR_DEV_SCH is not set
+CONFIG_SCSI_MULTI_LUN=y
CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_SPI_ATTRS=y
-# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_SCSI_LOGGING=y
+# CONFIG_SCSI_SCAN_ASYNC is not set
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_ISCSI_BOOT_SYSFS is not set
+# CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_CXGB4_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
+# CONFIG_SCSI_BNX2X_FCOE is not set
+# CONFIG_BE2ISCSI is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_HPSA is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_3W_SAS is not set
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AHA1740 is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
+# CONFIG_SCSI_MVUMI is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_SCSI_ARCMSR is not set
+CONFIG_MEGARAID_NEWGEN=y
+# CONFIG_MEGARAID_MM is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_MEGARAID_SAS is not set
+# CONFIG_SCSI_MPT2SAS is not set
+# CONFIG_SCSI_MPT3SAS is not set
+# CONFIG_SCSI_UFSHCD is not set
+# CONFIG_SCSI_HPTIOP is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_VMWARE_PVSCSI is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_FCOE is not set
+# CONFIG_FCOE_FNIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_ISCI is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_PPA is not set
+# CONFIG_SCSI_IMM is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_STEX is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+# CONFIG_SCSI_QLA_FC is not set
+# CONFIG_SCSI_QLA_ISCSI is not set
+# CONFIG_SCSI_LPFC is not set
+# CONFIG_SCSI_SIM710 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_PMCRAID is not set
+# CONFIG_SCSI_PM8001 is not set
+# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_BFA_FC is not set
+# CONFIG_SCSI_VIRTIO is not set
+# CONFIG_SCSI_CHELSIO_FCOE is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=y
+# CONFIG_ATA_NONSTANDARD is not set
+CONFIG_ATA_VERBOSE_ERROR=y
+CONFIG_SATA_PMP=y
+
+#
+# Controllers with non-SFF native interface
+#
CONFIG_SATA_AHCI=y
+# CONFIG_SATA_AHCI_PLATFORM is not set
+# CONFIG_SATA_AHCI_TEGRA is not set
+# CONFIG_SATA_INIC162X is not set
+# CONFIG_SATA_ACARD_AHCI is not set
+# CONFIG_SATA_SIL24 is not set
+CONFIG_ATA_SFF=y
+
+#
+# SFF controllers with custom DMA interface
+#
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_SX4 is not set
+CONFIG_ATA_BMDMA=y
+
+#
+# SATA SFF controllers with BMDMA
+#
CONFIG_ATA_PIIX=y
-CONFIG_PATA_AMD=y
-CONFIG_PATA_OLDPIIX=y
-CONFIG_PATA_SCH=y
-CONFIG_PATA_MPIIX=y
+# CONFIG_SATA_HIGHBANK is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_SVW is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+
+#
+# PATA SFF controllers with BMDMA
+#
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_ATP867X is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CS5535 is not set
+# CONFIG_PATA_CS5536 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT8213 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NINJA32 is not set
+# CONFIG_PATA_NS87415 is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RDC is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SCH is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_TOSHIBA is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+
+#
+# PIO-only SFF controllers
+#
+# CONFIG_PATA_CMD640_PCI is not set
+# CONFIG_PATA_ISAPNP is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_QDI is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_WINBOND_VLB is not set
+
+#
+# Generic fallback / legacy drivers
+#
CONFIG_ATA_GENERIC=y
+# CONFIG_PATA_LEGACY is not set
CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
+# CONFIG_BLK_DEV_MD is not set
+# CONFIG_BCACHE is not set
+CONFIG_BLK_DEV_DM_BUILTIN=y
CONFIG_BLK_DEV_DM=y
+# CONFIG_DM_DEBUG is not set
+# CONFIG_DM_CRYPT is not set
+CONFIG_DM_SNAPSHOT=y
+# CONFIG_DM_THIN_PROVISIONING is not set
+# CONFIG_DM_CACHE is not set
CONFIG_DM_MIRROR=y
-CONFIG_DM_ZERO=y
+# CONFIG_DM_RAID is not set
+# CONFIG_DM_LOG_USERSPACE is not set
+# CONFIG_DM_ZERO is not set
+# CONFIG_DM_MULTIPATH is not set
+# CONFIG_DM_DELAY is not set
+CONFIG_DM_UEVENT=y
+# CONFIG_DM_FLAKEY is not set
+# CONFIG_DM_VERITY is not set
+# CONFIG_TARGET_CORE is not set
+CONFIG_FUSION=y
+# CONFIG_FUSION_SPI is not set
+# CONFIG_FUSION_FC is not set
+# CONFIG_FUSION_SAS is not set
+CONFIG_FUSION_MAX_SGE=128
+CONFIG_FUSION_LOGGING=y
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_FIREWIRE is not set
+# CONFIG_FIREWIRE_NOSY is not set
+# CONFIG_I2O is not set
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_MAC_EMUMOUSEBTN=y
CONFIG_NETDEVICES=y
-CONFIG_NETCONSOLE=y
-CONFIG_BNX2=y
+CONFIG_NET_CORE=y
+# CONFIG_BONDING is not set
+CONFIG_DUMMY=y
+# CONFIG_EQUALIZER is not set
+CONFIG_NET_FC=y
+CONFIG_MII=y
+# CONFIG_IFB is not set
+# CONFIG_NET_TEAM is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_VXLAN is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+CONFIG_TUN=y
+CONFIG_VETH=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_ARCNET is not set
+CONFIG_ATM_DRIVERS=y
+# CONFIG_ATM_DUMMY is not set
+# CONFIG_ATM_TCP is not set
+# CONFIG_ATM_LANAI is not set
+# CONFIG_ATM_ENI is not set
+# CONFIG_ATM_FIRESTREAM is not set
+# CONFIG_ATM_ZATM is not set
+# CONFIG_ATM_NICSTAR is not set
+# CONFIG_ATM_IDT77252 is not set
+# CONFIG_ATM_AMBASSADOR is not set
+# CONFIG_ATM_HORIZON is not set
+# CONFIG_ATM_IA is not set
+# CONFIG_ATM_FORE200E is not set
+# CONFIG_ATM_HE is not set
+# CONFIG_ATM_SOLOS is not set
+
+#
+# CAIF transport drivers
+#
+# CONFIG_VHOST_NET is not set
+
+#
+# Distributed Switch Architecture drivers
+#
+# CONFIG_NET_DSA_MV88E6XXX is not set
+# CONFIG_NET_DSA_MV88E6060 is not set
+# CONFIG_NET_DSA_MV88E6XXX_NEED_PPU is not set
+# CONFIG_NET_DSA_MV88E6131 is not set
+# CONFIG_NET_DSA_MV88E6123_61_65 is not set
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_3COM=y
+# CONFIG_EL3 is not set
+# CONFIG_3C515 is not set
+# CONFIG_VORTEX is not set
+# CONFIG_TYPHOON is not set
+CONFIG_NET_VENDOR_ADAPTEC=y
+# CONFIG_ADAPTEC_STARFIRE is not set
+CONFIG_NET_VENDOR_ALTEON=y
+# CONFIG_ACENIC is not set
+CONFIG_NET_VENDOR_AMD=y
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_LANCE is not set
+# CONFIG_PCNET32 is not set
+# CONFIG_NI65 is not set
+CONFIG_NET_VENDOR_ATHEROS=y
+# CONFIG_ATL2 is not set
+# CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
+# CONFIG_ALX is not set
+CONFIG_NET_CADENCE=y
+# CONFIG_ARM_AT91_ETHER is not set
+# CONFIG_MACB is not set
+CONFIG_NET_VENDOR_BROADCOM=y
+# CONFIG_B44 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_CNIC is not set
CONFIG_TIGON3=y
-CONFIG_NET_TULIP=y
-CONFIG_E100=y
-CONFIG_E1000=y
+# CONFIG_BNX2X is not set
+CONFIG_NET_VENDOR_BROCADE=y
+# CONFIG_BNA is not set
+# CONFIG_NET_CALXEDA_XGMAC is not set
+CONFIG_NET_VENDOR_CHELSIO=y
+# CONFIG_CHELSIO_T1 is not set
+# CONFIG_CHELSIO_T3 is not set
+# CONFIG_CHELSIO_T4 is not set
+# CONFIG_CHELSIO_T4VF is not set
+CONFIG_NET_VENDOR_CIRRUS=y
+# CONFIG_CS89x0 is not set
+CONFIG_NET_VENDOR_CISCO=y
+# CONFIG_ENIC is not set
+# CONFIG_DNET is not set
+CONFIG_NET_VENDOR_DEC=y
+# CONFIG_NET_TULIP is not set
+CONFIG_NET_VENDOR_DLINK=y
+# CONFIG_DL2K is not set
+# CONFIG_SUNDANCE is not set
+CONFIG_NET_VENDOR_EMULEX=y
+# CONFIG_BE2NET is not set
+CONFIG_NET_VENDOR_EXAR=y
+# CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
+CONFIG_NET_VENDOR_FUJITSU=y
+CONFIG_NET_VENDOR_HP=y
+# CONFIG_HP100 is not set
+CONFIG_NET_VENDOR_INTEL=y
+# CONFIG_E100 is not set
+# CONFIG_E1000 is not set
CONFIG_E1000E=y
-CONFIG_SKY2=y
-CONFIG_NE2K_PCI=y
-CONFIG_FORCEDETH=y
-CONFIG_8139TOO=y
-# CONFIG_8139TOO_PIO is not set
-CONFIG_R8169=y
+# CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
+# CONFIG_IXGB is not set
+# CONFIG_IXGBE is not set
+# CONFIG_IXGBEVF is not set
+CONFIG_NET_VENDOR_I825XX=y
+# CONFIG_IP1000 is not set
+# CONFIG_JME is not set
+CONFIG_NET_VENDOR_MARVELL=y
+# CONFIG_MVMDIO is not set
+# CONFIG_SKGE is not set
+# CONFIG_SKY2 is not set
+CONFIG_NET_VENDOR_MELLANOX=y
+# CONFIG_MLX4_EN is not set
+# CONFIG_MLX4_CORE is not set
+CONFIG_NET_VENDOR_MICREL=y
+# CONFIG_KS8851_MLL is not set
+# CONFIG_KSZ884X_PCI is not set
+CONFIG_NET_VENDOR_MYRI=y
+# CONFIG_MYRI10GE is not set
+# CONFIG_FEALNX is not set
+CONFIG_NET_VENDOR_NATSEMI=y
+# CONFIG_NATSEMI is not set
+# CONFIG_NS83820 is not set
+CONFIG_NET_VENDOR_8390=y
+# CONFIG_NE2000 is not set
+# CONFIG_NE2K_PCI is not set
+# CONFIG_ULTRA is not set
+# CONFIG_WD80x3 is not set
+CONFIG_NET_VENDOR_NVIDIA=y
+# CONFIG_FORCEDETH is not set
+CONFIG_NET_VENDOR_OKI=y
+# CONFIG_PCH_GBE is not set
+# CONFIG_ETHOC is not set
+CONFIG_NET_PACKET_ENGINE=y
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+CONFIG_NET_VENDOR_QLOGIC=y
+# CONFIG_QLA3XXX is not set
+# CONFIG_QLCNIC is not set
+# CONFIG_QLGE is not set
+# CONFIG_NETXEN_NIC is not set
+CONFIG_NET_VENDOR_REALTEK=y
+# CONFIG_ATP is not set
+# CONFIG_8139CP is not set
+# CONFIG_8139TOO is not set
+# CONFIG_R8169 is not set
+CONFIG_NET_VENDOR_RDC=y
+# CONFIG_R6040 is not set
+CONFIG_NET_VENDOR_SEEQ=y
+CONFIG_NET_VENDOR_SILAN=y
+# CONFIG_SC92031 is not set
+CONFIG_NET_VENDOR_SIS=y
+# CONFIG_SIS900 is not set
+# CONFIG_SIS190 is not set
+# CONFIG_SFC is not set
+CONFIG_NET_VENDOR_SMSC=y
+# CONFIG_SMC9194 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SMSC9420 is not set
+CONFIG_NET_VENDOR_STMICRO=y
+# CONFIG_STMMAC_ETH is not set
+CONFIG_NET_VENDOR_SUN=y
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNGEM is not set
+# CONFIG_CASSINI is not set
+# CONFIG_NIU is not set
+CONFIG_NET_VENDOR_TEHUTI=y
+# CONFIG_TEHUTI is not set
+CONFIG_NET_VENDOR_TI=y
+# CONFIG_TLAN is not set
+CONFIG_NET_VENDOR_VIA=y
+# CONFIG_VIA_RHINE is not set
+# CONFIG_VIA_VELOCITY is not set
+CONFIG_NET_VENDOR_WIZNET=y
+# CONFIG_WIZNET_W5100 is not set
+# CONFIG_WIZNET_W5300 is not set
CONFIG_FDDI=y
-CONFIG_INPUT_POLLDEV=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+# CONFIG_DEFXX is not set
+# CONFIG_SKFP is not set
+CONFIG_HIPPI=y
+# CONFIG_ROADRUNNER is not set
+# CONFIG_NET_SB1000 is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_AT803X_PHY is not set
+# CONFIG_AMD_PHY is not set
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+# CONFIG_SMSC_PHY is not set
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_BCM87XX_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_MICREL_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
+# CONFIG_PLIP is not set
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_FILTER=y
+# CONFIG_PPP_MPPE is not set
+CONFIG_PPP_MULTILINK=y
+# CONFIG_PPPOATM is not set
+# CONFIG_PPPOE is not set
+# CONFIG_PPPOLAC is not set
+# CONFIG_PPPOPNS is not set
+CONFIG_PPP_ASYNC=y
+# CONFIG_PPP_SYNC_TTY is not set
+# CONFIG_SLIP is not set
+CONFIG_SLHC=y
+# CONFIG_WLAN is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+CONFIG_WAN=y
+# CONFIG_HDLC is not set
+# CONFIG_DLCI is not set
+# CONFIG_SBNI is not set
+# CONFIG_VMXNET3 is not set
+CONFIG_ISDN=y
+# CONFIG_ISDN_I4L is not set
+# CONFIG_ISDN_CAPI is not set
+# CONFIG_ISDN_DRV_GIGASET is not set
+# CONFIG_HYSDN is not set
+# CONFIG_MISDN is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+# CONFIG_INPUT_SPARSEKMAP is not set
+# CONFIG_INPUT_MATRIXKMAP is not set
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_INPUT_MOUSEDEV_PSAUX=y
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_EVBUG is not set
+# CONFIG_INPUT_KEYRESET is not set
+# CONFIG_INPUT_KEYCOMBO is not set
+# CONFIG_INPUT_CFBOOST is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+# CONFIG_KEYBOARD_ADP5588 is not set
+# CONFIG_KEYBOARD_ADP5589 is not set
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_QT1070 is not set
+# CONFIG_KEYBOARD_QT2160 is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_TCA6416 is not set
+# CONFIG_KEYBOARD_TCA8418 is not set
+# CONFIG_KEYBOARD_LM8333 is not set
+# CONFIG_KEYBOARD_MAX7359 is not set
+# CONFIG_KEYBOARD_MCS is not set
+# CONFIG_KEYBOARD_MPR121 is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_OPENCORES is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_CYPRESS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_ELANTECH is not set
+# CONFIG_MOUSE_PS2_SENTELIC is not set
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_CYAPA is not set
+# CONFIG_MOUSE_INPORT is not set
+# CONFIG_MOUSE_LOGIBM is not set
+# CONFIG_MOUSE_PC110PAD is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_MOUSE_SYNAPTICS_I2C is not set
CONFIG_INPUT_JOYSTICK=y
+# CONFIG_JOYSTICK_ANALOG is not set
+# CONFIG_JOYSTICK_A3D is not set
+# CONFIG_JOYSTICK_ADI is not set
+# CONFIG_JOYSTICK_COBRA is not set
+# CONFIG_JOYSTICK_GF2K is not set
+# CONFIG_JOYSTICK_GRIP is not set
+# CONFIG_JOYSTICK_GRIP_MP is not set
+# CONFIG_JOYSTICK_GUILLEMOT is not set
+# CONFIG_JOYSTICK_INTERACT is not set
+# CONFIG_JOYSTICK_SIDEWINDER is not set
+# CONFIG_JOYSTICK_TMDC is not set
+# CONFIG_JOYSTICK_IFORCE is not set
+# CONFIG_JOYSTICK_WARRIOR is not set
+# CONFIG_JOYSTICK_MAGELLAN is not set
+# CONFIG_JOYSTICK_SPACEORB is not set
+# CONFIG_JOYSTICK_SPACEBALL is not set
+# CONFIG_JOYSTICK_STINGER is not set
+# CONFIG_JOYSTICK_TWIDJOY is not set
+# CONFIG_JOYSTICK_ZHENHUA is not set
+# CONFIG_JOYSTICK_DB9 is not set
+# CONFIG_JOYSTICK_GAMECON is not set
+# CONFIG_JOYSTICK_TURBOGRAFX is not set
+# CONFIG_JOYSTICK_AS5011 is not set
+# CONFIG_JOYSTICK_JOYDUMP is not set
+# CONFIG_JOYSTICK_WALKERA0701 is not set
CONFIG_INPUT_TABLET=y
CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879 is not set
+# CONFIG_TOUCHSCREEN_ATMEL_MXT is not set
+# CONFIG_TOUCHSCREEN_BU21013 is not set
+# CONFIG_CYPRESS_SAR is not set
+# CONFIG_TOUCHSCREEN_CYTTSP_CORE is not set
+# CONFIG_TOUCHSCREEN_DYNAPRO is not set
+# CONFIG_TOUCHSCREEN_HAMPSHIRE is not set
+# CONFIG_TOUCHSCREEN_EETI is not set
+# CONFIG_TOUCHSCREEN_FUJITSU is not set
+# CONFIG_TOUCHSCREEN_ILI210X is not set
+# CONFIG_TOUCHSCREEN_GUNZE is not set
+# CONFIG_TOUCHSCREEN_ELO is not set
+# CONFIG_TOUCHSCREEN_WACOM_W8001 is not set
+# CONFIG_TOUCHSCREEN_WACOM_I2C is not set
+# CONFIG_TOUCHSCREEN_MAX11801 is not set
+# CONFIG_TOUCHSCREEN_MCS5000 is not set
+# CONFIG_TOUCHSCREEN_MMS114 is not set
+# CONFIG_TOUCHSCREEN_MTOUCH is not set
+# CONFIG_TOUCHSCREEN_INEXIO is not set
+# CONFIG_TOUCHSCREEN_MK712 is not set
+# CONFIG_TOUCHSCREEN_HTCPEN is not set
+# CONFIG_TOUCHSCREEN_PENMOUNT is not set
+# CONFIG_TOUCHSCREEN_EDT_FT5X06 is not set
+# CONFIG_TOUCHSCREEN_PANJIT_I2C is not set
+# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
+# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
+# CONFIG_TOUCHSCREEN_PIXCIR is not set
+# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set
+# CONFIG_TOUCHSCREEN_TSC_SERIO is not set
+# CONFIG_TOUCHSCREEN_TSC2007 is not set
+# CONFIG_TOUCHSCREEN_ST1232 is not set
+# CONFIG_TOUCHSCREEN_TPS6507X is not set
+# CONFIG_TOUCHSCREEN_MAX1187X is not set
+CONFIG_TOUCHSCREEN_SYNAPTICS_DSX=y
+CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_I2C=y
+# CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_RMI_HID_I2C is not set
+# CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_CORE is not set
CONFIG_INPUT_MISC=y
+# CONFIG_INPUT_AD714X is not set
+# CONFIG_INPUT_BMA150 is not set
+# CONFIG_INPUT_PCSPKR is not set
+# CONFIG_INPUT_MMA8450 is not set
+# CONFIG_INPUT_MPU3050 is not set
+# CONFIG_INPUT_WISTRON_BTNS is not set
+# CONFIG_INPUT_KEYCHORD is not set
+# CONFIG_INPUT_KXTJ9 is not set
+CONFIG_INPUT_UINPUT=y
+# CONFIG_INPUT_GPIO is not set
+# CONFIG_INPUT_PCF8574 is not set
+# CONFIG_INPUT_ADXL34X is not set
+# CONFIG_INPUT_CMA3000 is not set
+# CONFIG_INPUT_DRV2603_VIBRATOR is not set
+# CONFIG_INV_AK8975 is not set
+# CONFIG_INV_MPU is not set
+# CONFIG_INV_BMP180 is not set
+
+#
+# Hardware I/O ports
+#
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+# CONFIG_SERIO_SERPORT is not set
+# CONFIG_SERIO_CT82C710 is not set
+# CONFIG_SERIO_PARKBD is not set
+# CONFIG_SERIO_PCIPS2 is not set
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIO_RAW=y
+# CONFIG_SERIO_ALTERA_PS2 is not set
+# CONFIG_SERIO_PS2MULT is not set
+# CONFIG_SERIO_ARC_PS2 is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_TTY=y
+CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_LEGACY_PTYS is not set
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_ROCKETPORT is not set
+# CONFIG_CYCLADES is not set
+# CONFIG_MOXA_INTELLIO is not set
+# CONFIG_MOXA_SMARTIO is not set
+# CONFIG_SYNCLINK is not set
+# CONFIG_SYNCLINKMP is not set
+# CONFIG_SYNCLINK_GT is not set
+# CONFIG_NOZOMI is not set
+# CONFIG_ISI is not set
+# CONFIG_N_HDLC is not set
+# CONFIG_N_GSM is not set
+# CONFIG_TRACE_SINK is not set
+CONFIG_DEVMEM=y
+CONFIG_DEVKMEM=y
+CONFIG_STALDRV=y
+
+#
+# Serial drivers
+#
CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y
+CONFIG_SERIAL_8250_PNP=y
CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_FIX_EARLYCON_MEM=y
+CONFIG_SERIAL_8250_PCI=y
+CONFIG_SERIAL_8250_NR_UARTS=48
+CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
CONFIG_SERIAL_8250_MANY_PORTS=y
+# CONFIG_HAS_NS_SUPER_IO_CHIP is not set
+# CONFIG_SERIAL_8250_FOURPORT is not set
+# CONFIG_SERIAL_8250_ACCENT is not set
+# CONFIG_SERIAL_8250_BOCA is not set
+# CONFIG_SERIAL_8250_EXAR_ST16C554 is not set
+# CONFIG_SERIAL_8250_HUB6 is not set
CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_8250_DETECT_IRQ=y
+# CONFIG_SERIAL_8250_DETECT_IRQ is not set
CONFIG_SERIAL_8250_RSA=y
+# CONFIG_SERIAL_8250_DW is not set
+
+#
+# Non-8250 serial port support
+#
+# CONFIG_SERIAL_MFD_HSU is not set
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_SCCNXP is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
+# CONFIG_SERIAL_ALTERA_JTAGUART is not set
+# CONFIG_SERIAL_ALTERA_UART is not set
+# CONFIG_SERIAL_PCH_UART is not set
+# CONFIG_SERIAL_ARC is not set
+# CONFIG_SERIAL_RP2 is not set
+
+#
+# Diag Support
+#
+
+#
+# DIAG traffic over USB
+#
+
+#
+# SDIO support for DIAG
+#
+
+#
+# HSIC/SMUX support for DIAG
+#
+CONFIG_PRINTER=y
+# CONFIG_LP_CONSOLE is not set
+# CONFIG_PPDEV is not set
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
+# CONFIG_HW_RANDOM_GEODE is not set
+# CONFIG_HW_RANDOM_VIA is not set
+CONFIG_HW_RANDOM_VIRTIO=y
CONFIG_NVRAM=y
-CONFIG_HPET=y
-# CONFIG_HPET_MMAP is not set
-CONFIG_I2C_I801=y
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+# CONFIG_MWAVE is not set
+# CONFIG_PC8736x_GPIO is not set
+# CONFIG_NSC_GPIO is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HANGCHECK_TIMER is not set
+# CONFIG_TCG_TPM is not set
+# CONFIG_TELCLOCK is not set
+CONFIG_DEVPORT=y
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_COMPAT=y
+# CONFIG_I2C_CHARDEV is not set
+# CONFIG_I2C_MUX is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_INPUT_CWSTM32 is not set
+# CONFIG_I2C_SLAVE is not set
+# CONFIG_I2C_HELPER_AUTO is not set
+# CONFIG_I2C_SMBUS is not set
+
+#
+# I2C Algorithms
+#
+CONFIG_I2C_ALGOBIT=y
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# PC SMBus host controller drivers
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+CONFIG_I2C_ISCH=y
+# CONFIG_I2C_ISMT is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_DESIGNWARE_PCI is not set
+# CONFIG_I2C_EG20T is not set
+# CONFIG_I2C_INTEL_MID is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_PXA_PCI is not set
+# CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_XILINX is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_ISA is not set
+# CONFIG_SCx200_ACB is not set
+# CONFIG_I2C_PCA_GMI is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_SPI is not set
+
+#
+# Qualcomm MSM SSBI bus support
+#
+# CONFIG_SSBI is not set
+# CONFIG_HSI is not set
+
+#
+# PPS support
+#
+CONFIG_PPS=y
+# CONFIG_PPS_DEBUG is not set
+
+#
+# PPS clients support
+#
+# CONFIG_PPS_CLIENT_KTIMER is not set
+# CONFIG_PPS_CLIENT_LDISC is not set
+# CONFIG_PPS_CLIENT_PARPORT is not set
+# CONFIG_PPS_CLIENT_GPIO is not set
+
+#
+# PPS generators support
+#
+
+#
+# PTP clock support
+#
+CONFIG_PTP_1588_CLOCK=y
+
+#
+# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
+#
+# CONFIG_PTP_1588_CLOCK_PCH is not set
+CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
+CONFIG_GPIO_DEVRES=y
+# CONFIG_GPIOLIB is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_POWER_AVS is not set
+CONFIG_HWMON=y
+# CONFIG_HWMON_VID is not set
+# CONFIG_HWMON_DEBUG_CHIP is not set
+
+#
+# Native drivers
+#
+# CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ABITUGURU3 is not set
+# CONFIG_SENSORS_AD7414 is not set
+# CONFIG_SENSORS_AD7418 is not set
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1026 is not set
+# CONFIG_SENSORS_ADM1029 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ADT7410 is not set
+# CONFIG_SENSORS_ADT7411 is not set
+# CONFIG_SENSORS_ADT7462 is not set
+# CONFIG_SENSORS_ADT7470 is not set
+# CONFIG_SENSORS_ADT7475 is not set
+# CONFIG_SENSORS_ASC7621 is not set
+# CONFIG_SENSORS_K8TEMP is not set
+# CONFIG_SENSORS_K10TEMP is not set
+# CONFIG_SENSORS_FAM15H_POWER is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATXP1 is not set
+# CONFIG_SENSORS_DS620 is not set
+# CONFIG_SENSORS_DS1621 is not set
+# CONFIG_SENSORS_I5K_AMB is not set
+# CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_F71882FG is not set
+# CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
+# CONFIG_SENSORS_HIH6130 is not set
+# CONFIG_SENSORS_CORETEMP is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_JC42 is not set
+# CONFIG_SENSORS_LINEAGE is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM73 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
+# CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4151 is not set
+# CONFIG_SENSORS_LTC4215 is not set
+# CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LTC4261 is not set
+# CONFIG_SENSORS_LM95234 is not set
+# CONFIG_SENSORS_LM95241 is not set
+# CONFIG_SENSORS_LM95245 is not set
+# CONFIG_SENSORS_MAX16065 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_MAX1668 is not set
+# CONFIG_SENSORS_MAX197 is not set
+# CONFIG_SENSORS_MAX6639 is not set
+# CONFIG_SENSORS_MAX6642 is not set
+# CONFIG_SENSORS_MAX6650 is not set
+# CONFIG_SENSORS_MAX6697 is not set
+# CONFIG_SENSORS_MCP3021 is not set
+# CONFIG_SENSORS_NCT6775 is not set
+# CONFIG_SENSORS_NTC_THERMISTOR is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_PMBUS is not set
+# CONFIG_SENSORS_SHT21 is not set
+# CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_SMM665 is not set
+# CONFIG_SENSORS_DME1737 is not set
+# CONFIG_SENSORS_EMC1403 is not set
+# CONFIG_SENSORS_EMC2103 is not set
+# CONFIG_SENSORS_EMC6W201 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47M192 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_SCH56XX_COMMON is not set
+# CONFIG_SENSORS_SCH5627 is not set
+# CONFIG_SENSORS_SCH5636 is not set
+# CONFIG_SENSORS_ADS1015 is not set
+# CONFIG_SENSORS_ADS7828 is not set
+# CONFIG_SENSORS_AMC6821 is not set
+# CONFIG_SENSORS_INA209 is not set
+# CONFIG_SENSORS_INA2XX is not set
+# CONFIG_SENSORS_THMC50 is not set
+# CONFIG_SENSORS_TMP102 is not set
+# CONFIG_SENSORS_TMP401 is not set
+# CONFIG_SENSORS_TMP421 is not set
+# CONFIG_SENSORS_TMON_TMP411 is not set
+# CONFIG_SENSORS_VIA_CPUTEMP is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_VT8231 is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83791D is not set
+# CONFIG_SENSORS_W83792D is not set
+# CONFIG_SENSORS_W83793 is not set
+# CONFIG_SENSORS_W83795 is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83L786NG is not set
+# CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
+# CONFIG_SENSORS_APPLESMC is not set
+# CONFIG_SENSORS_INA219 is not set
+# CONFIG_SENSORS_INA230 is not set
+# CONFIG_SENSORS_INA3221 is not set
+# CONFIG_BATTERY_SYSTEM_VOLTAGE_MONITOR is not set
+# CONFIG_CABLE_VBUS_MONITOR is not set
+# CONFIG_THERMAL is not set
+
+#
+# Trusty
+#
+# CONFIG_TRUSTY is not set
CONFIG_WATCHDOG=y
-CONFIG_AGP=y
-CONFIG_AGP_AMD64=y
-CONFIG_AGP_INTEL=y
-CONFIG_DRM=y
-CONFIG_DRM_I915=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_FB_EFI=y
-# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_WATCHDOG_CORE=y
+# CONFIG_WATCHDOG_NOWAYOUT is not set
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+# CONFIG_ACQUIRE_WDT is not set
+# CONFIG_ADVANTECH_WDT is not set
+# CONFIG_ALIM1535_WDT is not set
+# CONFIG_ALIM7101_WDT is not set
+# CONFIG_F71808E_WDT is not set
+# CONFIG_SP5100_TCO is not set
+# CONFIG_SC520_WDT is not set
+# CONFIG_SBC_FITPC2_WATCHDOG is not set
+# CONFIG_EUROTECH_WDT is not set
+# CONFIG_IB700_WDT is not set
+# CONFIG_IBMASR is not set
+# CONFIG_WAFER_WDT is not set
+# CONFIG_I6300ESB_WDT is not set
+# CONFIG_IE6XX_WDT is not set
+CONFIG_ITCO_WDT=y
+CONFIG_ITCO_VENDOR_SUPPORT=y
+# CONFIG_IT8712F_WDT is not set
+# CONFIG_IT87_WDT is not set
+# CONFIG_HP_WATCHDOG is not set
+# CONFIG_SC1200_WDT is not set
+# CONFIG_PC87413_WDT is not set
+# CONFIG_NV_TCO is not set
+# CONFIG_60XX_WDT is not set
+# CONFIG_SBC8360_WDT is not set
+# CONFIG_SBC7240_WDT is not set
+# CONFIG_CPU5_WDT is not set
+# CONFIG_SMSC_SCH311X_WDT is not set
+# CONFIG_SMSC37B787_WDT is not set
+# CONFIG_VIA_WDT is not set
+# CONFIG_W83627HF_WDT is not set
+# CONFIG_W83697HF_WDT is not set
+# CONFIG_W83697UG_WDT is not set
+# CONFIG_W83877F_WDT is not set
+# CONFIG_W83977F_WDT is not set
+# CONFIG_MACHZ_WDT is not set
+# CONFIG_SBC_EPX_C3_WATCHDOG is not set
+
+#
+# ISA-based Watchdog Cards
+#
+# CONFIG_PCWATCHDOG is not set
+# CONFIG_MIXCOMWD is not set
+# CONFIG_WDT is not set
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+CONFIG_BCMA_POSSIBLE=y
+
+#
+# Broadcom specific AMBA
+#
+# CONFIG_BCMA is not set
+
+#
+# Multifunction device drivers
+#
+CONFIG_MFD_CORE=y
+# CONFIG_MFD_CS5535 is not set
+# CONFIG_MFD_AS3711 is not set
+# CONFIG_PMIC_ADP5520 is not set
+# CONFIG_MFD_AIC3256 is not set
+# CONFIG_MFD_AIC3256_I2C is not set
+# CONFIG_MFD_CROS_EC is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_DA9052_I2C is not set
+# CONFIG_MFD_DA9055 is not set
+# CONFIG_MFD_MC13XXX_I2C is not set
+# CONFIG_HTC_PASIC3 is not set
+CONFIG_LPC_ICH=y
+CONFIG_LPC_SCH=y
+# CONFIG_MFD_JANZ_CMODIO is not set
+# CONFIG_MFD_88PM800 is not set
+# CONFIG_MFD_88PM805 is not set
+# CONFIG_MFD_88PM860X is not set
+# CONFIG_MFD_MAX77665 is not set
+# CONFIG_MFD_MAX77686 is not set
+# CONFIG_MFD_MAX77693 is not set
+# CONFIG_MFD_MAX8907 is not set
+# CONFIG_MFD_MAX8925 is not set
+# CONFIG_MFD_MAX8997 is not set
+# CONFIG_MFD_MAX8998 is not set
+# CONFIG_MFD_RETU is not set
+# CONFIG_AIC3XXX_I2C_REGMAP is not set
+# CONFIG_AIC3XXX_CORE is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_MFD_RDC321X is not set
+# CONFIG_MFD_RTSX_PCI is not set
+# CONFIG_MFD_RC5T583 is not set
+# CONFIG_MFD_SEC_CORE is not set
+# CONFIG_MFD_SI476X_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_MFD_SMSC is not set
+# CONFIG_ABX500_CORE is not set
+# CONFIG_MFD_MAX8831 is not set
+# CONFIG_MFD_STMPE is not set
+# CONFIG_MFD_AS3722 is not set
+# CONFIG_MFD_SYSCON is not set
+# CONFIG_MFD_TI_AM335X_TSCADC is not set
+# CONFIG_MFD_LP8788 is not set
+# CONFIG_MFD_PALMAS is not set
+# CONFIG_MFD_MAX8907C is not set
+# CONFIG_MFD_MAX77663 is not set
+# CONFIG_MFD_AS3720 is not set
+# CONFIG_TPS6105X is not set
+# CONFIG_TPS6507X is not set
+# CONFIG_MFD_TPS65090 is not set
+# CONFIG_MFD_TPS65217 is not set
+# CONFIG_MFD_TPS6586X is not set
+# CONFIG_MFD_TPS80031 is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_TWL6040_CORE is not set
+# CONFIG_MFD_WL1273_CORE is not set
+# CONFIG_MFD_LM3533 is not set
+# CONFIG_MFD_TC3589X is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_VX855 is not set
+# CONFIG_MFD_ARIZONA_I2C is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM831X_I2C is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_WM8994 is not set
+# CONFIG_MFD_MAX77660 is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_MEDIA_SUPPORT is not set
+
+#
+# Graphics support
+#
+# CONFIG_AGP is not set
+CONFIG_VGA_ARB=y
+CONFIG_VGA_ARB_MAX_GPUS=16
+# CONFIG_DRM is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_EXYNOS_VIDEO is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Console display driver support
+#
+CONFIG_VGA_CONSOLE=y
CONFIG_VGACON_SOFT_SCROLLBACK=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_SEQ_DUMMY=y
-CONFIG_SND_MIXER_OSS=y
-CONFIG_SND_PCM_OSS=y
-CONFIG_SND_SEQUENCER_OSS=y
-CONFIG_SND_HRTIMER=y
-CONFIG_SND_HDA_INTEL=y
-CONFIG_SND_HDA_HWDEP=y
-CONFIG_HIDRAW=y
+CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256
+# CONFIG_MDA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_DS90UH925Q_SER is not set
+# CONFIG_SOUND is not set
+
+#
+# HID support
+#
+CONFIG_HID=y
+# CONFIG_HIDRAW is not set
+# CONFIG_UHID is not set
+CONFIG_HID_GENERIC=y
+
+#
+# Special HID drivers
+#
+CONFIG_HID_A4TECH=y
+# CONFIG_HID_ACRUX is not set
+CONFIG_HID_APPLE=y
+# CONFIG_HID_AUREAL is not set
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+# CONFIG_DRAGONRISE_FF is not set
+# CONFIG_HID_EMS_FF is not set
+# CONFIG_HID_ELECOM is not set
+CONFIG_HID_EZKEY=y
+# CONFIG_HID_KEYTOUCH is not set
+CONFIG_HID_KYE=y
+# CONFIG_HID_UCLOGIC is not set
+# CONFIG_HID_WALTOP is not set
CONFIG_HID_GYRATION=y
-CONFIG_LOGITECH_FF=y
-CONFIG_HID_NTRIG=y
+# CONFIG_HID_ICADE is not set
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+# CONFIG_HID_LCPOWER is not set
+CONFIG_HID_LOGITECH=y
+# CONFIG_HID_LOGITECH_DJ is not set
+# CONFIG_LOGITECH_FF is not set
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+# CONFIG_LOGIG940_FF is not set
+# CONFIG_LOGIWHEELS_FF is not set
+# CONFIG_HID_MAGICMOUSE is not set
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+# CONFIG_HID_MULTITOUCH is not set
+# CONFIG_HID_ORTEK is not set
CONFIG_HID_PANTHERLORD=y
-CONFIG_PANTHERLORD_FF=y
+# CONFIG_PANTHERLORD_FF is not set
CONFIG_HID_PETALYNX=y
+# CONFIG_HID_PICOLCD is not set
+# CONFIG_HID_PRIMAX is not set
+# CONFIG_HID_PS3REMOTE is not set
+# CONFIG_HID_SAITEK is not set
CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SONY=y
+# CONFIG_HID_SPEEDLINK is not set
+# CONFIG_HID_STEELSERIES is not set
CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+# CONFIG_GREENASIA_FF is not set
+CONFIG_HID_SMARTJOYPLUS=y
+# CONFIG_SMARTJOYPLUS_FF is not set
+# CONFIG_HID_TIVO is not set
CONFIG_HID_TOPSEED=y
-CONFIG_HID_PID=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB=y
-CONFIG_USB_DEBUG=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_TT_NEWSCHED is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_UHCI_HCD=y
-CONFIG_USB_PRINTER=y
-CONFIG_USB_STORAGE=y
-CONFIG_USB_LIBUSUAL=y
+CONFIG_HID_THRUSTMASTER=y
+# CONFIG_THRUSTMASTER_FF is not set
+CONFIG_HID_ZEROPLUS=y
+# CONFIG_ZEROPLUS_FF is not set
+# CONFIG_HID_ZYDACRON is not set
+# CONFIG_HID_SENSOR_HUB is not set
+
+#
+# I2C HID support
+#
+# CONFIG_I2C_HID is not set
+CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
+CONFIG_USB_ARCH_HAS_XHCI=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_UWB is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_SWITCH is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_INFINIBAND is not set
CONFIG_EDAC=y
-CONFIG_RTC_CLASS=y
-# CONFIG_RTC_HCTOSYS is not set
-CONFIG_DMADEVICES=y
-CONFIG_EEEPC_LAPTOP=y
-CONFIG_EFI_VARS=y
+CONFIG_EDAC_LEGACY_SYSFS=y
+# CONFIG_EDAC_DEBUG is not set
+CONFIG_EDAC_DECODE_MCE=y
+# CONFIG_EDAC_MCE_INJ is not set
+# CONFIG_EDAC_MM_EDAC is not set
+CONFIG_RTC_LIB=y
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+# CONFIG_UIO is not set
+# CONFIG_VIRT_DRIVERS is not set
+CONFIG_VIRTIO=y
+
+#
+# Virtio drivers
+#
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+# CONFIG_VIRTIO_MMIO is not set
+
+#
+# Microsoft Hyper-V guest support
+#
+# CONFIG_STAGING is not set
+# CONFIG_ANDROID is not set
+CONFIG_X86_PLATFORM_DEVICES=y
+# CONFIG_CHROMEOS_LAPTOP is not set
+# CONFIG_SENSORS_HDAPS is not set
+# CONFIG_IBM_RTL is not set
+# CONFIG_SAMSUNG_Q10 is not set
+
+#
+# Hardware Spinlock drivers
+#
+CONFIG_CLKSRC_I8253=y
+CONFIG_CLKEVT_I8253=y
+CONFIG_I8253_LOCK=y
+CONFIG_CLKBLD_I8253=y
+# CONFIG_MAILBOX is not set
+# CONFIG_IOMMU_SUPPORT is not set
+
+#
+# Remoteproc drivers
+#
+# CONFIG_STE_MODEM_RPROC is not set
+
+#
+# Rpmsg drivers
+#
+# CONFIG_PM_DEVFREQ is not set
+# CONFIG_EXTCON is not set
+# CONFIG_MIPI_BIF is not set
+# CONFIG_MEMORY is not set
+# CONFIG_IIO is not set
+# CONFIG_VME_BUS is not set
+# CONFIG_PWM is not set
+# CONFIG_IPACK_BUS is not set
+# CONFIG_RESET_CONTROLLER is not set
+
+#
+# SYSEDP Framework
+#
+# CONFIG_SYSEDP_FRAMEWORK is not set
+# CONFIG_GK20A is not set
+
+#
+# Android
+#
+
+#
+# Firmware Drivers
+#
+# CONFIG_EDD is not set
+CONFIG_FIRMWARE_MEMMAP=y
+# CONFIG_DELL_RBU is not set
+# CONFIG_DCDBAS is not set
+CONFIG_DMIID=y
+# CONFIG_DMI_SYSFS is not set
+CONFIG_ISCSI_IBFT_FIND=y
+# CONFIG_ISCSI_IBFT is not set
+# CONFIG_GOOGLE_FIRMWARE is not set
+
+#
+# File systems
+#
+CONFIG_DCACHE_WORD_ACCESS=y
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_USE_FOR_EXT23=y
+# CONFIG_EXT4_FS_POSIX_ACL is not set
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS_ENCRYPTION=y
+CONFIG_EXT4_DEBUG=y
+CONFIG_JBD2=y
+CONFIG_JBD2_DEBUG=y
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+CONFIG_FS_POSIX_ACL=y
+CONFIG_EXPORTFS=y
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_FANOTIFY is not set
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
-# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_PRINT_QUOTA_WARNING=y
+# CONFIG_QUOTA_DEBUG is not set
+CONFIG_QUOTA_TREE=y
+CONFIG_QFMT_V1=y
CONFIG_QFMT_V2=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_QUOTACTL=y
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+CONFIG_GENERIC_ACL=y
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
-CONFIG_MSDOS_FS=y
+CONFIG_UDF_FS=y
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+# CONFIG_MSDOS_FS is not set
CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+CONFIG_NTFS_FS=y
+# CONFIG_NTFS_DEBUG is not set
+CONFIG_NTFS_RW=y
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
+CONFIG_PROC_VMCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
+# CONFIG_REPORT_PRESENT_CPUS is not set
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_XATTR=y
CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_DEFAULT="utf8"
+CONFIG_HUGETLB_PAGE=y
+# CONFIG_CONFIGFS_FS is not set
+CONFIG_MISC_FILESYSTEMS=y
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_ECRYPT_FS is not set
+# CONFIG_ECRYPT_FS_MESSAGING is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
+CONFIG_CRAMFS=y
+# CONFIG_SQUASHFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_QNX6FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_PSTORE is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_F2FS_FS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="cp437"
CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+CONFIG_NLS_CODEPAGE_850=y
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_MAC_ROMAN is not set
+# CONFIG_NLS_MAC_CELTIC is not set
+# CONFIG_NLS_MAC_CENTEURO is not set
+# CONFIG_NLS_MAC_CROATIAN is not set
+# CONFIG_NLS_MAC_CYRILLIC is not set
+# CONFIG_NLS_MAC_GAELIC is not set
+# CONFIG_NLS_MAC_GREEK is not set
+# CONFIG_NLS_MAC_ICELAND is not set
+# CONFIG_NLS_MAC_INUIT is not set
+# CONFIG_NLS_MAC_ROMANIAN is not set
+# CONFIG_NLS_MAC_TURKISH is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
CONFIG_PRINTK_TIME=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-CONFIG_FRAME_WARN=2048
+CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
+CONFIG_ENABLE_WARN_DEPRECATED=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
CONFIG_MAGIC_SYSRQ=y
-# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_STRIP_ASM_SYMS=y
+# CONFIG_READABLE_ASM is not set
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_SECTION_MISMATCH is not set
CONFIG_DEBUG_KERNEL=y
-# CONFIG_SCHED_DEBUG is not set
+# CONFIG_LESS_GCC_OPT is not set
+# CONFIG_DEBUG_SHIRQ is not set
+# CONFIG_LOCKUP_DETECTOR is not set
+# CONFIG_PANIC_ON_OOPS is not set
+CONFIG_PANIC_ON_OOPS_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
+CONFIG_SCHED_DEBUG=y
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_DEBUG_SLAB is not set
+CONFIG_HAVE_DEBUG_KMEMLEAK=y
+# CONFIG_DEBUG_KMEMLEAK is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_LOCKDEP=y
+CONFIG_LOCK_STAT=y
+# CONFIG_DEBUG_LOCKDEP is not set
+CONFIG_TRACE_IRQFLAGS=y
+# CONFIG_DEBUG_ATOMIC_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
CONFIG_DEBUG_STACK_USAGE=y
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_HIGHMEM is not set
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_INFO_REDUCED is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_VIRTUAL is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_TEST_LIST_SORT is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_DEBUG_CREDENTIALS is not set
+CONFIG_ARCH_WANT_FRAME_POINTERS=y
+CONFIG_FRAME_POINTER=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
+
+#
+# RCU Debugging
+#
+# CONFIG_PROVE_RCU is not set
+# CONFIG_SPARSE_RCU_POINTER is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+# CONFIG_RCU_CPU_STALL_INFO is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_KPROBES_SANITY_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
+# CONFIG_DEBUG_PER_CPU_MAPS is not set
+# CONFIG_LKDTM is not set
+# CONFIG_NOTIFIER_ERROR_INJECTION is not set
+# CONFIG_FAULT_INJECTION is not set
+CONFIG_LATENCYTOP=y
+CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS=y
+# CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is not set
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_WANT_PAGE_DEBUG_FLAGS=y
+CONFIG_PAGE_GUARD=y
+CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST=y
+CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
+CONFIG_HAVE_C_RECORDMCOUNT=y
+CONFIG_TRACER_MAX_TRACE=y
+CONFIG_TRACE_CLOCK=y
+CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
+CONFIG_TRACING=y
+CONFIG_GENERIC_TRACER=y
+CONFIG_TRACING_SUPPORT=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+# CONFIG_IRQSOFF_TRACER is not set
+CONFIG_SCHED_TRACER=y
+# CONFIG_FTRACE_SYSCALLS is not set
+CONFIG_TRACER_SNAPSHOT=y
+# CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
+CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_KPROBE_EVENT=y
+# CONFIG_UPROBE_EVENT is not set
+CONFIG_PROBE_EVENTS=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_DYNAMIC_FTRACE_WITH_REGS=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_FTRACE_MCOUNT_RECORD=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
+# CONFIG_RING_BUFFER_BENCHMARK is not set
+# CONFIG_RING_BUFFER_STARTUP_TEST is not set
+# CONFIG_TRACELEVEL is not set
+# CONFIG_TRACEDUMP is not set
+# CONFIG_RBTREE_TEST is not set
+# CONFIG_INTERVAL_TREE_TEST is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
-CONFIG_EARLY_PRINTK_DBGP=y
+CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_DMA_API_DEBUG is not set
+# CONFIG_ATOMIC64_SELFTEST is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
+CONFIG_HAVE_ARCH_KMEMCHECK=y
+# CONFIG_TEST_STRING_HELPERS is not set
+# CONFIG_TEST_KSTRTOX is not set
+# CONFIG_STRICT_DEVMEM is not set
+CONFIG_X86_VERBOSE_BOOTUP=y
+CONFIG_EARLY_PRINTK=y
+# CONFIG_EARLY_PRINTK_DBGP is not set
CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_X86_PTDUMP is not set
+CONFIG_DEBUG_RODATA=y
# CONFIG_DEBUG_RODATA_TEST is not set
+# CONFIG_DEBUG_SET_MODULE_RONX is not set
+# CONFIG_DEBUG_NX_TEST is not set
+CONFIG_DOUBLEFAULT=y
+# CONFIG_DEBUG_TLBFLUSH is not set
+# CONFIG_IOMMU_STRESS is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
+# CONFIG_X86_DECODER_SELFTEST is not set
+CONFIG_IO_DELAY_TYPE_0X80=0
+CONFIG_IO_DELAY_TYPE_0XED=1
+CONFIG_IO_DELAY_TYPE_UDELAY=2
+CONFIG_IO_DELAY_TYPE_NONE=3
+CONFIG_IO_DELAY_0X80=y
+# CONFIG_IO_DELAY_0XED is not set
+# CONFIG_IO_DELAY_UDELAY is not set
+# CONFIG_IO_DELAY_NONE is not set
+CONFIG_DEFAULT_IO_DELAY_TYPE=0
CONFIG_DEBUG_BOOT_PARAMS=y
+# CONFIG_CPA_DEBUG is not set
CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_DEBUG_NMI_SELFTEST is not set
+
+#
+# Security options
+#
+CONFIG_KEYS=y
+CONFIG_ENCRYPTED_KEYS=y
CONFIG_KEYS_DEBUG_PROC_KEYS=y
+# CONFIG_SECURITY_DMESG_RESTRICT is not set
CONFIG_SECURITY=y
+# CONFIG_SECURITYFS is not set
CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
+# CONFIG_SECURITY_NETWORK_XFRM is not set
+# CONFIG_SECURITY_PATH is not set
+# CONFIG_SECURITY_SELINUX is not set
+# CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_SECURITY_APPARMOR is not set
+# CONFIG_TRUSTED_LITTLE_KERNEL is not set
+# CONFIG_SECURITY_YAMA is not set
+# CONFIG_IMA is not set
+# CONFIG_EVM is not set
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_DEFAULT_SECURITY=""
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_AEAD2=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_BLKCIPHER2=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG=y
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP2=y
+CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
+# CONFIG_CRYPTO_USER is not set
+CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
+CONFIG_CRYPTO_GF128MUL=y
+CONFIG_CRYPTO_NULL=y
+# CONFIG_CRYPTO_PCRYPT is not set
+CONFIG_CRYPTO_WORKQUEUE=y
+# CONFIG_CRYPTO_CRYPTD is not set
+CONFIG_CRYPTO_AUTHENC=y
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+CONFIG_CRYPTO_SEQIV=y
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_CTR=y
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=y
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+CONFIG_CRYPTO_XTS=y
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_CMAC is not set
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_XCBC=y
+# CONFIG_CRYPTO_VMAC is not set
+
+#
+# Digest
+#
+CONFIG_CRYPTO_CRC32C=y
+# CONFIG_CRYPTO_CRC32C_INTEL is not set
+# CONFIG_CRYPTO_CRC32 is not set
+# CONFIG_CRYPTO_CRC32_PCLMUL is not set
+# CONFIG_CRYPTO_GHASH is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+# CONFIG_CRYPTO_RMD128 is not set
+CONFIG_CRYPTO_RMD160=y
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_586=y
+# CONFIG_CRYPTO_AES_NI_INTEL is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=y
+CONFIG_CRYPTO_BLOWFISH=y
+CONFIG_CRYPTO_BLOWFISH_COMMON=y
+CONFIG_CRYPTO_CAMELLIA=y
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SALSA20_586 is not set
+# CONFIG_CRYPTO_SEED is not set
+CONFIG_CRYPTO_SERPENT=y
+# CONFIG_CRYPTO_SERPENT_SSE2_586 is not set
+# CONFIG_CRYPTO_TEA is not set
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_CRYPTO_TWOFISH_COMMON=y
+# CONFIG_CRYPTO_TWOFISH_586 is not set
+
+#
+# Compression
+#
+CONFIG_CRYPTO_DEFLATE=y
+# CONFIG_CRYPTO_ZLIB is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_USER_API_HASH is not set
+# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
+CONFIG_CRYPTO_HW=y
+CONFIG_CRYPTO_DEV_PADLOCK=y
+# CONFIG_CRYPTO_DEV_PADLOCK_AES is not set
+# CONFIG_CRYPTO_DEV_PADLOCK_SHA is not set
+# CONFIG_CRYPTO_DEV_GEODE is not set
+# CONFIG_CRYPTO_DEV_TEGRA_SE is not set
+# CONFIG_ASYMMETRIC_KEY_TYPE is not set
+CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_HAVE_KVM_IRQ_ROUTING=y
+CONFIG_HAVE_KVM_EVENTFD=y
+CONFIG_KVM_APIC_ARCHITECTURE=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM_ASYNC_PF=y
+CONFIG_HAVE_KVM_MSI=y
+CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=y
+CONFIG_KVM_INTEL=y
+# CONFIG_KVM_AMD is not set
+# CONFIG_KVM_MMU_AUDIT is not set
+# CONFIG_LGUEST is not set
+CONFIG_BINARY_PRINTF=y
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_STRNCPY_FROM_USER=y
+CONFIG_GENERIC_STRNLEN_USER=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_PCI_IOMAP=y
+CONFIG_GENERIC_IOMAP=y
+CONFIG_GENERIC_IO=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC16=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC32=y
+# CONFIG_CRC32_SELFTEST is not set
+CONFIG_CRC32_SLICEBY8=y
+# CONFIG_CRC32_SLICEBY4 is not set
+# CONFIG_CRC32_SARWATE is not set
+# CONFIG_CRC32_BIT is not set
+# CONFIG_CRC7 is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CRC8 is not set
+CONFIG_AUDIT_GENERIC=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_LZO_DECOMPRESS=y
+CONFIG_XZ_DEC=y
+CONFIG_XZ_DEC_X86=y
+CONFIG_XZ_DEC_POWERPC=y
+CONFIG_XZ_DEC_IA64=y
+CONFIG_XZ_DEC_ARM=y
+CONFIG_XZ_DEC_ARMTHUMB=y
+CONFIG_XZ_DEC_SPARC=y
+CONFIG_XZ_DEC_BCJ=y
+# CONFIG_XZ_DEC_TEST is not set
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
+CONFIG_DECOMPRESS_XZ=y
+CONFIG_DECOMPRESS_LZO=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
+CONFIG_DQL=y
+CONFIG_NLATTR=y
+CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE=y
+CONFIG_AVERAGE=y
+# CONFIG_CORDIC is not set
+# CONFIG_DDR is not set
diff --git a/arch/x86/configs/i386_qemu_defconfig b/arch/x86/configs/i386_qemu_defconfig
new file mode 100644
index 0000000..6bbf453
--- /dev/null
+++ b/arch/x86/configs/i386_qemu_defconfig
@@ -0,0 +1,2959 @@
+# CONFIG_64BIT is not set
+CONFIG_X86_32=y
+CONFIG_X86=y
+CONFIG_INSTRUCTION_DECODER=y
+CONFIG_OUTPUT_FORMAT="elf32-i386"
+CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_MMU=y
+CONFIG_NEED_SG_DMA_LENGTH=y
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_ARCH_HAS_CPU_RELAX=y
+CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
+CONFIG_ARCH_HAS_CPU_AUTOPROBE=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
+CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+# CONFIG_ZONE_DMA32 is not set
+# CONFIG_AUDIT_ARCH is not set
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
+CONFIG_X86_32_SMP=y
+CONFIG_X86_HT=y
+CONFIG_X86_32_LAZY_GS=y
+CONFIG_ARCH_HWEIGHT_CFLAGS="-fcall-saved-ecx -fcall-saved-edx"
+CONFIG_ARCH_CPU_PROBE_RELEASE=y
+CONFIG_ARCH_SUPPORTS_UPROBES=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_IRQ_WORK=y
+CONFIG_BUILDTIME_EXTABLE_SORT=y
+
+#
+# General setup
+#
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_CROSS_COMPILE=""
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_HAVE_KERNEL_XZ=y
+CONFIG_HAVE_KERNEL_LZO=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
+# CONFIG_KERNEL_XZ is not set
+# CONFIG_KERNEL_LZO is not set
+CONFIG_DEFAULT_HOSTNAME="(none)"
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
+CONFIG_FHANDLE=y
+CONFIG_AUDIT=y
+CONFIG_AUDITSYSCALL=y
+CONFIG_AUDIT_WATCH=y
+CONFIG_AUDIT_TREE=y
+# CONFIG_AUDIT_LOGINUID_IMMUTABLE is not set
+CONFIG_HAVE_GENERIC_HARDIRQS=y
+
+#
+# IRQ subsystem
+#
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_IRQ_SHOW=y
+CONFIG_GENERIC_PENDING_IRQ=y
+CONFIG_IRQ_DOMAIN=y
+# CONFIG_IRQ_DOMAIN_DEBUG is not set
+CONFIG_IRQ_FORCED_THREADING=y
+CONFIG_SPARSE_IRQ=y
+CONFIG_CLOCKSOURCE_WATCHDOG=y
+CONFIG_KTIME_SCALAR=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
+CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
+CONFIG_GENERIC_CMOS_UPDATE=y
+
+#
+# Timers subsystem
+#
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ_COMMON=y
+# CONFIG_HZ_PERIODIC is not set
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+
+#
+# CPU/Task time and stats accounting
+#
+CONFIG_TICK_CPU_ACCOUNTING=y
+# CONFIG_IRQ_TIME_ACCOUNTING is not set
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+
+#
+# RCU Subsystem
+#
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+CONFIG_RCU_STALL_COMMON=y
+CONFIG_RCU_FANOUT=32
+CONFIG_RCU_FANOUT_LEAF=16
+# CONFIG_RCU_FANOUT_EXACT is not set
+CONFIG_RCU_FAST_NO_HZ=y
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_RCU_NOCB_CPU is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=18
+CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
+CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
+CONFIG_ARCH_WANTS_PROT_NUMA_PROT_NONE=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CPUSETS=y
+CONFIG_PROC_PID_CPUSET=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+# CONFIG_MEMCG is not set
+# CONFIG_CGROUP_HUGETLB is not set
+# CONFIG_CGROUP_PERF is not set
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_BLK_CGROUP is not set
+# CONFIG_CHECKPOINT_RESTORE is not set
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+# CONFIG_USER_NS is not set
+CONFIG_PID_NS=y
+# CONFIG_NET_NS is not set
+CONFIG_UIDGID_CONVERTED=y
+# CONFIG_UIDGID_STRICT_TYPE_CHECKS is not set
+# CONFIG_SCHED_AUTOGROUP is not set
+# CONFIG_SYSFS_DEPRECATED is not set
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_XZ=y
+CONFIG_RD_LZO=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_HAVE_UID16=y
+CONFIG_SYSCTL_EXCEPTION_TRACE=y
+CONFIG_HOTPLUG=y
+CONFIG_HAVE_PCSPKR_PLATFORM=y
+CONFIG_PANIC_TIMEOUT=0
+# CONFIG_EXPERT is not set
+CONFIG_UID16=y
+# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_KALLSYMS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_PCSPKR_PLATFORM=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_PCI_QUIRKS=y
+# CONFIG_EMBEDDED is not set
+CONFIG_HAVE_PERF_EVENTS=y
+
+#
+# Kernel Performance Events And Counters
+#
+CONFIG_PERF_EVENTS=y
+# CONFIG_DEBUG_PERF_USE_VMALLOC is not set
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_COMPAT_BRK=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+CONFIG_PROFILING=y
+CONFIG_TRACEPOINTS=y
+# CONFIG_OPROFILE is not set
+CONFIG_HAVE_OPROFILE=y
+CONFIG_OPROFILE_NMI_TIMER=y
+CONFIG_KPROBES=y
+# CONFIG_JUMP_LABEL is not set
+CONFIG_OPTPROBES=y
+CONFIG_KPROBES_ON_FTRACE=y
+# CONFIG_HAVE_64BIT_ALIGNED_ACCESS is not set
+CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
+CONFIG_ARCH_USE_BUILTIN_BSWAP=y
+CONFIG_KRETPROBES=y
+CONFIG_USER_RETURN_NOTIFIER=y
+CONFIG_HAVE_IOREMAP_PROT=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_OPTPROBES=y
+CONFIG_HAVE_KPROBES_ON_FTRACE=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_ATTRS=y
+CONFIG_HAVE_DMA_CONTIGUOUS=y
+CONFIG_GENERIC_SMP_IDLE_THREAD=y
+CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+CONFIG_HAVE_HW_BREAKPOINT=y
+CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
+CONFIG_HAVE_USER_RETURN_NOTIFIER=y
+CONFIG_HAVE_PERF_EVENTS_NMI=y
+CONFIG_HAVE_PERF_REGS=y
+CONFIG_HAVE_PERF_USER_STACK_DUMP=y
+CONFIG_HAVE_ARCH_JUMP_LABEL=y
+CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
+CONFIG_HAVE_CMPXCHG_LOCAL=y
+CONFIG_HAVE_CMPXCHG_DOUBLE=y
+CONFIG_ARCH_WANT_IPC_PARSE_VERSION=y
+CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
+CONFIG_SECCOMP_FILTER=y
+CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
+CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
+CONFIG_MODULES_USE_ELF_REL=y
+CONFIG_CLONE_BACKWARDS=y
+CONFIG_OLD_SIGSUSPEND3=y
+CONFIG_OLD_SIGACTION=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_GCOV_KERNEL is not set
+# CONFIG_GCOV_TOOLCHAIN_IS_ANDROID is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+# CONFIG_MODVERSIONS is not set
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_MODULE_SIG is not set
+CONFIG_STOP_MACHINE=y
+CONFIG_BLOCK=y
+CONFIG_LBDAF=y
+CONFIG_BLK_DEV_BSG=y
+# CONFIG_BLK_DEV_BSGLIB is not set
+CONFIG_BLK_DEV_INTEGRITY=y
+
+#
+# Partition Types
+#
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+# CONFIG_OSF_PARTITION is not set
+# CONFIG_AMIGA_PARTITION is not set
+CONFIG_ATARI_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_MSDOS_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_LDM_PARTITION=y
+# CONFIG_LDM_DEBUG is not set
+CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
+CONFIG_SUN_PARTITION=y
+# CONFIG_KARMA_PARTITION is not set
+CONFIG_EFI_PARTITION=y
+CONFIG_SYSV68_PARTITION=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_PREEMPT_NOTIFIERS=y
+CONFIG_UNINLINE_SPIN_UNLOCK=y
+CONFIG_FREEZER=y
+
+#
+# Processor type and features
+#
+CONFIG_ZONE_DMA=y
+CONFIG_SMP=y
+CONFIG_X86_MPPARSE=y
+# CONFIG_X86_BIGSMP is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
+# CONFIG_X86_GOLDFISH is not set
+# CONFIG_X86_WANT_INTEL_MID is not set
+# CONFIG_X86_RDC321X is not set
+# CONFIG_X86_32_NON_STANDARD is not set
+CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y
+# CONFIG_X86_32_IRIS is not set
+# CONFIG_SCHED_OMIT_FRAME_POINTER is not set
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
+# CONFIG_PARAVIRT_DEBUG is not set
+# CONFIG_PARAVIRT_SPINLOCKS is not set
+# CONFIG_XEN is not set
+# CONFIG_XEN_PRIVILEGED_GUEST is not set
+# CONFIG_KVM_GUEST is not set
+CONFIG_LGUEST_GUEST=y
+# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set
+CONFIG_NO_BOOTMEM=y
+# CONFIG_MEMTEST is not set
+# CONFIG_M486 is not set
+# CONFIG_M586 is not set
+# CONFIG_M586TSC is not set
+# CONFIG_M586MMX is not set
+# CONFIG_M686 is not set
+# CONFIG_MPENTIUMII is not set
+# CONFIG_MPENTIUMIII is not set
+# CONFIG_MPENTIUMM is not set
+# CONFIG_MPENTIUM4 is not set
+# CONFIG_MK6 is not set
+# CONFIG_MK7 is not set
+# CONFIG_MK8 is not set
+# CONFIG_MCRUSOE is not set
+# CONFIG_MEFFICEON is not set
+# CONFIG_MWINCHIPC6 is not set
+# CONFIG_MWINCHIP3D is not set
+# CONFIG_MELAN is not set
+# CONFIG_MGEODEGX1 is not set
+# CONFIG_MGEODE_LX is not set
+# CONFIG_MCYRIXIII is not set
+# CONFIG_MVIAC3_2 is not set
+# CONFIG_MVIAC7 is not set
+CONFIG_MCORE2=y
+# CONFIG_MATOM is not set
+CONFIG_X86_GENERIC=y
+CONFIG_X86_INTERNODE_CACHE_SHIFT=6
+CONFIG_X86_L1_CACHE_SHIFT=6
+CONFIG_X86_INTEL_USERCOPY=y
+CONFIG_X86_USE_PPRO_CHECKSUM=y
+CONFIG_X86_TSC=y
+CONFIG_X86_CMPXCHG64=y
+CONFIG_X86_CMOV=y
+CONFIG_X86_MINIMUM_CPU_FAMILY=5
+CONFIG_X86_DEBUGCTLMSR=y
+CONFIG_CPU_SUP_INTEL=y
+CONFIG_CPU_SUP_AMD=y
+CONFIG_CPU_SUP_CENTAUR=y
+CONFIG_CPU_SUP_TRANSMETA_32=y
+CONFIG_HPET_TIMER=y
+CONFIG_DMI=y
+CONFIG_NR_CPUS=8
+CONFIG_SCHED_SMT=y
+CONFIG_SCHED_MC=y
+# CONFIG_PREEMPT_NONE is not set
+CONFIG_PREEMPT_VOLUNTARY=y
+# CONFIG_PREEMPT is not set
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_X86_IO_APIC=y
+# CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS is not set
+CONFIG_X86_MCE=y
+CONFIG_X86_MCE_INTEL=y
+CONFIG_X86_MCE_AMD=y
+# CONFIG_X86_ANCIENT_MCE is not set
+CONFIG_X86_MCE_THRESHOLD=y
+# CONFIG_X86_MCE_INJECT is not set
+CONFIG_X86_THERMAL_VECTOR=y
+CONFIG_VM86=y
+# CONFIG_TOSHIBA is not set
+# CONFIG_I8K is not set
+CONFIG_X86_REBOOTFIXUPS=y
+# CONFIG_MICROCODE is not set
+# CONFIG_X86_MSR is not set
+CONFIG_X86_CPUID=y
+# CONFIG_NOHIGHMEM is not set
+# CONFIG_HIGHMEM4G is not set
+CONFIG_HIGHMEM64G=y
+CONFIG_PAGE_OFFSET=0xC0000000
+CONFIG_HIGHMEM=y
+CONFIG_X86_PAE=y
+CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
+CONFIG_ARCH_DMA_ADDR_T_64BIT=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_ILLEGAL_POINTER_VALUE=0
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_SPARSEMEM_STATIC=y
+CONFIG_HAVE_MEMBLOCK=y
+CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
+CONFIG_ARCH_DISCARD_MEMBLOCK=y
+# CONFIG_HAVE_BOOTMEM_INFO_NODE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=999999
+# CONFIG_COMPACTION is not set
+CONFIG_PHYS_ADDR_T_64BIT=y
+CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
+CONFIG_MMU_NOTIFIER=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
+CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
+# CONFIG_MEMORY_FAILURE is not set
+# CONFIG_TRANSPARENT_HUGEPAGE is not set
+CONFIG_CROSS_MEMORY_ATTACH=y
+# CONFIG_CLEANCACHE is not set
+# CONFIG_FRONTSWAP is not set
+CONFIG_HIGHPTE=y
+# CONFIG_X86_CHECK_BIOS_CORRUPTION is not set
+CONFIG_X86_RESERVE_LOW=64
+# CONFIG_MATH_EMULATION is not set
+CONFIG_MTRR=y
+# CONFIG_MTRR_SANITIZER is not set
+CONFIG_X86_PAT=y
+CONFIG_ARCH_USES_PG_UNCACHED=y
+CONFIG_ARCH_RANDOM=y
+CONFIG_X86_SMAP=y
+CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
+# CONFIG_HZ_100 is not set
+# CONFIG_HZ_250 is not set
+CONFIG_HZ_300=y
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=300
+CONFIG_SCHED_HRTICK=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+CONFIG_PHYSICAL_START=0x100000
+CONFIG_RELOCATABLE=y
+CONFIG_X86_NEED_RELOCS=y
+CONFIG_PHYSICAL_ALIGN=0x100000
+CONFIG_HOTPLUG_CPU=y
+# CONFIG_BOOTPARAM_HOTPLUG_CPU0 is not set
+# CONFIG_DEBUG_HOTPLUG_CPU0 is not set
+CONFIG_COMPAT_VDSO=y
+# CONFIG_CMDLINE_BOOL is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+
+#
+# Power management and ACPI options
+#
+# CONFIG_SUSPEND is not set
+# CONFIG_HAS_WAKELOCK is not set
+# CONFIG_WAKELOCK is not set
+# CONFIG_HIBERNATION is not set
+# CONFIG_PM_RUNTIME is not set
+# CONFIG_SUSPEND_TIME is not set
+# CONFIG_ACPI is not set
+# CONFIG_SFI is not set
+
+#
+# CPU Frequency scaling
+#
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_COMMON=y
+CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_STAT_DETAILS=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE is not set
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+# CONFIG_CPU_FREQ_GOV_INTERACTIVE is not set
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+
+#
+# x86 CPU frequency scaling drivers
+#
+# CONFIG_X86_INTEL_PSTATE is not set
+# CONFIG_X86_POWERNOW_K6 is not set
+# CONFIG_X86_POWERNOW_K7 is not set
+# CONFIG_X86_GX_SUSPMOD is not set
+# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
+# CONFIG_X86_SPEEDSTEP_ICH is not set
+# CONFIG_X86_SPEEDSTEP_SMI is not set
+# CONFIG_X86_P4_CLOCKMOD is not set
+# CONFIG_X86_CPUFREQ_NFORCE2 is not set
+# CONFIG_X86_LONGRUN is not set
+
+#
+# shared options
+#
+# CONFIG_X86_SPEEDSTEP_LIB is not set
+CONFIG_CPU_IDLE=y
+# CONFIG_CPU_IDLE_MULTIPLE_DRIVERS is not set
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
+# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
+CONFIG_INTEL_IDLE=y
+
+#
+# Bus options (PCI etc.)
+#
+CONFIG_PCI=y
+# CONFIG_PCI_GOBIOS is not set
+# CONFIG_PCI_GOMMCONFIG is not set
+# CONFIG_PCI_GODIRECT is not set
+CONFIG_PCI_GOANY=y
+CONFIG_PCI_BIOS=y
+CONFIG_PCI_DIRECT=y
+CONFIG_PCI_DOMAINS=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_HOTPLUG_PCI_PCIE is not set
+CONFIG_PCIEAER=y
+# CONFIG_PCIE_ECRC is not set
+# CONFIG_PCIEAER_INJECT is not set
+CONFIG_PCIEASPM=y
+# CONFIG_PCIEASPM_DEBUG is not set
+CONFIG_PCIEASPM_DEFAULT=y
+# CONFIG_PCIEASPM_POWERSAVE is not set
+# CONFIG_PCIEASPM_PERFORMANCE is not set
+CONFIG_ARCH_SUPPORTS_MSI=y
+CONFIG_PCI_MSI=y
+# CONFIG_PCI_DEBUG is not set
+# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
+# CONFIG_PCI_STUB is not set
+CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
+# CONFIG_PCI_PRI is not set
+# CONFIG_PCI_PASID is not set
+CONFIG_PCI_LABEL=y
+
+#
+# PCIE Host Controller Drivers
+#
+CONFIG_ISA_DMA_API=y
+CONFIG_ISA=y
+CONFIG_EISA=y
+CONFIG_EISA_VLB_PRIMING=y
+CONFIG_EISA_PCI_EISA=y
+CONFIG_EISA_VIRTUAL_ROOT=y
+CONFIG_EISA_NAMES=y
+# CONFIG_SCx200 is not set
+# CONFIG_ALIX is not set
+# CONFIG_NET5501 is not set
+# CONFIG_GEOS is not set
+CONFIG_AMD_NB=y
+CONFIG_PCCARD=y
+# CONFIG_PCMCIA is not set
+CONFIG_CARDBUS=y
+
+#
+# PC-card bridges
+#
+CONFIG_YENTA=y
+CONFIG_YENTA_O2=y
+CONFIG_YENTA_RICOH=y
+CONFIG_YENTA_TI=y
+CONFIG_YENTA_ENE_TUNE=y
+CONFIG_YENTA_TOSHIBA=y
+CONFIG_PCMCIA_PROBE=y
+CONFIG_HOTPLUG_PCI=y
+# CONFIG_HOTPLUG_PCI_COMPAQ is not set
+# CONFIG_HOTPLUG_PCI_IBM is not set
+CONFIG_HOTPLUG_PCI_CPCI=y
+# CONFIG_HOTPLUG_PCI_CPCI_ZT5550 is not set
+# CONFIG_HOTPLUG_PCI_CPCI_GENERIC is not set
+CONFIG_HOTPLUG_PCI_SHPC=y
+# CONFIG_RAPIDIO is not set
+
+#
+# Executable file formats / Emulations
+#
+CONFIG_BINFMT_ELF=y
+CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_SCRIPT=y
+CONFIG_HAVE_AOUT=y
+# CONFIG_BINFMT_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+CONFIG_COREDUMP=y
+CONFIG_HAVE_ATOMIC_IOMAP=y
+CONFIG_HAVE_TEXT_POKE_SMP=y
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+# CONFIG_PACKET_DIAG is not set
+CONFIG_UNIX=y
+# CONFIG_UNIX_DIAG is not set
+CONFIG_XFRM=y
+CONFIG_XFRM_ALGO=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+# CONFIG_NET_KEY_MIGRATE is not set
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+# CONFIG_IP_FIB_TRIE_STATS is not set
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+# CONFIG_IP_PNP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE_DEMUX is not set
+# CONFIG_NET_IP_TUNNEL is not set
+CONFIG_IP_MROUTE=y
+# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+# CONFIG_ARPD is not set
+CONFIG_SYN_COOKIES=y
+# CONFIG_NET_IPVTI is not set
+# CONFIG_INET_AH is not set
+CONFIG_INET_ESP=y
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+# CONFIG_INET_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+# CONFIG_INET_XFRM_MODE_BEET is not set
+CONFIG_INET_LRO=y
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_INET_UDP_DIAG is not set
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+CONFIG_TCP_MD5SIG=y
+# CONFIG_IPV6 is not set
+# CONFIG_NETLABEL is not set
+# CONFIG_ANDROID_PARANOID_NETWORK is not set
+# CONFIG_NET_ACTIVITY_STATS is not set
+CONFIG_NETWORK_SECMARK=y
+# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
+
+#
+# Core Netfilter Configuration
+#
+# CONFIG_NETFILTER_NETLINK_ACCT is not set
+# CONFIG_NETFILTER_NETLINK_QUEUE is not set
+# CONFIG_NETFILTER_NETLINK_LOG is not set
+# CONFIG_NF_CONNTRACK is not set
+CONFIG_NETFILTER_XTABLES=y
+
+#
+# Xtables combined modules
+#
+# CONFIG_NETFILTER_XT_MARK is not set
+
+#
+# Xtables targets
+#
+# CONFIG_NETFILTER_XT_TARGET_AUDIT is not set
+# CONFIG_NETFILTER_XT_TARGET_CLASSIFY is not set
+# CONFIG_NETFILTER_XT_TARGET_HMARK is not set
+# CONFIG_NETFILTER_XT_TARGET_IDLETIMER is not set
+# CONFIG_NETFILTER_XT_TARGET_LOG is not set
+# CONFIG_NETFILTER_XT_TARGET_MARK is not set
+# CONFIG_NETFILTER_XT_TARGET_NFLOG is not set
+# CONFIG_NETFILTER_XT_TARGET_NFQUEUE is not set
+# CONFIG_NETFILTER_XT_TARGET_RATEEST is not set
+# CONFIG_NETFILTER_XT_TARGET_TEE is not set
+# CONFIG_NETFILTER_XT_TARGET_SECMARK is not set
+# CONFIG_NETFILTER_XT_TARGET_TCPMSS is not set
+
+#
+# Xtables matches
+#
+# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set
+# CONFIG_NETFILTER_XT_MATCH_BPF is not set
+# CONFIG_NETFILTER_XT_MATCH_COMMENT is not set
+# CONFIG_NETFILTER_XT_MATCH_CPU is not set
+# CONFIG_NETFILTER_XT_MATCH_DCCP is not set
+# CONFIG_NETFILTER_XT_MATCH_DEVGROUP is not set
+# CONFIG_NETFILTER_XT_MATCH_DSCP is not set
+# CONFIG_NETFILTER_XT_MATCH_ECN is not set
+# CONFIG_NETFILTER_XT_MATCH_ESP is not set
+# CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set
+# CONFIG_NETFILTER_XT_MATCH_HL is not set
+# CONFIG_NETFILTER_XT_MATCH_IPRANGE is not set
+# CONFIG_NETFILTER_XT_MATCH_LENGTH is not set
+# CONFIG_NETFILTER_XT_MATCH_LIMIT is not set
+# CONFIG_NETFILTER_XT_MATCH_MAC is not set
+# CONFIG_NETFILTER_XT_MATCH_MARK is not set
+# CONFIG_NETFILTER_XT_MATCH_MULTIPORT is not set
+# CONFIG_NETFILTER_XT_MATCH_NFACCT is not set
+# CONFIG_NETFILTER_XT_MATCH_OWNER is not set
+# CONFIG_NETFILTER_XT_MATCH_POLICY is not set
+# CONFIG_NETFILTER_XT_MATCH_PKTTYPE is not set
+# CONFIG_NETFILTER_XT_MATCH_QUOTA is not set
+# CONFIG_NETFILTER_XT_MATCH_QUOTA2 is not set
+# CONFIG_NETFILTER_XT_MATCH_RATEEST is not set
+# CONFIG_NETFILTER_XT_MATCH_REALM is not set
+# CONFIG_NETFILTER_XT_MATCH_RECENT is not set
+# CONFIG_NETFILTER_XT_MATCH_SCTP is not set
+# CONFIG_NETFILTER_XT_MATCH_STATISTIC is not set
+# CONFIG_NETFILTER_XT_MATCH_STRING is not set
+# CONFIG_NETFILTER_XT_MATCH_TCPMSS is not set
+# CONFIG_NETFILTER_XT_MATCH_TIME is not set
+# CONFIG_NETFILTER_XT_MATCH_U32 is not set
+# CONFIG_IP_VS is not set
+
+#
+# IP: Netfilter Configuration
+#
+# CONFIG_NF_DEFRAG_IPV4 is not set
+CONFIG_IP_NF_IPTABLES=y
+# CONFIG_IP_NF_MATCH_AH is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
+CONFIG_IP_NF_FILTER=y
+# CONFIG_IP_NF_TARGET_REJECT is not set
+# CONFIG_IP_NF_TARGET_ULOG is not set
+# CONFIG_IP_NF_MANGLE is not set
+# CONFIG_IP_NF_RAW is not set
+# CONFIG_IP_NF_SECURITY is not set
+# CONFIG_IP_NF_ARPTABLES is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
+# CONFIG_TIPC is not set
+CONFIG_ATM=y
+CONFIG_ATM_CLIP=y
+# CONFIG_ATM_CLIP_NO_ICMP is not set
+# CONFIG_ATM_LANE is not set
+# CONFIG_ATM_BR2684 is not set
+# CONFIG_L2TP is not set
+# CONFIG_BRIDGE is not set
+CONFIG_HAVE_NET_DSA=y
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_PHONET is not set
+# CONFIG_MHI is not set
+# CONFIG_IEEE802154 is not set
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+# CONFIG_NET_SCH_CBQ is not set
+# CONFIG_NET_SCH_HTB is not set
+# CONFIG_NET_SCH_HFSC is not set
+# CONFIG_NET_SCH_ATM is not set
+# CONFIG_NET_SCH_PRIO is not set
+# CONFIG_NET_SCH_MULTIQ is not set
+# CONFIG_NET_SCH_RED is not set
+# CONFIG_NET_SCH_SFB is not set
+# CONFIG_NET_SCH_SFQ is not set
+# CONFIG_NET_SCH_TEQL is not set
+# CONFIG_NET_SCH_TBF is not set
+# CONFIG_NET_SCH_GRED is not set
+# CONFIG_NET_SCH_DSMARK is not set
+# CONFIG_NET_SCH_NETEM is not set
+# CONFIG_NET_SCH_DRR is not set
+# CONFIG_NET_SCH_MQPRIO is not set
+# CONFIG_NET_SCH_CHOKE is not set
+# CONFIG_NET_SCH_QFQ is not set
+# CONFIG_NET_SCH_CODEL is not set
+# CONFIG_NET_SCH_FQ_CODEL is not set
+# CONFIG_NET_SCH_INGRESS is not set
+# CONFIG_NET_SCH_PLUG is not set
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+# CONFIG_NET_CLS_BASIC is not set
+# CONFIG_NET_CLS_TCINDEX is not set
+# CONFIG_NET_CLS_ROUTE4 is not set
+# CONFIG_NET_CLS_FW is not set
+# CONFIG_NET_CLS_U32 is not set
+# CONFIG_NET_CLS_RSVP is not set
+# CONFIG_NET_CLS_RSVP6 is not set
+# CONFIG_NET_CLS_FLOW is not set
+# CONFIG_NET_CLS_CGROUP is not set
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+# CONFIG_NET_EMATCH_CMP is not set
+# CONFIG_NET_EMATCH_NBYTE is not set
+# CONFIG_NET_EMATCH_U32 is not set
+# CONFIG_NET_EMATCH_META is not set
+# CONFIG_NET_EMATCH_TEXT is not set
+CONFIG_NET_CLS_ACT=y
+# CONFIG_NET_ACT_POLICE is not set
+# CONFIG_NET_ACT_GACT is not set
+# CONFIG_NET_ACT_MIRRED is not set
+# CONFIG_NET_ACT_IPT is not set
+# CONFIG_NET_ACT_NAT is not set
+# CONFIG_NET_ACT_PEDIT is not set
+# CONFIG_NET_ACT_SIMP is not set
+# CONFIG_NET_ACT_SKBEDIT is not set
+# CONFIG_NET_ACT_CSUM is not set
+CONFIG_NET_SCH_FIFO=y
+# CONFIG_DCB is not set
+CONFIG_DNS_RESOLVER=y
+# CONFIG_BATMAN_ADV is not set
+# CONFIG_OPENVSWITCH is not set
+# CONFIG_VSOCKETS is not set
+# CONFIG_NETLINK_MMAP is not set
+# CONFIG_NETLINK_DIAG is not set
+# CONFIG_RMNET_DATA is not set
+# CONFIG_NETPRIO_CGROUP is not set
+CONFIG_BQL=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+CONFIG_FIB_RULES=y
+# CONFIG_WIRELESS is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
+# CONFIG_CEPH_LIB is not set
+# CONFIG_NFC is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+# CONFIG_DEVTMPFS_MOUNT is not set
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+CONFIG_FW_LOADER_USER_HELPER=y
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_GENERIC_CPU_DEVICES is not set
+CONFIG_HAVE_CPU_AUTOPROBE=y
+# CONFIG_DMA_SHARED_BUFFER is not set
+# CONFIG_CMA is not set
+
+#
+# Bus devices
+#
+# CONFIG_CONNECTOR is not set
+# CONFIG_MTD is not set
+CONFIG_PARPORT=y
+CONFIG_PARPORT_PC=y
+# CONFIG_PARPORT_SERIAL is not set
+CONFIG_PARPORT_PC_FIFO=y
+# CONFIG_PARPORT_PC_SUPERIO is not set
+# CONFIG_PARPORT_GSC is not set
+# CONFIG_PARPORT_AX88796 is not set
+CONFIG_PARPORT_1284=y
+CONFIG_PNP=y
+CONFIG_PNP_DEBUG_MESSAGES=y
+
+#
+# Protocols
+#
+CONFIG_ISAPNP=y
+CONFIG_PNPBIOS=y
+CONFIG_PNPBIOS_PROC_FS=y
+# CONFIG_PNPACPI is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_PARIDE is not set
+# CONFIG_BLK_DEV_PCIESSD_MTIP32XX is not set
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
+# CONFIG_BLK_DEV_CRYPTOLOOP is not set
+# CONFIG_BLK_DEV_DRBD is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_NVME is not set
+# CONFIG_BLK_DEV_SX8 is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=65536
+# CONFIG_BLK_DEV_XIP is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+CONFIG_VIRTIO_BLK=y
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_BLK_DEV_RBD is not set
+# CONFIG_BLK_DEV_RSXX is not set
+
+#
+# Misc devices
+#
+# CONFIG_SENSORS_LIS3LV02D is not set
+# CONFIG_AD525X_DPOT is not set
+# CONFIG_DUMMY_IRQ is not set
+# CONFIG_IBM_ASM is not set
+# CONFIG_PHANTOM is not set
+# CONFIG_INTEL_MID_PTI is not set
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+# CONFIG_ICS932S401 is not set
+# CONFIG_ATMEL_SSC is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_KERNEL_DEBUGGER_CORE is not set
+# CONFIG_HP_ILO is not set
+# CONFIG_APDS9802ALS is not set
+# CONFIG_ISL29003 is not set
+# CONFIG_ISL29020 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_SENSORS_BH1780 is not set
+# CONFIG_SENSORS_BH1770 is not set
+# CONFIG_SENSORS_APDS990X is not set
+# CONFIG_HMC6352 is not set
+# CONFIG_SENSORS_NCT1008 is not set
+# CONFIG_DS1682 is not set
+# CONFIG_UID_STAT is not set
+# CONFIG_VMWARE_BALLOON is not set
+# CONFIG_BMP085_I2C is not set
+# CONFIG_PCH_PHUB is not set
+# CONFIG_USB_SWITCH_FSA9480 is not set
+# CONFIG_SRAM is not set
+# CONFIG_BCM4329_RFKILL is not set
+# CONFIG_TEGRA_CRYPTO_DEV is not set
+# CONFIG_APANIC is not set
+CONFIG_APANIC_PLABEL="kpanic"
+# CONFIG_THERM_EST is not set
+# CONFIG_FAN_THERM_EST is not set
+# CONFIG_BLUEDROID_PM is not set
+CONFIG_CPULOAD_MONITOR=y
+# CONFIG_MODS is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_LEGACY is not set
+# CONFIG_EEPROM_MAX6875 is not set
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
+
+#
+# Texas Instruments shared transport line discipline
+#
+# CONFIG_ST_GPS is not set
+# CONFIG_SENSORS_LIS3_I2C is not set
+
+#
+# Altera FPGA firmware download module
+#
+# CONFIG_ALTERA_STAPL is not set
+# CONFIG_INTEL_MEI is not set
+# CONFIG_INTEL_MEI_ME is not set
+# CONFIG_VMWARE_VMCI is not set
+# CONFIG_ISSP is not set
+# CONFIG_GPS is not set
+# CONFIG_HTC_HEADSET_MGR is not set
+# CONFIG_HEADSET_DEBUG_UART is not set
+
+#
+# Qualcomm Modem Drivers
+#
+CONFIG_HAVE_IDE=y
+CONFIG_IDE=y
+
+#
+# Please see Documentation/ide/ide.txt for help/info on IDE drives
+#
+CONFIG_IDE_ATAPI=y
+# CONFIG_BLK_DEV_IDE_SATA is not set
+CONFIG_IDE_GD=y
+CONFIG_IDE_GD_ATA=y
+# CONFIG_IDE_GD_ATAPI is not set
+# CONFIG_BLK_DEV_DELKIN is not set
+CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+CONFIG_IDE_PROC_FS=y
+
+#
+# IDE chipset support/bugfixes
+#
+# CONFIG_IDE_GENERIC is not set
+# CONFIG_BLK_DEV_PLATFORM is not set
+# CONFIG_BLK_DEV_CMD640 is not set
+# CONFIG_BLK_DEV_IDEPNP is not set
+
+#
+# PCI IDE chipsets support
+#
+# CONFIG_BLK_DEV_GENERIC is not set
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_RZ1000 is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_ATIIXP is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_CS5535 is not set
+# CONFIG_BLK_DEV_CS5536 is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_JMICRON is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_IT8172 is not set
+# CONFIG_BLK_DEV_IT8213 is not set
+# CONFIG_BLK_DEV_IT821X is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SIS5513 is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_BLK_DEV_TC86C001 is not set
+
+#
+# Other IDE chipsets support
+#
+
+#
+# Note: most of these also require special kernel boot parameters
+#
+# CONFIG_BLK_DEV_4DRIVES is not set
+# CONFIG_BLK_DEV_ALI14XX is not set
+# CONFIG_BLK_DEV_DTC2278 is not set
+# CONFIG_BLK_DEV_HT6560B is not set
+# CONFIG_BLK_DEV_QD65XX is not set
+# CONFIG_BLK_DEV_UMC8672 is not set
+# CONFIG_BLK_DEV_IDEDMA is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI_MOD=y
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
+# CONFIG_SCSI_TGT is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=y
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+# CONFIG_CHR_DEV_SCH is not set
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+# CONFIG_SCSI_SCAN_ASYNC is not set
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_ISCSI_BOOT_SYSFS is not set
+# CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_CXGB4_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
+# CONFIG_SCSI_BNX2X_FCOE is not set
+# CONFIG_BE2ISCSI is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_HPSA is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_3W_SAS is not set
+# CONFIG_SCSI_7000FASST is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AHA152X is not set
+# CONFIG_SCSI_AHA1542 is not set
+# CONFIG_SCSI_AHA1740 is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
+# CONFIG_SCSI_MVUMI is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_IN2000 is not set
+# CONFIG_SCSI_ARCMSR is not set
+CONFIG_MEGARAID_NEWGEN=y
+# CONFIG_MEGARAID_MM is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_MEGARAID_SAS is not set
+# CONFIG_SCSI_MPT2SAS is not set
+# CONFIG_SCSI_MPT3SAS is not set
+# CONFIG_SCSI_UFSHCD is not set
+# CONFIG_SCSI_HPTIOP is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_VMWARE_PVSCSI is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_FCOE is not set
+# CONFIG_FCOE_FNIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_DTC3280 is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH is not set
+# CONFIG_SCSI_ISCI is not set
+# CONFIG_SCSI_GENERIC_NCR5380 is not set
+# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_PPA is not set
+# CONFIG_SCSI_IMM is not set
+# CONFIG_SCSI_NCR53C406A is not set
+# CONFIG_SCSI_STEX is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_PAS16 is not set
+# CONFIG_SCSI_QLOGIC_FAS is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+# CONFIG_SCSI_QLA_FC is not set
+# CONFIG_SCSI_QLA_ISCSI is not set
+# CONFIG_SCSI_LPFC is not set
+# CONFIG_SCSI_SIM710 is not set
+# CONFIG_SCSI_SYM53C416 is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_T128 is not set
+# CONFIG_SCSI_U14_34F is not set
+# CONFIG_SCSI_ULTRASTOR is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_PMCRAID is not set
+# CONFIG_SCSI_PM8001 is not set
+# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_BFA_FC is not set
+# CONFIG_SCSI_VIRTIO is not set
+# CONFIG_SCSI_CHELSIO_FCOE is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
+CONFIG_ATA=y
+# CONFIG_ATA_NONSTANDARD is not set
+CONFIG_ATA_VERBOSE_ERROR=y
+CONFIG_SATA_PMP=y
+
+#
+# Controllers with non-SFF native interface
+#
+CONFIG_SATA_AHCI=y
+# CONFIG_SATA_AHCI_PLATFORM is not set
+# CONFIG_SATA_AHCI_TEGRA is not set
+# CONFIG_SATA_INIC162X is not set
+# CONFIG_SATA_ACARD_AHCI is not set
+# CONFIG_SATA_SIL24 is not set
+CONFIG_ATA_SFF=y
+
+#
+# SFF controllers with custom DMA interface
+#
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_SX4 is not set
+CONFIG_ATA_BMDMA=y
+
+#
+# SATA SFF controllers with BMDMA
+#
+CONFIG_ATA_PIIX=y
+# CONFIG_SATA_HIGHBANK is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_SVW is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+
+#
+# PATA SFF controllers with BMDMA
+#
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_ATP867X is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CS5535 is not set
+# CONFIG_PATA_CS5536 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT8213 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NINJA32 is not set
+# CONFIG_PATA_NS87415 is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RDC is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SCH is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_TOSHIBA is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+
+#
+# PIO-only SFF controllers
+#
+# CONFIG_PATA_CMD640_PCI is not set
+# CONFIG_PATA_ISAPNP is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_QDI is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_WINBOND_VLB is not set
+
+#
+# Generic fallback / legacy drivers
+#
+CONFIG_ATA_GENERIC=y
+# CONFIG_PATA_LEGACY is not set
+CONFIG_MD=y
+# CONFIG_BLK_DEV_MD is not set
+# CONFIG_BCACHE is not set
+CONFIG_BLK_DEV_DM_BUILTIN=y
+CONFIG_BLK_DEV_DM=y
+# CONFIG_DM_DEBUG is not set
+# CONFIG_DM_CRYPT is not set
+CONFIG_DM_SNAPSHOT=y
+# CONFIG_DM_THIN_PROVISIONING is not set
+# CONFIG_DM_CACHE is not set
+CONFIG_DM_MIRROR=y
+# CONFIG_DM_RAID is not set
+# CONFIG_DM_LOG_USERSPACE is not set
+# CONFIG_DM_ZERO is not set
+# CONFIG_DM_MULTIPATH is not set
+# CONFIG_DM_DELAY is not set
+CONFIG_DM_UEVENT=y
+# CONFIG_DM_FLAKEY is not set
+# CONFIG_DM_VERITY is not set
+# CONFIG_TARGET_CORE is not set
+CONFIG_FUSION=y
+# CONFIG_FUSION_SPI is not set
+# CONFIG_FUSION_FC is not set
+# CONFIG_FUSION_SAS is not set
+CONFIG_FUSION_MAX_SGE=128
+CONFIG_FUSION_LOGGING=y
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_FIREWIRE is not set
+# CONFIG_FIREWIRE_NOSY is not set
+# CONFIG_I2O is not set
+CONFIG_MACINTOSH_DRIVERS=y
+CONFIG_MAC_EMUMOUSEBTN=y
+CONFIG_NETDEVICES=y
+CONFIG_NET_CORE=y
+# CONFIG_BONDING is not set
+CONFIG_DUMMY=y
+# CONFIG_EQUALIZER is not set
+CONFIG_NET_FC=y
+CONFIG_MII=y
+# CONFIG_IFB is not set
+# CONFIG_NET_TEAM is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_VXLAN is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+CONFIG_TUN=y
+CONFIG_VETH=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_ARCNET is not set
+CONFIG_ATM_DRIVERS=y
+# CONFIG_ATM_DUMMY is not set
+# CONFIG_ATM_TCP is not set
+# CONFIG_ATM_LANAI is not set
+# CONFIG_ATM_ENI is not set
+# CONFIG_ATM_FIRESTREAM is not set
+# CONFIG_ATM_ZATM is not set
+# CONFIG_ATM_NICSTAR is not set
+# CONFIG_ATM_IDT77252 is not set
+# CONFIG_ATM_AMBASSADOR is not set
+# CONFIG_ATM_HORIZON is not set
+# CONFIG_ATM_IA is not set
+# CONFIG_ATM_FORE200E is not set
+# CONFIG_ATM_HE is not set
+# CONFIG_ATM_SOLOS is not set
+
+#
+# CAIF transport drivers
+#
+# CONFIG_VHOST_NET is not set
+
+#
+# Distributed Switch Architecture drivers
+#
+# CONFIG_NET_DSA_MV88E6XXX is not set
+# CONFIG_NET_DSA_MV88E6060 is not set
+# CONFIG_NET_DSA_MV88E6XXX_NEED_PPU is not set
+# CONFIG_NET_DSA_MV88E6131 is not set
+# CONFIG_NET_DSA_MV88E6123_61_65 is not set
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_3COM=y
+# CONFIG_EL3 is not set
+# CONFIG_3C515 is not set
+# CONFIG_VORTEX is not set
+# CONFIG_TYPHOON is not set
+CONFIG_NET_VENDOR_ADAPTEC=y
+# CONFIG_ADAPTEC_STARFIRE is not set
+CONFIG_NET_VENDOR_ALTEON=y
+# CONFIG_ACENIC is not set
+CONFIG_NET_VENDOR_AMD=y
+# CONFIG_AMD8111_ETH is not set
+# CONFIG_LANCE is not set
+# CONFIG_PCNET32 is not set
+# CONFIG_NI65 is not set
+CONFIG_NET_VENDOR_ATHEROS=y
+# CONFIG_ATL2 is not set
+# CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
+# CONFIG_ALX is not set
+CONFIG_NET_CADENCE=y
+# CONFIG_ARM_AT91_ETHER is not set
+# CONFIG_MACB is not set
+CONFIG_NET_VENDOR_BROADCOM=y
+# CONFIG_B44 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_CNIC is not set
+CONFIG_TIGON3=y
+# CONFIG_BNX2X is not set
+CONFIG_NET_VENDOR_BROCADE=y
+# CONFIG_BNA is not set
+# CONFIG_NET_CALXEDA_XGMAC is not set
+CONFIG_NET_VENDOR_CHELSIO=y
+# CONFIG_CHELSIO_T1 is not set
+# CONFIG_CHELSIO_T3 is not set
+# CONFIG_CHELSIO_T4 is not set
+# CONFIG_CHELSIO_T4VF is not set
+CONFIG_NET_VENDOR_CIRRUS=y
+# CONFIG_CS89x0 is not set
+CONFIG_NET_VENDOR_CISCO=y
+# CONFIG_ENIC is not set
+# CONFIG_DNET is not set
+CONFIG_NET_VENDOR_DEC=y
+# CONFIG_NET_TULIP is not set
+CONFIG_NET_VENDOR_DLINK=y
+# CONFIG_DL2K is not set
+# CONFIG_SUNDANCE is not set
+CONFIG_NET_VENDOR_EMULEX=y
+# CONFIG_BE2NET is not set
+CONFIG_NET_VENDOR_EXAR=y
+# CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
+CONFIG_NET_VENDOR_FUJITSU=y
+CONFIG_NET_VENDOR_HP=y
+# CONFIG_HP100 is not set
+CONFIG_NET_VENDOR_INTEL=y
+# CONFIG_E100 is not set
+# CONFIG_E1000 is not set
+CONFIG_E1000E=y
+# CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
+# CONFIG_IXGB is not set
+# CONFIG_IXGBE is not set
+# CONFIG_IXGBEVF is not set
+CONFIG_NET_VENDOR_I825XX=y
+# CONFIG_IP1000 is not set
+# CONFIG_JME is not set
+CONFIG_NET_VENDOR_MARVELL=y
+# CONFIG_MVMDIO is not set
+# CONFIG_SKGE is not set
+# CONFIG_SKY2 is not set
+CONFIG_NET_VENDOR_MELLANOX=y
+# CONFIG_MLX4_EN is not set
+# CONFIG_MLX4_CORE is not set
+CONFIG_NET_VENDOR_MICREL=y
+# CONFIG_KS8851_MLL is not set
+# CONFIG_KSZ884X_PCI is not set
+CONFIG_NET_VENDOR_MYRI=y
+# CONFIG_MYRI10GE is not set
+# CONFIG_FEALNX is not set
+CONFIG_NET_VENDOR_NATSEMI=y
+# CONFIG_NATSEMI is not set
+# CONFIG_NS83820 is not set
+CONFIG_NET_VENDOR_8390=y
+# CONFIG_NE2000 is not set
+# CONFIG_NE2K_PCI is not set
+# CONFIG_ULTRA is not set
+# CONFIG_WD80x3 is not set
+CONFIG_NET_VENDOR_NVIDIA=y
+# CONFIG_FORCEDETH is not set
+CONFIG_NET_VENDOR_OKI=y
+# CONFIG_PCH_GBE is not set
+# CONFIG_ETHOC is not set
+CONFIG_NET_PACKET_ENGINE=y
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+CONFIG_NET_VENDOR_QLOGIC=y
+# CONFIG_QLA3XXX is not set
+# CONFIG_QLCNIC is not set
+# CONFIG_QLGE is not set
+# CONFIG_NETXEN_NIC is not set
+CONFIG_NET_VENDOR_REALTEK=y
+# CONFIG_ATP is not set
+# CONFIG_8139CP is not set
+# CONFIG_8139TOO is not set
+# CONFIG_R8169 is not set
+CONFIG_NET_VENDOR_RDC=y
+# CONFIG_R6040 is not set
+CONFIG_NET_VENDOR_SEEQ=y
+CONFIG_NET_VENDOR_SILAN=y
+# CONFIG_SC92031 is not set
+CONFIG_NET_VENDOR_SIS=y
+# CONFIG_SIS900 is not set
+# CONFIG_SIS190 is not set
+# CONFIG_SFC is not set
+CONFIG_NET_VENDOR_SMSC=y
+# CONFIG_SMC9194 is not set
+# CONFIG_EPIC100 is not set
+# CONFIG_SMSC9420 is not set
+CONFIG_NET_VENDOR_STMICRO=y
+# CONFIG_STMMAC_ETH is not set
+CONFIG_NET_VENDOR_SUN=y
+# CONFIG_HAPPYMEAL is not set
+# CONFIG_SUNGEM is not set
+# CONFIG_CASSINI is not set
+# CONFIG_NIU is not set
+CONFIG_NET_VENDOR_TEHUTI=y
+# CONFIG_TEHUTI is not set
+CONFIG_NET_VENDOR_TI=y
+# CONFIG_TLAN is not set
+CONFIG_NET_VENDOR_VIA=y
+# CONFIG_VIA_RHINE is not set
+# CONFIG_VIA_VELOCITY is not set
+CONFIG_NET_VENDOR_WIZNET=y
+# CONFIG_WIZNET_W5100 is not set
+# CONFIG_WIZNET_W5300 is not set
+CONFIG_FDDI=y
+# CONFIG_DEFXX is not set
+# CONFIG_SKFP is not set
+CONFIG_HIPPI=y
+# CONFIG_ROADRUNNER is not set
+# CONFIG_NET_SB1000 is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_AT803X_PHY is not set
+# CONFIG_AMD_PHY is not set
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+# CONFIG_SMSC_PHY is not set
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_BCM87XX_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_MICREL_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
+# CONFIG_PLIP is not set
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_FILTER=y
+# CONFIG_PPP_MPPE is not set
+CONFIG_PPP_MULTILINK=y
+# CONFIG_PPPOATM is not set
+# CONFIG_PPPOE is not set
+# CONFIG_PPPOLAC is not set
+# CONFIG_PPPOPNS is not set
+CONFIG_PPP_ASYNC=y
+# CONFIG_PPP_SYNC_TTY is not set
+# CONFIG_SLIP is not set
+CONFIG_SLHC=y
+# CONFIG_WLAN is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+CONFIG_WAN=y
+# CONFIG_HDLC is not set
+# CONFIG_DLCI is not set
+# CONFIG_SBNI is not set
+# CONFIG_VMXNET3 is not set
+CONFIG_ISDN=y
+# CONFIG_ISDN_I4L is not set
+# CONFIG_ISDN_CAPI is not set
+# CONFIG_ISDN_DRV_GIGASET is not set
+# CONFIG_HYSDN is not set
+# CONFIG_MISDN is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+# CONFIG_INPUT_SPARSEKMAP is not set
+# CONFIG_INPUT_MATRIXKMAP is not set
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_INPUT_MOUSEDEV_PSAUX=y
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_EVBUG is not set
+# CONFIG_INPUT_KEYRESET is not set
+# CONFIG_INPUT_KEYCOMBO is not set
+# CONFIG_INPUT_CFBOOST is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+# CONFIG_KEYBOARD_ADP5588 is not set
+# CONFIG_KEYBOARD_ADP5589 is not set
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_QT1070 is not set
+# CONFIG_KEYBOARD_QT2160 is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_TCA6416 is not set
+# CONFIG_KEYBOARD_TCA8418 is not set
+# CONFIG_KEYBOARD_LM8333 is not set
+# CONFIG_KEYBOARD_MAX7359 is not set
+# CONFIG_KEYBOARD_MCS is not set
+# CONFIG_KEYBOARD_MPR121 is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_OPENCORES is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_CYPRESS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_ELANTECH is not set
+# CONFIG_MOUSE_PS2_SENTELIC is not set
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_CYAPA is not set
+# CONFIG_MOUSE_INPORT is not set
+# CONFIG_MOUSE_LOGIBM is not set
+# CONFIG_MOUSE_PC110PAD is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_MOUSE_SYNAPTICS_I2C is not set
+CONFIG_INPUT_JOYSTICK=y
+# CONFIG_JOYSTICK_ANALOG is not set
+# CONFIG_JOYSTICK_A3D is not set
+# CONFIG_JOYSTICK_ADI is not set
+# CONFIG_JOYSTICK_COBRA is not set
+# CONFIG_JOYSTICK_GF2K is not set
+# CONFIG_JOYSTICK_GRIP is not set
+# CONFIG_JOYSTICK_GRIP_MP is not set
+# CONFIG_JOYSTICK_GUILLEMOT is not set
+# CONFIG_JOYSTICK_INTERACT is not set
+# CONFIG_JOYSTICK_SIDEWINDER is not set
+# CONFIG_JOYSTICK_TMDC is not set
+# CONFIG_JOYSTICK_IFORCE is not set
+# CONFIG_JOYSTICK_WARRIOR is not set
+# CONFIG_JOYSTICK_MAGELLAN is not set
+# CONFIG_JOYSTICK_SPACEORB is not set
+# CONFIG_JOYSTICK_SPACEBALL is not set
+# CONFIG_JOYSTICK_STINGER is not set
+# CONFIG_JOYSTICK_TWIDJOY is not set
+# CONFIG_JOYSTICK_ZHENHUA is not set
+# CONFIG_JOYSTICK_DB9 is not set
+# CONFIG_JOYSTICK_GAMECON is not set
+# CONFIG_JOYSTICK_TURBOGRAFX is not set
+# CONFIG_JOYSTICK_AS5011 is not set
+# CONFIG_JOYSTICK_JOYDUMP is not set
+# CONFIG_JOYSTICK_WALKERA0701 is not set
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879 is not set
+# CONFIG_TOUCHSCREEN_ATMEL_MXT is not set
+# CONFIG_TOUCHSCREEN_BU21013 is not set
+# CONFIG_CYPRESS_SAR is not set
+# CONFIG_TOUCHSCREEN_CYTTSP_CORE is not set
+# CONFIG_TOUCHSCREEN_DYNAPRO is not set
+# CONFIG_TOUCHSCREEN_HAMPSHIRE is not set
+# CONFIG_TOUCHSCREEN_EETI is not set
+# CONFIG_TOUCHSCREEN_FUJITSU is not set
+# CONFIG_TOUCHSCREEN_ILI210X is not set
+# CONFIG_TOUCHSCREEN_GUNZE is not set
+# CONFIG_TOUCHSCREEN_ELO is not set
+# CONFIG_TOUCHSCREEN_WACOM_W8001 is not set
+# CONFIG_TOUCHSCREEN_WACOM_I2C is not set
+# CONFIG_TOUCHSCREEN_MAX11801 is not set
+# CONFIG_TOUCHSCREEN_MCS5000 is not set
+# CONFIG_TOUCHSCREEN_MMS114 is not set
+# CONFIG_TOUCHSCREEN_MTOUCH is not set
+# CONFIG_TOUCHSCREEN_INEXIO is not set
+# CONFIG_TOUCHSCREEN_MK712 is not set
+# CONFIG_TOUCHSCREEN_HTCPEN is not set
+# CONFIG_TOUCHSCREEN_PENMOUNT is not set
+# CONFIG_TOUCHSCREEN_EDT_FT5X06 is not set
+# CONFIG_TOUCHSCREEN_PANJIT_I2C is not set
+# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
+# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
+# CONFIG_TOUCHSCREEN_PIXCIR is not set
+# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set
+# CONFIG_TOUCHSCREEN_TSC_SERIO is not set
+# CONFIG_TOUCHSCREEN_TSC2007 is not set
+# CONFIG_TOUCHSCREEN_ST1232 is not set
+# CONFIG_TOUCHSCREEN_TPS6507X is not set
+# CONFIG_TOUCHSCREEN_MAX1187X is not set
+CONFIG_TOUCHSCREEN_SYNAPTICS_DSX=y
+CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_I2C=y
+# CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_RMI_HID_I2C is not set
+# CONFIG_TOUCHSCREEN_SYNAPTICS_DSX_CORE is not set
+CONFIG_INPUT_MISC=y
+# CONFIG_INPUT_AD714X is not set
+# CONFIG_INPUT_BMA150 is not set
+# CONFIG_INPUT_PCSPKR is not set
+# CONFIG_INPUT_MMA8450 is not set
+# CONFIG_INPUT_MPU3050 is not set
+# CONFIG_INPUT_WISTRON_BTNS is not set
+# CONFIG_INPUT_KEYCHORD is not set
+# CONFIG_INPUT_KXTJ9 is not set
+CONFIG_INPUT_UINPUT=y
+# CONFIG_INPUT_GPIO is not set
+# CONFIG_INPUT_PCF8574 is not set
+# CONFIG_INPUT_ADXL34X is not set
+# CONFIG_INPUT_CMA3000 is not set
+# CONFIG_INPUT_DRV2603_VIBRATOR is not set
+# CONFIG_INV_AK8975 is not set
+# CONFIG_INV_MPU is not set
+# CONFIG_INV_BMP180 is not set
+
+#
+# Hardware I/O ports
+#
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+# CONFIG_SERIO_SERPORT is not set
+# CONFIG_SERIO_CT82C710 is not set
+# CONFIG_SERIO_PARKBD is not set
+# CONFIG_SERIO_PCIPS2 is not set
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIO_RAW=y
+# CONFIG_SERIO_ALTERA_PS2 is not set
+# CONFIG_SERIO_PS2MULT is not set
+# CONFIG_SERIO_ARC_PS2 is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_TTY=y
+CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_ROCKETPORT is not set
+# CONFIG_CYCLADES is not set
+# CONFIG_MOXA_INTELLIO is not set
+# CONFIG_MOXA_SMARTIO is not set
+# CONFIG_SYNCLINK is not set
+# CONFIG_SYNCLINKMP is not set
+# CONFIG_SYNCLINK_GT is not set
+# CONFIG_NOZOMI is not set
+# CONFIG_ISI is not set
+# CONFIG_N_HDLC is not set
+# CONFIG_N_GSM is not set
+# CONFIG_TRACE_SINK is not set
+CONFIG_DEVMEM=y
+CONFIG_DEVKMEM=y
+CONFIG_STALDRV=y
+
+#
+# Serial drivers
+#
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y
+CONFIG_SERIAL_8250_PNP=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_FIX_EARLYCON_MEM=y
+CONFIG_SERIAL_8250_PCI=y
+CONFIG_SERIAL_8250_NR_UARTS=48
+CONFIG_SERIAL_8250_RUNTIME_UARTS=4
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+# CONFIG_HAS_NS_SUPER_IO_CHIP is not set
+# CONFIG_SERIAL_8250_FOURPORT is not set
+# CONFIG_SERIAL_8250_ACCENT is not set
+# CONFIG_SERIAL_8250_BOCA is not set
+# CONFIG_SERIAL_8250_EXAR_ST16C554 is not set
+# CONFIG_SERIAL_8250_HUB6 is not set
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+# CONFIG_SERIAL_8250_DETECT_IRQ is not set
+CONFIG_SERIAL_8250_RSA=y
+# CONFIG_SERIAL_8250_DW is not set
+
+#
+# Non-8250 serial port support
+#
+# CONFIG_SERIAL_MFD_HSU is not set
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_SCCNXP is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
+# CONFIG_SERIAL_ALTERA_JTAGUART is not set
+# CONFIG_SERIAL_ALTERA_UART is not set
+# CONFIG_SERIAL_PCH_UART is not set
+# CONFIG_SERIAL_ARC is not set
+# CONFIG_SERIAL_RP2 is not set
+
+#
+# Diag Support
+#
+
+#
+# DIAG traffic over USB
+#
+
+#
+# SDIO support for DIAG
+#
+
+#
+# HSIC/SMUX support for DIAG
+#
+CONFIG_PRINTER=y
+# CONFIG_LP_CONSOLE is not set
+# CONFIG_PPDEV is not set
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+# CONFIG_IPMI_HANDLER is not set
+CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
+# CONFIG_HW_RANDOM_GEODE is not set
+# CONFIG_HW_RANDOM_VIA is not set
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_NVRAM=y
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+# CONFIG_SONYPI is not set
+# CONFIG_MWAVE is not set
+# CONFIG_PC8736x_GPIO is not set
+# CONFIG_NSC_GPIO is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HANGCHECK_TIMER is not set
+# CONFIG_TCG_TPM is not set
+# CONFIG_TELCLOCK is not set
+CONFIG_DEVPORT=y
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_COMPAT=y
+# CONFIG_I2C_CHARDEV is not set
+# CONFIG_I2C_MUX is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_INPUT_CWSTM32 is not set
+# CONFIG_I2C_SLAVE is not set
+# CONFIG_I2C_HELPER_AUTO is not set
+# CONFIG_I2C_SMBUS is not set
+
+#
+# I2C Algorithms
+#
+CONFIG_I2C_ALGOBIT=y
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# PC SMBus host controller drivers
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+CONFIG_I2C_ISCH=y
+# CONFIG_I2C_ISMT is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_DESIGNWARE_PCI is not set
+# CONFIG_I2C_EG20T is not set
+# CONFIG_I2C_INTEL_MID is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_PXA_PCI is not set
+# CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_XILINX is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_ISA is not set
+# CONFIG_SCx200_ACB is not set
+# CONFIG_I2C_PCA_GMI is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_SPI is not set
+
+#
+# Qualcomm MSM SSBI bus support
+#
+# CONFIG_SSBI is not set
+# CONFIG_HSI is not set
+
+#
+# PPS support
+#
+CONFIG_PPS=y
+# CONFIG_PPS_DEBUG is not set
+
+#
+# PPS clients support
+#
+# CONFIG_PPS_CLIENT_KTIMER is not set
+# CONFIG_PPS_CLIENT_LDISC is not set
+# CONFIG_PPS_CLIENT_PARPORT is not set
+# CONFIG_PPS_CLIENT_GPIO is not set
+
+#
+# PPS generators support
+#
+
+#
+# PTP clock support
+#
+CONFIG_PTP_1588_CLOCK=y
+
+#
+# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
+#
+# CONFIG_PTP_1588_CLOCK_PCH is not set
+CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
+CONFIG_GPIO_DEVRES=y
+# CONFIG_GPIOLIB is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_POWER_AVS is not set
+CONFIG_HWMON=y
+# CONFIG_HWMON_VID is not set
+# CONFIG_HWMON_DEBUG_CHIP is not set
+
+#
+# Native drivers
+#
+# CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ABITUGURU3 is not set
+# CONFIG_SENSORS_AD7414 is not set
+# CONFIG_SENSORS_AD7418 is not set
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1026 is not set
+# CONFIG_SENSORS_ADM1029 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ADT7410 is not set
+# CONFIG_SENSORS_ADT7411 is not set
+# CONFIG_SENSORS_ADT7462 is not set
+# CONFIG_SENSORS_ADT7470 is not set
+# CONFIG_SENSORS_ADT7475 is not set
+# CONFIG_SENSORS_ASC7621 is not set
+# CONFIG_SENSORS_K8TEMP is not set
+# CONFIG_SENSORS_K10TEMP is not set
+# CONFIG_SENSORS_FAM15H_POWER is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATXP1 is not set
+# CONFIG_SENSORS_DS620 is not set
+# CONFIG_SENSORS_DS1621 is not set
+# CONFIG_SENSORS_I5K_AMB is not set
+# CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_F71882FG is not set
+# CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
+# CONFIG_SENSORS_HIH6130 is not set
+# CONFIG_SENSORS_CORETEMP is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_JC42 is not set
+# CONFIG_SENSORS_LINEAGE is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM73 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
+# CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4151 is not set
+# CONFIG_SENSORS_LTC4215 is not set
+# CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LTC4261 is not set
+# CONFIG_SENSORS_LM95234 is not set
+# CONFIG_SENSORS_LM95241 is not set
+# CONFIG_SENSORS_LM95245 is not set
+# CONFIG_SENSORS_MAX16065 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_MAX1668 is not set
+# CONFIG_SENSORS_MAX197 is not set
+# CONFIG_SENSORS_MAX6639 is not set
+# CONFIG_SENSORS_MAX6642 is not set
+# CONFIG_SENSORS_MAX6650 is not set
+# CONFIG_SENSORS_MAX6697 is not set
+# CONFIG_SENSORS_MCP3021 is not set
+# CONFIG_SENSORS_NCT6775 is not set
+# CONFIG_SENSORS_NTC_THERMISTOR is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_PMBUS is not set
+# CONFIG_SENSORS_SHT21 is not set
+# CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_SMM665 is not set
+# CONFIG_SENSORS_DME1737 is not set
+# CONFIG_SENSORS_EMC1403 is not set
+# CONFIG_SENSORS_EMC2103 is not set
+# CONFIG_SENSORS_EMC6W201 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47M192 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_SCH56XX_COMMON is not set
+# CONFIG_SENSORS_SCH5627 is not set
+# CONFIG_SENSORS_SCH5636 is not set
+# CONFIG_SENSORS_ADS1015 is not set
+# CONFIG_SENSORS_ADS7828 is not set
+# CONFIG_SENSORS_AMC6821 is not set
+# CONFIG_SENSORS_INA209 is not set
+# CONFIG_SENSORS_INA2XX is not set
+# CONFIG_SENSORS_THMC50 is not set
+# CONFIG_SENSORS_TMP102 is not set
+# CONFIG_SENSORS_TMP401 is not set
+# CONFIG_SENSORS_TMP421 is not set
+# CONFIG_SENSORS_TMON_TMP411 is not set
+# CONFIG_SENSORS_VIA_CPUTEMP is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_VT8231 is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83791D is not set
+# CONFIG_SENSORS_W83792D is not set
+# CONFIG_SENSORS_W83793 is not set
+# CONFIG_SENSORS_W83795 is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83L786NG is not set
+# CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
+# CONFIG_SENSORS_APPLESMC is not set
+# CONFIG_SENSORS_INA219 is not set
+# CONFIG_SENSORS_INA230 is not set
+# CONFIG_SENSORS_INA3221 is not set
+# CONFIG_BATTERY_SYSTEM_VOLTAGE_MONITOR is not set
+# CONFIG_CABLE_VBUS_MONITOR is not set
+# CONFIG_THERMAL is not set
+
+#
+# Trusty
+#
+# CONFIG_TRUSTY is not set
+CONFIG_WATCHDOG=y
+CONFIG_WATCHDOG_CORE=y
+# CONFIG_WATCHDOG_NOWAYOUT is not set
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+# CONFIG_ACQUIRE_WDT is not set
+# CONFIG_ADVANTECH_WDT is not set
+# CONFIG_ALIM1535_WDT is not set
+# CONFIG_ALIM7101_WDT is not set
+# CONFIG_F71808E_WDT is not set
+# CONFIG_SP5100_TCO is not set
+# CONFIG_SC520_WDT is not set
+# CONFIG_SBC_FITPC2_WATCHDOG is not set
+# CONFIG_EUROTECH_WDT is not set
+# CONFIG_IB700_WDT is not set
+# CONFIG_IBMASR is not set
+# CONFIG_WAFER_WDT is not set
+# CONFIG_I6300ESB_WDT is not set
+# CONFIG_IE6XX_WDT is not set
+CONFIG_ITCO_WDT=y
+CONFIG_ITCO_VENDOR_SUPPORT=y
+# CONFIG_IT8712F_WDT is not set
+# CONFIG_IT87_WDT is not set
+# CONFIG_HP_WATCHDOG is not set
+# CONFIG_SC1200_WDT is not set
+# CONFIG_PC87413_WDT is not set
+# CONFIG_NV_TCO is not set
+# CONFIG_60XX_WDT is not set
+# CONFIG_SBC8360_WDT is not set
+# CONFIG_SBC7240_WDT is not set
+# CONFIG_CPU5_WDT is not set
+# CONFIG_SMSC_SCH311X_WDT is not set
+# CONFIG_SMSC37B787_WDT is not set
+# CONFIG_VIA_WDT is not set
+# CONFIG_W83627HF_WDT is not set
+# CONFIG_W83697HF_WDT is not set
+# CONFIG_W83697UG_WDT is not set
+# CONFIG_W83877F_WDT is not set
+# CONFIG_W83977F_WDT is not set
+# CONFIG_MACHZ_WDT is not set
+# CONFIG_SBC_EPX_C3_WATCHDOG is not set
+
+#
+# ISA-based Watchdog Cards
+#
+# CONFIG_PCWATCHDOG is not set
+# CONFIG_MIXCOMWD is not set
+# CONFIG_WDT is not set
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+CONFIG_BCMA_POSSIBLE=y
+
+#
+# Broadcom specific AMBA
+#
+# CONFIG_BCMA is not set
+
+#
+# Multifunction device drivers
+#
+CONFIG_MFD_CORE=y
+# CONFIG_MFD_CS5535 is not set
+# CONFIG_MFD_AS3711 is not set
+# CONFIG_PMIC_ADP5520 is not set
+# CONFIG_MFD_AIC3256 is not set
+# CONFIG_MFD_AIC3256_I2C is not set
+# CONFIG_MFD_CROS_EC is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_DA9052_I2C is not set
+# CONFIG_MFD_DA9055 is not set
+# CONFIG_MFD_MC13XXX_I2C is not set
+# CONFIG_HTC_PASIC3 is not set
+CONFIG_LPC_ICH=y
+CONFIG_LPC_SCH=y
+# CONFIG_MFD_JANZ_CMODIO is not set
+# CONFIG_MFD_88PM800 is not set
+# CONFIG_MFD_88PM805 is not set
+# CONFIG_MFD_88PM860X is not set
+# CONFIG_MFD_MAX77665 is not set
+# CONFIG_MFD_MAX77686 is not set
+# CONFIG_MFD_MAX77693 is not set
+# CONFIG_MFD_MAX8907 is not set
+# CONFIG_MFD_MAX8925 is not set
+# CONFIG_MFD_MAX8997 is not set
+# CONFIG_MFD_MAX8998 is not set
+# CONFIG_MFD_RETU is not set
+# CONFIG_AIC3XXX_I2C_REGMAP is not set
+# CONFIG_AIC3XXX_CORE is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_MFD_RDC321X is not set
+# CONFIG_MFD_RTSX_PCI is not set
+# CONFIG_MFD_RC5T583 is not set
+# CONFIG_MFD_SEC_CORE is not set
+# CONFIG_MFD_SI476X_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_MFD_SMSC is not set
+# CONFIG_ABX500_CORE is not set
+# CONFIG_MFD_MAX8831 is not set
+# CONFIG_MFD_STMPE is not set
+# CONFIG_MFD_AS3722 is not set
+# CONFIG_MFD_SYSCON is not set
+# CONFIG_MFD_TI_AM335X_TSCADC is not set
+# CONFIG_MFD_LP8788 is not set
+# CONFIG_MFD_PALMAS is not set
+# CONFIG_MFD_MAX8907C is not set
+# CONFIG_MFD_MAX77663 is not set
+# CONFIG_MFD_AS3720 is not set
+# CONFIG_TPS6105X is not set
+# CONFIG_TPS6507X is not set
+# CONFIG_MFD_TPS65090 is not set
+# CONFIG_MFD_TPS65217 is not set
+# CONFIG_MFD_TPS6586X is not set
+# CONFIG_MFD_TPS80031 is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_TWL6040_CORE is not set
+# CONFIG_MFD_WL1273_CORE is not set
+# CONFIG_MFD_LM3533 is not set
+# CONFIG_MFD_TC3589X is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_VX855 is not set
+# CONFIG_MFD_ARIZONA_I2C is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM831X_I2C is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_WM8994 is not set
+# CONFIG_MFD_MAX77660 is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_MEDIA_SUPPORT is not set
+
+#
+# Graphics support
+#
+# CONFIG_AGP is not set
+CONFIG_VGA_ARB=y
+CONFIG_VGA_ARB_MAX_GPUS=16
+# CONFIG_DRM is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_EXYNOS_VIDEO is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Console display driver support
+#
+CONFIG_VGA_CONSOLE=y
+CONFIG_VGACON_SOFT_SCROLLBACK=y
+CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256
+# CONFIG_MDA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_DS90UH925Q_SER is not set
+# CONFIG_SOUND is not set
+
+#
+# HID support
+#
+CONFIG_HID=y
+# CONFIG_HIDRAW is not set
+# CONFIG_UHID is not set
+CONFIG_HID_GENERIC=y
+
+#
+# Special HID drivers
+#
+CONFIG_HID_A4TECH=y
+# CONFIG_HID_ACRUX is not set
+CONFIG_HID_APPLE=y
+# CONFIG_HID_AUREAL is not set
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+# CONFIG_DRAGONRISE_FF is not set
+# CONFIG_HID_EMS_FF is not set
+# CONFIG_HID_ELECOM is not set
+CONFIG_HID_EZKEY=y
+# CONFIG_HID_KEYTOUCH is not set
+CONFIG_HID_KYE=y
+# CONFIG_HID_UCLOGIC is not set
+# CONFIG_HID_WALTOP is not set
+CONFIG_HID_GYRATION=y
+# CONFIG_HID_ICADE is not set
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+# CONFIG_HID_LCPOWER is not set
+CONFIG_HID_LOGITECH=y
+# CONFIG_HID_LOGITECH_DJ is not set
+# CONFIG_LOGITECH_FF is not set
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+# CONFIG_LOGIG940_FF is not set
+# CONFIG_LOGIWHEELS_FF is not set
+# CONFIG_HID_MAGICMOUSE is not set
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+# CONFIG_HID_MULTITOUCH is not set
+# CONFIG_HID_ORTEK is not set
+CONFIG_HID_PANTHERLORD=y
+# CONFIG_PANTHERLORD_FF is not set
+CONFIG_HID_PETALYNX=y
+# CONFIG_HID_PICOLCD is not set
+# CONFIG_HID_PRIMAX is not set
+# CONFIG_HID_PS3REMOTE is not set
+# CONFIG_HID_SAITEK is not set
+CONFIG_HID_SAMSUNG=y
+# CONFIG_HID_SPEEDLINK is not set
+# CONFIG_HID_STEELSERIES is not set
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+# CONFIG_GREENASIA_FF is not set
+CONFIG_HID_SMARTJOYPLUS=y
+# CONFIG_SMARTJOYPLUS_FF is not set
+# CONFIG_HID_TIVO is not set
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+# CONFIG_THRUSTMASTER_FF is not set
+CONFIG_HID_ZEROPLUS=y
+# CONFIG_ZEROPLUS_FF is not set
+# CONFIG_HID_ZYDACRON is not set
+# CONFIG_HID_SENSOR_HUB is not set
+
+#
+# I2C HID support
+#
+# CONFIG_I2C_HID is not set
+CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
+CONFIG_USB_ARCH_HAS_XHCI=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_UWB is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_SWITCH is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_INFINIBAND is not set
+CONFIG_EDAC=y
+CONFIG_EDAC_LEGACY_SYSFS=y
+# CONFIG_EDAC_DEBUG is not set
+CONFIG_EDAC_DECODE_MCE=y
+# CONFIG_EDAC_MCE_INJ is not set
+# CONFIG_EDAC_MM_EDAC is not set
+CONFIG_RTC_LIB=y
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+# CONFIG_UIO is not set
+# CONFIG_VIRT_DRIVERS is not set
+CONFIG_VIRTIO=y
+
+#
+# Virtio drivers
+#
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+# CONFIG_VIRTIO_MMIO is not set
+
+#
+# Microsoft Hyper-V guest support
+#
+# CONFIG_STAGING is not set
+# CONFIG_ANDROID is not set
+CONFIG_X86_PLATFORM_DEVICES=y
+# CONFIG_CHROMEOS_LAPTOP is not set
+# CONFIG_SENSORS_HDAPS is not set
+# CONFIG_IBM_RTL is not set
+# CONFIG_SAMSUNG_Q10 is not set
+
+#
+# Hardware Spinlock drivers
+#
+CONFIG_CLKSRC_I8253=y
+CONFIG_CLKEVT_I8253=y
+CONFIG_I8253_LOCK=y
+CONFIG_CLKBLD_I8253=y
+# CONFIG_MAILBOX is not set
+# CONFIG_IOMMU_SUPPORT is not set
+
+#
+# Remoteproc drivers
+#
+# CONFIG_STE_MODEM_RPROC is not set
+
+#
+# Rpmsg drivers
+#
+# CONFIG_PM_DEVFREQ is not set
+# CONFIG_EXTCON is not set
+# CONFIG_MIPI_BIF is not set
+# CONFIG_MEMORY is not set
+# CONFIG_IIO is not set
+# CONFIG_VME_BUS is not set
+# CONFIG_PWM is not set
+# CONFIG_IPACK_BUS is not set
+# CONFIG_RESET_CONTROLLER is not set
+
+#
+# SYSEDP Framework
+#
+# CONFIG_SYSEDP_FRAMEWORK is not set
+# CONFIG_GK20A is not set
+
+#
+# Android
+#
+
+#
+# Firmware Drivers
+#
+# CONFIG_EDD is not set
+CONFIG_FIRMWARE_MEMMAP=y
+# CONFIG_DELL_RBU is not set
+# CONFIG_DCDBAS is not set
+CONFIG_DMIID=y
+# CONFIG_DMI_SYSFS is not set
+CONFIG_ISCSI_IBFT_FIND=y
+# CONFIG_ISCSI_IBFT is not set
+# CONFIG_GOOGLE_FIRMWARE is not set
+
+#
+# File systems
+#
+CONFIG_DCACHE_WORD_ACCESS=y
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_USE_FOR_EXT23=y
+# CONFIG_EXT4_FS_POSIX_ACL is not set
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS_ENCRYPTION=y
+CONFIG_FS_ENCRYPTION=y
+CONFIG_EXT4_DEBUG=y
+CONFIG_JBD2=y
+CONFIG_JBD2_DEBUG=y
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+CONFIG_FS_POSIX_ACL=y
+CONFIG_EXPORTFS=y
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_FANOTIFY is not set
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+CONFIG_PRINT_QUOTA_WARNING=y
+# CONFIG_QUOTA_DEBUG is not set
+CONFIG_QUOTA_TREE=y
+CONFIG_QFMT_V1=y
+CONFIG_QFMT_V2=y
+CONFIG_QUOTACTL=y
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+CONFIG_GENERIC_ACL=y
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=y
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+# CONFIG_MSDOS_FS is not set
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+CONFIG_NTFS_FS=y
+# CONFIG_NTFS_DEBUG is not set
+CONFIG_NTFS_RW=y
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_VMCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
+# CONFIG_REPORT_PRESENT_CPUS is not set
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+# CONFIG_CONFIGFS_FS is not set
+CONFIG_MISC_FILESYSTEMS=y
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+CONFIG_ECRYPT_FS=y
+# CONFIG_ECRYPT_FS_MESSAGING is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
+CONFIG_CRAMFS=y
+# CONFIG_SQUASHFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_QNX6FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_PSTORE is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_F2FS_FS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="cp437"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+CONFIG_NLS_CODEPAGE_850=y
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_MAC_ROMAN is not set
+# CONFIG_NLS_MAC_CELTIC is not set
+# CONFIG_NLS_MAC_CENTEURO is not set
+# CONFIG_NLS_MAC_CROATIAN is not set
+# CONFIG_NLS_MAC_CYRILLIC is not set
+# CONFIG_NLS_MAC_GAELIC is not set
+# CONFIG_NLS_MAC_GREEK is not set
+# CONFIG_NLS_MAC_ICELAND is not set
+# CONFIG_NLS_MAC_INUIT is not set
+# CONFIG_NLS_MAC_ROMANIAN is not set
+# CONFIG_NLS_MAC_TURKISH is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
+CONFIG_ENABLE_WARN_DEPRECATED=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_STRIP_ASM_SYMS=y
+# CONFIG_READABLE_ASM is not set
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_SECTION_MISMATCH is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_LESS_GCC_OPT is not set
+# CONFIG_DEBUG_SHIRQ is not set
+# CONFIG_LOCKUP_DETECTOR is not set
+# CONFIG_PANIC_ON_OOPS is not set
+CONFIG_PANIC_ON_OOPS_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
+CONFIG_SCHED_DEBUG=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_DEBUG_SLAB is not set
+CONFIG_HAVE_DEBUG_KMEMLEAK=y
+# CONFIG_DEBUG_KMEMLEAK is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_LOCKDEP=y
+CONFIG_LOCK_STAT=y
+# CONFIG_DEBUG_LOCKDEP is not set
+CONFIG_TRACE_IRQFLAGS=y
+# CONFIG_DEBUG_ATOMIC_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
+CONFIG_DEBUG_STACK_USAGE=y
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_HIGHMEM is not set
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_INFO_REDUCED is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_VIRTUAL is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_TEST_LIST_SORT is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_DEBUG_CREDENTIALS is not set
+CONFIG_ARCH_WANT_FRAME_POINTERS=y
+CONFIG_FRAME_POINTER=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
+
+#
+# RCU Debugging
+#
+# CONFIG_PROVE_RCU is not set
+# CONFIG_SPARSE_RCU_POINTER is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+# CONFIG_RCU_CPU_STALL_INFO is not set
+# CONFIG_RCU_TRACE is not set
+# CONFIG_KPROBES_SANITY_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
+# CONFIG_DEBUG_PER_CPU_MAPS is not set
+# CONFIG_LKDTM is not set
+# CONFIG_NOTIFIER_ERROR_INJECTION is not set
+# CONFIG_FAULT_INJECTION is not set
+CONFIG_LATENCYTOP=y
+CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS=y
+# CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is not set
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_WANT_PAGE_DEBUG_FLAGS=y
+CONFIG_PAGE_GUARD=y
+CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST=y
+CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
+CONFIG_HAVE_C_RECORDMCOUNT=y
+CONFIG_TRACER_MAX_TRACE=y
+CONFIG_TRACE_CLOCK=y
+CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
+CONFIG_TRACING=y
+CONFIG_GENERIC_TRACER=y
+CONFIG_TRACING_SUPPORT=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+# CONFIG_IRQSOFF_TRACER is not set
+CONFIG_SCHED_TRACER=y
+# CONFIG_FTRACE_SYSCALLS is not set
+CONFIG_TRACER_SNAPSHOT=y
+# CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_KPROBE_EVENT=y
+# CONFIG_UPROBE_EVENT is not set
+CONFIG_PROBE_EVENTS=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_DYNAMIC_FTRACE_WITH_REGS=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_FTRACE_MCOUNT_RECORD=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
+# CONFIG_RING_BUFFER_BENCHMARK is not set
+# CONFIG_RING_BUFFER_STARTUP_TEST is not set
+# CONFIG_TRACELEVEL is not set
+# CONFIG_TRACEDUMP is not set
+# CONFIG_RBTREE_TEST is not set
+# CONFIG_INTERVAL_TREE_TEST is not set
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_DMA_API_DEBUG is not set
+# CONFIG_ATOMIC64_SELFTEST is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
+CONFIG_HAVE_ARCH_KMEMCHECK=y
+# CONFIG_TEST_STRING_HELPERS is not set
+# CONFIG_TEST_KSTRTOX is not set
+# CONFIG_STRICT_DEVMEM is not set
+CONFIG_X86_VERBOSE_BOOTUP=y
+CONFIG_EARLY_PRINTK=y
+# CONFIG_EARLY_PRINTK_DBGP is not set
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_X86_PTDUMP is not set
+CONFIG_DEBUG_RODATA=y
+# CONFIG_DEBUG_RODATA_TEST is not set
+# CONFIG_DEBUG_SET_MODULE_RONX is not set
+# CONFIG_DEBUG_NX_TEST is not set
+CONFIG_DOUBLEFAULT=y
+# CONFIG_DEBUG_TLBFLUSH is not set
+# CONFIG_IOMMU_STRESS is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
+# CONFIG_X86_DECODER_SELFTEST is not set
+CONFIG_IO_DELAY_TYPE_0X80=0
+CONFIG_IO_DELAY_TYPE_0XED=1
+CONFIG_IO_DELAY_TYPE_UDELAY=2
+CONFIG_IO_DELAY_TYPE_NONE=3
+CONFIG_IO_DELAY_0X80=y
+# CONFIG_IO_DELAY_0XED is not set
+# CONFIG_IO_DELAY_UDELAY is not set
+# CONFIG_IO_DELAY_NONE is not set
+CONFIG_DEFAULT_IO_DELAY_TYPE=0
+CONFIG_DEBUG_BOOT_PARAMS=y
+# CONFIG_CPA_DEBUG is not set
+CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_DEBUG_NMI_SELFTEST is not set
+
+#
+# Security options
+#
+CONFIG_KEYS=y
+# CONFIG_ENCRYPTED_KEYS is not set
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+# CONFIG_SECURITY_DMESG_RESTRICT is not set
+CONFIG_SECURITY=y
+# CONFIG_SECURITYFS is not set
+CONFIG_SECURITY_NETWORK=y
+# CONFIG_SECURITY_NETWORK_XFRM is not set
+# CONFIG_SECURITY_PATH is not set
+# CONFIG_SECURITY_SELINUX is not set
+# CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_SECURITY_APPARMOR is not set
+# CONFIG_TRUSTED_LITTLE_KERNEL is not set
+# CONFIG_SECURITY_YAMA is not set
+# CONFIG_IMA is not set
+# CONFIG_EVM is not set
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_DEFAULT_SECURITY=""
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_AEAD2=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_BLKCIPHER2=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG=y
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP2=y
+CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
+# CONFIG_CRYPTO_USER is not set
+CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
+# CONFIG_CRYPTO_GF128MUL is not set
+CONFIG_CRYPTO_NULL=y
+# CONFIG_CRYPTO_PCRYPT is not set
+CONFIG_CRYPTO_WORKQUEUE=y
+# CONFIG_CRYPTO_CRYPTD is not set
+CONFIG_CRYPTO_AUTHENC=y
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+CONFIG_CRYPTO_SEQIV=y
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_CTR=y
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=y
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_CMAC is not set
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_XCBC=y
+# CONFIG_CRYPTO_VMAC is not set
+
+#
+# Digest
+#
+CONFIG_CRYPTO_CRC32C=y
+# CONFIG_CRYPTO_CRC32C_INTEL is not set
+# CONFIG_CRYPTO_CRC32 is not set
+# CONFIG_CRYPTO_CRC32_PCLMUL is not set
+# CONFIG_CRYPTO_GHASH is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+# CONFIG_CRYPTO_RMD128 is not set
+CONFIG_CRYPTO_RMD160=y
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_AES_586=y
+# CONFIG_CRYPTO_AES_NI_INTEL is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=y
+CONFIG_CRYPTO_BLOWFISH=y
+CONFIG_CRYPTO_BLOWFISH_COMMON=y
+CONFIG_CRYPTO_CAMELLIA=y
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SALSA20_586 is not set
+# CONFIG_CRYPTO_SEED is not set
+CONFIG_CRYPTO_SERPENT=y
+# CONFIG_CRYPTO_SERPENT_SSE2_586 is not set
+# CONFIG_CRYPTO_TEA is not set
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_CRYPTO_TWOFISH_COMMON=y
+# CONFIG_CRYPTO_TWOFISH_586 is not set
+
+#
+# Compression
+#
+CONFIG_CRYPTO_DEFLATE=y
+# CONFIG_CRYPTO_ZLIB is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_USER_API_HASH is not set
+# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
+CONFIG_CRYPTO_HW=y
+CONFIG_CRYPTO_DEV_PADLOCK=y
+# CONFIG_CRYPTO_DEV_PADLOCK_AES is not set
+# CONFIG_CRYPTO_DEV_PADLOCK_SHA is not set
+# CONFIG_CRYPTO_DEV_GEODE is not set
+# CONFIG_CRYPTO_DEV_TEGRA_SE is not set
+# CONFIG_ASYMMETRIC_KEY_TYPE is not set
+CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_HAVE_KVM_IRQ_ROUTING=y
+CONFIG_HAVE_KVM_EVENTFD=y
+CONFIG_KVM_APIC_ARCHITECTURE=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM_ASYNC_PF=y
+CONFIG_HAVE_KVM_MSI=y
+CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=y
+CONFIG_KVM_INTEL=y
+# CONFIG_KVM_AMD is not set
+# CONFIG_KVM_MMU_AUDIT is not set
+# CONFIG_LGUEST is not set
+CONFIG_BINARY_PRINTF=y
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_STRNCPY_FROM_USER=y
+CONFIG_GENERIC_STRNLEN_USER=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_PCI_IOMAP=y
+CONFIG_GENERIC_IOMAP=y
+CONFIG_GENERIC_IO=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC16=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC32=y
+# CONFIG_CRC32_SELFTEST is not set
+CONFIG_CRC32_SLICEBY8=y
+# CONFIG_CRC32_SLICEBY4 is not set
+# CONFIG_CRC32_SARWATE is not set
+# CONFIG_CRC32_BIT is not set
+# CONFIG_CRC7 is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CRC8 is not set
+CONFIG_AUDIT_GENERIC=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_LZO_DECOMPRESS=y
+CONFIG_XZ_DEC=y
+CONFIG_XZ_DEC_X86=y
+CONFIG_XZ_DEC_POWERPC=y
+CONFIG_XZ_DEC_IA64=y
+CONFIG_XZ_DEC_ARM=y
+CONFIG_XZ_DEC_ARMTHUMB=y
+CONFIG_XZ_DEC_SPARC=y
+CONFIG_XZ_DEC_BCJ=y
+# CONFIG_XZ_DEC_TEST is not set
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
+CONFIG_DECOMPRESS_XZ=y
+CONFIG_DECOMPRESS_LZO=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
+CONFIG_DQL=y
+CONFIG_NLATTR=y
+CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE=y
+CONFIG_AVERAGE=y
+# CONFIG_CORDIC is not set
+# CONFIG_DDR is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 671524d..a5191e2 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -259,8 +259,8 @@
# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
CONFIG_EFI_VARS=y
CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS_ENCRYPTION=y
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index c6cd358..04a4890 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -92,12 +92,53 @@
#endif
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
+#else /* !SMP */
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
#endif
/*
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index c5d1785..02bab09 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -1,13 +1,6 @@
#ifndef _ASM_X86_IDLE_H
#define _ASM_X86_IDLE_H
-#define IDLE_START 1
-#define IDLE_END 2
-
-struct notifier_block;
-void idle_notifier_register(struct notifier_block *n);
-void idle_notifier_unregister(struct notifier_block *n);
-
#ifdef CONFIG_X86_64
void enter_idle(void);
void exit_idle(void);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 22224b3..57437a1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -660,6 +660,10 @@
rep_nop();
}
+#ifndef cpu_read_relax
+#define cpu_read_relax() cpu_relax()
+#endif
+
/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
diff --git a/arch/x86/include/asm/relaxed.h b/arch/x86/include/asm/relaxed.h
new file mode 100644
index 0000000..4b38a06
--- /dev/null
+++ b/arch/x86/include/asm/relaxed.h
@@ -0,0 +1,22 @@
+/*
+ * x86/include/asm/relaxed.h
+ *
+ * (copied from arm/include/asm/relaxed.h)
+ *
+ * Copyright (c) 2014 NVIDIA Corporation. All rights reserved.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _ASM_RELAXED_H_
+#define _ASM_RELAXED_H_
+
+#include <asm-generic/relaxed.h>
+
+#endif /*_ASM_RELAXED_H_*/
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 2e188d6..f106908 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -90,8 +90,7 @@
memcpy(®s->bx + i, args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(struct task_struct *task,
- struct pt_regs *regs)
+static inline int syscall_get_arch(void)
{
return AUDIT_ARCH_I386;
}
@@ -220,8 +219,7 @@
}
}
-static inline int syscall_get_arch(struct task_struct *task,
- struct pt_regs *regs)
+static inline int syscall_get_arch(void)
{
#ifdef CONFIG_IA32_EMULATION
/*
@@ -233,7 +231,7 @@
*
* x32 tasks should be considered AUDIT_ARCH_X86_64.
*/
- if (task_thread_info(task)->status & TS_COMPAT)
+ if (task_thread_info(current)->status & TS_COMPAT)
return AUDIT_ARCH_I386;
#endif
/* Both x32 and x86_64 are considered "64-bit". */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 59b9037..48f4399 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -40,19 +40,6 @@
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
- atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
- atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
#endif
struct kmem_cache *task_xstate_cachep;
@@ -257,14 +244,14 @@
void enter_idle(void)
{
this_cpu_write(is_idle, 1);
- atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+ idle_notifier_call_chain(IDLE_START);
}
static void __exit_idle(void)
{
if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
return;
- atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+ idle_notifier_call_chain(IDLE_END);
}
/* Called from interrupts to signify idle end */
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 75f9e5d..75b36cc 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -69,15 +69,15 @@
{
unsigned long rnd = 0;
- /*
- * 8 bits of randomness in 32bit mmaps, 20 address space bits
- * 28 bits of randomness in 64bit mmaps, 40 address space bits
- */
if (current->flags & PF_RANDOMIZE) {
if (mmap_is_ia32())
- rnd = get_random_int() % (1<<8);
+#ifdef CONFIG_COMPAT
+ rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
+#else
+ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
+#endif
else
- rnd = get_random_int() % (1<<28);
+ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
}
return rnd << PAGE_SHIFT;
}
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index aabfb83..01ed502 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -357,3 +357,7 @@
348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
349 i386 kcmp sys_kcmp
350 i386 finit_module sys_finit_module
+# 351 i386 sched_setattr sys_sched_setattr
+# 352 i386 sched_getattr sys_sched_getattr
+# 353 i386 renameat2 sys_renameat2
+354 i386 seccomp sys_seccomp
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 63a8993..c7b4ac7 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -320,6 +320,10 @@
311 64 process_vm_writev sys_process_vm_writev
312 common kcmp sys_kcmp
313 common finit_module sys_finit_module
+# 314 common sched_setattr sys_sched_setattr
+# 315 common sched_getattr sys_sched_getattr
+# 316 common renameat2 sys_renameat2
+317 common seccomp sys_seccomp
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index ae7319d..5e04a1c 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -508,7 +508,6 @@
{
struct rt_sigframe __user *frame;
int err = 0;
- struct task_struct *me = current;
frame = (struct rt_sigframe __user *)
round_down(stack_top - sizeof(struct rt_sigframe), 16);
diff --git a/block/genhd.c b/block/genhd.c
index 7af2f6a..fd1946b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1117,6 +1117,22 @@
blk_put_queue(disk->queue);
kfree(disk);
}
+
+static int disk_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+ struct disk_part_iter piter;
+ struct hd_struct *part;
+ int cnt = 0;
+
+ disk_part_iter_init(&piter, disk, 0);
+ while((part = disk_part_iter_next(&piter)))
+ cnt++;
+ disk_part_iter_exit(&piter);
+ add_uevent_var(env, "NPARTS=%u", cnt);
+ return 0;
+}
+
struct class block_class = {
.name = "block",
};
@@ -1136,6 +1152,7 @@
.groups = disk_attr_groups,
.release = disk_release,
.devnode = block_devnode,
+ .uevent = disk_uevent,
};
#ifdef CONFIG_PROC_FS
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 0d9e5f9..47284e7 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -217,10 +217,21 @@
kfree(p);
}
+static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct hd_struct *part = dev_to_part(dev);
+
+ add_uevent_var(env, "PARTN=%u", part->partno);
+ if (part->info && part->info->volname[0])
+ add_uevent_var(env, "PARTNAME=%s", part->info->volname);
+ return 0;
+}
+
struct device_type part_type = {
.name = "partition",
.groups = part_attr_groups,
.release = part_release,
+ .uevent = part_uevent,
};
static void delete_partition_rcu_cb(struct rcu_head *head)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bf8148e..fa7e2a8 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -179,6 +179,10 @@
depends on X86
select CRYPTO_CRYPTD
+config CRYPTO_ABLK_HELPER
+ tristate
+ select CRYPTO_CRYPTD
+
config CRYPTO_GLUE_HELPER_X86
tristate
depends on X86
@@ -529,6 +533,17 @@
This is the powerpc hardware accelerated implementation of the
SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
+config CRYPTO_SHA1_ARM_NEON
+ tristate "SHA1 digest algorithm (ARM NEON)"
+ depends on ARM && KERNEL_MODE_NEON && !CPU_BIG_ENDIAN
+ select CRYPTO_SHA1_ARM
+ select CRYPTO_SHA1
+ select CRYPTO_HASH
+ help
+ SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+ using optimized ARM NEON assembly, when NEON instructions are
+ available.
+
config CRYPTO_SHA256
tristate "SHA224 and SHA256 digest algorithm"
select CRYPTO_HASH
@@ -541,6 +556,13 @@
This code also includes SHA-224, a 224 bit hash with 112 bits
of security against collision attacks.
+config CRYPTO_SHA256_ARM
+ tristate "SHA-224/256 digest algorithm (ARM-asm and NEON)"
+ select CRYPTO_HASH
+ help
+ SHA-256 secure hash standard (DFIPS 180-2) implemented
+ using optimized ARM assembler and NEON, when available.
+
config CRYPTO_SHA256_SPARC64
tristate "SHA224 and SHA256 digest algorithm (SPARC64)"
depends on SPARC64
@@ -562,6 +584,21 @@
This code also includes SHA-384, a 384 bit hash with 192 bits
of security against collision attacks.
+config CRYPTO_SHA512_ARM_NEON
+ tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
+ depends on ARM && KERNEL_MODE_NEON && !CPU_BIG_ENDIAN
+ select CRYPTO_SHA512
+ select CRYPTO_HASH
+ help
+ SHA-512 secure hash standard (DFIPS 180-2) implemented
+ using ARM NEON instructions, when available.
+
+ This version of SHA implements a 512 bit hash with 256 bits of
+ security against collision attacks.
+
+ This code also includes SHA-384, a 384 bit hash with 192 bits
+ of security against collision attacks.
+
config CRYPTO_SHA512_SPARC64
tristate "SHA384 and SHA512 digest algorithm (SPARC64)"
depends on SPARC64
@@ -757,6 +794,22 @@
See <http://csrc.nist.gov/encryption/aes/> for more information.
+config CRYPTO_AES_ARM_BS
+ tristate "Bit sliced AES using NEON instructions"
+ depends on ARM && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_AES_ARM
+ select CRYPTO_ABLK_HELPER
+ help
+ Use a faster and more secure NEON based implementation of AES in CBC,
+ CTR and XTS modes
+
+ Bit sliced AES gives around 45% speedup on Cortex-A15 for CTR mode
+ and for XTS mode encryption, CBC and XTS mode decryption speedup is
+ around 25%. (CBC encryption speed is not affected by this driver.)
+ This implementation does not rely on any lookup tables so it is
+ believed to be invulnerable to cache timing attacks.
+
config CRYPTO_ANUBIS
tristate "Anubis cipher algorithm"
select CRYPTO_ALGAPI
diff --git a/crypto/Makefile b/crypto/Makefile
index a8e9b0f..5d0b869 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -101,3 +101,4 @@
obj-$(CONFIG_XOR_BLOCKS) += xor.o
obj-$(CONFIG_ASYNC_CORE) += async_tx/
obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_ABLK_HELPER) += ablk_helper.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
new file mode 100644
index 0000000..ffe7278
--- /dev/null
+++ b/crypto/ablk_helper.c
@@ -0,0 +1,150 @@
+/*
+ * Shared async block cipher helpers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on aesni-intel_glue.c by:
+ * Copyright (C) 2008, Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
+ * USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <crypto/ablk_helper.h>
+#include <asm/simd.h>
+
+int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+ int err;
+
+ crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+ crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+ & CRYPTO_TFM_REQ_MASK);
+ err = crypto_ablkcipher_setkey(child, key, key_len);
+ crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+ & CRYPTO_TFM_RES_MASK);
+ return err;
+}
+EXPORT_SYMBOL_GPL(ablk_set_key);
+
+int __ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->encrypt(
+ &desc, req->dst, req->src, req->nbytes);
+}
+EXPORT_SYMBOL_GPL(__ablk_encrypt);
+
+int ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!may_use_simd()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ *cryptd_req = *req;
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_encrypt(cryptd_req);
+ } else {
+ return __ablk_encrypt(req);
+ }
+}
+EXPORT_SYMBOL_GPL(ablk_encrypt);
+
+int ablk_decrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!may_use_simd()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ *cryptd_req = *req;
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_decrypt(cryptd_req);
+ } else {
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->decrypt(
+ &desc, req->dst, req->src, req->nbytes);
+ }
+}
+EXPORT_SYMBOL_GPL(ablk_decrypt);
+
+void ablk_exit(struct crypto_tfm *tfm)
+{
+ struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+EXPORT_SYMBOL_GPL(ablk_exit);
+
+int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
+{
+ struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+
+ ctx->cryptd_tfm = cryptd_tfm;
+ tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+ crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ablk_init_common);
+
+int ablk_init(struct crypto_tfm *tfm)
+{
+ char drv_name[CRYPTO_MAX_ALG_NAME];
+
+ snprintf(drv_name, sizeof(drv_name), "__driver-%s",
+ crypto_tfm_alg_driver_name(tfm));
+
+ return ablk_init_common(tfm, drv_name);
+}
+EXPORT_SYMBOL_GPL(ablk_init);
+
+MODULE_LICENSE("GPL");
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9..0122bec 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@
return max(start, end_page);
}
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
- struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
unsigned int bsize)
{
u8 *addr;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
- addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+ addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
addr = blkcipher_get_spot(addr, bsize);
scatterwalk_copychunks(addr, &walk->out, bsize, 1);
return bsize;
@@ -105,7 +103,6 @@
int blkcipher_walk_done(struct blkcipher_desc *desc,
struct blkcipher_walk *walk, int err)
{
- struct crypto_blkcipher *tfm = desc->tfm;
unsigned int nbytes = 0;
if (likely(err >= 0)) {
@@ -117,7 +114,7 @@
err = -EINVAL;
goto err;
} else
- n = blkcipher_done_slow(tfm, walk, n);
+ n = blkcipher_done_slow(walk, n);
nbytes = walk->total - n;
err = 0;
@@ -136,7 +133,7 @@
}
if (walk->iv != desc->info)
- memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+ memcpy(desc->info, walk->iv, walk->ivsize);
if (walk->buffer != walk->page)
kfree(walk->buffer);
if (walk->page)
@@ -226,22 +223,20 @@
static int blkcipher_walk_next(struct blkcipher_desc *desc,
struct blkcipher_walk *walk)
{
- struct crypto_blkcipher *tfm = desc->tfm;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
unsigned int bsize;
unsigned int n;
int err;
n = walk->total;
- if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+ if (unlikely(n < walk->cipher_blocksize)) {
desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
return blkcipher_walk_done(desc, walk, -EINVAL);
}
walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
BLKCIPHER_WALK_DIFF);
- if (!scatterwalk_aligned(&walk->in, alignmask) ||
- !scatterwalk_aligned(&walk->out, alignmask)) {
+ if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+ !scatterwalk_aligned(&walk->out, walk->alignmask)) {
walk->flags |= BLKCIPHER_WALK_COPY;
if (!walk->page) {
walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@
}
}
- bsize = min(walk->blocksize, n);
+ bsize = min(walk->walk_blocksize, n);
n = scatterwalk_clamp(&walk->in, n);
n = scatterwalk_clamp(&walk->out, n);
if (unlikely(n < bsize)) {
- err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+ err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
goto set_phys_lowmem;
}
@@ -277,28 +272,26 @@
return err;
}
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
- struct crypto_blkcipher *tfm,
- unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
{
- unsigned bs = walk->blocksize;
- unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
- unsigned aligned_bs = ALIGN(bs, alignmask + 1);
- unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
- (alignmask + 1);
+ unsigned bs = walk->walk_blocksize;
+ unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+ unsigned int size = aligned_bs * 2 +
+ walk->ivsize + max(aligned_bs, walk->ivsize) -
+ (walk->alignmask + 1);
u8 *iv;
- size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+ size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
walk->buffer = kmalloc(size, GFP_ATOMIC);
if (!walk->buffer)
return -ENOMEM;
- iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+ iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
iv = blkcipher_get_spot(iv, bs) + aligned_bs;
iv = blkcipher_get_spot(iv, bs) + aligned_bs;
- iv = blkcipher_get_spot(iv, ivsize);
+ iv = blkcipher_get_spot(iv, walk->ivsize);
- walk->iv = memcpy(iv, walk->iv, ivsize);
+ walk->iv = memcpy(iv, walk->iv, walk->ivsize);
return 0;
}
@@ -306,7 +299,10 @@
struct blkcipher_walk *walk)
{
walk->flags &= ~BLKCIPHER_WALK_PHYS;
- walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->cipher_blocksize = walk->walk_blocksize;
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@
struct blkcipher_walk *walk)
{
walk->flags |= BLKCIPHER_WALK_PHYS;
- walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->cipher_blocksize = walk->walk_blocksize;
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@
static int blkcipher_walk_first(struct blkcipher_desc *desc,
struct blkcipher_walk *walk)
{
- struct crypto_blkcipher *tfm = desc->tfm;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
if (WARN_ON_ONCE(in_irq()))
return -EDEADLK;
@@ -335,8 +331,8 @@
walk->buffer = NULL;
walk->iv = desc->info;
- if (unlikely(((unsigned long)walk->iv & alignmask))) {
- int err = blkcipher_copy_iv(walk, tfm, alignmask);
+ if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+ int err = blkcipher_copy_iv(walk);
if (err)
return err;
}
@@ -353,11 +349,28 @@
unsigned int blocksize)
{
walk->flags &= ~BLKCIPHER_WALK_PHYS;
- walk->blocksize = blocksize;
+ walk->walk_blocksize = blocksize;
+ walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk,
+ struct crypto_aead *tfm,
+ unsigned int blocksize)
+{
+ walk->flags &= ~BLKCIPHER_WALK_PHYS;
+ walk->walk_blocksize = blocksize;
+ walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+ walk->ivsize = crypto_aead_ivsize(tfm);
+ walk->alignmask = crypto_aead_alignmask(tfm);
+ return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
unsigned int keylen)
{
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 9953a42..f1a9506 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -100,6 +100,8 @@
source "drivers/leds/Kconfig"
+source "drivers/switch/Kconfig"
+
source "drivers/accessibility/Kconfig"
source "drivers/infiniband/Kconfig"
@@ -166,4 +168,6 @@
source "drivers/reset/Kconfig"
+source "drivers/android/Kconfig"
+
endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 130abc1..fe5799a 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -111,6 +111,7 @@
obj-y += mmc/
obj-$(CONFIG_MEMSTICK) += memstick/
obj-y += leds/
+obj-$(CONFIG_SWITCH) += switch/
obj-$(CONFIG_INFINIBAND) += infiniband/
obj-$(CONFIG_SGI_SN) += sn/
obj-y += firmware/
@@ -152,3 +153,4 @@
obj-$(CONFIG_VME_BUS) += vme/
obj-$(CONFIG_IPACK_BUS) += ipack/
obj-$(CONFIG_NTB) += ntb/
+obj-$(CONFIG_ANDROID) += android/
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
new file mode 100644
index 0000000..bdfc6c6
--- /dev/null
+++ b/drivers/android/Kconfig
@@ -0,0 +1,37 @@
+menu "Android"
+
+config ANDROID
+ bool "Android Drivers"
+ ---help---
+ Enable support for various drivers needed on the Android platform
+
+if ANDROID
+
+config ANDROID_BINDER_IPC
+ bool "Android Binder IPC Driver"
+ depends on MMU
+ default n
+ ---help---
+ Binder is used in Android for both communication between processes,
+ and remote method invocation.
+
+ This means one Android process can call a method/routine in another
+ Android process, using Binder to identify, invoke and pass arguments
+ between said processes.
+
+config ANDROID_BINDER_IPC_32BIT
+ bool
+ depends on !64BIT && ANDROID_BINDER_IPC
+ default y
+ ---help---
+ The Binder API has been changed to support both 32 and 64bit
+ applications in a mixed environment.
+
+ Enable this to support an old 32-bit Android user-space (v4.4 and
+ earlier).
+
+ Note that enabling this will break newer Android user-space.
+
+endif # if ANDROID
+
+endmenu
diff --git a/drivers/android/Makefile b/drivers/android/Makefile
new file mode 100644
index 0000000..3b7e4b0
--- /dev/null
+++ b/drivers/android/Makefile
@@ -0,0 +1,3 @@
+ccflags-y += -I$(src) # needed for trace events
+
+obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o
diff --git a/drivers/staging/android/binder.c b/drivers/android/binder.c
similarity index 84%
rename from drivers/staging/android/binder.c
rename to drivers/android/binder.c
index 0fce5fc..d8b2013 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/android/binder.c
@@ -20,6 +20,7 @@
#include <asm/cacheflush.h>
#include <linux/fdtable.h>
#include <linux/file.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/miscdevice.h>
@@ -36,8 +37,13 @@
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
+#include <linux/security.h>
-#include "binder.h"
+#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
+#define BINDER_IPC_32BIT 1
+#endif
+
+#include <uapi/linux/android/binder.h>
#include "binder_trace.h"
static DEFINE_MUTEX(binder_main_lock);
@@ -117,6 +123,7 @@
struct kernel_param *kp)
{
int ret;
+
ret = param_set_int(val, kp);
if (binder_stop_on_user_error < 2)
wake_up(&binder_user_error_wait);
@@ -193,6 +200,7 @@
struct binder_transaction_log *log)
{
struct binder_transaction_log_entry *e;
+
e = &log->entry[log->next];
memset(e, 0, sizeof(*e));
log->next++;
@@ -227,8 +235,8 @@
int internal_strong_refs;
int local_weak_refs;
int local_strong_refs;
- void __user *ptr;
- void __user *cookie;
+ binder_uintptr_t ptr;
+ binder_uintptr_t cookie;
unsigned has_strong_ref:1;
unsigned pending_strong_ref:1;
unsigned has_weak_ref:1;
@@ -241,7 +249,7 @@
struct binder_ref_death {
struct binder_work work;
- void __user *cookie;
+ binder_uintptr_t cookie;
};
struct binder_ref {
@@ -371,6 +379,7 @@
struct files_struct *files = proc->files;
unsigned long rlim_cur;
unsigned long irqs;
+ int ret;
if (files == NULL)
return -ESRCH;
@@ -381,7 +390,11 @@
rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
unlock_task_sighand(proc->tsk, &irqs);
- return __alloc_fd(files, 0, rlim_cur, flags);
+ preempt_enable_no_resched();
+ ret = __alloc_fd(files, 0, rlim_cur, flags);
+ preempt_disable();
+
+ return ret;
}
/*
@@ -390,8 +403,11 @@
static void task_fd_install(
struct binder_proc *proc, unsigned int fd, struct file *file)
{
- if (proc->files)
+ if (proc->files) {
+ preempt_enable_no_resched();
__fd_install(proc->files, fd, file);
+ preempt_disable();
+ }
}
/*
@@ -419,6 +435,7 @@
{
trace_binder_lock(tag);
mutex_lock(&binder_main_lock);
+ preempt_disable();
trace_binder_locked(tag);
}
@@ -426,11 +443,66 @@
{
trace_binder_unlock(tag);
mutex_unlock(&binder_main_lock);
+ preempt_enable();
}
+static inline void *kzalloc_preempt_disabled(size_t size)
+{
+ void *ptr;
+
+ ptr = kzalloc(size, GFP_NOWAIT);
+ if (ptr)
+ return ptr;
+
+ preempt_enable_no_resched();
+ ptr = kzalloc(size, GFP_KERNEL);
+ preempt_disable();
+
+ return ptr;
+}
+
+static inline long copy_to_user_preempt_disabled(void __user *to, const void *from, long n)
+{
+ long ret;
+
+ preempt_enable_no_resched();
+ ret = copy_to_user(to, from, n);
+ preempt_disable();
+ return ret;
+}
+
+static inline long copy_from_user_preempt_disabled(void *to, const void __user *from, long n)
+{
+ long ret;
+
+ preempt_enable_no_resched();
+ ret = copy_from_user(to, from, n);
+ preempt_disable();
+ return ret;
+}
+
+#define get_user_preempt_disabled(x, ptr) \
+({ \
+ int __ret; \
+ preempt_enable_no_resched(); \
+ __ret = get_user(x, ptr); \
+ preempt_disable(); \
+ __ret; \
+})
+
+#define put_user_preempt_disabled(x, ptr) \
+({ \
+ int __ret; \
+ preempt_enable_no_resched(); \
+ __ret = put_user(x, ptr); \
+ preempt_disable(); \
+ __ret; \
+})
+
static void binder_set_nice(long nice)
{
long min_nice;
+
if (can_nice(current, nice)) {
set_user_nice(current, nice);
return;
@@ -450,9 +522,8 @@
{
if (list_is_last(&buffer->entry, &proc->buffers))
return proc->buffer + proc->buffer_size - (void *)buffer->data;
- else
- return (size_t)list_entry(buffer->entry.next,
- struct binder_buffer, entry) - (size_t)buffer->data;
+ return (size_t)list_entry(buffer->entry.next,
+ struct binder_buffer, entry) - (size_t)buffer->data;
}
static void binder_insert_free_buffer(struct binder_proc *proc,
@@ -514,14 +585,14 @@
}
static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc,
- void __user *user_ptr)
+ uintptr_t user_ptr)
{
struct rb_node *n = proc->allocated_buffers.rb_node;
struct binder_buffer *buffer;
struct binder_buffer *kern_ptr;
- kern_ptr = user_ptr - proc->user_buffer_offset
- - offsetof(struct binder_buffer, data);
+ kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset
+ - offsetof(struct binder_buffer, data));
while (n) {
buffer = rb_entry(n, struct binder_buffer, rb_node);
@@ -561,6 +632,8 @@
else
mm = get_task_mm(proc->tsk);
+ preempt_enable_no_resched();
+
if (mm) {
down_write(&mm->mmap_sem);
vma = proc->vma;
@@ -583,6 +656,7 @@
for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
int ret;
struct page **page_array_ptr;
+
page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
BUG_ON(*page);
@@ -615,6 +689,9 @@
up_write(&mm->mmap_sem);
mmput(mm);
}
+
+ preempt_disable();
+
return 0;
free_range:
@@ -637,6 +714,9 @@
up_write(&mm->mmap_sem);
mmput(mm);
}
+
+ preempt_disable();
+
return -ENOMEM;
}
@@ -725,6 +805,7 @@
binder_insert_allocated_buffer(proc, buffer);
if (buffer_size != size) {
struct binder_buffer *new_buffer = (void *)buffer->data + size;
+
list_add(&new_buffer->entry, &buffer->entry);
new_buffer->free = 1;
binder_insert_free_buffer(proc, new_buffer);
@@ -790,7 +871,7 @@
list_del(&buffer->entry);
if (free_page_start || free_page_end) {
binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
- "%d: merge free, buffer %p do not share page%s%s with with %p or %p\n",
+ "%d: merge free, buffer %p do not share page%s%s with %p or %p\n",
proc->pid, buffer, free_page_start ? "" : " end",
free_page_end ? "" : " start", prev, next);
binder_update_page_range(proc, 0, free_page_start ?
@@ -837,6 +918,7 @@
if (!list_is_last(&buffer->entry, &proc->buffers)) {
struct binder_buffer *next = list_entry(buffer->entry.next,
struct binder_buffer, entry);
+
if (next->free) {
rb_erase(&next->rb_node, &proc->free_buffers);
binder_delete_free_buffer(proc, next);
@@ -845,6 +927,7 @@
if (proc->buffers.next != &buffer->entry) {
struct binder_buffer *prev = list_entry(buffer->entry.prev,
struct binder_buffer, entry);
+
if (prev->free) {
binder_delete_free_buffer(proc, buffer);
rb_erase(&prev->rb_node, &proc->free_buffers);
@@ -855,7 +938,7 @@
}
static struct binder_node *binder_get_node(struct binder_proc *proc,
- void __user *ptr)
+ binder_uintptr_t ptr)
{
struct rb_node *n = proc->nodes.rb_node;
struct binder_node *node;
@@ -874,8 +957,8 @@
}
static struct binder_node *binder_new_node(struct binder_proc *proc,
- void __user *ptr,
- void __user *cookie)
+ binder_uintptr_t ptr,
+ binder_uintptr_t cookie)
{
struct rb_node **p = &proc->nodes.rb_node;
struct rb_node *parent = NULL;
@@ -893,7 +976,7 @@
return NULL;
}
- node = kzalloc(sizeof(*node), GFP_KERNEL);
+ node = kzalloc_preempt_disabled(sizeof(*node));
if (node == NULL)
return NULL;
binder_stats_created(BINDER_STAT_NODE);
@@ -907,9 +990,9 @@
INIT_LIST_HEAD(&node->work.entry);
INIT_LIST_HEAD(&node->async_todo);
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d:%d node %d u%p c%p created\n",
+ "%d:%d node %d u%016llx c%016llx created\n",
proc->pid, current->pid, node->debug_id,
- node->ptr, node->cookie);
+ (u64)node->ptr, (u64)node->cookie);
return node;
}
@@ -1030,7 +1113,7 @@
else
return ref;
}
- new_ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+ new_ref = kzalloc_preempt_disabled(sizeof(*ref));
if (new_ref == NULL)
return NULL;
binder_stats_created(BINDER_STAT_REF);
@@ -1106,6 +1189,7 @@
struct list_head *target_list)
{
int ret;
+
if (strong) {
if (ref->strong == 0) {
ret = binder_inc_node(ref->node, 1, 1, target_list);
@@ -1137,6 +1221,7 @@
ref->strong--;
if (ref->strong == 0) {
int ret;
+
ret = binder_dec_node(ref->node, strong, 1);
if (ret)
return ret;
@@ -1176,6 +1261,8 @@
uint32_t error_code)
{
struct binder_thread *target_thread;
+ struct binder_transaction *next;
+
BUG_ON(t->flags & TF_ONE_WAY);
while (1) {
target_thread = t->from;
@@ -1189,7 +1276,8 @@
if (target_thread->return_error == BR_OK) {
binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
"send failed reply for transaction %d to %d:%d\n",
- t->debug_id, target_thread->proc->pid,
+ t->debug_id,
+ target_thread->proc->pid,
target_thread->pid);
binder_pop_transaction(target_thread, t);
@@ -1202,32 +1290,31 @@
target_thread->return_error);
}
return;
- } else {
- struct binder_transaction *next = t->from_parent;
-
- binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
- "send failed reply for transaction %d, target dead\n",
- t->debug_id);
-
- binder_pop_transaction(target_thread, t);
- if (next == NULL) {
- binder_debug(BINDER_DEBUG_DEAD_BINDER,
- "reply failed, no target thread at root\n");
- return;
- }
- t = next;
- binder_debug(BINDER_DEBUG_DEAD_BINDER,
- "reply failed, no target thread -- retry %d\n",
- t->debug_id);
}
+ next = t->from_parent;
+
+ binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+ "send failed reply for transaction %d, target dead\n",
+ t->debug_id);
+
+ binder_pop_transaction(target_thread, t);
+ if (next == NULL) {
+ binder_debug(BINDER_DEBUG_DEAD_BINDER,
+ "reply failed, no target thread at root\n");
+ return;
+ }
+ t = next;
+ binder_debug(BINDER_DEBUG_DEAD_BINDER,
+ "reply failed, no target thread -- retry %d\n",
+ t->debug_id);
}
}
static void binder_transaction_buffer_release(struct binder_proc *proc,
struct binder_buffer *buffer,
- size_t *failed_at)
+ binder_size_t *failed_at)
{
- size_t *offp, *off_end;
+ binder_size_t *offp, *off_end;
int debug_id = buffer->debug_id;
binder_debug(BINDER_DEBUG_TRANSACTION,
@@ -1238,18 +1325,20 @@
if (buffer->target_node)
binder_dec_node(buffer->target_node, 1, 0);
- offp = (size_t *)(buffer->data + ALIGN(buffer->data_size, sizeof(void *)));
+ offp = (binder_size_t *)(buffer->data +
+ ALIGN(buffer->data_size, sizeof(void *)));
if (failed_at)
off_end = failed_at;
else
off_end = (void *)offp + buffer->offsets_size;
for (; offp < off_end; offp++) {
struct flat_binder_object *fp;
+
if (*offp > buffer->data_size - sizeof(*fp) ||
buffer->data_size < sizeof(*fp) ||
- !IS_ALIGNED(*offp, sizeof(void *))) {
- pr_err("transaction release %d bad offset %zd, size %zd\n",
- debug_id, *offp, buffer->data_size);
+ !IS_ALIGNED(*offp, sizeof(u32))) {
+ pr_err("transaction release %d bad offset %lld, size %zd\n",
+ debug_id, (u64)*offp, buffer->data_size);
continue;
}
fp = (struct flat_binder_object *)(buffer->data + *offp);
@@ -1257,21 +1346,23 @@
case BINDER_TYPE_BINDER:
case BINDER_TYPE_WEAK_BINDER: {
struct binder_node *node = binder_get_node(proc, fp->binder);
+
if (node == NULL) {
- pr_err("transaction release %d bad node %p\n",
- debug_id, fp->binder);
+ pr_err("transaction release %d bad node %016llx\n",
+ debug_id, (u64)fp->binder);
break;
}
binder_debug(BINDER_DEBUG_TRANSACTION,
- " node %d u%p\n",
- node->debug_id, node->ptr);
+ " node %d u%016llx\n",
+ node->debug_id, (u64)node->ptr);
binder_dec_node(node, fp->type == BINDER_TYPE_BINDER, 0);
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+
if (ref == NULL) {
- pr_err("transaction release %d bad handle %ld\n",
+ pr_err("transaction release %d bad handle %d\n",
debug_id, fp->handle);
break;
}
@@ -1283,13 +1374,13 @@
case BINDER_TYPE_FD:
binder_debug(BINDER_DEBUG_TRANSACTION,
- " fd %ld\n", fp->handle);
+ " fd %d\n", fp->handle);
if (failed_at)
task_close_fd(proc, fp->handle);
break;
default:
- pr_err("transaction release %d bad object type %lx\n",
+ pr_err("transaction release %d bad object type %x\n",
debug_id, fp->type);
break;
}
@@ -1302,7 +1393,8 @@
{
struct binder_transaction *t;
struct binder_work *tcomplete;
- size_t *offp, *off_end;
+ binder_size_t *offp, *off_end;
+ binder_size_t off_min;
struct binder_proc *target_proc;
struct binder_thread *target_thread = NULL;
struct binder_node *target_node = NULL;
@@ -1361,6 +1453,7 @@
} else {
if (tr->target.handle) {
struct binder_ref *ref;
+
ref = binder_get_ref(proc, tr->target.handle);
if (ref == NULL) {
binder_user_error("%d:%d got transaction to invalid handle\n",
@@ -1382,8 +1475,13 @@
return_error = BR_DEAD_REPLY;
goto err_dead_binder;
}
+ if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) {
+ return_error = BR_FAILED_REPLY;
+ goto err_invalid_target_handle;
+ }
if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) {
struct binder_transaction *tmp;
+
tmp = thread->transaction_stack;
if (tmp->to_thread != thread) {
binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n",
@@ -1412,14 +1510,14 @@
e->to_proc = target_proc->pid;
/* TODO: reuse incoming transaction for reply */
- t = kzalloc(sizeof(*t), GFP_KERNEL);
+ t = kzalloc_preempt_disabled(sizeof(*t));
if (t == NULL) {
return_error = BR_FAILED_REPLY;
goto err_alloc_t_failed;
}
binder_stats_created(BINDER_STAT_TRANSACTION);
- tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL);
+ tcomplete = kzalloc_preempt_disabled(sizeof(*tcomplete));
if (tcomplete == NULL) {
return_error = BR_FAILED_REPLY;
goto err_alloc_tcomplete_failed;
@@ -1431,24 +1529,26 @@
if (reply)
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d:%d BC_REPLY %d -> %d:%d, data %p-%p size %zd-%zd\n",
+ "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld\n",
proc->pid, thread->pid, t->debug_id,
target_proc->pid, target_thread->pid,
- tr->data.ptr.buffer, tr->data.ptr.offsets,
- tr->data_size, tr->offsets_size);
+ (u64)tr->data.ptr.buffer,
+ (u64)tr->data.ptr.offsets,
+ (u64)tr->data_size, (u64)tr->offsets_size);
else
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d:%d BC_TRANSACTION %d -> %d - node %d, data %p-%p size %zd-%zd\n",
+ "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld\n",
proc->pid, thread->pid, t->debug_id,
target_proc->pid, target_node->debug_id,
- tr->data.ptr.buffer, tr->data.ptr.offsets,
- tr->data_size, tr->offsets_size);
+ (u64)tr->data.ptr.buffer,
+ (u64)tr->data.ptr.offsets,
+ (u64)tr->data_size, (u64)tr->offsets_size);
if (!reply && !(tr->flags & TF_ONE_WAY))
t->from = thread;
else
t->from = NULL;
- t->sender_euid = proc->tsk->cred->euid;
+ t->sender_euid = task_euid(proc->tsk);
t->to_proc = target_proc;
t->to_thread = target_thread;
t->code = tr->code;
@@ -1471,43 +1571,54 @@
if (target_node)
binder_inc_node(target_node, 1, 0, NULL);
- offp = (size_t *)(t->buffer->data + ALIGN(tr->data_size, sizeof(void *)));
+ offp = (binder_size_t *)(t->buffer->data +
+ ALIGN(tr->data_size, sizeof(void *)));
- if (copy_from_user(t->buffer->data, tr->data.ptr.buffer, tr->data_size)) {
+ if (copy_from_user_preempt_disabled(t->buffer->data, (const void __user *)(uintptr_t)
+ tr->data.ptr.buffer, tr->data_size)) {
binder_user_error("%d:%d got transaction with invalid data ptr\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
goto err_copy_data_failed;
}
- if (copy_from_user(offp, tr->data.ptr.offsets, tr->offsets_size)) {
+ if (copy_from_user_preempt_disabled(offp, (const void __user *)(uintptr_t)
+ tr->data.ptr.offsets, tr->offsets_size)) {
binder_user_error("%d:%d got transaction with invalid offsets ptr\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
goto err_copy_data_failed;
}
- if (!IS_ALIGNED(tr->offsets_size, sizeof(size_t))) {
- binder_user_error("%d:%d got transaction with invalid offsets size, %zd\n",
- proc->pid, thread->pid, tr->offsets_size);
+ if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) {
+ binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n",
+ proc->pid, thread->pid, (u64)tr->offsets_size);
return_error = BR_FAILED_REPLY;
goto err_bad_offset;
}
off_end = (void *)offp + tr->offsets_size;
+ off_min = 0;
for (; offp < off_end; offp++) {
struct flat_binder_object *fp;
+
if (*offp > t->buffer->data_size - sizeof(*fp) ||
+ *offp < off_min ||
t->buffer->data_size < sizeof(*fp) ||
- !IS_ALIGNED(*offp, sizeof(void *))) {
- binder_user_error("%d:%d got transaction with invalid offset, %zd\n",
- proc->pid, thread->pid, *offp);
+ !IS_ALIGNED(*offp, sizeof(u32))) {
+ binder_user_error("%d:%d got transaction with invalid offset, %lld (min %lld, max %lld)\n",
+ proc->pid, thread->pid, (u64)*offp,
+ (u64)off_min,
+ (u64)(t->buffer->data_size -
+ sizeof(*fp)));
return_error = BR_FAILED_REPLY;
goto err_bad_offset;
}
fp = (struct flat_binder_object *)(t->buffer->data + *offp);
+ off_min = *offp + sizeof(struct flat_binder_object);
switch (fp->type) {
case BINDER_TYPE_BINDER:
case BINDER_TYPE_WEAK_BINDER: {
struct binder_ref *ref;
struct binder_node *node = binder_get_node(proc, fp->binder);
+
if (node == NULL) {
node = binder_new_node(proc, fp->binder, fp->cookie);
if (node == NULL) {
@@ -1518,10 +1629,15 @@
node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS);
}
if (fp->cookie != node->cookie) {
- binder_user_error("%d:%d sending u%p node %d, cookie mismatch %p != %p\n",
+ binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n",
proc->pid, thread->pid,
- fp->binder, node->debug_id,
- fp->cookie, node->cookie);
+ (u64)fp->binder, node->debug_id,
+ (u64)fp->cookie, (u64)node->cookie);
+ return_error = BR_FAILED_REPLY;
+ goto err_binder_get_ref_for_node_failed;
+ }
+ if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+ return_error = BR_FAILED_REPLY;
goto err_binder_get_ref_for_node_failed;
}
ref = binder_get_ref_for_node(target_proc, node);
@@ -1539,20 +1655,25 @@
trace_binder_transaction_node_to_ref(t, node, ref);
binder_debug(BINDER_DEBUG_TRANSACTION,
- " node %d u%p -> ref %d desc %d\n",
- node->debug_id, node->ptr, ref->debug_id,
- ref->desc);
+ " node %d u%016llx -> ref %d desc %d\n",
+ node->debug_id, (u64)node->ptr,
+ ref->debug_id, ref->desc);
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+
if (ref == NULL) {
- binder_user_error("%d:%d got transaction with invalid handle, %ld\n",
+ binder_user_error("%d:%d got transaction with invalid handle, %d\n",
proc->pid,
thread->pid, fp->handle);
return_error = BR_FAILED_REPLY;
goto err_binder_get_ref_failed;
}
+ if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+ return_error = BR_FAILED_REPLY;
+ goto err_binder_get_ref_failed;
+ }
if (ref->node->proc == target_proc) {
if (fp->type == BINDER_TYPE_HANDLE)
fp->type = BINDER_TYPE_BINDER;
@@ -1563,11 +1684,12 @@
binder_inc_node(ref->node, fp->type == BINDER_TYPE_BINDER, 0, NULL);
trace_binder_transaction_ref_to_node(t, ref);
binder_debug(BINDER_DEBUG_TRANSACTION,
- " ref %d desc %d -> node %d u%p\n",
+ " ref %d desc %d -> node %d u%016llx\n",
ref->debug_id, ref->desc, ref->node->debug_id,
- ref->node->ptr);
+ (u64)ref->node->ptr);
} else {
struct binder_ref *new_ref;
+
new_ref = binder_get_ref_for_node(target_proc, ref->node);
if (new_ref == NULL) {
return_error = BR_FAILED_REPLY;
@@ -1590,13 +1712,13 @@
if (reply) {
if (!(in_reply_to->flags & TF_ACCEPT_FDS)) {
- binder_user_error("%d:%d got reply with fd, %ld, but target does not allow fds\n",
+ binder_user_error("%d:%d got reply with fd, %d, but target does not allow fds\n",
proc->pid, thread->pid, fp->handle);
return_error = BR_FAILED_REPLY;
goto err_fd_not_allowed;
}
} else if (!target_node->accept_fds) {
- binder_user_error("%d:%d got transaction with fd, %ld, but target does not allow fds\n",
+ binder_user_error("%d:%d got transaction with fd, %d, but target does not allow fds\n",
proc->pid, thread->pid, fp->handle);
return_error = BR_FAILED_REPLY;
goto err_fd_not_allowed;
@@ -1604,11 +1726,16 @@
file = fget(fp->handle);
if (file == NULL) {
- binder_user_error("%d:%d got transaction with invalid fd, %ld\n",
+ binder_user_error("%d:%d got transaction with invalid fd, %d\n",
proc->pid, thread->pid, fp->handle);
return_error = BR_FAILED_REPLY;
goto err_fget_failed;
}
+ if (security_binder_transfer_file(proc->tsk, target_proc->tsk, file) < 0) {
+ fput(file);
+ return_error = BR_FAILED_REPLY;
+ goto err_get_unused_fd_failed;
+ }
target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
if (target_fd < 0) {
fput(file);
@@ -1618,13 +1745,13 @@
task_fd_install(target_proc, target_fd, file);
trace_binder_transaction_fd(t, fp->handle, target_fd);
binder_debug(BINDER_DEBUG_TRANSACTION,
- " fd %ld -> %d\n", fp->handle, target_fd);
+ " fd %d -> %d\n", fp->handle, target_fd);
/* TODO: fput? */
fp->handle = target_fd;
} break;
default:
- binder_user_error("%d:%d got transaction with invalid object type, %lx\n",
+ binder_user_error("%d:%d got transaction with invalid object type, %x\n",
proc->pid, thread->pid, fp->type);
return_error = BR_FAILED_REPLY;
goto err_bad_object_type;
@@ -1651,8 +1778,13 @@
list_add_tail(&t->work.entry, target_list);
tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
list_add_tail(&tcomplete->entry, &thread->todo);
- if (target_wait)
- wake_up_interruptible(target_wait);
+ if (target_wait) {
+ if (reply || !(t->flags & TF_ONE_WAY)) {
+ wake_up_interruptible_sync(target_wait);
+ } else {
+ wake_up_interruptible(target_wait);
+ }
+ }
return;
err_get_unused_fd_failed:
@@ -1681,12 +1813,13 @@
err_invalid_target_handle:
err_no_context_mgr_node:
binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
- "%d:%d transaction failed %d, size %zd-%zd\n",
+ "%d:%d transaction failed %d, size %lld-%lld\n",
proc->pid, thread->pid, return_error,
- tr->data_size, tr->offsets_size);
+ (u64)tr->data_size, (u64)tr->offsets_size);
{
struct binder_transaction_log_entry *fe;
+
fe = binder_transaction_log_add(&binder_transaction_log_failed);
*fe = *e;
}
@@ -1699,15 +1832,18 @@
thread->return_error = return_error;
}
-int binder_thread_write(struct binder_proc *proc, struct binder_thread *thread,
- void __user *buffer, int size, signed long *consumed)
+static int binder_thread_write(struct binder_proc *proc,
+ struct binder_thread *thread,
+ binder_uintptr_t binder_buffer, size_t size,
+ binder_size_t *consumed)
{
uint32_t cmd;
+ void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
void __user *ptr = buffer + *consumed;
void __user *end = buffer + size;
while (ptr < end && thread->return_error == BR_OK) {
- if (get_user(cmd, (uint32_t __user *)ptr))
+ if (get_user_preempt_disabled(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
trace_binder_command(cmd);
@@ -1725,7 +1861,7 @@
struct binder_ref *ref;
const char *debug_string;
- if (get_user(target, (uint32_t __user *)ptr))
+ if (get_user_preempt_disabled(target, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
if (target == 0 && binder_context_mgr_node &&
@@ -1771,33 +1907,33 @@
}
case BC_INCREFS_DONE:
case BC_ACQUIRE_DONE: {
- void __user *node_ptr;
- void *cookie;
+ binder_uintptr_t node_ptr;
+ binder_uintptr_t cookie;
struct binder_node *node;
- if (get_user(node_ptr, (void * __user *)ptr))
+ if (get_user_preempt_disabled(node_ptr, (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
- if (get_user(cookie, (void * __user *)ptr))
+ ptr += sizeof(binder_uintptr_t);
+ if (get_user_preempt_disabled(cookie, (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
+ ptr += sizeof(binder_uintptr_t);
node = binder_get_node(proc, node_ptr);
if (node == NULL) {
- binder_user_error("%d:%d %s u%p no match\n",
+ binder_user_error("%d:%d %s u%016llx no match\n",
proc->pid, thread->pid,
cmd == BC_INCREFS_DONE ?
"BC_INCREFS_DONE" :
"BC_ACQUIRE_DONE",
- node_ptr);
+ (u64)node_ptr);
break;
}
if (cookie != node->cookie) {
- binder_user_error("%d:%d %s u%p node %d cookie mismatch %p != %p\n",
+ binder_user_error("%d:%d %s u%016llx node %d cookie mismatch %016llx != %016llx\n",
proc->pid, thread->pid,
cmd == BC_INCREFS_DONE ?
"BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
- node_ptr, node->debug_id,
- cookie, node->cookie);
+ (u64)node_ptr, node->debug_id,
+ (u64)cookie, (u64)node->cookie);
break;
}
if (cmd == BC_ACQUIRE_DONE) {
@@ -1833,27 +1969,28 @@
return -EINVAL;
case BC_FREE_BUFFER: {
- void __user *data_ptr;
+ binder_uintptr_t data_ptr;
struct binder_buffer *buffer;
- if (get_user(data_ptr, (void * __user *)ptr))
+ if (get_user_preempt_disabled(data_ptr, (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
+ ptr += sizeof(binder_uintptr_t);
buffer = binder_buffer_lookup(proc, data_ptr);
if (buffer == NULL) {
- binder_user_error("%d:%d BC_FREE_BUFFER u%p no match\n",
- proc->pid, thread->pid, data_ptr);
+ binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n",
+ proc->pid, thread->pid, (u64)data_ptr);
break;
}
if (!buffer->allow_user_free) {
- binder_user_error("%d:%d BC_FREE_BUFFER u%p matched unreturned buffer\n",
- proc->pid, thread->pid, data_ptr);
+ binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n",
+ proc->pid, thread->pid, (u64)data_ptr);
break;
}
binder_debug(BINDER_DEBUG_FREE_BUFFER,
- "%d:%d BC_FREE_BUFFER u%p found buffer %d for %s transaction\n",
- proc->pid, thread->pid, data_ptr, buffer->debug_id,
+ "%d:%d BC_FREE_BUFFER u%016llx found buffer %d for %s transaction\n",
+ proc->pid, thread->pid, (u64)data_ptr,
+ buffer->debug_id,
buffer->transaction ? "active" : "finished");
if (buffer->transaction) {
@@ -1877,7 +2014,7 @@
case BC_REPLY: {
struct binder_transaction_data tr;
- if (copy_from_user(&tr, ptr, sizeof(tr)))
+ if (copy_from_user_preempt_disabled(&tr, ptr, sizeof(tr)))
return -EFAULT;
ptr += sizeof(tr);
binder_transaction(proc, thread, &tr, cmd == BC_REPLY);
@@ -1923,16 +2060,16 @@
case BC_REQUEST_DEATH_NOTIFICATION:
case BC_CLEAR_DEATH_NOTIFICATION: {
uint32_t target;
- void __user *cookie;
+ binder_uintptr_t cookie;
struct binder_ref *ref;
struct binder_ref_death *death;
- if (get_user(target, (uint32_t __user *)ptr))
+ if (get_user_preempt_disabled(target, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
- if (get_user(cookie, (void __user * __user *)ptr))
+ if (get_user_preempt_disabled(cookie, (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
+ ptr += sizeof(binder_uintptr_t);
ref = binder_get_ref(proc, target);
if (ref == NULL) {
binder_user_error("%d:%d %s invalid ref %d\n",
@@ -1945,12 +2082,12 @@
}
binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
- "%d:%d %s %p ref %d desc %d s %d w %d for node %d\n",
+ "%d:%d %s %016llx ref %d desc %d s %d w %d for node %d\n",
proc->pid, thread->pid,
cmd == BC_REQUEST_DEATH_NOTIFICATION ?
"BC_REQUEST_DEATH_NOTIFICATION" :
"BC_CLEAR_DEATH_NOTIFICATION",
- cookie, ref->debug_id, ref->desc,
+ (u64)cookie, ref->debug_id, ref->desc,
ref->strong, ref->weak, ref->node->debug_id);
if (cmd == BC_REQUEST_DEATH_NOTIFICATION) {
@@ -1959,7 +2096,7 @@
proc->pid, thread->pid);
break;
}
- death = kzalloc(sizeof(*death), GFP_KERNEL);
+ death = kzalloc_preempt_disabled(sizeof(*death));
if (death == NULL) {
thread->return_error = BR_ERROR;
binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
@@ -1988,9 +2125,10 @@
}
death = ref->death;
if (death->cookie != cookie) {
- binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch %p != %p\n",
+ binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch %016llx != %016llx\n",
proc->pid, thread->pid,
- death->cookie, cookie);
+ (u64)death->cookie,
+ (u64)cookie);
break;
}
ref->death = NULL;
@@ -2010,25 +2148,28 @@
} break;
case BC_DEAD_BINDER_DONE: {
struct binder_work *w;
- void __user *cookie;
+ binder_uintptr_t cookie;
struct binder_ref_death *death = NULL;
- if (get_user(cookie, (void __user * __user *)ptr))
+
+ if (get_user_preempt_disabled(cookie, (binder_uintptr_t __user *)ptr))
return -EFAULT;
ptr += sizeof(void *);
list_for_each_entry(w, &proc->delivered_death, entry) {
struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
+
if (tmp_death->cookie == cookie) {
death = tmp_death;
break;
}
}
binder_debug(BINDER_DEBUG_DEAD_BINDER,
- "%d:%d BC_DEAD_BINDER_DONE %p found %p\n",
- proc->pid, thread->pid, cookie, death);
+ "%d:%d BC_DEAD_BINDER_DONE %016llx found %p\n",
+ proc->pid, thread->pid, (u64)cookie,
+ death);
if (death == NULL) {
- binder_user_error("%d:%d BC_DEAD_BINDER_DONE %p not found\n",
- proc->pid, thread->pid, cookie);
+ binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n",
+ proc->pid, thread->pid, (u64)cookie);
break;
}
@@ -2054,8 +2195,8 @@
return 0;
}
-void binder_stat_br(struct binder_proc *proc, struct binder_thread *thread,
- uint32_t cmd)
+static void binder_stat_br(struct binder_proc *proc,
+ struct binder_thread *thread, uint32_t cmd)
{
trace_binder_return(cmd);
if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) {
@@ -2080,9 +2221,10 @@
static int binder_thread_read(struct binder_proc *proc,
struct binder_thread *thread,
- void __user *buffer, int size,
- signed long *consumed, int non_block)
+ binder_uintptr_t binder_buffer, size_t size,
+ binder_size_t *consumed, int non_block)
{
+ void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
void __user *ptr = buffer + *consumed;
void __user *end = buffer + size;
@@ -2090,7 +2232,7 @@
int wait_for_proc_work;
if (*consumed == 0) {
- if (put_user(BR_NOOP, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(BR_NOOP, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
}
@@ -2101,7 +2243,7 @@
if (thread->return_error != BR_OK && ptr < end) {
if (thread->return_error2 != BR_OK) {
- if (put_user(thread->return_error2, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(thread->return_error2, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
binder_stat_br(proc, thread, thread->return_error2);
@@ -2109,7 +2251,7 @@
goto done;
thread->return_error2 = BR_OK;
}
- if (put_user(thread->return_error, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(thread->return_error, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
binder_stat_br(proc, thread, thread->return_error);
@@ -2140,13 +2282,13 @@
if (!binder_has_proc_work(proc, thread))
ret = -EAGAIN;
} else
- ret = wait_event_interruptible_exclusive(proc->wait, binder_has_proc_work(proc, thread));
+ ret = wait_event_freezable_exclusive(proc->wait, binder_has_proc_work(proc, thread));
} else {
if (non_block) {
if (!binder_has_thread_work(thread))
ret = -EAGAIN;
} else
- ret = wait_event_interruptible(thread->wait, binder_has_thread_work(thread));
+ ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread));
}
binder_lock(__func__);
@@ -2164,12 +2306,16 @@
struct binder_work *w;
struct binder_transaction *t = NULL;
- if (!list_empty(&thread->todo))
- w = list_first_entry(&thread->todo, struct binder_work, entry);
- else if (!list_empty(&proc->todo) && wait_for_proc_work)
- w = list_first_entry(&proc->todo, struct binder_work, entry);
- else {
- if (ptr - buffer == 4 && !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN)) /* no data added */
+ if (!list_empty(&thread->todo)) {
+ w = list_first_entry(&thread->todo, struct binder_work,
+ entry);
+ } else if (!list_empty(&proc->todo) && wait_for_proc_work) {
+ w = list_first_entry(&proc->todo, struct binder_work,
+ entry);
+ } else {
+ /* no data added */
+ if (ptr - buffer == 4 &&
+ !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN))
goto retry;
break;
}
@@ -2183,7 +2329,7 @@
} break;
case BINDER_WORK_TRANSACTION_COMPLETE: {
cmd = BR_TRANSACTION_COMPLETE;
- if (put_user(cmd, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
@@ -2202,6 +2348,7 @@
const char *cmd_name;
int strong = node->internal_strong_refs || node->local_strong_refs;
int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong;
+
if (weak && !node->has_weak_ref) {
cmd = BR_INCREFS;
cmd_name = "BR_INCREFS";
@@ -2224,35 +2371,43 @@
node->has_weak_ref = 0;
}
if (cmd != BR_NOOP) {
- if (put_user(cmd, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
- if (put_user(node->ptr, (void * __user *)ptr))
+ if (put_user_preempt_disabled(node->ptr,
+ (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
- if (put_user(node->cookie, (void * __user *)ptr))
+ ptr += sizeof(binder_uintptr_t);
+ if (put_user_preempt_disabled(node->cookie,
+ (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
+ ptr += sizeof(binder_uintptr_t);
binder_stat_br(proc, thread, cmd);
binder_debug(BINDER_DEBUG_USER_REFS,
- "%d:%d %s %d u%p c%p\n",
- proc->pid, thread->pid, cmd_name, node->debug_id, node->ptr, node->cookie);
+ "%d:%d %s %d u%016llx c%016llx\n",
+ proc->pid, thread->pid, cmd_name,
+ node->debug_id,
+ (u64)node->ptr, (u64)node->cookie);
} else {
list_del_init(&w->entry);
if (!weak && !strong) {
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d:%d node %d u%p c%p deleted\n",
- proc->pid, thread->pid, node->debug_id,
- node->ptr, node->cookie);
+ "%d:%d node %d u%016llx c%016llx deleted\n",
+ proc->pid, thread->pid,
+ node->debug_id,
+ (u64)node->ptr,
+ (u64)node->cookie);
rb_erase(&node->rb_node, &proc->nodes);
kfree(node);
binder_stats_deleted(BINDER_STAT_NODE);
} else {
binder_debug(BINDER_DEBUG_INTERNAL_REFS,
- "%d:%d node %d u%p c%p state unchanged\n",
- proc->pid, thread->pid, node->debug_id, node->ptr,
- node->cookie);
+ "%d:%d node %d u%016llx c%016llx state unchanged\n",
+ proc->pid, thread->pid,
+ node->debug_id,
+ (u64)node->ptr,
+ (u64)node->cookie);
}
}
} break;
@@ -2267,20 +2422,21 @@
cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE;
else
cmd = BR_DEAD_BINDER;
- if (put_user(cmd, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
- if (put_user(death->cookie, (void * __user *)ptr))
+ if (put_user_preempt_disabled(death->cookie,
+ (binder_uintptr_t __user *)ptr))
return -EFAULT;
- ptr += sizeof(void *);
+ ptr += sizeof(binder_uintptr_t);
binder_stat_br(proc, thread, cmd);
binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
- "%d:%d %s %p\n",
+ "%d:%d %s %016llx\n",
proc->pid, thread->pid,
cmd == BR_DEAD_BINDER ?
"BR_DEAD_BINDER" :
"BR_CLEAR_DEATH_NOTIFICATION_DONE",
- death->cookie);
+ (u64)death->cookie);
if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) {
list_del(&w->entry);
@@ -2299,6 +2455,7 @@
BUG_ON(t->buffer == NULL);
if (t->buffer->target_node) {
struct binder_node *target_node = t->buffer->target_node;
+
tr.target.ptr = target_node->ptr;
tr.cookie = target_node->cookie;
t->saved_priority = task_nice(current);
@@ -2310,8 +2467,8 @@
binder_set_nice(target_node->min_priority);
cmd = BR_TRANSACTION;
} else {
- tr.target.ptr = NULL;
- tr.cookie = NULL;
+ tr.target.ptr = 0;
+ tr.cookie = 0;
cmd = BR_REPLY;
}
tr.code = t->code;
@@ -2320,6 +2477,7 @@
if (t->from) {
struct task_struct *sender = t->from->proc->tsk;
+
tr.sender_pid = task_tgid_nr_ns(sender,
task_active_pid_ns(current));
} else {
@@ -2328,30 +2486,31 @@
tr.data_size = t->buffer->data_size;
tr.offsets_size = t->buffer->offsets_size;
- tr.data.ptr.buffer = (void *)t->buffer->data +
- proc->user_buffer_offset;
+ tr.data.ptr.buffer = (binder_uintptr_t)(
+ (uintptr_t)t->buffer->data +
+ proc->user_buffer_offset);
tr.data.ptr.offsets = tr.data.ptr.buffer +
ALIGN(t->buffer->data_size,
sizeof(void *));
- if (put_user(cmd, (uint32_t __user *)ptr))
+ if (put_user_preempt_disabled(cmd, (uint32_t __user *)ptr))
return -EFAULT;
ptr += sizeof(uint32_t);
- if (copy_to_user(ptr, &tr, sizeof(tr)))
+ if (copy_to_user_preempt_disabled(ptr, &tr, sizeof(tr)))
return -EFAULT;
ptr += sizeof(tr);
trace_binder_transaction_received(t);
binder_stat_br(proc, thread, cmd);
binder_debug(BINDER_DEBUG_TRANSACTION,
- "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %p-%p\n",
+ "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n",
proc->pid, thread->pid,
(cmd == BR_TRANSACTION) ? "BR_TRANSACTION" :
"BR_REPLY",
t->debug_id, t->from ? t->from->proc->pid : 0,
t->from ? t->from->pid : 0, cmd,
t->buffer->data_size, t->buffer->offsets_size,
- tr.data.ptr.buffer, tr.data.ptr.offsets);
+ (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets);
list_del(&t->work.entry);
t->buffer->allow_user_free = 1;
@@ -2379,7 +2538,7 @@
binder_debug(BINDER_DEBUG_THREADS,
"%d:%d BR_SPAWN_LOOPER\n",
proc->pid, thread->pid);
- if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer))
+ if (put_user_preempt_disabled(BR_SPAWN_LOOPER, (uint32_t __user *)buffer))
return -EFAULT;
binder_stat_br(proc, thread, BR_SPAWN_LOOPER);
}
@@ -2389,6 +2548,7 @@
static void binder_release_work(struct list_head *list)
{
struct binder_work *w;
+
while (!list_empty(list)) {
w = list_first_entry(list, struct binder_work, entry);
list_del_init(&w->entry);
@@ -2421,8 +2581,8 @@
death = container_of(w, struct binder_ref_death, work);
binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
- "undelivered death notification, %p\n",
- death->cookie);
+ "undelivered death notification, %016llx\n",
+ (u64)death->cookie);
kfree(death);
binder_stats_deleted(BINDER_STAT_DEATH);
} break;
@@ -2453,7 +2613,7 @@
break;
}
if (*p == NULL) {
- thread = kzalloc(sizeof(*thread), GFP_KERNEL);
+ thread = kzalloc_preempt_disabled(sizeof(*thread));
if (thread == NULL)
return NULL;
binder_stats_created(BINDER_STAT_THREAD);
@@ -2543,6 +2703,109 @@
return 0;
}
+static int binder_ioctl_write_read(struct file *filp,
+ unsigned int cmd, unsigned long arg,
+ struct binder_thread *thread)
+{
+ int ret = 0;
+ struct binder_proc *proc = filp->private_data;
+ unsigned int size = _IOC_SIZE(cmd);
+ void __user *ubuf = (void __user *)arg;
+ struct binder_write_read bwr;
+
+ if (size != sizeof(struct binder_write_read)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (copy_from_user_preempt_disabled(&bwr, ubuf, sizeof(bwr))) {
+ ret = -EFAULT;
+ goto out;
+ }
+ binder_debug(BINDER_DEBUG_READ_WRITE,
+ "%d:%d write %lld at %016llx, read %lld at %016llx\n",
+ proc->pid, thread->pid,
+ (u64)bwr.write_size, (u64)bwr.write_buffer,
+ (u64)bwr.read_size, (u64)bwr.read_buffer);
+
+ if (bwr.write_size > 0) {
+ ret = binder_thread_write(proc, thread,
+ bwr.write_buffer,
+ bwr.write_size,
+ &bwr.write_consumed);
+ trace_binder_write_done(ret);
+ if (ret < 0) {
+ bwr.read_consumed = 0;
+ if (copy_to_user_preempt_disabled(ubuf, &bwr, sizeof(bwr)))
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+ if (bwr.read_size > 0) {
+ ret = binder_thread_read(proc, thread, bwr.read_buffer,
+ bwr.read_size,
+ &bwr.read_consumed,
+ filp->f_flags & O_NONBLOCK);
+ trace_binder_read_done(ret);
+ if (!list_empty(&proc->todo))
+ wake_up_interruptible(&proc->wait);
+ if (ret < 0) {
+ if (copy_to_user_preempt_disabled(ubuf, &bwr, sizeof(bwr)))
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+ binder_debug(BINDER_DEBUG_READ_WRITE,
+ "%d:%d wrote %lld of %lld, read return %lld of %lld\n",
+ proc->pid, thread->pid,
+ (u64)bwr.write_consumed, (u64)bwr.write_size,
+ (u64)bwr.read_consumed, (u64)bwr.read_size);
+ if (copy_to_user_preempt_disabled(ubuf, &bwr, sizeof(bwr))) {
+ ret = -EFAULT;
+ goto out;
+ }
+out:
+ return ret;
+}
+
+static int binder_ioctl_set_ctx_mgr(struct file *filp)
+{
+ int ret = 0;
+ struct binder_proc *proc = filp->private_data;
+ kuid_t curr_euid = current_euid();
+
+ if (binder_context_mgr_node != NULL) {
+ pr_err("BINDER_SET_CONTEXT_MGR already set\n");
+ ret = -EBUSY;
+ goto out;
+ }
+ ret = security_binder_set_context_mgr(proc->tsk);
+ if (ret < 0)
+ goto out;
+ if (uid_valid(binder_context_mgr_uid)) {
+ if (!uid_eq(binder_context_mgr_uid, curr_euid)) {
+ pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
+ from_kuid(&init_user_ns, curr_euid),
+ from_kuid(&init_user_ns,
+ binder_context_mgr_uid));
+ ret = -EPERM;
+ goto out;
+ }
+ } else {
+ binder_context_mgr_uid = curr_euid;
+ }
+ binder_context_mgr_node = binder_new_node(proc, 0, 0);
+ if (binder_context_mgr_node == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ binder_context_mgr_node->local_weak_refs++;
+ binder_context_mgr_node->local_strong_refs++;
+ binder_context_mgr_node->has_strong_ref = 1;
+ binder_context_mgr_node->has_weak_ref = 1;
+out:
+ return ret;
+}
+
static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
int ret;
@@ -2551,7 +2814,8 @@
unsigned int size = _IOC_SIZE(cmd);
void __user *ubuf = (void __user *)arg;
- /*pr_info("binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/
+ /*pr_info("binder_ioctl: %d:%d %x %lx\n",
+ proc->pid, current->pid, cmd, arg);*/
trace_binder_ioctl(cmd, arg);
@@ -2567,83 +2831,21 @@
}
switch (cmd) {
- case BINDER_WRITE_READ: {
- struct binder_write_read bwr;
- if (size != sizeof(struct binder_write_read)) {
- ret = -EINVAL;
+ case BINDER_WRITE_READ:
+ ret = binder_ioctl_write_read(filp, cmd, arg, thread);
+ if (ret)
goto err;
- }
- if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
- binder_debug(BINDER_DEBUG_READ_WRITE,
- "%d:%d write %ld at %08lx, read %ld at %08lx\n",
- proc->pid, thread->pid, bwr.write_size,
- bwr.write_buffer, bwr.read_size, bwr.read_buffer);
-
- if (bwr.write_size > 0) {
- ret = binder_thread_write(proc, thread, (void __user *)bwr.write_buffer, bwr.write_size, &bwr.write_consumed);
- trace_binder_write_done(ret);
- if (ret < 0) {
- bwr.read_consumed = 0;
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- if (bwr.read_size > 0) {
- ret = binder_thread_read(proc, thread, (void __user *)bwr.read_buffer, bwr.read_size, &bwr.read_consumed, filp->f_flags & O_NONBLOCK);
- trace_binder_read_done(ret);
- if (!list_empty(&proc->todo))
- wake_up_interruptible(&proc->wait);
- if (ret < 0) {
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- binder_debug(BINDER_DEBUG_READ_WRITE,
- "%d:%d wrote %ld of %ld, read return %ld of %ld\n",
- proc->pid, thread->pid, bwr.write_consumed, bwr.write_size,
- bwr.read_consumed, bwr.read_size);
- if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
break;
- }
case BINDER_SET_MAX_THREADS:
- if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
+ if (copy_from_user_preempt_disabled(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
ret = -EINVAL;
goto err;
}
break;
case BINDER_SET_CONTEXT_MGR:
- if (binder_context_mgr_node != NULL) {
- pr_err("BINDER_SET_CONTEXT_MGR already set\n");
- ret = -EBUSY;
+ ret = binder_ioctl_set_ctx_mgr(filp);
+ if (ret)
goto err;
- }
- if (uid_valid(binder_context_mgr_uid)) {
- if (!uid_eq(binder_context_mgr_uid, current->cred->euid)) {
- pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
- from_kuid(&init_user_ns, current->cred->euid),
- from_kuid(&init_user_ns, binder_context_mgr_uid));
- ret = -EPERM;
- goto err;
- }
- } else
- binder_context_mgr_uid = current->cred->euid;
- binder_context_mgr_node = binder_new_node(proc, NULL, NULL);
- if (binder_context_mgr_node == NULL) {
- ret = -ENOMEM;
- goto err;
- }
- binder_context_mgr_node->local_weak_refs++;
- binder_context_mgr_node->local_strong_refs++;
- binder_context_mgr_node->has_strong_ref = 1;
- binder_context_mgr_node->has_weak_ref = 1;
break;
case BINDER_THREAD_EXIT:
binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
@@ -2651,16 +2853,21 @@
binder_free_thread(proc, thread);
thread = NULL;
break;
- case BINDER_VERSION:
+ case BINDER_VERSION: {
+ struct binder_version __user *ver = ubuf;
+
if (size != sizeof(struct binder_version)) {
ret = -EINVAL;
goto err;
}
- if (put_user(BINDER_CURRENT_PROTOCOL_VERSION, &((struct binder_version *)ubuf)->protocol_version)) {
+
+ if (put_user_preempt_disabled(BINDER_CURRENT_PROTOCOL_VERSION,
+ &ver->protocol_version)) {
ret = -EINVAL;
goto err;
}
break;
+ }
default:
ret = -EINVAL;
goto err;
@@ -2681,6 +2888,7 @@
static void binder_vma_open(struct vm_area_struct *vma)
{
struct binder_proc *proc = vma->vm_private_data;
+
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
"%d open vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
proc->pid, vma->vm_start, vma->vm_end,
@@ -2691,6 +2899,7 @@
static void binder_vma_close(struct vm_area_struct *vma)
{
struct binder_proc *proc = vma->vm_private_data;
+
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
"%d close vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
proc->pid, vma->vm_start, vma->vm_end,
@@ -2701,14 +2910,21 @@
binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
}
+static int binder_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ return VM_FAULT_SIGBUS;
+}
+
static struct vm_operations_struct binder_vm_ops = {
.open = binder_vma_open,
.close = binder_vma_close,
+ .fault = binder_vm_fault,
};
static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
{
int ret;
+
struct vm_struct *area;
struct binder_proc *proc = filp->private_data;
const char *failure_string;
@@ -2769,7 +2985,11 @@
vma->vm_ops = &binder_vm_ops;
vma->vm_private_data = proc;
- if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) {
+ /* binder_update_page_range assumes preemption is disabled */
+ preempt_disable();
+ ret = binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma);
+ preempt_enable_no_resched();
+ if (ret) {
ret = -ENOMEM;
failure_string = "alloc small buf";
goto err_alloc_small_buf_failed;
@@ -2833,6 +3053,7 @@
if (binder_debugfs_dir_entry_proc) {
char strbuf[11];
+
snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
binder_debugfs_dir_entry_proc, proc, &binder_proc_fops);
@@ -2854,8 +3075,10 @@
{
struct rb_node *n;
int wake_count = 0;
+
for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) {
struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node);
+
thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
if (thread->looper & BINDER_LOOPER_STATE_WAITING) {
wake_up_interruptible(&thread->wait);
@@ -2872,6 +3095,7 @@
static int binder_release(struct inode *nodp, struct file *filp)
{
struct binder_proc *proc = filp->private_data;
+
debugfs_remove(proc->debugfs_entry);
binder_defer_work(proc, BINDER_DEFERRED_RELEASE);
@@ -3033,9 +3257,14 @@
struct files_struct *files;
int defer;
+
do {
- binder_lock(__func__);
+ trace_binder_lock(__func__);
+ mutex_lock(&binder_main_lock);
+ trace_binder_locked(__func__);
+
mutex_lock(&binder_deferred_lock);
+ preempt_disable();
if (!hlist_empty(&binder_deferred_list)) {
proc = hlist_entry(binder_deferred_list.first,
struct binder_proc, deferred_work_node);
@@ -3061,7 +3290,9 @@
if (defer & BINDER_DEFERRED_RELEASE)
binder_deferred_release(proc); /* frees proc */
- binder_unlock(__func__);
+ trace_binder_unlock(__func__);
+ mutex_unlock(&binder_main_lock);
+ preempt_enable_no_resched();
if (files)
put_files_struct(files);
} while (proc);
@@ -3130,8 +3361,9 @@
break;
case BINDER_WORK_NODE:
node = container_of(w, struct binder_node, work);
- seq_printf(m, "%snode work %d: u%p c%p\n",
- prefix, node->debug_id, node->ptr, node->cookie);
+ seq_printf(m, "%snode work %d: u%016llx c%016llx\n",
+ prefix, node->debug_id,
+ (u64)node->ptr, (u64)node->cookie);
break;
case BINDER_WORK_DEAD_BINDER:
seq_printf(m, "%shas dead binder\n", prefix);
@@ -3191,8 +3423,8 @@
hlist_for_each_entry(ref, &node->refs, node_entry)
count++;
- seq_printf(m, " node %d: u%p c%p hs %d hw %d ls %d lw %d is %d iw %d",
- node->debug_id, node->ptr, node->cookie,
+ seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d",
+ node->debug_id, (u64)node->ptr, (u64)node->cookie,
node->has_strong_ref, node->has_weak_ref,
node->local_strong_refs, node->local_weak_refs,
node->internal_strong_refs, count);
@@ -3453,13 +3685,24 @@
static int binder_proc_show(struct seq_file *m, void *unused)
{
+ struct binder_proc *itr;
struct binder_proc *proc = m->private;
int do_lock = !binder_debug_no_lock;
+ bool valid_proc = false;
if (do_lock)
binder_lock(__func__);
- seq_puts(m, "binder proc state:\n");
- print_binder_proc(m, proc, 1);
+
+ hlist_for_each_entry(itr, &binder_procs, proc_node) {
+ if (itr == proc) {
+ valid_proc = true;
+ break;
+ }
+ }
+ if (valid_proc) {
+ seq_puts(m, "binder proc state:\n");
+ print_binder_proc(m, proc, 1);
+ }
if (do_lock)
binder_unlock(__func__);
return 0;
@@ -3494,6 +3737,7 @@
.owner = THIS_MODULE,
.poll = binder_poll,
.unlocked_ioctl = binder_ioctl,
+ .compat_ioctl = binder_ioctl,
.mmap = binder_mmap,
.open = binder_open,
.flush = binder_flush,
diff --git a/drivers/staging/android/binder_trace.h b/drivers/android/binder_trace.h
similarity index 96%
rename from drivers/staging/android/binder_trace.h
rename to drivers/android/binder_trace.h
index 82a567c..7f20f3d 100644
--- a/drivers/staging/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -152,7 +152,7 @@
TP_STRUCT__entry(
__field(int, debug_id)
__field(int, node_debug_id)
- __field(void __user *, node_ptr)
+ __field(binder_uintptr_t, node_ptr)
__field(int, ref_debug_id)
__field(uint32_t, ref_desc)
),
@@ -163,8 +163,9 @@
__entry->ref_debug_id = ref->debug_id;
__entry->ref_desc = ref->desc;
),
- TP_printk("transaction=%d node=%d src_ptr=0x%p ==> dest_ref=%d dest_desc=%d",
- __entry->debug_id, __entry->node_debug_id, __entry->node_ptr,
+ TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d",
+ __entry->debug_id, __entry->node_debug_id,
+ (u64)__entry->node_ptr,
__entry->ref_debug_id, __entry->ref_desc)
);
@@ -177,7 +178,7 @@
__field(int, ref_debug_id)
__field(uint32_t, ref_desc)
__field(int, node_debug_id)
- __field(void __user *, node_ptr)
+ __field(binder_uintptr_t, node_ptr)
),
TP_fast_assign(
__entry->debug_id = t->debug_id;
@@ -186,9 +187,10 @@
__entry->node_debug_id = ref->node->debug_id;
__entry->node_ptr = ref->node->ptr;
),
- TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%p",
+ TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx",
__entry->debug_id, __entry->node_debug_id,
- __entry->ref_debug_id, __entry->ref_desc, __entry->node_ptr)
+ __entry->ref_debug_id, __entry->ref_desc,
+ (u64)__entry->node_ptr)
);
TRACE_EVENT(binder_transaction_ref_to_ref,
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 07abd9d..9634800 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -187,6 +187,14 @@
bool
default n
+config HAVE_CPU_AUTOPROBE
+ def_bool ARCH_HAS_CPU_AUTOPROBE
+
+config GENERIC_CPU_AUTOPROBE
+ bool
+ depends on !ARCH_HAS_CPU_AUTOPROBE
+ select HAVE_CPU_AUTOPROBE
+
config SOC_BUS
bool
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 3d48fc8..b566850 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -13,6 +13,7 @@
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/percpu.h>
+#include <linux/cpufeature.h>
#include "base.h"
@@ -260,6 +261,45 @@
*/
}
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+static ssize_t print_cpu_modalias(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ ssize_t n;
+ u32 i;
+
+ n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
+ CPU_FEATURE_TYPEVAL);
+
+ for (i = 0; i < MAX_CPU_FEATURES; i++)
+ if (cpu_have_feature(i)) {
+ if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
+ WARN(1, "CPU features overflow page\n");
+ break;
+ }
+ n += sprintf(&buf[n], ",%04X", i);
+ }
+ buf[n++] = '\n';
+ return n;
+}
+#else
+#define print_cpu_modalias arch_print_cpu_modalias
+#endif
+
+static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ if (buf) {
+ print_cpu_modalias(NULL, NULL, buf);
+ add_uevent_var(env, "MODALIAS=%s", buf);
+ kfree(buf);
+ }
+ return 0;
+}
+#endif
+
/*
* register_cpu - Setup a sysfs device for a CPU.
* @cpu - cpu->hotpluggable field set to 1 will generate a control file in
@@ -278,7 +318,7 @@
cpu->dev.bus = &cpu_subsys;
cpu->dev.release = cpu_device_release;
#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
- cpu->dev.bus->uevent = arch_cpu_uevent;
+ cpu->dev.bus->uevent = cpu_uevent;
#endif
error = device_register(&cpu->dev);
if (!error && cpu->hotpluggable)
@@ -307,8 +347,8 @@
}
EXPORT_SYMBOL_GPL(get_cpu_device);
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
#endif
static struct attribute *cpu_root_attrs[] = {
@@ -321,7 +361,7 @@
&cpu_attrs[2].attr.attr,
&dev_attr_kernel_max.attr,
&dev_attr_offline.attr,
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
&dev_attr_modalias.attr,
#endif
NULL
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index bc256b6..6ec0b77 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -1,3 +1,4 @@
+#if !defined(__i386__) && !defined(__amd64__)
/*
* Coherent per-device memory handling.
* Borrowed from i386
@@ -218,3 +219,228 @@
return 0;
}
EXPORT_SYMBOL(dma_mmap_from_coherent);
+#else
+/* CMA is a wretched hive of scum and villany --- and also doesn't
+ * compile on x86 */
+
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+ void *virt_base;
+ dma_addr_t device_base;
+ phys_addr_t pfn_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void __iomem *mem_base = NULL;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+ if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+ goto out;
+ if (!size)
+ goto out;
+ if (dev->dma_mem)
+ goto out;
+
+ /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+ mem_base = ioremap(bus_addr, size);
+ if (!mem_base)
+ goto out;
+
+ dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dev->dma_mem)
+ goto out;
+ dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!dev->dma_mem->bitmap)
+ goto free1_out;
+
+ dev->dma_mem->virt_base = mem_base;
+ dev->dma_mem->device_base = device_addr;
+ dev->dma_mem->pfn_base = PFN_DOWN(bus_addr);
+ dev->dma_mem->size = pages;
+ dev->dma_mem->flags = flags;
+
+ if (flags & DMA_MEMORY_MAP)
+ return DMA_MEMORY_MAP;
+
+ return DMA_MEMORY_IO;
+
+ free1_out:
+ kfree(dev->dma_mem);
+ out:
+ if (mem_base)
+ iounmap(mem_base);
+ return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if (!mem)
+ return;
+ dev->dma_mem = NULL;
+ iounmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ int pos, err;
+
+ size += device_addr & ~PAGE_MASK;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
+ *
+ * @dev: device from which we allocate memory
+ * @size: size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret: This pointer will be filled with the virtual address
+ * to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+ dma_addr_t *dma_handle, void **ret)
+{
+ struct dma_coherent_mem *mem;
+ int order = get_order(size);
+ int pageno;
+
+ if (!dev)
+ return 0;
+ mem = dev->dma_mem;
+ if (!mem)
+ return 0;
+
+ *ret = NULL;
+
+ if (unlikely(size > (mem->size << PAGE_SHIFT)))
+ goto err;
+
+ pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+ if (unlikely(pageno < 0))
+ goto err;
+
+ /*
+ * Memory was found in the per-device area.
+ */
+ *dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+ *ret = mem->virt_base + (pageno << PAGE_SHIFT);
+ memset(*ret, 0, size);
+
+ return 1;
+
+err:
+ /*
+ * In the case where the allocation can not be satisfied from the
+ * per-device area, try to fall back to generic memory if the
+ * constraints allow it.
+ */
+ return mem->flags & DMA_MEMORY_EXCLUSIVE;
+}
+EXPORT_SYMBOL(dma_alloc_from_coherent);
+
+/**
+ * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
+ * @dev: device from which the memory was allocated
+ * @order: the order of pages allocated
+ * @vaddr: virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+ if (mem && vaddr >= mem->virt_base && vaddr <
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+ bitmap_release_region(mem->bitmap, page, order);
+ return 1;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(dma_release_from_coherent);
+
+/**
+ * dma_mmap_from_coherent() - try to mmap the memory allocated from
+ * per-device coherent memory pool to userspace
+ * @dev: device from which the memory was allocated
+ * @vma: vm_area for the userspace memory
+ * @vaddr: cpu address returned by dma_alloc_from_coherent
+ * @size: size of the memory buffer allocated by dma_alloc_from_coherent
+ * @ret: result from remap_pfn_range()
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if we correctly mapped the memory, or 0 if the caller should
+ * proceed with mapping memory from generic pools.
+ */
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+ void *vaddr, size_t size, int *ret)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+ if (mem && vaddr >= mem->virt_base && vaddr + size <=
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ unsigned long off = vma->vm_pgoff;
+ int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+ int user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ int count = size >> PAGE_SHIFT;
+
+ *ret = -ENXIO;
+ if (off < count && user_count <= count - off) {
+ unsigned pfn = mem->pfn_base + start + off;
+ *ret = remap_pfn_range(vma, vma->vm_start, pfn,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+ return 1;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(dma_mmap_from_coherent);
+#endif
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8e08fab..30d575a 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -27,6 +27,7 @@
#include <linux/pm.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
+#include <linux/reboot.h>
#include <generated/utsrelease.h>
@@ -130,6 +131,7 @@
struct page **pages;
int nr_pages;
int page_array_size;
+ struct list_head pending_list;
#endif
char fw_id[];
};
@@ -171,6 +173,9 @@
strcpy(buf->fw_id, fw_name);
buf->fwc = fwc;
init_completion(&buf->completion);
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+ INIT_LIST_HEAD(&buf->pending_list);
+#endif
pr_debug("%s: fw-%s buf=%p\n", __func__, fw_name, buf);
@@ -446,10 +451,8 @@
return container_of(dev, struct firmware_priv, dev);
}
-static void fw_load_abort(struct firmware_priv *fw_priv)
+static void __fw_load_abort(struct firmware_buf *buf)
{
- struct firmware_buf *buf = fw_priv->buf;
-
/*
* There is a small window in which user can write to 'loading'
* between loading done and disappearance of 'loading'
@@ -457,8 +460,16 @@
if (test_bit(FW_STATUS_DONE, &buf->status))
return;
+ list_del_init(&buf->pending_list);
set_bit(FW_STATUS_ABORT, &buf->status);
complete_all(&buf->completion);
+}
+
+static void fw_load_abort(struct firmware_priv *fw_priv)
+{
+ struct firmware_buf *buf = fw_priv->buf;
+
+ __fw_load_abort(buf);
/* avoid user action after loading abort */
fw_priv->buf = NULL;
@@ -467,6 +478,25 @@
#define is_fw_load_aborted(buf) \
test_bit(FW_STATUS_ABORT, &(buf)->status)
+static LIST_HEAD(pending_fw_head);
+
+/* reboot notifier for avoid deadlock with usermode_lock */
+static int fw_shutdown_notify(struct notifier_block *unused1,
+ unsigned long unused2, void *unused3)
+{
+ mutex_lock(&fw_lock);
+ while (!list_empty(&pending_fw_head))
+ __fw_load_abort(list_first_entry(&pending_fw_head,
+ struct firmware_buf,
+ pending_list));
+ mutex_unlock(&fw_lock);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block fw_shutdown_nb = {
+ .notifier_call = fw_shutdown_notify,
+};
+
static ssize_t firmware_timeout_show(struct class *class,
struct class_attribute *attr,
char *buf)
@@ -629,6 +659,7 @@
* is completed.
* */
fw_map_pages_buf(fw_buf);
+ list_del_init(&fw_buf->pending_list);
complete_all(&fw_buf->completion);
break;
}
@@ -863,8 +894,15 @@
goto err_del_dev;
}
+ mutex_lock(&fw_lock);
+ list_add(&buf->pending_list, &pending_fw_head);
+ mutex_unlock(&fw_lock);
+
retval = device_create_file(f_dev, &dev_attr_loading);
if (retval) {
+ mutex_lock(&fw_lock);
+ list_del_init(&buf->pending_list);
+ mutex_unlock(&fw_lock);
dev_err(f_dev, "%s: device_create_file failed\n", __func__);
goto err_del_bin_attr;
}
@@ -1539,6 +1577,7 @@
{
fw_cache_init();
#ifdef CONFIG_FW_LOADER_USER_HELPER
+ register_reboot_notifier(&fw_shutdown_nb);
return class_register(&firmware_class);
#else
return 0;
@@ -1552,6 +1591,7 @@
unregister_pm_notifier(&fw_cache.pm_notify);
#endif
#ifdef CONFIG_FW_LOADER_USER_HELPER
+ unregister_reboot_notifier(&fw_shutdown_nb);
class_unregister(&firmware_class);
#endif
}
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 5a9b656..5131ad8 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -29,6 +29,9 @@
#include <linux/async.h>
#include <linux/suspend.h>
#include <linux/cpuidle.h>
+#include <linux/timer.h>
+#include <linux/wakeup_reason.h>
+
#include "../base.h"
#include "power.h"
@@ -54,6 +57,12 @@
static DEFINE_MUTEX(dpm_list_mtx);
static pm_message_t pm_transition;
+struct dpm_watchdog {
+ struct device *dev;
+ struct task_struct *tsk;
+ struct timer_list timer;
+};
+
static int async_error;
/**
@@ -384,6 +393,56 @@
return error;
}
+/**
+ * dpm_wd_handler - Driver suspend / resume watchdog handler.
+ *
+ * Called when a driver has timed out suspending or resuming.
+ * There's not much we can do here to recover so BUG() out for
+ * a crash-dump
+ */
+static void dpm_wd_handler(unsigned long data)
+{
+ struct dpm_watchdog *wd = (void *)data;
+ struct device *dev = wd->dev;
+ struct task_struct *tsk = wd->tsk;
+
+ dev_emerg(dev, "**** DPM device timeout ****\n");
+ show_stack(tsk, NULL);
+
+ BUG();
+}
+
+/**
+ * dpm_wd_set - Enable pm watchdog for given device.
+ * @wd: Watchdog. Must be allocated on the stack.
+ * @dev: Device to handle.
+ */
+static void dpm_wd_set(struct dpm_watchdog *wd, struct device *dev)
+{
+ struct timer_list *timer = &wd->timer;
+
+ wd->dev = dev;
+ wd->tsk = get_current();
+
+ init_timer_on_stack(timer);
+ timer->expires = jiffies + HZ * 12;
+ timer->function = dpm_wd_handler;
+ timer->data = (unsigned long)wd;
+ add_timer(timer);
+}
+
+/**
+ * dpm_wd_clear - Disable pm watchdog.
+ * @wd: Watchdog to disable.
+ */
+static void dpm_wd_clear(struct dpm_watchdog *wd)
+{
+ struct timer_list *timer = &wd->timer;
+
+ del_timer_sync(timer);
+ destroy_timer_on_stack(timer);
+}
+
/*------------------------- Resume routines -------------------------*/
/**
@@ -570,6 +629,7 @@
pm_callback_t callback = NULL;
char *info = NULL;
int error = 0;
+ struct dpm_watchdog wd;
TRACE_DEVICE(dev);
TRACE_RESUME(0);
@@ -585,6 +645,7 @@
* a resumed device, even if the device hasn't been completed yet.
*/
dev->power.is_prepared = false;
+ dpm_wd_set(&wd, dev);
if (!dev->power.is_suspended)
goto Unlock;
@@ -636,6 +697,7 @@
Unlock:
device_unlock(dev);
+ dpm_wd_clear(&wd);
Complete:
complete_all(&dev->power.completion);
@@ -877,6 +939,7 @@
static int dpm_suspend_noirq(pm_message_t state)
{
ktime_t starttime = ktime_get();
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
int error = 0;
cpuidle_pause();
@@ -904,6 +967,9 @@
put_device(dev);
if (pm_wakeup_pending()) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
error = -EBUSY;
break;
}
@@ -962,6 +1028,7 @@
static int dpm_suspend_late(pm_message_t state)
{
ktime_t starttime = ktime_get();
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
int error = 0;
mutex_lock(&dpm_list_mtx);
@@ -987,6 +1054,9 @@
put_device(dev);
if (pm_wakeup_pending()) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
error = -EBUSY;
break;
}
@@ -1053,6 +1123,8 @@
pm_callback_t callback = NULL;
char *info = NULL;
int error = 0;
+ struct dpm_watchdog wd;
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
dpm_wait_for_children(dev, async);
@@ -1069,12 +1141,17 @@
pm_wakeup_event(dev, 0);
if (pm_wakeup_pending()) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
async_error = -EBUSY;
goto Complete;
}
if (dev->power.syscore)
goto Complete;
+
+ dpm_wd_set(&wd, dev);
device_lock(dev);
@@ -1131,6 +1208,8 @@
device_unlock(dev);
+ dpm_wd_clear(&wd);
+
Complete:
complete_all(&dev->power.completion);
if (error)
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 79715e7..6cfdf97 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -14,6 +14,7 @@
#include <linux/suspend.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
+#include <linux/types.h>
#include <trace/events/power.h>
#include "power.h"
@@ -53,6 +54,8 @@
static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
+static ktime_t last_read_time;
+
/**
* wakeup_source_prepare - Prepare a new wakeup source for initialization.
* @ws: Wakeup source to prepare.
@@ -342,6 +345,20 @@
}
EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
+/**
+ * wakeup_source_not_registered - validate the given wakeup source.
+ * @ws: Wakeup source to be validated.
+ */
+static bool wakeup_source_not_registered(struct wakeup_source *ws)
+{
+ /*
+ * Use timer struct to check if the given source is initialized
+ * by wakeup_source_add.
+ */
+ return ws->timer.function != pm_wakeup_timer_fn ||
+ ws->timer.data != (unsigned long)ws;
+}
+
/*
* The functions below use the observation that each wakeup event starts a
* period in which the system should not be suspended. The moment this period
@@ -382,6 +399,10 @@
{
unsigned int cec;
+ if (WARN(wakeup_source_not_registered(ws),
+ "unregistered wakeup source\n"))
+ return;
+
/*
* active wakeup source should bring the system
* out of PM_SUSPEND_FREEZE state
@@ -659,6 +680,37 @@
}
EXPORT_SYMBOL_GPL(pm_wakeup_event);
+void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max)
+{
+ struct wakeup_source *ws, *last_active_ws = NULL;
+ int len = 0;
+ bool active = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+ if (ws->active && len < max) {
+ if (!active)
+ len += scnprintf(pending_wakeup_source, max,
+ "Pending Wakeup Sources: ");
+ len += scnprintf(pending_wakeup_source + len, max - len,
+ "%s ", ws->name);
+ active = true;
+ } else if (!active &&
+ (!last_active_ws ||
+ ktime_to_ns(ws->last_time) >
+ ktime_to_ns(last_active_ws->last_time))) {
+ last_active_ws = ws;
+ }
+ }
+ if (!active && last_active_ws) {
+ scnprintf(pending_wakeup_source, max,
+ "Last active Wakeup Source: %s",
+ last_active_ws->name);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources);
+
static void print_active_wakeup_sources(void)
{
struct wakeup_source *ws;
@@ -728,10 +780,15 @@
bool pm_get_wakeup_count(unsigned int *count, bool block)
{
unsigned int cnt, inpr;
+ unsigned long flags;
if (block) {
DEFINE_WAIT(wait);
+ spin_lock_irqsave(&events_lock, flags);
+ last_read_time = ktime_get();
+ spin_unlock_irqrestore(&events_lock, flags);
+
for (;;) {
prepare_to_wait(&wakeup_count_wait_queue, &wait,
TASK_INTERRUPTIBLE);
@@ -763,6 +820,7 @@
{
unsigned int cnt, inpr;
unsigned long flags;
+ struct wakeup_source *ws;
events_check_enabled = false;
spin_lock_irqsave(&events_lock, flags);
@@ -770,6 +828,15 @@
if (cnt == count && inpr == 0) {
saved_count = count;
events_check_enabled = true;
+ } else {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+ if (ws->active ||
+ ktime_compare(ws->last_time, last_read_time) > 0) {
+ ws->wakeup_count++;
+ }
+ }
+ rcu_read_unlock();
}
spin_unlock_irqrestore(&events_lock, flags);
return events_check_enabled;
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index e8d11b6..0ab5465 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/module.h>
#include <linux/interrupt.h>
+#include <linux/wakeup_reason.h>
static LIST_HEAD(syscore_ops_list);
static DEFINE_MUTEX(syscore_ops_lock);
@@ -73,6 +74,8 @@
return 0;
err_out:
+ log_suspend_abort_reason("System core suspend callback %pF failed",
+ ops->suspend);
pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
list_for_each_entry_continue(ops, &syscore_ops_list, node)
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b81ddfe..9da952c 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -105,6 +105,8 @@
source "drivers/block/mtip32xx/Kconfig"
+source "drivers/block/zram/Kconfig"
+
config BLK_CPQ_DA
tristate "Compaq SMART2 support"
depends on PCI && VIRT_TO_BUS
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index ca07399..3675937 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -41,6 +41,7 @@
obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX) += mtip32xx/
obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
+obj-$(CONFIG_ZRAM) += zram/
nvme-y := nvme-core.o nvme-scsi.o
swim_mod-y := swim.o swim_asm.o
diff --git a/drivers/staging/zram/Kconfig b/drivers/block/zram/Kconfig
similarity index 72%
rename from drivers/staging/zram/Kconfig
rename to drivers/block/zram/Kconfig
index 983314c..6489c0f 100644
--- a/drivers/staging/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -14,7 +14,16 @@
disks and maybe many more.
See zram.txt for more information.
- Project home: <https://compcache.googlecode.com/>
+
+config ZRAM_LZ4_COMPRESS
+ bool "Enable LZ4 algorithm support"
+ depends on ZRAM
+ select LZ4_COMPRESS
+ select LZ4_DECOMPRESS
+ default n
+ help
+ This option enables LZ4 compression algorithm support. Compression
+ algorithm can be changed using `comp_algorithm' device attribute.
config ZRAM_DEBUG
bool "Compressed RAM block device debug support"
diff --git a/drivers/block/zram/Makefile b/drivers/block/zram/Makefile
new file mode 100644
index 0000000..be0763f
--- /dev/null
+++ b/drivers/block/zram/Makefile
@@ -0,0 +1,5 @@
+zram-y := zcomp_lzo.o zcomp.o zram_drv.o
+
+zram-$(CONFIG_ZRAM_LZ4_COMPRESS) += zcomp_lz4.o
+
+obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
new file mode 100644
index 0000000..54d946a
--- /dev/null
+++ b/drivers/block/zram/zcomp.c
@@ -0,0 +1,355 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+
+#include "zcomp.h"
+#include "zcomp_lzo.h"
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+#include "zcomp_lz4.h"
+#endif
+
+/*
+ * single zcomp_strm backend
+ */
+struct zcomp_strm_single {
+ struct mutex strm_lock;
+ struct zcomp_strm *zstrm;
+};
+
+/*
+ * multi zcomp_strm backend
+ */
+struct zcomp_strm_multi {
+ /* protect strm list */
+ spinlock_t strm_lock;
+ /* max possible number of zstrm streams */
+ int max_strm;
+ /* number of available zstrm streams */
+ int avail_strm;
+ /* list of available strms */
+ struct list_head idle_strm;
+ wait_queue_head_t strm_wait;
+};
+
+static struct zcomp_backend *backends[] = {
+ &zcomp_lzo,
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+ &zcomp_lz4,
+#endif
+ NULL
+};
+
+static struct zcomp_backend *find_backend(const char *compress)
+{
+ int i = 0;
+ while (backends[i]) {
+ if (sysfs_streq(compress, backends[i]->name))
+ break;
+ i++;
+ }
+ return backends[i];
+}
+
+static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ if (zstrm->private)
+ comp->backend->destroy(zstrm->private);
+ free_pages((unsigned long)zstrm->buffer, 1);
+ kfree(zstrm);
+}
+
+/*
+ * allocate new zcomp_strm structure with ->private initialized by
+ * backend, return NULL on error
+ */
+static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
+{
+ struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
+ if (!zstrm)
+ return NULL;
+
+ zstrm->private = comp->backend->create();
+ /*
+ * allocate 2 pages. 1 for compressed data, plus 1 extra for the
+ * case when compressed size is larger than the original one
+ */
+ zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+ if (!zstrm->private || !zstrm->buffer) {
+ zcomp_strm_free(comp, zstrm);
+ zstrm = NULL;
+ }
+ return zstrm;
+}
+
+/*
+ * get idle zcomp_strm or wait until other process release
+ * (zcomp_strm_release()) one for us
+ */
+static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ while (1) {
+ spin_lock(&zs->strm_lock);
+ if (!list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ spin_unlock(&zs->strm_lock);
+ return zstrm;
+ }
+ /* zstrm streams limit reached, wait for idle stream */
+ if (zs->avail_strm >= zs->max_strm) {
+ spin_unlock(&zs->strm_lock);
+ wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+ continue;
+ }
+ /* allocate new zstrm stream */
+ zs->avail_strm++;
+ spin_unlock(&zs->strm_lock);
+
+ zstrm = zcomp_strm_alloc(comp);
+ if (!zstrm) {
+ spin_lock(&zs->strm_lock);
+ zs->avail_strm--;
+ spin_unlock(&zs->strm_lock);
+ wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+ continue;
+ }
+ break;
+ }
+ return zstrm;
+}
+
+/* add stream back to idle list and wake up waiter or free the stream */
+static void zcomp_strm_multi_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+
+ spin_lock(&zs->strm_lock);
+ if (zs->avail_strm <= zs->max_strm) {
+ list_add(&zstrm->list, &zs->idle_strm);
+ spin_unlock(&zs->strm_lock);
+ wake_up(&zs->strm_wait);
+ return;
+ }
+
+ zs->avail_strm--;
+ spin_unlock(&zs->strm_lock);
+ zcomp_strm_free(comp, zstrm);
+}
+
+/* change max_strm limit */
+static bool zcomp_strm_multi_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ spin_lock(&zs->strm_lock);
+ zs->max_strm = num_strm;
+ /*
+ * if user has lowered the limit and there are idle streams,
+ * immediately free as much streams (and memory) as we can.
+ */
+ while (zs->avail_strm > num_strm && !list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ zcomp_strm_free(comp, zstrm);
+ zs->avail_strm--;
+ }
+ spin_unlock(&zs->strm_lock);
+ return true;
+}
+
+static void zcomp_strm_multi_destroy(struct zcomp *comp)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ while (!list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ zcomp_strm_free(comp, zstrm);
+ }
+ kfree(zs);
+}
+
+static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm)
+{
+ struct zcomp_strm *zstrm;
+ struct zcomp_strm_multi *zs;
+
+ comp->destroy = zcomp_strm_multi_destroy;
+ comp->strm_find = zcomp_strm_multi_find;
+ comp->strm_release = zcomp_strm_multi_release;
+ comp->set_max_streams = zcomp_strm_multi_set_max_streams;
+ zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL);
+ if (!zs)
+ return -ENOMEM;
+
+ comp->stream = zs;
+ spin_lock_init(&zs->strm_lock);
+ INIT_LIST_HEAD(&zs->idle_strm);
+ init_waitqueue_head(&zs->strm_wait);
+ zs->max_strm = max_strm;
+ zs->avail_strm = 1;
+
+ zstrm = zcomp_strm_alloc(comp);
+ if (!zstrm) {
+ kfree(zs);
+ return -ENOMEM;
+ }
+ list_add(&zstrm->list, &zs->idle_strm);
+ return 0;
+}
+
+static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ mutex_lock(&zs->strm_lock);
+ return zs->zstrm;
+}
+
+static void zcomp_strm_single_release(struct zcomp *comp,
+ struct zcomp_strm *zstrm)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ mutex_unlock(&zs->strm_lock);
+}
+
+static bool zcomp_strm_single_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ /* zcomp_strm_single support only max_comp_streams == 1 */
+ return false;
+}
+
+static void zcomp_strm_single_destroy(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ zcomp_strm_free(comp, zs->zstrm);
+ kfree(zs);
+}
+
+static int zcomp_strm_single_create(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs;
+
+ comp->destroy = zcomp_strm_single_destroy;
+ comp->strm_find = zcomp_strm_single_find;
+ comp->strm_release = zcomp_strm_single_release;
+ comp->set_max_streams = zcomp_strm_single_set_max_streams;
+ zs = kmalloc(sizeof(struct zcomp_strm_single), GFP_KERNEL);
+ if (!zs)
+ return -ENOMEM;
+
+ comp->stream = zs;
+ mutex_init(&zs->strm_lock);
+ zs->zstrm = zcomp_strm_alloc(comp);
+ if (!zs->zstrm) {
+ kfree(zs);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+/* show available compressors */
+ssize_t zcomp_available_show(const char *comp, char *buf)
+{
+ ssize_t sz = 0;
+ int i = 0;
+
+ while (backends[i]) {
+ if (sysfs_streq(comp, backends[i]->name))
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+ "[%s] ", backends[i]->name);
+ else
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+ "%s ", backends[i]->name);
+ i++;
+ }
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n");
+ return sz;
+}
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ return comp->set_max_streams(comp, num_strm);
+}
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp)
+{
+ return comp->strm_find(comp);
+}
+
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ comp->strm_release(comp, zstrm);
+}
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+ const unsigned char *src, size_t *dst_len)
+{
+ return comp->backend->compress(src, zstrm->buffer, dst_len,
+ zstrm->private);
+}
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+ size_t src_len, unsigned char *dst)
+{
+ return comp->backend->decompress(src, src_len, dst);
+}
+
+void zcomp_destroy(struct zcomp *comp)
+{
+ comp->destroy(comp);
+ kfree(comp);
+}
+
+/*
+ * search available compressors for requested algorithm.
+ * allocate new zcomp and initialize it. return compressing
+ * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
+ * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
+ * case of allocation error, or any other error potentially
+ * returned by functions zcomp_strm_{multi,single}_create.
+ */
+struct zcomp *zcomp_create(const char *compress, int max_strm)
+{
+ struct zcomp *comp;
+ struct zcomp_backend *backend;
+ int error;
+
+ backend = find_backend(compress);
+ if (!backend)
+ return ERR_PTR(-EINVAL);
+
+ comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
+ if (!comp)
+ return ERR_PTR(-ENOMEM);
+
+ comp->backend = backend;
+ if (max_strm > 1)
+ error = zcomp_strm_multi_create(comp, max_strm);
+ else
+ error = zcomp_strm_single_create(comp);
+ if (error) {
+ kfree(comp);
+ return ERR_PTR(error);
+ }
+ return comp;
+}
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 0000000..c59d1fc
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+struct zcomp_strm {
+ /* compression/decompression buffer */
+ void *buffer;
+ /*
+ * The private data of the compression stream, only compression
+ * stream backend can touch this (e.g. compression algorithm
+ * working memory)
+ */
+ void *private;
+ /* used in multi stream backend, protected by backend strm_lock */
+ struct list_head list;
+};
+
+/* static compression backend */
+struct zcomp_backend {
+ int (*compress)(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private);
+
+ int (*decompress)(const unsigned char *src, size_t src_len,
+ unsigned char *dst);
+
+ void *(*create)(void);
+ void (*destroy)(void *private);
+
+ const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+ void *stream;
+ struct zcomp_backend *backend;
+
+ struct zcomp_strm *(*strm_find)(struct zcomp *comp);
+ void (*strm_release)(struct zcomp *comp, struct zcomp_strm *zstrm);
+ bool (*set_max_streams)(struct zcomp *comp, int num_strm);
+ void (*destroy)(struct zcomp *comp);
+};
+
+ssize_t zcomp_available_show(const char *comp, char *buf);
+
+struct zcomp *zcomp_create(const char *comp, int max_strm);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp);
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+ const unsigned char *src, size_t *dst_len);
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+ size_t src_len, unsigned char *dst);
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
+#endif /* _ZCOMP_H_ */
diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c
new file mode 100644
index 0000000..f2afb7e
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lz4.h>
+
+#include "zcomp_lz4.h"
+
+static void *zcomp_lz4_create(void)
+{
+ return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void zcomp_lz4_destroy(void *private)
+{
+ kfree(private);
+}
+
+static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private)
+{
+ /* return : Success if return 0 */
+ return lz4_compress(src, PAGE_SIZE, dst, dst_len, private);
+}
+
+static int zcomp_lz4_decompress(const unsigned char *src, size_t src_len,
+ unsigned char *dst)
+{
+ size_t dst_len = PAGE_SIZE;
+ /* return : Success if return 0 */
+ return lz4_decompress_unknownoutputsize(src, src_len, dst, &dst_len);
+}
+
+struct zcomp_backend zcomp_lz4 = {
+ .compress = zcomp_lz4_compress,
+ .decompress = zcomp_lz4_decompress,
+ .create = zcomp_lz4_create,
+ .destroy = zcomp_lz4_destroy,
+ .name = "lz4",
+};
diff --git a/drivers/block/zram/zcomp_lz4.h b/drivers/block/zram/zcomp_lz4.h
new file mode 100644
index 0000000..60613fb
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZ4_H_
+#define _ZCOMP_LZ4_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lz4;
+
+#endif /* _ZCOMP_LZ4_H_ */
diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c
new file mode 100644
index 0000000..da1bc47
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lzo.h>
+
+#include "zcomp_lzo.h"
+
+static void *lzo_create(void)
+{
+ return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void lzo_destroy(void *private)
+{
+ kfree(private);
+}
+
+static int lzo_compress(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private)
+{
+ int ret = lzo1x_1_compress(src, PAGE_SIZE, dst, dst_len, private);
+ return ret == LZO_E_OK ? 0 : ret;
+}
+
+static int lzo_decompress(const unsigned char *src, size_t src_len,
+ unsigned char *dst)
+{
+ size_t dst_len = PAGE_SIZE;
+ int ret = lzo1x_decompress_safe(src, src_len, dst, &dst_len);
+ return ret == LZO_E_OK ? 0 : ret;
+}
+
+struct zcomp_backend zcomp_lzo = {
+ .compress = lzo_compress,
+ .decompress = lzo_decompress,
+ .create = lzo_create,
+ .destroy = lzo_destroy,
+ .name = "lzo",
+};
diff --git a/drivers/block/zram/zcomp_lzo.h b/drivers/block/zram/zcomp_lzo.h
new file mode 100644
index 0000000..128c580
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZO_H_
+#define _ZCOMP_LZO_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lzo;
+
+#endif /* _ZCOMP_LZO_H_ */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
new file mode 100644
index 0000000..78a7d24
--- /dev/null
+++ b/drivers/block/zram/zram_drv.c
@@ -0,0 +1,1276 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#define KMSG_COMPONENT "zram"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#ifdef CONFIG_ZRAM_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bio.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+#include <linux/err.h>
+
+#include "zram_drv.h"
+
+/* Globals */
+static int zram_major;
+static struct zram *zram_devices;
+static const char *default_compressor = "lzo";
+
+/* Module params (documentation at end) */
+static unsigned int num_devices = 1;
+
+static inline void deprecated_attr_warn(const char *name)
+{
+ pr_warn_once("%d (%s) Attribute %s (and others) will be removed. %s\n",
+ task_pid_nr(current),
+ current->comm,
+ name,
+ "See zram documentation.");
+}
+
+#define ZRAM_ATTR_RO(name) \
+static ssize_t zram_attr_##name##_show(struct device *d, \
+ struct device_attribute *attr, char *b) \
+{ \
+ struct zram *zram = dev_to_zram(d); \
+ \
+ deprecated_attr_warn(__stringify(name)); \
+ return scnprintf(b, PAGE_SIZE, "%llu\n", \
+ (u64)atomic64_read(&zram->stats.name)); \
+} \
+static struct device_attribute dev_attr_##name = \
+ __ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
+
+static inline bool init_done(struct zram *zram)
+{
+ return zram->disksize;
+}
+
+static inline struct zram *dev_to_zram(struct device *dev)
+{
+ return (struct zram *)dev_to_disk(dev)->private_data;
+}
+
+static ssize_t compact_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ unsigned long nr_migrated;
+ struct zram *zram = dev_to_zram(dev);
+ struct zram_meta *meta;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ return -EINVAL;
+ }
+
+ meta = zram->meta;
+ nr_migrated = zs_compact(meta->mem_pool);
+ atomic64_add(nr_migrated, &zram->stats.num_migrated);
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t disksize_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
+}
+
+static ssize_t initstate_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = init_done(zram);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t orig_data_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ deprecated_attr_warn("orig_data_size");
+ return scnprintf(buf, PAGE_SIZE, "%llu\n",
+ (u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_total_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+
+ deprecated_attr_warn("mem_used_total");
+ down_read(&zram->init_lock);
+ if (init_done(zram)) {
+ struct zram_meta *meta = zram->meta;
+ val = zs_get_total_pages(meta->mem_pool);
+ }
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t max_comp_streams_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = zram->max_comp_streams;
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t mem_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ deprecated_attr_warn("mem_limit");
+ down_read(&zram->init_lock);
+ val = zram->limit_pages;
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_limit_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 limit;
+ char *tmp;
+ struct zram *zram = dev_to_zram(dev);
+
+ limit = memparse(buf, &tmp);
+ if (buf == tmp) /* no chars parsed, invalid input */
+ return -EINVAL;
+
+ down_write(&zram->init_lock);
+ zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+ up_write(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t mem_used_max_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+
+ deprecated_attr_warn("mem_used_max");
+ down_read(&zram->init_lock);
+ if (init_done(zram))
+ val = atomic_long_read(&zram->stats.max_used_pages);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int err;
+ unsigned long val;
+ struct zram *zram = dev_to_zram(dev);
+
+ err = kstrtoul(buf, 10, &val);
+ if (err || val != 0)
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (init_done(zram)) {
+ struct zram_meta *meta = zram->meta;
+ atomic_long_set(&zram->stats.max_used_pages,
+ zs_get_total_pages(meta->mem_pool));
+ }
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t max_comp_streams_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int num;
+ struct zram *zram = dev_to_zram(dev);
+ int ret;
+
+ ret = kstrtoint(buf, 0, &num);
+ if (ret < 0)
+ return ret;
+ if (num < 1)
+ return -EINVAL;
+
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ if (!zcomp_set_max_streams(zram->comp, num)) {
+ pr_info("Cannot change max compression streams\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+ zram->max_comp_streams = num;
+ ret = len;
+out:
+ up_write(&zram->init_lock);
+ return ret;
+}
+
+static ssize_t comp_algorithm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ size_t sz;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ sz = zcomp_available_show(zram->compressor, buf);
+ up_read(&zram->init_lock);
+
+ return sz;
+}
+
+static ssize_t comp_algorithm_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ up_write(&zram->init_lock);
+ pr_info("Can't change algorithm for initialized device\n");
+ return -EBUSY;
+ }
+ strlcpy(zram->compressor, buf, sizeof(zram->compressor));
+ up_write(&zram->init_lock);
+ return len;
+}
+
+/* flag operations needs meta->tb_lock */
+static int zram_test_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ return meta->table[index].value & BIT(flag);
+}
+
+static void zram_set_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].value |= BIT(flag);
+}
+
+static void zram_clear_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].value &= ~BIT(flag);
+}
+
+static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
+{
+ return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+}
+
+static void zram_set_obj_size(struct zram_meta *meta,
+ u32 index, size_t size)
+{
+ unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;
+
+ meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
+}
+
+static inline int is_partial_io(struct bio_vec *bvec)
+{
+ return bvec->bv_len != PAGE_SIZE;
+}
+
+/*
+ * Check if request is within bounds and aligned on zram logical blocks.
+ */
+static inline int valid_io_request(struct zram *zram,
+ sector_t start, unsigned int size)
+{
+ u64 end, bound;
+
+ /* unaligned request */
+ if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+ return 0;
+ if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+ return 0;
+
+ end = start + (size >> SECTOR_SHIFT);
+ bound = zram->disksize >> SECTOR_SHIFT;
+ /* out of range range */
+ if (unlikely(start >= bound || end > bound || start > end))
+ return 0;
+
+ /* I/O request is valid */
+ return 1;
+}
+
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
+{
+ size_t num_pages = disksize >> PAGE_SHIFT;
+ size_t index;
+
+ /* Free all pages that are still in this zram device */
+ for (index = 0; index < num_pages; index++) {
+ unsigned long handle = meta->table[index].handle;
+
+ if (!handle)
+ continue;
+
+ zs_free(meta->mem_pool, handle);
+ }
+
+ zs_destroy_pool(meta->mem_pool);
+ vfree(meta->table);
+ kfree(meta);
+}
+
+static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
+{
+ size_t num_pages;
+ char pool_name[8];
+ struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+
+ if (!meta)
+ return NULL;
+
+ num_pages = disksize >> PAGE_SHIFT;
+ meta->table = vzalloc(num_pages * sizeof(*meta->table));
+ if (!meta->table) {
+ pr_err("Error allocating zram address table\n");
+ goto out_error;
+ }
+
+ snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
+ meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
+ if (!meta->mem_pool) {
+ pr_err("Error creating memory pool\n");
+ goto out_error;
+ }
+
+ return meta;
+
+out_error:
+ vfree(meta->table);
+ kfree(meta);
+ return NULL;
+}
+
+static inline bool zram_meta_get(struct zram *zram)
+{
+ if (atomic_inc_not_zero(&zram->refcount))
+ return true;
+ return false;
+}
+
+static inline void zram_meta_put(struct zram *zram)
+{
+ atomic_dec(&zram->refcount);
+}
+
+static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
+{
+ if (*offset + bvec->bv_len >= PAGE_SIZE)
+ (*index)++;
+ *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
+}
+
+static int page_zero_filled(void *ptr)
+{
+ unsigned int pos;
+ unsigned long *page;
+
+ page = (unsigned long *)ptr;
+
+ for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
+ if (page[pos])
+ return 0;
+ }
+
+ return 1;
+}
+
+static void handle_zero_page(struct bio_vec *bvec)
+{
+ struct page *page = bvec->bv_page;
+ void *user_mem;
+
+ user_mem = kmap_atomic(page);
+ if (is_partial_io(bvec))
+ memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
+ else
+ clear_page(user_mem);
+ kunmap_atomic(user_mem);
+
+ flush_dcache_page(page);
+}
+
+
+/*
+ * To protect concurrent access to the same index entry,
+ * caller should hold this table index entry's bit_spinlock to
+ * indicate this index entry is accessing.
+ */
+static void zram_free_page(struct zram *zram, size_t index)
+{
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle = meta->table[index].handle;
+
+ if (unlikely(!handle)) {
+ /*
+ * No memory is allocated for zero filled pages.
+ * Simply clear zero page flag.
+ */
+ if (zram_test_flag(meta, index, ZRAM_ZERO)) {
+ zram_clear_flag(meta, index, ZRAM_ZERO);
+ atomic64_dec(&zram->stats.zero_pages);
+ }
+ return;
+ }
+
+ zs_free(meta->mem_pool, handle);
+
+ atomic64_sub(zram_get_obj_size(meta, index),
+ &zram->stats.compr_data_size);
+ atomic64_dec(&zram->stats.pages_stored);
+
+ meta->table[index].handle = 0;
+ zram_set_obj_size(meta, index, 0);
+}
+
+static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
+{
+ int ret = 0;
+ unsigned char *cmem;
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle;
+ size_t size;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ handle = meta->table[index].handle;
+ size = zram_get_obj_size(meta, index);
+
+ if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ clear_page(mem);
+ return 0;
+ }
+
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
+ if (size == PAGE_SIZE)
+ copy_page(mem, cmem);
+ else
+ ret = zcomp_decompress(zram->comp, cmem, size, mem);
+ zs_unmap_object(meta->mem_pool, handle);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret)) {
+ pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset)
+{
+ int ret;
+ struct page *page;
+ unsigned char *user_mem, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ page = bvec->bv_page;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ if (unlikely(!meta->table[index].handle) ||
+ zram_test_flag(meta, index, ZRAM_ZERO)) {
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ handle_zero_page(bvec);
+ return 0;
+ }
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ if (is_partial_io(bvec))
+ /* Use a temporary buffer to decompress the page */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+
+ user_mem = kmap_atomic(page);
+ if (!is_partial_io(bvec))
+ uncmem = user_mem;
+
+ if (!uncmem) {
+ pr_info("Unable to allocate temp memory\n");
+ ret = -ENOMEM;
+ goto out_cleanup;
+ }
+
+ ret = zram_decompress_page(zram, uncmem, index);
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret))
+ goto out_cleanup;
+
+ if (is_partial_io(bvec))
+ memcpy(user_mem + bvec->bv_offset, uncmem + offset,
+ bvec->bv_len);
+
+ flush_dcache_page(page);
+ ret = 0;
+out_cleanup:
+ kunmap_atomic(user_mem);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+ return ret;
+}
+
+static inline void update_used_max(struct zram *zram,
+ const unsigned long pages)
+{
+ unsigned long old_max, cur_max;
+
+ old_max = atomic_long_read(&zram->stats.max_used_pages);
+
+ do {
+ cur_max = old_max;
+ if (pages > cur_max)
+ old_max = atomic_long_cmpxchg(
+ &zram->stats.max_used_pages, cur_max, pages);
+ } while (old_max != cur_max);
+}
+
+static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset)
+{
+ int ret = 0;
+ size_t clen;
+ unsigned long handle;
+ struct page *page;
+ unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ struct zcomp_strm *zstrm;
+ bool locked = false;
+ unsigned long alloced_pages;
+
+ page = bvec->bv_page;
+ if (is_partial_io(bvec)) {
+ /*
+ * This is a partial IO. We need to read the full page
+ * before to write the changes.
+ */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+ if (!uncmem) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = zram_decompress_page(zram, uncmem, index);
+ if (ret)
+ goto out;
+ }
+
+ zstrm = zcomp_strm_find(zram->comp);
+ locked = true;
+ user_mem = kmap_atomic(page);
+
+ if (is_partial_io(bvec)) {
+ memcpy(uncmem + offset, user_mem + bvec->bv_offset,
+ bvec->bv_len);
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ } else {
+ uncmem = user_mem;
+ }
+
+ if (page_zero_filled(uncmem)) {
+ if (user_mem)
+ kunmap_atomic(user_mem);
+ /* Free memory associated with this sector now. */
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ zram_set_flag(meta, index, ZRAM_ZERO);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ atomic64_inc(&zram->stats.zero_pages);
+ ret = 0;
+ goto out;
+ }
+
+ ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
+ if (!is_partial_io(bvec)) {
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ uncmem = NULL;
+ }
+
+ if (unlikely(ret)) {
+ pr_err("Compression failed! err=%d\n", ret);
+ goto out;
+ }
+ src = zstrm->buffer;
+ if (unlikely(clen > max_zpage_size)) {
+ clen = PAGE_SIZE;
+ if (is_partial_io(bvec))
+ src = uncmem;
+ }
+
+ handle = zs_malloc(meta->mem_pool, clen);
+ if (!handle) {
+ pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
+ index, clen);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ alloced_pages = zs_get_total_pages(meta->mem_pool);
+ if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+ zs_free(meta->mem_pool, handle);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ update_used_max(zram, alloced_pages);
+
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
+
+ if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
+ src = kmap_atomic(page);
+ copy_page(cmem, src);
+ kunmap_atomic(src);
+ } else {
+ memcpy(cmem, src, clen);
+ }
+
+ zcomp_strm_release(zram->comp, zstrm);
+ locked = false;
+ zs_unmap_object(meta->mem_pool, handle);
+
+ /*
+ * Free memory associated with this sector
+ * before overwriting unused sectors.
+ */
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+
+ meta->table[index].handle = handle;
+ zram_set_obj_size(meta, index, clen);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ /* Update stats */
+ atomic64_add(clen, &zram->stats.compr_data_size);
+ atomic64_inc(&zram->stats.pages_stored);
+out:
+ if (locked)
+ zcomp_strm_release(zram->comp, zstrm);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+ return ret;
+}
+
+static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset, int rw)
+{
+ int ret;
+
+ if (rw == READ) {
+ atomic64_inc(&zram->stats.num_reads);
+ ret = zram_bvec_read(zram, bvec, index, offset);
+ } else {
+ atomic64_inc(&zram->stats.num_writes);
+ ret = zram_bvec_write(zram, bvec, index, offset);
+ }
+
+ if (unlikely(ret)) {
+ if (rw == READ)
+ atomic64_inc(&zram->stats.failed_reads);
+ else
+ atomic64_inc(&zram->stats.failed_writes);
+ }
+
+ return ret;
+}
+
+/*
+ * zram_bio_discard - handler on discard request
+ * @index: physical block index in PAGE_SIZE units
+ * @offset: byte offset within physical block
+ */
+static void zram_bio_discard(struct zram *zram, u32 index,
+ int offset, struct bio *bio)
+{
+ size_t n = bio->bi_size;
+ struct zram_meta *meta = zram->meta;
+
+ /*
+ * zram manages data in physical block size units. Because logical block
+ * size isn't identical with physical block size on some arch, we
+ * could get a discard request pointing to a specific offset within a
+ * certain physical block. Although we can handle this request by
+ * reading that physiclal block and decompressing and partially zeroing
+ * and re-compressing and then re-storing it, this isn't reasonable
+ * because our intent with a discard request is to save memory. So
+ * skipping this logical block is appropriate here.
+ */
+ if (offset) {
+ if (n <= (PAGE_SIZE - offset))
+ return;
+
+ n -= (PAGE_SIZE - offset);
+ index++;
+ }
+
+ while (n >= PAGE_SIZE) {
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ atomic64_inc(&zram->stats.notify_free);
+ index++;
+ n -= PAGE_SIZE;
+ }
+}
+
+static void zram_reset_device(struct zram *zram)
+{
+ struct zram_meta *meta;
+ struct zcomp *comp;
+ u64 disksize;
+
+ down_write(&zram->init_lock);
+
+ zram->limit_pages = 0;
+
+ if (!init_done(zram)) {
+ up_write(&zram->init_lock);
+ return;
+ }
+
+ meta = zram->meta;
+ comp = zram->comp;
+ disksize = zram->disksize;
+ /*
+ * Refcount will go down to 0 eventually and r/w handler
+ * cannot handle further I/O so it will bail out by
+ * check zram_meta_get.
+ */
+ zram_meta_put(zram);
+ /*
+ * We want to free zram_meta in process context to avoid
+ * deadlock between reclaim path and any other locks.
+ */
+ wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
+
+ /* Reset stats */
+ memset(&zram->stats, 0, sizeof(zram->stats));
+ zram->disksize = 0;
+ zram->max_comp_streams = 1;
+
+ set_capacity(zram->disk, 0);
+ part_stat_set_all(&zram->disk->part0, 0);
+
+ up_write(&zram->init_lock);
+ /* I/O operation under all of CPU are done so let's free */
+ zram_meta_free(meta, disksize);
+ zcomp_destroy(comp);
+}
+
+static ssize_t disksize_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 disksize;
+ struct zcomp *comp;
+ struct zram_meta *meta;
+ struct zram *zram = dev_to_zram(dev);
+ int err;
+
+ disksize = memparse(buf, NULL);
+ if (!disksize)
+ return -EINVAL;
+
+ disksize = PAGE_ALIGN(disksize);
+ meta = zram_meta_alloc(zram->disk->first_minor, disksize);
+ if (!meta)
+ return -ENOMEM;
+
+ comp = zcomp_create(zram->compressor, zram->max_comp_streams);
+ if (IS_ERR(comp)) {
+ pr_info("Cannot initialise %s compressing backend\n",
+ zram->compressor);
+ err = PTR_ERR(comp);
+ goto out_free_meta;
+ }
+
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ pr_info("Cannot change disksize for initialized device\n");
+ err = -EBUSY;
+ goto out_destroy_comp;
+ }
+
+ init_waitqueue_head(&zram->io_done);
+ atomic_set(&zram->refcount, 1);
+ zram->meta = meta;
+ zram->comp = comp;
+ zram->disksize = disksize;
+ set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
+ up_write(&zram->init_lock);
+
+ /*
+ * Revalidate disk out of the init_lock to avoid lockdep splat.
+ * It's okay because disk's capacity is protected by init_lock
+ * so that revalidate_disk always sees up-to-date capacity.
+ */
+ revalidate_disk(zram->disk);
+
+ return len;
+
+out_destroy_comp:
+ up_write(&zram->init_lock);
+ zcomp_destroy(comp);
+out_free_meta:
+ zram_meta_free(meta, disksize);
+ return err;
+}
+
+static ssize_t reset_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int ret;
+ unsigned short do_reset;
+ struct zram *zram;
+ struct block_device *bdev;
+
+ zram = dev_to_zram(dev);
+ bdev = bdget_disk(zram->disk, 0);
+
+ if (!bdev)
+ return -ENOMEM;
+
+ mutex_lock(&bdev->bd_mutex);
+ /* Do not reset an active device! */
+ if (bdev->bd_openers) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ret = kstrtou16(buf, 10, &do_reset);
+ if (ret)
+ goto out;
+
+ if (!do_reset) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Make sure all pending I/O is finished */
+ fsync_bdev(bdev);
+ zram_reset_device(zram);
+
+ mutex_unlock(&bdev->bd_mutex);
+ revalidate_disk(zram->disk);
+ bdput(bdev);
+
+ return len;
+
+out:
+ mutex_unlock(&bdev->bd_mutex);
+ bdput(bdev);
+ return ret;
+}
+
+static void __zram_make_request(struct zram *zram, struct bio *bio)
+{
+ int i, offset, rw;
+ u32 index;
+ struct bio_vec *bvec;
+
+ index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
+ offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
+
+ if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+ zram_bio_discard(zram, index, offset, bio);
+ bio_endio(bio, 0);
+ return;
+ }
+
+ rw = bio_data_dir(bio);
+ bio_for_each_segment(bvec, bio, i) {
+ int max_transfer_size = PAGE_SIZE - offset;
+
+ if (bvec->bv_len > max_transfer_size) {
+ /*
+ * zram_bvec_rw() can only make operation on a single
+ * zram page. Split the bio vector.
+ */
+ struct bio_vec bv;
+
+ bv.bv_page = bvec->bv_page;
+ bv.bv_len = max_transfer_size;
+ bv.bv_offset = bvec->bv_offset;
+
+ if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
+ goto out;
+
+ bv.bv_len = bvec->bv_len - max_transfer_size;
+ bv.bv_offset += max_transfer_size;
+ if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
+ goto out;
+ } else
+ if (zram_bvec_rw(zram, bvec, index, offset, rw) < 0)
+ goto out;
+
+ update_position(&index, &offset, bvec);
+ }
+
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio_endio(bio, 0);
+ return;
+
+out:
+ bio_io_error(bio);
+}
+
+/*
+ * Handler function for all zram I/O requests.
+ */
+static void zram_make_request(struct request_queue *queue, struct bio *bio)
+{
+ struct zram *zram = queue->queuedata;
+
+ if (unlikely(!zram_meta_get(zram)))
+ goto error;
+
+ if (!valid_io_request(zram, bio->bi_sector,
+ bio->bi_size)) {
+ atomic64_inc(&zram->stats.invalid_io);
+ goto put_zram;
+ }
+
+ __zram_make_request(zram, bio);
+ zram_meta_put(zram);
+ return;
+put_zram:
+ zram_meta_put(zram);
+error:
+ bio_io_error(bio);
+}
+
+static void zram_slot_free_notify(struct block_device *bdev,
+ unsigned long index)
+{
+ struct zram *zram;
+ struct zram_meta *meta;
+
+ zram = bdev->bd_disk->private_data;
+ meta = zram->meta;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ atomic64_inc(&zram->stats.notify_free);
+}
+
+static const struct block_device_operations zram_devops = {
+ .swap_slot_free_notify = zram_slot_free_notify,
+ .owner = THIS_MODULE
+};
+
+static DEVICE_ATTR(compact, S_IWUSR, NULL, compact_store);
+static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
+ disksize_show, disksize_store);
+static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
+static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
+static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
+static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
+ mem_limit_store);
+static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
+ mem_used_max_store);
+static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
+ max_comp_streams_show, max_comp_streams_store);
+static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
+ comp_algorithm_show, comp_algorithm_store);
+
+static ssize_t io_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+ ssize_t ret;
+
+ down_read(&zram->init_lock);
+ ret = scnprintf(buf, PAGE_SIZE,
+ "%8llu %8llu %8llu %8llu\n",
+ (u64)atomic64_read(&zram->stats.failed_reads),
+ (u64)atomic64_read(&zram->stats.failed_writes),
+ (u64)atomic64_read(&zram->stats.invalid_io),
+ (u64)atomic64_read(&zram->stats.notify_free));
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+
+static ssize_t mm_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+ u64 orig_size, mem_used = 0;
+ long max_used;
+ ssize_t ret;
+
+ down_read(&zram->init_lock);
+ if (init_done(zram))
+ mem_used = zs_get_total_pages(zram->meta->mem_pool);
+
+ orig_size = atomic64_read(&zram->stats.pages_stored);
+ max_used = atomic_long_read(&zram->stats.max_used_pages);
+
+ ret = scnprintf(buf, PAGE_SIZE,
+ "%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n",
+ orig_size << PAGE_SHIFT,
+ (u64)atomic64_read(&zram->stats.compr_data_size),
+ mem_used << PAGE_SHIFT,
+ zram->limit_pages << PAGE_SHIFT,
+ max_used << PAGE_SHIFT,
+ (u64)atomic64_read(&zram->stats.zero_pages),
+ (u64)atomic64_read(&zram->stats.num_migrated));
+ up_read(&zram->init_lock);
+
+ return ret;
+}
+
+static DEVICE_ATTR(io_stat, S_IRUGO, io_stat_show, NULL);
+static DEVICE_ATTR(mm_stat, S_IRUGO, mm_stat_show, NULL);
+ZRAM_ATTR_RO(num_reads);
+ZRAM_ATTR_RO(num_writes);
+ZRAM_ATTR_RO(failed_reads);
+ZRAM_ATTR_RO(failed_writes);
+ZRAM_ATTR_RO(invalid_io);
+ZRAM_ATTR_RO(notify_free);
+ZRAM_ATTR_RO(zero_pages);
+ZRAM_ATTR_RO(compr_data_size);
+
+static struct attribute *zram_disk_attrs[] = {
+ &dev_attr_disksize.attr,
+ &dev_attr_initstate.attr,
+ &dev_attr_reset.attr,
+ &dev_attr_num_reads.attr,
+ &dev_attr_num_writes.attr,
+ &dev_attr_failed_reads.attr,
+ &dev_attr_failed_writes.attr,
+ &dev_attr_compact.attr,
+ &dev_attr_invalid_io.attr,
+ &dev_attr_notify_free.attr,
+ &dev_attr_zero_pages.attr,
+ &dev_attr_orig_data_size.attr,
+ &dev_attr_compr_data_size.attr,
+ &dev_attr_mem_used_total.attr,
+ &dev_attr_mem_limit.attr,
+ &dev_attr_mem_used_max.attr,
+ &dev_attr_max_comp_streams.attr,
+ &dev_attr_comp_algorithm.attr,
+ &dev_attr_io_stat.attr,
+ &dev_attr_mm_stat.attr,
+ NULL,
+};
+
+static struct attribute_group zram_disk_attr_group = {
+ .attrs = zram_disk_attrs,
+};
+
+static int create_device(struct zram *zram, int device_id)
+{
+ struct request_queue *queue;
+ int ret = -ENOMEM;
+
+ init_rwsem(&zram->init_lock);
+
+ queue = blk_alloc_queue(GFP_KERNEL);
+ if (!queue) {
+ pr_err("Error allocating disk queue for device %d\n",
+ device_id);
+ goto out;
+ }
+
+ blk_queue_make_request(queue, zram_make_request);
+
+ /* gendisk structure */
+ zram->disk = alloc_disk(1);
+ if (!zram->disk) {
+ pr_warn("Error allocating disk structure for device %d\n",
+ device_id);
+ ret = -ENOMEM;
+ goto out_free_queue;
+ }
+
+ zram->disk->major = zram_major;
+ zram->disk->first_minor = device_id;
+ zram->disk->fops = &zram_devops;
+ zram->disk->queue = queue;
+ zram->disk->queue->queuedata = zram;
+ zram->disk->private_data = zram;
+ snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
+
+ /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
+ set_capacity(zram->disk, 0);
+ /* zram devices sort of resembles non-rotational disks */
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
+ /*
+ * To ensure that we always get PAGE_SIZE aligned
+ * and n*PAGE_SIZED sized I/O requests.
+ */
+ blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
+ blk_queue_logical_block_size(zram->disk->queue,
+ ZRAM_LOGICAL_BLOCK_SIZE);
+ blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
+ blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
+ zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+ zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
+ /*
+ * zram_bio_discard() will clear all logical blocks if logical block
+ * size is identical with physical block size(PAGE_SIZE). But if it is
+ * different, we will skip discarding some parts of logical blocks in
+ * the part of the request range which isn't aligned to physical block
+ * size. So we can't ensure that all discarded logical blocks are
+ * zeroed.
+ */
+ if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
+ zram->disk->queue->limits.discard_zeroes_data = 1;
+ else
+ zram->disk->queue->limits.discard_zeroes_data = 0;
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
+ add_disk(zram->disk);
+
+ ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+ if (ret < 0) {
+ pr_warn("Error creating sysfs group");
+ goto out_free_disk;
+ }
+ strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
+ zram->meta = NULL;
+ zram->max_comp_streams = 1;
+ return 0;
+
+out_free_disk:
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+out_free_queue:
+ blk_cleanup_queue(queue);
+out:
+ return ret;
+}
+
+static void destroy_devices(unsigned int nr)
+{
+ struct zram *zram;
+ unsigned int i;
+
+ for (i = 0; i < nr; i++) {
+ zram = &zram_devices[i];
+ /*
+ * Remove sysfs first, so no one will perform a disksize
+ * store while we destroy the devices
+ */
+ sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+
+ zram_reset_device(zram);
+
+ blk_cleanup_queue(zram->disk->queue);
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+ }
+
+ kfree(zram_devices);
+ unregister_blkdev(zram_major, "zram");
+ pr_info("Destroyed %u device(s)\n", nr);
+}
+
+static int __init zram_init(void)
+{
+ int ret, dev_id;
+
+ if (num_devices > max_num_devices) {
+ pr_warn("Invalid value for num_devices: %u\n",
+ num_devices);
+ return -EINVAL;
+ }
+
+ zram_major = register_blkdev(0, "zram");
+ if (zram_major <= 0) {
+ pr_warn("Unable to get major number\n");
+ return -EBUSY;
+ }
+
+ /* Allocate the device array and initialize each one */
+ zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
+ if (!zram_devices) {
+ unregister_blkdev(zram_major, "zram");
+ return -ENOMEM;
+ }
+
+ for (dev_id = 0; dev_id < num_devices; dev_id++) {
+ ret = create_device(&zram_devices[dev_id], dev_id);
+ if (ret)
+ goto out_error;
+ }
+
+ pr_info("Created %u device(s)\n", num_devices);
+ return 0;
+
+out_error:
+ destroy_devices(dev_id);
+ return ret;
+}
+
+static void __exit zram_exit(void)
+{
+ destroy_devices(num_devices);
+}
+
+module_init(zram_init);
+module_exit(zram_exit);
+
+module_param(num_devices, uint, 0);
+MODULE_PARM_DESC(num_devices, "Number of zram devices");
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
+MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
new file mode 100644
index 0000000..4269498
--- /dev/null
+++ b/drivers/block/zram/zram_drv.h
@@ -0,0 +1,126 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#ifndef _ZRAM_DRV_H_
+#define _ZRAM_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/zsmalloc.h>
+
+#include "zcomp.h"
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*-- Configurable parameters */
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
+ * always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT 9
+#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
+#define ZRAM_LOGICAL_BLOCK_SHIFT 12
+#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
+#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
+ (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
+
+
+/*
+ * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * object size (excluding header), the higher bits is for
+ * zram_pageflags.
+ *
+ * zram is mainly used for memory efficiency so we want to keep memory
+ * footprint small so we can squeeze size and flags into a field.
+ * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
+ * the higher bits is for zram_pageflags.
+ */
+#define ZRAM_FLAG_SHIFT 24
+
+/* Flags for zram pages (table[page_no].value) */
+enum zram_pageflags {
+ /* Page consists entirely of zeros */
+ ZRAM_ZERO = ZRAM_FLAG_SHIFT,
+ ZRAM_ACCESS, /* page is now accessed */
+
+ __NR_ZRAM_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/* Allocated for each disk page */
+struct zram_table_entry {
+ unsigned long handle;
+ unsigned long value;
+};
+
+struct zram_stats {
+ atomic64_t compr_data_size; /* compressed size of pages stored */
+ atomic64_t num_reads; /* failed + successful */
+ atomic64_t num_writes; /* --do-- */
+ atomic64_t num_migrated; /* no. of migrated object */
+ atomic64_t failed_reads; /* can happen when memory is too low */
+ atomic64_t failed_writes; /* can happen when memory is too low */
+ atomic64_t invalid_io; /* non-page-aligned I/O requests */
+ atomic64_t notify_free; /* no. of swap slot free notifications */
+ atomic64_t zero_pages; /* no. of zero filled pages */
+ atomic64_t pages_stored; /* no. of pages currently stored */
+ atomic_long_t max_used_pages; /* no. of maximum pages stored */
+};
+
+struct zram_meta {
+ struct zram_table_entry *table;
+ struct zs_pool *mem_pool;
+};
+
+struct zram {
+ struct zram_meta *meta;
+ struct zcomp *comp;
+ struct gendisk *disk;
+ /* Prevent concurrent execution of device init */
+ struct rw_semaphore init_lock;
+ /*
+ * the number of pages zram can consume for storing compressed data
+ */
+ unsigned long limit_pages;
+ int max_comp_streams;
+
+ struct zram_stats stats;
+ atomic_t refcount; /* refcount for zram_meta */
+ /* wait all IO under all of cpu are done */
+ wait_queue_head_t io_done;
+ /*
+ * This is the limit on amount of *uncompressed* worth of data
+ * we can store in a disk.
+ */
+ u64 disksize; /* bytes */
+ char compressor[10];
+};
+
+#endif
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 3bb6fa3..6fcb9b0 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -6,6 +6,19 @@
source "drivers/tty/Kconfig"
+config DEVMEM
+ bool "Memory device driver"
+ default y
+ help
+ The memory driver provides two character devices, mem and kmem, which
+ provide access to the system's memory. The mem device is a view of
+ physical memory, and each byte in the device corresponds to the
+ matching physical address. The kmem device is the same as mem, but
+ the addresses correspond to the kernel's virtual address space rather
+ than physical memory. These devices are standard parts of a Linux
+ system and most users should say Y here. You might say N if very
+ security conscience or memory is tight.
+
config DEVKMEM
bool "/dev/kmem virtual device support"
default y
@@ -584,6 +597,10 @@
depends on ISA || PCI
default y
+config DCC_TTY
+ tristate "DCC tty driver"
+ depends on ARM
+
source "drivers/s390/char/Kconfig"
config MSM_SMD_PKT
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index 7ff1d0d..e0047ed 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -56,6 +56,7 @@
obj-$(CONFIG_HANGCHECK_TIMER) += hangcheck-timer.o
obj-$(CONFIG_TCG_TPM) += tpm/
+obj-$(CONFIG_DCC_TTY) += dcc_tty.o
obj-$(CONFIG_PS3_FLASH) += ps3flash.o
obj-$(CONFIG_JS_RTC) += js-rtc.o
diff --git a/drivers/char/dcc_tty.c b/drivers/char/dcc_tty.c
new file mode 100644
index 0000000..a787acc
--- /dev/null
+++ b/drivers/char/dcc_tty.c
@@ -0,0 +1,326 @@
+/* drivers/char/dcc_tty.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/console.h>
+#include <linux/hrtimer.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+
+MODULE_DESCRIPTION("DCC TTY Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+
+static spinlock_t g_dcc_tty_lock = SPIN_LOCK_UNLOCKED;
+static struct hrtimer g_dcc_timer;
+static char g_dcc_buffer[16];
+static int g_dcc_buffer_head;
+static int g_dcc_buffer_count;
+static unsigned g_dcc_write_delay_usecs = 1;
+static struct tty_driver *g_dcc_tty_driver;
+static struct tty_struct *g_dcc_tty;
+static int g_dcc_tty_open_count;
+
+static void dcc_poll_locked(void)
+{
+ char ch;
+ int rch;
+ int written;
+
+ while (g_dcc_buffer_count) {
+ ch = g_dcc_buffer[g_dcc_buffer_head];
+ asm(
+ "mrc 14, 0, r15, c0, c1, 0\n"
+ "mcrcc 14, 0, %1, c0, c5, 0\n"
+ "movcc %0, #1\n"
+ "movcs %0, #0\n"
+ : "=r" (written)
+ : "r" (ch)
+ );
+ if (written) {
+ if (ch == '\n')
+ g_dcc_buffer[g_dcc_buffer_head] = '\r';
+ else {
+ g_dcc_buffer_head = (g_dcc_buffer_head + 1) % ARRAY_SIZE(g_dcc_buffer);
+ g_dcc_buffer_count--;
+ if (g_dcc_tty)
+ tty_wakeup(g_dcc_tty);
+ }
+ g_dcc_write_delay_usecs = 1;
+ } else {
+ if (g_dcc_write_delay_usecs > 0x100)
+ break;
+ g_dcc_write_delay_usecs <<= 1;
+ udelay(g_dcc_write_delay_usecs);
+ }
+ }
+
+ if (g_dcc_tty && !test_bit(TTY_THROTTLED, &g_dcc_tty->flags)) {
+ asm(
+ "mrc 14, 0, %0, c0, c1, 0\n"
+ "tst %0, #(1 << 30)\n"
+ "moveq %0, #-1\n"
+ "mrcne 14, 0, %0, c0, c5, 0\n"
+ : "=r" (rch)
+ );
+ if (rch >= 0) {
+ ch = rch;
+ tty_insert_flip_string(g_dcc_tty, &ch, 1);
+ tty_flip_buffer_push(g_dcc_tty);
+ }
+ }
+
+
+ if (g_dcc_buffer_count)
+ hrtimer_start(&g_dcc_timer, ktime_set(0, g_dcc_write_delay_usecs * NSEC_PER_USEC), HRTIMER_MODE_REL);
+ else
+ hrtimer_start(&g_dcc_timer, ktime_set(0, 20 * NSEC_PER_MSEC), HRTIMER_MODE_REL);
+}
+
+static int dcc_tty_open(struct tty_struct * tty, struct file * filp)
+{
+ int ret;
+ unsigned long irq_flags;
+
+ spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+ if (g_dcc_tty == NULL || g_dcc_tty == tty) {
+ g_dcc_tty = tty;
+ g_dcc_tty_open_count++;
+ ret = 0;
+ } else
+ ret = -EBUSY;
+ spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+
+ printk("dcc_tty_open, tty %p, f_flags %x, returned %d\n", tty, filp->f_flags, ret);
+
+ return ret;
+}
+
+static void dcc_tty_close(struct tty_struct * tty, struct file * filp)
+{
+ printk("dcc_tty_close, tty %p, f_flags %x\n", tty, filp->f_flags);
+ if (g_dcc_tty == tty) {
+ if (--g_dcc_tty_open_count == 0)
+ g_dcc_tty = NULL;
+ }
+}
+
+static int dcc_write(const unsigned char *buf_start, int count)
+{
+ const unsigned char *buf = buf_start;
+ unsigned long irq_flags;
+ int copy_len;
+ int space_left;
+ int tail;
+
+ if (count < 1)
+ return 0;
+
+ spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+ do {
+ tail = (g_dcc_buffer_head + g_dcc_buffer_count) % ARRAY_SIZE(g_dcc_buffer);
+ copy_len = ARRAY_SIZE(g_dcc_buffer) - tail;
+ space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+ if (copy_len > space_left)
+ copy_len = space_left;
+ if (copy_len > count)
+ copy_len = count;
+ memcpy(&g_dcc_buffer[tail], buf, copy_len);
+ g_dcc_buffer_count += copy_len;
+ buf += copy_len;
+ count -= copy_len;
+ if (copy_len < count && copy_len < space_left) {
+ space_left -= copy_len;
+ copy_len = count;
+ if (copy_len > space_left) {
+ copy_len = space_left;
+ }
+ memcpy(g_dcc_buffer, buf, copy_len);
+ buf += copy_len;
+ count -= copy_len;
+ g_dcc_buffer_count += copy_len;
+ }
+ dcc_poll_locked();
+ space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+ } while(count && space_left);
+ spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+ return buf - buf_start;
+}
+
+static int dcc_tty_write(struct tty_struct * tty, const unsigned char *buf, int count)
+{
+ int ret;
+ /* printk("dcc_tty_write %p, %d\n", buf, count); */
+ ret = dcc_write(buf, count);
+ if (ret != count)
+ printk("dcc_tty_write %p, %d, returned %d\n", buf, count, ret);
+ return ret;
+}
+
+static int dcc_tty_write_room(struct tty_struct *tty)
+{
+ int space_left;
+ unsigned long irq_flags;
+
+ spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+ space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+ spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+ return space_left;
+}
+
+static int dcc_tty_chars_in_buffer(struct tty_struct *tty)
+{
+ int ret;
+ asm(
+ "mrc 14, 0, %0, c0, c1, 0\n"
+ "mov %0, %0, LSR #30\n"
+ "and %0, %0, #1\n"
+ : "=r" (ret)
+ );
+ return ret;
+}
+
+static void dcc_tty_unthrottle(struct tty_struct * tty)
+{
+ unsigned long irq_flags;
+
+ spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+ dcc_poll_locked();
+ spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+}
+
+static enum hrtimer_restart dcc_tty_timer_func(struct hrtimer *timer)
+{
+ unsigned long irq_flags;
+
+ spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+ dcc_poll_locked();
+ spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+ return HRTIMER_NORESTART;
+}
+
+void dcc_console_write(struct console *co, const char *b, unsigned count)
+{
+#if 1
+ dcc_write(b, count);
+#else
+ /* blocking printk */
+ while (count > 0) {
+ int written;
+ written = dcc_write(b, count);
+ if (written) {
+ b += written;
+ count -= written;
+ }
+ }
+#endif
+}
+
+static struct tty_driver *dcc_console_device(struct console *c, int *index)
+{
+ *index = 0;
+ return g_dcc_tty_driver;
+}
+
+static int __init dcc_console_setup(struct console *co, char *options)
+{
+ if (co->index != 0)
+ return -ENODEV;
+ return 0;
+}
+
+
+static struct console dcc_console =
+{
+ .name = "ttyDCC",
+ .write = dcc_console_write,
+ .device = dcc_console_device,
+ .setup = dcc_console_setup,
+ .flags = CON_PRINTBUFFER,
+ .index = -1,
+};
+
+static struct tty_operations dcc_tty_ops = {
+ .open = dcc_tty_open,
+ .close = dcc_tty_close,
+ .write = dcc_tty_write,
+ .write_room = dcc_tty_write_room,
+ .chars_in_buffer = dcc_tty_chars_in_buffer,
+ .unthrottle = dcc_tty_unthrottle,
+};
+
+static int __init dcc_tty_init(void)
+{
+ int ret;
+
+ hrtimer_init(&g_dcc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ g_dcc_timer.function = dcc_tty_timer_func;
+
+ g_dcc_tty_driver = alloc_tty_driver(1);
+ if (!g_dcc_tty_driver) {
+ printk(KERN_ERR "dcc_tty_probe: alloc_tty_driver failed\n");
+ ret = -ENOMEM;
+ goto err_alloc_tty_driver_failed;
+ }
+ g_dcc_tty_driver->owner = THIS_MODULE;
+ g_dcc_tty_driver->driver_name = "dcc";
+ g_dcc_tty_driver->name = "ttyDCC";
+ g_dcc_tty_driver->major = 0; // auto assign
+ g_dcc_tty_driver->minor_start = 0;
+ g_dcc_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
+ g_dcc_tty_driver->subtype = SERIAL_TYPE_NORMAL;
+ g_dcc_tty_driver->init_termios = tty_std_termios;
+ g_dcc_tty_driver->flags = TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
+ tty_set_operations(g_dcc_tty_driver, &dcc_tty_ops);
+ ret = tty_register_driver(g_dcc_tty_driver);
+ if (ret) {
+ printk(KERN_ERR "dcc_tty_probe: tty_register_driver failed, %d\n", ret);
+ goto err_tty_register_driver_failed;
+ }
+ tty_register_device(g_dcc_tty_driver, 0, NULL);
+
+ register_console(&dcc_console);
+ hrtimer_start(&g_dcc_timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+
+ return 0;
+
+err_tty_register_driver_failed:
+ put_tty_driver(g_dcc_tty_driver);
+ g_dcc_tty_driver = NULL;
+err_alloc_tty_driver_failed:
+ return ret;
+}
+
+static void __exit dcc_tty_exit(void)
+{
+ int ret;
+
+ tty_unregister_device(g_dcc_tty_driver, 0);
+ ret = tty_unregister_driver(g_dcc_tty_driver);
+ if (ret < 0) {
+ printk(KERN_ERR "dcc_tty_remove: tty_unregister_driver failed, %d\n", ret);
+ } else {
+ put_tty_driver(g_dcc_tty_driver);
+ }
+ g_dcc_tty_driver = NULL;
+}
+
+module_init(dcc_tty_init);
+module_exit(dcc_tty_exit);
+
+
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 1ccbe94..38d3069 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -60,6 +60,7 @@
}
#endif
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)
#ifdef CONFIG_STRICT_DEVMEM
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
@@ -85,7 +86,9 @@
return 1;
}
#endif
+#endif
+#ifdef CONFIG_DEVMEM
void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
{
}
@@ -212,6 +215,9 @@
*ppos += written;
return written;
}
+#endif /* CONFIG_DEVMEM */
+
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)
int __weak phys_mem_access_prot_allowed(struct file *file,
unsigned long pfn, unsigned long size, pgprot_t *vma_prot)
@@ -333,6 +339,7 @@
}
return 0;
}
+#endif /* CONFIG_DEVMEM */
#ifdef CONFIG_DEVKMEM
static int mmap_kmem(struct file *file, struct vm_area_struct *vma)
@@ -727,6 +734,8 @@
return file->f_pos = 0;
}
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)
+
/*
* The memory devices use the full 32/64 bits of the offset, and so we cannot
* check against negative addresses: they are ok. The return value is weird,
@@ -760,10 +769,14 @@
return ret;
}
+#endif
+
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)
static int open_port(struct inode *inode, struct file *filp)
{
return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
}
+#endif
#define zero_lseek null_lseek
#define full_lseek null_lseek
@@ -774,6 +787,7 @@
#define open_kmem open_mem
#define open_oldmem open_mem
+#ifdef CONFIG_DEVMEM
static const struct file_operations mem_fops = {
.llseek = memory_lseek,
.read = read_mem,
@@ -782,6 +796,7 @@
.open = open_mem,
.get_unmapped_area = get_unmapped_area_mem,
};
+#endif
#ifdef CONFIG_DEVKMEM
static const struct file_operations kmem_fops = {
@@ -851,7 +866,9 @@
const struct file_operations *fops;
struct backing_dev_info *dev_info;
} devlist[] = {
+#ifdef CONFIG_DEVMEM
[1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+#endif
#ifdef CONFIG_DEVKMEM
[2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
#endif
diff --git a/drivers/char/random.c b/drivers/char/random.c
index aee3464..b223267 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1495,6 +1495,28 @@
EXPORT_SYMBOL(get_random_int);
/*
+ * Same as get_random_int(), but returns unsigned long.
+ */
+unsigned long get_random_long(void)
+{
+ __u32 *hash;
+ unsigned long ret;
+
+ if (arch_get_random_long(&ret))
+ return ret;
+
+ hash = get_cpu_var(get_random_int_hash);
+
+ hash[0] += current->pid + jiffies + get_cycles();
+ md5_transform(hash, random_int_secret);
+ ret = *(unsigned long *)hash;
+ put_cpu_var(get_random_int_hash);
+
+ return ret;
+}
+EXPORT_SYMBOL(get_random_long);
+
+/*
* randomize_range() returns a start address such that
*
* [...... <range> .....]
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 534fcb8..62236d6 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -102,6 +102,16 @@
Be aware that not all cpufreq drivers support the conservative
governor. If unsure have a look at the help section of the
driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+ bool "interactive"
+ select CPU_FREQ_GOV_INTERACTIVE
+ help
+ Use the CPUFreq governor 'interactive' as default. This allows
+ you to get a full dynamic cpu frequency capable system by simply
+ loading your cpufreq low-level hardware driver, using the
+ 'interactive' governor for latency-sensitive workloads.
+
endchoice
config CPU_FREQ_GOV_PERFORMANCE
@@ -160,6 +170,23 @@
If in doubt, say N.
+config CPU_FREQ_GOV_INTERACTIVE
+ tristate "'interactive' cpufreq policy governor"
+ help
+ 'interactive' - This driver adds a dynamic cpufreq policy governor
+ designed for latency-sensitive workloads.
+
+ This governor attempts to reduce the latency of clock
+ increases so that the system is more responsive to
+ interactive workloads.
+
+ To compile this driver as a module, choose M here: the
+ module will be called cpufreq_interactive.
+
+ For details, take a look at linux/Documentation/cpu-freq.
+
+ If in doubt, say N.
+
config CPU_FREQ_GOV_CONSERVATIVE
tristate "'conservative' cpufreq governor"
depends on CPU_FREQ
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 3b95322..0cece06 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -9,6 +9,7 @@
obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE) += cpufreq_userspace.o
obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND) += cpufreq_ondemand.o
obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE) += cpufreq_conservative.o
+obj-$(CONFIG_CPU_FREQ_GOV_INTERACTIVE) += cpufreq_interactive.o
obj-$(CONFIG_CPU_FREQ_GOV_COMMON) += cpufreq_governor.o
# CPUfreq cross-arch helpers
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 66f6cf5..bad5ef1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -133,6 +133,16 @@
{
return cpufreq_driver->have_governor_per_policy;
}
+EXPORT_SYMBOL_GPL(have_governor_per_policy);
+
+struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
+{
+ if (have_governor_per_policy())
+ return &policy->kobj;
+ else
+ return cpufreq_global_kobject;
+}
+EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs)
{
@@ -1736,6 +1746,7 @@
data->min = policy->min;
data->max = policy->max;
+ trace_cpu_frequency_limits(policy->max, policy->min, policy->cpu);
pr_debug("new min and max freqs are %u - %u kHz\n",
data->min, data->max);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 27b0e2a..7c4c1cc 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -29,14 +29,6 @@
#include "cpufreq_governor.h"
-static struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
-{
- if (have_governor_per_policy())
- return &policy->kobj;
- else
- return cpufreq_global_kobject;
-}
-
static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
{
if (have_governor_per_policy())
@@ -396,6 +388,7 @@
mutex_lock(&dbs_data->mutex);
mutex_destroy(&cpu_cdbs->timer_mutex);
+ cpu_cdbs->cur_policy = NULL;
mutex_unlock(&dbs_data->mutex);
diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c
new file mode 100644
index 0000000..0654e40
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_interactive.c
@@ -0,0 +1,1414 @@
+/*
+ * drivers/cpufreq/cpufreq_interactive.c
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ *
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/tick.h>
+#include <linux/time.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/kernel_stat.h>
+#include <asm/cputime.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/cpufreq_interactive.h>
+
+struct cpufreq_interactive_cpuinfo {
+ struct timer_list cpu_timer;
+ struct timer_list cpu_slack_timer;
+ spinlock_t load_lock; /* protects the next 4 fields */
+ u64 time_in_idle;
+ u64 time_in_idle_timestamp;
+ u64 cputime_speedadj;
+ u64 cputime_speedadj_timestamp;
+ struct cpufreq_policy *policy;
+ struct cpufreq_frequency_table *freq_table;
+ spinlock_t target_freq_lock; /*protects target freq */
+ unsigned int target_freq;
+ unsigned int floor_freq;
+ unsigned int max_freq;
+ u64 floor_validate_time;
+ u64 hispeed_validate_time;
+ struct rw_semaphore enable_sem;
+ int governor_enabled;
+};
+
+static DEFINE_PER_CPU(struct cpufreq_interactive_cpuinfo, cpuinfo);
+
+/* realtime thread handles frequency scaling */
+static struct task_struct *speedchange_task;
+static cpumask_t speedchange_cpumask;
+static spinlock_t speedchange_cpumask_lock;
+static struct mutex gov_lock;
+
+/* Target load. Lower values result in higher CPU speeds. */
+#define DEFAULT_TARGET_LOAD 90
+static unsigned int default_target_loads[] = {DEFAULT_TARGET_LOAD};
+
+#define DEFAULT_TIMER_RATE (20 * USEC_PER_MSEC)
+#define DEFAULT_ABOVE_HISPEED_DELAY DEFAULT_TIMER_RATE
+static unsigned int default_above_hispeed_delay[] = {
+ DEFAULT_ABOVE_HISPEED_DELAY };
+
+struct cpufreq_interactive_tunables {
+ int usage_count;
+ /* Hi speed to bump to from lo speed when load burst (default max) */
+ unsigned int hispeed_freq;
+ /* Go to hi speed when CPU load at or above this value. */
+#define DEFAULT_GO_HISPEED_LOAD 99
+ unsigned long go_hispeed_load;
+ /* Target load. Lower values result in higher CPU speeds. */
+ spinlock_t target_loads_lock;
+ unsigned int *target_loads;
+ int ntarget_loads;
+ /*
+ * The minimum amount of time to spend at a frequency before we can ramp
+ * down.
+ */
+#define DEFAULT_MIN_SAMPLE_TIME (80 * USEC_PER_MSEC)
+ unsigned long min_sample_time;
+ /*
+ * The sample rate of the timer used to increase frequency
+ */
+ unsigned long timer_rate;
+ /*
+ * Wait this long before raising speed above hispeed, by default a
+ * single timer interval.
+ */
+ spinlock_t above_hispeed_delay_lock;
+ unsigned int *above_hispeed_delay;
+ int nabove_hispeed_delay;
+ /* Non-zero means indefinite speed boost active */
+ int boost_val;
+ /* Duration of a boot pulse in usecs */
+ int boostpulse_duration_val;
+ /* End time of boost pulse in ktime converted to usecs */
+ u64 boostpulse_endtime;
+ bool boosted;
+ /*
+ * Max additional time to wait in idle, beyond timer_rate, at speeds
+ * above minimum before wakeup to reduce speed, or -1 if unnecessary.
+ */
+#define DEFAULT_TIMER_SLACK (4 * DEFAULT_TIMER_RATE)
+ int timer_slack_val;
+ bool io_is_busy;
+};
+
+/* For cases where we have single governor instance for system */
+static struct cpufreq_interactive_tunables *common_tunables;
+
+static struct attribute_group *get_sysfs_attr(void);
+
+static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
+ cputime64_t *wall)
+{
+ u64 idle_time;
+ u64 cur_wall_time;
+ u64 busy_time;
+
+ cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+
+ busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
+ busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
+ busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
+ busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
+ busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
+ busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+
+ idle_time = cur_wall_time - busy_time;
+ if (wall)
+ *wall = jiffies_to_usecs(cur_wall_time);
+
+ return jiffies_to_usecs(idle_time);
+}
+
+static inline cputime64_t get_cpu_idle_time(
+ unsigned int cpu,
+ cputime64_t *wall,
+ bool io_is_busy)
+{
+ u64 idle_time = get_cpu_idle_time_us(cpu, wall);
+
+ if (idle_time == -1ULL)
+ idle_time = get_cpu_idle_time_jiffy(cpu, wall);
+ else if (!io_is_busy)
+ idle_time += get_cpu_iowait_time_us(cpu, wall);
+
+ return idle_time;
+}
+
+static void cpufreq_interactive_timer_resched(
+ struct cpufreq_interactive_cpuinfo *pcpu)
+{
+ struct cpufreq_interactive_tunables *tunables =
+ pcpu->policy->governor_data;
+ unsigned long expires;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pcpu->load_lock, flags);
+ pcpu->time_in_idle =
+ get_cpu_idle_time(smp_processor_id(),
+ &pcpu->time_in_idle_timestamp,
+ tunables->io_is_busy);
+ pcpu->cputime_speedadj = 0;
+ pcpu->cputime_speedadj_timestamp = pcpu->time_in_idle_timestamp;
+ expires = jiffies + usecs_to_jiffies(tunables->timer_rate);
+ mod_timer_pinned(&pcpu->cpu_timer, expires);
+
+ if (tunables->timer_slack_val >= 0 &&
+ pcpu->target_freq > pcpu->policy->min) {
+ expires += usecs_to_jiffies(tunables->timer_slack_val);
+ mod_timer_pinned(&pcpu->cpu_slack_timer, expires);
+ }
+
+ spin_unlock_irqrestore(&pcpu->load_lock, flags);
+}
+
+/* The caller shall take enable_sem write semaphore to avoid any timer race.
+ * The cpu_timer and cpu_slack_timer must be deactivated when calling this
+ * function.
+ */
+static void cpufreq_interactive_timer_start(
+ struct cpufreq_interactive_tunables *tunables, int cpu)
+{
+ struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, cpu);
+ unsigned long expires = jiffies +
+ usecs_to_jiffies(tunables->timer_rate);
+ unsigned long flags;
+
+ pcpu->cpu_timer.expires = expires;
+ add_timer_on(&pcpu->cpu_timer, cpu);
+ if (tunables->timer_slack_val >= 0 &&
+ pcpu->target_freq > pcpu->policy->min) {
+ expires += usecs_to_jiffies(tunables->timer_slack_val);
+ pcpu->cpu_slack_timer.expires = expires;
+ add_timer_on(&pcpu->cpu_slack_timer, cpu);
+ }
+
+ spin_lock_irqsave(&pcpu->load_lock, flags);
+ pcpu->time_in_idle =
+ get_cpu_idle_time(cpu, &pcpu->time_in_idle_timestamp,
+ tunables->io_is_busy);
+ pcpu->cputime_speedadj = 0;
+ pcpu->cputime_speedadj_timestamp = pcpu->time_in_idle_timestamp;
+ spin_unlock_irqrestore(&pcpu->load_lock, flags);
+}
+
+static unsigned int freq_to_above_hispeed_delay(
+ struct cpufreq_interactive_tunables *tunables,
+ unsigned int freq)
+{
+ int i;
+ unsigned int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+ for (i = 0; i < tunables->nabove_hispeed_delay - 1 &&
+ freq >= tunables->above_hispeed_delay[i+1]; i += 2)
+ ;
+
+ ret = tunables->above_hispeed_delay[i];
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+ return ret;
+}
+
+static unsigned int freq_to_targetload(
+ struct cpufreq_interactive_tunables *tunables, unsigned int freq)
+{
+ int i;
+ unsigned int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+ for (i = 0; i < tunables->ntarget_loads - 1 &&
+ freq >= tunables->target_loads[i+1]; i += 2)
+ ;
+
+ ret = tunables->target_loads[i];
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+ return ret;
+}
+
+/*
+ * If increasing frequencies never map to a lower target load then
+ * choose_freq() will find the minimum frequency that does not exceed its
+ * target load given the current load.
+ */
+static unsigned int choose_freq(struct cpufreq_interactive_cpuinfo *pcpu,
+ unsigned int loadadjfreq)
+{
+ unsigned int freq = pcpu->policy->cur;
+ unsigned int prevfreq, freqmin, freqmax;
+ unsigned int tl;
+ int index;
+
+ freqmin = 0;
+ freqmax = UINT_MAX;
+
+ do {
+ prevfreq = freq;
+ tl = freq_to_targetload(pcpu->policy->governor_data, freq);
+
+ /*
+ * Find the lowest frequency where the computed load is less
+ * than or equal to the target load.
+ */
+
+ if (cpufreq_frequency_table_target(
+ pcpu->policy, pcpu->freq_table, loadadjfreq / tl,
+ CPUFREQ_RELATION_L, &index))
+ break;
+ freq = pcpu->freq_table[index].frequency;
+
+ if (freq > prevfreq) {
+ /* The previous frequency is too low. */
+ freqmin = prevfreq;
+
+ if (freq >= freqmax) {
+ /*
+ * Find the highest frequency that is less
+ * than freqmax.
+ */
+ if (cpufreq_frequency_table_target(
+ pcpu->policy, pcpu->freq_table,
+ freqmax - 1, CPUFREQ_RELATION_H,
+ &index))
+ break;
+ freq = pcpu->freq_table[index].frequency;
+
+ if (freq == freqmin) {
+ /*
+ * The first frequency below freqmax
+ * has already been found to be too
+ * low. freqmax is the lowest speed
+ * we found that is fast enough.
+ */
+ freq = freqmax;
+ break;
+ }
+ }
+ } else if (freq < prevfreq) {
+ /* The previous frequency is high enough. */
+ freqmax = prevfreq;
+
+ if (freq <= freqmin) {
+ /*
+ * Find the lowest frequency that is higher
+ * than freqmin.
+ */
+ if (cpufreq_frequency_table_target(
+ pcpu->policy, pcpu->freq_table,
+ freqmin + 1, CPUFREQ_RELATION_L,
+ &index))
+ break;
+ freq = pcpu->freq_table[index].frequency;
+
+ /*
+ * If freqmax is the first frequency above
+ * freqmin then we have already found that
+ * this speed is fast enough.
+ */
+ if (freq == freqmax)
+ break;
+ }
+ }
+
+ /* If same frequency chosen as previous then done. */
+ } while (freq != prevfreq);
+
+ return freq;
+}
+
+static u64 update_load(int cpu)
+{
+ struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, cpu);
+ struct cpufreq_interactive_tunables *tunables =
+ pcpu->policy->governor_data;
+ u64 now;
+ u64 now_idle;
+ unsigned int delta_idle;
+ unsigned int delta_time;
+ u64 active_time;
+
+ now_idle = get_cpu_idle_time(cpu, &now, tunables->io_is_busy);
+ delta_idle = (unsigned int)(now_idle - pcpu->time_in_idle);
+ delta_time = (unsigned int)(now - pcpu->time_in_idle_timestamp);
+
+ if (delta_time <= delta_idle)
+ active_time = 0;
+ else
+ active_time = delta_time - delta_idle;
+
+ pcpu->cputime_speedadj += active_time * pcpu->policy->cur;
+
+ pcpu->time_in_idle = now_idle;
+ pcpu->time_in_idle_timestamp = now;
+ return now;
+}
+
+static void cpufreq_interactive_timer(unsigned long data)
+{
+ u64 now;
+ unsigned int delta_time;
+ u64 cputime_speedadj;
+ int cpu_load;
+ struct cpufreq_interactive_cpuinfo *pcpu =
+ &per_cpu(cpuinfo, data);
+ struct cpufreq_interactive_tunables *tunables =
+ pcpu->policy->governor_data;
+ unsigned int new_freq;
+ unsigned int loadadjfreq;
+ unsigned int index;
+ unsigned long flags;
+
+ if (!down_read_trylock(&pcpu->enable_sem))
+ return;
+ if (!pcpu->governor_enabled)
+ goto exit;
+
+ spin_lock_irqsave(&pcpu->load_lock, flags);
+ now = update_load(data);
+ delta_time = (unsigned int)(now - pcpu->cputime_speedadj_timestamp);
+ cputime_speedadj = pcpu->cputime_speedadj;
+ spin_unlock_irqrestore(&pcpu->load_lock, flags);
+
+ if (WARN_ON_ONCE(!delta_time))
+ goto rearm;
+
+ spin_lock_irqsave(&pcpu->target_freq_lock, flags);
+ do_div(cputime_speedadj, delta_time);
+ loadadjfreq = (unsigned int)cputime_speedadj * 100;
+ cpu_load = loadadjfreq / pcpu->policy->cur;
+ tunables->boosted = tunables->boost_val || now < tunables->boostpulse_endtime;
+
+ if (cpu_load >= tunables->go_hispeed_load || tunables->boosted) {
+ if (pcpu->target_freq < tunables->hispeed_freq) {
+ new_freq = tunables->hispeed_freq;
+ } else {
+ new_freq = choose_freq(pcpu, loadadjfreq);
+
+ if (new_freq < tunables->hispeed_freq)
+ new_freq = tunables->hispeed_freq;
+ }
+ } else {
+ new_freq = choose_freq(pcpu, loadadjfreq);
+ if (new_freq > tunables->hispeed_freq &&
+ pcpu->target_freq < tunables->hispeed_freq)
+ new_freq = tunables->hispeed_freq;
+ }
+
+ if (pcpu->target_freq >= tunables->hispeed_freq &&
+ new_freq > pcpu->target_freq &&
+ now - pcpu->hispeed_validate_time <
+ freq_to_above_hispeed_delay(tunables, pcpu->target_freq)) {
+ trace_cpufreq_interactive_notyet(
+ data, cpu_load, pcpu->target_freq,
+ pcpu->policy->cur, new_freq);
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ goto rearm;
+ }
+
+ pcpu->hispeed_validate_time = now;
+
+ if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table,
+ new_freq, CPUFREQ_RELATION_L,
+ &index)) {
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ goto rearm;
+ }
+
+ new_freq = pcpu->freq_table[index].frequency;
+
+ /*
+ * Do not scale below floor_freq unless we have been at or above the
+ * floor frequency for the minimum sample time since last validated.
+ */
+ if (new_freq < pcpu->floor_freq) {
+ if (now - pcpu->floor_validate_time <
+ tunables->min_sample_time) {
+ trace_cpufreq_interactive_notyet(
+ data, cpu_load, pcpu->target_freq,
+ pcpu->policy->cur, new_freq);
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ goto rearm;
+ }
+ }
+
+ /*
+ * Update the timestamp for checking whether speed has been held at
+ * or above the selected frequency for a minimum of min_sample_time,
+ * if not boosted to hispeed_freq. If boosted to hispeed_freq then we
+ * allow the speed to drop as soon as the boostpulse duration expires
+ * (or the indefinite boost is turned off).
+ */
+
+ if (!tunables->boosted || new_freq > tunables->hispeed_freq) {
+ pcpu->floor_freq = new_freq;
+ pcpu->floor_validate_time = now;
+ }
+
+ if (pcpu->target_freq == new_freq &&
+ pcpu->target_freq <= pcpu->policy->cur) {
+ trace_cpufreq_interactive_already(
+ data, cpu_load, pcpu->target_freq,
+ pcpu->policy->cur, new_freq);
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ goto rearm_if_notmax;
+ }
+
+ trace_cpufreq_interactive_target(data, cpu_load, pcpu->target_freq,
+ pcpu->policy->cur, new_freq);
+
+ pcpu->target_freq = new_freq;
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+ cpumask_set_cpu(data, &speedchange_cpumask);
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+ wake_up_process(speedchange_task);
+
+rearm_if_notmax:
+ /*
+ * Already set max speed and don't see a need to change that,
+ * wait until next idle to re-evaluate, don't need timer.
+ */
+ if (pcpu->target_freq == pcpu->policy->max)
+ goto exit;
+
+rearm:
+ if (!timer_pending(&pcpu->cpu_timer))
+ cpufreq_interactive_timer_resched(pcpu);
+
+exit:
+ up_read(&pcpu->enable_sem);
+ return;
+}
+
+static void cpufreq_interactive_idle_start(void)
+{
+ struct cpufreq_interactive_cpuinfo *pcpu =
+ &per_cpu(cpuinfo, smp_processor_id());
+ int pending;
+
+ if (!down_read_trylock(&pcpu->enable_sem))
+ return;
+ if (!pcpu->governor_enabled) {
+ up_read(&pcpu->enable_sem);
+ return;
+ }
+
+ pending = timer_pending(&pcpu->cpu_timer);
+
+ if (pcpu->target_freq != pcpu->policy->min) {
+ /*
+ * Entering idle while not at lowest speed. On some
+ * platforms this can hold the other CPU(s) at that speed
+ * even though the CPU is idle. Set a timer to re-evaluate
+ * speed so this idle CPU doesn't hold the other CPUs above
+ * min indefinitely. This should probably be a quirk of
+ * the CPUFreq driver.
+ */
+ if (!pending)
+ cpufreq_interactive_timer_resched(pcpu);
+ }
+
+ up_read(&pcpu->enable_sem);
+}
+
+static void cpufreq_interactive_idle_end(void)
+{
+ struct cpufreq_interactive_cpuinfo *pcpu =
+ &per_cpu(cpuinfo, smp_processor_id());
+
+ if (!down_read_trylock(&pcpu->enable_sem))
+ return;
+ if (!pcpu->governor_enabled) {
+ up_read(&pcpu->enable_sem);
+ return;
+ }
+
+ /* Arm the timer for 1-2 ticks later if not already. */
+ if (!timer_pending(&pcpu->cpu_timer)) {
+ cpufreq_interactive_timer_resched(pcpu);
+ } else if (time_after_eq(jiffies, pcpu->cpu_timer.expires)) {
+ del_timer(&pcpu->cpu_timer);
+ del_timer(&pcpu->cpu_slack_timer);
+ cpufreq_interactive_timer(smp_processor_id());
+ }
+
+ up_read(&pcpu->enable_sem);
+}
+
+static int cpufreq_interactive_speedchange_task(void *data)
+{
+ unsigned int cpu;
+ cpumask_t tmp_mask;
+ unsigned long flags;
+ struct cpufreq_interactive_cpuinfo *pcpu;
+
+ while (1) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+
+ if (cpumask_empty(&speedchange_cpumask)) {
+ spin_unlock_irqrestore(&speedchange_cpumask_lock,
+ flags);
+ schedule();
+
+ if (kthread_should_stop())
+ break;
+
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+ }
+
+ set_current_state(TASK_RUNNING);
+ tmp_mask = speedchange_cpumask;
+ cpumask_clear(&speedchange_cpumask);
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+
+ for_each_cpu(cpu, &tmp_mask) {
+ unsigned int j;
+ unsigned int max_freq = 0;
+
+ pcpu = &per_cpu(cpuinfo, cpu);
+ if (!down_read_trylock(&pcpu->enable_sem))
+ continue;
+ if (!pcpu->governor_enabled) {
+ up_read(&pcpu->enable_sem);
+ continue;
+ }
+
+ for_each_cpu(j, pcpu->policy->cpus) {
+ struct cpufreq_interactive_cpuinfo *pjcpu =
+ &per_cpu(cpuinfo, j);
+
+ if (pjcpu->target_freq > max_freq)
+ max_freq = pjcpu->target_freq;
+ }
+
+ if (max_freq != pcpu->policy->cur)
+ __cpufreq_driver_target(pcpu->policy,
+ max_freq,
+ CPUFREQ_RELATION_H);
+ trace_cpufreq_interactive_setspeed(cpu,
+ pcpu->target_freq,
+ pcpu->policy->cur);
+
+ up_read(&pcpu->enable_sem);
+ }
+ }
+
+ return 0;
+}
+
+static void cpufreq_interactive_boost(struct cpufreq_interactive_tunables *tunables)
+{
+ int i;
+ int anyboost = 0;
+ unsigned long flags[2];
+ struct cpufreq_interactive_cpuinfo *pcpu;
+
+ tunables->boosted = true;
+
+ spin_lock_irqsave(&speedchange_cpumask_lock, flags[0]);
+
+ for_each_online_cpu(i) {
+ pcpu = &per_cpu(cpuinfo, i);
+ if (tunables != pcpu->policy->governor_data)
+ continue;
+
+ spin_lock_irqsave(&pcpu->target_freq_lock, flags[1]);
+ if (pcpu->target_freq < tunables->hispeed_freq) {
+ pcpu->target_freq = tunables->hispeed_freq;
+ cpumask_set_cpu(i, &speedchange_cpumask);
+ pcpu->hispeed_validate_time =
+ ktime_to_us(ktime_get());
+ anyboost = 1;
+ }
+
+ /*
+ * Set floor freq and (re)start timer for when last
+ * validated.
+ */
+
+ pcpu->floor_freq = tunables->hispeed_freq;
+ pcpu->floor_validate_time = ktime_to_us(ktime_get());
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags[1]);
+ }
+
+ spin_unlock_irqrestore(&speedchange_cpumask_lock, flags[0]);
+
+ if (anyboost)
+ wake_up_process(speedchange_task);
+}
+
+static int cpufreq_interactive_notifier(
+ struct notifier_block *nb, unsigned long val, void *data)
+{
+ struct cpufreq_freqs *freq = data;
+ struct cpufreq_interactive_cpuinfo *pcpu;
+ int cpu;
+ unsigned long flags;
+
+ if (val == CPUFREQ_POSTCHANGE) {
+ pcpu = &per_cpu(cpuinfo, freq->cpu);
+ if (!down_read_trylock(&pcpu->enable_sem))
+ return 0;
+ if (!pcpu->governor_enabled) {
+ up_read(&pcpu->enable_sem);
+ return 0;
+ }
+
+ for_each_cpu(cpu, pcpu->policy->cpus) {
+ struct cpufreq_interactive_cpuinfo *pjcpu =
+ &per_cpu(cpuinfo, cpu);
+ if (cpu != freq->cpu) {
+ if (!down_read_trylock(&pjcpu->enable_sem))
+ continue;
+ if (!pjcpu->governor_enabled) {
+ up_read(&pjcpu->enable_sem);
+ continue;
+ }
+ }
+ spin_lock_irqsave(&pjcpu->load_lock, flags);
+ update_load(cpu);
+ spin_unlock_irqrestore(&pjcpu->load_lock, flags);
+ if (cpu != freq->cpu)
+ up_read(&pjcpu->enable_sem);
+ }
+
+ up_read(&pcpu->enable_sem);
+ }
+ return 0;
+}
+
+static struct notifier_block cpufreq_notifier_block = {
+ .notifier_call = cpufreq_interactive_notifier,
+};
+
+static unsigned int *get_tokenized_data(const char *buf, int *num_tokens)
+{
+ const char *cp;
+ int i;
+ int ntokens = 1;
+ unsigned int *tokenized_data;
+ int err = -EINVAL;
+
+ cp = buf;
+ while ((cp = strpbrk(cp + 1, " :")))
+ ntokens++;
+
+ if (!(ntokens & 0x1))
+ goto err;
+
+ tokenized_data = kmalloc(ntokens * sizeof(unsigned int), GFP_KERNEL);
+ if (!tokenized_data) {
+ err = -ENOMEM;
+ goto err;
+ }
+
+ cp = buf;
+ i = 0;
+ while (i < ntokens) {
+ if (sscanf(cp, "%u", &tokenized_data[i++]) != 1)
+ goto err_kfree;
+
+ cp = strpbrk(cp, " :");
+ if (!cp)
+ break;
+ cp++;
+ }
+
+ if (i != ntokens)
+ goto err_kfree;
+
+ *num_tokens = ntokens;
+ return tokenized_data;
+
+err_kfree:
+ kfree(tokenized_data);
+err:
+ return ERR_PTR(err);
+}
+
+static ssize_t show_target_loads(
+ struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ int i;
+ ssize_t ret = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+ for (i = 0; i < tunables->ntarget_loads; i++)
+ ret += sprintf(buf + ret, "%u%s", tunables->target_loads[i],
+ i & 0x1 ? ":" : " ");
+
+ sprintf(buf + ret - 1, "\n");
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+ return ret;
+}
+
+static ssize_t store_target_loads(
+ struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ntokens;
+ unsigned int *new_target_loads = NULL;
+ unsigned long flags;
+
+ new_target_loads = get_tokenized_data(buf, &ntokens);
+ if (IS_ERR(new_target_loads))
+ return PTR_RET(new_target_loads);
+
+ spin_lock_irqsave(&tunables->target_loads_lock, flags);
+ if (tunables->target_loads != default_target_loads)
+ kfree(tunables->target_loads);
+ tunables->target_loads = new_target_loads;
+ tunables->ntarget_loads = ntokens;
+ spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+ return count;
+}
+
+static ssize_t show_above_hispeed_delay(
+ struct cpufreq_interactive_tunables *tunables, char *buf)
+{
+ int i;
+ ssize_t ret = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+ for (i = 0; i < tunables->nabove_hispeed_delay; i++)
+ ret += sprintf(buf + ret, "%u%s",
+ tunables->above_hispeed_delay[i],
+ i & 0x1 ? ":" : " ");
+
+ sprintf(buf + ret - 1, "\n");
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+ return ret;
+}
+
+static ssize_t store_above_hispeed_delay(
+ struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ntokens;
+ unsigned int *new_above_hispeed_delay = NULL;
+ unsigned long flags;
+
+ new_above_hispeed_delay = get_tokenized_data(buf, &ntokens);
+ if (IS_ERR(new_above_hispeed_delay))
+ return PTR_RET(new_above_hispeed_delay);
+
+ spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+ if (tunables->above_hispeed_delay != default_above_hispeed_delay)
+ kfree(tunables->above_hispeed_delay);
+ tunables->above_hispeed_delay = new_above_hispeed_delay;
+ tunables->nabove_hispeed_delay = ntokens;
+ spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+ return count;
+
+}
+
+static ssize_t show_hispeed_freq(struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ return sprintf(buf, "%u\n", tunables->hispeed_freq);
+}
+
+static ssize_t store_hispeed_freq(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ long unsigned int val;
+
+ ret = strict_strtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+ tunables->hispeed_freq = val;
+ return count;
+}
+
+static ssize_t show_go_hispeed_load(struct cpufreq_interactive_tunables
+ *tunables, char *buf)
+{
+ return sprintf(buf, "%lu\n", tunables->go_hispeed_load);
+}
+
+static ssize_t store_go_hispeed_load(struct cpufreq_interactive_tunables
+ *tunables, const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = strict_strtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+ tunables->go_hispeed_load = val;
+ return count;
+}
+
+static ssize_t show_min_sample_time(struct cpufreq_interactive_tunables
+ *tunables, char *buf)
+{
+ return sprintf(buf, "%lu\n", tunables->min_sample_time);
+}
+
+static ssize_t store_min_sample_time(struct cpufreq_interactive_tunables
+ *tunables, const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = strict_strtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+ tunables->min_sample_time = val;
+ return count;
+}
+
+static ssize_t show_timer_rate(struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ return sprintf(buf, "%lu\n", tunables->timer_rate);
+}
+
+static ssize_t store_timer_rate(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = strict_strtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+ tunables->timer_rate = val;
+ return count;
+}
+
+static ssize_t show_timer_slack(struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", tunables->timer_slack_val);
+}
+
+static ssize_t store_timer_slack(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = kstrtol(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->timer_slack_val = val;
+ return count;
+}
+
+static ssize_t show_boost(struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", tunables->boost_val);
+}
+
+static ssize_t store_boost(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boost_val = val;
+
+ if (tunables->boost_val) {
+ trace_cpufreq_interactive_boost("on");
+ if (!tunables->boosted)
+ cpufreq_interactive_boost(tunables);
+ } else {
+ tunables->boostpulse_endtime = ktime_to_us(ktime_get());
+ trace_cpufreq_interactive_unboost("off");
+ }
+
+ return count;
+}
+
+static ssize_t store_boostpulse(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boostpulse_endtime = ktime_to_us(ktime_get()) +
+ tunables->boostpulse_duration_val;
+ trace_cpufreq_interactive_boost("pulse");
+ if (!tunables->boosted)
+ cpufreq_interactive_boost(tunables);
+ return count;
+}
+
+static ssize_t show_boostpulse_duration(struct cpufreq_interactive_tunables
+ *tunables, char *buf)
+{
+ return sprintf(buf, "%d\n", tunables->boostpulse_duration_val);
+}
+
+static ssize_t store_boostpulse_duration(struct cpufreq_interactive_tunables
+ *tunables, const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ tunables->boostpulse_duration_val = val;
+ return count;
+}
+
+static ssize_t show_io_is_busy(struct cpufreq_interactive_tunables *tunables,
+ char *buf)
+{
+ return sprintf(buf, "%u\n", tunables->io_is_busy);
+}
+
+static ssize_t store_io_is_busy(struct cpufreq_interactive_tunables *tunables,
+ const char *buf, size_t count)
+{
+ int ret;
+ unsigned long val;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+ tunables->io_is_busy = val;
+ return count;
+}
+
+/*
+ * Create show/store routines
+ * - sys: One governor instance for complete SYSTEM
+ * - pol: One governor instance per struct cpufreq_policy
+ */
+#define show_gov_pol_sys(file_name) \
+static ssize_t show_##file_name##_gov_sys \
+(struct kobject *kobj, struct attribute *attr, char *buf) \
+{ \
+ return show_##file_name(common_tunables, buf); \
+} \
+ \
+static ssize_t show_##file_name##_gov_pol \
+(struct cpufreq_policy *policy, char *buf) \
+{ \
+ return show_##file_name(policy->governor_data, buf); \
+}
+
+#define store_gov_pol_sys(file_name) \
+static ssize_t store_##file_name##_gov_sys \
+(struct kobject *kobj, struct attribute *attr, const char *buf, \
+ size_t count) \
+{ \
+ return store_##file_name(common_tunables, buf, count); \
+} \
+ \
+static ssize_t store_##file_name##_gov_pol \
+(struct cpufreq_policy *policy, const char *buf, size_t count) \
+{ \
+ return store_##file_name(policy->governor_data, buf, count); \
+}
+
+#define show_store_gov_pol_sys(file_name) \
+show_gov_pol_sys(file_name); \
+store_gov_pol_sys(file_name)
+
+show_store_gov_pol_sys(target_loads);
+show_store_gov_pol_sys(above_hispeed_delay);
+show_store_gov_pol_sys(hispeed_freq);
+show_store_gov_pol_sys(go_hispeed_load);
+show_store_gov_pol_sys(min_sample_time);
+show_store_gov_pol_sys(timer_rate);
+show_store_gov_pol_sys(timer_slack);
+show_store_gov_pol_sys(boost);
+store_gov_pol_sys(boostpulse);
+show_store_gov_pol_sys(boostpulse_duration);
+show_store_gov_pol_sys(io_is_busy);
+
+#define gov_sys_attr_rw(_name) \
+static struct global_attr _name##_gov_sys = \
+__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
+
+#define gov_pol_attr_rw(_name) \
+static struct freq_attr _name##_gov_pol = \
+__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
+
+#define gov_sys_pol_attr_rw(_name) \
+ gov_sys_attr_rw(_name); \
+ gov_pol_attr_rw(_name)
+
+gov_sys_pol_attr_rw(target_loads);
+gov_sys_pol_attr_rw(above_hispeed_delay);
+gov_sys_pol_attr_rw(hispeed_freq);
+gov_sys_pol_attr_rw(go_hispeed_load);
+gov_sys_pol_attr_rw(min_sample_time);
+gov_sys_pol_attr_rw(timer_rate);
+gov_sys_pol_attr_rw(timer_slack);
+gov_sys_pol_attr_rw(boost);
+gov_sys_pol_attr_rw(boostpulse_duration);
+gov_sys_pol_attr_rw(io_is_busy);
+
+static struct global_attr boostpulse_gov_sys =
+ __ATTR(boostpulse, 0200, NULL, store_boostpulse_gov_sys);
+
+static struct freq_attr boostpulse_gov_pol =
+ __ATTR(boostpulse, 0200, NULL, store_boostpulse_gov_pol);
+
+/* One Governor instance for entire system */
+static struct attribute *interactive_attributes_gov_sys[] = {
+ &target_loads_gov_sys.attr,
+ &above_hispeed_delay_gov_sys.attr,
+ &hispeed_freq_gov_sys.attr,
+ &go_hispeed_load_gov_sys.attr,
+ &min_sample_time_gov_sys.attr,
+ &timer_rate_gov_sys.attr,
+ &timer_slack_gov_sys.attr,
+ &boost_gov_sys.attr,
+ &boostpulse_gov_sys.attr,
+ &boostpulse_duration_gov_sys.attr,
+ &io_is_busy_gov_sys.attr,
+ NULL,
+};
+
+static struct attribute_group interactive_attr_group_gov_sys = {
+ .attrs = interactive_attributes_gov_sys,
+ .name = "interactive",
+};
+
+/* Per policy governor instance */
+static struct attribute *interactive_attributes_gov_pol[] = {
+ &target_loads_gov_pol.attr,
+ &above_hispeed_delay_gov_pol.attr,
+ &hispeed_freq_gov_pol.attr,
+ &go_hispeed_load_gov_pol.attr,
+ &min_sample_time_gov_pol.attr,
+ &timer_rate_gov_pol.attr,
+ &timer_slack_gov_pol.attr,
+ &boost_gov_pol.attr,
+ &boostpulse_gov_pol.attr,
+ &boostpulse_duration_gov_pol.attr,
+ &io_is_busy_gov_pol.attr,
+ NULL,
+};
+
+static struct attribute_group interactive_attr_group_gov_pol = {
+ .attrs = interactive_attributes_gov_pol,
+ .name = "interactive",
+};
+
+static struct attribute_group *get_sysfs_attr(void)
+{
+ if (have_governor_per_policy())
+ return &interactive_attr_group_gov_pol;
+ else
+ return &interactive_attr_group_gov_sys;
+}
+
+static int cpufreq_interactive_idle_notifier(struct notifier_block *nb,
+ unsigned long val,
+ void *data)
+{
+ switch (val) {
+ case IDLE_START:
+ cpufreq_interactive_idle_start();
+ break;
+ case IDLE_END:
+ cpufreq_interactive_idle_end();
+ break;
+ }
+
+ return 0;
+}
+
+static struct notifier_block cpufreq_interactive_idle_nb = {
+ .notifier_call = cpufreq_interactive_idle_notifier,
+};
+
+static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
+ unsigned int event)
+{
+ int rc;
+ unsigned int j;
+ struct cpufreq_interactive_cpuinfo *pcpu;
+ struct cpufreq_frequency_table *freq_table;
+ struct cpufreq_interactive_tunables *tunables;
+ unsigned long flags;
+
+ if (have_governor_per_policy())
+ tunables = policy->governor_data;
+ else
+ tunables = common_tunables;
+
+ WARN_ON(!tunables && (event != CPUFREQ_GOV_POLICY_INIT));
+
+ switch (event) {
+ case CPUFREQ_GOV_POLICY_INIT:
+ if (have_governor_per_policy()) {
+ WARN_ON(tunables);
+ } else if (tunables) {
+ tunables->usage_count++;
+ policy->governor_data = tunables;
+ return 0;
+ }
+
+ tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
+ if (!tunables) {
+ pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
+ return -ENOMEM;
+ }
+
+ tunables->usage_count = 1;
+ tunables->above_hispeed_delay = default_above_hispeed_delay;
+ tunables->nabove_hispeed_delay =
+ ARRAY_SIZE(default_above_hispeed_delay);
+ tunables->go_hispeed_load = DEFAULT_GO_HISPEED_LOAD;
+ tunables->target_loads = default_target_loads;
+ tunables->ntarget_loads = ARRAY_SIZE(default_target_loads);
+ tunables->min_sample_time = DEFAULT_MIN_SAMPLE_TIME;
+ tunables->timer_rate = DEFAULT_TIMER_RATE;
+ tunables->boostpulse_duration_val = DEFAULT_MIN_SAMPLE_TIME;
+ tunables->timer_slack_val = DEFAULT_TIMER_SLACK;
+
+ spin_lock_init(&tunables->target_loads_lock);
+ spin_lock_init(&tunables->above_hispeed_delay_lock);
+
+ policy->governor_data = tunables;
+ if (!have_governor_per_policy())
+ common_tunables = tunables;
+
+ rc = sysfs_create_group(get_governor_parent_kobj(policy),
+ get_sysfs_attr());
+ if (rc) {
+ kfree(tunables);
+ policy->governor_data = NULL;
+ if (!have_governor_per_policy())
+ common_tunables = NULL;
+ return rc;
+ }
+
+ if (!policy->governor->initialized) {
+ idle_notifier_register(&cpufreq_interactive_idle_nb);
+ cpufreq_register_notifier(&cpufreq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ }
+
+ break;
+
+ case CPUFREQ_GOV_POLICY_EXIT:
+ if (!--tunables->usage_count) {
+ if (policy->governor->initialized == 1) {
+ cpufreq_unregister_notifier(&cpufreq_notifier_block,
+ CPUFREQ_TRANSITION_NOTIFIER);
+ idle_notifier_unregister(&cpufreq_interactive_idle_nb);
+ }
+
+ sysfs_remove_group(get_governor_parent_kobj(policy),
+ get_sysfs_attr());
+ kfree(tunables);
+ common_tunables = NULL;
+ }
+
+ policy->governor_data = NULL;
+ break;
+
+ case CPUFREQ_GOV_START:
+ mutex_lock(&gov_lock);
+
+ freq_table = cpufreq_frequency_get_table(policy->cpu);
+ if (!tunables->hispeed_freq)
+ tunables->hispeed_freq = policy->max;
+
+ for_each_cpu(j, policy->cpus) {
+ pcpu = &per_cpu(cpuinfo, j);
+ pcpu->policy = policy;
+ pcpu->target_freq = policy->cur;
+ pcpu->freq_table = freq_table;
+ pcpu->floor_freq = pcpu->target_freq;
+ pcpu->floor_validate_time =
+ ktime_to_us(ktime_get());
+ pcpu->hispeed_validate_time =
+ pcpu->floor_validate_time;
+ pcpu->max_freq = policy->max;
+ down_write(&pcpu->enable_sem);
+ del_timer_sync(&pcpu->cpu_timer);
+ del_timer_sync(&pcpu->cpu_slack_timer);
+ cpufreq_interactive_timer_start(tunables, j);
+ pcpu->governor_enabled = 1;
+ up_write(&pcpu->enable_sem);
+ }
+
+ mutex_unlock(&gov_lock);
+ break;
+
+ case CPUFREQ_GOV_STOP:
+ mutex_lock(&gov_lock);
+ for_each_cpu(j, policy->cpus) {
+ pcpu = &per_cpu(cpuinfo, j);
+ down_write(&pcpu->enable_sem);
+ pcpu->governor_enabled = 0;
+ del_timer_sync(&pcpu->cpu_timer);
+ del_timer_sync(&pcpu->cpu_slack_timer);
+ up_write(&pcpu->enable_sem);
+ }
+
+ mutex_unlock(&gov_lock);
+ break;
+
+ case CPUFREQ_GOV_LIMITS:
+ if (policy->max < policy->cur)
+ __cpufreq_driver_target(policy,
+ policy->max, CPUFREQ_RELATION_H);
+ else if (policy->min > policy->cur)
+ __cpufreq_driver_target(policy,
+ policy->min, CPUFREQ_RELATION_L);
+ for_each_cpu(j, policy->cpus) {
+ pcpu = &per_cpu(cpuinfo, j);
+
+ down_read(&pcpu->enable_sem);
+ if (pcpu->governor_enabled == 0) {
+ up_read(&pcpu->enable_sem);
+ continue;
+ }
+
+ spin_lock_irqsave(&pcpu->target_freq_lock, flags);
+ if (policy->max < pcpu->target_freq)
+ pcpu->target_freq = policy->max;
+ else if (policy->min > pcpu->target_freq)
+ pcpu->target_freq = policy->min;
+
+ spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+ up_read(&pcpu->enable_sem);
+
+ /* Reschedule timer only if policy->max is raised.
+ * Delete the timers, else the timer callback may
+ * return without re-arm the timer when failed
+ * acquire the semaphore. This race may cause timer
+ * stopped unexpectedly.
+ */
+
+ if (policy->max > pcpu->max_freq) {
+ down_write(&pcpu->enable_sem);
+ del_timer_sync(&pcpu->cpu_timer);
+ del_timer_sync(&pcpu->cpu_slack_timer);
+ cpufreq_interactive_timer_start(tunables, j);
+ up_write(&pcpu->enable_sem);
+ }
+
+ pcpu->max_freq = policy->max;
+ }
+ break;
+ }
+ return 0;
+}
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_interactive = {
+ .name = "interactive",
+ .governor = cpufreq_governor_interactive,
+ .max_transition_latency = 10000000,
+ .owner = THIS_MODULE,
+};
+
+static void cpufreq_interactive_nop_timer(unsigned long data)
+{
+}
+
+static int __init cpufreq_interactive_init(void)
+{
+ unsigned int i;
+ struct cpufreq_interactive_cpuinfo *pcpu;
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+
+ /* Initalize per-cpu timers */
+ for_each_possible_cpu(i) {
+ pcpu = &per_cpu(cpuinfo, i);
+ init_timer_deferrable(&pcpu->cpu_timer);
+ pcpu->cpu_timer.function = cpufreq_interactive_timer;
+ pcpu->cpu_timer.data = i;
+ init_timer(&pcpu->cpu_slack_timer);
+ pcpu->cpu_slack_timer.function = cpufreq_interactive_nop_timer;
+ spin_lock_init(&pcpu->load_lock);
+ spin_lock_init(&pcpu->target_freq_lock);
+ init_rwsem(&pcpu->enable_sem);
+ }
+
+ spin_lock_init(&speedchange_cpumask_lock);
+ mutex_init(&gov_lock);
+ speedchange_task =
+ kthread_create(cpufreq_interactive_speedchange_task, NULL,
+ "cfinteractive");
+ if (IS_ERR(speedchange_task))
+ return PTR_ERR(speedchange_task);
+
+ sched_setscheduler_nocheck(speedchange_task, SCHED_FIFO, ¶m);
+ get_task_struct(speedchange_task);
+
+ /* NB: wake up so the thread does not look hung to the freezer */
+ wake_up_process(speedchange_task);
+
+ return cpufreq_register_governor(&cpufreq_gov_interactive);
+}
+
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+fs_initcall(cpufreq_interactive_init);
+#else
+module_init(cpufreq_interactive_init);
+#endif
+
+static void __exit cpufreq_interactive_exit(void)
+{
+ cpufreq_unregister_governor(&cpufreq_gov_interactive);
+ kthread_stop(speedchange_task);
+ put_task_struct(speedchange_task);
+}
+
+module_exit(cpufreq_interactive_exit);
+
+MODULE_AUTHOR("Mike Chan <mike@android.com>");
+MODULE_DESCRIPTION("'cpufreq_interactive' - A cpufreq governor for "
+ "Latency sensitive workloads");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 7fb6002..0cfa547 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -20,6 +20,10 @@
#include <linux/kobject.h>
#include <linux/spinlock.h>
#include <linux/notifier.h>
+#include <linux/sort.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/sched.h>
#include <asm/cputime.h>
static spinlock_t cpufreq_stats_lock;
@@ -38,7 +42,28 @@
#endif
};
+struct all_cpufreq_stats {
+ unsigned int state_num;
+ cputime64_t *time_in_state;
+ unsigned int *freq_table;
+};
+
+struct cpufreq_power_stats {
+ unsigned int state_num;
+ unsigned int *curr;
+ unsigned int *freq_table;
+};
+
+struct all_freq_table {
+ unsigned int *freq_table;
+ unsigned int table_size;
+};
+
+static struct all_freq_table *all_freq_table;
+
+static DEFINE_PER_CPU(struct all_cpufreq_stats *, all_cpufreq_stats);
static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table);
+static DEFINE_PER_CPU(struct cpufreq_power_stats *, cpufreq_power_stats);
struct cpufreq_stats_attribute {
struct attribute attr;
@@ -48,14 +73,24 @@
static int cpufreq_stats_update(unsigned int cpu)
{
struct cpufreq_stats *stat;
+ struct all_cpufreq_stats *all_stat;
unsigned long long cur_time;
cur_time = get_jiffies_64();
spin_lock(&cpufreq_stats_lock);
stat = per_cpu(cpufreq_stats_table, cpu);
- if (stat->time_in_state)
+ all_stat = per_cpu(all_cpufreq_stats, cpu);
+ if (!stat) {
+ spin_unlock(&cpufreq_stats_lock);
+ return 0;
+ }
+ if (stat->time_in_state) {
stat->time_in_state[stat->last_index] +=
cur_time - stat->last_time;
+ if (all_stat)
+ all_stat->time_in_state[stat->last_index] +=
+ cur_time - stat->last_time;
+ }
stat->last_time = cur_time;
spin_unlock(&cpufreq_stats_lock);
return 0;
@@ -86,6 +121,104 @@
return len;
}
+static int get_index_all_cpufreq_stat(struct all_cpufreq_stats *all_stat,
+ unsigned int freq)
+{
+ int i;
+ if (!all_stat)
+ return -1;
+ for (i = 0; i < all_stat->state_num; i++) {
+ if (all_stat->freq_table[i] == freq)
+ return i;
+ }
+ return -1;
+}
+
+void acct_update_power(struct task_struct *task, cputime_t cputime) {
+ struct cpufreq_power_stats *powerstats;
+ struct cpufreq_stats *stats;
+ unsigned int cpu_num, curr;
+
+ if (!task)
+ return;
+ cpu_num = task_cpu(task);
+ powerstats = per_cpu(cpufreq_power_stats, cpu_num);
+ stats = per_cpu(cpufreq_stats_table, cpu_num);
+ if (!powerstats || !stats)
+ return;
+
+ curr = powerstats->curr[stats->last_index];
+ if (task->cpu_power != ULLONG_MAX)
+ task->cpu_power += curr * cputime_to_usecs(cputime);
+}
+EXPORT_SYMBOL_GPL(acct_update_power);
+
+static ssize_t show_current_in_state(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ ssize_t len = 0;
+ unsigned int i, cpu;
+ struct cpufreq_power_stats *powerstats;
+
+ spin_lock(&cpufreq_stats_lock);
+ for_each_possible_cpu(cpu) {
+ powerstats = per_cpu(cpufreq_power_stats, cpu);
+ if (!powerstats)
+ continue;
+ len += scnprintf(buf + len, PAGE_SIZE - len, "CPU%d:", cpu);
+ for (i = 0; i < powerstats->state_num; i++)
+ len += scnprintf(buf + len, PAGE_SIZE - len,
+ "%d=%d ", powerstats->freq_table[i],
+ powerstats->curr[i]);
+ len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+ }
+ spin_unlock(&cpufreq_stats_lock);
+ return len;
+}
+
+static ssize_t show_all_time_in_state(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ ssize_t len = 0;
+ unsigned int i, cpu, freq, index;
+ struct all_cpufreq_stats *all_stat;
+ struct cpufreq_policy *policy;
+
+ len += scnprintf(buf + len, PAGE_SIZE - len, "freq\t\t");
+ for_each_possible_cpu(cpu) {
+ len += scnprintf(buf + len, PAGE_SIZE - len, "cpu%d\t\t", cpu);
+ if (cpu_online(cpu))
+ cpufreq_stats_update(cpu);
+ }
+
+ if (!all_freq_table)
+ goto out;
+ for (i = 0; i < all_freq_table->table_size; i++) {
+ freq = all_freq_table->freq_table[i];
+ len += scnprintf(buf + len, PAGE_SIZE - len, "\n%u\t\t", freq);
+ for_each_possible_cpu(cpu) {
+ policy = cpufreq_cpu_get(cpu);
+ if (policy == NULL)
+ continue;
+ all_stat = per_cpu(all_cpufreq_stats, policy->cpu);
+ index = get_index_all_cpufreq_stat(all_stat, freq);
+ if (index != -1) {
+ len += scnprintf(buf + len, PAGE_SIZE - len,
+ "%llu\t\t", (unsigned long long)
+ cputime64_to_clock_t(all_stat->time_in_state[index]));
+ } else {
+ len += scnprintf(buf + len, PAGE_SIZE - len,
+ "N/A\t\t");
+ }
+ cpufreq_cpu_put(policy);
+ }
+ }
+
+out:
+ len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+ return len;
+}
+
#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
{
@@ -149,6 +282,12 @@
.name = "stats"
};
+static struct kobj_attribute _attr_all_time_in_state = __ATTR(all_time_in_state,
+ 0444, show_all_time_in_state, NULL);
+
+static struct kobj_attribute _attr_current_in_state = __ATTR(current_in_state,
+ 0444, show_current_in_state, NULL);
+
static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
{
int index;
@@ -195,10 +334,50 @@
cpufreq_cpu_put(policy);
}
-static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
- struct cpufreq_frequency_table *table)
+static void cpufreq_allstats_free(void)
{
- unsigned int i, j, count = 0, ret = 0;
+ int cpu;
+ struct all_cpufreq_stats *all_stat;
+
+ sysfs_remove_file(cpufreq_global_kobject,
+ &_attr_all_time_in_state.attr);
+
+ for_each_possible_cpu(cpu) {
+ all_stat = per_cpu(all_cpufreq_stats, cpu);
+ if (!all_stat)
+ continue;
+ kfree(all_stat->time_in_state);
+ kfree(all_stat);
+ per_cpu(all_cpufreq_stats, cpu) = NULL;
+ }
+ if (all_freq_table) {
+ kfree(all_freq_table->freq_table);
+ kfree(all_freq_table);
+ all_freq_table = NULL;
+ }
+}
+
+static void cpufreq_powerstats_free(void)
+{
+ int cpu;
+ struct cpufreq_power_stats *powerstats;
+
+ sysfs_remove_file(cpufreq_global_kobject, &_attr_current_in_state.attr);
+
+ for_each_possible_cpu(cpu) {
+ powerstats = per_cpu(cpufreq_power_stats, cpu);
+ if (!powerstats)
+ continue;
+ kfree(powerstats->curr);
+ kfree(powerstats);
+ per_cpu(cpufreq_power_stats, cpu) = NULL;
+ }
+}
+
+static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
+ struct cpufreq_frequency_table *table, int count)
+{
+ unsigned int i, j, ret = 0;
struct cpufreq_stats *stat;
struct cpufreq_policy *data;
unsigned int alloc_size;
@@ -222,12 +401,6 @@
stat->cpu = cpu;
per_cpu(cpufreq_stats_table, cpu) = stat;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- unsigned int freq = table[i].frequency;
- if (freq == CPUFREQ_ENTRY_INVALID)
- continue;
- count++;
- }
alloc_size = count * sizeof(int) + count * sizeof(u64);
@@ -281,13 +454,151 @@
stat->cpu = policy->cpu;
}
+static void cpufreq_powerstats_create(unsigned int cpu,
+ struct cpufreq_frequency_table *table, int count) {
+ unsigned int alloc_size, i = 0, j = 0, ret = 0;
+ struct cpufreq_power_stats *powerstats;
+ struct device_node *cpu_node;
+ char device_path[16];
+
+ powerstats = kzalloc(sizeof(struct cpufreq_power_stats),
+ GFP_KERNEL);
+ if (!powerstats)
+ return;
+
+ /* Allocate memory for freq table per cpu as well as clockticks per
+ * freq*/
+ alloc_size = count * sizeof(unsigned int) +
+ count * sizeof(unsigned int);
+ powerstats->curr = kzalloc(alloc_size, GFP_KERNEL);
+ if (!powerstats->curr) {
+ kfree(powerstats);
+ return;
+ }
+ powerstats->freq_table = powerstats->curr + count;
+
+ spin_lock(&cpufreq_stats_lock);
+ for (i = 0; table[i].frequency != CPUFREQ_TABLE_END && j < count; i++) {
+ unsigned int freq = table[i].frequency;
+
+ if (freq == CPUFREQ_ENTRY_INVALID)
+ continue;
+ powerstats->freq_table[j++] = freq;
+ }
+ powerstats->state_num = j;
+
+ snprintf(device_path, sizeof(device_path), "/cpus/cpu@%d", cpu);
+ cpu_node = of_find_node_by_path(device_path);
+ if (cpu_node) {
+ ret = of_property_read_u32_array(cpu_node, "current",
+ powerstats->curr, count);
+ if (ret) {
+ kfree(powerstats->curr);
+ kfree(powerstats);
+ powerstats = NULL;
+ }
+ }
+ per_cpu(cpufreq_power_stats, cpu) = powerstats;
+ spin_unlock(&cpufreq_stats_lock);
+}
+
+static int compare_for_sort(const void *lhs_ptr, const void *rhs_ptr)
+{
+ unsigned int lhs = *(const unsigned int *)(lhs_ptr);
+ unsigned int rhs = *(const unsigned int *)(rhs_ptr);
+ if (lhs < rhs)
+ return -1;
+ if (lhs > rhs)
+ return 1;
+ return 0;
+}
+
+static bool check_all_freq_table(unsigned int freq)
+{
+ int i;
+ for (i = 0; i < all_freq_table->table_size; i++) {
+ if (freq == all_freq_table->freq_table[i])
+ return true;
+ }
+ return false;
+}
+
+static void create_all_freq_table(void)
+{
+ all_freq_table = kzalloc(sizeof(struct all_freq_table),
+ GFP_KERNEL);
+ if (!all_freq_table)
+ pr_warn("could not allocate memory for all_freq_table\n");
+ return;
+}
+
+static void add_all_freq_table(unsigned int freq)
+{
+ unsigned int size;
+ size = sizeof(unsigned int) * (all_freq_table->table_size + 1);
+ all_freq_table->freq_table = krealloc(all_freq_table->freq_table,
+ size, GFP_ATOMIC);
+ if (IS_ERR(all_freq_table->freq_table)) {
+ pr_warn("Could not reallocate memory for freq_table\n");
+ all_freq_table->freq_table = NULL;
+ return;
+ }
+ all_freq_table->freq_table[all_freq_table->table_size++] = freq;
+}
+
+static void cpufreq_allstats_create(unsigned int cpu,
+ struct cpufreq_frequency_table *table, int count)
+{
+ int i , j = 0;
+ unsigned int alloc_size;
+ struct all_cpufreq_stats *all_stat;
+ bool sort_needed = false;
+
+ all_stat = kzalloc(sizeof(struct all_cpufreq_stats),
+ GFP_KERNEL);
+ if (!all_stat) {
+ pr_warn("Cannot allocate memory for cpufreq stats\n");
+ return;
+ }
+
+ /*Allocate memory for freq table per cpu as well as clockticks per freq*/
+ alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);
+ all_stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
+ if (!all_stat->time_in_state) {
+ pr_warn("Cannot allocate memory for cpufreq time_in_state\n");
+ kfree(all_stat);
+ all_stat = NULL;
+ return;
+ }
+ all_stat->freq_table = (unsigned int *)
+ (all_stat->time_in_state + count);
+
+ spin_lock(&cpufreq_stats_lock);
+ for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+ unsigned int freq = table[i].frequency;
+ if (freq == CPUFREQ_ENTRY_INVALID)
+ continue;
+ all_stat->freq_table[j++] = freq;
+ if (all_freq_table && !check_all_freq_table(freq)) {
+ add_all_freq_table(freq);
+ sort_needed = true;
+ }
+ }
+ if (sort_needed)
+ sort(all_freq_table->freq_table, all_freq_table->table_size,
+ sizeof(unsigned int), &compare_for_sort, NULL);
+ all_stat->state_num = j;
+ per_cpu(all_cpufreq_stats, cpu) = all_stat;
+ spin_unlock(&cpufreq_stats_lock);
+}
+
static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
unsigned long val, void *data)
{
- int ret;
+ int ret, count = 0, i;
struct cpufreq_policy *policy = data;
struct cpufreq_frequency_table *table;
- unsigned int cpu = policy->cpu;
+ unsigned int cpu_num, cpu = policy->cpu;
if (val == CPUFREQ_UPDATE_POLICY_CPU) {
cpufreq_stats_update_policy_cpu(policy);
@@ -299,7 +610,24 @@
table = cpufreq_frequency_get_table(cpu);
if (!table)
return 0;
- ret = cpufreq_stats_create_table(policy, table);
+
+ for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+ unsigned int freq = table[i].frequency;
+
+ if (freq == CPUFREQ_ENTRY_INVALID)
+ continue;
+ count++;
+ }
+
+ if (!per_cpu(all_cpufreq_stats, cpu))
+ cpufreq_allstats_create(cpu, table, count);
+
+ for_each_possible_cpu(cpu_num) {
+ if (!per_cpu(cpufreq_power_stats, cpu_num))
+ cpufreq_powerstats_create(cpu_num, table, count);
+ }
+
+ ret = cpufreq_stats_create_table(policy, table, count);
if (ret)
return ret;
return 0;
@@ -341,6 +669,43 @@
return 0;
}
+static int cpufreq_stats_create_table_cpu(unsigned int cpu)
+{
+ struct cpufreq_policy *policy;
+ struct cpufreq_frequency_table *table;
+ int i, count, cpu_num, ret = -ENODEV;
+
+ policy = cpufreq_cpu_get(cpu);
+ if (!policy)
+ return -ENODEV;
+
+ table = cpufreq_frequency_get_table(cpu);
+ if (!table)
+ goto out;
+
+ count = 0;
+ for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+ unsigned int freq = table[i].frequency;
+
+ if (freq != CPUFREQ_ENTRY_INVALID)
+ count++;
+ }
+
+ if (!per_cpu(all_cpufreq_stats, cpu))
+ cpufreq_allstats_create(cpu, table, count);
+
+ for_each_possible_cpu(cpu_num) {
+ if (!per_cpu(cpufreq_power_stats, cpu_num))
+ cpufreq_powerstats_create(cpu_num, table, count);
+ }
+
+ ret = cpufreq_stats_create_table(policy, table, count);
+
+out:
+ cpufreq_cpu_put(policy);
+ return ret;
+}
+
static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
@@ -360,6 +725,10 @@
case CPU_DEAD_FROZEN:
cpufreq_stats_free_table(cpu);
break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ cpufreq_stats_create_table_cpu(cpu);
+ break;
}
return NOTIFY_OK;
}
@@ -404,6 +773,17 @@
return ret;
}
+ create_all_freq_table();
+ ret = sysfs_create_file(cpufreq_global_kobject,
+ &_attr_all_time_in_state.attr);
+ if (ret)
+ pr_warn("Cannot create sysfs file for cpufreq stats\n");
+
+ ret = sysfs_create_file(cpufreq_global_kobject,
+ &_attr_current_in_state.attr);
+ if (ret)
+ pr_warn("Cannot create sysfs file for cpufreq current stats\n");
+
return 0;
}
static void __exit cpufreq_stats_exit(void)
@@ -419,6 +799,8 @@
cpufreq_stats_free_table(cpu);
cpufreq_stats_free_sysfs(cpu);
}
+ cpufreq_allstats_free();
+ cpufreq_powerstats_free();
}
MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 67fd901..16e8a59 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -173,7 +173,12 @@
/* for higher loadavg, we are more reluctant */
- mult += 2 * get_loadavg();
+ /*
+ * this doesn't work as intended - it is almost always 0, but can
+ * sometimes, depending on workload, spike very high into the hundreds
+ * even when the average cpu load is under 10%.
+ */
+ /* mult += 2 * get_loadavg(); */
/* for IO wait tasks (per cpu!) we add 5x each */
mult += 10 * nr_iowait_cpu(smp_processor_id());
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c3768fa..9002122 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -136,7 +136,7 @@
*/
static int desc_to_gpio(const struct gpio_desc *desc)
{
- return desc->chip->base + gpio_chip_hwgpio(desc);
+ return desc - &gpio_desc[0];
}
@@ -1242,15 +1242,14 @@
}
}
+ spin_unlock_irqrestore(&gpio_lock, flags);
+
#ifdef CONFIG_PINCTRL
INIT_LIST_HEAD(&chip->pin_ranges);
#endif
of_gpiochip_add(chip);
-unlock:
- spin_unlock_irqrestore(&gpio_lock, flags);
-
if (status)
goto fail;
@@ -1263,6 +1262,9 @@
chip->label ? : "generic");
return 0;
+
+unlock:
+ spin_unlock_irqrestore(&gpio_lock, flags);
fail:
/* failures here can mean systems won't boot... */
pr_err("gpiochip_add: gpios %d..%d (%s) failed to register\n",
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 8453214..941ab3c 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -768,6 +768,8 @@
[KEY_ALTERASE] = "AlternateErase", [KEY_CANCEL] = "Cancel",
[KEY_BRIGHTNESSDOWN] = "BrightnessDown", [KEY_BRIGHTNESSUP] = "BrightnessUp",
[KEY_MEDIA] = "Media", [KEY_UNKNOWN] = "Unknown",
+ [BTN_DPAD_UP] = "BtnDPadUp", [BTN_DPAD_DOWN] = "BtnDPadDown",
+ [BTN_DPAD_LEFT] = "BtnDPadLeft", [BTN_DPAD_RIGHT] = "BtnDPadRight",
[BTN_0] = "Btn0", [BTN_1] = "Btn1",
[BTN_2] = "Btn2", [BTN_3] = "Btn3",
[BTN_4] = "Btn4", [BTN_5] = "Btn5",
@@ -797,7 +799,8 @@
[BTN_TOOL_MOUSE] = "ToolMouse", [BTN_TOOL_LENS] = "ToolLens",
[BTN_TOUCH] = "Touch", [BTN_STYLUS] = "Stylus",
[BTN_STYLUS2] = "Stylus2", [BTN_TOOL_DOUBLETAP] = "ToolDoubleTap",
- [BTN_TOOL_TRIPLETAP] = "ToolTripleTap", [BTN_GEAR_DOWN] = "WheelBtn",
+ [BTN_TOOL_TRIPLETAP] = "ToolTripleTap", [BTN_TOOL_QUADTAP] = "ToolQuadrupleTap",
+ [BTN_GEAR_DOWN] = "WheelBtn",
[BTN_GEAR_UP] = "Gear up", [KEY_OK] = "Ok",
[KEY_SELECT] = "Select", [KEY_GOTO] = "Goto",
[KEY_CLEAR] = "Clear", [KEY_POWER2] = "Power2",
@@ -852,6 +855,16 @@
[KEY_KBDILLUMDOWN] = "KbdIlluminationDown",
[KEY_KBDILLUMUP] = "KbdIlluminationUp",
[KEY_SWITCHVIDEOMODE] = "SwitchVideoMode",
+ [KEY_BUTTONCONFIG] = "ButtonConfig",
+ [KEY_TASKMANAGER] = "TaskManager",
+ [KEY_JOURNAL] = "Journal",
+ [KEY_CONTROLPANEL] = "ControlPanel",
+ [KEY_APPSELECT] = "AppSelect",
+ [KEY_SCREENSAVER] = "ScreenSaver",
+ [KEY_VOICECOMMAND] = "VoiceCommand",
+ [KEY_BRIGHTNESS_MIN] = "BrightnessMin",
+ [KEY_BRIGHTNESS_MAX] = "BrightnessMax",
+ [KEY_BRIGHTNESS_AUTO] = "BrightnessAuto",
};
static const char *relatives[REL_MAX + 1] = {
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index eb5700e..8fae6e3 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -729,6 +729,13 @@
case 0x06c: map_key_clear(KEY_YELLOW); break;
case 0x06d: map_key_clear(KEY_ZOOM); break;
+ case 0x06f: map_key_clear(KEY_BRIGHTNESSUP); break;
+ case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN); break;
+ case 0x072: map_key_clear(KEY_BRIGHTNESS_TOGGLE); break;
+ case 0x073: map_key_clear(KEY_BRIGHTNESS_MIN); break;
+ case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break;
+ case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break;
+
case 0x082: map_key_clear(KEY_VIDEO_NEXT); break;
case 0x083: map_key_clear(KEY_LAST); break;
case 0x084: map_key_clear(KEY_ENTER); break;
@@ -769,6 +776,7 @@
case 0x0bf: map_key_clear(KEY_SLOW); break;
case 0x0cd: map_key_clear(KEY_PLAYPAUSE); break;
+ case 0x0cf: map_key_clear(KEY_VOICECOMMAND); break;
case 0x0e0: map_abs_clear(ABS_VOLUME); break;
case 0x0e2: map_key_clear(KEY_MUTE); break;
case 0x0e5: map_key_clear(KEY_BASSBOOST); break;
@@ -776,6 +784,7 @@
case 0x0ea: map_key_clear(KEY_VOLUMEDOWN); break;
case 0x0f5: map_key_clear(KEY_SLOW); break;
+ case 0x181: map_key_clear(KEY_BUTTONCONFIG); break;
case 0x182: map_key_clear(KEY_BOOKMARKS); break;
case 0x183: map_key_clear(KEY_CONFIG); break;
case 0x184: map_key_clear(KEY_WORDPROCESSOR); break;
@@ -789,6 +798,8 @@
case 0x18c: map_key_clear(KEY_VOICEMAIL); break;
case 0x18d: map_key_clear(KEY_ADDRESSBOOK); break;
case 0x18e: map_key_clear(KEY_CALENDAR); break;
+ case 0x18f: map_key_clear(KEY_TASKMANAGER); break;
+ case 0x190: map_key_clear(KEY_JOURNAL); break;
case 0x191: map_key_clear(KEY_FINANCE); break;
case 0x192: map_key_clear(KEY_CALC); break;
case 0x193: map_key_clear(KEY_PLAYER); break;
@@ -797,10 +808,16 @@
case 0x199: map_key_clear(KEY_CHAT); break;
case 0x19c: map_key_clear(KEY_LOGOFF); break;
case 0x19e: map_key_clear(KEY_COFFEE); break;
+ case 0x19f: map_key_clear(KEY_CONTROLPANEL); break;
+ case 0x1a2: map_key_clear(KEY_APPSELECT); break;
+ case 0x1a3: map_key_clear(KEY_NEXT); break;
+ case 0x1a4: map_key_clear(KEY_PREVIOUS); break;
case 0x1a6: map_key_clear(KEY_HELP); break;
case 0x1a7: map_key_clear(KEY_DOCUMENTS); break;
case 0x1ab: map_key_clear(KEY_SPELLCHECK); break;
case 0x1ae: map_key_clear(KEY_KEYBOARD); break;
+ case 0x1b1: map_key_clear(KEY_SCREENSAVER); break;
+ case 0x1b4: map_key_clear(KEY_FILE); break;
case 0x1b6: map_key_clear(KEY_IMAGES); break;
case 0x1b7: map_key_clear(KEY_AUDIO); break;
case 0x1b8: map_key_clear(KEY_VIDEO); break;
@@ -1358,8 +1375,9 @@
* UGCI) cram a lot of unrelated inputs into the
* same interface. */
hidinput->report = report;
- if (drv->input_configured)
- drv->input_configured(hid, hidinput);
+ if (drv->input_configured &&
+ drv->input_configured(hid, hidinput))
+ goto out_cleanup;
if (input_register_device(hidinput->input))
goto out_cleanup;
hidinput = NULL;
@@ -1380,8 +1398,9 @@
}
if (hidinput) {
- if (drv->input_configured)
- drv->input_configured(hid, hidinput);
+ if (drv->input_configured &&
+ drv->input_configured(hid, hidinput))
+ goto out_cleanup;
if (input_register_device(hidinput->input))
goto out_cleanup;
}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 3d8e58a..fb9ac12 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -443,6 +443,16 @@
(usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON)
td->mt_flags |= INPUT_MT_POINTER;
+ /* Only map fields from TouchScreen or TouchPad collections.
+ * We need to ignore fields that belong to other collections
+ * such as Mouse that might have the same GenericDesktop usages. */
+ if (field->application == HID_DG_TOUCHSCREEN)
+ set_bit(INPUT_PROP_DIRECT, hi->input->propbit);
+ else if (field->application == HID_DG_TOUCHPAD)
+ set_bit(INPUT_PROP_POINTER, hi->input->propbit);
+ else
+ return 0;
+
if (usage->usage_index)
prev_usage = &field->usage[usage->usage_index - 1];
@@ -772,12 +782,13 @@
mt_sync_frame(td, report->field[0]->hidinput->input);
}
-static void mt_touch_input_configured(struct hid_device *hdev,
+static int mt_touch_input_configured(struct hid_device *hdev,
struct hid_input *hi)
{
struct mt_device *td = hid_get_drvdata(hdev);
struct mt_class *cls = &td->mtclass;
struct input_dev *input = hi->input;
+ int ret;
if (!td->maxcontacts)
td->maxcontacts = MT_DEFAULT_MAXCONTACT;
@@ -792,9 +803,12 @@
if (cls->quirks & MT_QUIRK_NOT_SEEN_MEANS_UP)
td->mt_flags |= INPUT_MT_DROP_UNUSED;
- input_mt_init_slots(input, td->maxcontacts, td->mt_flags);
+ ret = input_mt_init_slots(input, td->maxcontacts, td->mt_flags);
+ if (ret)
+ return ret;
td->mt_flags = 0;
+ return 0;
}
static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
@@ -927,19 +941,21 @@
cls->quirks &= ~MT_QUIRK_CONTACT_CNT_ACCURATE;
}
-static void mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
+static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
{
struct mt_device *td = hid_get_drvdata(hdev);
char *name = kstrdup(hdev->name, GFP_KERNEL);
+ int ret = 0;
if (name)
hi->input->name = name;
if (hi->report->id == td->mt_report_id)
- mt_touch_input_configured(hdev, hi);
+ ret = mt_touch_input_configured(hdev, hi);
if (hi->report->id == td->pen_report_id)
mt_pen_input_configured(hdev, hi);
+ return ret;
}
static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 10aa9ef..145c986 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -35,6 +35,7 @@
*/
struct iio_event_interface {
wait_queue_head_t wait;
+ struct mutex read_lock;
DECLARE_KFIFO(det_events, struct iio_event_data, 16);
struct list_head dev_attr_list;
@@ -97,14 +98,16 @@
if (count < sizeof(struct iio_event_data))
return -EINVAL;
- spin_lock_irq(&ev_int->wait.lock);
+ if (mutex_lock_interruptible(&ev_int->read_lock))
+ return -ERESTARTSYS;
+
if (kfifo_is_empty(&ev_int->det_events)) {
if (filep->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
goto error_unlock;
}
/* Blocking on device; waiting for something to be there */
- ret = wait_event_interruptible_locked_irq(ev_int->wait,
+ ret = wait_event_interruptible(ev_int->wait,
!kfifo_is_empty(&ev_int->det_events));
if (ret)
goto error_unlock;
@@ -114,7 +117,7 @@
ret = kfifo_to_user(&ev_int->det_events, buf, count, &copied);
error_unlock:
- spin_unlock_irq(&ev_int->wait.lock);
+ mutex_unlock(&ev_int->read_lock);
return ret ? ret : copied;
}
@@ -371,6 +374,7 @@
{
INIT_KFIFO(ev_int->det_events);
init_waitqueue_head(&ev_int->wait);
+ mutex_init(&ev_int->read_lock);
}
static const char *iio_event_group_name = "events";
@@ -434,6 +438,7 @@
error_free_setup_event_lines:
__iio_remove_event_config_attrs(indio_dev);
+ mutex_destroy(&indio_dev->event_interface->read_lock);
kfree(indio_dev->event_interface);
error_ret:
@@ -446,5 +451,6 @@
return;
__iio_remove_event_config_attrs(indio_dev);
kfree(indio_dev->event_interface->group.attrs);
+ mutex_destroy(&indio_dev->event_interface->read_lock);
kfree(indio_dev->event_interface);
}
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74..518efa2 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -174,6 +174,25 @@
To compile this driver as a module, choose M here: the
module will be called apm-power.
+config INPUT_KEYRESET
+ tristate "Reset key"
+ depends on INPUT
+ select INPUT_KEYCOMBO
+ ---help---
+ Say Y here if you want to reboot when some keys are pressed;
+
+ To compile this driver as a module, choose M here: the
+ module will be called keyreset.
+
+config INPUT_KEYCOMBO
+ tristate "Key combo"
+ depends on INPUT
+ ---help---
+ Say Y here if you want to take action when some keys are pressed;
+
+ To compile this driver as a module, choose M here: the
+ module will be called keycombo.
+
comment "Input Device Drivers"
source "drivers/input/keyboard/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f63..ee4c0652 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -25,3 +25,6 @@
obj-$(CONFIG_INPUT_MISC) += misc/
obj-$(CONFIG_INPUT_APMPOWER) += apm-power.o
+obj-$(CONFIG_INPUT_KEYRESET) += keyreset.o
+obj-$(CONFIG_INPUT_KEYCOMBO) += keycombo.o
+
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index c122dd2..f4897c8 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -26,6 +26,7 @@
#include <linux/major.h>
#include <linux/device.h>
#include <linux/cdev.h>
+#include <linux/wakelock.h>
#include "input-compat.h"
struct evdev {
@@ -46,6 +47,9 @@
unsigned int tail;
unsigned int packet_head; /* [future] position of the first element of next packet */
spinlock_t buffer_lock; /* protects access to buffer, head and tail */
+ struct wake_lock wake_lock;
+ bool use_wake_lock;
+ char name[28];
struct fasync_struct *fasync;
struct evdev *evdev;
struct list_head node;
@@ -73,10 +77,14 @@
client->buffer[client->tail].value = 0;
client->packet_head = client->tail;
+ if (client->use_wake_lock)
+ wake_unlock(&client->wake_lock);
}
if (event->type == EV_SYN && event->code == SYN_REPORT) {
client->packet_head = client->head;
+ if (client->use_wake_lock)
+ wake_lock(&client->wake_lock);
kill_fasync(&client->fasync, SIGIO, POLL_IN);
}
}
@@ -291,6 +299,8 @@
mutex_unlock(&evdev->mutex);
evdev_detach_client(evdev, client);
+ if (client->use_wake_lock)
+ wake_lock_destroy(&client->wake_lock);
if (is_vmalloc_addr(client))
vfree(client);
@@ -328,6 +338,8 @@
client->bufsize = bufsize;
spin_lock_init(&client->buffer_lock);
+ snprintf(client->name, sizeof(client->name), "%s-%d",
+ dev_name(&evdev->dev), task_tgid_vnr(current));
client->evdev = evdev;
evdev_attach_client(evdev, client);
@@ -394,6 +406,9 @@
if (have_event) {
*event = client->buffer[client->tail++];
client->tail &= client->bufsize - 1;
+ if (client->use_wake_lock &&
+ client->packet_head == client->tail)
+ wake_unlock(&client->wake_lock);
}
spin_unlock_irq(&client->buffer_lock);
@@ -682,6 +697,35 @@
return 0;
}
+static int evdev_enable_suspend_block(struct evdev *evdev,
+ struct evdev_client *client)
+{
+ if (client->use_wake_lock)
+ return 0;
+
+ spin_lock_irq(&client->buffer_lock);
+ wake_lock_init(&client->wake_lock, WAKE_LOCK_SUSPEND, client->name);
+ client->use_wake_lock = true;
+ if (client->packet_head != client->tail)
+ wake_lock(&client->wake_lock);
+ spin_unlock_irq(&client->buffer_lock);
+ return 0;
+}
+
+static int evdev_disable_suspend_block(struct evdev *evdev,
+ struct evdev_client *client)
+{
+ if (!client->use_wake_lock)
+ return 0;
+
+ spin_lock_irq(&client->buffer_lock);
+ client->use_wake_lock = false;
+ wake_lock_destroy(&client->wake_lock);
+ spin_unlock_irq(&client->buffer_lock);
+
+ return 0;
+}
+
static long evdev_do_ioctl(struct file *file, unsigned int cmd,
void __user *p, int compat_mode)
{
@@ -763,6 +807,15 @@
case EVIOCSKEYCODE_V2:
return evdev_handle_set_keycode_v2(dev, p);
+
+ case EVIOCGSUSPENDBLOCK:
+ return put_user(client->use_wake_lock, ip);
+
+ case EVIOCSSUSPENDBLOCK:
+ if (p)
+ return evdev_enable_suspend_block(evdev, client);
+ else
+ return evdev_disable_suspend_block(evdev, client);
}
size = _IOC_SIZE(cmd);
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index da739d9..73f74b7 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -487,14 +487,14 @@
*/
static void gameport_init_port(struct gameport *gameport)
{
- static atomic_t gameport_no = ATOMIC_INIT(0);
+ static atomic_t gameport_no = ATOMIC_INIT(-1);
__module_get(THIS_MODULE);
mutex_init(&gameport->drv_mutex);
device_initialize(&gameport->dev);
dev_set_name(&gameport->dev, "gameport%lu",
- (unsigned long)atomic_inc_return(&gameport_no) - 1);
+ (unsigned long)atomic_inc_return(&gameport_no));
gameport->dev.bus = &gameport_bus;
gameport->dev.release = gameport_release_port;
if (gameport->parent)
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 685e125..4614d17 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -31,12 +31,14 @@
* - the iForce driver drivers/char/joystick/iforce.c
* - the skeleton-driver drivers/usb/usb-skeleton.c
* - Xbox 360 information http://www.free60.org/wiki/Gamepad
+ * - Xbox One information https://github.com/quantus/xbox-one-controller-protocol
*
* Thanks to:
* - ITO Takayuki for providing essential xpad information on his website
* - Vojtech Pavlik - iforce driver / input subsystem
* - Greg Kroah-Hartman - usb-skeleton driver
* - XBOX Linux project - extra USB id's
+ * - Pekka Pöyry (quantus) - Xbox One controller reverse engineering
*
* TODO:
* - fine tune axes (especially trigger axes)
@@ -96,7 +98,8 @@
#define XTYPE_XBOX 0
#define XTYPE_XBOX360 1
#define XTYPE_XBOX360W 2
-#define XTYPE_UNKNOWN 3
+#define XTYPE_XBOXONE 3
+#define XTYPE_UNKNOWN 4
static bool dpad_to_buttons;
module_param(dpad_to_buttons, bool, S_IRUGO);
@@ -122,9 +125,15 @@
{ 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX },
{ 0x045e, 0x0289, "Microsoft X-Box pad v2 (US)", 0, XTYPE_XBOX },
{ 0x045e, 0x028e, "Microsoft X-Box 360 pad", 0, XTYPE_XBOX360 },
+ { 0x045e, 0x02d1, "Microsoft X-Box One pad", 0, XTYPE_XBOXONE },
+ { 0x045e, 0x02dd, "Microsoft X-Box One pad (Covert Forces)", 0, XTYPE_XBOXONE },
{ 0x045e, 0x0291, "Xbox 360 Wireless Receiver (XBOX)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
+ { 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
+ { 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 },
+ { 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 },
+ { 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 },
{ 0x046d, 0xc242, "Logitech Chillstream Controller", 0, XTYPE_XBOX360 },
{ 0x046d, 0xca84, "Logitech Xbox Cordless Controller", 0, XTYPE_XBOX },
{ 0x046d, 0xca88, "Logitech Compact Controller for Xbox", 0, XTYPE_XBOX },
@@ -137,10 +146,17 @@
{ 0x0738, 0x4540, "Mad Catz Beat Pad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x0738, 0x4556, "Mad Catz Lynx Wireless Controller", 0, XTYPE_XBOX },
{ 0x0738, 0x4716, "Mad Catz Wired Xbox 360 Controller", 0, XTYPE_XBOX360 },
+ { 0x0738, 0x4718, "Mad Catz Street Fighter IV FightStick SE", 0, XTYPE_XBOX360 },
+ { 0x0738, 0x4726, "Mad Catz Xbox 360 Controller", 0, XTYPE_XBOX360 },
{ 0x0738, 0x4728, "Mad Catz Street Fighter IV FightPad", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0738, 0x4738, "Mad Catz Wired Xbox 360 Controller (SFIV)", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x0738, 0x4740, "Mad Catz Beat Pad", 0, XTYPE_XBOX360 },
{ 0x0738, 0x6040, "Mad Catz Beat Pad Pro", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
+ { 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 },
{ 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 },
+ { 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
{ 0x0c12, 0x8802, "Zeroplus Xbox Controller", 0, XTYPE_XBOX },
{ 0x0c12, 0x8809, "RedOctane Xbox Dance Pad", DANCEPAD_MAP_CONFIG, XTYPE_XBOX },
{ 0x0c12, 0x880a, "Pelican Eclipse PL-2023", 0, XTYPE_XBOX },
@@ -153,28 +169,51 @@
{ 0x0e6f, 0x0005, "Eclipse wireless Controller", 0, XTYPE_XBOX },
{ 0x0e6f, 0x0006, "Edge wireless Controller", 0, XTYPE_XBOX },
{ 0x0e6f, 0x0105, "HSM3 Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x0e6f, 0x0113, "Afterglow AX.1 Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0e6f, 0x0201, "Pelican PL-3601 'TSZ' Wired Xbox 360 Controller", 0, XTYPE_XBOX360 },
{ 0x0e6f, 0x0213, "Afterglow Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0e6f, 0x021f, "Rock Candy Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x0e6f, 0x0301, "Logic3 Controller", 0, XTYPE_XBOX360 },
+ { 0x0e6f, 0x0401, "Logic3 Controller", 0, XTYPE_XBOX360 },
{ 0x0e8f, 0x0201, "SmartJoy Frag Xpad/PS2 adaptor", 0, XTYPE_XBOX },
+ { 0x0e8f, 0x3008, "Generic xbox control (dealextreme)", 0, XTYPE_XBOX },
+ { 0x0f0d, 0x000a, "Hori Co. DOA4 FightStick", 0, XTYPE_XBOX360 },
{ 0x0f0d, 0x000d, "Hori Fighting Stick EX2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0f0d, 0x0016, "Hori Real Arcade Pro.EX", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
{ 0x102c, 0xff0c, "Joytech Wireless Advanced Controller", 0, XTYPE_XBOX },
{ 0x12ab, 0x0004, "Honey Bee Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x12ab, 0x0301, "PDP AFTERGLOW AX.1", 0, XTYPE_XBOX360 },
{ 0x12ab, 0x8809, "Xbox DDR dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x1430, 0x4748, "RedOctane Guitar Hero X-plorer", 0, XTYPE_XBOX360 },
{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
- { 0x1689, 0xfd00, "Razer Onza Tournament Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
- { 0x1689, 0xfd01, "Razer Onza Classic Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+ { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
+ { 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
+ { 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
+ { 0x162e, 0xbeef, "Joytech Neo-Se Take2", 0, XTYPE_XBOX360 },
+ { 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 },
+ { 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5d04, "Razer Sabertooth", 0, XTYPE_XBOX360 },
{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x1bad, 0xf016, "Mad Catz Xbox 360 Controller", 0, XTYPE_XBOX360 },
+ { 0x1bad, 0xf023, "MLG Pro Circuit Controller (Xbox)", 0, XTYPE_XBOX360 },
{ 0x1bad, 0xf028, "Street Fighter IV FightPad", 0, XTYPE_XBOX360 },
+ { 0x1bad, 0xf038, "Street Fighter IV FightStick TE", 0, XTYPE_XBOX360 },
+ { 0x1bad, 0xf900, "Harmonix Xbox 360 Controller", 0, XTYPE_XBOX360 },
{ 0x1bad, 0xf901, "Gamestop Xbox 360 Controller", 0, XTYPE_XBOX360 },
{ 0x1bad, 0xf903, "Tron Xbox 360 controller", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5303, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5500, "Hori XBOX 360 EX 2 with Turbo", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5501, "Hori Real Arcade Pro VX-SA", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5506, "Hori SOULCALIBUR V Stick", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5b02, "Thrustmaster, Inc. GPX Controller", 0, XTYPE_XBOX360 },
+ { 0x24c6, 0x5b03, "Thrustmaster Ferrari 458 Racing Wheel", 0, XTYPE_XBOX360 },
{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
};
@@ -205,7 +244,6 @@
-1
};
-
static const signed short xpad360_btn[] = { /* buttons for x360 controller */
BTN_TL, BTN_TR, /* Button LB/RB */
BTN_MODE, /* The big X button */
@@ -230,10 +268,12 @@
-1
};
-/* Xbox 360 has a vendor-specific class, so we cannot match it with only
+/*
+ * Xbox 360 has a vendor-specific class, so we cannot match it with only
* USB_INTERFACE_INFO (also specifically refused by USB subsystem), so we
* match against vendor id as well. Wired Xbox 360 devices have protocol 1,
- * wireless controllers have protocol 129. */
+ * wireless controllers have protocol 129.
+ */
#define XPAD_XBOX360_VENDOR_PROTOCOL(vend,pr) \
.match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_INFO, \
.idVendor = (vend), \
@@ -244,9 +284,21 @@
{ XPAD_XBOX360_VENDOR_PROTOCOL(vend,1) }, \
{ XPAD_XBOX360_VENDOR_PROTOCOL(vend,129) }
+/* The Xbox One controller uses subclass 71 and protocol 208. */
+#define XPAD_XBOXONE_VENDOR_PROTOCOL(vend, pr) \
+ .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_INFO, \
+ .idVendor = (vend), \
+ .bInterfaceClass = USB_CLASS_VENDOR_SPEC, \
+ .bInterfaceSubClass = 71, \
+ .bInterfaceProtocol = (pr)
+#define XPAD_XBOXONE_VENDOR(vend) \
+ { XPAD_XBOXONE_VENDOR_PROTOCOL(vend, 208) }
+
static struct usb_device_id xpad_table[] = {
{ USB_INTERFACE_INFO('X', 'B', 0) }, /* X-Box USB-IF not approved class */
+ XPAD_XBOX360_VENDOR(0x044f), /* Thrustmaster X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x045e), /* Microsoft X-Box 360 controllers */
+ XPAD_XBOXONE_VENDOR(0x045e), /* Microsoft X-Box One controllers */
XPAD_XBOX360_VENDOR(0x046d), /* Logitech X-Box 360 style controllers */
XPAD_XBOX360_VENDOR(0x0738), /* Mad Catz X-Box 360 controllers */
{ USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */
@@ -258,6 +310,9 @@
XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */
XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */
XPAD_XBOX360_VENDOR(0x24c6), /* PowerA Controllers */
+ XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */
+ XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */
+ XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */
{ }
};
@@ -274,15 +329,10 @@
unsigned char *idata; /* input data */
dma_addr_t idata_dma;
- struct urb *bulk_out;
- unsigned char *bdata;
-
-#if defined(CONFIG_JOYSTICK_XPAD_FF) || defined(CONFIG_JOYSTICK_XPAD_LEDS)
struct urb *irq_out; /* urb for interrupt out report */
unsigned char *odata; /* output data */
dma_addr_t odata_dma;
struct mutex odata_mutex;
-#endif
#if defined(CONFIG_JOYSTICK_XPAD_LEDS)
struct xpad_led *led;
@@ -292,6 +342,8 @@
int mapping; /* map d-pad to buttons or to axes */
int xtype; /* type of xbox device */
+ int pad_nr; /* the order x360 pads were attached */
+ const char *name; /* name of the device */
};
/*
@@ -303,7 +355,6 @@
* The used report descriptor was taken from ITO Takayukis website:
* http://euc.jp/periphs/xbox-controller.ja.html
*/
-
static void xpad_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
{
struct input_dev *dev = xpad->dev;
@@ -386,7 +437,16 @@
input_report_key(dev, BTN_TRIGGER_HAPPY2, data[2] & 0x08);
input_report_key(dev, BTN_TRIGGER_HAPPY3, data[2] & 0x01);
input_report_key(dev, BTN_TRIGGER_HAPPY4, data[2] & 0x02);
- } else {
+ }
+
+ /*
+ * This should be a simple else block. However historically
+ * xbox360w has mapped DPAD to buttons while xbox360 did not. This
+ * made no sense, but now we can not just switch back and have to
+ * support both behaviors.
+ */
+ if (!(xpad->mapping & MAP_DPAD_TO_BUTTONS) ||
+ xpad->xtype == XTYPE_XBOX360W) {
input_report_abs(dev, ABS_HAT0X,
!!(data[2] & 0x08) - !!(data[2] & 0x04));
input_report_abs(dev, ABS_HAT0Y,
@@ -436,6 +496,8 @@
input_sync(dev);
}
+static void xpad_identify_controller(struct usb_xpad *xpad);
+
/*
* xpad360w_process_packet
*
@@ -450,14 +512,17 @@
* 01.1 - Pad state (Bytes 4+) valid
*
*/
-
static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
{
/* Presence change */
if (data[0] & 0x08) {
if (data[1] & 0x80) {
xpad->pad_present = 1;
- usb_submit_urb(xpad->bulk_out, GFP_ATOMIC);
+ /*
+ * Light up the segment corresponding to
+ * controller number.
+ */
+ xpad_identify_controller(xpad);
} else
xpad->pad_present = 0;
}
@@ -469,6 +534,105 @@
xpad360_process_packet(xpad, cmd, &data[4]);
}
+/*
+ * xpadone_process_buttons
+ *
+ * Process a button update packet from an Xbox one controller.
+ */
+static void xpadone_process_buttons(struct usb_xpad *xpad,
+ struct input_dev *dev,
+ unsigned char *data)
+{
+ /* menu/view buttons */
+ input_report_key(dev, BTN_START, data[4] & 0x04);
+ input_report_key(dev, BTN_SELECT, data[4] & 0x08);
+
+ /* buttons A,B,X,Y */
+ input_report_key(dev, BTN_A, data[4] & 0x10);
+ input_report_key(dev, BTN_B, data[4] & 0x20);
+ input_report_key(dev, BTN_X, data[4] & 0x40);
+ input_report_key(dev, BTN_Y, data[4] & 0x80);
+
+ /* digital pad */
+ if (xpad->mapping & MAP_DPAD_TO_BUTTONS) {
+ /* dpad as buttons (left, right, up, down) */
+ input_report_key(dev, BTN_TRIGGER_HAPPY1, data[5] & 0x04);
+ input_report_key(dev, BTN_TRIGGER_HAPPY2, data[5] & 0x08);
+ input_report_key(dev, BTN_TRIGGER_HAPPY3, data[5] & 0x01);
+ input_report_key(dev, BTN_TRIGGER_HAPPY4, data[5] & 0x02);
+ } else {
+ input_report_abs(dev, ABS_HAT0X,
+ !!(data[5] & 0x08) - !!(data[5] & 0x04));
+ input_report_abs(dev, ABS_HAT0Y,
+ !!(data[5] & 0x02) - !!(data[5] & 0x01));
+ }
+
+ /* TL/TR */
+ input_report_key(dev, BTN_TL, data[5] & 0x10);
+ input_report_key(dev, BTN_TR, data[5] & 0x20);
+
+ /* stick press left/right */
+ input_report_key(dev, BTN_THUMBL, data[5] & 0x40);
+ input_report_key(dev, BTN_THUMBR, data[5] & 0x80);
+
+ if (!(xpad->mapping & MAP_STICKS_TO_NULL)) {
+ /* left stick */
+ input_report_abs(dev, ABS_X,
+ (__s16) le16_to_cpup((__le16 *)(data + 10)));
+ input_report_abs(dev, ABS_Y,
+ ~(__s16) le16_to_cpup((__le16 *)(data + 12)));
+
+ /* right stick */
+ input_report_abs(dev, ABS_RX,
+ (__s16) le16_to_cpup((__le16 *)(data + 14)));
+ input_report_abs(dev, ABS_RY,
+ ~(__s16) le16_to_cpup((__le16 *)(data + 16)));
+ }
+
+ /* triggers left/right */
+ if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) {
+ input_report_key(dev, BTN_TL2,
+ (__u16) le16_to_cpup((__le16 *)(data + 6)));
+ input_report_key(dev, BTN_TR2,
+ (__u16) le16_to_cpup((__le16 *)(data + 8)));
+ } else {
+ input_report_abs(dev, ABS_Z,
+ (__u16) le16_to_cpup((__le16 *)(data + 6)));
+ input_report_abs(dev, ABS_RZ,
+ (__u16) le16_to_cpup((__le16 *)(data + 8)));
+ }
+
+ input_sync(dev);
+}
+
+/*
+ * xpadone_process_packet
+ *
+ * Completes a request by converting the data into events for the
+ * input subsystem. This version is for the Xbox One controller.
+ *
+ * The report format was gleaned from
+ * https://github.com/kylelemons/xbox/blob/master/xbox.go
+ */
+
+static void xpadone_process_packet(struct usb_xpad *xpad,
+ u16 cmd, unsigned char *data)
+{
+ struct input_dev *dev = xpad->dev;
+
+ switch (data[0]) {
+ case 0x20:
+ xpadone_process_buttons(xpad, dev, data);
+ break;
+
+ case 0x07:
+ /* the xbox button has its own special report */
+ input_report_key(dev, BTN_MODE, data[4] & 0x01);
+ input_sync(dev);
+ break;
+ }
+}
+
static void xpad_irq_in(struct urb *urb)
{
struct usb_xpad *xpad = urb->context;
@@ -501,6 +665,9 @@
case XTYPE_XBOX360W:
xpad360w_process_packet(xpad, 0, xpad->idata);
break;
+ case XTYPE_XBOXONE:
+ xpadone_process_packet(xpad, 0, xpad->idata);
+ break;
default:
xpad_process_packet(xpad, 0, xpad->idata);
}
@@ -512,29 +679,6 @@
__func__, retval);
}
-static void xpad_bulk_out(struct urb *urb)
-{
- struct usb_xpad *xpad = urb->context;
- struct device *dev = &xpad->intf->dev;
-
- switch (urb->status) {
- case 0:
- /* success */
- break;
- case -ECONNRESET:
- case -ENOENT:
- case -ESHUTDOWN:
- /* this urb is terminated, clean up */
- dev_dbg(dev, "%s - urb shutting down with status: %d\n",
- __func__, urb->status);
- break;
- default:
- dev_dbg(dev, "%s - nonzero urb status received: %d\n",
- __func__, urb->status);
- }
-}
-
-#if defined(CONFIG_JOYSTICK_XPAD_FF) || defined(CONFIG_JOYSTICK_XPAD_LEDS)
static void xpad_irq_out(struct urb *urb)
{
struct usb_xpad *xpad = urb->context;
@@ -572,6 +716,7 @@
static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
{
struct usb_endpoint_descriptor *ep_irq_out;
+ int ep_irq_out_idx;
int error;
if (xpad->xtype == XTYPE_UNKNOWN)
@@ -592,7 +737,10 @@
goto fail2;
}
- ep_irq_out = &intf->cur_altsetting->endpoint[1].desc;
+ /* Xbox One controller has in/out endpoints swapped. */
+ ep_irq_out_idx = xpad->xtype == XTYPE_XBOXONE ? 0 : 1;
+ ep_irq_out = &intf->cur_altsetting->endpoint[ep_irq_out_idx].desc;
+
usb_fill_int_urb(xpad->irq_out, xpad->udev,
usb_sndintpipe(xpad->udev, ep_irq_out->bEndpointAddress),
xpad->odata, XPAD_PKT_LEN,
@@ -620,78 +768,115 @@
xpad->odata, xpad->odata_dma);
}
}
-#else
-static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad) { return 0; }
-static void xpad_deinit_output(struct usb_xpad *xpad) {}
-static void xpad_stop_output(struct usb_xpad *xpad) {}
-#endif
+
+static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
+{
+ int retval;
+
+ mutex_lock(&xpad->odata_mutex);
+
+ xpad->odata[0] = 0x08;
+ xpad->odata[1] = 0x00;
+ xpad->odata[2] = 0x0F;
+ xpad->odata[3] = 0xC0;
+ xpad->odata[4] = 0x00;
+ xpad->odata[5] = 0x00;
+ xpad->odata[6] = 0x00;
+ xpad->odata[7] = 0x00;
+ xpad->odata[8] = 0x00;
+ xpad->odata[9] = 0x00;
+ xpad->odata[10] = 0x00;
+ xpad->odata[11] = 0x00;
+ xpad->irq_out->transfer_buffer_length = 12;
+
+ retval = usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+
+ mutex_unlock(&xpad->odata_mutex);
+
+ return retval;
+}
#ifdef CONFIG_JOYSTICK_XPAD_FF
static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect)
{
struct usb_xpad *xpad = input_get_drvdata(dev);
+ __u16 strong;
+ __u16 weak;
- if (effect->type == FF_RUMBLE) {
- __u16 strong = effect->u.rumble.strong_magnitude;
- __u16 weak = effect->u.rumble.weak_magnitude;
+ if (effect->type != FF_RUMBLE)
+ return 0;
- switch (xpad->xtype) {
+ strong = effect->u.rumble.strong_magnitude;
+ weak = effect->u.rumble.weak_magnitude;
- case XTYPE_XBOX:
- xpad->odata[0] = 0x00;
- xpad->odata[1] = 0x06;
- xpad->odata[2] = 0x00;
- xpad->odata[3] = strong / 256; /* left actuator */
- xpad->odata[4] = 0x00;
- xpad->odata[5] = weak / 256; /* right actuator */
- xpad->irq_out->transfer_buffer_length = 6;
+ switch (xpad->xtype) {
+ case XTYPE_XBOX:
+ xpad->odata[0] = 0x00;
+ xpad->odata[1] = 0x06;
+ xpad->odata[2] = 0x00;
+ xpad->odata[3] = strong / 256; /* left actuator */
+ xpad->odata[4] = 0x00;
+ xpad->odata[5] = weak / 256; /* right actuator */
+ xpad->irq_out->transfer_buffer_length = 6;
+ break;
- return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+ case XTYPE_XBOX360:
+ xpad->odata[0] = 0x00;
+ xpad->odata[1] = 0x08;
+ xpad->odata[2] = 0x00;
+ xpad->odata[3] = strong / 256; /* left actuator? */
+ xpad->odata[4] = weak / 256; /* right actuator? */
+ xpad->odata[5] = 0x00;
+ xpad->odata[6] = 0x00;
+ xpad->odata[7] = 0x00;
+ xpad->irq_out->transfer_buffer_length = 8;
+ break;
- case XTYPE_XBOX360:
- xpad->odata[0] = 0x00;
- xpad->odata[1] = 0x08;
- xpad->odata[2] = 0x00;
- xpad->odata[3] = strong / 256; /* left actuator? */
- xpad->odata[4] = weak / 256; /* right actuator? */
- xpad->odata[5] = 0x00;
- xpad->odata[6] = 0x00;
- xpad->odata[7] = 0x00;
- xpad->irq_out->transfer_buffer_length = 8;
+ case XTYPE_XBOX360W:
+ xpad->odata[0] = 0x00;
+ xpad->odata[1] = 0x01;
+ xpad->odata[2] = 0x0F;
+ xpad->odata[3] = 0xC0;
+ xpad->odata[4] = 0x00;
+ xpad->odata[5] = strong / 256;
+ xpad->odata[6] = weak / 256;
+ xpad->odata[7] = 0x00;
+ xpad->odata[8] = 0x00;
+ xpad->odata[9] = 0x00;
+ xpad->odata[10] = 0x00;
+ xpad->odata[11] = 0x00;
+ xpad->irq_out->transfer_buffer_length = 12;
+ break;
- return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+ case XTYPE_XBOXONE:
+ xpad->odata[0] = 0x09; /* activate rumble */
+ xpad->odata[1] = 0x08;
+ xpad->odata[2] = 0x00;
+ xpad->odata[3] = 0x08; /* continuous effect */
+ xpad->odata[4] = 0x00; /* simple rumble mode */
+ xpad->odata[5] = 0x03; /* L and R actuator only */
+ xpad->odata[6] = 0x00; /* TODO: LT actuator */
+ xpad->odata[7] = 0x00; /* TODO: RT actuator */
+ xpad->odata[8] = strong / 256; /* left actuator */
+ xpad->odata[9] = weak / 256; /* right actuator */
+ xpad->odata[10] = 0x80; /* length of pulse */
+ xpad->odata[11] = 0x00; /* stop period of pulse */
+ xpad->irq_out->transfer_buffer_length = 12;
+ break;
- case XTYPE_XBOX360W:
- xpad->odata[0] = 0x00;
- xpad->odata[1] = 0x01;
- xpad->odata[2] = 0x0F;
- xpad->odata[3] = 0xC0;
- xpad->odata[4] = 0x00;
- xpad->odata[5] = strong / 256;
- xpad->odata[6] = weak / 256;
- xpad->odata[7] = 0x00;
- xpad->odata[8] = 0x00;
- xpad->odata[9] = 0x00;
- xpad->odata[10] = 0x00;
- xpad->odata[11] = 0x00;
- xpad->irq_out->transfer_buffer_length = 12;
-
- return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
-
- default:
- dev_dbg(&xpad->dev->dev,
- "%s - rumble command sent to unsupported xpad type: %d\n",
- __func__, xpad->xtype);
- return -1;
- }
+ default:
+ dev_dbg(&xpad->dev->dev,
+ "%s - rumble command sent to unsupported xpad type: %d\n",
+ __func__, xpad->xtype);
+ return -EINVAL;
}
- return 0;
+ return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
}
static int xpad_init_ff(struct usb_xpad *xpad)
{
- if (xpad->xtype == XTYPE_UNKNOWN)
+ if (xpad->xtype == XTYPE_UNKNOWN || xpad->xtype == XTYPE_XBOXONE)
return 0;
input_set_capability(xpad->dev, EV_FF, FF_RUMBLE);
@@ -705,6 +890,9 @@
#if defined(CONFIG_JOYSTICK_XPAD_LEDS)
#include <linux/leds.h>
+#include <linux/idr.h>
+
+static DEFINE_IDA(xpad_pad_seq);
struct xpad_led {
char name[16];
@@ -712,17 +900,67 @@
struct usb_xpad *xpad;
};
+/**
+ * set the LEDs on Xbox360 / Wireless Controllers
+ * @param command
+ * 0: off
+ * 1: all blink, then previous setting
+ * 2: 1/top-left blink, then on
+ * 3: 2/top-right blink, then on
+ * 4: 3/bottom-left blink, then on
+ * 5: 4/bottom-right blink, then on
+ * 6: 1/top-left on
+ * 7: 2/top-right on
+ * 8: 3/bottom-left on
+ * 9: 4/bottom-right on
+ * 10: rotate
+ * 11: blink, based on previous setting
+ * 12: slow blink, based on previous setting
+ * 13: rotate with two lights
+ * 14: persistent slow all blink
+ * 15: blink once, then previous setting
+ */
static void xpad_send_led_command(struct usb_xpad *xpad, int command)
{
- if (command >= 0 && command < 14) {
- mutex_lock(&xpad->odata_mutex);
+ command %= 16;
+
+ mutex_lock(&xpad->odata_mutex);
+
+ switch (xpad->xtype) {
+ case XTYPE_XBOX360:
xpad->odata[0] = 0x01;
xpad->odata[1] = 0x03;
xpad->odata[2] = command;
xpad->irq_out->transfer_buffer_length = 3;
- usb_submit_urb(xpad->irq_out, GFP_KERNEL);
- mutex_unlock(&xpad->odata_mutex);
+ break;
+ case XTYPE_XBOX360W:
+ xpad->odata[0] = 0x00;
+ xpad->odata[1] = 0x00;
+ xpad->odata[2] = 0x08;
+ xpad->odata[3] = 0x40 + command;
+ xpad->odata[4] = 0x00;
+ xpad->odata[5] = 0x00;
+ xpad->odata[6] = 0x00;
+ xpad->odata[7] = 0x00;
+ xpad->odata[8] = 0x00;
+ xpad->odata[9] = 0x00;
+ xpad->odata[10] = 0x00;
+ xpad->odata[11] = 0x00;
+ xpad->irq_out->transfer_buffer_length = 12;
+ break;
}
+
+ usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+ mutex_unlock(&xpad->odata_mutex);
+}
+
+/*
+ * Light up the segment corresponding to the pad number on
+ * Xbox 360 Controllers.
+ */
+static void xpad_identify_controller(struct usb_xpad *xpad)
+{
+ xpad_send_led_command(xpad, (xpad->pad_nr % 4) + 2);
}
static void xpad_led_set(struct led_classdev *led_cdev,
@@ -736,22 +974,24 @@
static int xpad_led_probe(struct usb_xpad *xpad)
{
- static atomic_t led_seq = ATOMIC_INIT(0);
- long led_no;
struct xpad_led *led;
struct led_classdev *led_cdev;
int error;
- if (xpad->xtype != XTYPE_XBOX360)
+ if (xpad->xtype != XTYPE_XBOX360 && xpad->xtype != XTYPE_XBOX360W)
return 0;
xpad->led = led = kzalloc(sizeof(struct xpad_led), GFP_KERNEL);
if (!led)
return -ENOMEM;
- led_no = (long)atomic_inc_return(&led_seq) - 1;
+ xpad->pad_nr = ida_simple_get(&xpad_pad_seq, 0, 0, GFP_KERNEL);
+ if (xpad->pad_nr < 0) {
+ error = xpad->pad_nr;
+ goto err_free_mem;
+ }
- snprintf(led->name, sizeof(led->name), "xpad%ld", led_no);
+ snprintf(led->name, sizeof(led->name), "xpad%d", xpad->pad_nr);
led->xpad = xpad;
led_cdev = &led->led_cdev;
@@ -759,18 +999,26 @@
led_cdev->brightness_set = xpad_led_set;
error = led_classdev_register(&xpad->udev->dev, led_cdev);
- if (error) {
- kfree(led);
- xpad->led = NULL;
- return error;
+ if (error)
+ goto err_free_id;
+
+ if (xpad->xtype == XTYPE_XBOX360) {
+ /*
+ * Light up the segment corresponding to controller
+ * number on wired devices. On wireless we'll do that
+ * when they respond to "presence" packet.
+ */
+ xpad_identify_controller(xpad);
}
- /*
- * Light up the segment corresponding to controller number
- */
- xpad_send_led_command(xpad, (led_no % 4) + 2);
-
return 0;
+
+err_free_id:
+ ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
+err_free_mem:
+ kfree(led);
+ xpad->led = NULL;
+ return error;
}
static void xpad_led_disconnect(struct usb_xpad *xpad)
@@ -779,15 +1027,16 @@
if (xpad_led) {
led_classdev_unregister(&xpad_led->led_cdev);
+ ida_simple_remove(&xpad_pad_seq, xpad->pad_nr);
kfree(xpad_led);
}
}
#else
static int xpad_led_probe(struct usb_xpad *xpad) { return 0; }
static void xpad_led_disconnect(struct usb_xpad *xpad) { }
+static void xpad_identify_controller(struct usb_xpad *xpad) { }
#endif
-
static int xpad_open(struct input_dev *dev)
{
struct usb_xpad *xpad = input_get_drvdata(dev);
@@ -800,6 +1049,14 @@
if (usb_submit_urb(xpad->irq_in, GFP_KERNEL))
return -EIO;
+ if (xpad->xtype == XTYPE_XBOXONE) {
+ /* Xbox one controller needs to be initialized. */
+ xpad->odata[0] = 0x05;
+ xpad->odata[1] = 0x20;
+ xpad->irq_out->transfer_buffer_length = 2;
+ return usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+ }
+
return 0;
}
@@ -815,6 +1072,7 @@
static void xpad_set_up_abs(struct input_dev *input_dev, signed short abs)
{
+ struct usb_xpad *xpad = input_get_drvdata(input_dev);
set_bit(abs, input_dev->absbit);
switch (abs) {
@@ -826,7 +1084,10 @@
break;
case ABS_Z:
case ABS_RZ: /* the triggers (if mapped to axes) */
- input_set_abs_params(input_dev, abs, 0, 255, 0, 0);
+ if (xpad->xtype == XTYPE_XBOXONE)
+ input_set_abs_params(input_dev, abs, 0, 1023, 0, 0);
+ else
+ input_set_abs_params(input_dev, abs, 0, 255, 0, 0);
break;
case ABS_HAT0X:
case ABS_HAT0Y: /* the d-pad (only if dpad is mapped to axes */
@@ -835,12 +1096,109 @@
}
}
+static void xpad_deinit_input(struct usb_xpad *xpad)
+{
+ xpad_led_disconnect(xpad);
+ input_unregister_device(xpad->dev);
+}
+
+static int xpad_init_input(struct usb_xpad *xpad)
+{
+ struct input_dev *input_dev;
+ int i, error;
+
+ input_dev = input_allocate_device();
+ if (!input_dev)
+ return -ENOMEM;
+
+ xpad->dev = input_dev;
+ input_dev->name = xpad->name;
+ input_dev->phys = xpad->phys;
+ usb_to_input_id(xpad->udev, &input_dev->id);
+ input_dev->dev.parent = &xpad->intf->dev;
+
+ input_set_drvdata(input_dev, xpad);
+
+ input_dev->open = xpad_open;
+ input_dev->close = xpad_close;
+
+ __set_bit(EV_KEY, input_dev->evbit);
+
+ if (!(xpad->mapping & MAP_STICKS_TO_NULL)) {
+ __set_bit(EV_ABS, input_dev->evbit);
+ /* set up axes */
+ for (i = 0; xpad_abs[i] >= 0; i++)
+ xpad_set_up_abs(input_dev, xpad_abs[i]);
+ }
+
+ /* set up standard buttons */
+ for (i = 0; xpad_common_btn[i] >= 0; i++)
+ __set_bit(xpad_common_btn[i], input_dev->keybit);
+
+ /* set up model-specific ones */
+ if (xpad->xtype == XTYPE_XBOX360 || xpad->xtype == XTYPE_XBOX360W ||
+ xpad->xtype == XTYPE_XBOXONE) {
+ for (i = 0; xpad360_btn[i] >= 0; i++)
+ __set_bit(xpad360_btn[i], input_dev->keybit);
+ } else {
+ for (i = 0; xpad_btn[i] >= 0; i++)
+ __set_bit(xpad_btn[i], input_dev->keybit);
+ }
+
+ if (xpad->mapping & MAP_DPAD_TO_BUTTONS) {
+ for (i = 0; xpad_btn_pad[i] >= 0; i++)
+ __set_bit(xpad_btn_pad[i], input_dev->keybit);
+ }
+
+ /*
+ * This should be a simple else block. However historically
+ * xbox360w has mapped DPAD to buttons while xbox360 did not. This
+ * made no sense, but now we can not just switch back and have to
+ * support both behaviors.
+ */
+ if (!(xpad->mapping & MAP_DPAD_TO_BUTTONS) ||
+ xpad->xtype == XTYPE_XBOX360W) {
+ for (i = 0; xpad_abs_pad[i] >= 0; i++)
+ xpad_set_up_abs(input_dev, xpad_abs_pad[i]);
+ }
+
+ if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) {
+ for (i = 0; xpad_btn_triggers[i] >= 0; i++)
+ __set_bit(xpad_btn_triggers[i], input_dev->keybit);
+ } else {
+ for (i = 0; xpad_abs_triggers[i] >= 0; i++)
+ xpad_set_up_abs(input_dev, xpad_abs_triggers[i]);
+ }
+
+ error = xpad_init_ff(xpad);
+ if (error)
+ goto err_free_input;
+
+ error = xpad_led_probe(xpad);
+ if (error)
+ goto err_destroy_ff;
+
+ error = input_register_device(xpad->dev);
+ if (error)
+ goto err_disconnect_led;
+
+ return 0;
+
+err_disconnect_led:
+ xpad_led_disconnect(xpad);
+err_destroy_ff:
+ input_ff_destroy(input_dev);
+err_free_input:
+ input_free_device(input_dev);
+ return error;
+}
+
static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id)
{
struct usb_device *udev = interface_to_usbdev(intf);
struct usb_xpad *xpad;
- struct input_dev *input_dev;
struct usb_endpoint_descriptor *ep_irq_in;
+ int ep_irq_in_idx;
int i, error;
if (intf->cur_altsetting->desc.bNumEndpoints != 2)
@@ -852,30 +1210,41 @@
break;
}
- xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
- input_dev = input_allocate_device();
- if (!xpad || !input_dev) {
- error = -ENOMEM;
- goto fail1;
+ if (xpad_device[i].xtype == XTYPE_XBOXONE &&
+ intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+ /*
+ * The Xbox One controller lists three interfaces all with the
+ * same interface class, subclass and protocol. Differentiate by
+ * interface number.
+ */
+ return -ENODEV;
}
+ xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
+ if (!xpad)
+ return -ENOMEM;
+
+ usb_make_path(udev, xpad->phys, sizeof(xpad->phys));
+ strlcat(xpad->phys, "/input0", sizeof(xpad->phys));
+
xpad->idata = usb_alloc_coherent(udev, XPAD_PKT_LEN,
GFP_KERNEL, &xpad->idata_dma);
if (!xpad->idata) {
error = -ENOMEM;
- goto fail1;
+ goto err_free_mem;
}
xpad->irq_in = usb_alloc_urb(0, GFP_KERNEL);
if (!xpad->irq_in) {
error = -ENOMEM;
- goto fail2;
+ goto err_free_idata;
}
xpad->udev = udev;
xpad->intf = intf;
xpad->mapping = xpad_device[i].mapping;
xpad->xtype = xpad_device[i].xtype;
+ xpad->name = xpad_device[i].name;
if (xpad->xtype == XTYPE_UNKNOWN) {
if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) {
@@ -883,8 +1252,9 @@
xpad->xtype = XTYPE_XBOX360W;
else
xpad->xtype = XTYPE_XBOX360;
- } else
+ } else {
xpad->xtype = XTYPE_XBOX;
+ }
if (dpad_to_buttons)
xpad->mapping |= MAP_DPAD_TO_BUTTONS;
@@ -894,71 +1264,14 @@
xpad->mapping |= MAP_STICKS_TO_NULL;
}
- xpad->dev = input_dev;
- usb_make_path(udev, xpad->phys, sizeof(xpad->phys));
- strlcat(xpad->phys, "/input0", sizeof(xpad->phys));
-
- input_dev->name = xpad_device[i].name;
- input_dev->phys = xpad->phys;
- usb_to_input_id(udev, &input_dev->id);
- input_dev->dev.parent = &intf->dev;
-
- input_set_drvdata(input_dev, xpad);
-
- input_dev->open = xpad_open;
- input_dev->close = xpad_close;
-
- input_dev->evbit[0] = BIT_MASK(EV_KEY);
-
- if (!(xpad->mapping & MAP_STICKS_TO_NULL)) {
- input_dev->evbit[0] |= BIT_MASK(EV_ABS);
- /* set up axes */
- for (i = 0; xpad_abs[i] >= 0; i++)
- xpad_set_up_abs(input_dev, xpad_abs[i]);
- }
-
- /* set up standard buttons */
- for (i = 0; xpad_common_btn[i] >= 0; i++)
- __set_bit(xpad_common_btn[i], input_dev->keybit);
-
- /* set up model-specific ones */
- if (xpad->xtype == XTYPE_XBOX360 || xpad->xtype == XTYPE_XBOX360W) {
- for (i = 0; xpad360_btn[i] >= 0; i++)
- __set_bit(xpad360_btn[i], input_dev->keybit);
- } else {
- for (i = 0; xpad_btn[i] >= 0; i++)
- __set_bit(xpad_btn[i], input_dev->keybit);
- }
-
- if (xpad->mapping & MAP_DPAD_TO_BUTTONS) {
- for (i = 0; xpad_btn_pad[i] >= 0; i++)
- __set_bit(xpad_btn_pad[i], input_dev->keybit);
- } else {
- for (i = 0; xpad_abs_pad[i] >= 0; i++)
- xpad_set_up_abs(input_dev, xpad_abs_pad[i]);
- }
-
- if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) {
- for (i = 0; xpad_btn_triggers[i] >= 0; i++)
- __set_bit(xpad_btn_triggers[i], input_dev->keybit);
- } else {
- for (i = 0; xpad_abs_triggers[i] >= 0; i++)
- xpad_set_up_abs(input_dev, xpad_abs_triggers[i]);
- }
-
error = xpad_init_output(intf, xpad);
if (error)
- goto fail3;
+ goto err_free_in_urb;
- error = xpad_init_ff(xpad);
- if (error)
- goto fail4;
+ /* Xbox One controller has in/out endpoints swapped. */
+ ep_irq_in_idx = xpad->xtype == XTYPE_XBOXONE ? 1 : 0;
+ ep_irq_in = &intf->cur_altsetting->endpoint[ep_irq_in_idx].desc;
- error = xpad_led_probe(xpad);
- if (error)
- goto fail5;
-
- ep_irq_in = &intf->cur_altsetting->endpoint[0].desc;
usb_fill_int_urb(xpad->irq_in, udev,
usb_rcvintpipe(udev, ep_irq_in->bEndpointAddress),
xpad->idata, XPAD_PKT_LEN, xpad_irq_in,
@@ -966,60 +1279,14 @@
xpad->irq_in->transfer_dma = xpad->idata_dma;
xpad->irq_in->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
- error = input_register_device(xpad->dev);
- if (error)
- goto fail6;
-
usb_set_intfdata(intf, xpad);
+ error = xpad_init_input(xpad);
+ if (error)
+ goto err_deinit_output;
+
if (xpad->xtype == XTYPE_XBOX360W) {
/*
- * Setup the message to set the LEDs on the
- * controller when it shows up
- */
- xpad->bulk_out = usb_alloc_urb(0, GFP_KERNEL);
- if (!xpad->bulk_out) {
- error = -ENOMEM;
- goto fail7;
- }
-
- xpad->bdata = kzalloc(XPAD_PKT_LEN, GFP_KERNEL);
- if (!xpad->bdata) {
- error = -ENOMEM;
- goto fail8;
- }
-
- xpad->bdata[2] = 0x08;
- switch (intf->cur_altsetting->desc.bInterfaceNumber) {
- case 0:
- xpad->bdata[3] = 0x42;
- break;
- case 2:
- xpad->bdata[3] = 0x43;
- break;
- case 4:
- xpad->bdata[3] = 0x44;
- break;
- case 6:
- xpad->bdata[3] = 0x45;
- }
-
- ep_irq_in = &intf->cur_altsetting->endpoint[1].desc;
- if (usb_endpoint_is_bulk_out(ep_irq_in)) {
- usb_fill_bulk_urb(xpad->bulk_out, udev,
- usb_sndbulkpipe(udev,
- ep_irq_in->bEndpointAddress),
- xpad->bdata, XPAD_PKT_LEN,
- xpad_bulk_out, xpad);
- } else {
- usb_fill_int_urb(xpad->bulk_out, udev,
- usb_sndintpipe(udev,
- ep_irq_in->bEndpointAddress),
- xpad->bdata, XPAD_PKT_LEN,
- xpad_bulk_out, xpad, 0);
- }
-
- /*
* Submit the int URB immediately rather than waiting for open
* because we get status messages from the device whether
* or not any controllers are attached. In fact, it's
@@ -1029,22 +1296,32 @@
xpad->irq_in->dev = xpad->udev;
error = usb_submit_urb(xpad->irq_in, GFP_KERNEL);
if (error)
- goto fail9;
- }
+ goto err_deinit_input;
+ /*
+ * Send presence packet.
+ * This will force the controller to resend connection packets.
+ * This is useful in the case we activate the module after the
+ * adapter has been plugged in, as it won't automatically
+ * send us info about the controllers.
+ */
+ error = xpad_inquiry_pad_presence(xpad);
+ if (error)
+ goto err_kill_in_urb;
+ }
return 0;
- fail9: kfree(xpad->bdata);
- fail8: usb_free_urb(xpad->bulk_out);
- fail7: input_unregister_device(input_dev);
- input_dev = NULL;
- fail6: xpad_led_disconnect(xpad);
- fail5: if (input_dev)
- input_ff_destroy(input_dev);
- fail4: xpad_deinit_output(xpad);
- fail3: usb_free_urb(xpad->irq_in);
- fail2: usb_free_coherent(udev, XPAD_PKT_LEN, xpad->idata, xpad->idata_dma);
- fail1: input_free_device(input_dev);
+err_kill_in_urb:
+ usb_kill_urb(xpad->irq_in);
+err_deinit_input:
+ xpad_deinit_input(xpad);
+err_deinit_output:
+ xpad_deinit_output(xpad);
+err_free_in_urb:
+ usb_free_urb(xpad->irq_in);
+err_free_idata:
+ usb_free_coherent(udev, XPAD_PKT_LEN, xpad->idata, xpad->idata_dma);
+err_free_mem:
kfree(xpad);
return error;
@@ -1054,13 +1331,10 @@
{
struct usb_xpad *xpad = usb_get_intfdata (intf);
- xpad_led_disconnect(xpad);
- input_unregister_device(xpad->dev);
+ xpad_deinit_input(xpad);
xpad_deinit_output(xpad);
if (xpad->xtype == XTYPE_XBOX360W) {
- usb_kill_urb(xpad->bulk_out);
- usb_free_urb(xpad->bulk_out);
usb_kill_urb(xpad->irq_in);
}
@@ -1068,7 +1342,6 @@
usb_free_coherent(xpad->udev, XPAD_PKT_LEN,
xpad->idata, xpad->idata_dma);
- kfree(xpad->bdata);
kfree(xpad);
usb_set_intfdata(intf, NULL);
diff --git a/drivers/input/keycombo.c b/drivers/input/keycombo.c
new file mode 100644
index 0000000..2fba451
--- /dev/null
+++ b/drivers/input/keycombo.c
@@ -0,0 +1,261 @@
+/* drivers/input/keycombo.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keycombo.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+struct keycombo_state {
+ struct input_handler input_handler;
+ unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+ unsigned long upbit[BITS_TO_LONGS(KEY_CNT)];
+ unsigned long key[BITS_TO_LONGS(KEY_CNT)];
+ spinlock_t lock;
+ struct workqueue_struct *wq;
+ int key_down_target;
+ int key_down;
+ int key_up;
+ struct delayed_work key_down_work;
+ int delay;
+ struct work_struct key_up_work;
+ void (*key_up_fn)(void *);
+ void (*key_down_fn)(void *);
+ void *priv;
+ int key_is_down;
+ struct wakeup_source combo_held_wake_source;
+ struct wakeup_source combo_up_wake_source;
+};
+
+static void do_key_down(struct work_struct *work)
+{
+ struct delayed_work *dwork = container_of(work, struct delayed_work,
+ work);
+ struct keycombo_state *state = container_of(dwork,
+ struct keycombo_state, key_down_work);
+ if (state->key_down_fn)
+ state->key_down_fn(state->priv);
+}
+
+static void do_key_up(struct work_struct *work)
+{
+ struct keycombo_state *state = container_of(work, struct keycombo_state,
+ key_up_work);
+ if (state->key_up_fn)
+ state->key_up_fn(state->priv);
+ __pm_relax(&state->combo_up_wake_source);
+}
+
+static void keycombo_event(struct input_handle *handle, unsigned int type,
+ unsigned int code, int value)
+{
+ unsigned long flags;
+ struct keycombo_state *state = handle->private;
+
+ if (type != EV_KEY)
+ return;
+
+ if (code >= KEY_MAX)
+ return;
+
+ if (!test_bit(code, state->keybit))
+ return;
+
+ spin_lock_irqsave(&state->lock, flags);
+ if (!test_bit(code, state->key) == !value)
+ goto done;
+ __change_bit(code, state->key);
+ if (test_bit(code, state->upbit)) {
+ if (value)
+ state->key_up++;
+ else
+ state->key_up--;
+ } else {
+ if (value)
+ state->key_down++;
+ else
+ state->key_down--;
+ }
+ if (state->key_down == state->key_down_target && state->key_up == 0) {
+ __pm_stay_awake(&state->combo_held_wake_source);
+ state->key_is_down = 1;
+ if (queue_delayed_work(state->wq, &state->key_down_work,
+ state->delay))
+ pr_debug("Key down work already queued!");
+ } else if (state->key_is_down) {
+ if (!cancel_delayed_work(&state->key_down_work)) {
+ __pm_stay_awake(&state->combo_up_wake_source);
+ queue_work(state->wq, &state->key_up_work);
+ }
+ __pm_relax(&state->combo_held_wake_source);
+ state->key_is_down = 0;
+ }
+done:
+ spin_unlock_irqrestore(&state->lock, flags);
+}
+
+static int keycombo_connect(struct input_handler *handler,
+ struct input_dev *dev,
+ const struct input_device_id *id)
+{
+ int i;
+ int ret;
+ struct input_handle *handle;
+ struct keycombo_state *state =
+ container_of(handler, struct keycombo_state, input_handler);
+ for (i = 0; i < KEY_MAX; i++) {
+ if (test_bit(i, state->keybit) && test_bit(i, dev->keybit))
+ break;
+ }
+ if (i == KEY_MAX)
+ return -ENODEV;
+
+ handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+ if (!handle)
+ return -ENOMEM;
+
+ handle->dev = dev;
+ handle->handler = handler;
+ handle->name = KEYCOMBO_NAME;
+ handle->private = state;
+
+ ret = input_register_handle(handle);
+ if (ret)
+ goto err_input_register_handle;
+
+ ret = input_open_device(handle);
+ if (ret)
+ goto err_input_open_device;
+
+ return 0;
+
+err_input_open_device:
+ input_unregister_handle(handle);
+err_input_register_handle:
+ kfree(handle);
+ return ret;
+}
+
+static void keycombo_disconnect(struct input_handle *handle)
+{
+ input_close_device(handle);
+ input_unregister_handle(handle);
+ kfree(handle);
+}
+
+static const struct input_device_id keycombo_ids[] = {
+ {
+ .flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+ .evbit = { BIT_MASK(EV_KEY) },
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(input, keycombo_ids);
+
+static int keycombo_probe(struct platform_device *pdev)
+{
+ int ret;
+ int key, *keyp;
+ struct keycombo_state *state;
+ struct keycombo_platform_data *pdata = pdev->dev.platform_data;
+
+ if (!pdata)
+ return -EINVAL;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ spin_lock_init(&state->lock);
+ keyp = pdata->keys_down;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ state->key_down_target++;
+ __set_bit(key, state->keybit);
+ }
+ if (pdata->keys_up) {
+ keyp = pdata->keys_up;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ __set_bit(key, state->keybit);
+ __set_bit(key, state->upbit);
+ }
+ }
+
+ state->wq = alloc_ordered_workqueue("keycombo", 0);
+ if (!state->wq)
+ return -ENOMEM;
+
+ state->priv = pdata->priv;
+
+ if (pdata->key_down_fn)
+ state->key_down_fn = pdata->key_down_fn;
+ INIT_DELAYED_WORK(&state->key_down_work, do_key_down);
+
+ if (pdata->key_up_fn)
+ state->key_up_fn = pdata->key_up_fn;
+ INIT_WORK(&state->key_up_work, do_key_up);
+
+ wakeup_source_init(&state->combo_held_wake_source, "key combo");
+ wakeup_source_init(&state->combo_up_wake_source, "key combo up");
+ state->delay = msecs_to_jiffies(pdata->key_down_delay);
+
+ state->input_handler.event = keycombo_event;
+ state->input_handler.connect = keycombo_connect;
+ state->input_handler.disconnect = keycombo_disconnect;
+ state->input_handler.name = KEYCOMBO_NAME;
+ state->input_handler.id_table = keycombo_ids;
+ ret = input_register_handler(&state->input_handler);
+ if (ret) {
+ kfree(state);
+ return ret;
+ }
+ platform_set_drvdata(pdev, state);
+ return 0;
+}
+
+int keycombo_remove(struct platform_device *pdev)
+{
+ struct keycombo_state *state = platform_get_drvdata(pdev);
+ input_unregister_handler(&state->input_handler);
+ destroy_workqueue(state->wq);
+ kfree(state);
+ return 0;
+}
+
+
+struct platform_driver keycombo_driver = {
+ .driver.name = KEYCOMBO_NAME,
+ .probe = keycombo_probe,
+ .remove = keycombo_remove,
+};
+
+static int __init keycombo_init(void)
+{
+ return platform_driver_register(&keycombo_driver);
+}
+
+static void __exit keycombo_exit(void)
+{
+ return platform_driver_unregister(&keycombo_driver);
+}
+
+module_init(keycombo_init);
+module_exit(keycombo_exit);
diff --git a/drivers/input/keyreset.c b/drivers/input/keyreset.c
new file mode 100644
index 0000000..7fbf724
--- /dev/null
+++ b/drivers/input/keyreset.c
@@ -0,0 +1,145 @@
+/* drivers/input/keyreset.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keyreset.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/keycombo.h>
+
+struct keyreset_state {
+ int restart_requested;
+ int (*reset_fn)(void);
+ struct platform_device *pdev_child;
+ struct work_struct restart_work;
+};
+
+static void do_restart(struct work_struct *unused)
+{
+ sys_sync();
+ kernel_restart(NULL);
+}
+
+static void do_reset_fn(void *priv)
+{
+ struct keyreset_state *state = priv;
+ if (state->restart_requested)
+ panic("keyboard reset failed, %d", state->restart_requested);
+ if (state->reset_fn) {
+ state->restart_requested = state->reset_fn();
+ } else {
+ pr_info("keyboard reset\n");
+ schedule_work(&state->restart_work);
+ state->restart_requested = 1;
+ }
+}
+
+static int keyreset_probe(struct platform_device *pdev)
+{
+ int ret = -ENOMEM;
+ struct keycombo_platform_data *pdata_child;
+ struct keyreset_platform_data *pdata = pdev->dev.platform_data;
+ int up_size = 0, down_size = 0, size;
+ int key, *keyp;
+ struct keyreset_state *state;
+
+ if (!pdata)
+ return -EINVAL;
+ state = devm_kzalloc(&pdev->dev, sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ state->pdev_child = platform_device_alloc(KEYCOMBO_NAME,
+ PLATFORM_DEVID_AUTO);
+ if (!state->pdev_child)
+ return -ENOMEM;
+ state->pdev_child->dev.parent = &pdev->dev;
+ INIT_WORK(&state->restart_work, do_restart);
+
+ keyp = pdata->keys_down;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ down_size++;
+ }
+ if (pdata->keys_up) {
+ keyp = pdata->keys_up;
+ while ((key = *keyp++)) {
+ if (key >= KEY_MAX)
+ continue;
+ up_size++;
+ }
+ }
+ size = sizeof(struct keycombo_platform_data)
+ + sizeof(int) * (down_size + 1);
+ pdata_child = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+ if (!pdata_child)
+ goto error;
+ memcpy(pdata_child->keys_down, pdata->keys_down,
+ sizeof(int) * down_size);
+ if (up_size > 0) {
+ pdata_child->keys_up = devm_kzalloc(&pdev->dev, up_size + 1,
+ GFP_KERNEL);
+ if (!pdata_child->keys_up)
+ goto error;
+ memcpy(pdata_child->keys_up, pdata->keys_up,
+ sizeof(int) * up_size);
+ if (!pdata_child->keys_up)
+ goto error;
+ }
+ state->reset_fn = pdata->reset_fn;
+ pdata_child->key_down_fn = do_reset_fn;
+ pdata_child->priv = state;
+ pdata_child->key_down_delay = pdata->key_down_delay;
+ ret = platform_device_add_data(state->pdev_child, pdata_child, size);
+ if (ret)
+ goto error;
+ platform_set_drvdata(pdev, state);
+ return platform_device_add(state->pdev_child);
+error:
+ platform_device_put(state->pdev_child);
+ return ret;
+}
+
+int keyreset_remove(struct platform_device *pdev)
+{
+ struct keyreset_state *state = platform_get_drvdata(pdev);
+ platform_device_put(state->pdev_child);
+ return 0;
+}
+
+
+struct platform_driver keyreset_driver = {
+ .driver.name = KEYRESET_NAME,
+ .probe = keyreset_probe,
+ .remove = keyreset_remove,
+};
+
+static int __init keyreset_init(void)
+{
+ return platform_driver_register(&keyreset_driver);
+}
+
+static void __exit keyreset_exit(void)
+{
+ return platform_driver_unregister(&keyreset_driver);
+}
+
+module_init(keyreset_init);
+module_exit(keyreset_exit);
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index bb698e1..4abf046 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -299,6 +299,17 @@
To compile this driver as a module, choose M here: the module will be
called ati_remote2.
+config INPUT_KEYCHORD
+ tristate "Key chord input driver support"
+ help
+ Say Y here if you want to enable the key chord driver
+ accessible at /dev/keychord. This driver can be used
+ for receiving notifications when client specified key
+ combinations are pressed.
+
+ To compile this driver as a module, choose M here: the
+ module will be called keychord.
+
config INPUT_KEYSPAN_REMOTE
tristate "Keyspan DMR USB remote control"
depends on USB_ARCH_HAS_HCD
@@ -434,6 +445,11 @@
To compile this driver as a module, choose M here: the
module will be called sgi_btns.
+config INPUT_GPIO
+ tristate "GPIO driver support"
+ help
+ Say Y here if you want to support gpio based keys, wheels etc...
+
config HP_SDC_RTC
tristate "HP SDC Real Time Clock"
depends on (GSC || HP300) && SERIO
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index d7fc17f..6b0e8a6 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -28,9 +28,11 @@
obj-$(CONFIG_INPUT_DM355EVM) += dm355evm_keys.o
obj-$(CONFIG_INPUT_GP2A) += gp2ap002a00f.o
obj-$(CONFIG_INPUT_GPIO_TILT_POLLED) += gpio_tilt_polled.o
+obj-$(CONFIG_INPUT_GPIO) += gpio_event.o gpio_matrix.o gpio_input.o gpio_output.o gpio_axis.o
obj-$(CONFIG_HP_SDC_RTC) += hp_sdc_rtc.o
obj-$(CONFIG_INPUT_IMS_PCU) += ims-pcu.o
obj-$(CONFIG_INPUT_IXP4XX_BEEPER) += ixp4xx-beeper.o
+obj-$(CONFIG_INPUT_KEYCHORD) += keychord.o
obj-$(CONFIG_INPUT_KEYSPAN_REMOTE) += keyspan_remote.o
obj-$(CONFIG_INPUT_KXTJ9) += kxtj9.o
obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.o
diff --git a/drivers/input/misc/gpio_axis.c b/drivers/input/misc/gpio_axis.c
new file mode 100644
index 0000000..0acf4a5
--- /dev/null
+++ b/drivers/input/misc/gpio_axis.c
@@ -0,0 +1,192 @@
+/* drivers/input/misc/gpio_axis.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+struct gpio_axis_state {
+ struct gpio_event_input_devs *input_devs;
+ struct gpio_event_axis_info *info;
+ uint32_t pos;
+};
+
+uint16_t gpio_axis_4bit_gray_map_table[] = {
+ [0x0] = 0x0, [0x1] = 0x1, /* 0000 0001 */
+ [0x3] = 0x2, [0x2] = 0x3, /* 0011 0010 */
+ [0x6] = 0x4, [0x7] = 0x5, /* 0110 0111 */
+ [0x5] = 0x6, [0x4] = 0x7, /* 0101 0100 */
+ [0xc] = 0x8, [0xd] = 0x9, /* 1100 1101 */
+ [0xf] = 0xa, [0xe] = 0xb, /* 1111 1110 */
+ [0xa] = 0xc, [0xb] = 0xd, /* 1010 1011 */
+ [0x9] = 0xe, [0x8] = 0xf, /* 1001 1000 */
+};
+uint16_t gpio_axis_4bit_gray_map(struct gpio_event_axis_info *info, uint16_t in)
+{
+ return gpio_axis_4bit_gray_map_table[in];
+}
+
+uint16_t gpio_axis_5bit_singletrack_map_table[] = {
+ [0x10] = 0x00, [0x14] = 0x01, [0x1c] = 0x02, /* 10000 10100 11100 */
+ [0x1e] = 0x03, [0x1a] = 0x04, [0x18] = 0x05, /* 11110 11010 11000 */
+ [0x08] = 0x06, [0x0a] = 0x07, [0x0e] = 0x08, /* 01000 01010 01110 */
+ [0x0f] = 0x09, [0x0d] = 0x0a, [0x0c] = 0x0b, /* 01111 01101 01100 */
+ [0x04] = 0x0c, [0x05] = 0x0d, [0x07] = 0x0e, /* 00100 00101 00111 */
+ [0x17] = 0x0f, [0x16] = 0x10, [0x06] = 0x11, /* 10111 10110 00110 */
+ [0x02] = 0x12, [0x12] = 0x13, [0x13] = 0x14, /* 00010 10010 10011 */
+ [0x1b] = 0x15, [0x0b] = 0x16, [0x03] = 0x17, /* 11011 01011 00011 */
+ [0x01] = 0x18, [0x09] = 0x19, [0x19] = 0x1a, /* 00001 01001 11001 */
+ [0x1d] = 0x1b, [0x15] = 0x1c, [0x11] = 0x1d, /* 11101 10101 10001 */
+};
+uint16_t gpio_axis_5bit_singletrack_map(
+ struct gpio_event_axis_info *info, uint16_t in)
+{
+ return gpio_axis_5bit_singletrack_map_table[in];
+}
+
+static void gpio_event_update_axis(struct gpio_axis_state *as, int report)
+{
+ struct gpio_event_axis_info *ai = as->info;
+ int i;
+ int change;
+ uint16_t state = 0;
+ uint16_t pos;
+ uint16_t old_pos = as->pos;
+ for (i = ai->count - 1; i >= 0; i--)
+ state = (state << 1) | gpio_get_value(ai->gpio[i]);
+ pos = ai->map(ai, state);
+ if (ai->flags & GPIOEAF_PRINT_RAW)
+ pr_info("axis %d-%d raw %x, pos %d -> %d\n",
+ ai->type, ai->code, state, old_pos, pos);
+ if (report && pos != old_pos) {
+ if (ai->type == EV_REL) {
+ change = (ai->decoded_size + pos - old_pos) %
+ ai->decoded_size;
+ if (change > ai->decoded_size / 2)
+ change -= ai->decoded_size;
+ if (change == ai->decoded_size / 2) {
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d unknown direction, "
+ "pos %d -> %d\n", ai->type,
+ ai->code, old_pos, pos);
+ change = 0; /* no closest direction */
+ }
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d change %d\n",
+ ai->type, ai->code, change);
+ input_report_rel(as->input_devs->dev[ai->dev],
+ ai->code, change);
+ } else {
+ if (ai->flags & GPIOEAF_PRINT_EVENT)
+ pr_info("axis %d-%d now %d\n",
+ ai->type, ai->code, pos);
+ input_event(as->input_devs->dev[ai->dev],
+ ai->type, ai->code, pos);
+ }
+ input_sync(as->input_devs->dev[ai->dev]);
+ }
+ as->pos = pos;
+}
+
+static irqreturn_t gpio_axis_irq_handler(int irq, void *dev_id)
+{
+ struct gpio_axis_state *as = dev_id;
+ gpio_event_update_axis(as, 1);
+ return IRQ_HANDLED;
+}
+
+int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int ret;
+ int i;
+ int irq;
+ struct gpio_event_axis_info *ai;
+ struct gpio_axis_state *as;
+
+ ai = container_of(info, struct gpio_event_axis_info, info);
+ if (func == GPIO_EVENT_FUNC_SUSPEND) {
+ for (i = 0; i < ai->count; i++)
+ disable_irq(gpio_to_irq(ai->gpio[i]));
+ return 0;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME) {
+ for (i = 0; i < ai->count; i++)
+ enable_irq(gpio_to_irq(ai->gpio[i]));
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ *data = as = kmalloc(sizeof(*as), GFP_KERNEL);
+ if (as == NULL) {
+ ret = -ENOMEM;
+ goto err_alloc_axis_state_failed;
+ }
+ as->input_devs = input_devs;
+ as->info = ai;
+ if (ai->dev >= input_devs->count) {
+ pr_err("gpio_event_axis: bad device index %d >= %d "
+ "for %d:%d\n", ai->dev, input_devs->count,
+ ai->type, ai->code);
+ ret = -EINVAL;
+ goto err_bad_device_index;
+ }
+
+ input_set_capability(input_devs->dev[ai->dev],
+ ai->type, ai->code);
+ if (ai->type == EV_ABS) {
+ input_set_abs_params(input_devs->dev[ai->dev], ai->code,
+ 0, ai->decoded_size - 1, 0, 0);
+ }
+ for (i = 0; i < ai->count; i++) {
+ ret = gpio_request(ai->gpio[i], "gpio_event_axis");
+ if (ret < 0)
+ goto err_request_gpio_failed;
+ ret = gpio_direction_input(ai->gpio[i]);
+ if (ret < 0)
+ goto err_gpio_direction_input_failed;
+ ret = irq = gpio_to_irq(ai->gpio[i]);
+ if (ret < 0)
+ goto err_get_irq_num_failed;
+ ret = request_irq(irq, gpio_axis_irq_handler,
+ IRQF_TRIGGER_RISING |
+ IRQF_TRIGGER_FALLING,
+ "gpio_event_axis", as);
+ if (ret < 0)
+ goto err_request_irq_failed;
+ }
+ gpio_event_update_axis(as, 0);
+ return 0;
+ }
+
+ ret = 0;
+ as = *data;
+ for (i = ai->count - 1; i >= 0; i--) {
+ free_irq(gpio_to_irq(ai->gpio[i]), as);
+err_request_irq_failed:
+err_get_irq_num_failed:
+err_gpio_direction_input_failed:
+ gpio_free(ai->gpio[i]);
+err_request_gpio_failed:
+ ;
+ }
+err_bad_device_index:
+ kfree(as);
+ *data = NULL;
+err_alloc_axis_state_failed:
+ return ret;
+}
diff --git a/drivers/input/misc/gpio_event.c b/drivers/input/misc/gpio_event.c
new file mode 100644
index 0000000..90f07eb
--- /dev/null
+++ b/drivers/input/misc/gpio_event.c
@@ -0,0 +1,228 @@
+/* drivers/input/misc/gpio_event.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+struct gpio_event {
+ struct gpio_event_input_devs *input_devs;
+ const struct gpio_event_platform_data *info;
+ void *state[0];
+};
+
+static int gpio_input_event(
+ struct input_dev *dev, unsigned int type, unsigned int code, int value)
+{
+ int i;
+ int devnr;
+ int ret = 0;
+ int tmp_ret;
+ struct gpio_event_info **ii;
+ struct gpio_event *ip = input_get_drvdata(dev);
+
+ for (devnr = 0; devnr < ip->input_devs->count; devnr++)
+ if (ip->input_devs->dev[devnr] == dev)
+ break;
+ if (devnr == ip->input_devs->count) {
+ pr_err("gpio_input_event: unknown device %p\n", dev);
+ return -EIO;
+ }
+
+ for (i = 0, ii = ip->info->info; i < ip->info->info_count; i++, ii++) {
+ if ((*ii)->event) {
+ tmp_ret = (*ii)->event(ip->input_devs, *ii,
+ &ip->state[i],
+ devnr, type, code, value);
+ if (tmp_ret)
+ ret = tmp_ret;
+ }
+ }
+ return ret;
+}
+
+static int gpio_event_call_all_func(struct gpio_event *ip, int func)
+{
+ int i;
+ int ret;
+ struct gpio_event_info **ii;
+
+ if (func == GPIO_EVENT_FUNC_INIT || func == GPIO_EVENT_FUNC_RESUME) {
+ ii = ip->info->info;
+ for (i = 0; i < ip->info->info_count; i++, ii++) {
+ if ((*ii)->func == NULL) {
+ ret = -ENODEV;
+ pr_err("gpio_event_probe: Incomplete pdata, "
+ "no function\n");
+ goto err_no_func;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME && (*ii)->no_suspend)
+ continue;
+ ret = (*ii)->func(ip->input_devs, *ii, &ip->state[i],
+ func);
+ if (ret) {
+ pr_err("gpio_event_probe: function failed\n");
+ goto err_func_failed;
+ }
+ }
+ return 0;
+ }
+
+ ret = 0;
+ i = ip->info->info_count;
+ ii = ip->info->info + i;
+ while (i > 0) {
+ i--;
+ ii--;
+ if ((func & ~1) == GPIO_EVENT_FUNC_SUSPEND && (*ii)->no_suspend)
+ continue;
+ (*ii)->func(ip->input_devs, *ii, &ip->state[i], func & ~1);
+err_func_failed:
+err_no_func:
+ ;
+ }
+ return ret;
+}
+
+static void __maybe_unused gpio_event_suspend(struct gpio_event *ip)
+{
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_SUSPEND);
+ if (ip->info->power)
+ ip->info->power(ip->info, 0);
+}
+
+static void __maybe_unused gpio_event_resume(struct gpio_event *ip)
+{
+ if (ip->info->power)
+ ip->info->power(ip->info, 1);
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_RESUME);
+}
+
+static int gpio_event_probe(struct platform_device *pdev)
+{
+ int err;
+ struct gpio_event *ip;
+ struct gpio_event_platform_data *event_info;
+ int dev_count = 1;
+ int i;
+ int registered = 0;
+
+ event_info = pdev->dev.platform_data;
+ if (event_info == NULL) {
+ pr_err("gpio_event_probe: No pdata\n");
+ return -ENODEV;
+ }
+ if ((!event_info->name && !event_info->names[0]) ||
+ !event_info->info || !event_info->info_count) {
+ pr_err("gpio_event_probe: Incomplete pdata\n");
+ return -ENODEV;
+ }
+ if (!event_info->name)
+ while (event_info->names[dev_count])
+ dev_count++;
+ ip = kzalloc(sizeof(*ip) +
+ sizeof(ip->state[0]) * event_info->info_count +
+ sizeof(*ip->input_devs) +
+ sizeof(ip->input_devs->dev[0]) * dev_count, GFP_KERNEL);
+ if (ip == NULL) {
+ err = -ENOMEM;
+ pr_err("gpio_event_probe: Failed to allocate private data\n");
+ goto err_kp_alloc_failed;
+ }
+ ip->input_devs = (void*)&ip->state[event_info->info_count];
+ platform_set_drvdata(pdev, ip);
+
+ for (i = 0; i < dev_count; i++) {
+ struct input_dev *input_dev = input_allocate_device();
+ if (input_dev == NULL) {
+ err = -ENOMEM;
+ pr_err("gpio_event_probe: "
+ "Failed to allocate input device\n");
+ goto err_input_dev_alloc_failed;
+ }
+ input_set_drvdata(input_dev, ip);
+ input_dev->name = event_info->name ?
+ event_info->name : event_info->names[i];
+ input_dev->event = gpio_input_event;
+ ip->input_devs->dev[i] = input_dev;
+ }
+ ip->input_devs->count = dev_count;
+ ip->info = event_info;
+ if (event_info->power)
+ ip->info->power(ip->info, 1);
+
+ err = gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_INIT);
+ if (err)
+ goto err_call_all_func_failed;
+
+ for (i = 0; i < dev_count; i++) {
+ err = input_register_device(ip->input_devs->dev[i]);
+ if (err) {
+ pr_err("gpio_event_probe: Unable to register %s "
+ "input device\n", ip->input_devs->dev[i]->name);
+ goto err_input_register_device_failed;
+ }
+ registered++;
+ }
+
+ return 0;
+
+err_input_register_device_failed:
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+err_call_all_func_failed:
+ if (event_info->power)
+ ip->info->power(ip->info, 0);
+ for (i = 0; i < registered; i++)
+ input_unregister_device(ip->input_devs->dev[i]);
+ for (i = dev_count - 1; i >= registered; i--) {
+ input_free_device(ip->input_devs->dev[i]);
+err_input_dev_alloc_failed:
+ ;
+ }
+ kfree(ip);
+err_kp_alloc_failed:
+ return err;
+}
+
+static int gpio_event_remove(struct platform_device *pdev)
+{
+ struct gpio_event *ip = platform_get_drvdata(pdev);
+ int i;
+
+ gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+ if (ip->info->power)
+ ip->info->power(ip->info, 0);
+ for (i = 0; i < ip->input_devs->count; i++)
+ input_unregister_device(ip->input_devs->dev[i]);
+ kfree(ip);
+ return 0;
+}
+
+static struct platform_driver gpio_event_driver = {
+ .probe = gpio_event_probe,
+ .remove = gpio_event_remove,
+ .driver = {
+ .name = GPIO_EVENT_DEV_NAME,
+ },
+};
+
+module_platform_driver(gpio_event_driver);
+
+MODULE_DESCRIPTION("GPIO Event Driver");
+MODULE_LICENSE("GPL");
+
diff --git a/drivers/input/misc/gpio_input.c b/drivers/input/misc/gpio_input.c
new file mode 100644
index 0000000..eefd027
--- /dev/null
+++ b/drivers/input/misc/gpio_input.c
@@ -0,0 +1,390 @@
+/* drivers/input/misc/gpio_input.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/pm_wakeup.h>
+
+enum {
+ DEBOUNCE_UNSTABLE = BIT(0), /* Got irq, while debouncing */
+ DEBOUNCE_PRESSED = BIT(1),
+ DEBOUNCE_NOTPRESSED = BIT(2),
+ DEBOUNCE_WAIT_IRQ = BIT(3), /* Stable irq state */
+ DEBOUNCE_POLL = BIT(4), /* Stable polling state */
+
+ DEBOUNCE_UNKNOWN =
+ DEBOUNCE_PRESSED | DEBOUNCE_NOTPRESSED,
+};
+
+struct gpio_key_state {
+ struct gpio_input_state *ds;
+ uint8_t debounce;
+};
+
+struct gpio_input_state {
+ struct gpio_event_input_devs *input_devs;
+ const struct gpio_event_input_info *info;
+ struct hrtimer timer;
+ int use_irq;
+ int debounce_count;
+ spinlock_t irq_lock;
+ struct wakeup_source *ws;
+ struct gpio_key_state key_state[0];
+};
+
+static enum hrtimer_restart gpio_event_input_timer_func(struct hrtimer *timer)
+{
+ int i;
+ int pressed;
+ struct gpio_input_state *ds =
+ container_of(timer, struct gpio_input_state, timer);
+ unsigned gpio_flags = ds->info->flags;
+ unsigned npolarity;
+ int nkeys = ds->info->keymap_size;
+ const struct gpio_event_direct_entry *key_entry;
+ struct gpio_key_state *key_state;
+ unsigned long irqflags;
+ uint8_t debounce;
+ bool sync_needed;
+
+#if 0
+ key_entry = kp->keys_info->keymap;
+ key_state = kp->key_state;
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++)
+ pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+ gpio_read_detect_status(key_entry->gpio));
+#endif
+ key_entry = ds->info->keymap;
+ key_state = ds->key_state;
+ sync_needed = false;
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+ debounce = key_state->debounce;
+ if (debounce & DEBOUNCE_WAIT_IRQ)
+ continue;
+ if (key_state->debounce & DEBOUNCE_UNSTABLE) {
+ debounce = key_state->debounce = DEBOUNCE_UNKNOWN;
+ enable_irq(gpio_to_irq(key_entry->gpio));
+ if (gpio_flags & GPIOEDF_PRINT_KEY_UNSTABLE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) continue debounce\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ }
+ npolarity = !(gpio_flags & GPIOEDF_ACTIVE_HIGH);
+ pressed = gpio_get_value(key_entry->gpio) ^ npolarity;
+ if (debounce & DEBOUNCE_POLL) {
+ if (pressed == !(debounce & DEBOUNCE_PRESSED)) {
+ ds->debounce_count++;
+ key_state->debounce = DEBOUNCE_UNKNOWN;
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-"
+ "%x, %d (%d) start debounce\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ }
+ continue;
+ }
+ if (pressed && (debounce & DEBOUNCE_NOTPRESSED)) {
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) debounce pressed 1\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ key_state->debounce = DEBOUNCE_PRESSED;
+ continue;
+ }
+ if (!pressed && (debounce & DEBOUNCE_PRESSED)) {
+ if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+ "(%d) debounce pressed 0\n",
+ ds->info->type, key_entry->code,
+ i, key_entry->gpio);
+ key_state->debounce = DEBOUNCE_NOTPRESSED;
+ continue;
+ }
+ /* key is stable */
+ ds->debounce_count--;
+ if (ds->use_irq)
+ key_state->debounce |= DEBOUNCE_WAIT_IRQ;
+ else
+ key_state->debounce |= DEBOUNCE_POLL;
+ if (gpio_flags & GPIOEDF_PRINT_KEYS)
+ pr_info("gpio_keys_scan_keys: key %x-%x, %d (%d) "
+ "changed to %d\n", ds->info->type,
+ key_entry->code, i, key_entry->gpio, pressed);
+ input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+ key_entry->code, pressed);
+ sync_needed = true;
+ }
+ if (sync_needed) {
+ for (i = 0; i < ds->input_devs->count; i++)
+ input_sync(ds->input_devs->dev[i]);
+ }
+
+#if 0
+ key_entry = kp->keys_info->keymap;
+ key_state = kp->key_state;
+ for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+ pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+ gpio_read_detect_status(key_entry->gpio));
+ }
+#endif
+
+ if (ds->debounce_count)
+ hrtimer_start(timer, ds->info->debounce_time, HRTIMER_MODE_REL);
+ else if (!ds->use_irq)
+ hrtimer_start(timer, ds->info->poll_time, HRTIMER_MODE_REL);
+ else
+ __pm_relax(ds->ws);
+
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+ return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_event_input_irq_handler(int irq, void *dev_id)
+{
+ struct gpio_key_state *ks = dev_id;
+ struct gpio_input_state *ds = ks->ds;
+ int keymap_index = ks - ds->key_state;
+ const struct gpio_event_direct_entry *key_entry;
+ unsigned long irqflags;
+ int pressed;
+
+ if (!ds->use_irq)
+ return IRQ_HANDLED;
+
+ key_entry = &ds->info->keymap[keymap_index];
+
+ if (ds->info->debounce_time.tv64) {
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ if (ks->debounce & DEBOUNCE_WAIT_IRQ) {
+ ks->debounce = DEBOUNCE_UNKNOWN;
+ if (ds->debounce_count++ == 0) {
+ __pm_stay_awake(ds->ws);
+ hrtimer_start(
+ &ds->timer, ds->info->debounce_time,
+ HRTIMER_MODE_REL);
+ }
+ if (ds->info->flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+ pr_info("gpio_event_input_irq_handler: "
+ "key %x-%x, %d (%d) start debounce\n",
+ ds->info->type, key_entry->code,
+ keymap_index, key_entry->gpio);
+ } else {
+ disable_irq_nosync(irq);
+ ks->debounce = DEBOUNCE_UNSTABLE;
+ }
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ } else {
+ pressed = gpio_get_value(key_entry->gpio) ^
+ !(ds->info->flags & GPIOEDF_ACTIVE_HIGH);
+ if (ds->info->flags & GPIOEDF_PRINT_KEYS)
+ pr_info("gpio_event_input_irq_handler: key %x-%x, %d "
+ "(%d) changed to %d\n",
+ ds->info->type, key_entry->code, keymap_index,
+ key_entry->gpio, pressed);
+ input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+ key_entry->code, pressed);
+ input_sync(ds->input_devs->dev[key_entry->dev]);
+ }
+ return IRQ_HANDLED;
+}
+
+static int gpio_event_input_request_irqs(struct gpio_input_state *ds)
+{
+ int i;
+ int err;
+ unsigned int irq;
+ unsigned long req_flags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+
+ for (i = 0; i < ds->info->keymap_size; i++) {
+ err = irq = gpio_to_irq(ds->info->keymap[i].gpio);
+ if (err < 0)
+ goto err_gpio_get_irq_num_failed;
+ err = request_irq(irq, gpio_event_input_irq_handler,
+ req_flags, "gpio_keys", &ds->key_state[i]);
+ if (err) {
+ pr_err("gpio_event_input_request_irqs: request_irq "
+ "failed for input %d, irq %d\n",
+ ds->info->keymap[i].gpio, irq);
+ goto err_request_irq_failed;
+ }
+ if (ds->info->info.no_suspend) {
+ err = enable_irq_wake(irq);
+ if (err) {
+ pr_err("gpio_event_input_request_irqs: "
+ "enable_irq_wake failed for input %d, "
+ "irq %d\n",
+ ds->info->keymap[i].gpio, irq);
+ goto err_enable_irq_wake_failed;
+ }
+ }
+ }
+ return 0;
+
+ for (i = ds->info->keymap_size - 1; i >= 0; i--) {
+ irq = gpio_to_irq(ds->info->keymap[i].gpio);
+ if (ds->info->info.no_suspend)
+ disable_irq_wake(irq);
+err_enable_irq_wake_failed:
+ free_irq(irq, &ds->key_state[i]);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+ ;
+ }
+ return err;
+}
+
+int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int ret;
+ int i;
+ unsigned long irqflags;
+ struct gpio_event_input_info *di;
+ struct gpio_input_state *ds = *data;
+ char *wlname;
+
+ di = container_of(info, struct gpio_event_input_info, info);
+
+ if (func == GPIO_EVENT_FUNC_SUSPEND) {
+ if (ds->use_irq)
+ for (i = 0; i < di->keymap_size; i++)
+ disable_irq(gpio_to_irq(di->keymap[i].gpio));
+ hrtimer_cancel(&ds->timer);
+ return 0;
+ }
+ if (func == GPIO_EVENT_FUNC_RESUME) {
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ if (ds->use_irq)
+ for (i = 0; i < di->keymap_size; i++)
+ enable_irq(gpio_to_irq(di->keymap[i].gpio));
+ hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ if (ktime_to_ns(di->poll_time) <= 0)
+ di->poll_time = ktime_set(0, 20 * NSEC_PER_MSEC);
+
+ *data = ds = kzalloc(sizeof(*ds) + sizeof(ds->key_state[0]) *
+ di->keymap_size, GFP_KERNEL);
+ if (ds == NULL) {
+ ret = -ENOMEM;
+ pr_err("gpio_event_input_func: "
+ "Failed to allocate private data\n");
+ goto err_ds_alloc_failed;
+ }
+ ds->debounce_count = di->keymap_size;
+ ds->input_devs = input_devs;
+ ds->info = di;
+ wlname = kasprintf(GFP_KERNEL, "gpio_input:%s%s",
+ input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "");
+
+ ds->ws = wakeup_source_register(wlname);
+ kfree(wlname);
+ if (!ds->ws) {
+ ret = -ENOMEM;
+ pr_err("gpio_event_input_func: "
+ "Failed to allocate wakeup source\n");
+ goto err_ws_failed;
+ }
+
+ spin_lock_init(&ds->irq_lock);
+
+ for (i = 0; i < di->keymap_size; i++) {
+ int dev = di->keymap[i].dev;
+ if (dev >= input_devs->count) {
+ pr_err("gpio_event_input_func: bad device "
+ "index %d >= %d for key code %d\n",
+ dev, input_devs->count,
+ di->keymap[i].code);
+ ret = -EINVAL;
+ goto err_bad_keymap;
+ }
+ input_set_capability(input_devs->dev[dev], di->type,
+ di->keymap[i].code);
+ ds->key_state[i].ds = ds;
+ ds->key_state[i].debounce = DEBOUNCE_UNKNOWN;
+ }
+
+ for (i = 0; i < di->keymap_size; i++) {
+ ret = gpio_request(di->keymap[i].gpio, "gpio_kp_in");
+ if (ret) {
+ pr_err("gpio_event_input_func: gpio_request "
+ "failed for %d\n", di->keymap[i].gpio);
+ goto err_gpio_request_failed;
+ }
+ ret = gpio_direction_input(di->keymap[i].gpio);
+ if (ret) {
+ pr_err("gpio_event_input_func: "
+ "gpio_direction_input failed for %d\n",
+ di->keymap[i].gpio);
+ goto err_gpio_configure_failed;
+ }
+ }
+
+ ret = gpio_event_input_request_irqs(ds);
+
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ ds->use_irq = ret == 0;
+
+ pr_info("GPIO Input Driver: Start gpio inputs for %s%s in %s "
+ "mode\n", input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "",
+ ret == 0 ? "interrupt" : "polling");
+
+ hrtimer_init(&ds->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ ds->timer.function = gpio_event_input_timer_func;
+ hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+ return 0;
+ }
+
+ ret = 0;
+ spin_lock_irqsave(&ds->irq_lock, irqflags);
+ hrtimer_cancel(&ds->timer);
+ if (ds->use_irq) {
+ for (i = di->keymap_size - 1; i >= 0; i--) {
+ int irq = gpio_to_irq(di->keymap[i].gpio);
+ if (ds->info->info.no_suspend)
+ disable_irq_wake(irq);
+ free_irq(irq, &ds->key_state[i]);
+ }
+ }
+ spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+ for (i = di->keymap_size - 1; i >= 0; i--) {
+err_gpio_configure_failed:
+ gpio_free(di->keymap[i].gpio);
+err_gpio_request_failed:
+ ;
+ }
+err_bad_keymap:
+ wakeup_source_unregister(ds->ws);
+err_ws_failed:
+ kfree(ds);
+err_ds_alloc_failed:
+ return ret;
+}
diff --git a/drivers/input/misc/gpio_matrix.c b/drivers/input/misc/gpio_matrix.c
new file mode 100644
index 0000000..eaa9e89
--- /dev/null
+++ b/drivers/input/misc/gpio_matrix.c
@@ -0,0 +1,441 @@
+/* drivers/input/misc/gpio_matrix.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/wakelock.h>
+
+struct gpio_kp {
+ struct gpio_event_input_devs *input_devs;
+ struct gpio_event_matrix_info *keypad_info;
+ struct hrtimer timer;
+ struct wake_lock wake_lock;
+ int current_output;
+ unsigned int use_irq:1;
+ unsigned int key_state_changed:1;
+ unsigned int last_key_state_changed:1;
+ unsigned int some_keys_pressed:2;
+ unsigned int disabled_irq:1;
+ unsigned long keys_pressed[0];
+};
+
+static void clear_phantom_key(struct gpio_kp *kp, int out, int in)
+{
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ int key_index = out * mi->ninputs + in;
+ unsigned short keyentry = mi->keymap[key_index];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+ if (!test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+ if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+ pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+ "cleared\n", keycode, out, in,
+ mi->output_gpios[out], mi->input_gpios[in]);
+ __clear_bit(key_index, kp->keys_pressed);
+ } else {
+ if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+ pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+ "not cleared\n", keycode, out, in,
+ mi->output_gpios[out], mi->input_gpios[in]);
+ }
+}
+
+static int restore_keys_for_input(struct gpio_kp *kp, int out, int in)
+{
+ int rv = 0;
+ int key_index;
+
+ key_index = out * kp->keypad_info->ninputs + in;
+ while (out < kp->keypad_info->noutputs) {
+ if (test_bit(key_index, kp->keys_pressed)) {
+ rv = 1;
+ clear_phantom_key(kp, out, in);
+ }
+ key_index += kp->keypad_info->ninputs;
+ out++;
+ }
+ return rv;
+}
+
+static void remove_phantom_keys(struct gpio_kp *kp)
+{
+ int out, in, inp;
+ int key_index;
+
+ if (kp->some_keys_pressed < 3)
+ return;
+
+ for (out = 0; out < kp->keypad_info->noutputs; out++) {
+ inp = -1;
+ key_index = out * kp->keypad_info->ninputs;
+ for (in = 0; in < kp->keypad_info->ninputs; in++, key_index++) {
+ if (test_bit(key_index, kp->keys_pressed)) {
+ if (inp == -1) {
+ inp = in;
+ continue;
+ }
+ if (inp >= 0) {
+ if (!restore_keys_for_input(kp, out + 1,
+ inp))
+ break;
+ clear_phantom_key(kp, out, inp);
+ inp = -2;
+ }
+ restore_keys_for_input(kp, out, in);
+ }
+ }
+ }
+}
+
+static void report_key(struct gpio_kp *kp, int key_index, int out, int in)
+{
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ int pressed = test_bit(key_index, kp->keys_pressed);
+ unsigned short keyentry = mi->keymap[key_index];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+ if (pressed != test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+ if (keycode == KEY_RESERVED) {
+ if (mi->flags & GPIOKPF_PRINT_UNMAPPED_KEYS)
+ pr_info("gpiomatrix: unmapped key, %d-%d "
+ "(%d-%d) changed to %d\n",
+ out, in, mi->output_gpios[out],
+ mi->input_gpios[in], pressed);
+ } else {
+ if (mi->flags & GPIOKPF_PRINT_MAPPED_KEYS)
+ pr_info("gpiomatrix: key %x, %d-%d (%d-%d) "
+ "changed to %d\n", keycode,
+ out, in, mi->output_gpios[out],
+ mi->input_gpios[in], pressed);
+ input_report_key(kp->input_devs->dev[dev], keycode, pressed);
+ }
+ }
+}
+
+static void report_sync(struct gpio_kp *kp)
+{
+ int i;
+
+ for (i = 0; i < kp->input_devs->count; i++)
+ input_sync(kp->input_devs->dev[i]);
+}
+
+static enum hrtimer_restart gpio_keypad_timer_func(struct hrtimer *timer)
+{
+ int out, in;
+ int key_index;
+ int gpio;
+ struct gpio_kp *kp = container_of(timer, struct gpio_kp, timer);
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ unsigned gpio_keypad_flags = mi->flags;
+ unsigned polarity = !!(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH);
+
+ out = kp->current_output;
+ if (out == mi->noutputs) {
+ out = 0;
+ kp->last_key_state_changed = kp->key_state_changed;
+ kp->key_state_changed = 0;
+ kp->some_keys_pressed = 0;
+ } else {
+ key_index = out * mi->ninputs;
+ for (in = 0; in < mi->ninputs; in++, key_index++) {
+ gpio = mi->input_gpios[in];
+ if (gpio_get_value(gpio) ^ !polarity) {
+ if (kp->some_keys_pressed < 3)
+ kp->some_keys_pressed++;
+ kp->key_state_changed |= !__test_and_set_bit(
+ key_index, kp->keys_pressed);
+ } else
+ kp->key_state_changed |= __test_and_clear_bit(
+ key_index, kp->keys_pressed);
+ }
+ gpio = mi->output_gpios[out];
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(gpio, !polarity);
+ else
+ gpio_direction_input(gpio);
+ out++;
+ }
+ kp->current_output = out;
+ if (out < mi->noutputs) {
+ gpio = mi->output_gpios[out];
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(gpio, polarity);
+ else
+ gpio_direction_output(gpio, polarity);
+ hrtimer_start(timer, mi->settle_time, HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+ if (gpio_keypad_flags & GPIOKPF_DEBOUNCE) {
+ if (kp->key_state_changed) {
+ hrtimer_start(&kp->timer, mi->debounce_delay,
+ HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+ kp->key_state_changed = kp->last_key_state_changed;
+ }
+ if (kp->key_state_changed) {
+ if (gpio_keypad_flags & GPIOKPF_REMOVE_SOME_PHANTOM_KEYS)
+ remove_phantom_keys(kp);
+ key_index = 0;
+ for (out = 0; out < mi->noutputs; out++)
+ for (in = 0; in < mi->ninputs; in++, key_index++)
+ report_key(kp, key_index, out, in);
+ report_sync(kp);
+ }
+ if (!kp->use_irq || kp->some_keys_pressed) {
+ hrtimer_start(timer, mi->poll_time, HRTIMER_MODE_REL);
+ return HRTIMER_NORESTART;
+ }
+
+ /* No keys are pressed, reenable interrupt */
+ for (out = 0; out < mi->noutputs; out++) {
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(mi->output_gpios[out], polarity);
+ else
+ gpio_direction_output(mi->output_gpios[out], polarity);
+ }
+ for (in = 0; in < mi->ninputs; in++)
+ enable_irq(gpio_to_irq(mi->input_gpios[in]));
+ wake_unlock(&kp->wake_lock);
+ return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_keypad_irq_handler(int irq_in, void *dev_id)
+{
+ int i;
+ struct gpio_kp *kp = dev_id;
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+ unsigned gpio_keypad_flags = mi->flags;
+
+ if (!kp->use_irq) {
+ /* ignore interrupt while registering the handler */
+ kp->disabled_irq = 1;
+ disable_irq_nosync(irq_in);
+ return IRQ_HANDLED;
+ }
+
+ for (i = 0; i < mi->ninputs; i++)
+ disable_irq_nosync(gpio_to_irq(mi->input_gpios[i]));
+ for (i = 0; i < mi->noutputs; i++) {
+ if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+ gpio_set_value(mi->output_gpios[i],
+ !(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH));
+ else
+ gpio_direction_input(mi->output_gpios[i]);
+ }
+ wake_lock(&kp->wake_lock);
+ hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+ return IRQ_HANDLED;
+}
+
+static int gpio_keypad_request_irqs(struct gpio_kp *kp)
+{
+ int i;
+ int err;
+ unsigned int irq;
+ unsigned long request_flags;
+ struct gpio_event_matrix_info *mi = kp->keypad_info;
+
+ switch (mi->flags & (GPIOKPF_ACTIVE_HIGH|GPIOKPF_LEVEL_TRIGGERED_IRQ)) {
+ default:
+ request_flags = IRQF_TRIGGER_FALLING;
+ break;
+ case GPIOKPF_ACTIVE_HIGH:
+ request_flags = IRQF_TRIGGER_RISING;
+ break;
+ case GPIOKPF_LEVEL_TRIGGERED_IRQ:
+ request_flags = IRQF_TRIGGER_LOW;
+ break;
+ case GPIOKPF_LEVEL_TRIGGERED_IRQ | GPIOKPF_ACTIVE_HIGH:
+ request_flags = IRQF_TRIGGER_HIGH;
+ break;
+ }
+
+ for (i = 0; i < mi->ninputs; i++) {
+ err = irq = gpio_to_irq(mi->input_gpios[i]);
+ if (err < 0)
+ goto err_gpio_get_irq_num_failed;
+ err = request_irq(irq, gpio_keypad_irq_handler, request_flags,
+ "gpio_kp", kp);
+ if (err) {
+ pr_err("gpiomatrix: request_irq failed for input %d, "
+ "irq %d\n", mi->input_gpios[i], irq);
+ goto err_request_irq_failed;
+ }
+ err = enable_irq_wake(irq);
+ if (err) {
+ pr_err("gpiomatrix: set_irq_wake failed for input %d, "
+ "irq %d\n", mi->input_gpios[i], irq);
+ }
+ disable_irq(irq);
+ if (kp->disabled_irq) {
+ kp->disabled_irq = 0;
+ enable_irq(irq);
+ }
+ }
+ return 0;
+
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+ free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+ ;
+ }
+ return err;
+}
+
+int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func)
+{
+ int i;
+ int err;
+ int key_count;
+ struct gpio_kp *kp;
+ struct gpio_event_matrix_info *mi;
+
+ mi = container_of(info, struct gpio_event_matrix_info, info);
+ if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME) {
+ /* TODO: disable scanning */
+ return 0;
+ }
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ if (mi->keymap == NULL ||
+ mi->input_gpios == NULL ||
+ mi->output_gpios == NULL) {
+ err = -ENODEV;
+ pr_err("gpiomatrix: Incomplete pdata\n");
+ goto err_invalid_platform_data;
+ }
+ key_count = mi->ninputs * mi->noutputs;
+
+ *data = kp = kzalloc(sizeof(*kp) + sizeof(kp->keys_pressed[0]) *
+ BITS_TO_LONGS(key_count), GFP_KERNEL);
+ if (kp == NULL) {
+ err = -ENOMEM;
+ pr_err("gpiomatrix: Failed to allocate private data\n");
+ goto err_kp_alloc_failed;
+ }
+ kp->input_devs = input_devs;
+ kp->keypad_info = mi;
+ for (i = 0; i < key_count; i++) {
+ unsigned short keyentry = mi->keymap[i];
+ unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+ unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+ if (dev >= input_devs->count) {
+ pr_err("gpiomatrix: bad device index %d >= "
+ "%d for key code %d\n",
+ dev, input_devs->count, keycode);
+ err = -EINVAL;
+ goto err_bad_keymap;
+ }
+ if (keycode && keycode <= KEY_MAX)
+ input_set_capability(input_devs->dev[dev],
+ EV_KEY, keycode);
+ }
+
+ for (i = 0; i < mi->noutputs; i++) {
+ err = gpio_request(mi->output_gpios[i], "gpio_kp_out");
+ if (err) {
+ pr_err("gpiomatrix: gpio_request failed for "
+ "output %d\n", mi->output_gpios[i]);
+ goto err_request_output_gpio_failed;
+ }
+ if (gpio_cansleep(mi->output_gpios[i])) {
+ pr_err("gpiomatrix: unsupported output gpio %d,"
+ " can sleep\n", mi->output_gpios[i]);
+ err = -EINVAL;
+ goto err_output_gpio_configure_failed;
+ }
+ if (mi->flags & GPIOKPF_DRIVE_INACTIVE)
+ err = gpio_direction_output(mi->output_gpios[i],
+ !(mi->flags & GPIOKPF_ACTIVE_HIGH));
+ else
+ err = gpio_direction_input(mi->output_gpios[i]);
+ if (err) {
+ pr_err("gpiomatrix: gpio_configure failed for "
+ "output %d\n", mi->output_gpios[i]);
+ goto err_output_gpio_configure_failed;
+ }
+ }
+ for (i = 0; i < mi->ninputs; i++) {
+ err = gpio_request(mi->input_gpios[i], "gpio_kp_in");
+ if (err) {
+ pr_err("gpiomatrix: gpio_request failed for "
+ "input %d\n", mi->input_gpios[i]);
+ goto err_request_input_gpio_failed;
+ }
+ err = gpio_direction_input(mi->input_gpios[i]);
+ if (err) {
+ pr_err("gpiomatrix: gpio_direction_input failed"
+ " for input %d\n", mi->input_gpios[i]);
+ goto err_gpio_direction_input_failed;
+ }
+ }
+ kp->current_output = mi->noutputs;
+ kp->key_state_changed = 1;
+
+ hrtimer_init(&kp->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ kp->timer.function = gpio_keypad_timer_func;
+ wake_lock_init(&kp->wake_lock, WAKE_LOCK_SUSPEND, "gpio_kp");
+ err = gpio_keypad_request_irqs(kp);
+ kp->use_irq = err == 0;
+
+ pr_info("GPIO Matrix Keypad Driver: Start keypad matrix for "
+ "%s%s in %s mode\n", input_devs->dev[0]->name,
+ (input_devs->count > 1) ? "..." : "",
+ kp->use_irq ? "interrupt" : "polling");
+
+ if (kp->use_irq)
+ wake_lock(&kp->wake_lock);
+ hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+
+ return 0;
+ }
+
+ err = 0;
+ kp = *data;
+
+ if (kp->use_irq)
+ for (i = mi->noutputs - 1; i >= 0; i--)
+ free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+
+ hrtimer_cancel(&kp->timer);
+ wake_lock_destroy(&kp->wake_lock);
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+err_gpio_direction_input_failed:
+ gpio_free(mi->input_gpios[i]);
+err_request_input_gpio_failed:
+ ;
+ }
+ for (i = mi->noutputs - 1; i >= 0; i--) {
+err_output_gpio_configure_failed:
+ gpio_free(mi->output_gpios[i]);
+err_request_output_gpio_failed:
+ ;
+ }
+err_bad_keymap:
+ kfree(kp);
+err_kp_alloc_failed:
+err_invalid_platform_data:
+ return err;
+}
diff --git a/drivers/input/misc/gpio_output.c b/drivers/input/misc/gpio_output.c
new file mode 100644
index 0000000..2aac2fa
--- /dev/null
+++ b/drivers/input/misc/gpio_output.c
@@ -0,0 +1,97 @@
+/* drivers/input/misc/gpio_output.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+
+int gpio_event_output_event(
+ struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+ void **data, unsigned int dev, unsigned int type,
+ unsigned int code, int value)
+{
+ int i;
+ struct gpio_event_output_info *oi;
+ oi = container_of(info, struct gpio_event_output_info, info);
+ if (type != oi->type)
+ return 0;
+ if (!(oi->flags & GPIOEDF_ACTIVE_HIGH))
+ value = !value;
+ for (i = 0; i < oi->keymap_size; i++)
+ if (dev == oi->keymap[i].dev && code == oi->keymap[i].code)
+ gpio_set_value(oi->keymap[i].gpio, value);
+ return 0;
+}
+
+int gpio_event_output_func(
+ struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+ void **data, int func)
+{
+ int ret;
+ int i;
+ struct gpio_event_output_info *oi;
+ oi = container_of(info, struct gpio_event_output_info, info);
+
+ if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME)
+ return 0;
+
+ if (func == GPIO_EVENT_FUNC_INIT) {
+ int output_level = !(oi->flags & GPIOEDF_ACTIVE_HIGH);
+
+ for (i = 0; i < oi->keymap_size; i++) {
+ int dev = oi->keymap[i].dev;
+ if (dev >= input_devs->count) {
+ pr_err("gpio_event_output_func: bad device "
+ "index %d >= %d for key code %d\n",
+ dev, input_devs->count,
+ oi->keymap[i].code);
+ ret = -EINVAL;
+ goto err_bad_keymap;
+ }
+ input_set_capability(input_devs->dev[dev], oi->type,
+ oi->keymap[i].code);
+ }
+
+ for (i = 0; i < oi->keymap_size; i++) {
+ ret = gpio_request(oi->keymap[i].gpio,
+ "gpio_event_output");
+ if (ret) {
+ pr_err("gpio_event_output_func: gpio_request "
+ "failed for %d\n", oi->keymap[i].gpio);
+ goto err_gpio_request_failed;
+ }
+ ret = gpio_direction_output(oi->keymap[i].gpio,
+ output_level);
+ if (ret) {
+ pr_err("gpio_event_output_func: "
+ "gpio_direction_output failed for %d\n",
+ oi->keymap[i].gpio);
+ goto err_gpio_direction_output_failed;
+ }
+ }
+ return 0;
+ }
+
+ ret = 0;
+ for (i = oi->keymap_size - 1; i >= 0; i--) {
+err_gpio_direction_output_failed:
+ gpio_free(oi->keymap[i].gpio);
+err_gpio_request_failed:
+ ;
+ }
+err_bad_keymap:
+ return ret;
+}
+
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 77164dc..3e6491d 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1625,7 +1625,7 @@
static int ims_pcu_init_application_mode(struct ims_pcu *pcu)
{
- static atomic_t device_no = ATOMIC_INIT(0);
+ static atomic_t device_no = ATOMIC_INIT(-1);
const struct ims_pcu_device_info *info;
u8 device_id;
@@ -1657,7 +1657,7 @@
}
/* Device appears to be operable, complete initialization */
- pcu->device_no = atomic_inc_return(&device_no) - 1;
+ pcu->device_no = atomic_inc_return(&device_no);
error = ims_pcu_setup_backlight(pcu);
if (error)
diff --git a/drivers/input/misc/keychord.c b/drivers/input/misc/keychord.c
new file mode 100644
index 0000000..a5ea27a
--- /dev/null
+++ b/drivers/input/misc/keychord.c
@@ -0,0 +1,391 @@
+/*
+ * drivers/input/misc/keychord.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/keychord.h>
+#include <linux/sched.h>
+
+#define KEYCHORD_NAME "keychord"
+#define BUFFER_SIZE 16
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("Key chord input driver");
+MODULE_SUPPORTED_DEVICE("keychord");
+MODULE_LICENSE("GPL");
+
+#define NEXT_KEYCHORD(kc) ((struct input_keychord *) \
+ ((char *)kc + sizeof(struct input_keychord) + \
+ kc->count * sizeof(kc->keycodes[0])))
+
+struct keychord_device {
+ struct input_handler input_handler;
+ int registered;
+
+ /* list of keychords to monitor */
+ struct input_keychord *keychords;
+ int keychord_count;
+
+ /* bitmask of keys contained in our keychords */
+ unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+ /* current state of the keys */
+ unsigned long keystate[BITS_TO_LONGS(KEY_CNT)];
+ /* number of keys that are currently pressed */
+ int key_down;
+
+ /* second input_device_id is needed for null termination */
+ struct input_device_id device_ids[2];
+
+ spinlock_t lock;
+ wait_queue_head_t waitq;
+ unsigned char head;
+ unsigned char tail;
+ __u16 buff[BUFFER_SIZE];
+};
+
+static int check_keychord(struct keychord_device *kdev,
+ struct input_keychord *keychord)
+{
+ int i;
+
+ if (keychord->count != kdev->key_down)
+ return 0;
+
+ for (i = 0; i < keychord->count; i++) {
+ if (!test_bit(keychord->keycodes[i], kdev->keystate))
+ return 0;
+ }
+
+ /* we have a match */
+ return 1;
+}
+
+static void keychord_event(struct input_handle *handle, unsigned int type,
+ unsigned int code, int value)
+{
+ struct keychord_device *kdev = handle->private;
+ struct input_keychord *keychord;
+ unsigned long flags;
+ int i, got_chord = 0;
+
+ if (type != EV_KEY || code >= KEY_MAX)
+ return;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* do nothing if key state did not change */
+ if (!test_bit(code, kdev->keystate) == !value)
+ goto done;
+ __change_bit(code, kdev->keystate);
+ if (value)
+ kdev->key_down++;
+ else
+ kdev->key_down--;
+
+ /* don't notify on key up */
+ if (!value)
+ goto done;
+ /* ignore this event if it is not one of the keys we are monitoring */
+ if (!test_bit(code, kdev->keybit))
+ goto done;
+
+ keychord = kdev->keychords;
+ if (!keychord)
+ goto done;
+
+ /* check to see if the keyboard state matches any keychords */
+ for (i = 0; i < kdev->keychord_count; i++) {
+ if (check_keychord(kdev, keychord)) {
+ kdev->buff[kdev->head] = keychord->id;
+ kdev->head = (kdev->head + 1) % BUFFER_SIZE;
+ got_chord = 1;
+ break;
+ }
+ /* skip to next keychord */
+ keychord = NEXT_KEYCHORD(keychord);
+ }
+
+done:
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ if (got_chord) {
+ pr_info("keychord: got keychord id %d. Any tasks: %d\n",
+ keychord->id,
+ !list_empty_careful(&kdev->waitq.task_list));
+ wake_up_interruptible(&kdev->waitq);
+ }
+}
+
+static int keychord_connect(struct input_handler *handler,
+ struct input_dev *dev,
+ const struct input_device_id *id)
+{
+ int i, ret;
+ struct input_handle *handle;
+ struct keychord_device *kdev =
+ container_of(handler, struct keychord_device, input_handler);
+
+ /*
+ * ignore this input device if it does not contain any keycodes
+ * that we are monitoring
+ */
+ for (i = 0; i < KEY_MAX; i++) {
+ if (test_bit(i, kdev->keybit) && test_bit(i, dev->keybit))
+ break;
+ }
+ if (i == KEY_MAX)
+ return -ENODEV;
+
+ handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+ if (!handle)
+ return -ENOMEM;
+
+ handle->dev = dev;
+ handle->handler = handler;
+ handle->name = KEYCHORD_NAME;
+ handle->private = kdev;
+
+ ret = input_register_handle(handle);
+ if (ret)
+ goto err_input_register_handle;
+
+ ret = input_open_device(handle);
+ if (ret)
+ goto err_input_open_device;
+
+ pr_info("keychord: using input dev %s for fevent\n", dev->name);
+
+ return 0;
+
+err_input_open_device:
+ input_unregister_handle(handle);
+err_input_register_handle:
+ kfree(handle);
+ return ret;
+}
+
+static void keychord_disconnect(struct input_handle *handle)
+{
+ input_close_device(handle);
+ input_unregister_handle(handle);
+ kfree(handle);
+}
+
+/*
+ * keychord_read is used to read keychord events from the driver
+ */
+static ssize_t keychord_read(struct file *file, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct keychord_device *kdev = file->private_data;
+ __u16 id;
+ int retval;
+ unsigned long flags;
+
+ if (count < sizeof(id))
+ return -EINVAL;
+ count = sizeof(id);
+
+ if (kdev->head == kdev->tail && (file->f_flags & O_NONBLOCK))
+ return -EAGAIN;
+
+ retval = wait_event_interruptible(kdev->waitq,
+ kdev->head != kdev->tail);
+ if (retval)
+ return retval;
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* pop a keychord ID off the queue */
+ id = kdev->buff[kdev->tail];
+ kdev->tail = (kdev->tail + 1) % BUFFER_SIZE;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ if (copy_to_user(buffer, &id, count))
+ return -EFAULT;
+
+ return count;
+}
+
+/*
+ * keychord_write is used to configure the driver
+ */
+static ssize_t keychord_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct keychord_device *kdev = file->private_data;
+ struct input_keychord *keychords = 0;
+ struct input_keychord *keychord, *next, *end;
+ int ret, i, key;
+ unsigned long flags;
+
+ if (count < sizeof(struct input_keychord))
+ return -EINVAL;
+ keychords = kzalloc(count, GFP_KERNEL);
+ if (!keychords)
+ return -ENOMEM;
+
+ /* read list of keychords from userspace */
+ if (copy_from_user(keychords, buffer, count)) {
+ kfree(keychords);
+ return -EFAULT;
+ }
+
+ /* unregister handler before changing configuration */
+ if (kdev->registered) {
+ input_unregister_handler(&kdev->input_handler);
+ kdev->registered = 0;
+ }
+
+ spin_lock_irqsave(&kdev->lock, flags);
+ /* clear any existing configuration */
+ kfree(kdev->keychords);
+ kdev->keychords = 0;
+ kdev->keychord_count = 0;
+ kdev->key_down = 0;
+ memset(kdev->keybit, 0, sizeof(kdev->keybit));
+ memset(kdev->keystate, 0, sizeof(kdev->keystate));
+ kdev->head = kdev->tail = 0;
+
+ keychord = keychords;
+ end = (struct input_keychord *)((char *)keychord + count);
+
+ while (keychord < end) {
+ next = NEXT_KEYCHORD(keychord);
+ if (keychord->count <= 0 || next > end) {
+ pr_err("keychord: invalid keycode count %d\n",
+ keychord->count);
+ goto err_unlock_return;
+ }
+ if (keychord->version != KEYCHORD_VERSION) {
+ pr_err("keychord: unsupported version %d\n",
+ keychord->version);
+ goto err_unlock_return;
+ }
+
+ /* keep track of the keys we are monitoring in keybit */
+ for (i = 0; i < keychord->count; i++) {
+ key = keychord->keycodes[i];
+ if (key < 0 || key >= KEY_CNT) {
+ pr_err("keychord: keycode %d out of range\n",
+ key);
+ goto err_unlock_return;
+ }
+ __set_bit(key, kdev->keybit);
+ }
+
+ kdev->keychord_count++;
+ keychord = next;
+ }
+
+ kdev->keychords = keychords;
+ spin_unlock_irqrestore(&kdev->lock, flags);
+
+ ret = input_register_handler(&kdev->input_handler);
+ if (ret) {
+ kfree(keychords);
+ kdev->keychords = 0;
+ return ret;
+ }
+ kdev->registered = 1;
+
+ return count;
+
+err_unlock_return:
+ spin_unlock_irqrestore(&kdev->lock, flags);
+ kfree(keychords);
+ return -EINVAL;
+}
+
+static unsigned int keychord_poll(struct file *file, poll_table *wait)
+{
+ struct keychord_device *kdev = file->private_data;
+
+ poll_wait(file, &kdev->waitq, wait);
+
+ if (kdev->head != kdev->tail)
+ return POLLIN | POLLRDNORM;
+
+ return 0;
+}
+
+static int keychord_open(struct inode *inode, struct file *file)
+{
+ struct keychord_device *kdev;
+
+ kdev = kzalloc(sizeof(struct keychord_device), GFP_KERNEL);
+ if (!kdev)
+ return -ENOMEM;
+
+ spin_lock_init(&kdev->lock);
+ init_waitqueue_head(&kdev->waitq);
+
+ kdev->input_handler.event = keychord_event;
+ kdev->input_handler.connect = keychord_connect;
+ kdev->input_handler.disconnect = keychord_disconnect;
+ kdev->input_handler.name = KEYCHORD_NAME;
+ kdev->input_handler.id_table = kdev->device_ids;
+
+ kdev->device_ids[0].flags = INPUT_DEVICE_ID_MATCH_EVBIT;
+ __set_bit(EV_KEY, kdev->device_ids[0].evbit);
+
+ file->private_data = kdev;
+
+ return 0;
+}
+
+static int keychord_release(struct inode *inode, struct file *file)
+{
+ struct keychord_device *kdev = file->private_data;
+
+ if (kdev->registered)
+ input_unregister_handler(&kdev->input_handler);
+ kfree(kdev);
+
+ return 0;
+}
+
+static const struct file_operations keychord_fops = {
+ .owner = THIS_MODULE,
+ .open = keychord_open,
+ .release = keychord_release,
+ .read = keychord_read,
+ .write = keychord_write,
+ .poll = keychord_poll,
+};
+
+static struct miscdevice keychord_misc = {
+ .fops = &keychord_fops,
+ .name = KEYCHORD_NAME,
+ .minor = MISC_DYNAMIC_MINOR,
+};
+
+static int __init keychord_init(void)
+{
+ return misc_register(&keychord_misc);
+}
+
+static void __exit keychord_exit(void)
+{
+ misc_deregister(&keychord_misc);
+}
+
+module_init(keychord_init);
+module_exit(keychord_exit);
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 25fc597..2f2abf4 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -496,7 +496,7 @@
*/
static void serio_init_port(struct serio *serio)
{
- static atomic_t serio_no = ATOMIC_INIT(0);
+ static atomic_t serio_no = ATOMIC_INIT(-1);
__module_get(THIS_MODULE);
@@ -507,7 +507,7 @@
mutex_init(&serio->drv_mutex);
device_initialize(&serio->dev);
dev_set_name(&serio->dev, "serio%ld",
- (long)atomic_inc_return(&serio_no) - 1);
+ (long)atomic_inc_return(&serio_no));
serio->dev.bus = &serio_bus;
serio->dev.release = serio_release_port;
serio->dev.groups = serio_device_attr_groups;
diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index 59df2e7..d91990b 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -293,7 +293,7 @@
static int serio_raw_connect(struct serio *serio, struct serio_driver *drv)
{
- static atomic_t serio_raw_no = ATOMIC_INIT(0);
+ static atomic_t serio_raw_no = ATOMIC_INIT(-1);
struct serio_raw *serio_raw;
int err;
@@ -304,7 +304,7 @@
}
snprintf(serio_raw->name, sizeof(serio_raw->name),
- "serio_raw%ld", (long)atomic_inc_return(&serio_raw_no) - 1);
+ "serio_raw%ld", (long)atomic_inc_return(&serio_raw_no));
kref_init(&serio_raw->kref);
INIT_LIST_HEAD(&serio_raw->client_list);
init_waitqueue_head(&serio_raw->wait);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 29cff90..bab5b55 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -416,4 +416,32 @@
If unsure, say N.
+config DM_VERITY_FEC
+ bool "Verity forward error correction support"
+ depends on DM_VERITY
+ select REED_SOLOMON
+ select REED_SOLOMON_DEC8
+ ---help---
+ Add forward error correction support to dm-verity. This option
+ makes it possible to use pre-generated error correction data to
+ recover from corrupted blocks.
+
+ If unsure, say N.
+
+config DM_ANDROID_VERITY
+ bool "Android verity target support"
+ depends on DM_VERITY
+ depends on X509_CERTIFICATE_PARSER
+ depends on SYSTEM_TRUSTED_KEYRING
+ depends on PUBLIC_KEY_ALGO_RSA
+ depends on KEYS
+ depends on ASYMMETRIC_KEY_TYPE
+ depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+ ---help---
+ This device-mapper target is virtually a VERITY target. This
+ target is setup by reading the metadata contents piggybacked
+ to the actual data blocks in the block device. The signature
+ of the metadata contents are verified against the key included
+ in the system keyring. Upon success, the underlying verity
+ target is setup.
endif # MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 3591a72..7711806 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -14,6 +14,7 @@
dm-cache-y += dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
dm-cache-mq-y += dm-cache-policy-mq.o
dm-cache-cleaner-y += dm-cache-policy-cleaner.o
+dm-verity-y += dm-verity-target.o
md-mod-y += md.o bitmap.o
raid456-y += raid5.o
@@ -56,3 +57,11 @@
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
endif
+
+ifeq ($(CONFIG_DM_VERITY_FEC),y)
+dm-verity-objs += dm-verity-fec.o
+endif
+
+ifeq ($(CONFIG_DM_ANDROID_VERITY),y)
+dm-verity-objs += dm-android-verity.o
+endif
diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c
new file mode 100644
index 0000000..17cdfa8
--- /dev/null
+++ b/drivers/md/dm-android-verity.c
@@ -0,0 +1,852 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/device-mapper.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/fcntl.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/of.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include <asm/setup.h>
+#include <crypto/hash.h>
+#include <crypto/public_key.h>
+#include <crypto/sha.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+
+#include "dm-verity.h"
+#include "dm-android-verity.h"
+
+static char verifiedbootstate[VERITY_COMMANDLINE_PARAM_LENGTH];
+static char veritymode[VERITY_COMMANDLINE_PARAM_LENGTH];
+
+static bool target_added;
+static bool verity_enabled = true;
+struct dentry *debug_dir;
+static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv);
+
+static struct target_type android_verity_target = {
+ .name = "android-verity",
+ .version = {1, 0, 0},
+ .module = THIS_MODULE,
+ .ctr = android_verity_ctr,
+ .dtr = verity_dtr,
+ .map = verity_map,
+ .status = verity_status,
+ .ioctl = verity_ioctl,
+ .merge = verity_merge,
+ .iterate_devices = verity_iterate_devices,
+ .io_hints = verity_io_hints,
+};
+
+static int __init verified_boot_state_param(char *line)
+{
+ strlcpy(verifiedbootstate, line, sizeof(verifiedbootstate));
+ return 1;
+}
+
+__setup("androidboot.verifiedbootstate=", verified_boot_state_param);
+
+static int __init verity_mode_param(char *line)
+{
+ strlcpy(veritymode, line, sizeof(veritymode));
+ return 1;
+}
+
+__setup("androidboot.veritymode=", verity_mode_param);
+
+static int table_extract_mpi_array(struct public_key_signature *pks,
+ const void *data, size_t len)
+{
+ MPI mpi = mpi_read_raw_data(data, len);
+
+ if (!mpi) {
+ DMERR("Error while allocating mpi array");
+ return -ENOMEM;
+ }
+
+ pks->mpi[0] = mpi;
+ pks->nr_mpi = 1;
+ return 0;
+}
+
+static struct public_key_signature *table_make_digest(
+ enum pkey_hash_algo hash,
+ const void *table,
+ unsigned long table_len)
+{
+ struct public_key_signature *pks = NULL;
+ struct crypto_shash *tfm;
+ struct shash_desc *desc;
+ size_t digest_size, desc_size;
+ int ret;
+
+ /* Allocate the hashing algorithm we're going to need and find out how
+ * big the hash operational data will be.
+ */
+ tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0);
+ if (IS_ERR(tfm))
+ return ERR_CAST(tfm);
+
+ desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
+ digest_size = crypto_shash_digestsize(tfm);
+
+ /* We allocate the hash operational data storage on the end of out
+ * context data and the digest output buffer on the end of that.
+ */
+ ret = -ENOMEM;
+ pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL);
+ if (!pks)
+ goto error;
+
+ pks->pkey_hash_algo = hash;
+ pks->digest = (u8 *)pks + sizeof(*pks) + desc_size;
+ pks->digest_size = digest_size;
+
+ desc = (struct shash_desc *)(pks + 1);
+ desc->tfm = tfm;
+ desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ ret = crypto_shash_init(desc);
+ if (ret < 0)
+ goto error;
+
+ ret = crypto_shash_finup(desc, table, table_len, pks->digest);
+ if (ret < 0)
+ goto error;
+
+ crypto_free_shash(tfm);
+ return pks;
+
+error:
+ kfree(pks);
+ crypto_free_shash(tfm);
+ return ERR_PTR(ret);
+}
+
+static int read_block_dev(struct bio_read *payload, struct block_device *bdev,
+ sector_t offset, int length)
+{
+ struct bio *bio;
+ int err = 0, i;
+
+ payload->number_of_pages = DIV_ROUND_UP(length, PAGE_SIZE);
+
+ bio = bio_alloc(GFP_KERNEL, payload->number_of_pages);
+ if (!bio) {
+ DMERR("Error while allocating bio");
+ return -ENOMEM;
+ }
+
+ bio->bi_bdev = bdev;
+ bio->bi_sector = offset;
+
+ payload->page_io = kzalloc(sizeof(struct page *) *
+ payload->number_of_pages, GFP_KERNEL);
+ if (!payload->page_io) {
+ DMERR("page_io array alloc failed");
+ err = -ENOMEM;
+ goto free_bio;
+ }
+
+ for (i = 0; i < payload->number_of_pages; i++) {
+ payload->page_io[i] = alloc_page(GFP_KERNEL);
+ if (!payload->page_io[i]) {
+ DMERR("alloc_page failed");
+ err = -ENOMEM;
+ goto free_pages;
+ }
+ if (!bio_add_page(bio, payload->page_io[i], PAGE_SIZE, 0)) {
+ DMERR("bio_add_page error");
+ err = -EIO;
+ goto free_pages;
+ }
+ }
+
+ if (!submit_bio_wait(READ, bio))
+ /* success */
+ goto free_bio;
+ DMERR("bio read failed");
+ err = -EIO;
+
+free_pages:
+ for (i = 0; i < payload->number_of_pages; i++)
+ if (payload->page_io[i])
+ __free_page(payload->page_io[i]);
+ kfree(payload->page_io);
+free_bio:
+ bio_put(bio);
+ return err;
+}
+
+static inline u64 fec_div_round_up(u64 x, u64 y)
+{
+ u64 remainder;
+
+ return div64_u64_rem(x, y, &remainder) +
+ (remainder > 0 ? 1 : 0);
+}
+
+static inline void populate_fec_metadata(struct fec_header *header,
+ struct fec_ecc_metadata *ecc)
+{
+ ecc->blocks = fec_div_round_up(le64_to_cpu(header->inp_size),
+ FEC_BLOCK_SIZE);
+ ecc->roots = le32_to_cpu(header->roots);
+ ecc->start = le64_to_cpu(header->inp_size);
+}
+
+static inline int validate_fec_header(struct fec_header *header, u64 offset)
+{
+ /* move offset to make the sanity check work for backup header
+ * as well. */
+ offset -= offset % FEC_BLOCK_SIZE;
+ if (le32_to_cpu(header->magic) != FEC_MAGIC ||
+ le32_to_cpu(header->version) != FEC_VERSION ||
+ le32_to_cpu(header->size) != sizeof(struct fec_header) ||
+ le32_to_cpu(header->roots) == 0 ||
+ le32_to_cpu(header->roots) >= FEC_RSM ||
+ offset < le32_to_cpu(header->fec_size) ||
+ offset - le32_to_cpu(header->fec_size) !=
+ le64_to_cpu(header->inp_size))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int extract_fec_header(dev_t dev, struct fec_header *fec,
+ struct fec_ecc_metadata *ecc)
+{
+ u64 device_size;
+ struct bio_read payload;
+ int i, err = 0;
+ struct block_device *bdev;
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+
+ if (IS_ERR(bdev)) {
+ DMERR("bdev get error");
+ return PTR_ERR(bdev);
+ }
+
+ device_size = i_size_read(bdev->bd_inode);
+
+ /* fec metadata size is a power of 2 and PAGE_SIZE
+ * is a power of 2 as well.
+ */
+ BUG_ON(FEC_BLOCK_SIZE > PAGE_SIZE);
+ /* 512 byte sector alignment */
+ BUG_ON(((device_size - FEC_BLOCK_SIZE) % (1 << SECTOR_SHIFT)) != 0);
+
+ err = read_block_dev(&payload, bdev, (device_size -
+ FEC_BLOCK_SIZE) / (1 << SECTOR_SHIFT), FEC_BLOCK_SIZE);
+ if (err) {
+ DMERR("Error while reading verity metadata");
+ goto error;
+ }
+
+ BUG_ON(sizeof(struct fec_header) > PAGE_SIZE);
+ memcpy(fec, page_address(payload.page_io[0]),
+ sizeof(*fec));
+
+ ecc->valid = true;
+ if (validate_fec_header(fec, device_size - FEC_BLOCK_SIZE)) {
+ /* Try the backup header */
+ memcpy(fec, page_address(payload.page_io[0]) + FEC_BLOCK_SIZE
+ - sizeof(*fec) ,
+ sizeof(*fec));
+ if (validate_fec_header(fec, device_size -
+ sizeof(struct fec_header)))
+ ecc->valid = false;
+ }
+
+ if (ecc->valid)
+ populate_fec_metadata(fec, ecc);
+
+ for (i = 0; i < payload.number_of_pages; i++)
+ __free_page(payload.page_io[i]);
+ kfree(payload.page_io);
+
+error:
+ blkdev_put(bdev, FMODE_READ);
+ return err;
+}
+static void find_metadata_offset(struct fec_header *fec,
+ struct block_device *bdev, u64 *metadata_offset)
+{
+ u64 device_size;
+
+ device_size = i_size_read(bdev->bd_inode);
+
+ if (le32_to_cpu(fec->magic) == FEC_MAGIC)
+ *metadata_offset = le64_to_cpu(fec->inp_size) -
+ VERITY_METADATA_SIZE;
+ else
+ *metadata_offset = device_size - VERITY_METADATA_SIZE;
+}
+
+static struct android_metadata *extract_metadata(dev_t dev,
+ struct fec_header *fec)
+{
+ struct block_device *bdev;
+ struct android_metadata_header *header;
+ struct android_metadata *uninitialized_var(metadata);
+ int i;
+ u32 table_length, copy_length, offset;
+ u64 metadata_offset;
+ struct bio_read payload;
+ int err = 0;
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+
+ if (IS_ERR(bdev)) {
+ DMERR("blkdev_get_by_dev failed");
+ return ERR_CAST(bdev);
+ }
+
+ find_metadata_offset(fec, bdev, &metadata_offset);
+
+ /* Verity metadata size is a power of 2 and PAGE_SIZE
+ * is a power of 2 as well.
+ * PAGE_SIZE is also a multiple of 512 bytes.
+ */
+ if (VERITY_METADATA_SIZE > PAGE_SIZE)
+ BUG_ON(VERITY_METADATA_SIZE % PAGE_SIZE != 0);
+ /* 512 byte sector alignment */
+ BUG_ON(metadata_offset % (1 << SECTOR_SHIFT) != 0);
+
+ err = read_block_dev(&payload, bdev, metadata_offset /
+ (1 << SECTOR_SHIFT), VERITY_METADATA_SIZE);
+ if (err) {
+ DMERR("Error while reading verity metadata");
+ metadata = ERR_PTR(err);
+ goto blkdev_release;
+ }
+
+ header = kzalloc(sizeof(*header), GFP_KERNEL);
+ if (!header) {
+ DMERR("kzalloc failed for header");
+ err = -ENOMEM;
+ goto free_payload;
+ }
+
+ memcpy(header, page_address(payload.page_io[0]),
+ sizeof(*header));
+
+ DMINFO("bio magic_number:%u protocol_version:%d table_length:%u",
+ le32_to_cpu(header->magic_number),
+ le32_to_cpu(header->protocol_version),
+ le32_to_cpu(header->table_length));
+
+ metadata = kzalloc(sizeof(*metadata), GFP_KERNEL);
+ if (!metadata) {
+ DMERR("kzalloc for metadata failed");
+ err = -ENOMEM;
+ goto free_header;
+ }
+
+ metadata->header = header;
+ table_length = le32_to_cpu(header->table_length);
+
+ if (table_length == 0 ||
+ table_length > (VERITY_METADATA_SIZE -
+ sizeof(struct android_metadata_header)))
+ goto free_metadata;
+
+ metadata->verity_table = kzalloc(table_length + 1, GFP_KERNEL);
+
+ if (!metadata->verity_table) {
+ DMERR("kzalloc verity_table failed");
+ err = -ENOMEM;
+ goto free_metadata;
+ }
+
+ if (sizeof(struct android_metadata_header) +
+ table_length <= PAGE_SIZE) {
+ memcpy(metadata->verity_table, page_address(payload.page_io[0])
+ + sizeof(struct android_metadata_header),
+ table_length);
+ } else {
+ copy_length = PAGE_SIZE -
+ sizeof(struct android_metadata_header);
+ memcpy(metadata->verity_table, page_address(payload.page_io[0])
+ + sizeof(struct android_metadata_header),
+ copy_length);
+ table_length -= copy_length;
+ offset = copy_length;
+ i = 1;
+ while (table_length != 0) {
+ if (table_length > PAGE_SIZE) {
+ memcpy(metadata->verity_table + offset,
+ page_address(payload.page_io[i]),
+ PAGE_SIZE);
+ offset += PAGE_SIZE;
+ table_length -= PAGE_SIZE;
+ } else {
+ memcpy(metadata->verity_table + offset,
+ page_address(payload.page_io[i]),
+ table_length);
+ table_length = 0;
+ }
+ i++;
+ }
+ }
+ metadata->verity_table[table_length] = '\0';
+
+ goto free_payload;
+
+free_metadata:
+ kfree(metadata);
+free_header:
+ kfree(header);
+ metadata = ERR_PTR(err);
+free_payload:
+ for (i = 0; i < payload.number_of_pages; i++)
+ if (payload.page_io[i])
+ __free_page(payload.page_io[i]);
+ kfree(payload.page_io);
+
+ DMINFO("verity_table: %s", metadata->verity_table);
+blkdev_release:
+ blkdev_put(bdev, FMODE_READ);
+ return metadata;
+}
+
+/* helper functions to extract properties from dts */
+const char *find_dt_value(const char *name)
+{
+ struct device_node *firmware;
+ const char *value;
+
+ firmware = of_find_node_by_path("/firmware/android");
+ if (!firmware)
+ return NULL;
+ value = of_get_property(firmware, name, NULL);
+ of_node_put(firmware);
+
+ return value;
+}
+
+static bool is_unlocked(void)
+{
+ static const char unlocked[] = "orange";
+ static const char verified_boot_prop[] = "verifiedbootstate";
+ const char *value;
+
+ value = find_dt_value(verified_boot_prop);
+ if (!value)
+ value = verifiedbootstate;
+
+ return !strncmp(value, unlocked, sizeof(unlocked) - 1);
+}
+
+static int verity_mode(void)
+{
+ static const char enforcing[] = "enforcing";
+ static const char verified_mode_prop[] = "veritymode";
+ const char *value;
+
+ value = find_dt_value(verified_mode_prop);
+ if (!value)
+ value = veritymode;
+ if (!strncmp(value, enforcing, sizeof(enforcing) - 1))
+ return DM_VERITY_MODE_RESTART;
+
+ return DM_VERITY_MODE_EIO;
+}
+
+static int verify_header(struct android_metadata_header *header)
+{
+ int retval = -EINVAL;
+
+ if (is_unlocked() && le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_DISABLE) {
+ retval = VERITY_STATE_DISABLE;
+ return retval;
+ }
+
+ if (!(le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_NUMBER) ||
+ (le32_to_cpu(header->magic_number) ==
+ VERITY_METADATA_MAGIC_DISABLE)) {
+ DMERR("Incorrect magic number");
+ return retval;
+ }
+
+ if (le32_to_cpu(header->protocol_version) !=
+ VERITY_METADATA_VERSION) {
+ DMERR("Unsupported version %u",
+ le32_to_cpu(header->protocol_version));
+ return retval;
+ }
+
+ return 0;
+}
+
+static int verify_verity_signature(char *key_id,
+ struct android_metadata *metadata)
+{
+ key_ref_t key_ref;
+ struct key *key;
+ struct public_key_signature *pks = NULL;
+ int retval = -EINVAL;
+
+ key_ref = keyring_search(make_key_ref(system_trusted_keyring, 1),
+ &key_type_asymmetric, key_id);
+
+ if (IS_ERR(key_ref)) {
+ DMERR("keyring: key not found");
+ return -ENOKEY;
+ }
+
+ key = key_ref_to_ptr(key_ref);
+
+ pks = table_make_digest(PKEY_HASH_SHA256,
+ (const void *)metadata->verity_table,
+ le32_to_cpu(metadata->header->table_length));
+
+ if (IS_ERR(pks)) {
+ DMERR("hashing failed");
+ goto error;
+ }
+
+ retval = table_extract_mpi_array(pks, &metadata->header->signature[0],
+ RSANUMBYTES);
+ if (retval < 0) {
+ DMERR("Error extracting mpi %d", retval);
+ goto error;
+ }
+
+ retval = verify_signature(key, pks);
+ mpi_free(pks->rsa.s);
+error:
+ kfree(pks);
+ key_put(key);
+
+ return retval;
+}
+
+static void handle_error(void)
+{
+ int mode = verity_mode();
+ if (mode == DM_VERITY_MODE_RESTART) {
+ DMERR("triggering restart");
+ kernel_restart("dm-verity device corrupted");
+ } else {
+ DMERR("Mounting verity root failed");
+ }
+}
+
+static inline bool test_mult_overflow(sector_t a, u32 b)
+{
+ sector_t r = (sector_t)~0ULL;
+
+ sector_div(r, b);
+ return a > r;
+}
+
+static int add_as_linear_device(struct dm_target *ti, char *dev)
+{
+ /*Move to linear mapping defines*/
+ char *linear_table_args[DM_LINEAR_ARGS] = {dev,
+ DM_LINEAR_TARGET_OFFSET};
+ int err = 0;
+
+ android_verity_target.dtr = dm_linear_dtr,
+ android_verity_target.map = dm_linear_map,
+ android_verity_target.status = dm_linear_status,
+ android_verity_target.ioctl = dm_linear_ioctl,
+ android_verity_target.merge = dm_linear_merge,
+ android_verity_target.iterate_devices = dm_linear_iterate_devices,
+ android_verity_target.io_hints = NULL;
+
+ err = dm_linear_ctr(ti, DM_LINEAR_ARGS, linear_table_args);
+
+ if (!err) {
+ DMINFO("Added android-verity as a linear target");
+ target_added = true;
+ } else
+ DMERR("Failed to add android-verity as linear target");
+
+ return err;
+}
+
+/*
+ * Target parameters:
+ * <key id> Key id of the public key in the system keyring.
+ * Verity metadata's signature would be verified against
+ * this. If the key id contains spaces, replace them
+ * with '#'.
+ * <block device> The block device for which dm-verity is being setup.
+ */
+static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ dev_t uninitialized_var(dev);
+ struct android_metadata *uninitialized_var(metadata);
+ int err = 0, i, mode;
+ char *key_id, *table_ptr, dummy,
+ *verity_table_args[VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS];
+ /* One for specifying number of opt args and one for mode */
+ sector_t data_sectors;
+ u32 data_block_size;
+ unsigned int no_of_args = VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS;
+ struct fec_header uninitialized_var(fec);
+ struct fec_ecc_metadata uninitialized_var(ecc);
+ char buf[FEC_ARG_LENGTH], *buf_ptr;
+ unsigned long long tmpll;
+
+ if (argc != 2) {
+ DMERR("Incorrect number of arguments");
+ handle_error();
+ return -EINVAL;
+ }
+
+ /* should come as one of the arguments for the verity target */
+ key_id = argv[0];
+ strreplace(argv[0], '#', ' ');
+
+ dev = name_to_dev_t(argv[1]);
+ if (!dev) {
+ DMERR("no dev found for %s", argv[1]);
+ handle_error();
+ return -EINVAL;
+ }
+
+ DMINFO("key:%s dev:%s", argv[0], argv[1]);
+
+ if (extract_fec_header(dev, &fec, &ecc)) {
+ DMERR("Error while extracting fec header");
+ handle_error();
+ return -EINVAL;
+ }
+
+ metadata = extract_metadata(dev, &fec);
+
+ if (IS_ERR(metadata)) {
+ DMERR("Error while extracting metadata");
+ handle_error();
+ return -EINVAL;
+ }
+
+ err = verify_header(metadata->header);
+
+ if (err == VERITY_STATE_DISABLE) {
+ DMERR("Mounting root with verity disabled");
+ verity_enabled = false;
+ /* we would still have to parse the args to figure out
+ * the data blocks size. Or may be could map the entire
+ * partition similar to mounting the device.
+ */
+ } else if (err) {
+ DMERR("Verity header handle error");
+ handle_error();
+ goto free_metadata;
+ }
+
+ if (!verity_enabled) {
+ err = verify_verity_signature(key_id, metadata);
+
+ if (err) {
+ DMERR("Signature verification failed");
+ handle_error();
+ goto free_metadata;
+ } else
+ DMINFO("Signature verification success");
+ }
+
+ table_ptr = metadata->verity_table;
+
+ for (i = 0; i < VERITY_TABLE_ARGS; i++) {
+ verity_table_args[i] = strsep(&table_ptr, " ");
+ if (verity_table_args[i] == NULL)
+ break;
+ }
+
+ if (i != VERITY_TABLE_ARGS) {
+ DMERR("Verity table not in the expected format");
+ err = -EINVAL;
+ handle_error();
+ goto free_metadata;
+ }
+
+ if (sscanf(verity_table_args[5], "%llu%c", &tmpll, &dummy)
+ != 1) {
+ DMERR("Verity table not in the expected format");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ if (tmpll > ULONG_MAX) {
+ DMERR("<num_data_blocks> too large. Forgot to turn on CONFIG_LBDAF?");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ data_sectors = tmpll;
+
+ if (sscanf(verity_table_args[3], "%u%c", &data_block_size, &dummy)
+ != 1) {
+ DMERR("Verity table not in the expected format");
+ handle_error();
+ err = -EINVAL;
+ goto free_metadata;
+ }
+
+ if (test_mult_overflow(data_sectors, data_block_size >>
+ SECTOR_SHIFT)) {
+ DMERR("data_sectors too large");
+ handle_error();
+ err = -EOVERFLOW;
+ goto free_metadata;
+ }
+
+ data_sectors *= data_block_size >> SECTOR_SHIFT;
+ DMINFO("Data sectors %llu", (unsigned long long)data_sectors);
+
+ /* update target length */
+ ti->len = data_sectors;
+
+ /* Setup linear target and free */
+ if (!verity_enabled) {
+ err = add_as_linear_device(ti, argv[1]);
+ goto free_metadata;
+ }
+
+ /*substitute data_dev and hash_dev*/
+ verity_table_args[1] = argv[1];
+ verity_table_args[2] = argv[1];
+
+ mode = verity_mode();
+
+ if (ecc.valid && IS_BUILTIN(CONFIG_DM_VERITY_FEC)) {
+ if (mode) {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "%u %s " VERITY_TABLE_OPT_FEC_FORMAT,
+ 1 + VERITY_TABLE_OPT_FEC_ARGS,
+ mode == DM_VERITY_MODE_RESTART ?
+ VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING,
+ argv[1], ecc.start / FEC_BLOCK_SIZE, ecc.blocks,
+ ecc.roots);
+ } else {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "%u " VERITY_TABLE_OPT_FEC_FORMAT,
+ VERITY_TABLE_OPT_FEC_ARGS, argv[1],
+ ecc.start / FEC_BLOCK_SIZE, ecc.blocks, ecc.roots);
+ }
+ } else if (mode) {
+ err = snprintf(buf, FEC_ARG_LENGTH,
+ "2 " VERITY_TABLE_OPT_IGNZERO " %s",
+ mode == DM_VERITY_MODE_RESTART ?
+ VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING);
+ } else {
+ err = snprintf(buf, FEC_ARG_LENGTH, "1 %s",
+ "ignore_zero_blocks");
+ }
+
+ if (err < 0 || err >= FEC_ARG_LENGTH)
+ goto free_metadata;
+
+ buf_ptr = buf;
+
+ for (i = VERITY_TABLE_ARGS; i < (VERITY_TABLE_ARGS +
+ VERITY_TABLE_OPT_FEC_ARGS + 2); i++) {
+ verity_table_args[i] = strsep(&buf_ptr, " ");
+ if (verity_table_args[i] == NULL) {
+ no_of_args = i;
+ break;
+ }
+ }
+
+ err = verity_ctr(ti, no_of_args, verity_table_args);
+
+ if (err)
+ DMERR("android-verity failed to mount as verity target");
+ else {
+ target_added = true;
+ DMINFO("android-verity mounted as verity target");
+ }
+
+free_metadata:
+ kfree(metadata->header);
+ kfree(metadata->verity_table);
+ kfree(metadata);
+ return err;
+}
+
+static int __init dm_android_verity_init(void)
+{
+ int r;
+ struct dentry *file;
+
+ r = dm_register_target(&android_verity_target);
+ if (r < 0)
+ DMERR("register failed %d", r);
+
+ /* Tracks the status of the last added target */
+ debug_dir = debugfs_create_dir("android_verity", NULL);
+
+ if (IS_ERR_OR_NULL(debug_dir)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ goto end;
+ }
+
+ file = debugfs_create_bool("target_added", S_IRUGO, debug_dir,
+ (u32 *)&target_added);
+
+ if (IS_ERR_OR_NULL(file)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ debugfs_remove_recursive(debug_dir);
+ goto end;
+ }
+
+ file = debugfs_create_bool("verity_enabled", S_IRUGO, debug_dir,
+ (u32 *)&verity_enabled);
+
+ if (IS_ERR_OR_NULL(file)) {
+ DMERR("Cannot create android_verity debugfs directory: %ld",
+ PTR_ERR(debug_dir));
+ debugfs_remove_recursive(debug_dir);
+ }
+
+end:
+ return r;
+}
+
+static void __exit dm_android_verity_exit(void)
+{
+ if (!IS_ERR_OR_NULL(debug_dir))
+ debugfs_remove_recursive(debug_dir);
+
+ dm_unregister_target(&android_verity_target);
+}
+
+module_init(dm_android_verity_init);
+module_exit(dm_android_verity_exit);
diff --git a/drivers/md/dm-android-verity.h b/drivers/md/dm-android-verity.h
new file mode 100644
index 0000000..efb7965
--- /dev/null
+++ b/drivers/md/dm-android-verity.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef DM_ANDROID_VERITY_H
+#define DM_ANDROID_VERITY_H
+
+#include <crypto/sha.h>
+
+#define RSANUMBYTES 256
+#define VERITY_METADATA_MAGIC_NUMBER 0xb001b001
+#define VERITY_METADATA_MAGIC_DISABLE 0x46464f56
+#define VERITY_METADATA_VERSION 0
+#define VERITY_STATE_DISABLE 1
+#define DATA_BLOCK_SIZE (4 * 1024)
+#define VERITY_METADATA_SIZE (8 * DATA_BLOCK_SIZE)
+#define VERITY_TABLE_ARGS 10
+#define VERITY_COMMANDLINE_PARAM_LENGTH 20
+
+#define FEC_MAGIC 0xFECFECFE
+#define FEC_BLOCK_SIZE (4 * 1024)
+#define FEC_VERSION 0
+#define FEC_RSM 255
+#define FEC_ARG_LENGTH 300
+
+#define VERITY_TABLE_OPT_RESTART "restart_on_corruption"
+#define VERITY_TABLE_OPT_LOGGING "ignore_corruption"
+#define VERITY_TABLE_OPT_IGNZERO "ignore_zero_blocks"
+
+#define VERITY_TABLE_OPT_FEC_FORMAT \
+ "use_fec_from_device %s fec_start %llu fec_blocks %llu fec_roots %u ignore_zero_blocks"
+#define VERITY_TABLE_OPT_FEC_ARGS 9
+
+#define VERITY_DEBUG 0
+
+#define DM_MSG_PREFIX "android-verity"
+
+#define DM_LINEAR_ARGS 2
+#define DM_LINEAR_TARGET_OFFSET "0"
+
+/*
+ * There can be two formats.
+ * if fec is present
+ * <data_blocks> <verity_tree> <verity_metdata_32K><fec_data><fec_data_4K>
+ * if fec is not present
+ * <data_blocks> <verity_tree> <verity_metdata_32K>
+ */
+/* TODO: rearrange structure to reduce memory holes
+ * depends on userspace change.
+ */
+struct fec_header {
+ __le32 magic;
+ __le32 version;
+ __le32 size;
+ __le32 roots;
+ __le32 fec_size;
+ __le64 inp_size;
+ u8 hash[SHA256_DIGEST_SIZE];
+};
+
+struct android_metadata_header {
+ __le32 magic_number;
+ __le32 protocol_version;
+ char signature[RSANUMBYTES];
+ __le32 table_length;
+};
+
+struct android_metadata {
+ struct android_metadata_header *header;
+ char *verity_table;
+};
+
+struct fec_ecc_metadata {
+ bool valid;
+ u32 roots;
+ u64 blocks;
+ u64 rounds;
+ u64 start;
+};
+
+struct bio_read {
+ struct page **page_io;
+ int number_of_pages;
+};
+
+extern struct target_type linear_target;
+
+extern void dm_linear_dtr(struct dm_target *ti);
+extern int dm_linear_map(struct dm_target *ti, struct bio *bio);
+extern void dm_linear_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen);
+extern int dm_linear_ioctl(struct dm_target *ti, unsigned int cmd,
+ unsigned long arg);
+extern int dm_linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+ struct bio_vec *biovec, int max_size);
+extern int dm_linear_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data);
+extern int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv);
+#endif /* DM_ANDROID_VERITY_H */
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 7409d79..c01095b 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -17,9 +17,11 @@
#include <linux/slab.h>
#include <linux/crypto.h>
#include <linux/workqueue.h>
+#include <linux/kthread.h>
#include <linux/backing-dev.h>
#include <linux/atomic.h>
#include <linux/scatterlist.h>
+#include <linux/rbtree.h>
#include <asm/page.h>
#include <asm/unaligned.h>
#include <crypto/hash.h>
@@ -59,8 +61,9 @@
atomic_t io_pending;
int error;
sector_t sector;
- struct dm_crypt_io *base_io;
-};
+
+ struct rb_node rb_node;
+} CRYPTO_MINALIGN_ATTR;
struct dm_crypt_request {
struct convert_context *ctx;
@@ -115,14 +118,18 @@
* pool for per bio private data, crypto requests and
* encryption requeusts/buffer pages
*/
- mempool_t *io_pool;
mempool_t *req_pool;
mempool_t *page_pool;
struct bio_set *bs;
+ struct mutex bio_alloc_lock;
struct workqueue_struct *io_queue;
struct workqueue_struct *crypt_queue;
+ struct task_struct *write_thread;
+ wait_queue_head_t write_thread_wait;
+ struct rb_root write_tree;
+
char *cipher;
char *cipher_string;
@@ -155,6 +162,8 @@
*/
unsigned int dmreq_start;
+ unsigned int per_bio_data_size;
+
unsigned long flags;
unsigned int key_size;
unsigned int key_parts;
@@ -162,9 +171,6 @@
};
#define MIN_IOS 16
-#define MIN_POOL_PAGES 32
-
-static struct kmem_cache *_crypt_io_pool;
static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -730,6 +736,15 @@
kcryptd_async_done, dmreq_of_req(cc, ctx->req));
}
+static void crypt_free_req(struct crypt_config *cc,
+ struct ablkcipher_request *req, struct bio *base_bio)
+{
+ struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
+
+ if ((struct ablkcipher_request *)(io + 1) != req)
+ mempool_free(req, cc->req_pool);
+}
+
/*
* Encrypt / decrypt data from one bio to another one (can be the same one)
*/
@@ -777,57 +792,70 @@
return 0;
}
+static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
+
/*
* Generate a new unfragmented bio with the given size
* This should never violate the device limitations
- * May return a smaller bio when running out of pages, indicated by
- * *out_of_pages set to 1.
+ *
+ * This function may be called concurrently. If we allocate from the mempool
+ * concurrently, there is a possibility of deadlock. For example, if we have
+ * mempool of 256 pages, two processes, each wanting 256, pages allocate from
+ * the mempool concurrently, it may deadlock in a situation where both processes
+ * have allocated 128 pages and the mempool is exhausted.
+ *
+ * In order to avoid this scenario we allocate the pages under a mutex.
+ *
+ * In order to not degrade performance with excessive locking, we try
+ * non-blocking allocations without a mutex first but on failure we fallback
+ * to blocking allocations with a mutex.
*/
-static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
- unsigned *out_of_pages)
+static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
- gfp_t gfp_mask = GFP_NOIO | __GFP_HIGHMEM;
- unsigned i, len;
+ gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
+ unsigned i, len, remaining_size;
struct page *page;
+ struct bio_vec *bvec;
+
+retry:
+ if (unlikely(gfp_mask & __GFP_WAIT))
+ mutex_lock(&cc->bio_alloc_lock);
clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
if (!clone)
- return NULL;
+ goto return_clone;
clone_init(io, clone);
- *out_of_pages = 0;
+
+ remaining_size = size;
for (i = 0; i < nr_iovecs; i++) {
page = mempool_alloc(cc->page_pool, gfp_mask);
if (!page) {
- *out_of_pages = 1;
- break;
+ crypt_free_buffer_pages(cc, clone);
+ bio_put(clone);
+ gfp_mask |= __GFP_WAIT;
+ goto retry;
}
- /*
- * If additional pages cannot be allocated without waiting,
- * return a partially-allocated bio. The caller will then try
- * to allocate more bios while submitting this partial bio.
- */
- gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
+ len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
- len = (size > PAGE_SIZE) ? PAGE_SIZE : size;
+ bvec = &clone->bi_io_vec[clone->bi_vcnt++];
+ bvec->bv_page = page;
+ bvec->bv_len = len;
+ bvec->bv_offset = 0;
- if (!bio_add_page(clone, page, len, 0)) {
- mempool_free(page, cc->page_pool);
- break;
- }
+ clone->bi_size += len;
- size -= len;
+ remaining_size -= len;
}
- if (!clone->bi_size) {
- bio_put(clone);
- return NULL;
- }
+return_clone:
+ if (unlikely(gfp_mask & __GFP_WAIT))
+ mutex_unlock(&cc->bio_alloc_lock);
return clone;
}
@@ -844,21 +872,15 @@
}
}
-static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc,
- struct bio *bio, sector_t sector)
+static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
+ struct bio *bio, sector_t sector)
{
- struct dm_crypt_io *io;
-
- io = mempool_alloc(cc->io_pool, GFP_NOIO);
io->cc = cc;
io->base_bio = bio;
io->sector = sector;
io->error = 0;
- io->base_io = NULL;
io->ctx.req = NULL;
atomic_set(&io->io_pending, 0);
-
- return io;
}
static void crypt_inc_pending(struct dm_crypt_io *io)
@@ -869,29 +891,20 @@
/*
* One of the bios was finished. Check for completion of
* the whole request and correctly clean up the buffer.
- * If base_io is set, wait for the last fragment to complete.
*/
static void crypt_dec_pending(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
struct bio *base_bio = io->base_bio;
- struct dm_crypt_io *base_io = io->base_io;
int error = io->error;
if (!atomic_dec_and_test(&io->io_pending))
return;
if (io->ctx.req)
- mempool_free(io->ctx.req, cc->req_pool);
- mempool_free(io, cc->io_pool);
+ crypt_free_req(cc, io->ctx.req, base_bio);
- if (likely(!base_io))
- bio_endio(base_bio, error);
- else {
- if (error && !base_io->error)
- base_io->error = error;
- crypt_dec_pending(base_io);
- }
+ bio_endio(base_bio, error);
}
/*
@@ -973,37 +986,97 @@
return 0;
}
-static void kcryptd_io_write(struct dm_crypt_io *io)
-{
- struct bio *clone = io->ctx.bio_out;
- generic_make_request(clone);
-}
-
-static void kcryptd_io(struct work_struct *work)
+static void kcryptd_io_read_work(struct work_struct *work)
{
struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
- if (bio_data_dir(io->base_bio) == READ) {
- crypt_inc_pending(io);
- if (kcryptd_io_read(io, GFP_NOIO))
- io->error = -ENOMEM;
- crypt_dec_pending(io);
- } else
- kcryptd_io_write(io);
+ crypt_inc_pending(io);
+ if (kcryptd_io_read(io, GFP_NOIO))
+ io->error = -ENOMEM;
+ crypt_dec_pending(io);
}
-static void kcryptd_queue_io(struct dm_crypt_io *io)
+static void kcryptd_queue_read(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
- INIT_WORK(&io->work, kcryptd_io);
+ INIT_WORK(&io->work, kcryptd_io_read_work);
queue_work(cc->io_queue, &io->work);
}
+static void kcryptd_io_write(struct dm_crypt_io *io)
+{
+ struct bio *clone = io->ctx.bio_out;
+
+ generic_make_request(clone);
+}
+
+#define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node)
+
+static int dmcrypt_write(void *data)
+{
+ struct crypt_config *cc = data;
+ struct dm_crypt_io *io;
+
+ while (1) {
+ struct rb_root write_tree;
+ struct blk_plug plug;
+
+ DECLARE_WAITQUEUE(wait, current);
+
+ spin_lock_irq(&cc->write_thread_wait.lock);
+continue_locked:
+
+ if (!RB_EMPTY_ROOT(&cc->write_tree))
+ goto pop_from_list;
+
+ __set_current_state(TASK_INTERRUPTIBLE);
+ __add_wait_queue(&cc->write_thread_wait, &wait);
+
+ spin_unlock_irq(&cc->write_thread_wait.lock);
+
+ if (unlikely(kthread_should_stop())) {
+ set_task_state(current, TASK_RUNNING);
+ remove_wait_queue(&cc->write_thread_wait, &wait);
+ break;
+ }
+
+ schedule();
+
+ set_task_state(current, TASK_RUNNING);
+ spin_lock_irq(&cc->write_thread_wait.lock);
+ __remove_wait_queue(&cc->write_thread_wait, &wait);
+ goto continue_locked;
+
+pop_from_list:
+ write_tree = cc->write_tree;
+ cc->write_tree = RB_ROOT;
+ spin_unlock_irq(&cc->write_thread_wait.lock);
+
+ BUG_ON(rb_parent(write_tree.rb_node));
+
+ /*
+ * Note: we cannot walk the tree here with rb_next because
+ * the structures may be freed when kcryptd_io_write is called.
+ */
+ blk_start_plug(&plug);
+ do {
+ io = crypt_io_from_node(rb_first(&write_tree));
+ rb_erase(&io->rb_node, &write_tree);
+ kcryptd_io_write(io);
+ } while (!RB_EMPTY_ROOT(&write_tree));
+ blk_finish_plug(&plug);
+ }
+ return 0;
+}
+
static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
{
struct bio *clone = io->ctx.bio_out;
struct crypt_config *cc = io->cc;
+ unsigned long flags;
+ sector_t sector;
+ struct rb_node **rbp, *parent;
if (unlikely(io->error < 0)) {
crypt_free_buffer_pages(cc, clone);
@@ -1017,20 +1090,29 @@
clone->bi_sector = cc->start + io->sector;
- if (async)
- kcryptd_queue_io(io);
- else
- generic_make_request(clone);
+ spin_lock_irqsave(&cc->write_thread_wait.lock, flags);
+ rbp = &cc->write_tree.rb_node;
+ parent = NULL;
+ sector = io->sector;
+ while (*rbp) {
+ parent = *rbp;
+ if (sector < crypt_io_from_node(parent)->sector)
+ rbp = &(*rbp)->rb_left;
+ else
+ rbp = &(*rbp)->rb_right;
+ }
+ rb_link_node(&io->rb_node, parent, rbp);
+ rb_insert_color(&io->rb_node, &cc->write_tree);
+
+ wake_up_locked(&cc->write_thread_wait);
+ spin_unlock_irqrestore(&cc->write_thread_wait.lock, flags);
}
static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
- struct dm_crypt_io *new_io;
int crypt_finished;
- unsigned out_of_pages = 0;
- unsigned remaining = io->base_bio->bi_size;
sector_t sector = io->sector;
int r;
@@ -1040,81 +1122,29 @@
crypt_inc_pending(io);
crypt_convert_init(cc, &io->ctx, NULL, io->base_bio, sector);
- /*
- * The allocated buffers can be smaller than the whole bio,
- * so repeat the whole process until all the data can be handled.
- */
- while (remaining) {
- clone = crypt_alloc_buffer(io, remaining, &out_of_pages);
- if (unlikely(!clone)) {
- io->error = -ENOMEM;
- break;
- }
-
- io->ctx.bio_out = clone;
- io->ctx.idx_out = 0;
-
- remaining -= clone->bi_size;
- sector += bio_sectors(clone);
-
- crypt_inc_pending(io);
-
- r = crypt_convert(cc, &io->ctx);
- if (r < 0)
- io->error = -EIO;
-
- crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
-
- /* Encryption was already finished, submit io now */
- if (crypt_finished) {
- kcryptd_crypt_write_io_submit(io, 0);
-
- /*
- * If there was an error, do not try next fragments.
- * For async, error is processed in async handler.
- */
- if (unlikely(r < 0))
- break;
-
- io->sector = sector;
- }
-
- /*
- * Out of memory -> run queues
- * But don't wait if split was due to the io size restriction
- */
- if (unlikely(out_of_pages))
- congestion_wait(BLK_RW_ASYNC, HZ/100);
-
- /*
- * With async crypto it is unsafe to share the crypto context
- * between fragments, so switch to a new dm_crypt_io structure.
- */
- if (unlikely(!crypt_finished && remaining)) {
- new_io = crypt_io_alloc(io->cc, io->base_bio,
- sector);
- crypt_inc_pending(new_io);
- crypt_convert_init(cc, &new_io->ctx, NULL,
- io->base_bio, sector);
- new_io->ctx.idx_in = io->ctx.idx_in;
- new_io->ctx.offset_in = io->ctx.offset_in;
-
- /*
- * Fragments after the first use the base_io
- * pending count.
- */
- if (!io->base_io)
- new_io->base_io = io;
- else {
- new_io->base_io = io->base_io;
- crypt_inc_pending(io->base_io);
- crypt_dec_pending(io);
- }
-
- io = new_io;
- }
+ clone = crypt_alloc_buffer(io, io->base_bio->bi_size);
+ if (unlikely(!clone)) {
+ io->error = -EIO;
+ goto dec;
}
+ io->ctx.bio_out = clone;
+
+ sector += bio_sectors(clone);
+
+ crypt_inc_pending(io);
+ r = crypt_convert(cc, &io->ctx);
+ if (r)
+ io->error = -EIO;
+ crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
+
+ /* Encryption was already finished, submit io now */
+ if (crypt_finished) {
+ kcryptd_crypt_write_io_submit(io, 0);
+ io->sector = sector;
+ }
+
+dec:
crypt_dec_pending(io);
}
@@ -1162,7 +1192,7 @@
if (error < 0)
io->error = -EIO;
- mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool);
+ crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
if (!atomic_dec_and_test(&ctx->cc_pending))
return;
@@ -1314,6 +1344,9 @@
if (!cc)
return;
+ if (cc->write_thread)
+ kthread_stop(cc->write_thread);
+
if (cc->io_queue)
destroy_workqueue(cc->io_queue);
if (cc->crypt_queue)
@@ -1328,8 +1361,6 @@
mempool_destroy(cc->page_pool);
if (cc->req_pool)
mempool_destroy(cc->req_pool);
- if (cc->io_pool)
- mempool_destroy(cc->io_pool);
if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
cc->iv_gen_ops->dtr(cc);
@@ -1534,13 +1565,6 @@
if (ret < 0)
goto bad;
- ret = -ENOMEM;
- cc->io_pool = mempool_create_slab_pool(MIN_IOS, _crypt_io_pool);
- if (!cc->io_pool) {
- ti->error = "Cannot allocate crypt io mempool";
- goto bad;
- }
-
cc->dmreq_start = sizeof(struct ablkcipher_request);
cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
@@ -1558,6 +1582,7 @@
iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
}
+ ret = -ENOMEM;
cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
if (!cc->req_pool) {
@@ -1565,7 +1590,12 @@
goto bad;
}
- cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0);
+ cc->per_bio_data_size = ti->per_bio_data_size =
+ ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start +
+ sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
+ ARCH_KMALLOC_MINALIGN);
+
+ cc->page_pool = mempool_create_page_pool(BIO_MAX_PAGES, 0);
if (!cc->page_pool) {
ti->error = "Cannot allocate page mempool";
goto bad;
@@ -1577,6 +1607,8 @@
goto bad;
}
+ mutex_init(&cc->bio_alloc_lock);
+
ret = -EINVAL;
if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid iv_offset sector";
@@ -1621,6 +1653,7 @@
ret = -ENOMEM;
cc->io_queue = alloc_workqueue("kcryptd_io",
+ WQ_HIGHPRI |
WQ_NON_REENTRANT|
WQ_MEM_RECLAIM,
1);
@@ -1630,15 +1663,26 @@
}
cc->crypt_queue = alloc_workqueue("kcryptd",
- WQ_NON_REENTRANT|
- WQ_CPU_INTENSIVE|
- WQ_MEM_RECLAIM,
- 1);
+ WQ_HIGHPRI |
+ WQ_MEM_RECLAIM |
+ WQ_UNBOUND, num_online_cpus());
if (!cc->crypt_queue) {
ti->error = "Couldn't create kcryptd queue";
goto bad;
}
+ init_waitqueue_head(&cc->write_thread_wait);
+ cc->write_tree = RB_ROOT;
+
+ cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write");
+ if (IS_ERR(cc->write_thread)) {
+ ret = PTR_ERR(cc->write_thread);
+ cc->write_thread = NULL;
+ ti->error = "Couldn't spawn write thread";
+ goto bad;
+ }
+ wake_up_process(cc->write_thread);
+
ti->num_flush_bios = 1;
ti->discard_zeroes_data_unsupported = true;
@@ -1666,11 +1710,13 @@
return DM_MAPIO_REMAPPED;
}
- io = crypt_io_alloc(cc, bio, dm_target_offset(ti, bio->bi_sector));
+ io = dm_per_bio_data(bio, cc->per_bio_data_size);
+ crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_sector));
+ io->ctx.req = (struct ablkcipher_request *)(io + 1);
if (bio_data_dir(io->base_bio) == READ) {
if (kcryptd_io_read(io, GFP_NOWAIT))
- kcryptd_queue_io(io);
+ kcryptd_queue_read(io);
} else
kcryptd_queue_crypt(io);
@@ -1816,15 +1862,9 @@
{
int r;
- _crypt_io_pool = KMEM_CACHE(dm_crypt_io, 0);
- if (!_crypt_io_pool)
- return -ENOMEM;
-
r = dm_register_target(&crypt_target);
- if (r < 0) {
+ if (r < 0)
DMERR("register failed %d", r);
- kmem_cache_destroy(_crypt_io_pool);
- }
return r;
}
@@ -1832,7 +1872,6 @@
static void __exit dm_crypt_exit(void)
{
dm_unregister_target(&crypt_target);
- kmem_cache_destroy(_crypt_io_pool);
}
module_init(dm_crypt_init);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 81a79b7..1debe04 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1849,6 +1849,45 @@
dm_hash_exit();
}
+
+/**
+ * dm_ioctl_export - Permanently export a mapped device via the ioctl interface
+ * @md: Pointer to mapped_device
+ * @name: Buffer (size DM_NAME_LEN) for name
+ * @uuid: Buffer (size DM_UUID_LEN) for uuid or NULL if not desired
+ */
+int dm_ioctl_export(struct mapped_device *md, const char *name,
+ const char *uuid)
+{
+ int r = 0;
+ struct hash_cell *hc;
+
+ if (!md) {
+ r = -ENXIO;
+ goto out;
+ }
+
+ /* The name and uuid can only be set once. */
+ mutex_lock(&dm_hash_cells_mutex);
+ hc = dm_get_mdptr(md);
+ mutex_unlock(&dm_hash_cells_mutex);
+ if (hc) {
+ DMERR("%s: already exported", dm_device_name(md));
+ r = -ENXIO;
+ goto out;
+ }
+
+ r = dm_hash_insert(name, uuid, md);
+ if (r) {
+ DMERR("%s: could not bind to '%s'", dm_device_name(md), name);
+ goto out;
+ }
+
+ /* Let udev know we've changed. */
+ dm_kobject_uevent(md, KOBJ_CHANGE, dm_get_event_nr(md));
+out:
+ return r;
+}
/**
* dm_copy_name_and_uuid - Copy mapped device name & uuid into supplied buffers
* @md: Pointer to mapped_device
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 4f99d26..f63e07d 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -25,7 +25,7 @@
/*
* Construct a linear mapping: <dev_path> <offset>
*/
-static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct linear_c *lc;
unsigned long long tmp;
@@ -64,7 +64,7 @@
return -EINVAL;
}
-static void linear_dtr(struct dm_target *ti)
+void dm_linear_dtr(struct dm_target *ti)
{
struct linear_c *lc = (struct linear_c *) ti->private;
@@ -88,14 +88,14 @@
bio->bi_sector = linear_map_sector(ti, bio->bi_sector);
}
-static int linear_map(struct dm_target *ti, struct bio *bio)
+int dm_linear_map(struct dm_target *ti, struct bio *bio)
{
linear_map_bio(ti, bio);
return DM_MAPIO_REMAPPED;
}
-static void linear_status(struct dm_target *ti, status_type_t type,
+void dm_linear_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct linear_c *lc = (struct linear_c *) ti->private;
@@ -112,7 +112,7 @@
}
}
-static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
+int dm_linear_ioctl(struct dm_target *ti, unsigned int cmd,
unsigned long arg)
{
struct linear_c *lc = (struct linear_c *) ti->private;
@@ -129,7 +129,7 @@
return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
}
-static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+int dm_linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
struct bio_vec *biovec, int max_size)
{
struct linear_c *lc = ti->private;
@@ -144,7 +144,7 @@
return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
}
-static int linear_iterate_devices(struct dm_target *ti,
+int dm_linear_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct linear_c *lc = ti->private;
@@ -156,13 +156,13 @@
.name = "linear",
.version = {1, 2, 1},
.module = THIS_MODULE,
- .ctr = linear_ctr,
- .dtr = linear_dtr,
- .map = linear_map,
- .status = linear_status,
- .ioctl = linear_ioctl,
- .merge = linear_merge,
- .iterate_devices = linear_iterate_devices,
+ .ctr = dm_linear_ctr,
+ .dtr = dm_linear_dtr,
+ .map = dm_linear_map,
+ .status = dm_linear_status,
+ .ioctl = dm_linear_ioctl,
+ .merge = dm_linear_merge,
+ .iterate_devices = dm_linear_iterate_devices,
};
int __init dm_linear_init(void)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index bd88d3da..6457828 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -11,6 +11,7 @@
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
+#include <linux/mount.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/slab.h>
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
new file mode 100644
index 0000000..94edd50
--- /dev/null
+++ b/drivers/md/dm-verity-fec.c
@@ -0,0 +1,886 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * Author: Sami Tolvanen <samitolvanen@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include "dm-verity-fec.h"
+#include <linux/sysfs.h>
+
+#define DM_MSG_PREFIX "verity-fec"
+
+/*
+ * If error correction has been configured, returns true.
+ */
+bool verity_fec_is_enabled(struct dm_verity *v)
+{
+ return v->fec && v->fec->dev;
+}
+
+/*
+ * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable
+ * length fields.
+ */
+static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io)
+{
+ return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io);
+}
+
+/*
+ * Return an interleaved offset for a byte in RS block.
+ */
+static inline u64 fec_interleave(struct dm_verity *v, u64 offset)
+{
+ u32 mod;
+
+ mod = do_div(offset, v->fec->rsn);
+ return offset + mod * (v->fec->rounds << v->data_dev_block_bits);
+}
+
+/*
+ * Decode an RS block using Reed-Solomon.
+ */
+static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio,
+ u8 *data, u8 *fec, int neras)
+{
+ int i;
+ uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN];
+
+ for (i = 0; i < v->fec->roots; i++)
+ par[i] = fec[i];
+
+ return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras,
+ fio->erasures, 0, NULL);
+}
+
+/*
+ * Read error-correcting codes for the requested RS block. Returns a pointer
+ * to the data block. Caller is responsible for releasing buf.
+ */
+static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index,
+ unsigned *offset, struct dm_buffer **buf)
+{
+ u64 position, block;
+ u8 *res;
+
+ position = (index + rsb) * v->fec->roots;
+ block = position >> v->data_dev_block_bits;
+ *offset = (unsigned)(position - (block << v->data_dev_block_bits));
+
+ res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf);
+ if (unlikely(IS_ERR(res))) {
+ DMERR("%s: FEC %llu: parity read failed (block %llu): %ld",
+ v->data_dev->name, (unsigned long long)rsb,
+ (unsigned long long)(v->fec->start + block),
+ PTR_ERR(res));
+ *buf = NULL;
+ }
+
+ return res;
+}
+
+/* Loop over each preallocated buffer slot. */
+#define fec_for_each_prealloc_buffer(__i) \
+ for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++)
+
+/* Loop over each extra buffer slot. */
+#define fec_for_each_extra_buffer(io, __i) \
+ for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++)
+
+/* Loop over each allocated buffer. */
+#define fec_for_each_buffer(io, __i) \
+ for (__i = 0; __i < (io)->nbufs; __i++)
+
+/* Loop over each RS block in each allocated buffer. */
+#define fec_for_each_buffer_rs_block(io, __i, __j) \
+ fec_for_each_buffer(io, __i) \
+ for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++)
+
+/*
+ * Return a pointer to the current RS block when called inside
+ * fec_for_each_buffer_rs_block.
+ */
+static inline u8 *fec_buffer_rs_block(struct dm_verity *v,
+ struct dm_verity_fec_io *fio,
+ unsigned i, unsigned j)
+{
+ return &fio->bufs[i][j * v->fec->rsn];
+}
+
+/*
+ * Return an index to the current RS block when called inside
+ * fec_for_each_buffer_rs_block.
+ */
+static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j)
+{
+ return (i << DM_VERITY_FEC_BUF_RS_BITS) + j;
+}
+
+/*
+ * Decode all RS blocks from buffers and copy corrected bytes into fio->output
+ * starting from block_offset.
+ */
+static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
+ u64 rsb, int byte_index, unsigned block_offset,
+ int neras)
+{
+ int r, corrected = 0, res;
+ struct dm_buffer *buf;
+ unsigned n, i, offset;
+ u8 *par, *block;
+
+ par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
+ if (IS_ERR(par))
+ return PTR_ERR(par);
+
+ /*
+ * Decode the RS blocks we have in bufs. Each RS block results in
+ * one corrected target byte and consumes fec->roots parity bytes.
+ */
+ fec_for_each_buffer_rs_block(fio, n, i) {
+ block = fec_buffer_rs_block(v, fio, n, i);
+ res = fec_decode_rs8(v, fio, block, &par[offset], neras);
+ if (res < 0) {
+ dm_bufio_release(buf);
+
+ r = res;
+ goto error;
+ }
+
+ corrected += res;
+ fio->output[block_offset] = block[byte_index];
+
+ block_offset++;
+ if (block_offset >= 1 << v->data_dev_block_bits)
+ goto done;
+
+ /* read the next block when we run out of parity bytes */
+ offset += v->fec->roots;
+ if (offset >= 1 << v->data_dev_block_bits) {
+ dm_bufio_release(buf);
+
+ par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
+ if (unlikely(IS_ERR(par)))
+ return PTR_ERR(par);
+ }
+ }
+done:
+ r = corrected;
+error:
+ if (r < 0 && neras)
+ DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
+ v->data_dev->name, (unsigned long long)rsb, r);
+ else if (r > 0) {
+ DMWARN_LIMIT("%s: FEC %llu: corrected %d errors",
+ v->data_dev->name, (unsigned long long)rsb, r);
+ atomic_add_unless(&v->fec->corrected, 1, INT_MAX);
+ }
+
+ return r;
+}
+
+/*
+ * Locate data block erasures using verity hashes.
+ */
+static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
+ u8 *want_digest, u8 *data)
+{
+ if (unlikely(verity_hash(v, verity_io_hash_desc(v, io),
+ data, 1 << v->data_dev_block_bits,
+ verity_io_real_digest(v, io))))
+ return 0;
+
+ return memcmp(verity_io_real_digest(v, io), want_digest,
+ v->digest_size) != 0;
+}
+
+/*
+ * Read data blocks that are part of the RS block and deinterleave as much as
+ * fits into buffers. Check for erasure locations if @neras is non-NULL.
+ */
+static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io,
+ u64 rsb, u64 target, unsigned block_offset,
+ int *neras)
+{
+ bool is_zero;
+ int i, j, target_index = -1;
+ struct dm_buffer *buf;
+ struct dm_bufio_client *bufio;
+ struct dm_verity_fec_io *fio = fec_io(io);
+ u64 block, ileaved;
+ u8 *bbuf, *rs_block;
+ u8 want_digest[v->digest_size];
+ unsigned n, k;
+
+ if (neras)
+ *neras = 0;
+
+ /*
+ * read each of the rsn data blocks that are part of the RS block, and
+ * interleave contents to available bufs
+ */
+ for (i = 0; i < v->fec->rsn; i++) {
+ ileaved = fec_interleave(v, rsb * v->fec->rsn + i);
+
+ /*
+ * target is the data block we want to correct, target_index is
+ * the index of this block within the rsn RS blocks
+ */
+ if (ileaved == target)
+ target_index = i;
+
+ block = ileaved >> v->data_dev_block_bits;
+ bufio = v->fec->data_bufio;
+
+ if (block >= v->data_blocks) {
+ block -= v->data_blocks;
+
+ /*
+ * blocks outside the area were assumed to contain
+ * zeros when encoding data was generated
+ */
+ if (unlikely(block >= v->fec->hash_blocks))
+ continue;
+
+ block += v->hash_start;
+ bufio = v->bufio;
+ }
+
+ bbuf = dm_bufio_read(bufio, block, &buf);
+
+ if (unlikely(IS_ERR(bbuf))) {
+ DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld",
+ v->data_dev->name,
+ (unsigned long long)rsb,
+ (unsigned long long)block, PTR_ERR(bbuf));
+
+ /* assume the block is corrupted */
+ if (neras && *neras <= v->fec->roots)
+ fio->erasures[(*neras)++] = i;
+
+ continue;
+ }
+
+ /* locate erasures if the block is on the data device */
+ if (bufio == v->fec->data_bufio &&
+ verity_hash_for_block(v, io, block, want_digest,
+ &is_zero) == 0) {
+ /* skip known zero blocks entirely */
+ if (is_zero)
+ continue;
+
+ /*
+ * skip if we have already found the theoretical
+ * maximum number (i.e. fec->roots) of erasures
+ */
+ if (neras && *neras <= v->fec->roots &&
+ fec_is_erasure(v, io, want_digest, bbuf))
+ fio->erasures[(*neras)++] = i;
+ }
+
+ /*
+ * deinterleave and copy the bytes that fit into bufs,
+ * starting from block_offset
+ */
+ fec_for_each_buffer_rs_block(fio, n, j) {
+ k = fec_buffer_rs_index(n, j) + block_offset;
+
+ if (k >= 1 << v->data_dev_block_bits)
+ goto done;
+
+ rs_block = fec_buffer_rs_block(v, fio, n, j);
+ rs_block[i] = bbuf[k];
+ }
+done:
+ dm_bufio_release(buf);
+ }
+
+ return target_index;
+}
+
+/*
+ * Allocate RS control structure and FEC buffers from preallocated mempools,
+ * and attempt to allocate as many extra buffers as available.
+ */
+static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
+{
+ unsigned n;
+
+ if (!fio->rs) {
+ fio->rs = mempool_alloc(v->fec->rs_pool, 0);
+ if (unlikely(!fio->rs)) {
+ DMERR("failed to allocate RS");
+ return -ENOMEM;
+ }
+ }
+
+ fec_for_each_prealloc_buffer(n) {
+ if (fio->bufs[n])
+ continue;
+
+ fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO);
+ if (unlikely(!fio->bufs[n])) {
+ DMERR("failed to allocate FEC buffer");
+ return -ENOMEM;
+ }
+ }
+
+ /* try to allocate the maximum number of buffers */
+ fec_for_each_extra_buffer(fio, n) {
+ if (fio->bufs[n])
+ continue;
+
+ fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO);
+ /* we can manage with even one buffer if necessary */
+ if (unlikely(!fio->bufs[n]))
+ break;
+ }
+ fio->nbufs = n;
+
+ if (!fio->output) {
+ fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO);
+
+ if (!fio->output) {
+ DMERR("failed to allocate FEC page");
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are
+ * zeroed before deinterleaving.
+ */
+static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
+{
+ unsigned n;
+
+ fec_for_each_buffer(fio, n)
+ memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS);
+
+ memset(fio->erasures, 0, sizeof(fio->erasures));
+}
+
+/*
+ * Decode all RS blocks in a single data block and return the target block
+ * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses
+ * hashes to locate erasures.
+ */
+static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
+ struct dm_verity_fec_io *fio, u64 rsb, u64 offset,
+ bool use_erasures)
+{
+ int r, neras = 0;
+ unsigned pos;
+
+ r = fec_alloc_bufs(v, fio);
+ if (unlikely(r < 0))
+ return r;
+
+ for (pos = 0; pos < 1 << v->data_dev_block_bits; ) {
+ fec_init_bufs(v, fio);
+
+ r = fec_read_bufs(v, io, rsb, offset, pos,
+ use_erasures ? &neras : NULL);
+ if (unlikely(r < 0))
+ return r;
+
+ r = fec_decode_bufs(v, fio, rsb, r, pos, neras);
+ if (r < 0)
+ return r;
+
+ pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS;
+ }
+
+ /* Always re-validate the corrected block against the expected hash */
+ r = verity_hash(v, verity_io_hash_desc(v, io), fio->output,
+ 1 << v->data_dev_block_bits,
+ verity_io_real_digest(v, io));
+ if (unlikely(r < 0))
+ return r;
+
+ if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io),
+ v->digest_size)) {
+ DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)",
+ v->data_dev->name, (unsigned long long)rsb, neras);
+ return -EILSEQ;
+ }
+
+ return 0;
+}
+
+static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data,
+ size_t len)
+{
+ struct dm_verity_fec_io *fio = fec_io(io);
+
+ memcpy(data, &fio->output[fio->output_pos], len);
+ fio->output_pos += len;
+
+ return 0;
+}
+
+/*
+ * Correct errors in a block. Copies corrected block to dest if non-NULL,
+ * otherwise to io->io_vec starting from provided vector and offset.
+ */
+int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
+ enum verity_block_type type, sector_t block, u8 *dest,
+ unsigned bv_vector, unsigned bv_offset)
+{
+ int r;
+ struct dm_verity_fec_io *fio = fec_io(io);
+ u64 offset, res, rsb;
+
+ if (!verity_fec_is_enabled(v))
+ return -EOPNOTSUPP;
+
+ if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) {
+ DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name);
+ return -EIO;
+ }
+
+ fio->level++;
+
+ if (type == DM_VERITY_BLOCK_TYPE_METADATA)
+ block += v->data_blocks;
+
+ /*
+ * For RS(M, N), the continuous FEC data is divided into blocks of N
+ * bytes. Since block size may not be divisible by N, the last block
+ * is zero padded when decoding.
+ *
+ * Each byte of the block is covered by a different RS(M, N) code,
+ * and each code is interleaved over N blocks to make it less likely
+ * that bursty corruption will leave us in unrecoverable state.
+ */
+
+ offset = block << v->data_dev_block_bits;
+
+ res = offset;
+ do_div(res, v->fec->rounds << v->data_dev_block_bits);
+
+ /*
+ * The base RS block we can feed to the interleaver to find out all
+ * blocks required for decoding.
+ */
+ rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits);
+
+ /*
+ * Locating erasures is slow, so attempt to recover the block without
+ * them first. Do a second attempt with erasures if the corruption is
+ * bad enough.
+ */
+ r = fec_decode_rsb(v, io, fio, rsb, offset, false);
+ if (r < 0) {
+ r = fec_decode_rsb(v, io, fio, rsb, offset, true);
+ if (r < 0)
+ goto done;
+ }
+
+ if (dest)
+ memcpy(dest, fio->output, 1 << v->data_dev_block_bits);
+ else {
+ fio->output_pos = 0;
+ r = verity_for_bv_block(v, io, &bv_vector, &bv_offset,
+ fec_bv_copy);
+ }
+
+done:
+ fio->level--;
+ return r;
+}
+
+/*
+ * Clean up per-bio data.
+ */
+void verity_fec_finish_io(struct dm_verity_io *io, int error)
+{
+ unsigned n;
+ struct dm_verity_fec *f = io->v->fec;
+ struct dm_verity_fec_io *fio = fec_io(io);
+ struct bio *bio = dm_bio_from_per_bio_data(io,
+ io->v->ti->per_bio_data_size);
+
+ if (!verity_fec_is_enabled(io->v))
+ return;
+
+ if (fio->rs)
+ mempool_free(fio->rs, f->rs_pool);
+
+ fec_for_each_prealloc_buffer(n)
+ if (fio->bufs[n])
+ mempool_free(fio->bufs[n], f->prealloc_pool);
+
+ fec_for_each_extra_buffer(fio, n)
+ if (fio->bufs[n])
+ mempool_free(fio->bufs[n], f->extra_pool);
+
+ if (fio->output)
+ mempool_free(fio->output, f->output_pool);
+
+ if (!error && !test_bit(BIO_UPTODATE, &bio->bi_flags))
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
+}
+
+/*
+ * Initialize per-bio data.
+ */
+void verity_fec_init_io(struct dm_verity_io *io)
+{
+ struct dm_verity_fec_io *fio = fec_io(io);
+
+ if (!verity_fec_is_enabled(io->v))
+ return;
+
+ fio->rs = NULL;
+ memset(fio->bufs, 0, sizeof(fio->bufs));
+ fio->nbufs = 0;
+ fio->output = NULL;
+ fio->level = 0;
+}
+
+/*
+ * Append feature arguments and values to the status table.
+ */
+unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz,
+ char *result, unsigned maxlen)
+{
+ if (!verity_fec_is_enabled(v))
+ return sz;
+
+ DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s "
+ DM_VERITY_OPT_FEC_BLOCKS " %llu "
+ DM_VERITY_OPT_FEC_START " %llu "
+ DM_VERITY_OPT_FEC_ROOTS " %d",
+ v->fec->dev->name,
+ (unsigned long long)v->fec->blocks,
+ (unsigned long long)v->fec->start,
+ v->fec->roots);
+
+ return sz;
+}
+
+void verity_fec_dtr(struct dm_verity *v)
+{
+ struct dm_verity_fec *f = v->fec;
+ struct kobject *kobj = &f->kobj_holder.kobj;
+
+ if (!verity_fec_is_enabled(v))
+ goto out;
+
+ if (f->rs_pool)
+ mempool_destroy(f->rs_pool);
+ if (f->prealloc_pool)
+ mempool_destroy(f->prealloc_pool);
+ if (f->extra_pool)
+ mempool_destroy(f->extra_pool);
+ if (f->cache)
+ kmem_cache_destroy(f->cache);
+
+ if (f->data_bufio)
+ dm_bufio_client_destroy(f->data_bufio);
+ if (f->bufio)
+ dm_bufio_client_destroy(f->bufio);
+
+ if (f->dev)
+ dm_put_device(v->ti, f->dev);
+
+ if (kobj->state_initialized) {
+ kobject_put(kobj);
+ wait_for_completion(dm_get_completion_from_kobject(kobj));
+ }
+
+out:
+ kfree(f);
+ v->fec = NULL;
+}
+
+static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data)
+{
+ struct dm_verity *v = (struct dm_verity *)pool_data;
+
+ return init_rs(8, 0x11d, 0, 1, v->fec->roots);
+}
+
+static void fec_rs_free(void *element, void *pool_data)
+{
+ struct rs_control *rs = (struct rs_control *)element;
+
+ if (rs)
+ free_rs(rs);
+}
+
+bool verity_is_fec_opt_arg(const char *arg_name)
+{
+ return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) ||
+ !strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) ||
+ !strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) ||
+ !strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS));
+}
+
+int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
+ unsigned *argc, const char *arg_name)
+{
+ int r;
+ struct dm_target *ti = v->ti;
+ const char *arg_value;
+ unsigned long long num_ll;
+ unsigned char num_c;
+ char dummy;
+
+ if (!*argc) {
+ ti->error = "FEC feature arguments require a value";
+ return -EINVAL;
+ }
+
+ arg_value = dm_shift_arg(as);
+ (*argc)--;
+
+ if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) {
+ r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev);
+ if (r) {
+ ti->error = "FEC device lookup failed";
+ return r;
+ }
+
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) {
+ if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 ||
+ ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT))
+ >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) {
+ ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS;
+ return -EINVAL;
+ }
+ v->fec->blocks = num_ll;
+
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) {
+ if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 ||
+ ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >>
+ (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) {
+ ti->error = "Invalid " DM_VERITY_OPT_FEC_START;
+ return -EINVAL;
+ }
+ v->fec->start = num_ll;
+
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) {
+ if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c ||
+ num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) ||
+ num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) {
+ ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS;
+ return -EINVAL;
+ }
+ v->fec->roots = num_c;
+
+ } else {
+ ti->error = "Unrecognized verity FEC feature request";
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static ssize_t corrected_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct dm_verity_fec *f = container_of(kobj, struct dm_verity_fec,
+ kobj_holder.kobj);
+
+ return sprintf(buf, "%d\n", atomic_read(&f->corrected));
+}
+
+static struct kobj_attribute attr_corrected = __ATTR_RO(corrected);
+
+static struct attribute *fec_attrs[] = {
+ &attr_corrected.attr,
+ NULL
+};
+
+static struct kobj_type fec_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_attrs = fec_attrs,
+ .release = dm_kobject_release
+};
+
+/*
+ * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr.
+ */
+int verity_fec_ctr_alloc(struct dm_verity *v)
+{
+ struct dm_verity_fec *f;
+
+ f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL);
+ if (!f) {
+ v->ti->error = "Cannot allocate FEC structure";
+ return -ENOMEM;
+ }
+ v->fec = f;
+
+ return 0;
+}
+
+/*
+ * Validate arguments and preallocate memory. Must be called after arguments
+ * have been parsed using verity_fec_parse_opt_args.
+ */
+int verity_fec_ctr(struct dm_verity *v)
+{
+ int r;
+ struct dm_verity_fec *f = v->fec;
+ struct dm_target *ti = v->ti;
+ struct mapped_device *md = dm_table_get_md(ti->table);
+ u64 hash_blocks;
+
+ if (!verity_fec_is_enabled(v)) {
+ verity_fec_dtr(v);
+ return 0;
+ }
+
+ /* Create a kobject and sysfs attributes */
+ init_completion(&f->kobj_holder.completion);
+
+ r = kobject_init_and_add(&f->kobj_holder.kobj, &fec_ktype,
+ &disk_to_dev(dm_disk(md))->kobj, "%s", "fec");
+ if (r) {
+ ti->error = "Cannot create kobject";
+ return r;
+ }
+
+ /*
+ * FEC is computed over data blocks, possible metadata, and
+ * hash blocks. In other words, FEC covers total of fec_blocks
+ * blocks consisting of the following:
+ *
+ * data blocks | hash blocks | metadata (optional)
+ *
+ * We allow metadata after hash blocks to support a use case
+ * where all data is stored on the same device and FEC covers
+ * the entire area.
+ *
+ * If metadata is included, we require it to be available on the
+ * hash device after the hash blocks.
+ */
+
+ hash_blocks = v->hash_blocks - v->hash_start;
+
+ /*
+ * Require matching block sizes for data and hash devices for
+ * simplicity.
+ */
+ if (v->data_dev_block_bits != v->hash_dev_block_bits) {
+ ti->error = "Block sizes must match to use FEC";
+ return -EINVAL;
+ }
+
+ if (!f->roots) {
+ ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS;
+ return -EINVAL;
+ }
+ f->rsn = DM_VERITY_FEC_RSM - f->roots;
+
+ if (!f->blocks) {
+ ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS;
+ return -EINVAL;
+ }
+
+ f->rounds = f->blocks;
+ if (sector_div(f->rounds, f->rsn))
+ f->rounds++;
+
+ /*
+ * Due to optional metadata, f->blocks can be larger than
+ * data_blocks and hash_blocks combined.
+ */
+ if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) {
+ ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS;
+ return -EINVAL;
+ }
+
+ /*
+ * Metadata is accessed through the hash device, so we require
+ * it to be large enough.
+ */
+ f->hash_blocks = f->blocks - v->data_blocks;
+ if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) {
+ ti->error = "Hash device is too small for "
+ DM_VERITY_OPT_FEC_BLOCKS;
+ return -E2BIG;
+ }
+
+ f->bufio = dm_bufio_client_create(f->dev->bdev,
+ 1 << v->data_dev_block_bits,
+ 1, 0, NULL, NULL);
+ if (IS_ERR(f->bufio)) {
+ ti->error = "Cannot initialize FEC bufio client";
+ return PTR_ERR(f->bufio);
+ }
+
+ if (dm_bufio_get_device_size(f->bufio) <
+ ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) {
+ ti->error = "FEC device is too small";
+ return -E2BIG;
+ }
+
+ f->data_bufio = dm_bufio_client_create(v->data_dev->bdev,
+ 1 << v->data_dev_block_bits,
+ 1, 0, NULL, NULL);
+ if (IS_ERR(f->data_bufio)) {
+ ti->error = "Cannot initialize FEC data bufio client";
+ return PTR_ERR(f->data_bufio);
+ }
+
+ if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) {
+ ti->error = "Data device is too small";
+ return -E2BIG;
+ }
+
+ /* Preallocate an rs_control structure for each worker thread */
+ f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc,
+ fec_rs_free, (void *) v);
+ if (!f->rs_pool) {
+ ti->error = "Cannot allocate RS pool";
+ return -ENOMEM;
+ }
+
+ f->cache = kmem_cache_create("dm_verity_fec_buffers",
+ f->rsn << DM_VERITY_FEC_BUF_RS_BITS,
+ 0, 0, NULL);
+ if (!f->cache) {
+ ti->error = "Cannot create FEC buffer cache";
+ return -ENOMEM;
+ }
+
+ /* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */
+ f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() *
+ DM_VERITY_FEC_BUF_PREALLOC,
+ f->cache);
+ if (!f->prealloc_pool) {
+ ti->error = "Cannot allocate FEC buffer prealloc pool";
+ return -ENOMEM;
+ }
+
+ f->extra_pool = mempool_create_slab_pool(0, f->cache);
+ if (!f->extra_pool) {
+ ti->error = "Cannot allocate FEC buffer extra pool";
+ return -ENOMEM;
+ }
+
+ /* Preallocate an output buffer for each thread */
+ f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(),
+ 1 << v->data_dev_block_bits);
+ if (!f->output_pool) {
+ ti->error = "Cannot allocate FEC output pool";
+ return -ENOMEM;
+ }
+
+ /* Reserve space for our per-bio data */
+ ti->per_bio_data_size += sizeof(struct dm_verity_fec_io);
+
+ return 0;
+}
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
new file mode 100644
index 0000000..f6ebcbf
--- /dev/null
+++ b/drivers/md/dm-verity-fec.h
@@ -0,0 +1,159 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * Author: Sami Tolvanen <samitolvanen@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef DM_VERITY_FEC_H
+#define DM_VERITY_FEC_H
+
+#include "dm.h"
+#include "dm-verity.h"
+#include <linux/rslib.h>
+
+/* Reed-Solomon(M, N) parameters */
+#define DM_VERITY_FEC_RSM 255
+#define DM_VERITY_FEC_MAX_RSN 253
+#define DM_VERITY_FEC_MIN_RSN 231 /* ~10% space overhead */
+
+/* buffers for deinterleaving and decoding */
+#define DM_VERITY_FEC_BUF_PREALLOC 1 /* buffers to preallocate */
+#define DM_VERITY_FEC_BUF_RS_BITS 4 /* 1 << RS blocks per buffer */
+/* we need buffers for at most 1 << block size RS blocks */
+#define DM_VERITY_FEC_BUF_MAX \
+ (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
+
+/* maximum recursion level for verity_fec_decode */
+#define DM_VERITY_FEC_MAX_RECURSION 4
+
+#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device"
+#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks"
+#define DM_VERITY_OPT_FEC_START "fec_start"
+#define DM_VERITY_OPT_FEC_ROOTS "fec_roots"
+
+/* configuration */
+struct dm_verity_fec {
+ struct dm_dev *dev; /* parity data device */
+ struct dm_bufio_client *data_bufio; /* for data dev access */
+ struct dm_bufio_client *bufio; /* for parity data access */
+ sector_t start; /* parity data start in blocks */
+ sector_t blocks; /* number of blocks covered */
+ sector_t rounds; /* number of interleaving rounds */
+ sector_t hash_blocks; /* blocks covered after v->hash_start */
+ unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */
+ unsigned char rsn; /* N of RS(M, N) */
+ mempool_t *rs_pool; /* mempool for fio->rs */
+ mempool_t *prealloc_pool; /* mempool for preallocated buffers */
+ mempool_t *extra_pool; /* mempool for extra buffers */
+ mempool_t *output_pool; /* mempool for output */
+ struct kmem_cache *cache; /* cache for buffers */
+ atomic_t corrected; /* corrected errors */
+ struct dm_kobject_holder kobj_holder; /* for sysfs attributes */
+};
+
+/* per-bio data */
+struct dm_verity_fec_io {
+ struct rs_control *rs; /* Reed-Solomon state */
+ int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */
+ u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */
+ unsigned nbufs; /* number of buffers allocated */
+ u8 *output; /* buffer for corrected output */
+ size_t output_pos;
+ unsigned level; /* recursion level */
+};
+
+#ifdef CONFIG_DM_VERITY_FEC
+
+/* each feature parameter requires a value */
+#define DM_VERITY_OPTS_FEC 8
+
+extern bool verity_fec_is_enabled(struct dm_verity *v);
+
+extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
+ enum verity_block_type type, sector_t block,
+ u8 *dest, unsigned vector, unsigned offset);
+
+extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz,
+ char *result, unsigned maxlen);
+
+extern void verity_fec_finish_io(struct dm_verity_io *io, int error);
+extern void verity_fec_init_io(struct dm_verity_io *io);
+
+extern bool verity_is_fec_opt_arg(const char *arg_name);
+extern int verity_fec_parse_opt_args(struct dm_arg_set *as,
+ struct dm_verity *v, unsigned *argc,
+ const char *arg_name);
+
+extern void verity_fec_dtr(struct dm_verity *v);
+
+extern int verity_fec_ctr_alloc(struct dm_verity *v);
+extern int verity_fec_ctr(struct dm_verity *v);
+
+#else /* !CONFIG_DM_VERITY_FEC */
+
+#define DM_VERITY_OPTS_FEC 0
+
+static inline bool verity_fec_is_enabled(struct dm_verity *v)
+{
+ return false;
+}
+
+static inline int verity_fec_decode(struct dm_verity *v,
+ struct dm_verity_io *io,
+ enum verity_block_type type,
+ sector_t block, u8 *dest,
+ unsigned vector, unsigned offset)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline unsigned verity_fec_status_table(struct dm_verity *v,
+ unsigned sz, char *result,
+ unsigned maxlen)
+{
+ return sz;
+}
+
+static inline void verity_fec_finish_io(struct dm_verity_io *io, int error)
+{
+}
+
+static inline void verity_fec_init_io(struct dm_verity_io *io)
+{
+}
+
+static inline bool verity_is_fec_opt_arg(const char *arg_name)
+{
+ return false;
+}
+
+static inline int verity_fec_parse_opt_args(struct dm_arg_set *as,
+ struct dm_verity *v,
+ unsigned *argc,
+ const char *arg_name)
+{
+ return -EINVAL;
+}
+
+static inline void verity_fec_dtr(struct dm_verity *v)
+{
+}
+
+static inline int verity_fec_ctr_alloc(struct dm_verity *v)
+{
+ return 0;
+}
+
+static inline int verity_fec_ctr(struct dm_verity *v)
+{
+ return 0;
+}
+
+#endif /* CONFIG_DM_VERITY_FEC */
+
+#endif /* DM_VERITY_FEC_H */
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c
similarity index 60%
rename from drivers/md/dm-verity.c
rename to drivers/md/dm-verity-target.c
index 0d2e812..84f73cc 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity-target.c
@@ -14,85 +14,32 @@
* access behavior.
*/
-#include "dm-bufio.h"
+#include "dm-verity.h"
+#include "dm-verity-fec.h"
#include <linux/module.h>
-#include <linux/device-mapper.h>
-#include <crypto/hash.h>
+#include <linux/reboot.h>
#define DM_MSG_PREFIX "verity"
-#define DM_VERITY_IO_VEC_INLINE 16
+#define DM_VERITY_ENV_LENGTH 42
+#define DM_VERITY_ENV_VAR_NAME "DM_VERITY_ERR_BLOCK_NR"
+
#define DM_VERITY_MEMPOOL_SIZE 4
#define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144
-#define DM_VERITY_MAX_LEVELS 63
+#define DM_VERITY_MAX_CORRUPTED_ERRS 100
+
+#define DM_VERITY_OPT_LOGGING "ignore_corruption"
+#define DM_VERITY_OPT_RESTART "restart_on_corruption"
+#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks"
+
+#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC)
static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR);
-struct dm_verity {
- struct dm_dev *data_dev;
- struct dm_dev *hash_dev;
- struct dm_target *ti;
- struct dm_bufio_client *bufio;
- char *alg_name;
- struct crypto_shash *tfm;
- u8 *root_digest; /* digest of the root block */
- u8 *salt; /* salt: its size is salt_size */
- unsigned salt_size;
- sector_t data_start; /* data offset in 512-byte sectors */
- sector_t hash_start; /* hash start in blocks */
- sector_t data_blocks; /* the number of data blocks */
- sector_t hash_blocks; /* the number of hash blocks */
- unsigned char data_dev_block_bits; /* log2(data blocksize) */
- unsigned char hash_dev_block_bits; /* log2(hash blocksize) */
- unsigned char hash_per_block_bits; /* log2(hashes in hash block) */
- unsigned char levels; /* the number of tree levels */
- unsigned char version;
- unsigned digest_size; /* digest size for the current hash algorithm */
- unsigned shash_descsize;/* the size of temporary space for crypto */
- int hash_failed; /* set to 1 if hash of any block failed */
-
- mempool_t *vec_mempool; /* mempool of bio vector */
-
- struct workqueue_struct *verify_wq;
-
- /* starting blocks for each tree level. 0 is the lowest level. */
- sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
-};
-
-struct dm_verity_io {
- struct dm_verity *v;
-
- /* original values of bio->bi_end_io and bio->bi_private */
- bio_end_io_t *orig_bi_end_io;
- void *orig_bi_private;
-
- sector_t block;
- unsigned n_blocks;
-
- /* saved bio vector */
- struct bio_vec *io_vec;
- unsigned io_vec_size;
-
- struct work_struct work;
-
- /* A space for short vectors; longer vectors are allocated separately. */
- struct bio_vec io_vec_inline[DM_VERITY_IO_VEC_INLINE];
-
- /*
- * Three variably-size fields follow this struct:
- *
- * u8 hash_desc[v->shash_descsize];
- * u8 real_digest[v->digest_size];
- * u8 want_digest[v->digest_size];
- *
- * To access them use: io_hash_desc(), io_real_digest() and io_want_digest().
- */
-};
-
struct dm_verity_prefetch_work {
struct work_struct work;
struct dm_verity *v;
@@ -100,21 +47,6 @@
unsigned n_blocks;
};
-static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io)
-{
- return (struct shash_desc *)(io + 1);
-}
-
-static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io)
-{
- return (u8 *)(io + 1) + v->shash_descsize;
-}
-
-static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io)
-{
- return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
-}
-
/*
* Auxiliary structure appended to each dm-bufio buffer. If the value
* hash_verified is nonzero, hash of the block has been verified.
@@ -161,6 +93,84 @@
return block >> (level * v->hash_per_block_bits);
}
+/*
+ * Wrapper for crypto_shash_init, which handles verity salting.
+ */
+static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc)
+{
+ int r;
+
+ desc->tfm = v->tfm;
+ desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ r = crypto_shash_init(desc);
+
+ if (unlikely(r < 0)) {
+ DMERR("crypto_shash_init failed: %d", r);
+ return r;
+ }
+
+ if (likely(v->version >= 1)) {
+ r = crypto_shash_update(desc, v->salt, v->salt_size);
+
+ if (unlikely(r < 0)) {
+ DMERR("crypto_shash_update failed: %d", r);
+ return r;
+ }
+ }
+
+ return 0;
+}
+
+static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc,
+ const u8 *data, size_t len)
+{
+ int r = crypto_shash_update(desc, data, len);
+
+ if (unlikely(r < 0))
+ DMERR("crypto_shash_update failed: %d", r);
+
+ return r;
+}
+
+static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc,
+ u8 *digest)
+{
+ int r;
+
+ if (unlikely(!v->version)) {
+ r = crypto_shash_update(desc, v->salt, v->salt_size);
+
+ if (r < 0) {
+ DMERR("crypto_shash_update failed: %d", r);
+ return r;
+ }
+ }
+
+ r = crypto_shash_final(desc, digest);
+
+ if (unlikely(r < 0))
+ DMERR("crypto_shash_final failed: %d", r);
+
+ return r;
+}
+
+int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+ const u8 *data, size_t len, u8 *digest)
+{
+ int r;
+
+ r = verity_hash_init(v, desc);
+ if (unlikely(r < 0))
+ return r;
+
+ r = verity_hash_update(v, desc, data, len);
+ if (unlikely(r < 0))
+ return r;
+
+ return verity_hash_final(v, desc, digest);
+}
+
static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
sector_t *hash_block, unsigned *offset)
{
@@ -180,20 +190,71 @@
}
/*
+ * Handle verification errors.
+ */
+static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
+ unsigned long long block)
+{
+ char verity_env[DM_VERITY_ENV_LENGTH];
+ char *envp[] = { verity_env, NULL };
+ const char *type_str = "";
+ struct mapped_device *md = dm_table_get_md(v->ti->table);
+
+ /* Corruption should be visible in device status in all modes */
+ v->hash_failed = 1;
+
+ if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS)
+ goto out;
+
+ v->corrupted_errs++;
+
+ switch (type) {
+ case DM_VERITY_BLOCK_TYPE_DATA:
+ type_str = "data";
+ break;
+ case DM_VERITY_BLOCK_TYPE_METADATA:
+ type_str = "metadata";
+ break;
+ default:
+ BUG();
+ }
+
+ DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str,
+ block);
+
+ if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS)
+ DMERR("%s: reached maximum errors", v->data_dev->name);
+
+ snprintf(verity_env, DM_VERITY_ENV_LENGTH, "%s=%d,%llu",
+ DM_VERITY_ENV_VAR_NAME, type, block);
+
+ kobject_uevent_env(&disk_to_dev(dm_disk(md))->kobj, KOBJ_CHANGE, envp);
+
+out:
+ if (v->mode == DM_VERITY_MODE_LOGGING)
+ return 0;
+
+ if (v->mode == DM_VERITY_MODE_RESTART)
+ kernel_restart("dm-verity device corrupted");
+
+ return 1;
+}
+
+/*
* Verify hash of a metadata block pertaining to the specified data block
* ("block" argument) at a specified level ("level" argument).
*
- * On successful return, io_want_digest(v, io) contains the hash value for
- * a lower tree level or for the data block (if we're at the lowest leve).
+ * On successful return, verity_io_want_digest(v, io) contains the hash value
+ * for a lower tree level or for the data block (if we're at the lowest level).
*
* If "skip_unverified" is true, unverified buffer is skipped and 1 is returned.
* If "skip_unverified" is false, unverified buffer is hashed and verified
- * against current value of io_want_digest(v, io).
+ * against current value of verity_io_want_digest(v, io).
*/
-static int verity_verify_level(struct dm_verity_io *io, sector_t block,
- int level, bool skip_unverified)
+static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
+ sector_t block, int level, bool skip_unverified,
+ u8 *want_digest)
{
- struct dm_verity *v = io->v;
struct dm_buffer *buf;
struct buffer_aux *aux;
u8 *data;
@@ -204,184 +265,203 @@
verity_hash_at_level(v, block, level, &hash_block, &offset);
data = dm_bufio_read(v->bufio, hash_block, &buf);
- if (unlikely(IS_ERR(data)))
+ if (IS_ERR(data))
return PTR_ERR(data);
aux = dm_bufio_get_aux_data(buf);
if (!aux->hash_verified) {
- struct shash_desc *desc;
- u8 *result;
-
if (skip_unverified) {
r = 1;
goto release_ret_r;
}
- desc = io_hash_desc(v, io);
- desc->tfm = v->tfm;
- desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- r = crypto_shash_init(desc);
- if (r < 0) {
- DMERR("crypto_shash_init failed: %d", r);
+ r = verity_hash(v, verity_io_hash_desc(v, io),
+ data, 1 << v->hash_dev_block_bits,
+ verity_io_real_digest(v, io));
+ if (unlikely(r < 0))
goto release_ret_r;
- }
- if (likely(v->version >= 1)) {
- r = crypto_shash_update(desc, v->salt, v->salt_size);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- goto release_ret_r;
- }
- }
-
- r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- goto release_ret_r;
- }
-
- if (!v->version) {
- r = crypto_shash_update(desc, v->salt, v->salt_size);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- goto release_ret_r;
- }
- }
-
- result = io_real_digest(v, io);
- r = crypto_shash_final(desc, result);
- if (r < 0) {
- DMERR("crypto_shash_final failed: %d", r);
- goto release_ret_r;
- }
- if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
- DMERR_LIMIT("metadata block %llu is corrupted",
- (unsigned long long)hash_block);
- v->hash_failed = 1;
+ if (likely(memcmp(verity_io_real_digest(v, io), want_digest,
+ v->digest_size) == 0))
+ aux->hash_verified = 1;
+ else if (verity_fec_decode(v, io,
+ DM_VERITY_BLOCK_TYPE_METADATA,
+ hash_block, data, 0, 0) == 0)
+ aux->hash_verified = 1;
+ else if (verity_handle_err(v,
+ DM_VERITY_BLOCK_TYPE_METADATA,
+ hash_block)) {
r = -EIO;
goto release_ret_r;
- } else
- aux->hash_verified = 1;
+ }
}
data += offset;
-
- memcpy(io_want_digest(v, io), data, v->digest_size);
-
- dm_bufio_release(buf);
- return 0;
+ memcpy(want_digest, data, v->digest_size);
+ r = 0;
release_ret_r:
dm_bufio_release(buf);
+ return r;
+}
+
+/*
+ * Find a hash for a given block, write it to digest and verify the integrity
+ * of the hash tree if necessary.
+ */
+int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
+ sector_t block, u8 *digest, bool *is_zero)
+{
+ int r = 0, i;
+
+ if (likely(v->levels)) {
+ /*
+ * First, we try to get the requested hash for
+ * the current block. If the hash block itself is
+ * verified, zero is returned. If it isn't, this
+ * function returns 1 and we fall back to whole
+ * chain verification.
+ */
+ r = verity_verify_level(v, io, block, 0, true, digest);
+ if (likely(r <= 0))
+ goto out;
+ }
+
+ memcpy(digest, v->root_digest, v->digest_size);
+
+ for (i = v->levels - 1; i >= 0; i--) {
+ r = verity_verify_level(v, io, block, i, false, digest);
+ if (unlikely(r))
+ goto out;
+ }
+
+out:
+ if (!r && v->zero_digest)
+ *is_zero = !memcmp(v->zero_digest, digest, v->digest_size);
+ else
+ *is_zero = false;
return r;
}
/*
+ * Calls function process for 1 << v->data_dev_block_bits bytes in io->io_vec
+ * starting from (vector, offset).
+ */
+int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
+ unsigned *vector, unsigned *offset,
+ int (*process)(struct dm_verity *v,
+ struct dm_verity_io *io,
+ u8 *data, size_t len))
+{
+ unsigned todo = 1 << v->data_dev_block_bits;
+
+ do {
+ int r;
+ struct bio_vec *bv;
+ u8 *page;
+ unsigned len;
+
+ BUG_ON(*vector >= io->io_vec_size);
+ bv = &io->io_vec[*vector];
+ page = kmap_atomic(bv->bv_page);
+ len = bv->bv_len - *offset;
+
+ if (likely(len >= todo))
+ len = todo;
+
+ r = process(v, io, page + bv->bv_offset + *offset, len);
+ kunmap_atomic(page);
+
+ if (r < 0)
+ return r;
+
+ *offset += len;
+
+ if (likely(*offset == bv->bv_len)) {
+ *offset = 0;
+ (*vector)++;
+ }
+
+ todo -= len;
+ } while (todo);
+
+ return 0;
+}
+
+static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io,
+ u8 *data, size_t len)
+{
+ return verity_hash_update(v, verity_io_hash_desc(v, io), data, len);
+}
+
+static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
+ u8 *data, size_t len)
+{
+ memset(data, 0, len);
+ return 0;
+}
+
+/*
* Verify one "dm_verity_io" structure.
*/
static int verity_verify_io(struct dm_verity_io *io)
{
+ bool is_zero;
struct dm_verity *v = io->v;
unsigned b;
- int i;
unsigned vector = 0, offset = 0;
+ unsigned start_vector, start_offset;
for (b = 0; b < io->n_blocks; b++) {
- struct shash_desc *desc;
- u8 *result;
int r;
- unsigned todo;
+ struct shash_desc *desc = verity_io_hash_desc(v, io);
- if (likely(v->levels)) {
+ r = verity_hash_for_block(v, io, io->block + b,
+ verity_io_want_digest(v, io),
+ &is_zero);
+ if (unlikely(r < 0))
+ return r;
+
+ if (is_zero) {
/*
- * First, we try to get the requested hash for
- * the current block. If the hash block itself is
- * verified, zero is returned. If it isn't, this
- * function returns 0 and we fall back to whole
- * chain verification.
+ * If we expect a zero block, don't validate, just
+ * return zeros.
*/
- int r = verity_verify_level(io, io->block + b, 0, true);
- if (likely(!r))
- goto test_block_hash;
- if (r < 0)
+ r = verity_for_bv_block(v, io, &vector, &offset,
+ verity_bv_zero);
+ if (unlikely(r < 0))
return r;
+
+ continue;
}
- memcpy(io_want_digest(v, io), v->root_digest, v->digest_size);
-
- for (i = v->levels - 1; i >= 0; i--) {
- int r = verity_verify_level(io, io->block + b, i, false);
- if (unlikely(r))
- return r;
- }
-
-test_block_hash:
- desc = io_hash_desc(v, io);
- desc->tfm = v->tfm;
- desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
- r = crypto_shash_init(desc);
- if (r < 0) {
- DMERR("crypto_shash_init failed: %d", r);
+ r = verity_hash_init(v, desc);
+ if (unlikely(r < 0))
return r;
- }
- if (likely(v->version >= 1)) {
- r = crypto_shash_update(desc, v->salt, v->salt_size);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- return r;
- }
- }
+ start_vector = vector;
+ start_offset = offset;
- todo = 1 << v->data_dev_block_bits;
- do {
- struct bio_vec *bv;
- u8 *page;
- unsigned len;
-
- BUG_ON(vector >= io->io_vec_size);
- bv = &io->io_vec[vector];
- page = kmap_atomic(bv->bv_page);
- len = bv->bv_len - offset;
- if (likely(len >= todo))
- len = todo;
- r = crypto_shash_update(desc,
- page + bv->bv_offset + offset, len);
- kunmap_atomic(page);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- return r;
- }
- offset += len;
- if (likely(offset == bv->bv_len)) {
- offset = 0;
- vector++;
- }
- todo -= len;
- } while (todo);
-
- if (!v->version) {
- r = crypto_shash_update(desc, v->salt, v->salt_size);
- if (r < 0) {
- DMERR("crypto_shash_update failed: %d", r);
- return r;
- }
- }
-
- result = io_real_digest(v, io);
- r = crypto_shash_final(desc, result);
- if (r < 0) {
- DMERR("crypto_shash_final failed: %d", r);
+ r = verity_for_bv_block(v, io, &vector, &offset,
+ verity_bv_hash_update);
+ if (unlikely(r < 0))
return r;
- }
- if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
- DMERR_LIMIT("data block %llu is corrupted",
- (unsigned long long)(io->block + b));
- v->hash_failed = 1;
+
+ r = verity_hash_final(v, desc, verity_io_real_digest(v, io));
+ if (unlikely(r < 0))
+ return r;
+
+ if (likely(memcmp(verity_io_real_digest(v, io),
+ verity_io_want_digest(v, io), v->digest_size) == 0))
+ continue;
+ else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
+ io->block + b, NULL, start_vector, start_offset) == 0)
+ continue;
+ else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
+ io->block + b))
return -EIO;
- }
}
BUG_ON(vector != io->io_vec_size);
BUG_ON(offset);
@@ -403,6 +483,8 @@
if (io->io_vec != io->io_vec_inline)
mempool_free(io->io_vec, v->vec_mempool);
+ verity_fec_finish_io(io, error);
+
bio_endio(bio, error);
}
@@ -417,7 +499,7 @@
{
struct dm_verity_io *io = bio->bi_private;
- if (error) {
+ if (error && !verity_fec_is_enabled(io->v)) {
verity_finish_io(io, error);
return;
}
@@ -451,7 +533,7 @@
goto no_prefetch_cluster;
if (unlikely(cluster & (cluster - 1)))
- cluster = 1 << (fls(cluster) - 1);
+ cluster = 1 << __fls(cluster);
hash_block_start &= ~(sector_t)(cluster - 1);
hash_block_end |= cluster - 1;
@@ -487,7 +569,7 @@
* Bio map function. It allocates dm_verity_io structure and bio vector and
* fills them. Then it issues prefetches and the I/O.
*/
-static int verity_map(struct dm_target *ti, struct bio *bio)
+int verity_map(struct dm_target *ti, struct bio *bio)
{
struct dm_verity *v = ti->private;
struct dm_verity_io *io;
@@ -527,6 +609,8 @@
memcpy(io->io_vec, bio_iovec(bio),
io->io_vec_size * sizeof(struct bio_vec));
+ verity_fec_init_io(io);
+
verity_submit_prefetch(v, io);
generic_make_request(bio);
@@ -537,10 +621,11 @@
/*
* Status: V (valid) or C (corruption found)
*/
-static void verity_status(struct dm_target *ti, status_type_t type,
+void verity_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct dm_verity *v = ti->private;
+ unsigned args = 0;
unsigned sz = 0;
unsigned x;
@@ -567,11 +652,36 @@
else
for (x = 0; x < v->salt_size; x++)
DMEMIT("%02x", v->salt[x]);
+ if (v->mode != DM_VERITY_MODE_EIO)
+ args++;
+ if (verity_fec_is_enabled(v))
+ args += DM_VERITY_OPTS_FEC;
+ if (v->zero_digest)
+ args++;
+ if (!args)
+ return;
+ DMEMIT(" %u", args);
+ if (v->mode != DM_VERITY_MODE_EIO) {
+ DMEMIT(" ");
+ switch (v->mode) {
+ case DM_VERITY_MODE_LOGGING:
+ DMEMIT(DM_VERITY_OPT_LOGGING);
+ break;
+ case DM_VERITY_MODE_RESTART:
+ DMEMIT(DM_VERITY_OPT_RESTART);
+ break;
+ default:
+ BUG();
+ }
+ }
+ if (v->zero_digest)
+ DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
+ sz = verity_fec_status_table(v, sz, result, maxlen);
break;
}
}
-static int verity_ioctl(struct dm_target *ti, unsigned cmd,
+int verity_ioctl(struct dm_target *ti, unsigned cmd,
unsigned long arg)
{
struct dm_verity *v = ti->private;
@@ -585,7 +695,7 @@
cmd, arg);
}
-static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
struct bio_vec *biovec, int max_size)
{
struct dm_verity *v = ti->private;
@@ -600,7 +710,7 @@
return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
}
-static int verity_iterate_devices(struct dm_target *ti,
+int verity_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct dm_verity *v = ti->private;
@@ -608,7 +718,7 @@
return fn(ti, v->data_dev, v->data_start, ti->len, data);
}
-static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
+void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct dm_verity *v = ti->private;
@@ -621,7 +731,7 @@
blk_limits_io_min(limits, limits->logical_block_size);
}
-static void verity_dtr(struct dm_target *ti)
+void verity_dtr(struct dm_target *ti)
{
struct dm_verity *v = ti->private;
@@ -636,6 +746,7 @@
kfree(v->salt);
kfree(v->root_digest);
+ kfree(v->zero_digest);
if (v->tfm)
crypto_free_shash(v->tfm);
@@ -648,9 +759,94 @@
if (v->data_dev)
dm_put_device(ti, v->data_dev);
+ verity_fec_dtr(v);
+
kfree(v);
}
+static int verity_alloc_zero_digest(struct dm_verity *v)
+{
+ int r = -ENOMEM;
+ struct shash_desc *desc;
+ u8 *zero_data;
+
+ v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);
+
+ if (!v->zero_digest)
+ return r;
+
+ desc = kmalloc(v->shash_descsize, GFP_KERNEL);
+
+ if (!desc)
+ return r; /* verity_dtr will free zero_digest */
+
+ zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL);
+
+ if (!zero_data)
+ goto out;
+
+ r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits,
+ v->zero_digest);
+
+out:
+ kfree(desc);
+ kfree(zero_data);
+
+ return r;
+}
+
+static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
+{
+ int r;
+ unsigned argc;
+ struct dm_target *ti = v->ti;
+ const char *arg_name;
+
+ static struct dm_arg _args[] = {
+ {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"},
+ };
+
+ r = dm_read_arg_group(_args, as, &argc, &ti->error);
+ if (r)
+ return -EINVAL;
+
+ if (!argc)
+ return 0;
+
+ do {
+ arg_name = dm_shift_arg(as);
+ argc--;
+
+ if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) {
+ v->mode = DM_VERITY_MODE_LOGGING;
+ continue;
+
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) {
+ v->mode = DM_VERITY_MODE_RESTART;
+ continue;
+
+ } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) {
+ r = verity_alloc_zero_digest(v);
+ if (r) {
+ ti->error = "Cannot allocate zero digest";
+ return r;
+ }
+ continue;
+
+ } else if (verity_is_fec_opt_arg(arg_name)) {
+ r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
+ if (r)
+ return r;
+ continue;
+ }
+
+ ti->error = "Unrecognized verity feature request";
+ return -EINVAL;
+ } while (argc && !r);
+
+ return r;
+}
+
/*
* Target parameters:
* <version> The current format is version 1.
@@ -665,10 +861,11 @@
* <digest>
* <salt> Hex string or "-" if no salt.
*/
-static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
+int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
struct dm_verity *v;
- unsigned num;
+ struct dm_arg_set as;
+ unsigned int num;
unsigned long long num_ll;
int r;
int i;
@@ -683,20 +880,24 @@
ti->private = v;
v->ti = ti;
+ r = verity_fec_ctr_alloc(v);
+ if (r)
+ goto bad;
+
if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) {
ti->error = "Device must be readonly";
r = -EINVAL;
goto bad;
}
- if (argc != 10) {
- ti->error = "Invalid argument count: exactly 10 arguments required";
+ if (argc < 10) {
+ ti->error = "Not enough arguments";
r = -EINVAL;
goto bad;
}
- if (sscanf(argv[0], "%d%c", &num, &dummy) != 1 ||
- num < 0 || num > 1) {
+ if (sscanf(argv[0], "%u%c", &num, &dummy) != 1 ||
+ num > 1) {
ti->error = "Invalid version";
r = -EINVAL;
goto bad;
@@ -723,7 +924,7 @@
r = -EINVAL;
goto bad;
}
- v->data_dev_block_bits = ffs(num) - 1;
+ v->data_dev_block_bits = __ffs(num);
if (sscanf(argv[4], "%u%c", &num, &dummy) != 1 ||
!num || (num & (num - 1)) ||
@@ -733,7 +934,7 @@
r = -EINVAL;
goto bad;
}
- v->hash_dev_block_bits = ffs(num) - 1;
+ v->hash_dev_block_bits = __ffs(num);
if (sscanf(argv[5], "%llu%c", &num_ll, &dummy) != 1 ||
(sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT))
@@ -811,8 +1012,21 @@
}
}
+ argv += 10;
+ argc -= 10;
+
+ /* Optional parameters */
+ if (argc) {
+ as.argc = argc;
+ as.argv = argv;
+
+ r = verity_parse_opt_args(&as, v);
+ if (r < 0)
+ goto bad;
+ }
+
v->hash_per_block_bits =
- fls((1 << v->hash_dev_block_bits) / v->digest_size) - 1;
+ __fls((1 << v->hash_dev_block_bits) / v->digest_size);
v->levels = 0;
if (v->data_blocks)
@@ -858,8 +1072,6 @@
goto bad;
}
- ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io));
-
v->vec_mempool = mempool_create_kmalloc_pool(DM_VERITY_MEMPOOL_SIZE,
BIO_MAX_PAGES * sizeof(struct bio_vec));
if (!v->vec_mempool) {
@@ -869,13 +1081,25 @@
}
/* WQ_UNBOUND greatly improves performance when running on ramdisk */
- v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus());
+ v->verify_wq = alloc_workqueue("kverityd",
+ WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND,
+ num_online_cpus());
if (!v->verify_wq) {
ti->error = "Cannot allocate workqueue";
r = -ENOMEM;
goto bad;
}
+ ti->per_bio_data_size = sizeof(struct dm_verity_io) +
+ v->shash_descsize + v->digest_size * 2;
+
+ r = verity_fec_ctr(v);
+ if (r)
+ goto bad;
+
+ ti->per_bio_data_size = roundup(ti->per_bio_data_size,
+ __alignof__(struct dm_verity_io));
+
return 0;
bad:
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
new file mode 100644
index 0000000..ea14a90
--- /dev/null
+++ b/drivers/md/dm-verity.h
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef DM_VERITY_H
+#define DM_VERITY_H
+
+#include "dm-bufio.h"
+#include <linux/device-mapper.h>
+#include <crypto/hash.h>
+
+#define DM_VERITY_IO_VEC_INLINE 16
+#define DM_VERITY_MAX_LEVELS 63
+
+
+enum verity_mode {
+ DM_VERITY_MODE_EIO,
+ DM_VERITY_MODE_LOGGING,
+ DM_VERITY_MODE_RESTART
+};
+
+enum verity_block_type {
+ DM_VERITY_BLOCK_TYPE_DATA,
+ DM_VERITY_BLOCK_TYPE_METADATA
+};
+
+struct dm_verity {
+ struct dm_dev *data_dev;
+ struct dm_dev *hash_dev;
+ struct dm_target *ti;
+ struct dm_bufio_client *bufio;
+ char *alg_name;
+ struct crypto_shash *tfm;
+ u8 *root_digest; /* digest of the root block */
+ u8 *salt; /* salt: its size is salt_size */
+ u8 *zero_digest; /* digest for a zero block */
+ unsigned salt_size;
+ sector_t data_start; /* data offset in 512-byte sectors */
+ sector_t hash_start; /* hash start in blocks */
+ sector_t data_blocks; /* the number of data blocks */
+ sector_t hash_blocks; /* the number of hash blocks */
+ unsigned char data_dev_block_bits; /* log2(data blocksize) */
+ unsigned char hash_dev_block_bits; /* log2(hash blocksize) */
+ unsigned char hash_per_block_bits; /* log2(hashes in hash block) */
+ unsigned char levels; /* the number of tree levels */
+ unsigned char version;
+ unsigned digest_size; /* digest size for the current hash algorithm */
+ unsigned shash_descsize;/* the size of temporary space for crypto */
+ int hash_failed; /* set to 1 if hash of any block failed */
+ enum verity_mode mode; /* mode for handling verification errors */
+ unsigned corrupted_errs;/* Number of errors for corrupted blocks */
+
+ mempool_t *vec_mempool; /* mempool of bio vector */
+
+ struct workqueue_struct *verify_wq;
+
+ /* starting blocks for each tree level. 0 is the lowest level. */
+ sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
+
+ struct dm_verity_fec *fec; /* forward error correction */
+};
+
+struct dm_verity_io {
+ struct dm_verity *v;
+
+ /* original values of bio->bi_end_io and bio->bi_private */
+ bio_end_io_t *orig_bi_end_io;
+ void *orig_bi_private;
+
+ sector_t block;
+ unsigned n_blocks;
+
+ /* saved bio vector */
+ struct bio_vec *io_vec;
+ unsigned io_vec_size;
+
+ struct work_struct work;
+
+ /* A space for short vectors; longer vectors are allocated separately. */
+ struct bio_vec io_vec_inline[DM_VERITY_IO_VEC_INLINE];
+
+ /*
+ * Three variably-size fields follow this struct:
+ *
+ * u8 hash_desc[v->shash_descsize];
+ * u8 real_digest[v->digest_size];
+ * u8 want_digest[v->digest_size];
+ *
+ * To access them use: verity_io_hash_desc(), verity_io_real_digest()
+ * and verity_io_want_digest().
+ */
+};
+
+static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v,
+ struct dm_verity_io *io)
+{
+ return (struct shash_desc *)(io + 1);
+}
+
+static inline u8 *verity_io_real_digest(struct dm_verity *v,
+ struct dm_verity_io *io)
+{
+ return (u8 *)(io + 1) + v->shash_descsize;
+}
+
+static inline u8 *verity_io_want_digest(struct dm_verity *v,
+ struct dm_verity_io *io)
+{
+ return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
+}
+
+static inline u8 *verity_io_digest_end(struct dm_verity *v,
+ struct dm_verity_io *io)
+{
+ return verity_io_want_digest(v, io) + v->digest_size;
+}
+
+extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
+ unsigned *vector, unsigned *offset,
+ int (*process)(struct dm_verity *v,
+ struct dm_verity_io *io,
+ u8 *data, size_t len));
+
+extern int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+ const u8 *data, size_t len, u8 *digest);
+
+extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
+ sector_t block, u8 *digest, bool *is_zero);
+
+extern void verity_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen);
+extern int verity_ioctl(struct dm_target *ti, unsigned cmd,
+ unsigned long arg);
+extern int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+ struct bio_vec *biovec, int max_size);
+extern int verity_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data);
+extern void verity_io_hints(struct dm_target *ti, struct queue_limits *limits);
+extern void verity_dtr(struct dm_target *ti);
+extern int verity_ctr(struct dm_target *ti, unsigned argc, char **argv);
+extern int verity_map(struct dm_target *ti, struct bio *bio);
+#endif /* DM_VERITY_H */
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 7a68184..f35f656 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -424,6 +424,10 @@
This driver can also be built as a module. If so, the module
will be called ti_dac7512.
+config UID_STAT
+ bool "UID based statistics tracking exported to /proc/uid_stat"
+ default n
+
config VMWARE_BALLOON
tristate "VMware Balloon Driver"
depends on X86 && HYPERVISOR_GUEST
@@ -527,6 +531,12 @@
the genalloc API. It is supposed to be used for small on-chip SRAM
areas found on many SoCs.
+config UID_CPUTIME
+ tristate "Per-UID cpu time statistics"
+ depends on PROFILING
+ help
+ Per UID based cpu time statistics exported to /proc/uid_cputime
+
source "drivers/misc/c2port/Kconfig"
source "drivers/misc/eeprom/Kconfig"
source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index c235d5b..89435c9 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -36,6 +36,7 @@
obj-$(CONFIG_EP93XX_PWM) += ep93xx_pwm.o
obj-$(CONFIG_DS1682) += ds1682.o
obj-$(CONFIG_TI_DAC7512) += ti_dac7512.o
+obj-$(CONFIG_UID_STAT) += uid_stat.o
obj-$(CONFIG_C2PORT) += c2port/
obj-$(CONFIG_HMC6352) += hmc6352.o
obj-y += eeprom/
@@ -53,3 +54,4 @@
obj-$(CONFIG_VMWARE_VMCI) += vmw_vmci/
obj-$(CONFIG_LATTICE_ECP3_CONFIG) += lattice-ecp3-config.o
obj-$(CONFIG_SRAM) += sram.o
+obj-$(CONFIG_UID_CPUTIME) += uid_cputime.o
diff --git a/drivers/misc/uid_cputime.c b/drivers/misc/uid_cputime.c
new file mode 100644
index 0000000..c751188
--- /dev/null
+++ b/drivers/misc/uid_cputime.c
@@ -0,0 +1,254 @@
+/* drivers/misc/uid_cputime.c
+ *
+ * Copyright (C) 2014 - 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#define UID_HASH_BITS 10
+DECLARE_HASHTABLE(hash_table, UID_HASH_BITS);
+
+static DEFINE_MUTEX(uid_lock);
+static struct proc_dir_entry *parent;
+
+struct uid_entry {
+ uid_t uid;
+ cputime_t utime;
+ cputime_t stime;
+ cputime_t active_utime;
+ cputime_t active_stime;
+ unsigned long long active_power;
+ unsigned long long power;
+ struct hlist_node hash;
+};
+
+static struct uid_entry *find_uid_entry(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+ hash_for_each_possible(hash_table, uid_entry, hash, uid) {
+ if (uid_entry->uid == uid)
+ return uid_entry;
+ }
+ return NULL;
+}
+
+static struct uid_entry *find_or_register_uid(uid_t uid)
+{
+ struct uid_entry *uid_entry;
+
+ uid_entry = find_uid_entry(uid);
+ if (uid_entry)
+ return uid_entry;
+
+ uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC);
+ if (!uid_entry)
+ return NULL;
+
+ uid_entry->uid = uid;
+
+ hash_add(hash_table, &uid_entry->hash, uid);
+
+ return uid_entry;
+}
+
+static int uid_stat_show(struct seq_file *m, void *v)
+{
+ struct uid_entry *uid_entry;
+ struct task_struct *task, *temp;
+ cputime_t utime;
+ cputime_t stime;
+ unsigned long bkt;
+
+ mutex_lock(&uid_lock);
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ uid_entry->active_stime = 0;
+ uid_entry->active_utime = 0;
+ uid_entry->active_power = 0;
+ }
+
+ read_lock(&tasklist_lock);
+ do_each_thread(temp, task) {
+ uid_entry = find_or_register_uid(from_kuid_munged(
+ current_user_ns(), task_uid(task)));
+ if (!uid_entry) {
+ read_unlock(&tasklist_lock);
+ mutex_unlock(&uid_lock);
+ pr_err("%s: failed to find the uid_entry for uid %d\n",
+ __func__, from_kuid_munged(current_user_ns(),
+ task_uid(task)));
+ return -ENOMEM;
+ }
+ /* if this task is exiting, we have already accounted for the
+ * time and power.
+ */
+ if (task->cpu_power == ULLONG_MAX)
+ continue;
+ task_cputime_adjusted(task, &utime, &stime);
+ uid_entry->active_utime += utime;
+ uid_entry->active_stime += stime;
+ uid_entry->active_power += task->cpu_power;
+ } while_each_thread(temp, task);
+ read_unlock(&tasklist_lock);
+
+ hash_for_each(hash_table, bkt, uid_entry, hash) {
+ cputime_t total_utime = uid_entry->utime +
+ uid_entry->active_utime;
+ cputime_t total_stime = uid_entry->stime +
+ uid_entry->active_stime;
+ unsigned long long total_power = uid_entry->power +
+ uid_entry->active_power;
+ seq_printf(m, "%d: %llu %llu %llu\n", uid_entry->uid,
+ (unsigned long long)jiffies_to_msecs(
+ cputime_to_jiffies(total_utime)) * USEC_PER_MSEC,
+ (unsigned long long)jiffies_to_msecs(
+ cputime_to_jiffies(total_stime)) * USEC_PER_MSEC,
+ total_power);
+ }
+
+ mutex_unlock(&uid_lock);
+ return 0;
+}
+
+static int uid_stat_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, uid_stat_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_stat_fops = {
+ .open = uid_stat_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int uid_remove_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, NULL, NULL);
+}
+
+static ssize_t uid_remove_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos)
+{
+ struct uid_entry *uid_entry;
+ struct hlist_node *tmp;
+ char uids[128];
+ char *start_uid, *end_uid = NULL;
+ long int uid_start = 0, uid_end = 0;
+
+ if (count >= sizeof(uids))
+ count = sizeof(uids) - 1;
+
+ if (copy_from_user(uids, buffer, count))
+ return -EFAULT;
+
+ uids[count] = '\0';
+ end_uid = uids;
+ start_uid = strsep(&end_uid, "-");
+
+ if (!start_uid || !end_uid)
+ return -EINVAL;
+
+ if (kstrtol(start_uid, 10, &uid_start) != 0 ||
+ kstrtol(end_uid, 10, &uid_end) != 0) {
+ return -EINVAL;
+ }
+ mutex_lock(&uid_lock);
+
+ for (; uid_start <= uid_end; uid_start++) {
+ hash_for_each_possible_safe(hash_table, uid_entry, tmp,
+ hash, (uid_t)uid_start) {
+ if (uid_start == uid_entry->uid) {
+ hash_del(&uid_entry->hash);
+ kfree(uid_entry);
+ }
+ }
+ }
+
+ mutex_unlock(&uid_lock);
+ return count;
+}
+
+static const struct file_operations uid_remove_fops = {
+ .open = uid_remove_open,
+ .release = single_release,
+ .write = uid_remove_write,
+};
+
+static int process_notifier(struct notifier_block *self,
+ unsigned long cmd, void *v)
+{
+ struct task_struct *task = v;
+ struct uid_entry *uid_entry;
+ cputime_t utime, stime;
+ uid_t uid;
+
+ if (!task)
+ return NOTIFY_OK;
+
+ mutex_lock(&uid_lock);
+ uid = from_kuid_munged(current_user_ns(), task_uid(task));
+ uid_entry = find_or_register_uid(uid);
+ if (!uid_entry) {
+ pr_err("%s: failed to find uid %d\n", __func__, uid);
+ goto exit;
+ }
+
+ task_cputime_adjusted(task, &utime, &stime);
+ uid_entry->utime += utime;
+ uid_entry->stime += stime;
+ uid_entry->power += task->cpu_power;
+ task->cpu_power = ULLONG_MAX;
+
+exit:
+ mutex_unlock(&uid_lock);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block process_notifier_block = {
+ .notifier_call = process_notifier,
+};
+
+static int __init proc_uid_cputime_init(void)
+{
+ hash_init(hash_table);
+
+ parent = proc_mkdir("uid_cputime", NULL);
+ if (!parent) {
+ pr_err("%s: failed to create proc entry\n", __func__);
+ return -ENOMEM;
+ }
+
+ proc_create_data("remove_uid_range", S_IWUGO, parent, &uid_remove_fops,
+ NULL);
+
+ proc_create_data("show_uid_stat", S_IRUGO, parent, &uid_stat_fops,
+ NULL);
+
+ profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block);
+
+ return 0;
+}
+
+early_initcall(proc_uid_cputime_init);
diff --git a/drivers/misc/uid_stat.c b/drivers/misc/uid_stat.c
new file mode 100644
index 0000000..4766c1f
--- /dev/null
+++ b/drivers/misc/uid_stat.c
@@ -0,0 +1,152 @@
+/* drivers/misc/uid_stat.c
+ *
+ * Copyright (C) 2008 - 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <asm/atomic.h>
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/uid_stat.h>
+#include <net/activity_stats.h>
+
+static DEFINE_SPINLOCK(uid_lock);
+static LIST_HEAD(uid_list);
+static struct proc_dir_entry *parent;
+
+struct uid_stat {
+ struct list_head link;
+ uid_t uid;
+ atomic_t tcp_rcv;
+ atomic_t tcp_snd;
+};
+
+static struct uid_stat *find_uid_stat(uid_t uid) {
+ struct uid_stat *entry;
+
+ list_for_each_entry(entry, &uid_list, link) {
+ if (entry->uid == uid) {
+ return entry;
+ }
+ }
+ return NULL;
+}
+
+static int uid_stat_atomic_int_show(struct seq_file *m, void *v)
+{
+ unsigned int bytes;
+ atomic_t *counter = m->private;
+
+ bytes = (unsigned int) (atomic_read(counter) + INT_MIN);
+ return seq_printf(m, "%u\n", bytes);
+}
+
+static int uid_stat_read_atomic_int_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, uid_stat_atomic_int_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_stat_read_atomic_int_fops = {
+ .open = uid_stat_read_atomic_int_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+/* Create a new entry for tracking the specified uid. */
+static struct uid_stat *create_stat(uid_t uid) {
+ struct uid_stat *new_uid;
+ /* Create the uid stat struct and append it to the list. */
+ new_uid = kmalloc(sizeof(struct uid_stat), GFP_ATOMIC);
+ if (!new_uid)
+ return NULL;
+
+ new_uid->uid = uid;
+ /* Counters start at INT_MIN, so we can track 4GB of network traffic. */
+ atomic_set(&new_uid->tcp_rcv, INT_MIN);
+ atomic_set(&new_uid->tcp_snd, INT_MIN);
+
+ list_add_tail(&new_uid->link, &uid_list);
+ return new_uid;
+}
+
+static void create_stat_proc(struct uid_stat *new_uid)
+{
+ char uid_s[32];
+ struct proc_dir_entry *entry;
+ sprintf(uid_s, "%d", new_uid->uid);
+ entry = proc_mkdir(uid_s, parent);
+
+ /* Keep reference to uid_stat so we know what uid to read stats from. */
+ proc_create_data("tcp_snd", S_IRUGO, entry,
+ &uid_stat_read_atomic_int_fops, &new_uid->tcp_snd);
+
+ proc_create_data("tcp_rcv", S_IRUGO, entry,
+ &uid_stat_read_atomic_int_fops, &new_uid->tcp_rcv);
+}
+
+static struct uid_stat *find_or_create_uid_stat(uid_t uid)
+{
+ struct uid_stat *entry;
+ unsigned long flags;
+ spin_lock_irqsave(&uid_lock, flags);
+ entry = find_uid_stat(uid);
+ if (entry) {
+ spin_unlock_irqrestore(&uid_lock, flags);
+ return entry;
+ }
+ entry = create_stat(uid);
+ spin_unlock_irqrestore(&uid_lock, flags);
+ if (entry)
+ create_stat_proc(entry);
+ return entry;
+}
+
+int uid_stat_tcp_snd(uid_t uid, int size) {
+ struct uid_stat *entry;
+ activity_stats_update();
+ entry = find_or_create_uid_stat(uid);
+ if (!entry)
+ return -1;
+ atomic_add(size, &entry->tcp_snd);
+ return 0;
+}
+
+int uid_stat_tcp_rcv(uid_t uid, int size) {
+ struct uid_stat *entry;
+ activity_stats_update();
+ entry = find_or_create_uid_stat(uid);
+ if (!entry)
+ return -1;
+ atomic_add(size, &entry->tcp_rcv);
+ return 0;
+}
+
+static int __init uid_stat_init(void)
+{
+ parent = proc_mkdir("uid_stat", NULL);
+ if (!parent) {
+ pr_err("uid_stat: failed to create proc entry\n");
+ return -1;
+ }
+ return 0;
+}
+
+__initcall(uid_stat_init);
diff --git a/drivers/mmc/card/Kconfig b/drivers/mmc/card/Kconfig
index 5562308..ae6c60b 100644
--- a/drivers/mmc/card/Kconfig
+++ b/drivers/mmc/card/Kconfig
@@ -50,6 +50,15 @@
If unsure, say Y here.
+config MMC_BLOCK_DEFERRED_RESUME
+ bool "Deferr MMC layer resume until I/O is requested"
+ depends on MMC_BLOCK
+ default n
+ help
+ Say Y here to enable deferred MMC resume until I/O
+ is requested. This will reduce overall resume latency and
+ save power when theres an SD card inserted but not being used.
+
config SDIO_UART
tristate "SDIO UART/GPS class support"
depends on TTY
@@ -68,3 +77,15 @@
This driver is only of interest to those developing or
testing a host driver. Most people should say N here.
+
+config MMC_SIMULATE_MAX_SPEED
+ bool "Turn on maximum speed control per block device"
+ depends on MMC_BLOCK
+ help
+ Say Y here to enable MMC device speed limiting. Used to test and
+ simulate the behavior of the system when confronted with a slow MMC.
+
+ Enables max_read_speed, max_write_speed and cache_size attributes to
+ control the write or read maximum KB/second speed behaviors.
+
+ If unsure, say N here.
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index a2863b7..cd5cf25 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -35,6 +35,9 @@
#include <linux/capability.h>
#include <linux/compat.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/mmc.h>
+
#include <linux/mmc/ioctl.h>
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
@@ -162,11 +165,7 @@
static inline int mmc_get_devidx(struct gendisk *disk)
{
- int devmaj = MAJOR(disk_devt(disk));
- int devidx = MINOR(disk_devt(disk)) / perdev_minors;
-
- if (!devmaj)
- devidx = disk->first_minor / perdev_minors;
+ int devidx = disk->first_minor / perdev_minors;
return devidx;
}
@@ -284,6 +283,250 @@
return ret;
}
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+
+static int max_read_speed, max_write_speed, cache_size = 4;
+
+module_param(max_read_speed, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(max_read_speed, "maximum KB/s read speed 0=off");
+module_param(max_write_speed, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(max_write_speed, "maximum KB/s write speed 0=off");
+module_param(cache_size, int, S_IRUSR | S_IRGRP);
+MODULE_PARM_DESC(cache_size, "MB high speed memory or SLC cache");
+
+/*
+ * helper macros and expectations:
+ * size - unsigned long number of bytes
+ * jiffies - unsigned long HZ timestamp difference
+ * speed - unsigned KB/s transfer rate
+ */
+#define size_and_speed_to_jiffies(size, speed) \
+ ((size) * HZ / (speed) / 1024UL)
+#define jiffies_and_speed_to_size(jiffies, speed) \
+ (((speed) * (jiffies) * 1024UL) / HZ)
+#define jiffies_and_size_to_speed(jiffies, size) \
+ ((size) * HZ / (jiffies) / 1024UL)
+
+/* Limits to report warning */
+/* jiffies_and_size_to_speed(10*HZ, queue_max_hw_sectors(q) * 512UL) ~ 25 */
+#define MIN_SPEED(q) 250 /* 10 times faster than a floppy disk */
+#define MAX_SPEED(q) jiffies_and_size_to_speed(1, queue_max_sectors(q) * 512UL)
+
+#define speed_valid(speed) ((speed) > 0)
+
+static const char off[] = "off\n";
+
+static int max_speed_show(int speed, char *buf)
+{
+ if (speed)
+ return scnprintf(buf, PAGE_SIZE, "%uKB/s\n", speed);
+ else
+ return scnprintf(buf, PAGE_SIZE, off);
+}
+
+static int max_speed_store(const char *buf, struct request_queue *q)
+{
+ unsigned int limit, set = 0;
+
+ if (!strncasecmp(off, buf, sizeof(off) - 2))
+ return set;
+ if (kstrtouint(buf, 0, &set) || (set > INT_MAX))
+ return -EINVAL;
+ if (set == 0)
+ return set;
+ limit = MAX_SPEED(q);
+ if (set > limit)
+ pr_warn("max speed %u ineffective above %u\n", set, limit);
+ limit = MIN_SPEED(q);
+ if (set < limit)
+ pr_warn("max speed %u painful below %u\n", set, limit);
+ return set;
+}
+
+static ssize_t max_write_speed_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int ret = max_speed_show(atomic_read(&md->queue.max_write_speed), buf);
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t max_write_speed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int set = max_speed_store(buf, md->queue.queue);
+
+ if (set < 0) {
+ mmc_blk_put(md);
+ return set;
+ }
+
+ atomic_set(&md->queue.max_write_speed, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(max_write_speed, S_IRUGO | S_IWUSR,
+ max_write_speed_show, max_write_speed_store);
+
+static ssize_t max_read_speed_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int ret = max_speed_show(atomic_read(&md->queue.max_read_speed), buf);
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t max_read_speed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ int set = max_speed_store(buf, md->queue.queue);
+
+ if (set < 0) {
+ mmc_blk_put(md);
+ return set;
+ }
+
+ atomic_set(&md->queue.max_read_speed, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(max_read_speed, S_IRUGO | S_IWUSR,
+ max_read_speed_show, max_read_speed_store);
+
+static ssize_t cache_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
+ struct mmc_queue *mq = &md->queue;
+ int cache_size = atomic_read(&mq->cache_size);
+ int ret;
+
+ if (!cache_size)
+ ret = scnprintf(buf, PAGE_SIZE, off);
+ else {
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (!speed_valid(speed))
+ ret = scnprintf(buf, PAGE_SIZE, "%uMB\n", cache_size);
+ else { /* We accept race between cache_jiffies and cache_used */
+ unsigned long size = jiffies_and_speed_to_size(
+ jiffies - mq->cache_jiffies, speed);
+ long used = atomic_long_read(&mq->cache_used);
+
+ if (size >= used)
+ size = 0;
+ else
+ size = (used - size) * 100 / cache_size
+ / 1024UL / 1024UL;
+
+ ret = scnprintf(buf, PAGE_SIZE, "%uMB %lu%% used\n",
+ cache_size, size);
+ }
+ }
+
+ mmc_blk_put(md);
+ return ret;
+}
+
+static ssize_t cache_size_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_blk_data *md;
+ unsigned int set = 0;
+
+ if (strncasecmp(off, buf, sizeof(off) - 2)
+ && (kstrtouint(buf, 0, &set) || (set > INT_MAX)))
+ return -EINVAL;
+
+ md = mmc_blk_get(dev_to_disk(dev));
+ atomic_set(&md->queue.cache_size, set);
+ mmc_blk_put(md);
+ return count;
+}
+
+static const DEVICE_ATTR(cache_size, S_IRUGO | S_IWUSR,
+ cache_size_show, cache_size_store);
+
+/* correct for write-back */
+static long mmc_blk_cache_used(struct mmc_queue *mq, unsigned long waitfor)
+{
+ long used = 0;
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (speed_valid(speed)) {
+ unsigned long size = jiffies_and_speed_to_size(
+ waitfor - mq->cache_jiffies, speed);
+ used = atomic_long_read(&mq->cache_used);
+
+ if (size >= used)
+ used = 0;
+ else
+ used -= size;
+ }
+
+ atomic_long_set(&mq->cache_used, used);
+ mq->cache_jiffies = waitfor;
+
+ return used;
+}
+
+static void mmc_blk_simulate_delay(
+ struct mmc_queue *mq,
+ struct request *req,
+ unsigned long waitfor)
+{
+ int max_speed;
+
+ if (!req)
+ return;
+
+ max_speed = (rq_data_dir(req) == READ)
+ ? atomic_read(&mq->max_read_speed)
+ : atomic_read(&mq->max_write_speed);
+ if (speed_valid(max_speed)) {
+ unsigned long bytes = blk_rq_bytes(req);
+
+ if (rq_data_dir(req) != READ) {
+ int cache_size = atomic_read(&mq->cache_size);
+
+ if (cache_size) {
+ unsigned long size = cache_size * 1024L * 1024L;
+ long used = mmc_blk_cache_used(mq, waitfor);
+
+ used += bytes;
+ atomic_long_set(&mq->cache_used, used);
+ bytes = 0;
+ if (used > size)
+ bytes = used - size;
+ }
+ }
+ waitfor += size_and_speed_to_jiffies(bytes, max_speed);
+ if (time_is_after_jiffies(waitfor)) {
+ long msecs = jiffies_to_msecs(waitfor - jiffies);
+
+ if (likely(msecs > 0))
+ msleep(msecs);
+ }
+ }
+}
+
+#else
+
+#define mmc_blk_simulate_delay(mq, req, waitfor)
+
+#endif
+
static int mmc_blk_open(struct block_device *bdev, fmode_t mode)
{
struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk);
@@ -729,18 +972,22 @@
req->rq_disk->disk_name, "timed out", name, status);
/* If the status cmd initially failed, retry the r/w cmd */
- if (!status_valid)
+ if (!status_valid) {
+ pr_err("%s: status not valid, retrying timeout\n", req->rq_disk->disk_name);
return ERR_RETRY;
-
+ }
/*
* If it was a r/w cmd crc error, or illegal command
* (eg, issued in wrong state) then retry - we should
* have corrected the state problem above.
*/
- if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND))
+ if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND)) {
+ pr_err("%s: command error, retrying timeout\n", req->rq_disk->disk_name);
return ERR_RETRY;
+ }
/* Otherwise abort the command */
+ pr_err("%s: not retrying timeout\n", req->rq_disk->disk_name);
return ERR_ABORT;
default:
@@ -1032,9 +1279,12 @@
goto out;
}
- if (mmc_can_sanitize(card))
+ if (mmc_can_sanitize(card)) {
+ trace_mmc_blk_erase_start(EXT_CSD_SANITIZE_START, 0, 0);
err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
EXT_CSD_SANITIZE_START, 1, 0);
+ trace_mmc_blk_erase_end(EXT_CSD_SANITIZE_START, 0, 0);
+ }
out_retry:
if (err && !mmc_blk_reset(md, card->host, type))
goto retry;
@@ -1056,6 +1306,23 @@
if (ret)
ret = -EIO;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ else if (atomic_read(&mq->cache_size)) {
+ long used = mmc_blk_cache_used(mq, jiffies);
+
+ if (used) {
+ int speed = atomic_read(&mq->max_write_speed);
+
+ if (speed_valid(speed)) {
+ unsigned long msecs = jiffies_to_msecs(
+ size_and_speed_to_jiffies(
+ used, speed));
+ if (msecs)
+ msleep(msecs);
+ }
+ }
+ }
+#endif
blk_end_request_all(req, ret);
return ret ? 0 : 1;
@@ -1757,6 +2024,9 @@
struct mmc_async_req *areq;
const u8 packed_nr = 2;
u8 reqs = 0;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ unsigned long waitfor = jiffies;
+#endif
if (!rqc && !mq->mqrq_prev->req)
return 0;
@@ -1807,6 +2077,8 @@
*/
mmc_blk_reset_success(md, type);
+ mmc_blk_simulate_delay(mq, rqc, waitfor);
+
if (mmc_packed_cmd(mq_rq->cmd_type)) {
ret = mmc_blk_end_packed_req(mq_rq);
break;
@@ -1944,6 +2216,11 @@
unsigned long flags;
unsigned int cmd_flags = req ? req->cmd_flags : 0;
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+ if (mmc_bus_needs_resume(card->host))
+ mmc_resume_bus(card->host);
+#endif
+
if (req && !mq->mqrq_prev->req)
/* claim host only for the first request */
mmc_claim_host(card->host);
@@ -2066,6 +2343,7 @@
md->disk->queue = md->queue.queue;
md->disk->driverfs_dev = parent;
set_disk_ro(md->disk, md->read_only || default_ro);
+ md->disk->flags = GENHD_FL_EXT_DEVT;
if (area_type & MMC_BLK_DATA_AREA_RPMB)
md->disk->flags |= GENHD_FL_NO_PART_SCAN;
@@ -2216,6 +2494,14 @@
card->ext_csd.boot_ro_lockable)
device_remove_file(disk_to_dev(md->disk),
&md->power_ro_lock);
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_max_write_speed);
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_max_read_speed);
+ device_remove_file(disk_to_dev(md->disk),
+ &dev_attr_cache_size);
+#endif
/* Stop new requests from getting into the queue */
del_gendisk(md->disk);
@@ -2257,6 +2543,24 @@
ret = device_create_file(disk_to_dev(md->disk), &md->force_ro);
if (ret)
goto force_ro_fail;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ atomic_set(&md->queue.max_write_speed, max_write_speed);
+ ret = device_create_file(disk_to_dev(md->disk),
+ &dev_attr_max_write_speed);
+ if (ret)
+ goto max_write_speed_fail;
+ atomic_set(&md->queue.max_read_speed, max_read_speed);
+ ret = device_create_file(disk_to_dev(md->disk),
+ &dev_attr_max_read_speed);
+ if (ret)
+ goto max_read_speed_fail;
+ atomic_set(&md->queue.cache_size, cache_size);
+ atomic_long_set(&md->queue.cache_used, 0);
+ md->queue.cache_jiffies = jiffies;
+ ret = device_create_file(disk_to_dev(md->disk), &dev_attr_cache_size);
+ if (ret)
+ goto cache_size_fail;
+#endif
if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) &&
card->ext_csd.boot_ro_lockable) {
@@ -2281,6 +2585,14 @@
return ret;
power_ro_lock_fail:
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_cache_size);
+cache_size_fail:
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_max_read_speed);
+max_read_speed_fail:
+ device_remove_file(disk_to_dev(md->disk), &dev_attr_max_write_speed);
+max_write_speed_fail:
+#endif
device_remove_file(disk_to_dev(md->disk), &md->force_ro);
force_ro_fail:
del_gendisk(md->disk);
@@ -2381,6 +2693,9 @@
mmc_set_drvdata(card, md);
mmc_fixup_device(card, blk_fixups);
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+ mmc_set_bus_resume_policy(card->host, 1);
+#endif
if (mmc_add_disk(md))
goto out;
@@ -2406,10 +2721,12 @@
mmc_release_host(card->host);
mmc_blk_remove_req(md);
mmc_set_drvdata(card, NULL);
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+ mmc_set_bus_resume_policy(card->host, 0);
+#endif
}
-#ifdef CONFIG_PM
-static int mmc_blk_suspend(struct mmc_card *card)
+static int _mmc_blk_suspend(struct mmc_card *card)
{
struct mmc_blk_data *part_md;
struct mmc_blk_data *md = mmc_get_drvdata(card);
@@ -2423,6 +2740,17 @@
return 0;
}
+static void mmc_blk_shutdown(struct mmc_card *card)
+{
+ _mmc_blk_suspend(card);
+}
+
+#ifdef CONFIG_PM
+static int mmc_blk_suspend(struct mmc_card *card)
+{
+ return _mmc_blk_suspend(card);
+}
+
static int mmc_blk_resume(struct mmc_card *card)
{
struct mmc_blk_data *part_md;
@@ -2454,6 +2782,7 @@
.remove = mmc_blk_remove,
.suspend = mmc_blk_suspend,
.resume = mmc_blk_resume,
+ .shutdown = mmc_blk_shutdown,
};
static int __init mmc_blk_init(void)
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 759714e..a69df52 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -3025,12 +3025,17 @@
mmc_test_free_dbgfs_file(card);
}
+static void mmc_test_shutdown(struct mmc_card *card)
+{
+}
+
static struct mmc_driver mmc_driver = {
.drv = {
.name = "mmc_test",
},
.probe = mmc_test_probe,
.remove = mmc_test_remove,
+ .shutdown = mmc_test_shutdown,
};
static int __init mmc_test_init(void)
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 645519f..6f16e66 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -18,6 +18,7 @@
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
+#include <linux/sched/rt.h>
#include "queue.h"
#define MMC_QUEUE_BOUNCESZ 65536
@@ -50,6 +51,11 @@
struct mmc_queue *mq = d;
struct request_queue *q = mq->queue;
+ struct sched_param scheduler_params = {0};
+ scheduler_params.sched_priority = 1;
+
+ sched_setscheduler(current, SCHED_FIFO, &scheduler_params);
+
current->flags |= PF_MEMALLOC;
down(&mq->thread_sem);
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 99e6521..e417903 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -57,6 +57,14 @@
struct mmc_queue_req mqrq[2];
struct mmc_queue_req *mqrq_cur;
struct mmc_queue_req *mqrq_prev;
+#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED
+ atomic_t max_write_speed;
+ atomic_t max_read_speed;
+ atomic_t cache_size;
+ /* i/o tracking */
+ atomic_long_t cache_used;
+ unsigned long cache_jiffies;
+#endif
};
extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index 269d072..ae10a37 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -26,3 +26,18 @@
support handling this in order for it to be of any use.
If unsure, say N.
+
+config MMC_EMBEDDED_SDIO
+ boolean "MMC embedded SDIO device support (EXPERIMENTAL)"
+ help
+ If you say Y here, support will be added for embedded SDIO
+ devices which do not contain the necessary enumeration
+ support in hardware to be properly detected.
+
+config MMC_PARANOID_SD_INIT
+ bool "Enable paranoid SD card initialization (EXPERIMENTAL)"
+ help
+ If you say Y here, the MMC layer will be extra paranoid
+ about re-trying SD init requests. This can be a useful
+ work-around for buggy controllers and hardware. Enable
+ if you are experiencing issues with SD detection.
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index e219c97..d0b980c 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -122,6 +122,24 @@
return 0;
}
+static void mmc_bus_shutdown(struct device *dev)
+{
+ struct mmc_driver *drv = to_mmc_driver(dev->driver);
+ struct mmc_card *card = mmc_dev_to_card(dev);
+ struct mmc_host *host = card->host;
+ int ret;
+
+ if (dev->driver && drv->shutdown)
+ drv->shutdown(card);
+
+ if (host->bus_ops->shutdown) {
+ ret = host->bus_ops->shutdown(host);
+ if (ret)
+ pr_warn("%s: error %d during shutdown\n",
+ mmc_hostname(host), ret);
+ }
+}
+
#ifdef CONFIG_PM_SLEEP
static int mmc_bus_suspend(struct device *dev)
{
@@ -182,6 +200,7 @@
.uevent = mmc_bus_uevent,
.probe = mmc_bus_probe,
.remove = mmc_bus_remove,
+ .shutdown = mmc_bus_shutdown,
.pm = &mmc_bus_pm_ops,
};
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 3ae6f13..859144b 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -27,12 +27,17 @@
#include <linux/fault-inject.h>
#include <linux/random.h>
#include <linux/slab.h>
+#include <linux/wakelock.h>
+
+#include <trace/events/mmc.h>
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
#include <linux/mmc/mmc.h>
#include <linux/mmc/sd.h>
+#include <linux/math64.h>
+
#include "core.h"
#include "bus.h"
#include "host.h"
@@ -62,6 +67,33 @@
bool use_spi_crc = 1;
module_param(use_spi_crc, bool, 0);
+static inline void
+mmc_update_latency_hist(struct mmc_host *host, int read, u_int64_t delta_us)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++) {
+ if (delta_us < (u_int64_t)latency_x_axis_us[i]) {
+ if (read)
+ host->latency_y_axis_read[i]++;
+ else
+ host->latency_y_axis_write[i]++;
+ break;
+ }
+ }
+ if (i == ARRAY_SIZE(latency_x_axis_us)) {
+ /* Overflowed the histogram */
+ if (read)
+ host->latency_y_axis_read[i]++;
+ else
+ host->latency_y_axis_write[i]++;
+ }
+ if (read)
+ host->latency_reads_elems++;
+ else
+ host->latency_writes_elems++;
+}
+
/*
* We normally treat cards as removed during suspend if they are not
* known to be on a non-removable bus, to avoid the risk of writing
@@ -172,6 +204,18 @@
pr_debug("%s: %d bytes transferred: %d\n",
mmc_hostname(host),
mrq->data->bytes_xfered, mrq->data->error);
+ if (mrq->lat_hist_enabled) {
+ ktime_t completion;
+ u_int64_t delta_us;
+
+ completion = ktime_get();
+ delta_us = ktime_us_delta(completion,
+ mrq->io_start);
+ mmc_update_latency_hist(host,
+ (mrq->data->flags & MMC_DATA_READ),
+ delta_us);
+ }
+ trace_mmc_blk_rw_end(cmd->opcode, cmd->arg, mrq->data);
}
if (mrq->stop) {
@@ -538,8 +582,17 @@
mmc_start_bkops(host->card, true);
}
- if (!err && areq)
+ if (!err && areq) {
+ if (host->latency_hist_enabled) {
+ areq->mrq->io_start = ktime_get();
+ areq->mrq->lat_hist_enabled = 1;
+ } else
+ areq->mrq->lat_hist_enabled = 0;
+ trace_mmc_blk_rw_start(areq->mrq->cmd->opcode,
+ areq->mrq->cmd->arg,
+ areq->mrq->data);
start_err = __mmc_start_data_req(host, areq->mrq);
+ }
if (host->areq)
mmc_post_req(host, host->areq->mrq, 0);
@@ -1593,6 +1646,36 @@
spin_unlock_irqrestore(&host->lock, flags);
}
+int mmc_resume_bus(struct mmc_host *host)
+{
+ unsigned long flags;
+
+ if (!mmc_bus_needs_resume(host))
+ return -EINVAL;
+
+ printk("%s: Starting deferred resume\n", mmc_hostname(host));
+ spin_lock_irqsave(&host->lock, flags);
+ host->bus_resume_flags &= ~MMC_BUSRESUME_NEEDS_RESUME;
+ host->rescan_disable = 0;
+ spin_unlock_irqrestore(&host->lock, flags);
+
+ mmc_bus_get(host);
+ if (host->bus_ops && !host->bus_dead) {
+ mmc_power_up(host);
+ BUG_ON(!host->bus_ops->resume);
+ host->bus_ops->resume(host);
+ }
+
+ if (host->bus_ops->detect && !host->bus_dead)
+ host->bus_ops->detect(host);
+
+ mmc_bus_put(host);
+ printk("%s: Deferred resume completed\n", mmc_hostname(host));
+ return 0;
+}
+
+EXPORT_SYMBOL(mmc_resume_bus);
+
/*
* Assign a mmc bus handler to a host. Only one bus handler may control a
* host at any given time.
@@ -1658,6 +1741,8 @@
spin_unlock_irqrestore(&host->lock, flags);
#endif
host->detect_change = 1;
+
+ wake_lock(&host->detect_wake_lock);
mmc_schedule_delayed_work(&host->detect, delay);
}
@@ -1713,7 +1798,7 @@
}
static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card,
- unsigned int arg, unsigned int qty)
+ unsigned int arg, unsigned int qty)
{
unsigned int erase_timeout;
@@ -1817,8 +1902,13 @@
struct mmc_command cmd = {0};
unsigned int qty = 0;
unsigned long timeout;
+ unsigned int fr, nr;
int err;
+ fr = from;
+ nr = to - from + 1;
+ trace_mmc_blk_erase_start(arg, fr, nr);
+
/*
* qty is used to calculate the erase timeout which depends on how many
* erase groups (or allocation units in SD terminology) are affected.
@@ -1922,6 +2012,8 @@
} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
(R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
out:
+
+ trace_mmc_blk_erase_end(arg, fr, nr);
return err;
}
@@ -2353,6 +2445,7 @@
struct mmc_host *host =
container_of(work, struct mmc_host, detect.work);
int i;
+ bool extend_wakelock = false;
if (host->rescan_disable)
return;
@@ -2374,6 +2467,12 @@
host->detect_change = 0;
+ /* If the card was removed the bus will be marked
+ * as dead - extend the wakelock so userspace
+ * can respond */
+ if (host->bus_dead)
+ extend_wakelock = 1;
+
/*
* Let mmc_bus_put() free the bus/bus_ops if we've found that
* the card is no longer present.
@@ -2402,16 +2501,24 @@
mmc_claim_host(host);
for (i = 0; i < ARRAY_SIZE(freqs); i++) {
- if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min)))
+ if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min))) {
+ extend_wakelock = true;
break;
+ }
if (freqs[i] <= host->f_min)
break;
}
mmc_release_host(host);
out:
- if (host->caps & MMC_CAP_NEEDS_POLL)
+ if (extend_wakelock)
+ wake_lock_timeout(&host->detect_wake_lock, HZ / 2);
+ else
+ wake_unlock(&host->detect_wake_lock);
+ if (host->caps & MMC_CAP_NEEDS_POLL) {
+ wake_lock(&host->detect_wake_lock);
mmc_schedule_delayed_work(&host->detect, HZ);
+ }
}
void mmc_start_host(struct mmc_host *host)
@@ -2435,7 +2542,8 @@
#endif
host->rescan_disable = 1;
- cancel_delayed_work_sync(&host->detect);
+ if (cancel_delayed_work_sync(&host->detect))
+ wake_unlock(&host->detect_wake_lock);
mmc_flush_scheduled_work();
/* clear pm flags now and let card drivers set them as needed */
@@ -2582,44 +2690,6 @@
}
EXPORT_SYMBOL(mmc_flush_cache);
-/*
- * Turn the cache ON/OFF.
- * Turning the cache OFF shall trigger flushing of the data
- * to the non-volatile storage.
- * This function should be called with host claimed
- */
-int mmc_cache_ctrl(struct mmc_host *host, u8 enable)
-{
- struct mmc_card *card = host->card;
- unsigned int timeout;
- int err = 0;
-
- if (!(host->caps2 & MMC_CAP2_CACHE_CTRL) ||
- mmc_card_is_removable(host))
- return err;
-
- if (card && mmc_card_mmc(card) &&
- (card->ext_csd.cache_size > 0)) {
- enable = !!enable;
-
- if (card->ext_csd.cache_ctrl ^ enable) {
- timeout = enable ? card->ext_csd.generic_cmd6_time : 0;
- err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
- EXT_CSD_CACHE_CTRL, enable, timeout);
- if (err)
- pr_err("%s: cache %s error %d\n",
- mmc_hostname(card->host),
- enable ? "on" : "off",
- err);
- else
- card->ext_csd.cache_ctrl = enable;
- }
- }
-
- return err;
-}
-EXPORT_SYMBOL(mmc_cache_ctrl);
-
#ifdef CONFIG_PM
/**
@@ -2630,7 +2700,11 @@
{
int err = 0;
- cancel_delayed_work(&host->detect);
+ if (mmc_bus_needs_resume(host))
+ return 0;
+
+ if (cancel_delayed_work(&host->detect))
+ wake_unlock(&host->detect_wake_lock);
mmc_flush_scheduled_work();
mmc_bus_get(host);
@@ -2681,6 +2755,12 @@
int err = 0;
mmc_bus_get(host);
+ if (mmc_bus_manual_resume(host)) {
+ host->bus_resume_flags |= MMC_BUSRESUME_NEEDS_RESUME;
+ mmc_bus_put(host);
+ return 0;
+ }
+
if (host->bus_ops && !host->bus_dead) {
if (!mmc_card_keep_power(host)) {
mmc_power_up(host);
@@ -2741,9 +2821,14 @@
}
spin_lock_irqsave(&host->lock, flags);
+ if (mmc_bus_needs_resume(host)) {
+ spin_unlock_irqrestore(&host->lock, flags);
+ break;
+ }
host->rescan_disable = 1;
spin_unlock_irqrestore(&host->lock, flags);
- cancel_delayed_work_sync(&host->detect);
+ if (cancel_delayed_work_sync(&host->detect))
+ wake_unlock(&host->detect_wake_lock);
if (!host->bus_ops || host->bus_ops->suspend)
break;
@@ -2764,6 +2849,10 @@
case PM_POST_RESTORE:
spin_lock_irqsave(&host->lock, flags);
+ if (mmc_bus_manual_resume(host)) {
+ spin_unlock_irqrestore(&host->lock, flags);
+ break;
+ }
host->rescan_disable = 0;
spin_unlock_irqrestore(&host->lock, flags);
mmc_detect_change(host, 0);
@@ -2791,6 +2880,22 @@
init_waitqueue_head(&host->context_info.wait);
}
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+void mmc_set_embedded_sdio_data(struct mmc_host *host,
+ struct sdio_cis *cis,
+ struct sdio_cccr *cccr,
+ struct sdio_embedded_func *funcs,
+ int num_funcs)
+{
+ host->embedded_sdio_data.cis = cis;
+ host->embedded_sdio_data.cccr = cccr;
+ host->embedded_sdio_data.funcs = funcs;
+ host->embedded_sdio_data.num_funcs = num_funcs;
+}
+
+EXPORT_SYMBOL(mmc_set_embedded_sdio_data);
+#endif
+
static int __init mmc_init(void)
{
int ret;
@@ -2831,6 +2936,124 @@
destroy_workqueue(workqueue);
}
+/*
+ * MMC IO latency support. We want this to be as cheap as possible, so doing
+ * this lockless (and avoiding atomics), a few off by a few errors in this
+ * code is not harmful, and we don't want to do anything that is
+ * perf-impactful.
+ * TODO : If necessary, we can make the histograms per-cpu and aggregate
+ * them when printing them out.
+ */
+static void
+mmc_zero_latency_hist(struct mmc_host *host)
+{
+ memset(host->latency_y_axis_read, 0,
+ sizeof(host->latency_y_axis_read));
+ memset(host->latency_y_axis_write, 0,
+ sizeof(host->latency_y_axis_write));
+ host->latency_reads_elems = 0;
+ host->latency_writes_elems = 0;
+}
+
+static ssize_t
+latency_hist_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ int i;
+ struct mmc_host *host = cls_dev_to_mmc_host(dev);
+ int bytes_written = 0;
+ u_int64_t num_elem, elem;
+ int pct;
+
+ num_elem = host->latency_reads_elems;
+ if (num_elem > 0) {
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "IO svc_time Read Latency Histogram :\n");
+ for (i = 0;
+ i < ARRAY_SIZE(latency_x_axis_us);
+ i++) {
+ elem = host->latency_y_axis_read[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t< %5lluus%15llu%15d%%\n",
+ latency_x_axis_us[i],
+ elem, pct);
+ }
+ /* Last element in y-axis table is overflow */
+ elem = host->latency_y_axis_read[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t> %5dms%15llu%15d%%\n", 10,
+ elem, pct);
+ }
+ num_elem = host->latency_writes_elems;
+ if (num_elem > 0) {
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "IO svc_time Write Latency Histogram :\n");
+ for (i = 0;
+ i < ARRAY_SIZE(latency_x_axis_us);
+ i++) {
+ elem = host->latency_y_axis_write[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t< %5lluus%15llu%15d%%\n",
+ latency_x_axis_us[i],
+ elem, pct);
+ }
+ /* Last element in y-axis table is overflow */
+ elem = host->latency_y_axis_write[i];
+ pct = div64_u64(elem * 100, num_elem);
+ bytes_written += scnprintf(buf + bytes_written,
+ PAGE_SIZE - bytes_written,
+ "\t> %5dms%15llu%15d%%\n", 10,
+ elem, pct);
+ }
+ return bytes_written;
+}
+/*
+ * Values permitted 0, 1, 2.
+ * 0 -> Disable IO latency histograms (default)
+ * 1 -> Enable IO latency histograms
+ * 2 -> Zero out IO latency histograms
+ */
+static ssize_t
+latency_hist_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mmc_host *host = cls_dev_to_mmc_host(dev);
+ long value;
+
+ if (kstrtol(buf, 0, &value))
+ return -EINVAL;
+ if (value == MMC_IO_LAT_HIST_ZERO)
+ mmc_zero_latency_hist(host);
+ else if (value == MMC_IO_LAT_HIST_ENABLE ||
+ value == MMC_IO_LAT_HIST_DISABLE)
+ host->latency_hist_enabled = value;
+ return count;
+}
+
+static DEVICE_ATTR(latency_hist, S_IRUGO | S_IWUSR,
+ latency_hist_show, latency_hist_store);
+
+void
+mmc_latency_hist_sysfs_init(struct mmc_host *host)
+{
+ if (device_create_file(&host->class_dev, &dev_attr_latency_hist))
+ dev_err(&host->class_dev,
+ "Failed to create latency_hist sysfs entry\n");
+}
+
+void
+mmc_latency_hist_sysfs_exit(struct mmc_host *host)
+{
+ device_remove_file(&host->class_dev, &dev_attr_latency_hist);
+}
+
subsys_initcall(mmc_init);
module_exit(mmc_exit);
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index b9f18a2..c9c2c2f 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -25,6 +25,7 @@
int (*power_save)(struct mmc_host *);
int (*power_restore)(struct mmc_host *);
int (*alive)(struct mmc_host *);
+ int (*shutdown)(struct mmc_host *);
};
void mmc_attach_bus(struct mmc_host *host, const struct mmc_bus_ops *ops);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 2a3593d..c074ef7 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -30,8 +30,6 @@
#include "core.h"
#include "host.h"
-#define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev)
-
static void mmc_host_classdev_release(struct device *dev)
{
struct mmc_host *host = cls_dev_to_mmc_host(dev);
@@ -409,6 +407,8 @@
host->caps |= MMC_CAP_POWER_OFF_CARD;
if (of_find_property(np, "cap-sdio-irq", &len))
host->caps |= MMC_CAP_SDIO_IRQ;
+ if (of_find_property(np, "full-pwr-cycle", &len))
+ host->caps2 |= MMC_CAP2_FULL_PWR_CYCLE;
if (of_find_property(np, "keep-power-in-suspend", &len))
host->pm_caps |= MMC_PM_KEEP_POWER;
if (of_find_property(np, "enable-sdio-wakeup", &len))
@@ -459,6 +459,8 @@
spin_lock_init(&host->lock);
init_waitqueue_head(&host->wq);
+ wake_lock_init(&host->detect_wake_lock, WAKE_LOCK_SUSPEND,
+ kasprintf(GFP_KERNEL, "%s_detect", mmc_hostname(host)));
INIT_DELAYED_WORK(&host->detect, mmc_rescan);
#ifdef CONFIG_PM
host->pm_notify.notifier_call = mmc_pm_notify;
@@ -510,8 +512,11 @@
#endif
mmc_host_clk_sysfs_init(host);
+ mmc_latency_hist_sysfs_init(host);
+
mmc_start_host(host);
- register_pm_notifier(&host->pm_notify);
+ if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+ register_pm_notifier(&host->pm_notify);
return 0;
}
@@ -528,7 +533,9 @@
*/
void mmc_remove_host(struct mmc_host *host)
{
- unregister_pm_notifier(&host->pm_notify);
+ if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+ unregister_pm_notifier(&host->pm_notify);
+
mmc_stop_host(host);
#ifdef CONFIG_DEBUG_FS
@@ -555,7 +562,8 @@
spin_lock(&mmc_host_lock);
idr_remove(&mmc_host_idr, host->index);
spin_unlock(&mmc_host_lock);
-
+ wake_lock_destroy(&host->detect_wake_lock);
+ mmc_latency_hist_sysfs_exit(host);
put_device(&host->class_dev);
}
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index f2ab9e5..4dcf499 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -12,8 +12,13 @@
#define _MMC_CORE_HOST_H
#include <linux/mmc/host.h>
+#define cls_dev_to_mmc_host(d) container_of(d, struct mmc_host, class_dev)
+
int mmc_register_host_class(void);
void mmc_unregister_host_class(void);
+void mmc_latency_hist_sysfs_init(struct mmc_host *host);
+void mmc_latency_hist_sysfs_exit(struct mmc_host *host);
+
#endif
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index dda1a42..833d106 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1020,11 +1020,9 @@
}
/*
- * If the host supports the power_off_notify capability then
- * set the notification byte in the ext_csd register of device
+ * Enable power_off_notification byte in the ext_csd register
*/
- if ((host->caps2 & MMC_CAP2_POWEROFF_NOTIFY) &&
- (card->ext_csd.rev >= 6)) {
+ if (card->ext_csd.rev >= 6) {
err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
EXT_CSD_POWER_OFF_NOTIFICATION,
EXT_CSD_POWER_ON,
@@ -1406,24 +1404,24 @@
}
}
-/*
- * Suspend callback from host.
- */
-static int mmc_suspend(struct mmc_host *host)
+static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
{
int err = 0;
+ unsigned int notify_type = is_suspend ? EXT_CSD_POWER_OFF_SHORT :
+ EXT_CSD_POWER_OFF_LONG;
BUG_ON(!host);
BUG_ON(!host->card);
mmc_claim_host(host);
- err = mmc_cache_ctrl(host, 0);
+ err = mmc_flush_cache(host->card);
if (err)
goto out;
- if (mmc_can_poweroff_notify(host->card))
- err = mmc_poweroff_notify(host->card, EXT_CSD_POWER_OFF_SHORT);
+ if (mmc_can_poweroff_notify(host->card) &&
+ ((host->caps2 & MMC_CAP2_FULL_PWR_CYCLE) || !is_suspend))
+ err = mmc_poweroff_notify(host->card, notify_type);
else if (mmc_card_can_sleep(host))
err = mmc_card_sleep(host);
else if (!mmc_host_is_spi(host))
@@ -1436,6 +1434,22 @@
}
/*
+ * Suspend callback from host.
+ */
+static int mmc_suspend(struct mmc_host *host)
+{
+ return _mmc_suspend(host, true);
+}
+
+/*
+ * Shutdown callback
+ */
+static int mmc_shutdown(struct mmc_host *host)
+{
+ return _mmc_suspend(host, false);
+}
+
+/*
* Resume callback from host.
*
* This function tries to determine if the same card is still present
@@ -1506,6 +1520,7 @@
.resume = NULL,
.power_restore = mmc_power_restore,
.alive = mmc_alive,
+ .shutdown = mmc_shutdown,
};
static const struct mmc_bus_ops mmc_ops_unsafe = {
@@ -1517,6 +1532,7 @@
.resume = mmc_resume,
.power_restore = mmc_power_restore,
.alive = mmc_alive,
+ .shutdown = mmc_shutdown,
};
static void mmc_attach_bus_ops(struct mmc_host *host)
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 9e645e1..6d945e0 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -805,6 +805,9 @@
bool reinit)
{
int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
if (!reinit) {
/*
@@ -831,7 +834,26 @@
/*
* Fetch switch information from card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ for (retries = 1; retries <= 3; retries++) {
+ err = mmc_read_switch(card);
+ if (!err) {
+ if (retries > 1) {
+ printk(KERN_WARNING
+ "%s: recovered\n",
+ mmc_hostname(host));
+ }
+ break;
+ } else {
+ printk(KERN_WARNING
+ "%s: read switch failed (attempt %d)\n",
+ mmc_hostname(host), retries);
+ }
+ }
+#else
err = mmc_read_switch(card);
+#endif
+
if (err)
return err;
}
@@ -1032,7 +1054,10 @@
*/
static void mmc_sd_detect(struct mmc_host *host)
{
- int err;
+ int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries = 5;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
@@ -1042,7 +1067,23 @@
/*
* Just check if our card has been removed.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ while(retries) {
+ err = mmc_send_status(host->card, NULL);
+ if (err) {
+ retries--;
+ udelay(5);
+ continue;
+ }
+ break;
+ }
+ if (!retries) {
+ printk(KERN_ERR "%s(%s): Unable to re-detect card (%d)\n",
+ __func__, mmc_hostname(host), err);
+ }
+#else
err = _mmc_detect_card_removed(host);
+#endif
mmc_release_host(host);
@@ -1084,12 +1125,31 @@
static int mmc_sd_resume(struct mmc_host *host)
{
int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
mmc_claim_host(host);
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, host->ocr, host->card);
+
+ if (err) {
+ printk(KERN_ERR "%s: Re-init card rc = %d (retries = %d)\n",
+ mmc_hostname(host), err, retries);
+ mdelay(5);
+ retries--;
+ continue;
+ }
+ break;
+ }
+#else
err = mmc_sd_init_card(host, host->ocr, host->card);
+#endif
mmc_release_host(host);
return err;
@@ -1114,6 +1174,7 @@
.resume = NULL,
.power_restore = mmc_sd_power_restore,
.alive = mmc_sd_alive,
+ .shutdown = mmc_sd_suspend,
};
static const struct mmc_bus_ops mmc_sd_ops_unsafe = {
@@ -1123,6 +1184,7 @@
.resume = mmc_sd_resume,
.power_restore = mmc_sd_power_restore,
.alive = mmc_sd_alive,
+ .shutdown = mmc_sd_suspend,
};
static void mmc_sd_attach_bus_ops(struct mmc_host *host)
@@ -1143,6 +1205,9 @@
{
int err;
u32 ocr;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
WARN_ON(!host->claimed);
@@ -1198,9 +1263,27 @@
/*
* Detect and init the card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, host->ocr, NULL);
+ if (err) {
+ retries--;
+ continue;
+ }
+ break;
+ }
+
+ if (!retries) {
+ printk(KERN_ERR "%s: mmc_sd_init_card() failure (err = %d)\n",
+ mmc_hostname(host), err);
+ goto err;
+ }
+#else
err = mmc_sd_init_card(host, host->ocr, NULL);
if (err)
goto err;
+#endif
mmc_release_host(host);
err = mmc_add_card(host->card);
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 6889a82..46e68f1 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -10,6 +10,7 @@
*/
#include <linux/err.h>
+#include <linux/module.h>
#include <linux/pm_runtime.h>
#include <linux/mmc/host.h>
@@ -28,6 +29,10 @@
#include "sdio_ops.h"
#include "sdio_cis.h"
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/sdio_ids.h>
+#endif
+
static int sdio_read_fbr(struct sdio_func *func)
{
int ret;
@@ -728,19 +733,35 @@
goto finish;
}
- /*
- * Read the common registers.
- */
- err = sdio_read_cccr(card, ocr);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cccr)
+ memcpy(&card->cccr, host->embedded_sdio_data.cccr, sizeof(struct sdio_cccr));
+ else {
+#endif
+ /*
+ * Read the common registers.
+ */
+ err = sdio_read_cccr(card, ocr);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
- /*
- * Read the common CIS tuples.
- */
- err = sdio_read_common_cis(card);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cis)
+ memcpy(&card->cis, host->embedded_sdio_data.cis, sizeof(struct sdio_cis));
+ else {
+#endif
+ /*
+ * Read the common CIS tuples.
+ */
+ err = sdio_read_common_cis(card);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
if (oldcard) {
int same = (card->cis.vendor == oldcard->cis.vendor &&
@@ -1147,14 +1168,36 @@
funcs = (ocr & 0x70000000) >> 28;
card->sdio_funcs = 0;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs)
+ card->sdio_funcs = funcs = host->embedded_sdio_data.num_funcs;
+#endif
+
/*
* Initialize (but don't add) all present functions.
*/
for (i = 0; i < funcs; i++, card->sdio_funcs++) {
- err = sdio_init_func(host->card, i + 1);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs) {
+ struct sdio_func *tmp;
+ tmp = sdio_alloc_func(host->card);
+ if (IS_ERR(tmp))
+ goto remove;
+ tmp->num = (i + 1);
+ card->sdio_func[i] = tmp;
+ tmp->class = host->embedded_sdio_data.funcs[i].f_class;
+ tmp->max_blksize = host->embedded_sdio_data.funcs[i].f_maxblksize;
+ tmp->vendor = card->cis.vendor;
+ tmp->device = card->cis.device;
+ } else {
+#endif
+ err = sdio_init_func(host->card, i + 1);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
/*
* Enable Runtime PM for this func (if supported)
*/
@@ -1202,3 +1245,39 @@
return err;
}
+int sdio_reset_comm(struct mmc_card *card)
+{
+ struct mmc_host *host = card->host;
+ u32 ocr;
+ int err;
+
+ printk("%s():\n", __func__);
+ mmc_claim_host(host);
+
+ mmc_go_idle(host);
+
+ mmc_set_clock(host, host->f_min);
+
+ err = mmc_send_io_op_cond(host, 0, &ocr);
+ if (err)
+ goto err;
+
+ host->ocr = mmc_select_voltage(host, ocr);
+ if (!host->ocr) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = mmc_sdio_init_card(host, host->ocr, card, 0);
+ if (err)
+ goto err;
+
+ mmc_release_host(host);
+ return 0;
+err:
+ printk("%s: Error resetting SDIO communications (%d)\n",
+ mmc_hostname(host), err);
+ mmc_release_host(host);
+ return err;
+}
+EXPORT_SYMBOL(sdio_reset_comm);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 546c67c..c012cf5 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -25,6 +25,10 @@
#include "sdio_cis.h"
#include "sdio_bus.h"
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/host.h>
+#endif
+
/* show configuration fields */
#define sdio_config_attr(field, format_string) \
static ssize_t \
@@ -270,7 +274,14 @@
{
struct sdio_func *func = dev_to_sdio_func(dev);
- sdio_free_func_cis(func);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ /*
+ * If this device is embedded then we never allocated
+ * cis tables for this func
+ */
+ if (!func->card->host->embedded_sdio_data.funcs)
+#endif
+ sdio_free_func_cis(func);
kfree(func->info);
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
old mode 100644
new mode 100755
index 78cb4d5..8fdeb07
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -384,6 +384,39 @@
EXPORT_SYMBOL_GPL(sdio_readb);
/**
+ * sdio_readb_ext - read a single byte from a SDIO function
+ * @func: SDIO function to access
+ * @addr: address to read
+ * @err_ret: optional status value from transfer
+ * @in: value to add to argument
+ *
+ * Reads a single byte from the address space of a given SDIO
+ * function. If there is a problem reading the address, 0xff
+ * is returned and @err_ret will contain the error code.
+ */
+unsigned char sdio_readb_ext(struct sdio_func *func, unsigned int addr,
+ int *err_ret, unsigned in)
+{
+ int ret;
+ unsigned char val;
+
+ BUG_ON(!func);
+
+ if (err_ret)
+ *err_ret = 0;
+
+ ret = mmc_io_rw_direct(func->card, 0, func->num, addr, (u8)in, &val);
+ if (ret) {
+ if (err_ret)
+ *err_ret = ret;
+ return 0xFF;
+ }
+
+ return val;
+}
+EXPORT_SYMBOL_GPL(sdio_readb_ext);
+
+/**
* sdio_writeb - write a single byte to a SDIO function
* @func: SDIO function to access
* @b: byte to write
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 50543f1..f2ab08c 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -1,3 +1,10 @@
+config MTD_NAND_IDS
+ tristate "Include chip ids for known NAND devices."
+ depends on MTD
+ help
+ Useful for NAND drivers that do not use the NAND subsystem but
+ still like to take advantage of the known chip information.
+
config MTD_NAND_ECC
tristate
@@ -133,9 +140,6 @@
default 8 if MTD_NAND_OMAP_BCH8
endif
-config MTD_NAND_IDS
- tristate
-
config MTD_NAND_RICOH
tristate "Ricoh xD card reader"
default n
diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig
index 1373c6d..282aec4 100644
--- a/drivers/net/ppp/Kconfig
+++ b/drivers/net/ppp/Kconfig
@@ -149,6 +149,23 @@
tunnels. L2TP is replacing PPTP for VPN uses.
if TTY
+config PPPOLAC
+ tristate "PPP on L2TP Access Concentrator"
+ depends on PPP && INET
+ help
+ L2TP (RFC 2661) is a tunneling protocol widely used in virtual private
+ networks. This driver handles L2TP data packets between a UDP socket
+ and a PPP channel, but only permits one session per socket. Thus it is
+ fairly simple and suited for clients.
+
+config PPPOPNS
+ tristate "PPP on PPTP Network Server"
+ depends on PPP && INET
+ help
+ PPTP (RFC 2637) is a tunneling protocol widely used in virtual private
+ networks. This driver handles PPTP data packets between a RAW socket
+ and a PPP channel. It is fairly simple and easy to use.
+
config PPP_ASYNC
tristate "PPP support for async serial ports"
depends on PPP
diff --git a/drivers/net/ppp/Makefile b/drivers/net/ppp/Makefile
index a6b6297..d283d03c 100644
--- a/drivers/net/ppp/Makefile
+++ b/drivers/net/ppp/Makefile
@@ -11,3 +11,5 @@
obj-$(CONFIG_PPPOE) += pppox.o pppoe.o
obj-$(CONFIG_PPPOL2TP) += pppox.o
obj-$(CONFIG_PPTP) += pppox.o pptp.o
+obj-$(CONFIG_PPPOLAC) += pppox.o pppolac.o
+obj-$(CONFIG_PPPOPNS) += pppox.o pppopns.o
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 14a8d29..95ca33b 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2925,6 +2925,9 @@
*/
static void ppp_destroy_channel(struct channel *pch)
{
+ put_net(pch->chan_net);
+ pch->chan_net = NULL;
+
atomic_dec(&channel_count);
if (!pch->file.dead) {
diff --git a/drivers/net/ppp/pppolac.c b/drivers/net/ppp/pppolac.c
new file mode 100644
index 0000000..a5d3d63
--- /dev/null
+++ b/drivers/net/ppp/pppolac.c
@@ -0,0 +1,449 @@
+/* drivers/net/pppolac.c
+ *
+ * Driver for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles L2TP data packets between a UDP socket and a PPP channel.
+ * The socket must keep connected, and only one session per socket is permitted.
+ * Sequencing of outgoing packets is controlled by LNS. Incoming packets with
+ * sequences are reordered within a sliding window of one second. Currently
+ * reordering only happens when a packet is received. It is done for simplicity
+ * since no additional locks or threads are required. This driver only works on
+ * IPv4 due to the lack of UDP encapsulation support in IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/udp.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <net/tcp_states.h>
+#include <asm/uaccess.h>
+
+#define L2TP_CONTROL_BIT 0x80
+#define L2TP_LENGTH_BIT 0x40
+#define L2TP_SEQUENCE_BIT 0x08
+#define L2TP_OFFSET_BIT 0x02
+#define L2TP_VERSION 0x02
+#define L2TP_VERSION_MASK 0x0F
+
+#define PPP_ADDR 0xFF
+#define PPP_CTRL 0x03
+
+union unaligned {
+ __u32 u32;
+} __attribute__((packed));
+
+static inline union unaligned *unaligned(void *ptr)
+{
+ return (union unaligned *)ptr;
+}
+
+struct meta {
+ __u32 sequence;
+ __u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+ return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
+{
+ struct sock *sk = (struct sock *)sk_udp->sk_user_data;
+ struct pppolac_opt *opt = &pppox_sk(sk)->proto.lac;
+ struct meta *meta = skb_meta(skb);
+ __u32 now = jiffies;
+ __u8 bits;
+ __u8 *ptr;
+
+ /* Drop the packet if L2TP header is missing. */
+ if (skb->len < sizeof(struct udphdr) + 6)
+ goto drop;
+
+ /* Put it back if it is a control packet. */
+ if (skb->data[sizeof(struct udphdr)] & L2TP_CONTROL_BIT)
+ return opt->backlog_rcv(sk_udp, skb);
+
+ /* Skip UDP header. */
+ skb_pull(skb, sizeof(struct udphdr));
+
+ /* Check the version. */
+ if ((skb->data[1] & L2TP_VERSION_MASK) != L2TP_VERSION)
+ goto drop;
+ bits = skb->data[0];
+ ptr = &skb->data[2];
+
+ /* Check the length if it is present. */
+ if (bits & L2TP_LENGTH_BIT) {
+ if ((ptr[0] << 8 | ptr[1]) != skb->len)
+ goto drop;
+ ptr += 2;
+ }
+
+ /* Skip all fields including optional ones. */
+ if (!skb_pull(skb, 6 + (bits & L2TP_SEQUENCE_BIT ? 4 : 0) +
+ (bits & L2TP_LENGTH_BIT ? 2 : 0) +
+ (bits & L2TP_OFFSET_BIT ? 2 : 0)))
+ goto drop;
+
+ /* Skip the offset padding if it is present. */
+ if (bits & L2TP_OFFSET_BIT &&
+ !skb_pull(skb, skb->data[-2] << 8 | skb->data[-1]))
+ goto drop;
+
+ /* Check the tunnel and the session. */
+ if (unaligned(ptr)->u32 != opt->local)
+ goto drop;
+
+ /* Check the sequence if it is present. */
+ if (bits & L2TP_SEQUENCE_BIT) {
+ meta->sequence = ptr[4] << 8 | ptr[5];
+ if ((__s16)(meta->sequence - opt->recv_sequence) < 0)
+ goto drop;
+ }
+
+ /* Skip PPP address and control if they are present. */
+ if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+ skb->data[1] == PPP_CTRL)
+ skb_pull(skb, 2);
+
+ /* Fix PPP protocol if it is compressed. */
+ if (skb->len >= 1 && skb->data[0] & 1)
+ skb_push(skb, 1)[0] = 0;
+
+ /* Drop the packet if PPP protocol is missing. */
+ if (skb->len < 2)
+ goto drop;
+
+ /* Perform reordering if sequencing is enabled. */
+ atomic_set(&opt->sequencing, bits & L2TP_SEQUENCE_BIT);
+ if (bits & L2TP_SEQUENCE_BIT) {
+ struct sk_buff *skb1;
+
+ /* Insert the packet into receive queue in order. */
+ skb_set_owner_r(skb, sk);
+ skb_queue_walk(&sk->sk_receive_queue, skb1) {
+ struct meta *meta1 = skb_meta(skb1);
+ __s16 order = meta->sequence - meta1->sequence;
+ if (order == 0)
+ goto drop;
+ if (order < 0) {
+ meta->timestamp = meta1->timestamp;
+ skb_insert(skb1, skb, &sk->sk_receive_queue);
+ skb = NULL;
+ break;
+ }
+ }
+ if (skb) {
+ meta->timestamp = now;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ }
+
+ /* Remove packets from receive queue as long as
+ * 1. the receive buffer is full,
+ * 2. they are queued longer than one second, or
+ * 3. there are no missing packets before them. */
+ skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+ meta = skb_meta(skb);
+ if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+ now - meta->timestamp < HZ &&
+ meta->sequence != opt->recv_sequence)
+ break;
+ skb_unlink(skb, &sk->sk_receive_queue);
+ opt->recv_sequence = (__u16)(meta->sequence + 1);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ }
+ return NET_RX_SUCCESS;
+ }
+
+ /* Flush receive queue if sequencing is disabled. */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ return NET_RX_SUCCESS;
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static int pppolac_recv(struct sock *sk_udp, struct sk_buff *skb)
+{
+ sock_hold(sk_udp);
+ sk_receive_skb(sk_udp, skb, 0);
+ return 0;
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppolac_xmit_core(struct work_struct *delivery_work)
+{
+ mm_segment_t old_fs = get_fs();
+ struct sk_buff *skb;
+
+ set_fs(KERNEL_DS);
+ while ((skb = skb_dequeue(&delivery_queue))) {
+ struct sock *sk_udp = skb->sk;
+ struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+ struct msghdr msg = {
+ .msg_iov = (struct iovec *)&iov,
+ .msg_iovlen = 1,
+ .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+ };
+ sk_udp->sk_prot->sendmsg(NULL, sk_udp, &msg, skb->len);
+ kfree_skb(skb);
+ }
+ set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppolac_xmit_core);
+
+static int pppolac_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ struct sock *sk_udp = (struct sock *)chan->private;
+ struct pppolac_opt *opt = &pppox_sk(sk_udp->sk_user_data)->proto.lac;
+
+ /* Install PPP address and control. */
+ skb_push(skb, 2);
+ skb->data[0] = PPP_ADDR;
+ skb->data[1] = PPP_CTRL;
+
+ /* Install L2TP header. */
+ if (atomic_read(&opt->sequencing)) {
+ skb_push(skb, 10);
+ skb->data[0] = L2TP_SEQUENCE_BIT;
+ skb->data[6] = opt->xmit_sequence >> 8;
+ skb->data[7] = opt->xmit_sequence;
+ skb->data[8] = 0;
+ skb->data[9] = 0;
+ opt->xmit_sequence++;
+ } else {
+ skb_push(skb, 6);
+ skb->data[0] = 0;
+ }
+ skb->data[1] = L2TP_VERSION;
+ unaligned(&skb->data[2])->u32 = opt->remote;
+
+ /* Now send the packet via the delivery queue. */
+ skb_set_owner_w(skb, sk_udp);
+ skb_queue_tail(&delivery_queue, skb);
+ schedule_work(&delivery_work);
+ return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppolac_channel_ops = {
+ .start_xmit = pppolac_xmit,
+};
+
+static int pppolac_connect(struct socket *sock, struct sockaddr *useraddr,
+ int addrlen, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct sockaddr_pppolac *addr = (struct sockaddr_pppolac *)useraddr;
+ struct socket *sock_udp = NULL;
+ struct sock *sk_udp;
+ int error;
+
+ if (addrlen != sizeof(struct sockaddr_pppolac) ||
+ !addr->local.tunnel || !addr->local.session ||
+ !addr->remote.tunnel || !addr->remote.session) {
+ return -EINVAL;
+ }
+
+ lock_sock(sk);
+ error = -EALREADY;
+ if (sk->sk_state != PPPOX_NONE)
+ goto out;
+
+ sock_udp = sockfd_lookup(addr->udp_socket, &error);
+ if (!sock_udp)
+ goto out;
+ sk_udp = sock_udp->sk;
+ lock_sock(sk_udp);
+
+ /* Remove this check when IPv6 supports UDP encapsulation. */
+ error = -EAFNOSUPPORT;
+ if (sk_udp->sk_family != AF_INET)
+ goto out;
+ error = -EPROTONOSUPPORT;
+ if (sk_udp->sk_protocol != IPPROTO_UDP)
+ goto out;
+ error = -EDESTADDRREQ;
+ if (sk_udp->sk_state != TCP_ESTABLISHED)
+ goto out;
+ error = -EBUSY;
+ if (udp_sk(sk_udp)->encap_type || sk_udp->sk_user_data)
+ goto out;
+ if (!sk_udp->sk_bound_dev_if) {
+ struct dst_entry *dst = sk_dst_get(sk_udp);
+ error = -ENODEV;
+ if (!dst)
+ goto out;
+ sk_udp->sk_bound_dev_if = dst->dev->ifindex;
+ dst_release(dst);
+ }
+
+ po->chan.hdrlen = 12;
+ po->chan.private = sk_udp;
+ po->chan.ops = &pppolac_channel_ops;
+ po->chan.mtu = PPP_MRU - 80;
+ po->proto.lac.local = unaligned(&addr->local)->u32;
+ po->proto.lac.remote = unaligned(&addr->remote)->u32;
+ atomic_set(&po->proto.lac.sequencing, 1);
+ po->proto.lac.backlog_rcv = sk_udp->sk_backlog_rcv;
+
+ error = ppp_register_channel(&po->chan);
+ if (error)
+ goto out;
+
+ sk->sk_state = PPPOX_CONNECTED;
+ udp_sk(sk_udp)->encap_type = UDP_ENCAP_L2TPINUDP;
+ udp_sk(sk_udp)->encap_rcv = pppolac_recv;
+ sk_udp->sk_backlog_rcv = pppolac_recv_core;
+ sk_udp->sk_user_data = sk;
+out:
+ if (sock_udp) {
+ release_sock(sk_udp);
+ if (error)
+ sockfd_put(sock_udp);
+ }
+ release_sock(sk);
+ return error;
+}
+
+static int pppolac_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ release_sock(sk);
+ return -EBADF;
+ }
+
+ if (sk->sk_state != PPPOX_NONE) {
+ struct sock *sk_udp = (struct sock *)pppox_sk(sk)->chan.private;
+ lock_sock(sk_udp);
+ skb_queue_purge(&sk->sk_receive_queue);
+ pppox_unbind_sock(sk);
+ udp_sk(sk_udp)->encap_type = 0;
+ udp_sk(sk_udp)->encap_rcv = NULL;
+ sk_udp->sk_backlog_rcv = pppox_sk(sk)->proto.lac.backlog_rcv;
+ sk_udp->sk_user_data = NULL;
+ release_sock(sk_udp);
+ sockfd_put(sk_udp->sk_socket);
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppolac_proto = {
+ .name = "PPPOLAC",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppolac_proto_ops = {
+ .family = PF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppolac_release,
+ .bind = sock_no_bind,
+ .connect = pppolac_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = sock_no_poll,
+ .ioctl = pppox_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = sock_no_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = sock_no_mmap,
+};
+
+static int pppolac_create(struct net *net, struct socket *sock)
+{
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppolac_proto);
+ if (!sk)
+ return -ENOMEM;
+
+ sock_init_data(sock, sk);
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppolac_proto_ops;
+ sk->sk_protocol = PX_PROTO_OLAC;
+ sk->sk_state = PPPOX_NONE;
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppolac_pppox_proto = {
+ .create = pppolac_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init pppolac_init(void)
+{
+ int error;
+
+ error = proto_register(&pppolac_proto, 0);
+ if (error)
+ return error;
+
+ error = register_pppox_proto(PX_PROTO_OLAC, &pppolac_pppox_proto);
+ if (error)
+ proto_unregister(&pppolac_proto);
+ else
+ skb_queue_head_init(&delivery_queue);
+ return error;
+}
+
+static void __exit pppolac_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OLAC);
+ proto_unregister(&pppolac_proto);
+}
+
+module_init(pppolac_init);
+module_exit(pppolac_exit);
+
+MODULE_DESCRIPTION("PPP on L2TP Access Concentrator (PPPoLAC)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/pppopns.c b/drivers/net/ppp/pppopns.c
new file mode 100644
index 0000000..6016d29
--- /dev/null
+++ b/drivers/net/ppp/pppopns.c
@@ -0,0 +1,428 @@
+/* drivers/net/pppopns.c
+ *
+ * Driver for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles PPTP data packets between a RAW socket and a PPP channel.
+ * The socket is created in the kernel space and connected to the same address
+ * of the control socket. Outgoing packets are always sent with sequences but
+ * without acknowledgements. Incoming packets with sequences are reordered
+ * within a sliding window of one second. Currently reordering only happens when
+ * a packet is received. It is done for simplicity since no additional locks or
+ * threads are required. This driver should work on both IPv4 and IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/ppp_defs.h>
+#include <linux/if.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <asm/uaccess.h>
+
+#define GRE_HEADER_SIZE 8
+
+#define PPTP_GRE_BITS htons(0x2001)
+#define PPTP_GRE_BITS_MASK htons(0xEF7F)
+#define PPTP_GRE_SEQ_BIT htons(0x1000)
+#define PPTP_GRE_ACK_BIT htons(0x0080)
+#define PPTP_GRE_TYPE htons(0x880B)
+
+#define PPP_ADDR 0xFF
+#define PPP_CTRL 0x03
+
+struct header {
+ __u16 bits;
+ __u16 type;
+ __u16 length;
+ __u16 call;
+ __u32 sequence;
+} __attribute__((packed));
+
+struct meta {
+ __u32 sequence;
+ __u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+ return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
+{
+ struct sock *sk = (struct sock *)sk_raw->sk_user_data;
+ struct pppopns_opt *opt = &pppox_sk(sk)->proto.pns;
+ struct meta *meta = skb_meta(skb);
+ __u32 now = jiffies;
+ struct header *hdr;
+
+ /* Skip transport header */
+ skb_pull(skb, skb_transport_header(skb) - skb->data);
+
+ /* Drop the packet if GRE header is missing. */
+ if (skb->len < GRE_HEADER_SIZE)
+ goto drop;
+ hdr = (struct header *)skb->data;
+
+ /* Check the header. */
+ if (hdr->type != PPTP_GRE_TYPE || hdr->call != opt->local ||
+ (hdr->bits & PPTP_GRE_BITS_MASK) != PPTP_GRE_BITS)
+ goto drop;
+
+ /* Skip all fields including optional ones. */
+ if (!skb_pull(skb, GRE_HEADER_SIZE +
+ (hdr->bits & PPTP_GRE_SEQ_BIT ? 4 : 0) +
+ (hdr->bits & PPTP_GRE_ACK_BIT ? 4 : 0)))
+ goto drop;
+
+ /* Check the length. */
+ if (skb->len != ntohs(hdr->length))
+ goto drop;
+
+ /* Check the sequence if it is present. */
+ if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+ meta->sequence = ntohl(hdr->sequence);
+ if ((__s32)(meta->sequence - opt->recv_sequence) < 0)
+ goto drop;
+ }
+
+ /* Skip PPP address and control if they are present. */
+ if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+ skb->data[1] == PPP_CTRL)
+ skb_pull(skb, 2);
+
+ /* Fix PPP protocol if it is compressed. */
+ if (skb->len >= 1 && skb->data[0] & 1)
+ skb_push(skb, 1)[0] = 0;
+
+ /* Drop the packet if PPP protocol is missing. */
+ if (skb->len < 2)
+ goto drop;
+
+ /* Perform reordering if sequencing is enabled. */
+ if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+ struct sk_buff *skb1;
+
+ /* Insert the packet into receive queue in order. */
+ skb_set_owner_r(skb, sk);
+ skb_queue_walk(&sk->sk_receive_queue, skb1) {
+ struct meta *meta1 = skb_meta(skb1);
+ __s32 order = meta->sequence - meta1->sequence;
+ if (order == 0)
+ goto drop;
+ if (order < 0) {
+ meta->timestamp = meta1->timestamp;
+ skb_insert(skb1, skb, &sk->sk_receive_queue);
+ skb = NULL;
+ break;
+ }
+ }
+ if (skb) {
+ meta->timestamp = now;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ }
+
+ /* Remove packets from receive queue as long as
+ * 1. the receive buffer is full,
+ * 2. they are queued longer than one second, or
+ * 3. there are no missing packets before them. */
+ skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+ meta = skb_meta(skb);
+ if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+ now - meta->timestamp < HZ &&
+ meta->sequence != opt->recv_sequence)
+ break;
+ skb_unlink(skb, &sk->sk_receive_queue);
+ opt->recv_sequence = meta->sequence + 1;
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ }
+ return NET_RX_SUCCESS;
+ }
+
+ /* Flush receive queue if sequencing is disabled. */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_orphan(skb);
+ ppp_input(&pppox_sk(sk)->chan, skb);
+ return NET_RX_SUCCESS;
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static void pppopns_recv(struct sock *sk_raw, int length)
+{
+ struct sk_buff *skb;
+ while ((skb = skb_dequeue(&sk_raw->sk_receive_queue))) {
+ sock_hold(sk_raw);
+ sk_receive_skb(sk_raw, skb, 0);
+ }
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppopns_xmit_core(struct work_struct *delivery_work)
+{
+ mm_segment_t old_fs = get_fs();
+ struct sk_buff *skb;
+
+ set_fs(KERNEL_DS);
+ while ((skb = skb_dequeue(&delivery_queue))) {
+ struct sock *sk_raw = skb->sk;
+ struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+ struct msghdr msg = {
+ .msg_iov = (struct iovec *)&iov,
+ .msg_iovlen = 1,
+ .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+ };
+ sk_raw->sk_prot->sendmsg(NULL, sk_raw, &msg, skb->len);
+ kfree_skb(skb);
+ }
+ set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppopns_xmit_core);
+
+static int pppopns_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ struct sock *sk_raw = (struct sock *)chan->private;
+ struct pppopns_opt *opt = &pppox_sk(sk_raw->sk_user_data)->proto.pns;
+ struct header *hdr;
+ __u16 length;
+
+ /* Install PPP address and control. */
+ skb_push(skb, 2);
+ skb->data[0] = PPP_ADDR;
+ skb->data[1] = PPP_CTRL;
+ length = skb->len;
+
+ /* Install PPTP GRE header. */
+ hdr = (struct header *)skb_push(skb, 12);
+ hdr->bits = PPTP_GRE_BITS | PPTP_GRE_SEQ_BIT;
+ hdr->type = PPTP_GRE_TYPE;
+ hdr->length = htons(length);
+ hdr->call = opt->remote;
+ hdr->sequence = htonl(opt->xmit_sequence);
+ opt->xmit_sequence++;
+
+ /* Now send the packet via the delivery queue. */
+ skb_set_owner_w(skb, sk_raw);
+ skb_queue_tail(&delivery_queue, skb);
+ schedule_work(&delivery_work);
+ return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppopns_channel_ops = {
+ .start_xmit = pppopns_xmit,
+};
+
+static int pppopns_connect(struct socket *sock, struct sockaddr *useraddr,
+ int addrlen, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct sockaddr_pppopns *addr = (struct sockaddr_pppopns *)useraddr;
+ struct sockaddr_storage ss;
+ struct socket *sock_tcp = NULL;
+ struct socket *sock_raw = NULL;
+ struct sock *sk_tcp;
+ struct sock *sk_raw;
+ int error;
+
+ if (addrlen != sizeof(struct sockaddr_pppopns))
+ return -EINVAL;
+
+ lock_sock(sk);
+ error = -EALREADY;
+ if (sk->sk_state != PPPOX_NONE)
+ goto out;
+
+ sock_tcp = sockfd_lookup(addr->tcp_socket, &error);
+ if (!sock_tcp)
+ goto out;
+ sk_tcp = sock_tcp->sk;
+ error = -EPROTONOSUPPORT;
+ if (sk_tcp->sk_protocol != IPPROTO_TCP)
+ goto out;
+ addrlen = sizeof(struct sockaddr_storage);
+ error = kernel_getpeername(sock_tcp, (struct sockaddr *)&ss, &addrlen);
+ if (error)
+ goto out;
+ if (!sk_tcp->sk_bound_dev_if) {
+ struct dst_entry *dst = sk_dst_get(sk_tcp);
+ error = -ENODEV;
+ if (!dst)
+ goto out;
+ sk_tcp->sk_bound_dev_if = dst->dev->ifindex;
+ dst_release(dst);
+ }
+
+ error = sock_create(ss.ss_family, SOCK_RAW, IPPROTO_GRE, &sock_raw);
+ if (error)
+ goto out;
+ sk_raw = sock_raw->sk;
+ sk_raw->sk_bound_dev_if = sk_tcp->sk_bound_dev_if;
+ error = kernel_connect(sock_raw, (struct sockaddr *)&ss, addrlen, 0);
+ if (error)
+ goto out;
+
+ po->chan.hdrlen = 14;
+ po->chan.private = sk_raw;
+ po->chan.ops = &pppopns_channel_ops;
+ po->chan.mtu = PPP_MRU - 80;
+ po->proto.pns.local = addr->local;
+ po->proto.pns.remote = addr->remote;
+ po->proto.pns.data_ready = sk_raw->sk_data_ready;
+ po->proto.pns.backlog_rcv = sk_raw->sk_backlog_rcv;
+
+ error = ppp_register_channel(&po->chan);
+ if (error)
+ goto out;
+
+ sk->sk_state = PPPOX_CONNECTED;
+ lock_sock(sk_raw);
+ sk_raw->sk_data_ready = pppopns_recv;
+ sk_raw->sk_backlog_rcv = pppopns_recv_core;
+ sk_raw->sk_user_data = sk;
+ release_sock(sk_raw);
+out:
+ if (sock_tcp)
+ sockfd_put(sock_tcp);
+ if (error && sock_raw)
+ sock_release(sock_raw);
+ release_sock(sk);
+ return error;
+}
+
+static int pppopns_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ release_sock(sk);
+ return -EBADF;
+ }
+
+ if (sk->sk_state != PPPOX_NONE) {
+ struct sock *sk_raw = (struct sock *)pppox_sk(sk)->chan.private;
+ lock_sock(sk_raw);
+ skb_queue_purge(&sk->sk_receive_queue);
+ pppox_unbind_sock(sk);
+ sk_raw->sk_data_ready = pppox_sk(sk)->proto.pns.data_ready;
+ sk_raw->sk_backlog_rcv = pppox_sk(sk)->proto.pns.backlog_rcv;
+ sk_raw->sk_user_data = NULL;
+ release_sock(sk_raw);
+ sock_release(sk_raw->sk_socket);
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppopns_proto = {
+ .name = "PPPOPNS",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppopns_proto_ops = {
+ .family = PF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppopns_release,
+ .bind = sock_no_bind,
+ .connect = pppopns_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = sock_no_poll,
+ .ioctl = pppox_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = sock_no_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = sock_no_mmap,
+};
+
+static int pppopns_create(struct net *net, struct socket *sock)
+{
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppopns_proto);
+ if (!sk)
+ return -ENOMEM;
+
+ sock_init_data(sock, sk);
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppopns_proto_ops;
+ sk->sk_protocol = PX_PROTO_OPNS;
+ sk->sk_state = PPPOX_NONE;
+ return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppopns_pppox_proto = {
+ .create = pppopns_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init pppopns_init(void)
+{
+ int error;
+
+ error = proto_register(&pppopns_proto, 0);
+ if (error)
+ return error;
+
+ error = register_pppox_proto(PX_PROTO_OPNS, &pppopns_pppox_proto);
+ if (error)
+ proto_unregister(&pppopns_proto);
+ else
+ skb_queue_head_init(&delivery_queue);
+ return error;
+}
+
+static void __exit pppopns_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OPNS);
+ proto_unregister(&pppopns_proto);
+}
+
+module_init(pppopns_init);
+module_exit(pppopns_exit);
+
+MODULE_DESCRIPTION("PPP on PPTP Network Server (PPPoPNS)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5824971..aeff706 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1898,6 +1898,12 @@
int vnet_hdr_sz;
int ret;
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+ if (cmd != TUNGETIFF && !capable(CAP_NET_ADMIN)) {
+ return -EPERM;
+ }
+#endif
+
if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index f8f0156..5b0a49c 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -264,6 +264,11 @@
To compile this driver as a module, choose M here: the module
will be called mwl8k. If unsure, say N.
+config WIFI_CONTROL_FUNC
+ bool "Enable WiFi control function abstraction"
+ help
+ Enables Power/Reset/Carddetect function abstraction
+
source "drivers/net/wireless/ath/Kconfig"
source "drivers/net/wireless/b43/Kconfig"
source "drivers/net/wireless/b43legacy/Kconfig"
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 5c9736a..008b4d9 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -3244,6 +3244,14 @@
struct ath6kl_vif *vif = netdev_priv(dev);
u16 interval;
int ret, rssi_thold;
+ int n_match_sets = request->n_match_sets;
+
+ /* If there's a matchset w/o an SSID, then assume it's just for
+ * the RSSI (nothing else is currently supported) and ignore it.
+ * The device only supports a global RSSI filter that we set below.
+ */
+ if (n_match_sets == 1 && !request->match_sets[0].ssid.ssid_len)
+ n_match_sets = 0;
if (ar->state != ATH6KL_STATE_ON)
return -EIO;
@@ -3256,11 +3264,11 @@
ret = ath6kl_set_probed_ssids(ar, vif, request->ssids,
request->n_ssids,
request->match_sets,
- request->n_match_sets);
+ n_match_sets);
if (ret < 0)
return ret;
- if (!request->n_match_sets) {
+ if (!n_match_sets) {
ret = ath6kl_wmi_bssfilter_cmd(ar->wmi, vif->fw_vif_idx,
ALL_BSS_FILTER, 0);
if (ret < 0)
@@ -3274,12 +3282,12 @@
if (test_bit(ATH6KL_FW_CAPABILITY_RSSI_SCAN_THOLD,
ar->fw_capabilities)) {
- if (request->rssi_thold <= NL80211_SCAN_RSSI_THOLD_OFF)
+ if (request->min_rssi_thold <= NL80211_SCAN_RSSI_THOLD_OFF)
rssi_thold = 0;
- else if (request->rssi_thold < -127)
+ else if (request->min_rssi_thold < -127)
rssi_thold = -127;
else
- rssi_thold = request->rssi_thold;
+ rssi_thold = request->min_rssi_thold;
ret = ath6kl_wmi_set_rssi_filter_cmd(ar->wmi, vif->fw_vif_idx,
rssi_thold);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 1187737..8c5b334 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -661,36 +661,66 @@
return 0;
}
+/*
+ * Convert configs to something easy to use in C code
+ */
+#if defined(CONFIG_CMDLINE_FORCE)
+static const int overwrite_incoming_cmdline = 1;
+static const int read_dt_cmdline;
+static const int concat_cmdline;
+#elif defined(CONFIG_CMDLINE_EXTEND)
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline = 1;
+#else /* CMDLINE_FROM_BOOTLOADER */
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline;
+#endif
+
+#ifdef CONFIG_CMDLINE
+static const char *config_cmdline = CONFIG_CMDLINE;
+#else
+static const char *config_cmdline = "";
+#endif
+
int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data)
{
- unsigned long l;
- char *p;
+ unsigned long l = 0;
+ char *p = NULL;
+ char *cmdline = data;
pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
- if (depth != 1 || !data ||
+ if (depth != 1 || !cmdline ||
(strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
return 0;
early_init_dt_check_for_initrd(node);
- /* Retrieve command line */
- p = of_get_flat_dt_prop(node, "bootargs", &l);
- if (p != NULL && l > 0)
- strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE));
+ /* Put CONFIG_CMDLINE in if forced or if data had nothing in it to start */
+ if (overwrite_incoming_cmdline || !cmdline[0])
+ strlcpy(cmdline, config_cmdline, COMMAND_LINE_SIZE);
- /*
- * CONFIG_CMDLINE is meant to be a default in case nothing else
- * managed to set the command line, unless CONFIG_CMDLINE_FORCE
- * is set in which case we override whatever was found earlier.
- */
-#ifdef CONFIG_CMDLINE
-#ifndef CONFIG_CMDLINE_FORCE
- if (!((char *)data)[0])
-#endif
- strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif /* CONFIG_CMDLINE */
+ /* Retrieve command line unless forcing */
+ if (read_dt_cmdline)
+ p = of_get_flat_dt_prop(node, "bootargs", &l);
+
+ if (p != NULL && l > 0) {
+ if (concat_cmdline) {
+ int cmdline_len;
+ int copy_len;
+ strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+ cmdline_len = strlen(cmdline);
+ copy_len = COMMAND_LINE_SIZE - cmdline_len - 1;
+ copy_len = min((int)l, copy_len);
+ strncpy(cmdline + cmdline_len, p, copy_len);
+ cmdline[cmdline_len + copy_len] = '\0';
+ } else {
+ strlcpy(cmdline, p, min((int)l, COMMAND_LINE_SIZE));
+ }
+ }
pr_debug("Command line is: %s\n", (char*)data);
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 1c517c3..082d3c2 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -67,23 +67,40 @@
static void power_supply_changed_work(struct work_struct *work)
{
+ unsigned long flags;
struct power_supply *psy = container_of(work, struct power_supply,
changed_work);
dev_dbg(psy->dev, "%s\n", __func__);
- class_for_each_device(power_supply_class, NULL, psy,
- __power_supply_changed_work);
+ spin_lock_irqsave(&psy->changed_lock, flags);
+ if (psy->changed) {
+ psy->changed = false;
+ spin_unlock_irqrestore(&psy->changed_lock, flags);
- power_supply_update_leds(psy);
+ class_for_each_device(power_supply_class, NULL, psy,
+ __power_supply_changed_work);
- kobject_uevent(&psy->dev->kobj, KOBJ_CHANGE);
+ power_supply_update_leds(psy);
+
+ kobject_uevent(&psy->dev->kobj, KOBJ_CHANGE);
+ spin_lock_irqsave(&psy->changed_lock, flags);
+ }
+ if (!psy->changed)
+ pm_relax(psy->dev);
+ spin_unlock_irqrestore(&psy->changed_lock, flags);
}
void power_supply_changed(struct power_supply *psy)
{
+ unsigned long flags;
+
dev_dbg(psy->dev, "%s\n", __func__);
+ spin_lock_irqsave(&psy->changed_lock, flags);
+ psy->changed = true;
+ pm_stay_awake(psy->dev);
+ spin_unlock_irqrestore(&psy->changed_lock, flags);
schedule_work(&psy->changed_work);
}
EXPORT_SYMBOL_GPL(power_supply_changed);
@@ -504,6 +521,11 @@
if (rc)
goto device_add_failed;
+ spin_lock_init(&psy->changed_lock);
+ rc = device_init_wakeup(dev, true);
+ if (rc)
+ goto wakeup_init_failed;
+
rc = psy_register_thermal(psy);
if (rc)
goto register_thermal_failed;
@@ -525,6 +547,7 @@
register_cooler_failed:
psy_unregister_thermal(psy);
register_thermal_failed:
+wakeup_init_failed:
device_del(dev);
kobject_set_name_failed:
device_add_failed:
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 29178f7..1f7d79b 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -105,7 +105,10 @@
else if (off >= POWER_SUPPLY_PROP_MODEL_NAME)
return sprintf(buf, "%s\n", value.strval);
- return sprintf(buf, "%d\n", value.intval);
+ if (off == POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT)
+ return sprintf(buf, "%lld\n", value.int64val);
+ else
+ return sprintf(buf, "%d\n", value.intval);
}
static ssize_t power_supply_store_property(struct device *dev,
@@ -189,6 +192,12 @@
POWER_SUPPLY_ATTR(time_to_full_avg),
POWER_SUPPLY_ATTR(type),
POWER_SUPPLY_ATTR(scope),
+ /* Local extensions */
+ POWER_SUPPLY_ATTR(usb_hc),
+ POWER_SUPPLY_ATTR(usb_otg),
+ POWER_SUPPLY_ATTR(charge_enabled),
+ /* Local extensions of type int64_t */
+ POWER_SUPPLY_ATTR(charge_counter_ext),
/* Properties of type `const char *' */
POWER_SUPPLY_ATTR(model_name),
POWER_SUPPLY_ATTR(manufacturer),
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index 50204d4..8acc5c6 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -45,6 +45,42 @@
/* Total number of RTC registers needed to set time*/
#define PALMAS_NUM_TIME_REGS (PALMAS_YEARS_REG - PALMAS_SECONDS_REG + 1)
+/*
+ * Special bin2bcd mapping to deal with bcd storage of year.
+ *
+ * 0-69 -> 0xD0
+ * 70-99 (1970 - 1999) -> 0xD0 - 0xF9 (correctly rolls to 0x00)
+ * 100-199 (2000 - 2099) -> 0x00 - 0x99 (does not roll to 0xA0 :-( )
+ * 200-229 (2100 - 2129) -> 0xA0 - 0xC9 (really for completeness)
+ * 230- -> 0xC9
+ *
+ * Confirmed: the only transition that does not work correctly for this rtc
+ * clock is the transition from 2099 to 2100, it proceeds to 2000. We will
+ * accept this issue since the clock retains and transitions the year correctly
+ * in all other conditions.
+ */
+static unsigned char year_bin2bcd(int val)
+{
+ if (val < 70)
+ return 0xD0;
+ if (val < 100)
+ return bin2bcd(val - 20) | 0x80; /* KISS leverage of bin2bcd */
+ if (val >= 230)
+ return 0xC9;
+ if (val >= 200)
+ return bin2bcd(val - 180) | 0x80;
+ return bin2bcd(val - 100);
+}
+
+static int year_bcd2bin(unsigned char val)
+{
+ if (val >= 0xD0)
+ return bcd2bin(val & 0x7F) + 20;
+ if (val >= 0xA0)
+ return bcd2bin(val & 0x7F) + 180;
+ return bcd2bin(val) + 100;
+}
+
static int palmas_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
unsigned char rtc_data[PALMAS_NUM_TIME_REGS];
@@ -71,7 +107,7 @@
tm->tm_hour = bcd2bin(rtc_data[2]);
tm->tm_mday = bcd2bin(rtc_data[3]);
tm->tm_mon = bcd2bin(rtc_data[4]) - 1;
- tm->tm_year = bcd2bin(rtc_data[5]) + 100;
+ tm->tm_year = year_bcd2bin(rtc_data[5]);
return ret;
}
@@ -87,7 +123,7 @@
rtc_data[2] = bin2bcd(tm->tm_hour);
rtc_data[3] = bin2bcd(tm->tm_mday);
rtc_data[4] = bin2bcd(tm->tm_mon + 1);
- rtc_data[5] = bin2bcd(tm->tm_year - 100);
+ rtc_data[5] = year_bin2bcd(tm->tm_year);
/* Stop RTC while updating the RTC time registers */
ret = palmas_update_bits(palmas, PALMAS_RTC_BASE, PALMAS_RTC_CTRL_REG,
@@ -142,7 +178,7 @@
alm->time.tm_hour = bcd2bin(alarm_data[2]);
alm->time.tm_mday = bcd2bin(alarm_data[3]);
alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1;
- alm->time.tm_year = bcd2bin(alarm_data[5]) + 100;
+ alm->time.tm_year = year_bcd2bin(alarm_data[5]);
ret = palmas_read(palmas, PALMAS_RTC_BASE, PALMAS_RTC_INTERRUPTS_REG,
&int_val);
@@ -173,7 +209,7 @@
alarm_data[2] = bin2bcd(alm->time.tm_hour);
alarm_data[3] = bin2bcd(alm->time.tm_mday);
alarm_data[4] = bin2bcd(alm->time.tm_mon + 1);
- alarm_data[5] = bin2bcd(alm->time.tm_year - 100);
+ alarm_data[5] = year_bin2bcd(alm->time.tm_year);
ret = palmas_bulk_write(palmas, PALMAS_RTC_BASE,
PALMAS_ALARM_SECONDS_REG, alarm_data, PALMAS_NUM_TIME_REGS);
@@ -318,7 +354,7 @@
};
#ifdef CONFIG_OF
-static struct of_device_id of_palmas_rtc_match[] = {
+static const struct of_device_id of_palmas_rtc_match[] = {
{ .compatible = "ti,palmas-rtc"},
{ },
};
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index aefe820..25c8bff 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -72,10 +72,6 @@
source "drivers/staging/iio/Kconfig"
-source "drivers/staging/zsmalloc/Kconfig"
-
-source "drivers/staging/zram/Kconfig"
-
source "drivers/staging/wlags49_h2/Kconfig"
source "drivers/staging/wlags49_h25/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 415772e..f9d86a4 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -30,8 +30,6 @@
obj-$(CONFIG_VME_BUS) += vme/
obj-$(CONFIG_DX_SEP) += sep/
obj-$(CONFIG_IIO) += iio/
-obj-$(CONFIG_ZRAM) += zram/
-obj-$(CONFIG_ZSMALLOC) += zsmalloc/
obj-$(CONFIG_WLAGS49_H2) += wlags49_h2/
obj-$(CONFIG_WLAGS49_H25) += wlags49_h25/
obj-$(CONFIG_FB_SM7XX) += sm7xxfb/
diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig
index c0c95be..b3c054e 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -8,17 +8,6 @@
if ANDROID
-config ANDROID_BINDER_IPC
- bool "Android Binder IPC Driver"
- default n
- ---help---
- Binder is used in Android for both communication between processes,
- and remote method invocation.
-
- This means one Android process can call a method/routine in another
- Android process, using Binder to identify, invoke and pass arguments
- between said processes.
-
config ASHMEM
bool "Enable the Anonymous Shared Memory Subsystem"
default n
@@ -31,23 +20,6 @@
It is, in theory, a good memory allocator for low-memory devices,
because it can discard shared memory units when under memory pressure.
-config ANDROID_LOGGER
- tristate "Android log driver"
- default n
- ---help---
- This adds support for system-wide logging using four log buffers.
-
- These are:
-
- 1: main
- 2: events
- 3: radio
- 4: system
-
- Log reading and writing is performed via normal Linux reads and
- optimized writes. This optimization avoids logging having too
- much overhead in the system.
-
config ANDROID_TIMED_OUTPUT
bool "Timed output class driver"
default y
@@ -63,14 +35,14 @@
---help---
Registers processes to be killed when memory is low
-config ANDROID_INTF_ALARM_DEV
- bool "Android alarm driver"
- depends on RTC_CLASS
- default n
+config ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+ bool "Android Low Memory Killer: detect oom_adj values"
+ depends on ANDROID_LOW_MEMORY_KILLER
+ default y
---help---
- Provides non-wakeup and rtc backed wakeup alarms based on rtc or
- elapsed realtime, and a non-wakeup alarm on the monotonic clock.
- Also exports the alarm interface to user-space.
+ Detect oom_adj values written to
+ /sys/module/lowmemorykiller/parameters/adj and convert them
+ to oom_score_adj values.
config SYNC
bool "Synchronization framework"
@@ -99,6 +71,10 @@
*WARNING* improper use of this can result in deadlocking kernel
drivers from userspace.
+source "drivers/staging/android/ion/Kconfig"
+
+source "drivers/staging/android/fiq_debugger/Kconfig"
+
endif # if ANDROID
endmenu
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index c136299..30ba2f0 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -1,11 +1,11 @@
ccflags-y += -I$(src) # needed for trace events
-obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o
+obj-y += ion/
+obj-$(CONFIG_FIQ_DEBUGGER) += fiq_debugger/
+
obj-$(CONFIG_ASHMEM) += ashmem.o
-obj-$(CONFIG_ANDROID_LOGGER) += logger.o
obj-$(CONFIG_ANDROID_TIMED_OUTPUT) += timed_output.o
obj-$(CONFIG_ANDROID_TIMED_GPIO) += timed_gpio.o
obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER) += lowmemorykiller.o
-obj-$(CONFIG_ANDROID_INTF_ALARM_DEV) += alarm-dev.o
obj-$(CONFIG_SYNC) += sync.o
obj-$(CONFIG_SW_SYNC) += sw_sync.o
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
deleted file mode 100644
index b15fb0d..0000000
--- a/drivers/staging/android/TODO
+++ /dev/null
@@ -1,10 +0,0 @@
-TODO:
- - checkpatch.pl cleanups
- - sparse fixes
- - rename files to be not so "generic"
- - make sure things build as modules properly
- - add proper arch dependencies as needed
- - audit userspace interfaces to make sure they are sane
-
-Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
-Brian Swetland <swetland@google.com>
diff --git a/drivers/staging/android/alarm-dev.c b/drivers/staging/android/alarm-dev.c
deleted file mode 100644
index 6dc27da..0000000
--- a/drivers/staging/android/alarm-dev.c
+++ /dev/null
@@ -1,443 +0,0 @@
-/* drivers/rtc/alarm-dev.c
- *
- * Copyright (C) 2007-2009 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/time.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/miscdevice.h>
-#include <linux/fs.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
-#include <linux/alarmtimer.h>
-#include "android_alarm.h"
-
-#define ANDROID_ALARM_PRINT_INFO (1U << 0)
-#define ANDROID_ALARM_PRINT_IO (1U << 1)
-#define ANDROID_ALARM_PRINT_INT (1U << 2)
-
-static int debug_mask = ANDROID_ALARM_PRINT_INFO;
-module_param_named(debug_mask, debug_mask, int, S_IRUGO | S_IWUSR | S_IWGRP);
-
-#define alarm_dbg(debug_level_mask, fmt, ...) \
-do { \
- if (debug_mask & ANDROID_ALARM_PRINT_##debug_level_mask) \
- pr_info(fmt, ##__VA_ARGS__); \
-} while (0)
-
-#define ANDROID_ALARM_WAKEUP_MASK ( \
- ANDROID_ALARM_RTC_WAKEUP_MASK | \
- ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK)
-
-static int alarm_opened;
-static DEFINE_SPINLOCK(alarm_slock);
-static struct wakeup_source alarm_wake_lock;
-static DECLARE_WAIT_QUEUE_HEAD(alarm_wait_queue);
-static uint32_t alarm_pending;
-static uint32_t alarm_enabled;
-static uint32_t wait_pending;
-
-struct devalarm {
- union {
- struct hrtimer hrt;
- struct alarm alrm;
- } u;
- enum android_alarm_type type;
-};
-
-static struct devalarm alarms[ANDROID_ALARM_TYPE_COUNT];
-
-
-static int is_wakeup(enum android_alarm_type type)
-{
- return (type == ANDROID_ALARM_RTC_WAKEUP ||
- type == ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP);
-}
-
-
-static void devalarm_start(struct devalarm *alrm, ktime_t exp)
-{
- if (is_wakeup(alrm->type))
- alarm_start(&alrm->u.alrm, exp);
- else
- hrtimer_start(&alrm->u.hrt, exp, HRTIMER_MODE_ABS);
-}
-
-
-static int devalarm_try_to_cancel(struct devalarm *alrm)
-{
- if (is_wakeup(alrm->type))
- return alarm_try_to_cancel(&alrm->u.alrm);
- return hrtimer_try_to_cancel(&alrm->u.hrt);
-}
-
-static void devalarm_cancel(struct devalarm *alrm)
-{
- if (is_wakeup(alrm->type))
- alarm_cancel(&alrm->u.alrm);
- else
- hrtimer_cancel(&alrm->u.hrt);
-}
-
-static void alarm_clear(enum android_alarm_type alarm_type)
-{
- uint32_t alarm_type_mask = 1U << alarm_type;
- unsigned long flags;
-
- spin_lock_irqsave(&alarm_slock, flags);
- alarm_dbg(IO, "alarm %d clear\n", alarm_type);
- devalarm_try_to_cancel(&alarms[alarm_type]);
- if (alarm_pending) {
- alarm_pending &= ~alarm_type_mask;
- if (!alarm_pending && !wait_pending)
- __pm_relax(&alarm_wake_lock);
- }
- alarm_enabled &= ~alarm_type_mask;
- spin_unlock_irqrestore(&alarm_slock, flags);
-
-}
-
-static void alarm_set(enum android_alarm_type alarm_type,
- struct timespec *ts)
-{
- uint32_t alarm_type_mask = 1U << alarm_type;
- unsigned long flags;
-
- spin_lock_irqsave(&alarm_slock, flags);
- alarm_dbg(IO, "alarm %d set %ld.%09ld\n",
- alarm_type, ts->tv_sec, ts->tv_nsec);
- alarm_enabled |= alarm_type_mask;
- devalarm_start(&alarms[alarm_type], timespec_to_ktime(*ts));
- spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-static int alarm_wait(void)
-{
- unsigned long flags;
- int rv = 0;
-
- spin_lock_irqsave(&alarm_slock, flags);
- alarm_dbg(IO, "alarm wait\n");
- if (!alarm_pending && wait_pending) {
- __pm_relax(&alarm_wake_lock);
- wait_pending = 0;
- }
- spin_unlock_irqrestore(&alarm_slock, flags);
-
- rv = wait_event_interruptible(alarm_wait_queue, alarm_pending);
- if (rv)
- return rv;
-
- spin_lock_irqsave(&alarm_slock, flags);
- rv = alarm_pending;
- wait_pending = 1;
- alarm_pending = 0;
- spin_unlock_irqrestore(&alarm_slock, flags);
-
- return rv;
-}
-
-static int alarm_set_rtc(struct timespec *ts)
-{
- struct rtc_time new_rtc_tm;
- struct rtc_device *rtc_dev;
- unsigned long flags;
- int rv = 0;
-
- rtc_time_to_tm(ts->tv_sec, &new_rtc_tm);
- rtc_dev = alarmtimer_get_rtcdev();
- rv = do_settimeofday(ts);
- if (rv < 0)
- return rv;
- if (rtc_dev)
- rv = rtc_set_time(rtc_dev, &new_rtc_tm);
-
- spin_lock_irqsave(&alarm_slock, flags);
- alarm_pending |= ANDROID_ALARM_TIME_CHANGE_MASK;
- wake_up(&alarm_wait_queue);
- spin_unlock_irqrestore(&alarm_slock, flags);
-
- return rv;
-}
-
-static int alarm_get_time(enum android_alarm_type alarm_type,
- struct timespec *ts)
-{
- int rv = 0;
-
- switch (alarm_type) {
- case ANDROID_ALARM_RTC_WAKEUP:
- case ANDROID_ALARM_RTC:
- getnstimeofday(ts);
- break;
- case ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP:
- case ANDROID_ALARM_ELAPSED_REALTIME:
- get_monotonic_boottime(ts);
- break;
- case ANDROID_ALARM_SYSTEMTIME:
- ktime_get_ts(ts);
- break;
- default:
- rv = -EINVAL;
- }
- return rv;
-}
-
-static long alarm_do_ioctl(struct file *file, unsigned int cmd,
- struct timespec *ts)
-{
- int rv = 0;
- unsigned long flags;
- enum android_alarm_type alarm_type = ANDROID_ALARM_IOCTL_TO_TYPE(cmd);
-
- if (alarm_type >= ANDROID_ALARM_TYPE_COUNT)
- return -EINVAL;
-
- if (ANDROID_ALARM_BASE_CMD(cmd) != ANDROID_ALARM_GET_TIME(0)) {
- if ((file->f_flags & O_ACCMODE) == O_RDONLY)
- return -EPERM;
- if (file->private_data == NULL &&
- cmd != ANDROID_ALARM_SET_RTC) {
- spin_lock_irqsave(&alarm_slock, flags);
- if (alarm_opened) {
- spin_unlock_irqrestore(&alarm_slock, flags);
- return -EBUSY;
- }
- alarm_opened = 1;
- file->private_data = (void *)1;
- spin_unlock_irqrestore(&alarm_slock, flags);
- }
- }
-
- switch (ANDROID_ALARM_BASE_CMD(cmd)) {
- case ANDROID_ALARM_CLEAR(0):
- alarm_clear(alarm_type);
- break;
- case ANDROID_ALARM_SET(0):
- alarm_set(alarm_type, ts);
- break;
- case ANDROID_ALARM_SET_AND_WAIT(0):
- alarm_set(alarm_type, ts);
- /* fall though */
- case ANDROID_ALARM_WAIT:
- rv = alarm_wait();
- break;
- case ANDROID_ALARM_SET_RTC:
- rv = alarm_set_rtc(ts);
- break;
- case ANDROID_ALARM_GET_TIME(0):
- rv = alarm_get_time(alarm_type, ts);
- break;
-
- default:
- rv = -EINVAL;
- }
- return rv;
-}
-
-static long alarm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-
- struct timespec ts;
- int rv;
-
- switch (ANDROID_ALARM_BASE_CMD(cmd)) {
- case ANDROID_ALARM_SET_AND_WAIT(0):
- case ANDROID_ALARM_SET(0):
- case ANDROID_ALARM_SET_RTC:
- if (copy_from_user(&ts, (void __user *)arg, sizeof(ts)))
- return -EFAULT;
- break;
- }
-
- rv = alarm_do_ioctl(file, cmd, &ts);
- if (rv)
- return rv;
-
- switch (ANDROID_ALARM_BASE_CMD(cmd)) {
- case ANDROID_ALARM_GET_TIME(0):
- if (copy_to_user((void __user *)arg, &ts, sizeof(ts)))
- return -EFAULT;
- break;
- }
-
- return 0;
-}
-#ifdef CONFIG_COMPAT
-static long alarm_compat_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
-
- struct timespec ts;
- int rv;
-
- switch (ANDROID_ALARM_BASE_CMD(cmd)) {
- case ANDROID_ALARM_SET_AND_WAIT_COMPAT(0):
- case ANDROID_ALARM_SET_COMPAT(0):
- case ANDROID_ALARM_SET_RTC_COMPAT:
- if (compat_get_timespec(&ts, (void __user *)arg))
- return -EFAULT;
- /* fall through */
- case ANDROID_ALARM_GET_TIME_COMPAT(0):
- cmd = ANDROID_ALARM_COMPAT_TO_NORM(cmd);
- break;
- }
-
- rv = alarm_do_ioctl(file, cmd, &ts);
- if (rv)
- return rv;
-
- switch (ANDROID_ALARM_BASE_CMD(cmd)) {
- case ANDROID_ALARM_GET_TIME(0): /* NOTE: we modified cmd above */
- if (compat_put_timespec(&ts, (void __user *)arg))
- return -EFAULT;
- break;
- }
-
- return 0;
-}
-#endif
-
-static int alarm_open(struct inode *inode, struct file *file)
-{
- file->private_data = NULL;
- return 0;
-}
-
-static int alarm_release(struct inode *inode, struct file *file)
-{
- int i;
- unsigned long flags;
-
- spin_lock_irqsave(&alarm_slock, flags);
- if (file->private_data) {
- for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
- uint32_t alarm_type_mask = 1U << i;
- if (alarm_enabled & alarm_type_mask) {
- alarm_dbg(INFO,
- "%s: clear alarm, pending %d\n",
- __func__,
- !!(alarm_pending & alarm_type_mask));
- alarm_enabled &= ~alarm_type_mask;
- }
- spin_unlock_irqrestore(&alarm_slock, flags);
- devalarm_cancel(&alarms[i]);
- spin_lock_irqsave(&alarm_slock, flags);
- }
- if (alarm_pending | wait_pending) {
- if (alarm_pending)
- alarm_dbg(INFO, "%s: clear pending alarms %x\n",
- __func__, alarm_pending);
- __pm_relax(&alarm_wake_lock);
- wait_pending = 0;
- alarm_pending = 0;
- }
- alarm_opened = 0;
- }
- spin_unlock_irqrestore(&alarm_slock, flags);
- return 0;
-}
-
-static void devalarm_triggered(struct devalarm *alarm)
-{
- unsigned long flags;
- uint32_t alarm_type_mask = 1U << alarm->type;
-
- alarm_dbg(INT, "%s: type %d\n", __func__, alarm->type);
- spin_lock_irqsave(&alarm_slock, flags);
- if (alarm_enabled & alarm_type_mask) {
- __pm_wakeup_event(&alarm_wake_lock, 5000); /* 5secs */
- alarm_enabled &= ~alarm_type_mask;
- alarm_pending |= alarm_type_mask;
- wake_up(&alarm_wait_queue);
- }
- spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-
-static enum hrtimer_restart devalarm_hrthandler(struct hrtimer *hrt)
-{
- struct devalarm *devalrm = container_of(hrt, struct devalarm, u.hrt);
-
- devalarm_triggered(devalrm);
- return HRTIMER_NORESTART;
-}
-
-static enum alarmtimer_restart devalarm_alarmhandler(struct alarm *alrm,
- ktime_t now)
-{
- struct devalarm *devalrm = container_of(alrm, struct devalarm, u.alrm);
-
- devalarm_triggered(devalrm);
- return ALARMTIMER_NORESTART;
-}
-
-
-static const struct file_operations alarm_fops = {
- .owner = THIS_MODULE,
- .unlocked_ioctl = alarm_ioctl,
- .open = alarm_open,
- .release = alarm_release,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = alarm_compat_ioctl,
-#endif
-};
-
-static struct miscdevice alarm_device = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "alarm",
- .fops = &alarm_fops,
-};
-
-static int __init alarm_dev_init(void)
-{
- int err;
- int i;
-
- err = misc_register(&alarm_device);
- if (err)
- return err;
-
- alarm_init(&alarms[ANDROID_ALARM_RTC_WAKEUP].u.alrm,
- ALARM_REALTIME, devalarm_alarmhandler);
- hrtimer_init(&alarms[ANDROID_ALARM_RTC].u.hrt,
- CLOCK_REALTIME, HRTIMER_MODE_ABS);
- alarm_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP].u.alrm,
- ALARM_BOOTTIME, devalarm_alarmhandler);
- hrtimer_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME].u.hrt,
- CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
- hrtimer_init(&alarms[ANDROID_ALARM_SYSTEMTIME].u.hrt,
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-
- for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
- alarms[i].type = i;
- if (!is_wakeup(i))
- alarms[i].u.hrt.function = devalarm_hrthandler;
- }
-
- wakeup_source_init(&alarm_wake_lock, "alarm");
- return 0;
-}
-
-static void __exit alarm_dev_exit(void)
-{
- misc_deregister(&alarm_device);
- wakeup_source_trash(&alarm_wake_lock);
-}
-
-module_init(alarm_dev_init);
-module_exit(alarm_dev_exit);
-
diff --git a/drivers/staging/android/android_alarm.h b/drivers/staging/android/android_alarm.h
deleted file mode 100644
index 4fd32f3..0000000
--- a/drivers/staging/android/android_alarm.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/* include/linux/android_alarm.h
- *
- * Copyright (C) 2006-2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _LINUX_ANDROID_ALARM_H
-#define _LINUX_ANDROID_ALARM_H
-
-#include <linux/ioctl.h>
-#include <linux/time.h>
-#include <linux/compat.h>
-
-enum android_alarm_type {
- /* return code bit numbers or set alarm arg */
- ANDROID_ALARM_RTC_WAKEUP,
- ANDROID_ALARM_RTC,
- ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
- ANDROID_ALARM_ELAPSED_REALTIME,
- ANDROID_ALARM_SYSTEMTIME,
-
- ANDROID_ALARM_TYPE_COUNT,
-
- /* return code bit numbers */
- /* ANDROID_ALARM_TIME_CHANGE = 16 */
-};
-
-enum android_alarm_return_flags {
- ANDROID_ALARM_RTC_WAKEUP_MASK = 1U << ANDROID_ALARM_RTC_WAKEUP,
- ANDROID_ALARM_RTC_MASK = 1U << ANDROID_ALARM_RTC,
- ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK =
- 1U << ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
- ANDROID_ALARM_ELAPSED_REALTIME_MASK =
- 1U << ANDROID_ALARM_ELAPSED_REALTIME,
- ANDROID_ALARM_SYSTEMTIME_MASK = 1U << ANDROID_ALARM_SYSTEMTIME,
- ANDROID_ALARM_TIME_CHANGE_MASK = 1U << 16
-};
-
-/* Disable alarm */
-#define ANDROID_ALARM_CLEAR(type) _IO('a', 0 | ((type) << 4))
-
-/* Ack last alarm and wait for next */
-#define ANDROID_ALARM_WAIT _IO('a', 1)
-
-#define ALARM_IOW(c, type, size) _IOW('a', (c) | ((type) << 4), size)
-/* Set alarm */
-#define ANDROID_ALARM_SET(type) ALARM_IOW(2, type, struct timespec)
-#define ANDROID_ALARM_SET_AND_WAIT(type) ALARM_IOW(3, type, struct timespec)
-#define ANDROID_ALARM_GET_TIME(type) ALARM_IOW(4, type, struct timespec)
-#define ANDROID_ALARM_SET_RTC _IOW('a', 5, struct timespec)
-#define ANDROID_ALARM_BASE_CMD(cmd) (cmd & ~(_IOC(0, 0, 0xf0, 0)))
-#define ANDROID_ALARM_IOCTL_TO_TYPE(cmd) (_IOC_NR(cmd) >> 4)
-
-
-#ifdef CONFIG_COMPAT
-#define ANDROID_ALARM_SET_COMPAT(type) ALARM_IOW(2, type, \
- struct compat_timespec)
-#define ANDROID_ALARM_SET_AND_WAIT_COMPAT(type) ALARM_IOW(3, type, \
- struct compat_timespec)
-#define ANDROID_ALARM_GET_TIME_COMPAT(type) ALARM_IOW(4, type, \
- struct compat_timespec)
-#define ANDROID_ALARM_SET_RTC_COMPAT _IOW('a', 5, \
- struct compat_timespec)
-#define ANDROID_ALARM_IOCTL_NR(cmd) (_IOC_NR(cmd) & ((1<<4)-1))
-#define ANDROID_ALARM_COMPAT_TO_NORM(cmd) \
- ALARM_IOW(ANDROID_ALARM_IOCTL_NR(cmd), \
- ANDROID_ALARM_IOCTL_TO_TYPE(cmd), \
- struct timespec)
-
-#endif
-
-#endif
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index e681bdd..9ab0320 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -224,21 +224,29 @@
/* If size is not set, or set to 0, always return EOF. */
if (asma->size == 0)
- goto out;
+ goto out_unlock;
if (!asma->file) {
ret = -EBADF;
- goto out;
+ goto out_unlock;
}
+ mutex_unlock(&ashmem_mutex);
+
+ /*
+ * asma and asma->file are used outside the lock here. We assume
+ * once asma->file is set it will never be changed, and will not
+ * be destroyed until all references to the file are dropped and
+ * ashmem_release is called.
+ */
ret = asma->file->f_op->read(asma->file, buf, len, pos);
- if (ret < 0)
- goto out;
+ if (ret >= 0) {
+ /** Update backing file pos, since f_ops->read() doesn't */
+ asma->file->f_pos = *pos;
+ }
+ return ret;
- /** Update backing file pos, since f_ops->read() doesn't */
- asma->file->f_pos = *pos;
-
-out:
+out_unlock:
mutex_unlock(&ashmem_mutex);
return ret;
}
@@ -317,22 +325,14 @@
}
get_file(asma->file);
- /*
- * XXX - Reworked to use shmem_zero_setup() instead of
- * shmem_set_file while we're in staging. -jstultz
- */
- if (vma->vm_flags & VM_SHARED) {
- ret = shmem_zero_setup(vma);
- if (ret) {
- fput(asma->file);
- goto out;
- }
+ if (vma->vm_flags & VM_SHARED)
+ shmem_set_file(vma, asma->file);
+ else {
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = asma->file;
}
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = asma->file;
-
out:
mutex_unlock(&ashmem_mutex);
return ret;
@@ -363,12 +363,14 @@
if (!sc->nr_to_scan)
return lru_count;
- mutex_lock(&ashmem_mutex);
+ if (!mutex_trylock(&ashmem_mutex))
+ return -1;
+
list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
loff_t start = range->pgstart * PAGE_SIZE;
loff_t end = (range->pgend + 1) * PAGE_SIZE;
- do_fallocate(range->asma->file,
+ range->asma->file->f_op->fallocate(range->asma->file,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
start, end - start);
range->purged = ASHMEM_WAS_PURGED;
@@ -413,6 +415,7 @@
static int set_name(struct ashmem_area *asma, void __user *name)
{
+ int len;
int ret = 0;
char local_name[ASHMEM_NAME_LEN];
@@ -425,21 +428,19 @@
* variable that does not need protection and later copy the local
* variable to the structure member with lock held.
*/
- if (copy_from_user(local_name, name, ASHMEM_NAME_LEN))
- return -EFAULT;
-
+ len = strncpy_from_user(local_name, name, ASHMEM_NAME_LEN);
+ if (len < 0)
+ return len;
+ if (len == ASHMEM_NAME_LEN)
+ local_name[ASHMEM_NAME_LEN - 1] = '\0';
mutex_lock(&ashmem_mutex);
/* cannot change an existing mapping's name */
- if (unlikely(asma->file)) {
+ if (unlikely(asma->file))
ret = -EINVAL;
- goto out;
- }
- memcpy(asma->name + ASHMEM_NAME_PREFIX_LEN,
- local_name, ASHMEM_NAME_LEN);
- asma->name[ASHMEM_FULL_NAME_LEN-1] = '\0';
-out:
- mutex_unlock(&ashmem_mutex);
+ else
+ strcpy(asma->name + ASHMEM_NAME_PREFIX_LEN, local_name);
+ mutex_unlock(&ashmem_mutex);
return ret;
}
diff --git a/drivers/staging/android/ashmem.h b/drivers/staging/android/ashmem.h
index 8dc0f0d..5abcfd7 100644
--- a/drivers/staging/android/ashmem.h
+++ b/drivers/staging/android/ashmem.h
@@ -16,35 +16,7 @@
#include <linux/ioctl.h>
#include <linux/compat.h>
-#define ASHMEM_NAME_LEN 256
-
-#define ASHMEM_NAME_DEF "dev/ashmem"
-
-/* Return values from ASHMEM_PIN: Was the mapping purged while unpinned? */
-#define ASHMEM_NOT_PURGED 0
-#define ASHMEM_WAS_PURGED 1
-
-/* Return values from ASHMEM_GET_PIN_STATUS: Is the mapping pinned? */
-#define ASHMEM_IS_UNPINNED 0
-#define ASHMEM_IS_PINNED 1
-
-struct ashmem_pin {
- __u32 offset; /* offset into region, in bytes, page-aligned */
- __u32 len; /* length forward from offset, in bytes, page-aligned */
-};
-
-#define __ASHMEMIOC 0x77
-
-#define ASHMEM_SET_NAME _IOW(__ASHMEMIOC, 1, char[ASHMEM_NAME_LEN])
-#define ASHMEM_GET_NAME _IOR(__ASHMEMIOC, 2, char[ASHMEM_NAME_LEN])
-#define ASHMEM_SET_SIZE _IOW(__ASHMEMIOC, 3, size_t)
-#define ASHMEM_GET_SIZE _IO(__ASHMEMIOC, 4)
-#define ASHMEM_SET_PROT_MASK _IOW(__ASHMEMIOC, 5, unsigned long)
-#define ASHMEM_GET_PROT_MASK _IO(__ASHMEMIOC, 6)
-#define ASHMEM_PIN _IOW(__ASHMEMIOC, 7, struct ashmem_pin)
-#define ASHMEM_UNPIN _IOW(__ASHMEMIOC, 8, struct ashmem_pin)
-#define ASHMEM_GET_PIN_STATUS _IO(__ASHMEMIOC, 9)
-#define ASHMEM_PURGE_ALL_CACHES _IO(__ASHMEMIOC, 10)
+#include "uapi/ashmem.h"
/* support of 32bit userspace on 64bit platforms */
#ifdef CONFIG_COMPAT
diff --git a/drivers/staging/android/fiq_debugger/Kconfig b/drivers/staging/android/fiq_debugger/Kconfig
new file mode 100644
index 0000000..56f7f99
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Kconfig
@@ -0,0 +1,49 @@
+config FIQ_DEBUGGER
+ bool "FIQ Mode Serial Debugger"
+ default n
+ depends on ARM || ARM64
+ help
+ The FIQ serial debugger can accept commands even when the
+ kernel is unresponsive due to being stuck with interrupts
+ disabled.
+
+config FIQ_DEBUGGER_NO_SLEEP
+ bool "Keep serial debugger active"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Enables the serial debugger at boot. Passing
+ fiq_debugger.no_sleep on the kernel commandline will
+ override this config option.
+
+config FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+ bool "Don't disable wakeup IRQ when debugger is active"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Don't disable the wakeup irq when enabling the uart clock. This will
+ cause extra interrupts, but it makes the serial debugger usable with
+ on some MSM radio builds that ignore the uart clock request in power
+ collapse.
+
+config FIQ_DEBUGGER_CONSOLE
+ bool "Console on FIQ Serial Debugger port"
+ depends on FIQ_DEBUGGER
+ default n
+ help
+ Enables a console so that printk messages are displayed on
+ the debugger serial port as the occur.
+
+config FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+ bool "Put the FIQ debugger into console mode by default"
+ depends on FIQ_DEBUGGER_CONSOLE
+ default n
+ help
+ If enabled, this puts the fiq debugger into console mode by default.
+ Otherwise, the fiq debugger will start out in debug mode.
+
+config FIQ_WATCHDOG
+ bool
+ select FIQ_DEBUGGER
+ select PSTORE_RAM
+ default n
diff --git a/drivers/staging/android/fiq_debugger/Makefile b/drivers/staging/android/fiq_debugger/Makefile
new file mode 100644
index 0000000..a7ca487
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Makefile
@@ -0,0 +1,4 @@
+obj-y += fiq_debugger.o
+obj-$(CONFIG_ARM) += fiq_debugger_arm.o
+obj-$(CONFIG_ARM64) += fiq_debugger_arm64.o
+obj-$(CONFIG_FIQ_WATCHDOG) += fiq_watchdog.o
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.c b/drivers/staging/android/fiq_debugger/fiq_debugger.c
new file mode 100644
index 0000000..1d73362
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.c
@@ -0,0 +1,1213 @@
+/*
+ * drivers/staging/android/fiq_debugger.c
+ *
+ * Serial Debugger Interface accessed through an FIQ interrupt.
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/console.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/kernel_stat.h>
+#include <linux/kmsg_dump.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/timer.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/wakelock.h>
+
+#ifdef CONFIG_FIQ_GLUE
+#include <asm/fiq_glue.h>
+#endif
+
+#include <linux/uaccess.h>
+
+#include "fiq_debugger.h"
+#include "fiq_debugger_priv.h"
+#include "fiq_debugger_ringbuf.h"
+
+#define DEBUG_MAX 64
+#define MAX_UNHANDLED_FIQ_COUNT 1000000
+
+#define MAX_FIQ_DEBUGGER_PORTS 4
+
+struct fiq_debugger_state {
+#ifdef CONFIG_FIQ_GLUE
+ struct fiq_glue_handler handler;
+#endif
+ struct fiq_debugger_output output;
+
+ int fiq;
+ int uart_irq;
+ int signal_irq;
+ int wakeup_irq;
+ bool wakeup_irq_no_set_wake;
+ struct clk *clk;
+ struct fiq_debugger_pdata *pdata;
+ struct platform_device *pdev;
+
+ char debug_cmd[DEBUG_MAX];
+ int debug_busy;
+ int debug_abort;
+
+ char debug_buf[DEBUG_MAX];
+ int debug_count;
+
+ bool no_sleep;
+ bool debug_enable;
+ bool ignore_next_wakeup_irq;
+ struct timer_list sleep_timer;
+ spinlock_t sleep_timer_lock;
+ bool uart_enabled;
+ struct wake_lock debugger_wake_lock;
+ bool console_enable;
+ int current_cpu;
+ atomic_t unhandled_fiq_count;
+ bool in_fiq;
+
+ struct work_struct work;
+ spinlock_t work_lock;
+ char work_cmd[DEBUG_MAX];
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+ spinlock_t console_lock;
+ struct console console;
+ struct tty_port tty_port;
+ struct fiq_debugger_ringbuf *tty_rbuf;
+ bool syslog_dumping;
+#endif
+
+ unsigned int last_irqs[NR_IRQS];
+ unsigned int last_local_timer_irqs[NR_CPUS];
+};
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+struct tty_driver *fiq_tty_driver;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_NO_SLEEP
+static bool initial_no_sleep = true;
+#else
+static bool initial_no_sleep;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+static bool initial_debug_enable = true;
+static bool initial_console_enable = true;
+#else
+static bool initial_debug_enable;
+static bool initial_console_enable;
+#endif
+
+static bool fiq_kgdb_enable;
+
+module_param_named(no_sleep, initial_no_sleep, bool, 0644);
+module_param_named(debug_enable, initial_debug_enable, bool, 0644);
+module_param_named(console_enable, initial_console_enable, bool, 0644);
+module_param_named(kgdb_enable, fiq_kgdb_enable, bool, 0644);
+
+#ifdef CONFIG_FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state) {}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state) {}
+#else
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state)
+{
+ if (state->wakeup_irq < 0)
+ return;
+ enable_irq(state->wakeup_irq);
+ if (!state->wakeup_irq_no_set_wake)
+ enable_irq_wake(state->wakeup_irq);
+}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state)
+{
+ if (state->wakeup_irq < 0)
+ return;
+ disable_irq_nosync(state->wakeup_irq);
+ if (!state->wakeup_irq_no_set_wake)
+ disable_irq_wake(state->wakeup_irq);
+}
+#endif
+
+static inline bool fiq_debugger_have_fiq(struct fiq_debugger_state *state)
+{
+ return (state->fiq >= 0);
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_force_irq(struct fiq_debugger_state *state)
+{
+ unsigned int irq = state->signal_irq;
+
+ if (WARN_ON(!fiq_debugger_have_fiq(state)))
+ return;
+ if (state->pdata->force_irq) {
+ state->pdata->force_irq(state->pdev, irq);
+ } else {
+ struct irq_chip *chip = irq_get_chip(irq);
+ if (chip && chip->irq_retrigger)
+ chip->irq_retrigger(irq_get_irq_data(irq));
+ }
+}
+#endif
+
+static void fiq_debugger_uart_enable(struct fiq_debugger_state *state)
+{
+ if (state->clk)
+ clk_enable(state->clk);
+ if (state->pdata->uart_enable)
+ state->pdata->uart_enable(state->pdev);
+}
+
+static void fiq_debugger_uart_disable(struct fiq_debugger_state *state)
+{
+ if (state->pdata->uart_disable)
+ state->pdata->uart_disable(state->pdev);
+ if (state->clk)
+ clk_disable(state->clk);
+}
+
+static void fiq_debugger_uart_flush(struct fiq_debugger_state *state)
+{
+ if (state->pdata->uart_flush)
+ state->pdata->uart_flush(state->pdev);
+}
+
+static void fiq_debugger_putc(struct fiq_debugger_state *state, char c)
+{
+ state->pdata->uart_putc(state->pdev, c);
+}
+
+static void fiq_debugger_puts(struct fiq_debugger_state *state, char *s)
+{
+ unsigned c;
+ while ((c = *s++)) {
+ if (c == '\n')
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, c);
+ }
+}
+
+static void fiq_debugger_prompt(struct fiq_debugger_state *state)
+{
+ fiq_debugger_puts(state, "debug> ");
+}
+
+static void fiq_debugger_dump_kernel_log(struct fiq_debugger_state *state)
+{
+ char buf[512];
+ size_t len;
+ struct kmsg_dumper dumper = { .active = true };
+
+
+ kmsg_dump_rewind_nolock(&dumper);
+ while (kmsg_dump_get_line_nolock(&dumper, true, buf,
+ sizeof(buf) - 1, &len)) {
+ buf[len] = 0;
+ fiq_debugger_puts(state, buf);
+ }
+}
+
+static void fiq_debugger_printf(struct fiq_debugger_output *output,
+ const char *fmt, ...)
+{
+ struct fiq_debugger_state *state;
+ char buf[256];
+ va_list ap;
+
+ state = container_of(output, struct fiq_debugger_state, output);
+ va_start(ap, fmt);
+ vsnprintf(buf, sizeof(buf), fmt, ap);
+ va_end(ap);
+
+ fiq_debugger_puts(state, buf);
+}
+
+/* Safe outside fiq context */
+static int fiq_debugger_printf_nfiq(void *cookie, const char *fmt, ...)
+{
+ struct fiq_debugger_state *state = cookie;
+ char buf[256];
+ va_list ap;
+ unsigned long irq_flags;
+
+ va_start(ap, fmt);
+ vsnprintf(buf, 128, fmt, ap);
+ va_end(ap);
+
+ local_irq_save(irq_flags);
+ fiq_debugger_puts(state, buf);
+ fiq_debugger_uart_flush(state);
+ local_irq_restore(irq_flags);
+ return state->debug_abort;
+}
+
+static void fiq_debugger_dump_irqs(struct fiq_debugger_state *state)
+{
+ int n;
+ struct irq_desc *desc;
+
+ fiq_debugger_printf(&state->output,
+ "irqnr total since-last status name\n");
+ for_each_irq_desc(n, desc) {
+ struct irqaction *act = desc->action;
+ if (!act && !kstat_irqs(n))
+ continue;
+ fiq_debugger_printf(&state->output, "%5d: %10u %11u %8x %s\n", n,
+ kstat_irqs(n),
+ kstat_irqs(n) - state->last_irqs[n],
+ desc->status_use_accessors,
+ (act && act->name) ? act->name : "???");
+ state->last_irqs[n] = kstat_irqs(n);
+ }
+}
+
+static void fiq_debugger_do_ps(struct fiq_debugger_state *state)
+{
+ struct task_struct *g;
+ struct task_struct *p;
+ unsigned task_state;
+ static const char stat_nam[] = "RSDTtZX";
+
+ fiq_debugger_printf(&state->output, "pid ppid prio task pc\n");
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ task_state = p->state ? __ffs(p->state) + 1 : 0;
+ fiq_debugger_printf(&state->output,
+ "%5d %5d %4d ", p->pid, p->parent->pid, p->prio);
+ fiq_debugger_printf(&state->output, "%-13.13s %c", p->comm,
+ task_state >= sizeof(stat_nam) ? '?' : stat_nam[task_state]);
+ if (task_state == TASK_RUNNING)
+ fiq_debugger_printf(&state->output, " running\n");
+ else
+ fiq_debugger_printf(&state->output, " %08lx\n",
+ thread_saved_pc(p));
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
+}
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+ state->syslog_dumping = true;
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+ state->syslog_dumping = false;
+}
+#else
+extern int do_syslog(int type, char __user *bug, int count);
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+ do_syslog(5 /* clear */, NULL, 0);
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+ fiq_debugger_dump_kernel_log(state);
+}
+#endif
+
+static void fiq_debugger_do_sysrq(struct fiq_debugger_state *state, char rq)
+{
+ if ((rq == 'g' || rq == 'G') && !fiq_kgdb_enable) {
+ fiq_debugger_printf(&state->output, "sysrq-g blocked\n");
+ return;
+ }
+ fiq_debugger_begin_syslog_dump(state);
+ handle_sysrq(rq);
+ fiq_debugger_end_syslog_dump(state);
+}
+
+#ifdef CONFIG_KGDB
+static void fiq_debugger_do_kgdb(struct fiq_debugger_state *state)
+{
+ if (!fiq_kgdb_enable) {
+ fiq_debugger_printf(&state->output, "kgdb through fiq debugger not enabled\n");
+ return;
+ }
+
+ fiq_debugger_printf(&state->output, "enabling console and triggering kgdb\n");
+ state->console_enable = true;
+ handle_sysrq('g');
+}
+#endif
+
+static void fiq_debugger_schedule_work(struct fiq_debugger_state *state,
+ char *cmd)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->work_lock, flags);
+ if (state->work_cmd[0] != '\0') {
+ fiq_debugger_printf(&state->output, "work command processor busy\n");
+ spin_unlock_irqrestore(&state->work_lock, flags);
+ return;
+ }
+
+ strlcpy(state->work_cmd, cmd, sizeof(state->work_cmd));
+ spin_unlock_irqrestore(&state->work_lock, flags);
+
+ schedule_work(&state->work);
+}
+
+static void fiq_debugger_work(struct work_struct *work)
+{
+ struct fiq_debugger_state *state;
+ char work_cmd[DEBUG_MAX];
+ char *cmd;
+ unsigned long flags;
+
+ state = container_of(work, struct fiq_debugger_state, work);
+
+ spin_lock_irqsave(&state->work_lock, flags);
+
+ strlcpy(work_cmd, state->work_cmd, sizeof(work_cmd));
+ state->work_cmd[0] = '\0';
+
+ spin_unlock_irqrestore(&state->work_lock, flags);
+
+ cmd = work_cmd;
+ if (!strncmp(cmd, "reboot", 6)) {
+ cmd += 6;
+ while (*cmd == ' ')
+ cmd++;
+ if (cmd != '\0')
+ kernel_restart(cmd);
+ else
+ kernel_restart(NULL);
+ } else {
+ fiq_debugger_printf(&state->output, "unknown work command '%s'\n",
+ work_cmd);
+ }
+}
+
+/* This function CANNOT be called in FIQ context */
+static void fiq_debugger_irq_exec(struct fiq_debugger_state *state, char *cmd)
+{
+ if (!strcmp(cmd, "ps"))
+ fiq_debugger_do_ps(state);
+ if (!strcmp(cmd, "sysrq"))
+ fiq_debugger_do_sysrq(state, 'h');
+ if (!strncmp(cmd, "sysrq ", 6))
+ fiq_debugger_do_sysrq(state, cmd[6]);
+#ifdef CONFIG_KGDB
+ if (!strcmp(cmd, "kgdb"))
+ fiq_debugger_do_kgdb(state);
+#endif
+ if (!strncmp(cmd, "reboot", 6))
+ fiq_debugger_schedule_work(state, cmd);
+}
+
+static void fiq_debugger_help(struct fiq_debugger_state *state)
+{
+ fiq_debugger_printf(&state->output,
+ "FIQ Debugger commands:\n"
+ " pc PC status\n"
+ " regs Register dump\n"
+ " allregs Extended Register dump\n"
+ " bt Stack trace\n");
+ fiq_debugger_printf(&state->output,
+ " reboot [<c>] Reboot with command <c>\n"
+ " reset [<c>] Hard reset with command <c>\n"
+ " irqs Interupt status\n"
+ " kmsg Kernel log\n"
+ " version Kernel version\n");
+ fiq_debugger_printf(&state->output,
+ " sleep Allow sleep while in FIQ\n"
+ " nosleep Disable sleep while in FIQ\n"
+ " console Switch terminal to console\n"
+ " cpu Current CPU\n"
+ " cpu <number> Switch to CPU<number>\n");
+ fiq_debugger_printf(&state->output,
+ " ps Process list\n"
+ " sysrq sysrq options\n"
+ " sysrq <param> Execute sysrq with <param>\n");
+#ifdef CONFIG_KGDB
+ fiq_debugger_printf(&state->output,
+ " kgdb Enter kernel debugger\n");
+#endif
+}
+
+static void fiq_debugger_take_affinity(void *info)
+{
+ struct fiq_debugger_state *state = info;
+ struct cpumask cpumask;
+
+ cpumask_clear(&cpumask);
+ cpumask_set_cpu(get_cpu(), &cpumask);
+
+ irq_set_affinity(state->uart_irq, &cpumask);
+}
+
+static void fiq_debugger_switch_cpu(struct fiq_debugger_state *state, int cpu)
+{
+ if (!fiq_debugger_have_fiq(state))
+ smp_call_function_single(cpu, fiq_debugger_take_affinity, state,
+ false);
+ state->current_cpu = cpu;
+}
+
+static bool fiq_debugger_fiq_exec(struct fiq_debugger_state *state,
+ const char *cmd, const struct pt_regs *regs,
+ void *svc_sp)
+{
+ bool signal_helper = false;
+
+ if (!strcmp(cmd, "help") || !strcmp(cmd, "?")) {
+ fiq_debugger_help(state);
+ } else if (!strcmp(cmd, "pc")) {
+ fiq_debugger_dump_pc(&state->output, regs);
+ } else if (!strcmp(cmd, "regs")) {
+ fiq_debugger_dump_regs(&state->output, regs);
+ } else if (!strcmp(cmd, "allregs")) {
+ fiq_debugger_dump_allregs(&state->output, regs);
+ } else if (!strcmp(cmd, "bt")) {
+ fiq_debugger_dump_stacktrace(&state->output, regs, 100, svc_sp);
+ } else if (!strncmp(cmd, "reset", 5)) {
+ cmd += 5;
+ while (*cmd == ' ')
+ cmd++;
+ if (*cmd) {
+ char tmp_cmd[32];
+ strlcpy(tmp_cmd, cmd, sizeof(tmp_cmd));
+ machine_restart(tmp_cmd);
+ } else {
+ machine_restart(NULL);
+ }
+ } else if (!strcmp(cmd, "irqs")) {
+ fiq_debugger_dump_irqs(state);
+ } else if (!strcmp(cmd, "kmsg")) {
+ fiq_debugger_dump_kernel_log(state);
+ } else if (!strcmp(cmd, "version")) {
+ fiq_debugger_printf(&state->output, "%s\n", linux_banner);
+ } else if (!strcmp(cmd, "sleep")) {
+ state->no_sleep = false;
+ fiq_debugger_printf(&state->output, "enabling sleep\n");
+ } else if (!strcmp(cmd, "nosleep")) {
+ state->no_sleep = true;
+ fiq_debugger_printf(&state->output, "disabling sleep\n");
+ } else if (!strcmp(cmd, "console")) {
+ fiq_debugger_printf(&state->output, "console mode\n");
+ fiq_debugger_uart_flush(state);
+ state->console_enable = true;
+ } else if (!strcmp(cmd, "cpu")) {
+ fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+ } else if (!strncmp(cmd, "cpu ", 4)) {
+ unsigned long cpu = 0;
+ if (strict_strtoul(cmd + 4, 10, &cpu) == 0)
+ fiq_debugger_switch_cpu(state, cpu);
+ else
+ fiq_debugger_printf(&state->output, "invalid cpu\n");
+ fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+ } else {
+ if (state->debug_busy) {
+ fiq_debugger_printf(&state->output,
+ "command processor busy. trying to abort.\n");
+ state->debug_abort = -1;
+ } else {
+ strcpy(state->debug_cmd, cmd);
+ state->debug_busy = 1;
+ }
+
+ return true;
+ }
+ if (!state->console_enable)
+ fiq_debugger_prompt(state);
+
+ return signal_helper;
+}
+
+static void fiq_debugger_sleep_timer_expired(unsigned long data)
+{
+ struct fiq_debugger_state *state = (struct fiq_debugger_state *)data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ if (state->uart_enabled && !state->no_sleep) {
+ if (state->debug_enable && !state->console_enable) {
+ state->debug_enable = false;
+ fiq_debugger_printf_nfiq(state,
+ "suspending fiq debugger\n");
+ }
+ state->ignore_next_wakeup_irq = true;
+ fiq_debugger_uart_disable(state);
+ state->uart_enabled = false;
+ fiq_debugger_enable_wakeup_irq(state);
+ }
+ wake_unlock(&state->debugger_wake_lock);
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static void fiq_debugger_handle_wakeup(struct fiq_debugger_state *state)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ if (state->wakeup_irq >= 0 && state->ignore_next_wakeup_irq) {
+ state->ignore_next_wakeup_irq = false;
+ } else if (!state->uart_enabled) {
+ wake_lock(&state->debugger_wake_lock);
+ fiq_debugger_uart_enable(state);
+ state->uart_enabled = true;
+ fiq_debugger_disable_wakeup_irq(state);
+ mod_timer(&state->sleep_timer, jiffies + HZ / 2);
+ }
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static irqreturn_t fiq_debugger_wakeup_irq_handler(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+
+ if (!state->no_sleep)
+ fiq_debugger_puts(state, "WAKEUP\n");
+ fiq_debugger_handle_wakeup(state);
+
+ return IRQ_HANDLED;
+}
+
+static
+void fiq_debugger_handle_console_irq_context(struct fiq_debugger_state *state)
+{
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ if (state->tty_port.ops) {
+ int i;
+ int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+ for (i = 0; i < count; i++) {
+ int c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+ tty_insert_flip_char(&state->tty_port, c, TTY_NORMAL);
+ if (!fiq_debugger_ringbuf_consume(state->tty_rbuf, 1))
+ pr_warn("fiq tty failed to consume byte\n");
+ }
+ tty_flip_buffer_push(&state->tty_port);
+ }
+#endif
+}
+
+static void fiq_debugger_handle_irq_context(struct fiq_debugger_state *state)
+{
+ if (!state->no_sleep) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&state->sleep_timer_lock, flags);
+ wake_lock(&state->debugger_wake_lock);
+ mod_timer(&state->sleep_timer, jiffies + HZ * 5);
+ spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+ }
+ fiq_debugger_handle_console_irq_context(state);
+ if (state->debug_busy) {
+ fiq_debugger_irq_exec(state, state->debug_cmd);
+ if (!state->console_enable)
+ fiq_debugger_prompt(state);
+ state->debug_busy = 0;
+ }
+}
+
+static int fiq_debugger_getc(struct fiq_debugger_state *state)
+{
+ return state->pdata->uart_getc(state->pdev);
+}
+
+static bool fiq_debugger_handle_uart_interrupt(struct fiq_debugger_state *state,
+ int this_cpu, const struct pt_regs *regs, void *svc_sp)
+{
+ int c;
+ static int last_c;
+ int count = 0;
+ bool signal_helper = false;
+
+ if (this_cpu != state->current_cpu) {
+ if (state->in_fiq)
+ return false;
+
+ if (atomic_inc_return(&state->unhandled_fiq_count) !=
+ MAX_UNHANDLED_FIQ_COUNT)
+ return false;
+
+ fiq_debugger_printf(&state->output,
+ "fiq_debugger: cpu %d not responding, "
+ "reverting to cpu %d\n", state->current_cpu,
+ this_cpu);
+
+ atomic_set(&state->unhandled_fiq_count, 0);
+ fiq_debugger_switch_cpu(state, this_cpu);
+ return false;
+ }
+
+ state->in_fiq = true;
+
+ while ((c = fiq_debugger_getc(state)) != FIQ_DEBUGGER_NO_CHAR) {
+ count++;
+ if (!state->debug_enable) {
+ if ((c == 13) || (c == 10)) {
+ state->debug_enable = true;
+ state->debug_count = 0;
+ fiq_debugger_prompt(state);
+ }
+ } else if (c == FIQ_DEBUGGER_BREAK) {
+ state->console_enable = false;
+ fiq_debugger_puts(state, "fiq debugger mode\n");
+ state->debug_count = 0;
+ fiq_debugger_prompt(state);
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+ } else if (state->console_enable && state->tty_rbuf) {
+ fiq_debugger_ringbuf_push(state->tty_rbuf, c);
+ signal_helper = true;
+#endif
+ } else if ((c >= ' ') && (c < 127)) {
+ if (state->debug_count < (DEBUG_MAX - 1)) {
+ state->debug_buf[state->debug_count++] = c;
+ fiq_debugger_putc(state, c);
+ }
+ } else if ((c == 8) || (c == 127)) {
+ if (state->debug_count > 0) {
+ state->debug_count--;
+ fiq_debugger_putc(state, 8);
+ fiq_debugger_putc(state, ' ');
+ fiq_debugger_putc(state, 8);
+ }
+ } else if ((c == 13) || (c == 10)) {
+ if (c == '\r' || (c == '\n' && last_c != '\r')) {
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, '\n');
+ }
+ if (state->debug_count) {
+ state->debug_buf[state->debug_count] = 0;
+ state->debug_count = 0;
+ signal_helper |=
+ fiq_debugger_fiq_exec(state,
+ state->debug_buf,
+ regs, svc_sp);
+ } else {
+ fiq_debugger_prompt(state);
+ }
+ }
+ last_c = c;
+ }
+ if (!state->console_enable)
+ fiq_debugger_uart_flush(state);
+ if (state->pdata->fiq_ack)
+ state->pdata->fiq_ack(state->pdev, state->fiq);
+
+ /* poke sleep timer if necessary */
+ if (state->debug_enable && !state->no_sleep)
+ signal_helper = true;
+
+ atomic_set(&state->unhandled_fiq_count, 0);
+ state->in_fiq = false;
+
+ return signal_helper;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_fiq(struct fiq_glue_handler *h,
+ const struct pt_regs *regs, void *svc_sp)
+{
+ struct fiq_debugger_state *state =
+ container_of(h, struct fiq_debugger_state, handler);
+ unsigned int this_cpu = THREAD_INFO(svc_sp)->cpu;
+ bool need_irq;
+
+ need_irq = fiq_debugger_handle_uart_interrupt(state, this_cpu, regs,
+ svc_sp);
+ if (need_irq)
+ fiq_debugger_force_irq(state);
+}
+#endif
+
+/*
+ * When not using FIQs, we only use this single interrupt as an entry point.
+ * This just effectively takes over the UART interrupt and does all the work
+ * in this context.
+ */
+static irqreturn_t fiq_debugger_uart_irq(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+ bool not_done;
+
+ fiq_debugger_handle_wakeup(state);
+
+ /* handle the debugger irq in regular context */
+ not_done = fiq_debugger_handle_uart_interrupt(state, smp_processor_id(),
+ get_irq_regs(),
+ current_thread_info());
+ if (not_done)
+ fiq_debugger_handle_irq_context(state);
+
+ return IRQ_HANDLED;
+}
+
+/*
+ * If FIQs are used, not everything can happen in fiq context.
+ * FIQ handler does what it can and then signals this interrupt to finish the
+ * job in irq context.
+ */
+static irqreturn_t fiq_debugger_signal_irq(int irq, void *dev)
+{
+ struct fiq_debugger_state *state = dev;
+
+ if (state->pdata->force_irq_ack)
+ state->pdata->force_irq_ack(state->pdev, state->signal_irq);
+
+ fiq_debugger_handle_irq_context(state);
+
+ return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_resume(struct fiq_glue_handler *h)
+{
+ struct fiq_debugger_state *state =
+ container_of(h, struct fiq_debugger_state, handler);
+ if (state->pdata->uart_resume)
+ state->pdata->uart_resume(state->pdev);
+}
+#endif
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+struct tty_driver *fiq_debugger_console_device(struct console *co, int *index)
+{
+ *index = co->index;
+ return fiq_tty_driver;
+}
+
+static void fiq_debugger_console_write(struct console *co,
+ const char *s, unsigned int count)
+{
+ struct fiq_debugger_state *state;
+ unsigned long flags;
+
+ state = container_of(co, struct fiq_debugger_state, console);
+
+ if (!state->console_enable && !state->syslog_dumping)
+ return;
+
+ fiq_debugger_uart_enable(state);
+ spin_lock_irqsave(&state->console_lock, flags);
+ while (count--) {
+ if (*s == '\n')
+ fiq_debugger_putc(state, '\r');
+ fiq_debugger_putc(state, *s++);
+ }
+ fiq_debugger_uart_flush(state);
+ spin_unlock_irqrestore(&state->console_lock, flags);
+ fiq_debugger_uart_disable(state);
+}
+
+static struct console fiq_debugger_console = {
+ .name = "ttyFIQ",
+ .device = fiq_debugger_console_device,
+ .write = fiq_debugger_console_write,
+ .flags = CON_PRINTBUFFER | CON_ANYTIME | CON_ENABLED,
+};
+
+int fiq_tty_open(struct tty_struct *tty, struct file *filp)
+{
+ int line = tty->index;
+ struct fiq_debugger_state **states = tty->driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+
+ return tty_port_open(&state->tty_port, tty, filp);
+}
+
+void fiq_tty_close(struct tty_struct *tty, struct file *filp)
+{
+ tty_port_close(tty->port, tty, filp);
+}
+
+int fiq_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+{
+ int i;
+ int line = tty->index;
+ struct fiq_debugger_state **states = tty->driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+
+ if (!state->console_enable)
+ return count;
+
+ fiq_debugger_uart_enable(state);
+ spin_lock_irq(&state->console_lock);
+ for (i = 0; i < count; i++)
+ fiq_debugger_putc(state, *buf++);
+ spin_unlock_irq(&state->console_lock);
+ fiq_debugger_uart_disable(state);
+
+ return count;
+}
+
+int fiq_tty_write_room(struct tty_struct *tty)
+{
+ return 16;
+}
+
+#ifdef CONFIG_CONSOLE_POLL
+static int fiq_tty_poll_init(struct tty_driver *driver, int line, char *options)
+{
+ return 0;
+}
+
+static int fiq_tty_poll_get_char(struct tty_driver *driver, int line)
+{
+ struct fiq_debugger_state **states = driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+ int c = NO_POLL_CHAR;
+
+ fiq_debugger_uart_enable(state);
+ if (fiq_debugger_have_fiq(state)) {
+ int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+ if (count > 0) {
+ c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+ fiq_debugger_ringbuf_consume(state->tty_rbuf, 1);
+ }
+ } else {
+ c = fiq_debugger_getc(state);
+ if (c == FIQ_DEBUGGER_NO_CHAR)
+ c = NO_POLL_CHAR;
+ }
+ fiq_debugger_uart_disable(state);
+
+ return c;
+}
+
+static void fiq_tty_poll_put_char(struct tty_driver *driver, int line, char ch)
+{
+ struct fiq_debugger_state **states = driver->driver_state;
+ struct fiq_debugger_state *state = states[line];
+ fiq_debugger_uart_enable(state);
+ fiq_debugger_putc(state, ch);
+ fiq_debugger_uart_disable(state);
+}
+#endif
+
+static const struct tty_port_operations fiq_tty_port_ops;
+
+static const struct tty_operations fiq_tty_driver_ops = {
+ .write = fiq_tty_write,
+ .write_room = fiq_tty_write_room,
+ .open = fiq_tty_open,
+ .close = fiq_tty_close,
+#ifdef CONFIG_CONSOLE_POLL
+ .poll_init = fiq_tty_poll_init,
+ .poll_get_char = fiq_tty_poll_get_char,
+ .poll_put_char = fiq_tty_poll_put_char,
+#endif
+};
+
+static int fiq_debugger_tty_init(void)
+{
+ int ret;
+ struct fiq_debugger_state **states = NULL;
+
+ states = kzalloc(sizeof(*states) * MAX_FIQ_DEBUGGER_PORTS, GFP_KERNEL);
+ if (!states) {
+ pr_err("Failed to allocate fiq debugger state structres\n");
+ return -ENOMEM;
+ }
+
+ fiq_tty_driver = alloc_tty_driver(MAX_FIQ_DEBUGGER_PORTS);
+ if (!fiq_tty_driver) {
+ pr_err("Failed to allocate fiq debugger tty\n");
+ ret = -ENOMEM;
+ goto err_free_state;
+ }
+
+ fiq_tty_driver->owner = THIS_MODULE;
+ fiq_tty_driver->driver_name = "fiq-debugger";
+ fiq_tty_driver->name = "ttyFIQ";
+ fiq_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
+ fiq_tty_driver->subtype = SERIAL_TYPE_NORMAL;
+ fiq_tty_driver->init_termios = tty_std_termios;
+ fiq_tty_driver->flags = TTY_DRIVER_REAL_RAW |
+ TTY_DRIVER_DYNAMIC_DEV;
+ fiq_tty_driver->driver_state = states;
+
+ fiq_tty_driver->init_termios.c_cflag =
+ B115200 | CS8 | CREAD | HUPCL | CLOCAL;
+ fiq_tty_driver->init_termios.c_ispeed = 115200;
+ fiq_tty_driver->init_termios.c_ospeed = 115200;
+
+ tty_set_operations(fiq_tty_driver, &fiq_tty_driver_ops);
+
+ ret = tty_register_driver(fiq_tty_driver);
+ if (ret) {
+ pr_err("Failed to register fiq tty: %d\n", ret);
+ goto err_free_tty;
+ }
+
+ pr_info("Registered FIQ tty driver\n");
+ return 0;
+
+err_free_tty:
+ put_tty_driver(fiq_tty_driver);
+ fiq_tty_driver = NULL;
+err_free_state:
+ kfree(states);
+ return ret;
+}
+
+static int fiq_debugger_tty_init_one(struct fiq_debugger_state *state)
+{
+ int ret;
+ struct device *tty_dev;
+ struct fiq_debugger_state **states = fiq_tty_driver->driver_state;
+
+ states[state->pdev->id] = state;
+
+ state->tty_rbuf = fiq_debugger_ringbuf_alloc(1024);
+ if (!state->tty_rbuf) {
+ pr_err("Failed to allocate fiq debugger ringbuf\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ tty_port_init(&state->tty_port);
+ state->tty_port.ops = &fiq_tty_port_ops;
+
+ tty_dev = tty_port_register_device(&state->tty_port, fiq_tty_driver,
+ state->pdev->id, &state->pdev->dev);
+ if (IS_ERR(tty_dev)) {
+ pr_err("Failed to register fiq debugger tty device\n");
+ ret = PTR_ERR(tty_dev);
+ goto err;
+ }
+
+ device_set_wakeup_capable(tty_dev, 1);
+
+ pr_info("Registered fiq debugger ttyFIQ%d\n", state->pdev->id);
+
+ return 0;
+
+err:
+ fiq_debugger_ringbuf_free(state->tty_rbuf);
+ state->tty_rbuf = NULL;
+ return ret;
+}
+#endif
+
+static int fiq_debugger_dev_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+ if (state->pdata->uart_dev_suspend)
+ return state->pdata->uart_dev_suspend(pdev);
+ return 0;
+}
+
+static int fiq_debugger_dev_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+ if (state->pdata->uart_dev_resume)
+ return state->pdata->uart_dev_resume(pdev);
+ return 0;
+}
+
+static int fiq_debugger_probe(struct platform_device *pdev)
+{
+ int ret;
+ struct fiq_debugger_pdata *pdata = dev_get_platdata(&pdev->dev);
+ struct fiq_debugger_state *state;
+ int fiq;
+ int uart_irq;
+
+ if (pdev->id >= MAX_FIQ_DEBUGGER_PORTS)
+ return -EINVAL;
+
+ if (!pdata->uart_getc || !pdata->uart_putc)
+ return -EINVAL;
+ if ((pdata->uart_enable && !pdata->uart_disable) ||
+ (!pdata->uart_enable && pdata->uart_disable))
+ return -EINVAL;
+
+ fiq = platform_get_irq_byname(pdev, "fiq");
+ uart_irq = platform_get_irq_byname(pdev, "uart_irq");
+
+ /* uart_irq mode and fiq mode are mutually exclusive, but one of them
+ * is required */
+ if ((uart_irq < 0 && fiq < 0) || (uart_irq >= 0 && fiq >= 0))
+ return -EINVAL;
+ if (fiq >= 0 && !pdata->fiq_enable)
+ return -EINVAL;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ state->output.printf = fiq_debugger_printf;
+ setup_timer(&state->sleep_timer, fiq_debugger_sleep_timer_expired,
+ (unsigned long)state);
+ state->pdata = pdata;
+ state->pdev = pdev;
+ state->no_sleep = initial_no_sleep;
+ state->debug_enable = initial_debug_enable;
+ state->console_enable = initial_console_enable;
+
+ state->fiq = fiq;
+ state->uart_irq = uart_irq;
+ state->signal_irq = platform_get_irq_byname(pdev, "signal");
+ state->wakeup_irq = platform_get_irq_byname(pdev, "wakeup");
+
+ INIT_WORK(&state->work, fiq_debugger_work);
+ spin_lock_init(&state->work_lock);
+
+ platform_set_drvdata(pdev, state);
+
+ spin_lock_init(&state->sleep_timer_lock);
+
+ if (state->wakeup_irq < 0 && fiq_debugger_have_fiq(state))
+ state->no_sleep = true;
+ state->ignore_next_wakeup_irq = !state->no_sleep;
+
+ wake_lock_init(&state->debugger_wake_lock,
+ WAKE_LOCK_SUSPEND, "serial-debug");
+
+ state->clk = clk_get(&pdev->dev, NULL);
+ if (IS_ERR(state->clk))
+ state->clk = NULL;
+
+ /* do not call pdata->uart_enable here since uart_init may still
+ * need to do some initialization before uart_enable can work.
+ * So, only try to manage the clock during init.
+ */
+ if (state->clk)
+ clk_enable(state->clk);
+
+ if (pdata->uart_init) {
+ ret = pdata->uart_init(pdev);
+ if (ret)
+ goto err_uart_init;
+ }
+
+ fiq_debugger_printf_nfiq(state,
+ "<hit enter %sto activate fiq debugger>\n",
+ state->no_sleep ? "" : "twice ");
+
+#ifdef CONFIG_FIQ_GLUE
+ if (fiq_debugger_have_fiq(state)) {
+ state->handler.fiq = fiq_debugger_fiq;
+ state->handler.resume = fiq_debugger_resume;
+ ret = fiq_glue_register_handler(&state->handler);
+ if (ret) {
+ pr_err("%s: could not install fiq handler\n", __func__);
+ goto err_register_irq;
+ }
+
+ pdata->fiq_enable(pdev, state->fiq, 1);
+ } else
+#endif
+ {
+ ret = request_irq(state->uart_irq, fiq_debugger_uart_irq,
+ IRQF_NO_SUSPEND, "debug", state);
+ if (ret) {
+ pr_err("%s: could not install irq handler\n", __func__);
+ goto err_register_irq;
+ }
+
+ /* for irq-only mode, we want this irq to wake us up, if it
+ * can.
+ */
+ enable_irq_wake(state->uart_irq);
+ }
+
+ if (state->clk)
+ clk_disable(state->clk);
+
+ if (state->signal_irq >= 0) {
+ ret = request_irq(state->signal_irq, fiq_debugger_signal_irq,
+ IRQF_TRIGGER_RISING, "debug-signal", state);
+ if (ret)
+ pr_err("serial_debugger: could not install signal_irq");
+ }
+
+ if (state->wakeup_irq >= 0) {
+ ret = request_irq(state->wakeup_irq,
+ fiq_debugger_wakeup_irq_handler,
+ IRQF_TRIGGER_FALLING | IRQF_DISABLED,
+ "debug-wakeup", state);
+ if (ret) {
+ pr_err("serial_debugger: "
+ "could not install wakeup irq\n");
+ state->wakeup_irq = -1;
+ } else {
+ ret = enable_irq_wake(state->wakeup_irq);
+ if (ret) {
+ pr_err("serial_debugger: "
+ "could not enable wakeup\n");
+ state->wakeup_irq_no_set_wake = true;
+ }
+ }
+ }
+ if (state->no_sleep)
+ fiq_debugger_handle_wakeup(state);
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ spin_lock_init(&state->console_lock);
+ state->console = fiq_debugger_console;
+ state->console.index = pdev->id;
+ if (!console_set_on_cmdline)
+ add_preferred_console(state->console.name,
+ state->console.index, NULL);
+ register_console(&state->console);
+ fiq_debugger_tty_init_one(state);
+#endif
+ return 0;
+
+err_register_irq:
+ if (pdata->uart_free)
+ pdata->uart_free(pdev);
+err_uart_init:
+ if (state->clk)
+ clk_disable(state->clk);
+ if (state->clk)
+ clk_put(state->clk);
+ wake_lock_destroy(&state->debugger_wake_lock);
+ platform_set_drvdata(pdev, NULL);
+ kfree(state);
+ return ret;
+}
+
+static const struct dev_pm_ops fiq_debugger_dev_pm_ops = {
+ .suspend = fiq_debugger_dev_suspend,
+ .resume = fiq_debugger_dev_resume,
+};
+
+static struct platform_driver fiq_debugger_driver = {
+ .probe = fiq_debugger_probe,
+ .driver = {
+ .name = "fiq_debugger",
+ .pm = &fiq_debugger_dev_pm_ops,
+ },
+};
+
+static int __init fiq_debugger_init(void)
+{
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+ fiq_debugger_tty_init();
+#endif
+ return platform_driver_register(&fiq_debugger_driver);
+}
+
+postcore_initcall(fiq_debugger_init);
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.h b/drivers/staging/android/fiq_debugger/fiq_debugger.h
new file mode 100644
index 0000000..c9ec4f8
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.h
@@ -0,0 +1,64 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+#define _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+
+#include <linux/serial_core.h>
+
+#define FIQ_DEBUGGER_NO_CHAR NO_POLL_CHAR
+#define FIQ_DEBUGGER_BREAK 0x00ff0100
+
+#define FIQ_DEBUGGER_FIQ_IRQ_NAME "fiq"
+#define FIQ_DEBUGGER_SIGNAL_IRQ_NAME "signal"
+#define FIQ_DEBUGGER_WAKEUP_IRQ_NAME "wakeup"
+
+/**
+ * struct fiq_debugger_pdata - fiq debugger platform data
+ * @uart_resume: used to restore uart state right before enabling
+ * the fiq.
+ * @uart_enable: Do the work necessary to communicate with the uart
+ * hw (enable clocks, etc.). This must be ref-counted.
+ * @uart_disable: Do the work necessary to disable the uart hw
+ * (disable clocks, etc.). This must be ref-counted.
+ * @uart_dev_suspend: called during PM suspend, generally not needed
+ * for real fiq mode debugger.
+ * @uart_dev_resume: called during PM resume, generally not needed
+ * for real fiq mode debugger.
+ */
+struct fiq_debugger_pdata {
+ int (*uart_init)(struct platform_device *pdev);
+ void (*uart_free)(struct platform_device *pdev);
+ int (*uart_resume)(struct platform_device *pdev);
+ int (*uart_getc)(struct platform_device *pdev);
+ void (*uart_putc)(struct platform_device *pdev, unsigned int c);
+ void (*uart_flush)(struct platform_device *pdev);
+ void (*uart_enable)(struct platform_device *pdev);
+ void (*uart_disable)(struct platform_device *pdev);
+
+ int (*uart_dev_suspend)(struct platform_device *pdev);
+ int (*uart_dev_resume)(struct platform_device *pdev);
+
+ void (*fiq_enable)(struct platform_device *pdev, unsigned int fiq,
+ bool enable);
+ void (*fiq_ack)(struct platform_device *pdev, unsigned int fiq);
+
+ void (*force_irq)(struct platform_device *pdev, unsigned int irq);
+ void (*force_irq_ack)(struct platform_device *pdev, unsigned int irq);
+};
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
new file mode 100644
index 0000000..8b3e013
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(unsigned cpsr)
+{
+ switch (cpsr & MODE_MASK) {
+ case USR_MODE: return "USR";
+ case FIQ_MODE: return "FIQ";
+ case IRQ_MODE: return "IRQ";
+ case SVC_MODE: return "SVC";
+ case ABT_MODE: return "ABT";
+ case UND_MODE: return "UND";
+ case SYSTEM_MODE: return "SYS";
+ default: return "???";
+ }
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " pc %08x cpsr %08x mode %s\n",
+ regs->ARM_pc, regs->ARM_cpsr, mode_name(regs->ARM_cpsr));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output,
+ " r0 %08x r1 %08x r2 %08x r3 %08x\n",
+ regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
+ output->printf(output,
+ " r4 %08x r5 %08x r6 %08x r7 %08x\n",
+ regs->ARM_r4, regs->ARM_r5, regs->ARM_r6, regs->ARM_r7);
+ output->printf(output,
+ " r8 %08x r9 %08x r10 %08x r11 %08x mode %s\n",
+ regs->ARM_r8, regs->ARM_r9, regs->ARM_r10, regs->ARM_fp,
+ mode_name(regs->ARM_cpsr));
+ output->printf(output,
+ " ip %08x sp %08x lr %08x pc %08x cpsr %08x\n",
+ regs->ARM_ip, regs->ARM_sp, regs->ARM_lr, regs->ARM_pc,
+ regs->ARM_cpsr);
+}
+
+struct mode_regs {
+ unsigned long sp_svc;
+ unsigned long lr_svc;
+ unsigned long spsr_svc;
+
+ unsigned long sp_abt;
+ unsigned long lr_abt;
+ unsigned long spsr_abt;
+
+ unsigned long sp_und;
+ unsigned long lr_und;
+ unsigned long spsr_und;
+
+ unsigned long sp_irq;
+ unsigned long lr_irq;
+ unsigned long spsr_irq;
+
+ unsigned long r8_fiq;
+ unsigned long r9_fiq;
+ unsigned long r10_fiq;
+ unsigned long r11_fiq;
+ unsigned long r12_fiq;
+ unsigned long sp_fiq;
+ unsigned long lr_fiq;
+ unsigned long spsr_fiq;
+};
+
+static void __naked get_mode_regs(struct mode_regs *regs)
+{
+ asm volatile (
+ "mrs r1, cpsr\n"
+ "msr cpsr_c, #0xd3 @(SVC_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd7 @(ABT_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xdb @(UND_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd2 @(IRQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r13 - r14}\n"
+ "mrs r2, spsr\n"
+ "msr cpsr_c, #0xd1 @(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+ "stmia r0!, {r2, r8 - r14}\n"
+ "mrs r2, spsr\n"
+ "stmia r0!, {r2}\n"
+ "msr cpsr_c, r1\n"
+ "bx lr\n");
+}
+
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ struct mode_regs mode_regs;
+ unsigned long mode = regs->ARM_cpsr & MODE_MASK;
+
+ fiq_debugger_dump_regs(output, regs);
+ get_mode_regs(&mode_regs);
+
+ output->printf(output,
+ "%csvc: sp %08x lr %08x spsr %08x\n",
+ mode == SVC_MODE ? '*' : ' ',
+ mode_regs.sp_svc, mode_regs.lr_svc, mode_regs.spsr_svc);
+ output->printf(output,
+ "%cabt: sp %08x lr %08x spsr %08x\n",
+ mode == ABT_MODE ? '*' : ' ',
+ mode_regs.sp_abt, mode_regs.lr_abt, mode_regs.spsr_abt);
+ output->printf(output,
+ "%cund: sp %08x lr %08x spsr %08x\n",
+ mode == UND_MODE ? '*' : ' ',
+ mode_regs.sp_und, mode_regs.lr_und, mode_regs.spsr_und);
+ output->printf(output,
+ "%cirq: sp %08x lr %08x spsr %08x\n",
+ mode == IRQ_MODE ? '*' : ' ',
+ mode_regs.sp_irq, mode_regs.lr_irq, mode_regs.spsr_irq);
+ output->printf(output,
+ "%cfiq: r8 %08x r9 %08x r10 %08x r11 %08x r12 %08x\n",
+ mode == FIQ_MODE ? '*' : ' ',
+ mode_regs.r8_fiq, mode_regs.r9_fiq, mode_regs.r10_fiq,
+ mode_regs.r11_fiq, mode_regs.r12_fiq);
+ output->printf(output,
+ " fiq: sp %08x lr %08x spsr %08x\n",
+ mode_regs.sp_fiq, mode_regs.lr_fiq, mode_regs.spsr_fiq);
+}
+
+struct stacktrace_state {
+ struct fiq_debugger_output *output;
+ unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+ struct stacktrace_state *sts = d;
+
+ if (sts->depth) {
+ sts->output->printf(sts->output,
+ " pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+ frame->pc, frame->pc, frame->lr, frame->lr,
+ frame->sp, frame->fp);
+ sts->depth--;
+ return 0;
+ }
+ sts->output->printf(sts->output, " ...\n");
+
+ return sts->depth == 0;
+}
+
+struct frame_tail {
+ struct frame_tail *fp;
+ unsigned long sp;
+ unsigned long lr;
+} __attribute__((packed));
+
+static struct frame_tail *user_backtrace(struct fiq_debugger_output *output,
+ struct frame_tail *tail)
+{
+ struct frame_tail buftail[2];
+
+ /* Also check accessibility of one struct frame_tail beyond */
+ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) {
+ output->printf(output, " invalid frame pointer %p\n",
+ tail);
+ return NULL;
+ }
+ if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) {
+ output->printf(output,
+ " failed to copy frame pointer %p\n", tail);
+ return NULL;
+ }
+
+ output->printf(output, " %p\n", buftail[0].lr);
+
+ /* frame pointers should strictly progress back up the stack
+ * (towards higher addresses) */
+ if (tail >= buftail[0].fp)
+ return NULL;
+
+ return buftail[0].fp-1;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+ struct frame_tail *tail;
+ struct thread_info *real_thread_info = THREAD_INFO(ssp);
+ struct stacktrace_state sts;
+
+ sts.depth = depth;
+ sts.output = output;
+ *current_thread_info() = *real_thread_info;
+
+ if (!current)
+ output->printf(output, "current NULL\n");
+ else
+ output->printf(output, "pid: %d comm: %s\n",
+ current->pid, current->comm);
+ fiq_debugger_dump_regs(output, regs);
+
+ if (!user_mode(regs)) {
+ struct stackframe frame;
+ frame.fp = regs->ARM_fp;
+ frame.sp = regs->ARM_sp;
+ frame.lr = regs->ARM_lr;
+ frame.pc = regs->ARM_pc;
+ output->printf(output,
+ " pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+ regs->ARM_pc, regs->ARM_pc, regs->ARM_lr, regs->ARM_lr,
+ regs->ARM_sp, regs->ARM_fp);
+ walk_stackframe(&frame, report_trace, &sts);
+ return;
+ }
+
+ tail = ((struct frame_tail *) regs->ARM_fp) - 1;
+ while (depth-- && tail && !((unsigned long) tail & 3))
+ tail = user_backtrace(output, tail);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
new file mode 100644
index 0000000..99c6584
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ptrace.h>
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(const struct pt_regs *regs)
+{
+ if (compat_user_mode(regs)) {
+ return "USR";
+ } else {
+ switch (processor_mode(regs)) {
+ case PSR_MODE_EL0t: return "EL0t";
+ case PSR_MODE_EL1t: return "EL1t";
+ case PSR_MODE_EL1h: return "EL1h";
+ case PSR_MODE_EL2t: return "EL2t";
+ case PSR_MODE_EL2h: return "EL2h";
+ default: return "???";
+ }
+ }
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " pc %016lx cpsr %08lx mode %s\n",
+ regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch32(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ output->printf(output, " r0 %08x r1 %08x r2 %08x r3 %08x\n",
+ regs->compat_usr(0), regs->compat_usr(1),
+ regs->compat_usr(2), regs->compat_usr(3));
+ output->printf(output, " r4 %08x r5 %08x r6 %08x r7 %08x\n",
+ regs->compat_usr(4), regs->compat_usr(5),
+ regs->compat_usr(6), regs->compat_usr(7));
+ output->printf(output, " r8 %08x r9 %08x r10 %08x r11 %08x\n",
+ regs->compat_usr(8), regs->compat_usr(9),
+ regs->compat_usr(10), regs->compat_usr(11));
+ output->printf(output, " ip %08x sp %08x lr %08x pc %08x\n",
+ regs->compat_usr(12), regs->compat_sp,
+ regs->compat_lr, regs->pc);
+ output->printf(output, " cpsr %08x (%s)\n",
+ regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch64(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+
+ output->printf(output, " x0 %016lx x1 %016lx\n",
+ regs->regs[0], regs->regs[1]);
+ output->printf(output, " x2 %016lx x3 %016lx\n",
+ regs->regs[2], regs->regs[3]);
+ output->printf(output, " x4 %016lx x5 %016lx\n",
+ regs->regs[4], regs->regs[5]);
+ output->printf(output, " x6 %016lx x7 %016lx\n",
+ regs->regs[6], regs->regs[7]);
+ output->printf(output, " x8 %016lx x9 %016lx\n",
+ regs->regs[8], regs->regs[9]);
+ output->printf(output, " x10 %016lx x11 %016lx\n",
+ regs->regs[10], regs->regs[11]);
+ output->printf(output, " x12 %016lx x13 %016lx\n",
+ regs->regs[12], regs->regs[13]);
+ output->printf(output, " x14 %016lx x15 %016lx\n",
+ regs->regs[14], regs->regs[15]);
+ output->printf(output, " x16 %016lx x17 %016lx\n",
+ regs->regs[16], regs->regs[17]);
+ output->printf(output, " x18 %016lx x19 %016lx\n",
+ regs->regs[18], regs->regs[19]);
+ output->printf(output, " x20 %016lx x21 %016lx\n",
+ regs->regs[20], regs->regs[21]);
+ output->printf(output, " x22 %016lx x23 %016lx\n",
+ regs->regs[22], regs->regs[23]);
+ output->printf(output, " x24 %016lx x25 %016lx\n",
+ regs->regs[24], regs->regs[25]);
+ output->printf(output, " x26 %016lx x27 %016lx\n",
+ regs->regs[26], regs->regs[27]);
+ output->printf(output, " x28 %016lx x29 %016lx\n",
+ regs->regs[28], regs->regs[29]);
+ output->printf(output, " x30 %016lx sp %016lx\n",
+ regs->regs[30], regs->sp);
+ output->printf(output, " pc %016lx cpsr %08x (%s)\n",
+ regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ if (compat_user_mode(regs))
+ fiq_debugger_dump_regs_aarch32(output, regs);
+ else
+ fiq_debugger_dump_regs_aarch64(output, regs);
+}
+
+#define READ_SPECIAL_REG(x) ({ \
+ u64 val; \
+ asm volatile ("mrs %0, " # x : "=r"(val)); \
+ val; \
+})
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs)
+{
+ u32 pstate = READ_SPECIAL_REG(CurrentEl);
+ bool in_el2 = (pstate & PSR_MODE_MASK) >= PSR_MODE_EL2t;
+
+ fiq_debugger_dump_regs(output, regs);
+
+ output->printf(output, " sp_el0 %016lx\n",
+ READ_SPECIAL_REG(sp_el0));
+
+ if (in_el2)
+ output->printf(output, " sp_el1 %016lx\n",
+ READ_SPECIAL_REG(sp_el1));
+
+ output->printf(output, " elr_el1 %016lx\n",
+ READ_SPECIAL_REG(elr_el1));
+
+ output->printf(output, " spsr_el1 %08lx\n",
+ READ_SPECIAL_REG(spsr_el1));
+
+ if (in_el2) {
+ output->printf(output, " spsr_irq %08lx\n",
+ READ_SPECIAL_REG(spsr_irq));
+ output->printf(output, " spsr_abt %08lx\n",
+ READ_SPECIAL_REG(spsr_abt));
+ output->printf(output, " spsr_und %08lx\n",
+ READ_SPECIAL_REG(spsr_und));
+ output->printf(output, " spsr_fiq %08lx\n",
+ READ_SPECIAL_REG(spsr_fiq));
+ output->printf(output, " spsr_el2 %08lx\n",
+ READ_SPECIAL_REG(elr_el2));
+ output->printf(output, " spsr_el2 %08lx\n",
+ READ_SPECIAL_REG(spsr_el2));
+ }
+}
+
+struct stacktrace_state {
+ struct fiq_debugger_output *output;
+ unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+ struct stacktrace_state *sts = d;
+
+ if (sts->depth) {
+ sts->output->printf(sts->output, "%pF:\n", frame->pc);
+ sts->output->printf(sts->output,
+ " pc %016lx sp %016lx fp %016lx\n",
+ frame->pc, frame->sp, frame->fp);
+ sts->depth--;
+ return 0;
+ }
+ sts->output->printf(sts->output, " ...\n");
+
+ return sts->depth == 0;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+ struct thread_info *real_thread_info = THREAD_INFO(ssp);
+ struct stacktrace_state sts;
+
+ sts.depth = depth;
+ sts.output = output;
+ *current_thread_info() = *real_thread_info;
+
+ if (!current)
+ output->printf(output, "current NULL\n");
+ else
+ output->printf(output, "pid: %d comm: %s\n",
+ current->pid, current->comm);
+ fiq_debugger_dump_regs(output, regs);
+
+ if (!user_mode(regs)) {
+ struct stackframe frame;
+ frame.fp = regs->regs[29];
+ frame.sp = regs->sp;
+ frame.pc = regs->pc;
+ output->printf(output, "\n");
+ walk_stackframe(&frame, report_trace, &sts);
+ }
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
new file mode 100644
index 0000000..d5d051f
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _FIQ_DEBUGGER_PRIV_H_
+#define _FIQ_DEBUGGER_PRIV_H_
+
+#define THREAD_INFO(sp) ((struct thread_info *) \
+ ((unsigned long)(sp) & ~(THREAD_SIZE - 1)))
+
+struct fiq_debugger_output {
+ void (*printf)(struct fiq_debugger_output *output, const char *fmt, ...);
+};
+
+struct pt_regs;
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+ const struct pt_regs *regs);
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+ const struct pt_regs *regs, unsigned int depth, void *ssp);
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
new file mode 100644
index 0000000..10c3c5d
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
@@ -0,0 +1,94 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
+ *
+ * simple lockless ringbuffer
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+struct fiq_debugger_ringbuf {
+ int len;
+ int head;
+ int tail;
+ u8 buf[];
+};
+
+
+static inline struct fiq_debugger_ringbuf *fiq_debugger_ringbuf_alloc(int len)
+{
+ struct fiq_debugger_ringbuf *rbuf;
+
+ rbuf = kzalloc(sizeof(*rbuf) + len, GFP_KERNEL);
+ if (rbuf == NULL)
+ return NULL;
+
+ rbuf->len = len;
+ rbuf->head = 0;
+ rbuf->tail = 0;
+ smp_mb();
+
+ return rbuf;
+}
+
+static inline void fiq_debugger_ringbuf_free(struct fiq_debugger_ringbuf *rbuf)
+{
+ kfree(rbuf);
+}
+
+static inline int fiq_debugger_ringbuf_level(struct fiq_debugger_ringbuf *rbuf)
+{
+ int level = rbuf->head - rbuf->tail;
+
+ if (level < 0)
+ level = rbuf->len + level;
+
+ return level;
+}
+
+static inline int fiq_debugger_ringbuf_room(struct fiq_debugger_ringbuf *rbuf)
+{
+ return rbuf->len - fiq_debugger_ringbuf_level(rbuf) - 1;
+}
+
+static inline u8
+fiq_debugger_ringbuf_peek(struct fiq_debugger_ringbuf *rbuf, int i)
+{
+ return rbuf->buf[(rbuf->tail + i) % rbuf->len];
+}
+
+static inline int
+fiq_debugger_ringbuf_consume(struct fiq_debugger_ringbuf *rbuf, int count)
+{
+ count = min(count, fiq_debugger_ringbuf_level(rbuf));
+
+ rbuf->tail = (rbuf->tail + count) % rbuf->len;
+ smp_mb();
+
+ return count;
+}
+
+static inline int
+fiq_debugger_ringbuf_push(struct fiq_debugger_ringbuf *rbuf, u8 datum)
+{
+ if (fiq_debugger_ringbuf_room(rbuf) == 0)
+ return 0;
+
+ rbuf->buf[rbuf->head] = datum;
+ smp_mb();
+ rbuf->head = (rbuf->head + 1) % rbuf->len;
+ smp_mb();
+
+ return 1;
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.c b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
new file mode 100644
index 0000000..194b541
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/pstore_ram.h>
+
+#include "fiq_watchdog.h"
+#include "fiq_debugger_priv.h"
+
+static DEFINE_RAW_SPINLOCK(fiq_watchdog_lock);
+
+static void fiq_watchdog_printf(struct fiq_debugger_output *output,
+ const char *fmt, ...)
+{
+ char buf[256];
+ va_list ap;
+ int len;
+
+ va_start(ap, fmt);
+ len = vscnprintf(buf, sizeof(buf), fmt, ap);
+ va_end(ap);
+
+ ramoops_console_write_buf(buf, len);
+}
+
+struct fiq_debugger_output fiq_watchdog_output = {
+ .printf = fiq_watchdog_printf,
+};
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp)
+{
+ char msg[24];
+ int len;
+
+ raw_spin_lock(&fiq_watchdog_lock);
+
+ len = scnprintf(msg, sizeof(msg), "watchdog fiq cpu %d\n",
+ THREAD_INFO(svc_sp)->cpu);
+ ramoops_console_write_buf(msg, len);
+
+ fiq_debugger_dump_stacktrace(&fiq_watchdog_output, regs, 100, svc_sp);
+
+ raw_spin_unlock(&fiq_watchdog_lock);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.h b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
new file mode 100644
index 0000000..c6b507f
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _FIQ_WATCHDOG_H_
+#define _FIQ_WATCHDOG_H_
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp);
+
+#endif
diff --git a/drivers/staging/android/ion/Kconfig b/drivers/staging/android/ion/Kconfig
new file mode 100644
index 0000000..5f520b7
--- /dev/null
+++ b/drivers/staging/android/ion/Kconfig
@@ -0,0 +1,32 @@
+menuconfig ION
+ bool "Ion Memory Manager"
+ depends on HAVE_MEMBLOCK
+ select GENERIC_ALLOCATOR
+ select DMA_SHARED_BUFFER
+ ---help---
+ Chose this option to enable the ION Memory Manager,
+ used by Android to efficiently allocate buffers
+ from userspace that can be shared between drivers.
+ If you're not using Android its probably safe to
+ say N here.
+
+config ION_TEST
+ tristate "Ion Test Device"
+ depends on ION
+ help
+ Choose this option to create a device that can be used to test the
+ kernel and device side ION functions.
+
+config ION_TEGRA
+ tristate "Ion for Tegra"
+ depends on ARCH_TEGRA && ION
+ help
+ Choose this option if you wish to use ion on an nVidia Tegra.
+
+config ION_POOL_CACHE_POLICY
+ bool "Ion set page pool cache policy"
+ depends on ION
+ default y if X86
+ help
+ Choose this option if need to explicity set cache policy of the
+ pages in the page pool.
diff --git a/drivers/staging/android/ion/Makefile b/drivers/staging/android/ion/Makefile
new file mode 100644
index 0000000..75039b9
--- /dev/null
+++ b/drivers/staging/android/ion/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_ION) += ion.o ion_heap.o ion_page_pool.o ion_system_heap.o \
+ ion_carveout_heap.o ion_chunk_heap.o ion_cma_heap.o
+obj-$(CONFIG_ION_TEST) += ion_test.o
+ifdef CONFIG_COMPAT
+obj-$(CONFIG_ION) += compat_ion.o
+endif
+obj-$(CONFIG_ION_TEGRA) += tegra/
diff --git a/drivers/staging/android/ion/compat_ion.c b/drivers/staging/android/ion/compat_ion.c
new file mode 100644
index 0000000..a5e8c40
--- /dev/null
+++ b/drivers/staging/android/ion/compat_ion.c
@@ -0,0 +1,195 @@
+/*
+ * drivers/gpu/ion/compat_ion.c
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/compat.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+
+#include "ion.h"
+#include "compat_ion.h"
+
+/* See drivers/staging/android/uapi/ion.h for the definition of these structs */
+struct compat_ion_allocation_data {
+ compat_size_t len;
+ compat_size_t align;
+ compat_uint_t heap_id_mask;
+ compat_uint_t flags;
+ compat_int_t handle;
+};
+
+struct compat_ion_custom_data {
+ compat_uint_t cmd;
+ compat_ulong_t arg;
+};
+
+struct compat_ion_handle_data {
+ compat_int_t handle;
+};
+
+#define COMPAT_ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \
+ struct compat_ion_allocation_data)
+#define COMPAT_ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, \
+ struct compat_ion_handle_data)
+#define COMPAT_ION_IOC_CUSTOM _IOWR(ION_IOC_MAGIC, 6, \
+ struct compat_ion_custom_data)
+
+static int compat_get_ion_allocation_data(
+ struct compat_ion_allocation_data __user *data32,
+ struct ion_allocation_data __user *data)
+{
+ compat_size_t s;
+ compat_uint_t u;
+ compat_int_t i;
+ int err;
+
+ err = get_user(s, &data32->len);
+ err |= put_user(s, &data->len);
+ err |= get_user(s, &data32->align);
+ err |= put_user(s, &data->align);
+ err |= get_user(u, &data32->heap_id_mask);
+ err |= put_user(u, &data->heap_id_mask);
+ err |= get_user(u, &data32->flags);
+ err |= put_user(u, &data->flags);
+ err |= get_user(i, &data32->handle);
+ err |= put_user(i, &data->handle);
+
+ return err;
+}
+
+static int compat_get_ion_handle_data(
+ struct compat_ion_handle_data __user *data32,
+ struct ion_handle_data __user *data)
+{
+ compat_int_t i;
+ int err;
+
+ err = get_user(i, &data32->handle);
+ err |= put_user(i, &data->handle);
+
+ return err;
+}
+
+static int compat_put_ion_allocation_data(
+ struct compat_ion_allocation_data __user *data32,
+ struct ion_allocation_data __user *data)
+{
+ compat_size_t s;
+ compat_uint_t u;
+ compat_int_t i;
+ int err;
+
+ err = get_user(s, &data->len);
+ err |= put_user(s, &data32->len);
+ err |= get_user(s, &data->align);
+ err |= put_user(s, &data32->align);
+ err |= get_user(u, &data->heap_id_mask);
+ err |= put_user(u, &data32->heap_id_mask);
+ err |= get_user(u, &data->flags);
+ err |= put_user(u, &data32->flags);
+ err |= get_user(i, &data->handle);
+ err |= put_user(i, &data32->handle);
+
+ return err;
+}
+
+static int compat_get_ion_custom_data(
+ struct compat_ion_custom_data __user *data32,
+ struct ion_custom_data __user *data)
+{
+ compat_uint_t cmd;
+ compat_ulong_t arg;
+ int err;
+
+ err = get_user(cmd, &data32->cmd);
+ err |= put_user(cmd, &data->cmd);
+ err |= get_user(arg, &data32->arg);
+ err |= put_user(arg, &data->arg);
+
+ return err;
+};
+
+long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ long ret;
+
+ if (!filp->f_op || !filp->f_op->unlocked_ioctl)
+ return -ENOTTY;
+
+ switch (cmd) {
+ case COMPAT_ION_IOC_ALLOC:
+ {
+ struct compat_ion_allocation_data __user *data32;
+ struct ion_allocation_data __user *data;
+ int err;
+
+ data32 = compat_ptr(arg);
+ data = compat_alloc_user_space(sizeof(*data));
+ if (data == NULL)
+ return -EFAULT;
+
+ err = compat_get_ion_allocation_data(data32, data);
+ if (err)
+ return err;
+ ret = filp->f_op->unlocked_ioctl(filp, ION_IOC_ALLOC,
+ (unsigned long)data);
+ err = compat_put_ion_allocation_data(data32, data);
+ return ret ? ret : err;
+ }
+ case COMPAT_ION_IOC_FREE:
+ {
+ struct compat_ion_handle_data __user *data32;
+ struct ion_handle_data __user *data;
+ int err;
+
+ data32 = compat_ptr(arg);
+ data = compat_alloc_user_space(sizeof(*data));
+ if (data == NULL)
+ return -EFAULT;
+
+ err = compat_get_ion_handle_data(data32, data);
+ if (err)
+ return err;
+
+ return filp->f_op->unlocked_ioctl(filp, ION_IOC_FREE,
+ (unsigned long)data);
+ }
+ case COMPAT_ION_IOC_CUSTOM: {
+ struct compat_ion_custom_data __user *data32;
+ struct ion_custom_data __user *data;
+ int err;
+
+ data32 = compat_ptr(arg);
+ data = compat_alloc_user_space(sizeof(*data));
+ if (data == NULL)
+ return -EFAULT;
+
+ err = compat_get_ion_custom_data(data32, data);
+ if (err)
+ return err;
+
+ return filp->f_op->unlocked_ioctl(filp, ION_IOC_CUSTOM,
+ (unsigned long)data);
+ }
+ case ION_IOC_SHARE:
+ case ION_IOC_MAP:
+ case ION_IOC_IMPORT:
+ case ION_IOC_SYNC:
+ return filp->f_op->unlocked_ioctl(filp, cmd,
+ (unsigned long)compat_ptr(arg));
+ default:
+ return -ENOIOCTLCMD;
+ }
+}
diff --git a/drivers/staging/android/ion/compat_ion.h b/drivers/staging/android/ion/compat_ion.h
new file mode 100644
index 0000000..3a9c8c0
--- /dev/null
+++ b/drivers/staging/android/ion/compat_ion.h
@@ -0,0 +1,30 @@
+/*
+
+ * drivers/gpu/ion/compat_ion.h
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_COMPAT_ION_H
+#define _LINUX_COMPAT_ION_H
+
+#if IS_ENABLED(CONFIG_COMPAT)
+
+long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+
+#else
+
+#define compat_ion_ioctl NULL
+
+#endif /* CONFIG_COMPAT */
+#endif /* _LINUX_COMPAT_ION_H */
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
new file mode 100644
index 0000000..0e893a0
--- /dev/null
+++ b/drivers/staging/android/ion/ion.c
@@ -0,0 +1,1644 @@
+/*
+
+ * drivers/gpu/ion/ion.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/freezer.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/miscdevice.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/mm_types.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+#include <linux/idr.h>
+
+#include "ion.h"
+#include "ion_priv.h"
+#include "compat_ion.h"
+
+/**
+ * struct ion_device - the metadata of the ion device node
+ * @dev: the actual misc device
+ * @buffers: an rb tree of all the existing buffers
+ * @buffer_lock: lock protecting the tree of buffers
+ * @lock: rwsem protecting the tree of heaps and clients
+ * @heaps: list of all the heaps in the system
+ * @user_clients: list of all the clients created from userspace
+ */
+struct ion_device {
+ struct miscdevice dev;
+ struct rb_root buffers;
+ struct mutex buffer_lock;
+ struct rw_semaphore lock;
+ struct plist_head heaps;
+ long (*custom_ioctl) (struct ion_client *client, unsigned int cmd,
+ unsigned long arg);
+ struct rb_root clients;
+ struct dentry *debug_root;
+ struct dentry *heaps_debug_root;
+ struct dentry *clients_debug_root;
+};
+
+/**
+ * struct ion_client - a process/hw block local address space
+ * @node: node in the tree of all clients
+ * @dev: backpointer to ion device
+ * @handles: an rb tree of all the handles in this client
+ * @idr: an idr space for allocating handle ids
+ * @lock: lock protecting the tree of handles
+ * @name: used for debugging
+ * @display_name: used for debugging (unique version of @name)
+ * @display_serial: used for debugging (to make display_name unique)
+ * @task: used for debugging
+ *
+ * A client represents a list of buffers this client may access.
+ * The mutex stored here is used to protect both handles tree
+ * as well as the handles themselves, and should be held while modifying either.
+ */
+struct ion_client {
+ struct rb_node node;
+ struct ion_device *dev;
+ struct rb_root handles;
+ struct idr idr;
+ struct mutex lock;
+ const char *name;
+ char *display_name;
+ int display_serial;
+ struct task_struct *task;
+ pid_t pid;
+ struct dentry *debug_root;
+};
+
+/**
+ * ion_handle - a client local reference to a buffer
+ * @ref: reference count
+ * @client: back pointer to the client the buffer resides in
+ * @buffer: pointer to the buffer
+ * @node: node in the client's handle rbtree
+ * @kmap_cnt: count of times this client has mapped to kernel
+ * @id: client-unique id allocated by client->idr
+ *
+ * Modifications to node, map_cnt or mapping should be protected by the
+ * lock in the client. Other fields are never changed after initialization.
+ */
+struct ion_handle {
+ struct kref ref;
+ struct ion_client *client;
+ struct ion_buffer *buffer;
+ struct rb_node node;
+ unsigned int kmap_cnt;
+ int id;
+};
+
+bool ion_buffer_fault_user_mappings(struct ion_buffer *buffer)
+{
+ return (buffer->flags & ION_FLAG_CACHED) &&
+ !(buffer->flags & ION_FLAG_CACHED_NEEDS_SYNC);
+}
+
+bool ion_buffer_cached(struct ion_buffer *buffer)
+{
+ return !!(buffer->flags & ION_FLAG_CACHED);
+}
+
+static inline struct page *ion_buffer_page(struct page *page)
+{
+ return (struct page *)((unsigned long)page & ~(1UL));
+}
+
+static inline bool ion_buffer_page_is_dirty(struct page *page)
+{
+ return !!((unsigned long)page & 1UL);
+}
+
+static inline void ion_buffer_page_dirty(struct page **page)
+{
+ *page = (struct page *)((unsigned long)(*page) | 1UL);
+}
+
+static inline void ion_buffer_page_clean(struct page **page)
+{
+ *page = (struct page *)((unsigned long)(*page) & ~(1UL));
+}
+
+/* this function should only be called while dev->lock is held */
+static void ion_buffer_add(struct ion_device *dev,
+ struct ion_buffer *buffer)
+{
+ struct rb_node **p = &dev->buffers.rb_node;
+ struct rb_node *parent = NULL;
+ struct ion_buffer *entry;
+
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct ion_buffer, node);
+
+ if (buffer < entry) {
+ p = &(*p)->rb_left;
+ } else if (buffer > entry) {
+ p = &(*p)->rb_right;
+ } else {
+ pr_err("%s: buffer already found.", __func__);
+ BUG();
+ }
+ }
+
+ rb_link_node(&buffer->node, parent, p);
+ rb_insert_color(&buffer->node, &dev->buffers);
+}
+
+/* this function should only be called while dev->lock is held */
+static struct ion_buffer *ion_buffer_create(struct ion_heap *heap,
+ struct ion_device *dev,
+ unsigned long len,
+ unsigned long align,
+ unsigned long flags)
+{
+ struct ion_buffer *buffer;
+ struct sg_table *table;
+ struct scatterlist *sg;
+ int i, ret;
+
+ buffer = kzalloc(sizeof(struct ion_buffer), GFP_KERNEL);
+ if (!buffer)
+ return ERR_PTR(-ENOMEM);
+
+ buffer->heap = heap;
+ buffer->flags = flags;
+ kref_init(&buffer->ref);
+
+ ret = heap->ops->allocate(heap, buffer, len, align, flags);
+
+ if (ret) {
+ if (!(heap->flags & ION_HEAP_FLAG_DEFER_FREE))
+ goto err2;
+
+ ion_heap_freelist_drain(heap, 0);
+ ret = heap->ops->allocate(heap, buffer, len, align,
+ flags);
+ if (ret)
+ goto err2;
+ }
+
+ buffer->dev = dev;
+ buffer->size = len;
+
+ table = heap->ops->map_dma(heap, buffer);
+ if (WARN_ONCE(table == NULL,
+ "heap->ops->map_dma should return ERR_PTR on error"))
+ table = ERR_PTR(-EINVAL);
+ if (IS_ERR(table)) {
+ heap->ops->free(buffer);
+ kfree(buffer);
+ return ERR_PTR(PTR_ERR(table));
+ }
+ buffer->sg_table = table;
+ if (ion_buffer_fault_user_mappings(buffer)) {
+ int num_pages = PAGE_ALIGN(buffer->size) / PAGE_SIZE;
+ struct scatterlist *sg;
+ int i, j, k = 0;
+
+ buffer->pages = vmalloc(sizeof(struct page *) * num_pages);
+ if (!buffer->pages) {
+ ret = -ENOMEM;
+ goto err1;
+ }
+
+ for_each_sg(table->sgl, sg, table->nents, i) {
+ struct page *page = sg_page(sg);
+
+ for (j = 0; j < sg->length / PAGE_SIZE; j++)
+ buffer->pages[k++] = page++;
+ }
+
+ if (ret)
+ goto err;
+ }
+
+ buffer->dev = dev;
+ buffer->size = len;
+ INIT_LIST_HEAD(&buffer->vmas);
+ mutex_init(&buffer->lock);
+ /* this will set up dma addresses for the sglist -- it is not
+ technically correct as per the dma api -- a specific
+ device isn't really taking ownership here. However, in practice on
+ our systems the only dma_address space is physical addresses.
+ Additionally, we can't afford the overhead of invalidating every
+ allocation via dma_map_sg. The implicit contract here is that
+ memory comming from the heaps is ready for dma, ie if it has a
+ cached mapping that mapping has been invalidated */
+ for_each_sg(buffer->sg_table->sgl, sg, buffer->sg_table->nents, i)
+ sg_dma_address(sg) = sg_phys(sg);
+ mutex_lock(&dev->buffer_lock);
+ ion_buffer_add(dev, buffer);
+ mutex_unlock(&dev->buffer_lock);
+ return buffer;
+
+err:
+ heap->ops->unmap_dma(heap, buffer);
+ heap->ops->free(buffer);
+err1:
+ if (buffer->pages)
+ vfree(buffer->pages);
+err2:
+ kfree(buffer);
+ return ERR_PTR(ret);
+}
+
+void ion_buffer_destroy(struct ion_buffer *buffer)
+{
+ if (WARN_ON(buffer->kmap_cnt > 0))
+ buffer->heap->ops->unmap_kernel(buffer->heap, buffer);
+ buffer->heap->ops->unmap_dma(buffer->heap, buffer);
+ buffer->heap->ops->free(buffer);
+ if (buffer->pages)
+ vfree(buffer->pages);
+ kfree(buffer);
+}
+
+static void _ion_buffer_destroy(struct kref *kref)
+{
+ struct ion_buffer *buffer = container_of(kref, struct ion_buffer, ref);
+ struct ion_heap *heap = buffer->heap;
+ struct ion_device *dev = buffer->dev;
+
+ mutex_lock(&dev->buffer_lock);
+ rb_erase(&buffer->node, &dev->buffers);
+ mutex_unlock(&dev->buffer_lock);
+
+ if (heap->flags & ION_HEAP_FLAG_DEFER_FREE)
+ ion_heap_freelist_add(heap, buffer);
+ else
+ ion_buffer_destroy(buffer);
+}
+
+static void ion_buffer_get(struct ion_buffer *buffer)
+{
+ kref_get(&buffer->ref);
+}
+
+static int ion_buffer_put(struct ion_buffer *buffer)
+{
+ return kref_put(&buffer->ref, _ion_buffer_destroy);
+}
+
+static void ion_buffer_add_to_handle(struct ion_buffer *buffer)
+{
+ mutex_lock(&buffer->lock);
+ buffer->handle_count++;
+ mutex_unlock(&buffer->lock);
+}
+
+static void ion_buffer_remove_from_handle(struct ion_buffer *buffer)
+{
+ /*
+ * when a buffer is removed from a handle, if it is not in
+ * any other handles, copy the taskcomm and the pid of the
+ * process it's being removed from into the buffer. At this
+ * point there will be no way to track what processes this buffer is
+ * being used by, it only exists as a dma_buf file descriptor.
+ * The taskcomm and pid can provide a debug hint as to where this fd
+ * is in the system
+ */
+ mutex_lock(&buffer->lock);
+ buffer->handle_count--;
+ BUG_ON(buffer->handle_count < 0);
+ if (!buffer->handle_count) {
+ struct task_struct *task;
+
+ task = current->group_leader;
+ get_task_comm(buffer->task_comm, task);
+ buffer->pid = task_pid_nr(task);
+ }
+ mutex_unlock(&buffer->lock);
+}
+
+static struct ion_handle *ion_handle_create(struct ion_client *client,
+ struct ion_buffer *buffer)
+{
+ struct ion_handle *handle;
+
+ handle = kzalloc(sizeof(struct ion_handle), GFP_KERNEL);
+ if (!handle)
+ return ERR_PTR(-ENOMEM);
+ kref_init(&handle->ref);
+ RB_CLEAR_NODE(&handle->node);
+ handle->client = client;
+ ion_buffer_get(buffer);
+ ion_buffer_add_to_handle(buffer);
+ handle->buffer = buffer;
+
+ return handle;
+}
+
+static void ion_handle_kmap_put(struct ion_handle *);
+
+static void ion_handle_destroy(struct kref *kref)
+{
+ struct ion_handle *handle = container_of(kref, struct ion_handle, ref);
+ struct ion_client *client = handle->client;
+ struct ion_buffer *buffer = handle->buffer;
+
+ mutex_lock(&buffer->lock);
+ while (handle->kmap_cnt)
+ ion_handle_kmap_put(handle);
+ mutex_unlock(&buffer->lock);
+
+ idr_remove(&client->idr, handle->id);
+ if (!RB_EMPTY_NODE(&handle->node))
+ rb_erase(&handle->node, &client->handles);
+
+ ion_buffer_remove_from_handle(buffer);
+ ion_buffer_put(buffer);
+
+ kfree(handle);
+}
+
+struct ion_buffer *ion_handle_buffer(struct ion_handle *handle)
+{
+ return handle->buffer;
+}
+
+static void ion_handle_get(struct ion_handle *handle)
+{
+ kref_get(&handle->ref);
+}
+
+static int ion_handle_put(struct ion_handle *handle)
+{
+ struct ion_client *client = handle->client;
+ int ret;
+
+ mutex_lock(&client->lock);
+ ret = kref_put(&handle->ref, ion_handle_destroy);
+ mutex_unlock(&client->lock);
+
+ return ret;
+}
+
+static struct ion_handle *ion_handle_lookup(struct ion_client *client,
+ struct ion_buffer *buffer)
+{
+ struct rb_node *n = client->handles.rb_node;
+
+ while (n) {
+ struct ion_handle *entry = rb_entry(n, struct ion_handle, node);
+
+ if (buffer < entry->buffer)
+ n = n->rb_left;
+ else if (buffer > entry->buffer)
+ n = n->rb_right;
+ else
+ return entry;
+ }
+ return ERR_PTR(-EINVAL);
+}
+
+static struct ion_handle *ion_handle_get_by_id(struct ion_client *client,
+ int id)
+{
+ struct ion_handle *handle;
+
+ mutex_lock(&client->lock);
+ handle = idr_find(&client->idr, id);
+ if (handle)
+ ion_handle_get(handle);
+ mutex_unlock(&client->lock);
+
+ return handle ? handle : ERR_PTR(-EINVAL);
+}
+
+static bool ion_handle_validate(struct ion_client *client,
+ struct ion_handle *handle)
+{
+ WARN_ON(!mutex_is_locked(&client->lock));
+ return (idr_find(&client->idr, handle->id) == handle);
+}
+
+static int ion_handle_add(struct ion_client *client, struct ion_handle *handle)
+{
+ int id;
+ struct rb_node **p = &client->handles.rb_node;
+ struct rb_node *parent = NULL;
+ struct ion_handle *entry;
+
+ id = idr_alloc(&client->idr, handle, 1, 0, GFP_KERNEL);
+ if (id < 0)
+ return id;
+
+ handle->id = id;
+
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct ion_handle, node);
+
+ if (handle->buffer < entry->buffer)
+ p = &(*p)->rb_left;
+ else if (handle->buffer > entry->buffer)
+ p = &(*p)->rb_right;
+ else
+ WARN(1, "%s: buffer already found.", __func__);
+ }
+
+ rb_link_node(&handle->node, parent, p);
+ rb_insert_color(&handle->node, &client->handles);
+
+ return 0;
+}
+
+struct ion_handle *ion_alloc(struct ion_client *client, size_t len,
+ size_t align, unsigned int heap_id_mask,
+ unsigned int flags)
+{
+ struct ion_handle *handle;
+ struct ion_device *dev = client->dev;
+ struct ion_buffer *buffer = NULL;
+ struct ion_heap *heap;
+ int ret;
+
+ pr_debug("%s: len %zu align %zu heap_id_mask %u flags %x\n", __func__,
+ len, align, heap_id_mask, flags);
+ /*
+ * traverse the list of heaps available in this system in priority
+ * order. If the heap type is supported by the client, and matches the
+ * request of the caller allocate from it. Repeat until allocate has
+ * succeeded or all heaps have been tried
+ */
+ len = PAGE_ALIGN(len);
+
+ if (!len)
+ return ERR_PTR(-EINVAL);
+
+ down_read(&dev->lock);
+ plist_for_each_entry(heap, &dev->heaps, node) {
+ /* if the caller didn't specify this heap id */
+ if (!((1 << heap->id) & heap_id_mask))
+ continue;
+ buffer = ion_buffer_create(heap, dev, len, align, flags);
+ if (!IS_ERR(buffer))
+ break;
+ }
+ up_read(&dev->lock);
+
+ if (buffer == NULL)
+ return ERR_PTR(-ENODEV);
+
+ if (IS_ERR(buffer))
+ return ERR_PTR(PTR_ERR(buffer));
+
+ handle = ion_handle_create(client, buffer);
+
+ /*
+ * ion_buffer_create will create a buffer with a ref_cnt of 1,
+ * and ion_handle_create will take a second reference, drop one here
+ */
+ ion_buffer_put(buffer);
+
+ if (IS_ERR(handle))
+ return handle;
+
+ mutex_lock(&client->lock);
+ ret = ion_handle_add(client, handle);
+ mutex_unlock(&client->lock);
+ if (ret) {
+ ion_handle_put(handle);
+ handle = ERR_PTR(ret);
+ }
+
+ return handle;
+}
+EXPORT_SYMBOL(ion_alloc);
+
+void ion_free(struct ion_client *client, struct ion_handle *handle)
+{
+ bool valid_handle;
+
+ BUG_ON(client != handle->client);
+
+ mutex_lock(&client->lock);
+ valid_handle = ion_handle_validate(client, handle);
+
+ if (!valid_handle) {
+ WARN(1, "%s: invalid handle passed to free.\n", __func__);
+ mutex_unlock(&client->lock);
+ return;
+ }
+ mutex_unlock(&client->lock);
+ ion_handle_put(handle);
+}
+EXPORT_SYMBOL(ion_free);
+
+int ion_phys(struct ion_client *client, struct ion_handle *handle,
+ ion_phys_addr_t *addr, size_t *len)
+{
+ struct ion_buffer *buffer;
+ int ret;
+
+ mutex_lock(&client->lock);
+ if (!ion_handle_validate(client, handle)) {
+ mutex_unlock(&client->lock);
+ return -EINVAL;
+ }
+
+ buffer = handle->buffer;
+
+ if (!buffer->heap->ops->phys) {
+ pr_err("%s: ion_phys is not implemented by this heap.\n",
+ __func__);
+ mutex_unlock(&client->lock);
+ return -ENODEV;
+ }
+ mutex_unlock(&client->lock);
+ ret = buffer->heap->ops->phys(buffer->heap, buffer, addr, len);
+ return ret;
+}
+EXPORT_SYMBOL(ion_phys);
+
+static void *ion_buffer_kmap_get(struct ion_buffer *buffer)
+{
+ void *vaddr;
+
+ if (buffer->kmap_cnt) {
+ buffer->kmap_cnt++;
+ return buffer->vaddr;
+ }
+ vaddr = buffer->heap->ops->map_kernel(buffer->heap, buffer);
+ if (WARN_ONCE(vaddr == NULL,
+ "heap->ops->map_kernel should return ERR_PTR on error"))
+ return ERR_PTR(-EINVAL);
+ if (IS_ERR(vaddr))
+ return vaddr;
+ buffer->vaddr = vaddr;
+ buffer->kmap_cnt++;
+ return vaddr;
+}
+
+static void *ion_handle_kmap_get(struct ion_handle *handle)
+{
+ struct ion_buffer *buffer = handle->buffer;
+ void *vaddr;
+
+ if (handle->kmap_cnt) {
+ handle->kmap_cnt++;
+ return buffer->vaddr;
+ }
+ vaddr = ion_buffer_kmap_get(buffer);
+ if (IS_ERR(vaddr))
+ return vaddr;
+ handle->kmap_cnt++;
+ return vaddr;
+}
+
+static void ion_buffer_kmap_put(struct ion_buffer *buffer)
+{
+ buffer->kmap_cnt--;
+ if (!buffer->kmap_cnt) {
+ buffer->heap->ops->unmap_kernel(buffer->heap, buffer);
+ buffer->vaddr = NULL;
+ }
+}
+
+static void ion_handle_kmap_put(struct ion_handle *handle)
+{
+ struct ion_buffer *buffer = handle->buffer;
+
+ handle->kmap_cnt--;
+ if (!handle->kmap_cnt)
+ ion_buffer_kmap_put(buffer);
+}
+
+void *ion_map_kernel(struct ion_client *client, struct ion_handle *handle)
+{
+ struct ion_buffer *buffer;
+ void *vaddr;
+
+ mutex_lock(&client->lock);
+ if (!ion_handle_validate(client, handle)) {
+ pr_err("%s: invalid handle passed to map_kernel.\n",
+ __func__);
+ mutex_unlock(&client->lock);
+ return ERR_PTR(-EINVAL);
+ }
+
+ buffer = handle->buffer;
+
+ if (!handle->buffer->heap->ops->map_kernel) {
+ pr_err("%s: map_kernel is not implemented by this heap.\n",
+ __func__);
+ mutex_unlock(&client->lock);
+ return ERR_PTR(-ENODEV);
+ }
+
+ mutex_lock(&buffer->lock);
+ vaddr = ion_handle_kmap_get(handle);
+ mutex_unlock(&buffer->lock);
+ mutex_unlock(&client->lock);
+ return vaddr;
+}
+EXPORT_SYMBOL(ion_map_kernel);
+
+void ion_unmap_kernel(struct ion_client *client, struct ion_handle *handle)
+{
+ struct ion_buffer *buffer;
+
+ mutex_lock(&client->lock);
+ buffer = handle->buffer;
+ mutex_lock(&buffer->lock);
+ ion_handle_kmap_put(handle);
+ mutex_unlock(&buffer->lock);
+ mutex_unlock(&client->lock);
+}
+EXPORT_SYMBOL(ion_unmap_kernel);
+
+static int ion_debug_client_show(struct seq_file *s, void *unused)
+{
+ struct ion_client *client = s->private;
+ struct rb_node *n;
+ size_t sizes[ION_NUM_HEAP_IDS] = {0};
+ const char *names[ION_NUM_HEAP_IDS] = {NULL};
+ int i;
+
+ mutex_lock(&client->lock);
+ for (n = rb_first(&client->handles); n; n = rb_next(n)) {
+ struct ion_handle *handle = rb_entry(n, struct ion_handle,
+ node);
+ unsigned int id = handle->buffer->heap->id;
+
+ if (!names[id])
+ names[id] = handle->buffer->heap->name;
+ sizes[id] += handle->buffer->size;
+ }
+ mutex_unlock(&client->lock);
+
+ seq_printf(s, "%16.16s: %16.16s\n", "heap_name", "size_in_bytes");
+ for (i = 0; i < ION_NUM_HEAP_IDS; i++) {
+ if (!names[i])
+ continue;
+ seq_printf(s, "%16.16s: %16zu\n", names[i], sizes[i]);
+ }
+ return 0;
+}
+
+static int ion_debug_client_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ion_debug_client_show, inode->i_private);
+}
+
+static const struct file_operations debug_client_fops = {
+ .open = ion_debug_client_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int ion_get_client_serial(const struct rb_root *root,
+ const unsigned char *name)
+{
+ int serial = -1;
+ struct rb_node *node;
+
+ for (node = rb_first(root); node; node = rb_next(node)) {
+ struct ion_client *client = rb_entry(node, struct ion_client,
+ node);
+
+ if (strcmp(client->name, name))
+ continue;
+ serial = max(serial, client->display_serial);
+ }
+ return serial + 1;
+}
+
+struct ion_client *ion_client_create(struct ion_device *dev,
+ const char *name)
+{
+ struct ion_client *client;
+ struct task_struct *task;
+ struct rb_node **p;
+ struct rb_node *parent = NULL;
+ struct ion_client *entry;
+ pid_t pid;
+
+ if (!name) {
+ pr_err("%s: Name cannot be null\n", __func__);
+ return ERR_PTR(-EINVAL);
+ }
+
+ get_task_struct(current->group_leader);
+ task_lock(current->group_leader);
+ pid = task_pid_nr(current->group_leader);
+ /* don't bother to store task struct for kernel threads,
+ they can't be killed anyway */
+ if (current->group_leader->flags & PF_KTHREAD) {
+ put_task_struct(current->group_leader);
+ task = NULL;
+ } else {
+ task = current->group_leader;
+ }
+ task_unlock(current->group_leader);
+
+ client = kzalloc(sizeof(struct ion_client), GFP_KERNEL);
+ if (!client)
+ goto err_put_task_struct;
+
+ client->dev = dev;
+ client->handles = RB_ROOT;
+ idr_init(&client->idr);
+ mutex_init(&client->lock);
+ client->task = task;
+ client->pid = pid;
+ client->name = kstrdup(name, GFP_KERNEL);
+ if (!client->name)
+ goto err_free_client;
+
+ down_write(&dev->lock);
+ client->display_serial = ion_get_client_serial(&dev->clients, name);
+ client->display_name = kasprintf(
+ GFP_KERNEL, "%s-%d", name, client->display_serial);
+ if (!client->display_name) {
+ up_write(&dev->lock);
+ goto err_free_client_name;
+ }
+ p = &dev->clients.rb_node;
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct ion_client, node);
+
+ if (client < entry)
+ p = &(*p)->rb_left;
+ else if (client > entry)
+ p = &(*p)->rb_right;
+ }
+ rb_link_node(&client->node, parent, p);
+ rb_insert_color(&client->node, &dev->clients);
+
+ client->debug_root = debugfs_create_file(client->display_name, 0664,
+ dev->clients_debug_root,
+ client, &debug_client_fops);
+ if (!client->debug_root) {
+ char buf[256], *path;
+ path = dentry_path(dev->clients_debug_root, buf, 256);
+ pr_err("Failed to create client debugfs at %s/%s\n",
+ path, client->display_name);
+ }
+
+ up_write(&dev->lock);
+
+ return client;
+
+err_free_client_name:
+ kfree(client->name);
+err_free_client:
+ kfree(client);
+err_put_task_struct:
+ if (task)
+ put_task_struct(current->group_leader);
+ return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL(ion_client_create);
+
+void ion_client_destroy(struct ion_client *client)
+{
+ struct ion_device *dev = client->dev;
+ struct rb_node *n;
+
+ pr_debug("%s: %d\n", __func__, __LINE__);
+ while ((n = rb_first(&client->handles))) {
+ struct ion_handle *handle = rb_entry(n, struct ion_handle,
+ node);
+ ion_handle_destroy(&handle->ref);
+ }
+
+ idr_destroy(&client->idr);
+
+ down_write(&dev->lock);
+ if (client->task)
+ put_task_struct(client->task);
+ rb_erase(&client->node, &dev->clients);
+ debugfs_remove_recursive(client->debug_root);
+ up_write(&dev->lock);
+
+ kfree(client->display_name);
+ kfree(client->name);
+ kfree(client);
+}
+EXPORT_SYMBOL(ion_client_destroy);
+
+struct sg_table *ion_sg_table(struct ion_client *client,
+ struct ion_handle *handle)
+{
+ struct ion_buffer *buffer;
+ struct sg_table *table;
+
+ mutex_lock(&client->lock);
+ if (!ion_handle_validate(client, handle)) {
+ pr_err("%s: invalid handle passed to map_dma.\n",
+ __func__);
+ mutex_unlock(&client->lock);
+ return ERR_PTR(-EINVAL);
+ }
+ buffer = handle->buffer;
+ table = buffer->sg_table;
+ mutex_unlock(&client->lock);
+ return table;
+}
+EXPORT_SYMBOL(ion_sg_table);
+
+static void ion_buffer_sync_for_device(struct ion_buffer *buffer,
+ struct device *dev,
+ enum dma_data_direction direction);
+
+static struct sg_table *ion_map_dma_buf(struct dma_buf_attachment *attachment,
+ enum dma_data_direction direction)
+{
+ struct dma_buf *dmabuf = attachment->dmabuf;
+ struct ion_buffer *buffer = dmabuf->priv;
+
+ ion_buffer_sync_for_device(buffer, attachment->dev, direction);
+ return buffer->sg_table;
+}
+
+static void ion_unmap_dma_buf(struct dma_buf_attachment *attachment,
+ struct sg_table *table,
+ enum dma_data_direction direction)
+{
+}
+
+void ion_pages_sync_for_device(struct device *dev, struct page *page,
+ size_t size, enum dma_data_direction dir)
+{
+ struct scatterlist sg;
+
+ sg_init_table(&sg, 1);
+ sg_set_page(&sg, page, size, 0);
+ /*
+ * This is not correct - sg_dma_address needs a dma_addr_t that is valid
+ * for the the targeted device, but this works on the currently targeted
+ * hardware.
+ */
+ sg_dma_address(&sg) = page_to_phys(page);
+ dma_sync_sg_for_device(dev, &sg, 1, dir);
+}
+
+struct ion_vma_list {
+ struct list_head list;
+ struct vm_area_struct *vma;
+};
+
+static void ion_buffer_sync_for_device(struct ion_buffer *buffer,
+ struct device *dev,
+ enum dma_data_direction dir)
+{
+ struct ion_vma_list *vma_list;
+ int pages = PAGE_ALIGN(buffer->size) / PAGE_SIZE;
+ int i;
+
+ pr_debug("%s: syncing for device %s\n", __func__,
+ dev ? dev_name(dev) : "null");
+
+ if (!ion_buffer_fault_user_mappings(buffer))
+ return;
+
+ mutex_lock(&buffer->lock);
+ for (i = 0; i < pages; i++) {
+ struct page *page = buffer->pages[i];
+
+ if (ion_buffer_page_is_dirty(page))
+ ion_pages_sync_for_device(dev, ion_buffer_page(page),
+ PAGE_SIZE, dir);
+
+ ion_buffer_page_clean(buffer->pages + i);
+ }
+ list_for_each_entry(vma_list, &buffer->vmas, list) {
+ struct vm_area_struct *vma = vma_list->vma;
+
+ zap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start,
+ NULL);
+ }
+ mutex_unlock(&buffer->lock);
+}
+
+static int ion_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct ion_buffer *buffer = vma->vm_private_data;
+ unsigned long pfn;
+ int ret;
+
+ mutex_lock(&buffer->lock);
+ ion_buffer_page_dirty(buffer->pages + vmf->pgoff);
+ BUG_ON(!buffer->pages || !buffer->pages[vmf->pgoff]);
+
+ pfn = page_to_pfn(ion_buffer_page(buffer->pages[vmf->pgoff]));
+ ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+ mutex_unlock(&buffer->lock);
+ if (ret)
+ return VM_FAULT_ERROR;
+
+ return VM_FAULT_NOPAGE;
+}
+
+static void ion_vm_open(struct vm_area_struct *vma)
+{
+ struct ion_buffer *buffer = vma->vm_private_data;
+ struct ion_vma_list *vma_list;
+
+ vma_list = kmalloc(sizeof(struct ion_vma_list), GFP_KERNEL);
+ if (!vma_list)
+ return;
+ vma_list->vma = vma;
+ mutex_lock(&buffer->lock);
+ list_add(&vma_list->list, &buffer->vmas);
+ mutex_unlock(&buffer->lock);
+ pr_debug("%s: adding %p\n", __func__, vma);
+}
+
+static void ion_vm_close(struct vm_area_struct *vma)
+{
+ struct ion_buffer *buffer = vma->vm_private_data;
+ struct ion_vma_list *vma_list, *tmp;
+
+ pr_debug("%s\n", __func__);
+ mutex_lock(&buffer->lock);
+ list_for_each_entry_safe(vma_list, tmp, &buffer->vmas, list) {
+ if (vma_list->vma != vma)
+ continue;
+ list_del(&vma_list->list);
+ kfree(vma_list);
+ pr_debug("%s: deleting %p\n", __func__, vma);
+ break;
+ }
+ mutex_unlock(&buffer->lock);
+}
+
+static struct vm_operations_struct ion_vma_ops = {
+ .open = ion_vm_open,
+ .close = ion_vm_close,
+ .fault = ion_vm_fault,
+};
+
+static int ion_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+ struct ion_buffer *buffer = dmabuf->priv;
+ int ret = 0;
+
+ if (!buffer->heap->ops->map_user) {
+ pr_err("%s: this heap does not define a method for mapping "
+ "to userspace\n", __func__);
+ return -EINVAL;
+ }
+
+ if (ion_buffer_fault_user_mappings(buffer)) {
+ vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND |
+ VM_DONTDUMP;
+ vma->vm_private_data = buffer;
+ vma->vm_ops = &ion_vma_ops;
+ ion_vm_open(vma);
+ return 0;
+ }
+
+ if (!(buffer->flags & ION_FLAG_CACHED))
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+
+ mutex_lock(&buffer->lock);
+ /* now map it to userspace */
+ ret = buffer->heap->ops->map_user(buffer->heap, buffer, vma);
+ mutex_unlock(&buffer->lock);
+
+ if (ret)
+ pr_err("%s: failure mapping buffer to userspace\n",
+ __func__);
+
+ return ret;
+}
+
+static void ion_dma_buf_release(struct dma_buf *dmabuf)
+{
+ struct ion_buffer *buffer = dmabuf->priv;
+
+ ion_buffer_put(buffer);
+}
+
+static void *ion_dma_buf_kmap(struct dma_buf *dmabuf, unsigned long offset)
+{
+ struct ion_buffer *buffer = dmabuf->priv;
+
+ return buffer->vaddr + offset * PAGE_SIZE;
+}
+
+static void ion_dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long offset,
+ void *ptr)
+{
+ return;
+}
+
+static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, size_t start,
+ size_t len,
+ enum dma_data_direction direction)
+{
+ struct ion_buffer *buffer = dmabuf->priv;
+ void *vaddr;
+
+ if (!buffer->heap->ops->map_kernel) {
+ pr_err("%s: map kernel is not implemented by this heap.\n",
+ __func__);
+ return -ENODEV;
+ }
+
+ mutex_lock(&buffer->lock);
+ vaddr = ion_buffer_kmap_get(buffer);
+ mutex_unlock(&buffer->lock);
+ if (IS_ERR(vaddr))
+ return PTR_ERR(vaddr);
+ return 0;
+}
+
+static void ion_dma_buf_end_cpu_access(struct dma_buf *dmabuf, size_t start,
+ size_t len,
+ enum dma_data_direction direction)
+{
+ struct ion_buffer *buffer = dmabuf->priv;
+
+ mutex_lock(&buffer->lock);
+ ion_buffer_kmap_put(buffer);
+ mutex_unlock(&buffer->lock);
+}
+
+static struct dma_buf_ops dma_buf_ops = {
+ .map_dma_buf = ion_map_dma_buf,
+ .unmap_dma_buf = ion_unmap_dma_buf,
+ .mmap = ion_mmap,
+ .release = ion_dma_buf_release,
+ .begin_cpu_access = ion_dma_buf_begin_cpu_access,
+ .end_cpu_access = ion_dma_buf_end_cpu_access,
+ .kmap_atomic = ion_dma_buf_kmap,
+ .kunmap_atomic = ion_dma_buf_kunmap,
+ .kmap = ion_dma_buf_kmap,
+ .kunmap = ion_dma_buf_kunmap,
+};
+
+struct dma_buf *ion_share_dma_buf(struct ion_client *client,
+ struct ion_handle *handle)
+{
+ struct ion_buffer *buffer;
+ struct dma_buf *dmabuf;
+ bool valid_handle;
+
+ mutex_lock(&client->lock);
+ valid_handle = ion_handle_validate(client, handle);
+ if (!valid_handle) {
+ WARN(1, "%s: invalid handle passed to share.\n", __func__);
+ mutex_unlock(&client->lock);
+ return ERR_PTR(-EINVAL);
+ }
+ buffer = handle->buffer;
+ ion_buffer_get(buffer);
+ mutex_unlock(&client->lock);
+
+ dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR);
+ if (IS_ERR(dmabuf)) {
+ ion_buffer_put(buffer);
+ return dmabuf;
+ }
+
+ return dmabuf;
+}
+EXPORT_SYMBOL(ion_share_dma_buf);
+
+int ion_share_dma_buf_fd(struct ion_client *client, struct ion_handle *handle)
+{
+ struct dma_buf *dmabuf;
+ int fd;
+
+ dmabuf = ion_share_dma_buf(client, handle);
+ if (IS_ERR(dmabuf))
+ return PTR_ERR(dmabuf);
+
+ fd = dma_buf_fd(dmabuf, O_CLOEXEC);
+ if (fd < 0)
+ dma_buf_put(dmabuf);
+
+ return fd;
+}
+EXPORT_SYMBOL(ion_share_dma_buf_fd);
+
+struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd)
+{
+ struct dma_buf *dmabuf;
+ struct ion_buffer *buffer;
+ struct ion_handle *handle;
+ int ret;
+
+ dmabuf = dma_buf_get(fd);
+ if (IS_ERR(dmabuf))
+ return ERR_PTR(PTR_ERR(dmabuf));
+ /* if this memory came from ion */
+
+ if (dmabuf->ops != &dma_buf_ops) {
+ pr_err("%s: can not import dmabuf from another exporter\n",
+ __func__);
+ dma_buf_put(dmabuf);
+ return ERR_PTR(-EINVAL);
+ }
+ buffer = dmabuf->priv;
+
+ mutex_lock(&client->lock);
+ /* if a handle exists for this buffer just take a reference to it */
+ handle = ion_handle_lookup(client, buffer);
+ if (!IS_ERR(handle)) {
+ ion_handle_get(handle);
+ mutex_unlock(&client->lock);
+ goto end;
+ }
+
+ handle = ion_handle_create(client, buffer);
+ if (IS_ERR(handle)) {
+ mutex_unlock(&client->lock);
+ goto end;
+ }
+
+ ret = ion_handle_add(client, handle);
+ mutex_unlock(&client->lock);
+ if (ret) {
+ ion_handle_put(handle);
+ handle = ERR_PTR(ret);
+ }
+
+end:
+ dma_buf_put(dmabuf);
+ return handle;
+}
+EXPORT_SYMBOL(ion_import_dma_buf);
+
+static int ion_sync_for_device(struct ion_client *client, int fd)
+{
+ struct dma_buf *dmabuf;
+ struct ion_buffer *buffer;
+
+ dmabuf = dma_buf_get(fd);
+ if (IS_ERR(dmabuf))
+ return PTR_ERR(dmabuf);
+
+ /* if this memory came from ion */
+ if (dmabuf->ops != &dma_buf_ops) {
+ pr_err("%s: can not sync dmabuf from another exporter\n",
+ __func__);
+ dma_buf_put(dmabuf);
+ return -EINVAL;
+ }
+ buffer = dmabuf->priv;
+
+ dma_sync_sg_for_device(NULL, buffer->sg_table->sgl,
+ buffer->sg_table->nents, DMA_BIDIRECTIONAL);
+ dma_buf_put(dmabuf);
+ return 0;
+}
+
+/* fix up the cases where the ioctl direction bits are incorrect */
+static unsigned int ion_ioctl_dir(unsigned int cmd)
+{
+ switch (cmd) {
+ case ION_IOC_SYNC:
+ case ION_IOC_FREE:
+ case ION_IOC_CUSTOM:
+ return _IOC_WRITE;
+ default:
+ return _IOC_DIR(cmd);
+ }
+}
+
+static long ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct ion_client *client = filp->private_data;
+ struct ion_device *dev = client->dev;
+ struct ion_handle *cleanup_handle = NULL;
+ int ret = 0;
+ unsigned int dir;
+
+ union {
+ struct ion_fd_data fd;
+ struct ion_allocation_data allocation;
+ struct ion_handle_data handle;
+ struct ion_custom_data custom;
+ } data;
+
+ dir = ion_ioctl_dir(cmd);
+
+ if (_IOC_SIZE(cmd) > sizeof(data))
+ return -EINVAL;
+
+ if (dir & _IOC_WRITE)
+ if (copy_from_user(&data, (void __user *)arg, _IOC_SIZE(cmd)))
+ return -EFAULT;
+
+ switch (cmd) {
+ case ION_IOC_ALLOC:
+ {
+ struct ion_handle *handle;
+
+ handle = ion_alloc(client, data.allocation.len,
+ data.allocation.align,
+ data.allocation.heap_id_mask,
+ data.allocation.flags);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ data.allocation.handle = handle->id;
+
+ cleanup_handle = handle;
+ break;
+ }
+ case ION_IOC_FREE:
+ {
+ struct ion_handle *handle;
+
+ handle = ion_handle_get_by_id(client, data.handle.handle);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ion_free(client, handle);
+ ion_handle_put(handle);
+ break;
+ }
+ case ION_IOC_SHARE:
+ case ION_IOC_MAP:
+ {
+ struct ion_handle *handle;
+
+ handle = ion_handle_get_by_id(client, data.handle.handle);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ data.fd.fd = ion_share_dma_buf_fd(client, handle);
+ ion_handle_put(handle);
+ if (data.fd.fd < 0)
+ ret = data.fd.fd;
+ break;
+ }
+ case ION_IOC_IMPORT:
+ {
+ struct ion_handle *handle;
+
+ handle = ion_import_dma_buf(client, data.fd.fd);
+ if (IS_ERR(handle))
+ ret = PTR_ERR(handle);
+ else
+ data.handle.handle = handle->id;
+ break;
+ }
+ case ION_IOC_SYNC:
+ {
+ ret = ion_sync_for_device(client, data.fd.fd);
+ break;
+ }
+ case ION_IOC_CUSTOM:
+ {
+ if (!dev->custom_ioctl)
+ return -ENOTTY;
+ ret = dev->custom_ioctl(client, data.custom.cmd,
+ data.custom.arg);
+ break;
+ }
+ default:
+ return -ENOTTY;
+ }
+
+ if (dir & _IOC_READ) {
+ if (copy_to_user((void __user *)arg, &data, _IOC_SIZE(cmd))) {
+ if (cleanup_handle)
+ ion_free(client, cleanup_handle);
+ return -EFAULT;
+ }
+ }
+ return ret;
+}
+
+static int ion_release(struct inode *inode, struct file *file)
+{
+ struct ion_client *client = file->private_data;
+
+ pr_debug("%s: %d\n", __func__, __LINE__);
+ ion_client_destroy(client);
+ return 0;
+}
+
+static int ion_open(struct inode *inode, struct file *file)
+{
+ struct miscdevice *miscdev = file->private_data;
+ struct ion_device *dev = container_of(miscdev, struct ion_device, dev);
+ struct ion_client *client;
+ char debug_name[64];
+
+ pr_debug("%s: %d\n", __func__, __LINE__);
+ snprintf(debug_name, 64, "%u", task_pid_nr(current->group_leader));
+ client = ion_client_create(dev, debug_name);
+ if (IS_ERR(client))
+ return PTR_ERR(client);
+ file->private_data = client;
+
+ return 0;
+}
+
+static const struct file_operations ion_fops = {
+ .owner = THIS_MODULE,
+ .open = ion_open,
+ .release = ion_release,
+ .unlocked_ioctl = ion_ioctl,
+ .compat_ioctl = compat_ion_ioctl,
+};
+
+static size_t ion_debug_heap_total(struct ion_client *client,
+ unsigned int id)
+{
+ size_t size = 0;
+ struct rb_node *n;
+
+ mutex_lock(&client->lock);
+ for (n = rb_first(&client->handles); n; n = rb_next(n)) {
+ struct ion_handle *handle = rb_entry(n,
+ struct ion_handle,
+ node);
+ if (handle->buffer->heap->id == id)
+ size += handle->buffer->size;
+ }
+ mutex_unlock(&client->lock);
+ return size;
+}
+
+static int ion_debug_heap_show(struct seq_file *s, void *unused)
+{
+ struct ion_heap *heap = s->private;
+ struct ion_device *dev = heap->dev;
+ struct rb_node *n;
+ size_t total_size = 0;
+ size_t total_orphaned_size = 0;
+
+ seq_printf(s, "%16.s %16.s %16.s\n", "client", "pid", "size");
+ seq_printf(s, "----------------------------------------------------\n");
+
+ for (n = rb_first(&dev->clients); n; n = rb_next(n)) {
+ struct ion_client *client = rb_entry(n, struct ion_client,
+ node);
+ size_t size = ion_debug_heap_total(client, heap->id);
+
+ if (!size)
+ continue;
+ if (client->task) {
+ char task_comm[TASK_COMM_LEN];
+
+ get_task_comm(task_comm, client->task);
+ seq_printf(s, "%16.s %16u %16zu\n", task_comm,
+ client->pid, size);
+ } else {
+ seq_printf(s, "%16.s %16u %16zu\n", client->name,
+ client->pid, size);
+ }
+ }
+ seq_printf(s, "----------------------------------------------------\n");
+ seq_printf(s, "orphaned allocations (info is from last known client):"
+ "\n");
+ mutex_lock(&dev->buffer_lock);
+ for (n = rb_first(&dev->buffers); n; n = rb_next(n)) {
+ struct ion_buffer *buffer = rb_entry(n, struct ion_buffer,
+ node);
+ if (buffer->heap->id != heap->id)
+ continue;
+ total_size += buffer->size;
+ if (!buffer->handle_count) {
+ seq_printf(s, "%16.s %16u %16zu %d %d\n",
+ buffer->task_comm, buffer->pid,
+ buffer->size, buffer->kmap_cnt,
+ atomic_read(&buffer->ref.refcount));
+ total_orphaned_size += buffer->size;
+ }
+ }
+ mutex_unlock(&dev->buffer_lock);
+ seq_printf(s, "----------------------------------------------------\n");
+ seq_printf(s, "%16.s %16zu\n", "total orphaned",
+ total_orphaned_size);
+ seq_printf(s, "%16.s %16zu\n", "total ", total_size);
+ if (heap->flags & ION_HEAP_FLAG_DEFER_FREE)
+ seq_printf(s, "%16.s %16zu\n", "deferred free",
+ heap->free_list_size);
+ seq_printf(s, "----------------------------------------------------\n");
+
+ if (heap->debug_show)
+ heap->debug_show(heap, s, unused);
+
+ return 0;
+}
+
+static int ion_debug_heap_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ion_debug_heap_show, inode->i_private);
+}
+
+static const struct file_operations debug_heap_fops = {
+ .open = ion_debug_heap_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#ifdef DEBUG_HEAP_SHRINKER
+static int debug_shrink_set(void *data, u64 val)
+{
+ struct ion_heap *heap = data;
+ struct shrink_control sc;
+ int objs;
+
+ sc.gfp_mask = -1;
+ sc.nr_to_scan = 0;
+
+ if (!val)
+ return 0;
+
+ objs = heap->shrinker.shrink(&heap->shrinker, &sc);
+ sc.nr_to_scan = objs;
+
+ heap->shrinker.shrink(&heap->shrinker, &sc);
+ return 0;
+}
+
+static int debug_shrink_get(void *data, u64 *val)
+{
+ struct ion_heap *heap = data;
+ struct shrink_control sc;
+ int objs;
+
+ sc.gfp_mask = -1;
+ sc.nr_to_scan = 0;
+
+ objs = heap->shrinker.shrink(&heap->shrinker, &sc);
+ *val = objs;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(debug_shrink_fops, debug_shrink_get,
+ debug_shrink_set, "%llu\n");
+#endif
+
+void ion_device_add_heap(struct ion_device *dev, struct ion_heap *heap)
+{
+ struct dentry *debug_file;
+
+ if (!heap->ops->allocate || !heap->ops->free || !heap->ops->map_dma ||
+ !heap->ops->unmap_dma)
+ pr_err("%s: can not add heap with invalid ops struct.\n",
+ __func__);
+
+ if (heap->flags & ION_HEAP_FLAG_DEFER_FREE)
+ ion_heap_init_deferred_free(heap);
+
+ if ((heap->flags & ION_HEAP_FLAG_DEFER_FREE) || heap->ops->shrink)
+ ion_heap_init_shrinker(heap);
+
+ heap->dev = dev;
+ down_write(&dev->lock);
+ /* use negative heap->id to reverse the priority -- when traversing
+ the list later attempt higher id numbers first */
+ plist_node_init(&heap->node, -heap->id);
+ plist_add(&heap->node, &dev->heaps);
+ debug_file = debugfs_create_file(heap->name, 0664,
+ dev->heaps_debug_root, heap,
+ &debug_heap_fops);
+
+ if (!debug_file) {
+ char buf[256], *path;
+
+ path = dentry_path(dev->heaps_debug_root, buf, 256);
+ pr_err("Failed to create heap debugfs at %s/%s\n",
+ path, heap->name);
+ }
+
+#ifdef DEBUG_HEAP_SHRINKER
+ if (heap->shrinker.shrink) {
+ char debug_name[64];
+
+ snprintf(debug_name, 64, "%s_shrink", heap->name);
+ debug_file = debugfs_create_file(
+ debug_name, 0644, dev->heaps_debug_root, heap,
+ &debug_shrink_fops);
+ if (!debug_file) {
+ char buf[256], *path;
+
+ path = dentry_path(dev->heaps_debug_root, buf, 256);
+ pr_err("Failed to create heap shrinker debugfs at %s/%s\n",
+ path, debug_name);
+ }
+ }
+#endif
+ up_write(&dev->lock);
+}
+
+struct ion_device *ion_device_create(long (*custom_ioctl)
+ (struct ion_client *client,
+ unsigned int cmd,
+ unsigned long arg))
+{
+ struct ion_device *idev;
+ int ret;
+
+ idev = kzalloc(sizeof(struct ion_device), GFP_KERNEL);
+ if (!idev)
+ return ERR_PTR(-ENOMEM);
+
+ idev->dev.minor = MISC_DYNAMIC_MINOR;
+ idev->dev.name = "ion";
+ idev->dev.fops = &ion_fops;
+ idev->dev.parent = NULL;
+ ret = misc_register(&idev->dev);
+ if (ret) {
+ pr_err("ion: failed to register misc device.\n");
+ return ERR_PTR(ret);
+ }
+
+ idev->debug_root = debugfs_create_dir("ion", NULL);
+ if (!idev->debug_root) {
+ pr_err("ion: failed to create debugfs root directory.\n");
+ goto debugfs_done;
+ }
+ idev->heaps_debug_root = debugfs_create_dir("heaps", idev->debug_root);
+ if (!idev->heaps_debug_root) {
+ pr_err("ion: failed to create debugfs heaps directory.\n");
+ goto debugfs_done;
+ }
+ idev->clients_debug_root = debugfs_create_dir("clients",
+ idev->debug_root);
+ if (!idev->clients_debug_root)
+ pr_err("ion: failed to create debugfs clients directory.\n");
+
+debugfs_done:
+
+ idev->custom_ioctl = custom_ioctl;
+ idev->buffers = RB_ROOT;
+ mutex_init(&idev->buffer_lock);
+ init_rwsem(&idev->lock);
+ plist_head_init(&idev->heaps);
+ idev->clients = RB_ROOT;
+ return idev;
+}
+
+void ion_device_destroy(struct ion_device *dev)
+{
+ misc_deregister(&dev->dev);
+ debugfs_remove_recursive(dev->debug_root);
+ /* XXX need to free the heaps and clients ? */
+ kfree(dev);
+}
+
+void __init ion_reserve(struct ion_platform_data *data)
+{
+ int i;
+
+ for (i = 0; i < data->nr; i++) {
+ if (data->heaps[i].size == 0)
+ continue;
+
+ if (data->heaps[i].base == 0) {
+ phys_addr_t paddr;
+
+ paddr = memblock_alloc_base(data->heaps[i].size,
+ data->heaps[i].align,
+ MEMBLOCK_ALLOC_ANYWHERE);
+ if (!paddr) {
+ pr_err("%s: error allocating memblock for "
+ "heap %d\n",
+ __func__, i);
+ continue;
+ }
+ data->heaps[i].base = paddr;
+ } else {
+ int ret = memblock_reserve(data->heaps[i].base,
+ data->heaps[i].size);
+ if (ret)
+ pr_err("memblock reserve of %zx@%lx failed\n",
+ data->heaps[i].size,
+ data->heaps[i].base);
+ }
+ pr_info("%s: %s reserved base %lx size %zu\n", __func__,
+ data->heaps[i].name,
+ data->heaps[i].base,
+ data->heaps[i].size);
+ }
+}
diff --git a/drivers/staging/android/ion/ion.h b/drivers/staging/android/ion/ion.h
new file mode 100644
index 0000000..dcd2a0c
--- /dev/null
+++ b/drivers/staging/android/ion/ion.h
@@ -0,0 +1,204 @@
+/*
+ * drivers/staging/android/ion/ion.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_ION_H
+#define _LINUX_ION_H
+
+#include <linux/types.h>
+
+#include "../uapi/ion.h"
+
+struct ion_handle;
+struct ion_device;
+struct ion_heap;
+struct ion_mapper;
+struct ion_client;
+struct ion_buffer;
+
+/* This should be removed some day when phys_addr_t's are fully
+ plumbed in the kernel, and all instances of ion_phys_addr_t should
+ be converted to phys_addr_t. For the time being many kernel interfaces
+ do not accept phys_addr_t's that would have to */
+#define ion_phys_addr_t unsigned long
+
+/**
+ * struct ion_platform_heap - defines a heap in the given platform
+ * @type: type of the heap from ion_heap_type enum
+ * @id: unique identifier for heap. When allocating higher numbers
+ * will be allocated from first. At allocation these are passed
+ * as a bit mask and therefore can not exceed ION_NUM_HEAP_IDS.
+ * @name: used for debug purposes
+ * @base: base address of heap in physical memory if applicable
+ * @size: size of the heap in bytes if applicable
+ * @align: required alignment in physical memory if applicable
+ * @priv: private info passed from the board file
+ *
+ * Provided by the board file.
+ */
+struct ion_platform_heap {
+ enum ion_heap_type type;
+ unsigned int id;
+ const char *name;
+ ion_phys_addr_t base;
+ size_t size;
+ ion_phys_addr_t align;
+ void *priv;
+};
+
+/**
+ * struct ion_platform_data - array of platform heaps passed from board file
+ * @nr: number of structures in the array
+ * @heaps: array of platform_heap structions
+ *
+ * Provided by the board file in the form of platform data to a platform device.
+ */
+struct ion_platform_data {
+ int nr;
+ struct ion_platform_heap *heaps;
+};
+
+/**
+ * ion_reserve() - reserve memory for ion heaps if applicable
+ * @data: platform data specifying starting physical address and
+ * size
+ *
+ * Calls memblock reserve to set aside memory for heaps that are
+ * located at specific memory addresses or of specfic sizes not
+ * managed by the kernel
+ */
+void ion_reserve(struct ion_platform_data *data);
+
+/**
+ * ion_client_create() - allocate a client and returns it
+ * @dev: the global ion device
+ * @heap_type_mask: mask of heaps this client can allocate from
+ * @name: used for debugging
+ */
+struct ion_client *ion_client_create(struct ion_device *dev,
+ const char *name);
+
+/**
+ * ion_client_destroy() - free's a client and all it's handles
+ * @client: the client
+ *
+ * Free the provided client and all it's resources including
+ * any handles it is holding.
+ */
+void ion_client_destroy(struct ion_client *client);
+
+/**
+ * ion_alloc - allocate ion memory
+ * @client: the client
+ * @len: size of the allocation
+ * @align: requested allocation alignment, lots of hardware blocks
+ * have alignment requirements of some kind
+ * @heap_id_mask: mask of heaps to allocate from, if multiple bits are set
+ * heaps will be tried in order from highest to lowest
+ * id
+ * @flags: heap flags, the low 16 bits are consumed by ion, the
+ * high 16 bits are passed on to the respective heap and
+ * can be heap custom
+ *
+ * Allocate memory in one of the heaps provided in heap mask and return
+ * an opaque handle to it.
+ */
+struct ion_handle *ion_alloc(struct ion_client *client, size_t len,
+ size_t align, unsigned int heap_id_mask,
+ unsigned int flags);
+
+/**
+ * ion_free - free a handle
+ * @client: the client
+ * @handle: the handle to free
+ *
+ * Free the provided handle.
+ */
+void ion_free(struct ion_client *client, struct ion_handle *handle);
+
+/**
+ * ion_phys - returns the physical address and len of a handle
+ * @client: the client
+ * @handle: the handle
+ * @addr: a pointer to put the address in
+ * @len: a pointer to put the length in
+ *
+ * This function queries the heap for a particular handle to get the
+ * handle's physical address. It't output is only correct if
+ * a heap returns physically contiguous memory -- in other cases
+ * this api should not be implemented -- ion_sg_table should be used
+ * instead. Returns -EINVAL if the handle is invalid. This has
+ * no implications on the reference counting of the handle --
+ * the returned value may not be valid if the caller is not
+ * holding a reference.
+ */
+int ion_phys(struct ion_client *client, struct ion_handle *handle,
+ ion_phys_addr_t *addr, size_t *len);
+
+/**
+ * ion_map_dma - return an sg_table describing a handle
+ * @client: the client
+ * @handle: the handle
+ *
+ * This function returns the sg_table describing
+ * a particular ion handle.
+ */
+struct sg_table *ion_sg_table(struct ion_client *client,
+ struct ion_handle *handle);
+
+/**
+ * ion_map_kernel - create mapping for the given handle
+ * @client: the client
+ * @handle: handle to map
+ *
+ * Map the given handle into the kernel and return a kernel address that
+ * can be used to access this address.
+ */
+void *ion_map_kernel(struct ion_client *client, struct ion_handle *handle);
+
+/**
+ * ion_unmap_kernel() - destroy a kernel mapping for a handle
+ * @client: the client
+ * @handle: handle to unmap
+ */
+void ion_unmap_kernel(struct ion_client *client, struct ion_handle *handle);
+
+/**
+ * ion_share_dma_buf() - share buffer as dma-buf
+ * @client: the client
+ * @handle: the handle
+ */
+struct dma_buf *ion_share_dma_buf(struct ion_client *client,
+ struct ion_handle *handle);
+
+/**
+ * ion_share_dma_buf_fd() - given an ion client, create a dma-buf fd
+ * @client: the client
+ * @handle: the handle
+ */
+int ion_share_dma_buf_fd(struct ion_client *client, struct ion_handle *handle);
+
+/**
+ * ion_import_dma_buf() - given an dma-buf fd from the ion exporter get handle
+ * @client: the client
+ * @fd: the dma-buf fd
+ *
+ * Given an dma-buf fd that was allocated through ion via ion_share_dma_buf,
+ * import that fd and return a handle representing it. If a dma-buf from
+ * another exporter is passed in this function will return ERR_PTR(-EINVAL)
+ */
+struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd);
+
+#endif /* _LINUX_ION_H */
diff --git a/drivers/staging/android/ion/ion_carveout_heap.c b/drivers/staging/android/ion/ion_carveout_heap.c
new file mode 100644
index 0000000..5165de2
--- /dev/null
+++ b/drivers/staging/android/ion/ion_carveout_heap.c
@@ -0,0 +1,194 @@
+/*
+ * drivers/gpu/ion/ion_carveout_heap.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/genalloc.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include "ion.h"
+#include "ion_priv.h"
+
+struct ion_carveout_heap {
+ struct ion_heap heap;
+ struct gen_pool *pool;
+ ion_phys_addr_t base;
+};
+
+ion_phys_addr_t ion_carveout_allocate(struct ion_heap *heap,
+ unsigned long size,
+ unsigned long align)
+{
+ struct ion_carveout_heap *carveout_heap =
+ container_of(heap, struct ion_carveout_heap, heap);
+ unsigned long offset = gen_pool_alloc(carveout_heap->pool, size);
+
+ if (!offset)
+ return ION_CARVEOUT_ALLOCATE_FAIL;
+
+ return offset;
+}
+
+void ion_carveout_free(struct ion_heap *heap, ion_phys_addr_t addr,
+ unsigned long size)
+{
+ struct ion_carveout_heap *carveout_heap =
+ container_of(heap, struct ion_carveout_heap, heap);
+
+ if (addr == ION_CARVEOUT_ALLOCATE_FAIL)
+ return;
+ gen_pool_free(carveout_heap->pool, addr, size);
+}
+
+static int ion_carveout_heap_phys(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ ion_phys_addr_t *addr, size_t *len)
+{
+ struct sg_table *table = buffer->priv_virt;
+ struct page *page = sg_page(table->sgl);
+ ion_phys_addr_t paddr = PFN_PHYS(page_to_pfn(page));
+
+ *addr = paddr;
+ *len = buffer->size;
+ return 0;
+}
+
+static int ion_carveout_heap_allocate(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long size, unsigned long align,
+ unsigned long flags)
+{
+ struct sg_table *table;
+ ion_phys_addr_t paddr;
+ int ret;
+
+ if (align > PAGE_SIZE)
+ return -EINVAL;
+
+ table = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+ ret = sg_alloc_table(table, 1, GFP_KERNEL);
+ if (ret)
+ goto err_free;
+
+ paddr = ion_carveout_allocate(heap, size, align);
+ if (paddr == ION_CARVEOUT_ALLOCATE_FAIL) {
+ ret = -ENOMEM;
+ goto err_free_table;
+ }
+
+ sg_set_page(table->sgl, pfn_to_page(PFN_DOWN(paddr)), size, 0);
+ buffer->priv_virt = table;
+
+ return 0;
+
+err_free_table:
+ sg_free_table(table);
+err_free:
+ kfree(table);
+ return ret;
+}
+
+static void ion_carveout_heap_free(struct ion_buffer *buffer)
+{
+ struct ion_heap *heap = buffer->heap;
+ struct sg_table *table = buffer->priv_virt;
+ struct page *page = sg_page(table->sgl);
+ ion_phys_addr_t paddr = PFN_PHYS(page_to_pfn(page));
+
+ ion_heap_buffer_zero(buffer);
+
+ if (ion_buffer_cached(buffer))
+ dma_sync_sg_for_device(NULL, table->sgl, table->nents,
+ DMA_BIDIRECTIONAL);
+
+ ion_carveout_free(heap, paddr, buffer->size);
+ sg_free_table(table);
+ kfree(table);
+}
+
+static struct sg_table *ion_carveout_heap_map_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return buffer->priv_virt;
+}
+
+static void ion_carveout_heap_unmap_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return;
+}
+
+static struct ion_heap_ops carveout_heap_ops = {
+ .allocate = ion_carveout_heap_allocate,
+ .free = ion_carveout_heap_free,
+ .phys = ion_carveout_heap_phys,
+ .map_dma = ion_carveout_heap_map_dma,
+ .unmap_dma = ion_carveout_heap_unmap_dma,
+ .map_user = ion_heap_map_user,
+ .map_kernel = ion_heap_map_kernel,
+ .unmap_kernel = ion_heap_unmap_kernel,
+};
+
+struct ion_heap *ion_carveout_heap_create(struct ion_platform_heap *heap_data)
+{
+ struct ion_carveout_heap *carveout_heap;
+ int ret;
+
+ struct page *page;
+ size_t size;
+
+ page = pfn_to_page(PFN_DOWN(heap_data->base));
+ size = heap_data->size;
+
+ ion_pages_sync_for_device(NULL, page, size, DMA_BIDIRECTIONAL);
+
+ ret = ion_heap_pages_zero(page, size, pgprot_writecombine(PAGE_KERNEL));
+ if (ret)
+ return ERR_PTR(ret);
+
+ carveout_heap = kzalloc(sizeof(struct ion_carveout_heap), GFP_KERNEL);
+ if (!carveout_heap)
+ return ERR_PTR(-ENOMEM);
+
+ carveout_heap->pool = gen_pool_create(12, -1);
+ if (!carveout_heap->pool) {
+ kfree(carveout_heap);
+ return ERR_PTR(-ENOMEM);
+ }
+ carveout_heap->base = heap_data->base;
+ gen_pool_add(carveout_heap->pool, carveout_heap->base, heap_data->size,
+ -1);
+ carveout_heap->heap.ops = &carveout_heap_ops;
+ carveout_heap->heap.type = ION_HEAP_TYPE_CARVEOUT;
+ carveout_heap->heap.flags = ION_HEAP_FLAG_DEFER_FREE;
+
+ return &carveout_heap->heap;
+}
+
+void ion_carveout_heap_destroy(struct ion_heap *heap)
+{
+ struct ion_carveout_heap *carveout_heap =
+ container_of(heap, struct ion_carveout_heap, heap);
+
+ gen_pool_destroy(carveout_heap->pool);
+ kfree(carveout_heap);
+ carveout_heap = NULL;
+}
diff --git a/drivers/staging/android/ion/ion_chunk_heap.c b/drivers/staging/android/ion/ion_chunk_heap.c
new file mode 100644
index 0000000..ca20d62
--- /dev/null
+++ b/drivers/staging/android/ion/ion_chunk_heap.c
@@ -0,0 +1,195 @@
+/*
+ * drivers/gpu/ion/ion_chunk_heap.c
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/genalloc.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include "ion.h"
+#include "ion_priv.h"
+
+struct ion_chunk_heap {
+ struct ion_heap heap;
+ struct gen_pool *pool;
+ ion_phys_addr_t base;
+ unsigned long chunk_size;
+ unsigned long size;
+ unsigned long allocated;
+};
+
+static int ion_chunk_heap_allocate(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long size, unsigned long align,
+ unsigned long flags)
+{
+ struct ion_chunk_heap *chunk_heap =
+ container_of(heap, struct ion_chunk_heap, heap);
+ struct sg_table *table;
+ struct scatterlist *sg;
+ int ret, i;
+ unsigned long num_chunks;
+ unsigned long allocated_size;
+
+ if (align > chunk_heap->chunk_size)
+ return -EINVAL;
+
+ allocated_size = ALIGN(size, chunk_heap->chunk_size);
+ num_chunks = allocated_size / chunk_heap->chunk_size;
+
+ if (allocated_size > chunk_heap->size - chunk_heap->allocated)
+ return -ENOMEM;
+
+ table = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+ ret = sg_alloc_table(table, num_chunks, GFP_KERNEL);
+ if (ret) {
+ kfree(table);
+ return ret;
+ }
+
+ sg = table->sgl;
+ for (i = 0; i < num_chunks; i++) {
+ unsigned long paddr = gen_pool_alloc(chunk_heap->pool,
+ chunk_heap->chunk_size);
+ if (!paddr)
+ goto err;
+ sg_set_page(sg, pfn_to_page(PFN_DOWN(paddr)),
+ chunk_heap->chunk_size, 0);
+ sg = sg_next(sg);
+ }
+
+ buffer->priv_virt = table;
+ chunk_heap->allocated += allocated_size;
+ return 0;
+err:
+ sg = table->sgl;
+ for (i -= 1; i >= 0; i--) {
+ gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)),
+ sg->length);
+ sg = sg_next(sg);
+ }
+ sg_free_table(table);
+ kfree(table);
+ return -ENOMEM;
+}
+
+static void ion_chunk_heap_free(struct ion_buffer *buffer)
+{
+ struct ion_heap *heap = buffer->heap;
+ struct ion_chunk_heap *chunk_heap =
+ container_of(heap, struct ion_chunk_heap, heap);
+ struct sg_table *table = buffer->priv_virt;
+ struct scatterlist *sg;
+ int i;
+ unsigned long allocated_size;
+
+ allocated_size = ALIGN(buffer->size, chunk_heap->chunk_size);
+
+ ion_heap_buffer_zero(buffer);
+
+ if (ion_buffer_cached(buffer))
+ dma_sync_sg_for_device(NULL, table->sgl, table->nents,
+ DMA_BIDIRECTIONAL);
+
+ for_each_sg(table->sgl, sg, table->nents, i) {
+ gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)),
+ sg->length);
+ }
+ chunk_heap->allocated -= allocated_size;
+ sg_free_table(table);
+ kfree(table);
+}
+
+static struct sg_table *ion_chunk_heap_map_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return buffer->priv_virt;
+}
+
+static void ion_chunk_heap_unmap_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return;
+}
+
+static struct ion_heap_ops chunk_heap_ops = {
+ .allocate = ion_chunk_heap_allocate,
+ .free = ion_chunk_heap_free,
+ .map_dma = ion_chunk_heap_map_dma,
+ .unmap_dma = ion_chunk_heap_unmap_dma,
+ .map_user = ion_heap_map_user,
+ .map_kernel = ion_heap_map_kernel,
+ .unmap_kernel = ion_heap_unmap_kernel,
+};
+
+struct ion_heap *ion_chunk_heap_create(struct ion_platform_heap *heap_data)
+{
+ struct ion_chunk_heap *chunk_heap;
+ int ret;
+ struct page *page;
+ size_t size;
+
+ page = pfn_to_page(PFN_DOWN(heap_data->base));
+ size = heap_data->size;
+
+ ion_pages_sync_for_device(NULL, page, size, DMA_BIDIRECTIONAL);
+
+ ret = ion_heap_pages_zero(page, size, pgprot_writecombine(PAGE_KERNEL));
+ if (ret)
+ return ERR_PTR(ret);
+
+ chunk_heap = kzalloc(sizeof(struct ion_chunk_heap), GFP_KERNEL);
+ if (!chunk_heap)
+ return ERR_PTR(-ENOMEM);
+
+ chunk_heap->chunk_size = (unsigned long)heap_data->priv;
+ chunk_heap->pool = gen_pool_create(get_order(chunk_heap->chunk_size) +
+ PAGE_SHIFT, -1);
+ if (!chunk_heap->pool) {
+ ret = -ENOMEM;
+ goto error_gen_pool_create;
+ }
+ chunk_heap->base = heap_data->base;
+ chunk_heap->size = heap_data->size;
+ chunk_heap->allocated = 0;
+
+ gen_pool_add(chunk_heap->pool, chunk_heap->base, heap_data->size, -1);
+ chunk_heap->heap.ops = &chunk_heap_ops;
+ chunk_heap->heap.type = ION_HEAP_TYPE_CHUNK;
+ chunk_heap->heap.flags = ION_HEAP_FLAG_DEFER_FREE;
+ pr_info("%s: base %lu size %zu align %ld\n", __func__, chunk_heap->base,
+ heap_data->size, heap_data->align);
+
+ return &chunk_heap->heap;
+
+error_gen_pool_create:
+ kfree(chunk_heap);
+ return ERR_PTR(ret);
+}
+
+void ion_chunk_heap_destroy(struct ion_heap *heap)
+{
+ struct ion_chunk_heap *chunk_heap =
+ container_of(heap, struct ion_chunk_heap, heap);
+
+ gen_pool_destroy(chunk_heap->pool);
+ kfree(chunk_heap);
+ chunk_heap = NULL;
+}
diff --git a/drivers/staging/android/ion/ion_cma_heap.c b/drivers/staging/android/ion/ion_cma_heap.c
new file mode 100644
index 0000000..4418bda
--- /dev/null
+++ b/drivers/staging/android/ion/ion_cma_heap.c
@@ -0,0 +1,218 @@
+/*
+ * drivers/gpu/ion/ion_cma_heap.c
+ *
+ * Copyright (C) Linaro 2012
+ * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/dma-mapping.h>
+
+#include "ion.h"
+#include "ion_priv.h"
+
+#define ION_CMA_ALLOCATE_FAILED -1
+
+struct ion_cma_heap {
+ struct ion_heap heap;
+ struct device *dev;
+};
+
+#define to_cma_heap(x) container_of(x, struct ion_cma_heap, heap)
+
+struct ion_cma_buffer_info {
+ void *cpu_addr;
+ dma_addr_t handle;
+ struct sg_table *table;
+};
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ * This function could be replaced by dma_common_get_sgtable
+ * as soon as it will avalaible.
+ */
+static int ion_cma_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size)
+{
+ struct page *page = virt_to_page(cpu_addr);
+ int ret;
+
+ ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+ if (unlikely(ret))
+ return ret;
+
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+ return 0;
+}
+
+/* ION CMA heap operations functions */
+static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer,
+ unsigned long len, unsigned long align,
+ unsigned long flags)
+{
+ struct ion_cma_heap *cma_heap = to_cma_heap(heap);
+ struct device *dev = cma_heap->dev;
+ struct ion_cma_buffer_info *info;
+
+ dev_dbg(dev, "Request buffer allocation len %ld\n", len);
+
+ if (buffer->flags & ION_FLAG_CACHED)
+ return -EINVAL;
+
+ if (align > PAGE_SIZE)
+ return -EINVAL;
+
+ info = kzalloc(sizeof(struct ion_cma_buffer_info), GFP_KERNEL);
+ if (!info) {
+ dev_err(dev, "Can't allocate buffer info\n");
+ return ION_CMA_ALLOCATE_FAILED;
+ }
+
+ info->cpu_addr = dma_alloc_coherent(dev, len, &(info->handle),
+ GFP_HIGHUSER | __GFP_ZERO);
+
+ if (!info->cpu_addr) {
+ dev_err(dev, "Fail to allocate buffer\n");
+ goto err;
+ }
+
+ info->table = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
+ if (!info->table) {
+ dev_err(dev, "Fail to allocate sg table\n");
+ goto free_mem;
+ }
+
+ if (ion_cma_get_sgtable
+ (dev, info->table, info->cpu_addr, info->handle, len))
+ goto free_table;
+ /* keep this for memory release */
+ buffer->priv_virt = info;
+ dev_dbg(dev, "Allocate buffer %p\n", buffer);
+ return 0;
+
+free_table:
+ kfree(info->table);
+free_mem:
+ dma_free_coherent(dev, len, info->cpu_addr, info->handle);
+err:
+ kfree(info);
+ return ION_CMA_ALLOCATE_FAILED;
+}
+
+static void ion_cma_free(struct ion_buffer *buffer)
+{
+ struct ion_cma_heap *cma_heap = to_cma_heap(buffer->heap);
+ struct device *dev = cma_heap->dev;
+ struct ion_cma_buffer_info *info = buffer->priv_virt;
+
+ dev_dbg(dev, "Release buffer %p\n", buffer);
+ /* release memory */
+ dma_free_coherent(dev, buffer->size, info->cpu_addr, info->handle);
+ /* release sg table */
+ sg_free_table(info->table);
+ kfree(info->table);
+ kfree(info);
+}
+
+/* return physical address in addr */
+static int ion_cma_phys(struct ion_heap *heap, struct ion_buffer *buffer,
+ ion_phys_addr_t *addr, size_t *len)
+{
+ struct ion_cma_heap *cma_heap = to_cma_heap(buffer->heap);
+ struct device *dev = cma_heap->dev;
+ struct ion_cma_buffer_info *info = buffer->priv_virt;
+
+ dev_dbg(dev, "Return buffer %p physical address 0x%pa\n", buffer,
+ &info->handle);
+
+ *addr = info->handle;
+ *len = buffer->size;
+
+ return 0;
+}
+
+static struct sg_table *ion_cma_heap_map_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ struct ion_cma_buffer_info *info = buffer->priv_virt;
+
+ return info->table;
+}
+
+static void ion_cma_heap_unmap_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return;
+}
+
+static int ion_cma_mmap(struct ion_heap *mapper, struct ion_buffer *buffer,
+ struct vm_area_struct *vma)
+{
+ struct ion_cma_heap *cma_heap = to_cma_heap(buffer->heap);
+ struct device *dev = cma_heap->dev;
+ struct ion_cma_buffer_info *info = buffer->priv_virt;
+
+ return dma_mmap_coherent(dev, vma, info->cpu_addr, info->handle,
+ buffer->size);
+}
+
+static void *ion_cma_map_kernel(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ struct ion_cma_buffer_info *info = buffer->priv_virt;
+ /* kernel memory mapping has been done at allocation time */
+ return info->cpu_addr;
+}
+
+static void ion_cma_unmap_kernel(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+}
+
+static struct ion_heap_ops ion_cma_ops = {
+ .allocate = ion_cma_allocate,
+ .free = ion_cma_free,
+ .map_dma = ion_cma_heap_map_dma,
+ .unmap_dma = ion_cma_heap_unmap_dma,
+ .phys = ion_cma_phys,
+ .map_user = ion_cma_mmap,
+ .map_kernel = ion_cma_map_kernel,
+ .unmap_kernel = ion_cma_unmap_kernel,
+};
+
+struct ion_heap *ion_cma_heap_create(struct ion_platform_heap *data)
+{
+ struct ion_cma_heap *cma_heap;
+
+ cma_heap = kzalloc(sizeof(struct ion_cma_heap), GFP_KERNEL);
+
+ if (!cma_heap)
+ return ERR_PTR(-ENOMEM);
+
+ cma_heap->heap.ops = &ion_cma_ops;
+ /* get device from private heaps data, later it will be
+ * used to make the link with reserved CMA memory */
+ cma_heap->dev = data->priv;
+ cma_heap->heap.type = ION_HEAP_TYPE_DMA;
+ return &cma_heap->heap;
+}
+
+void ion_cma_heap_destroy(struct ion_heap *heap)
+{
+ struct ion_cma_heap *cma_heap = to_cma_heap(heap);
+
+ kfree(cma_heap);
+}
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
new file mode 100644
index 0000000..e1bbd8b
--- /dev/null
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -0,0 +1,371 @@
+/*
+ * drivers/gpu/ion/ion_heap.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/scatterlist.h>
+#include <linux/vmalloc.h>
+#include "ion.h"
+#include "ion_priv.h"
+
+void *ion_heap_map_kernel(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ struct scatterlist *sg;
+ int i, j;
+ void *vaddr;
+ pgprot_t pgprot;
+ struct sg_table *table = buffer->sg_table;
+ int npages = PAGE_ALIGN(buffer->size) / PAGE_SIZE;
+ struct page **pages = vmalloc(sizeof(struct page *) * npages);
+ struct page **tmp = pages;
+
+ if (!pages)
+ return NULL;
+
+ if (buffer->flags & ION_FLAG_CACHED)
+ pgprot = PAGE_KERNEL;
+ else
+ pgprot = pgprot_writecombine(PAGE_KERNEL);
+
+ for_each_sg(table->sgl, sg, table->nents, i) {
+ int npages_this_entry = PAGE_ALIGN(sg->length) / PAGE_SIZE;
+ struct page *page = sg_page(sg);
+
+ BUG_ON(i >= npages);
+ for (j = 0; j < npages_this_entry; j++)
+ *(tmp++) = page++;
+ }
+ vaddr = vmap(pages, npages, VM_MAP, pgprot);
+ vfree(pages);
+
+ if (vaddr == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ return vaddr;
+}
+
+void ion_heap_unmap_kernel(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ vunmap(buffer->vaddr);
+}
+
+int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,
+ struct vm_area_struct *vma)
+{
+ struct sg_table *table = buffer->sg_table;
+ unsigned long addr = vma->vm_start;
+ unsigned long offset = vma->vm_pgoff * PAGE_SIZE;
+ struct scatterlist *sg;
+ int i;
+ int ret;
+
+ for_each_sg(table->sgl, sg, table->nents, i) {
+ struct page *page = sg_page(sg);
+ unsigned long remainder = vma->vm_end - addr;
+ unsigned long len = sg->length;
+
+ if (offset >= sg->length) {
+ offset -= sg->length;
+ continue;
+ } else if (offset) {
+ page += offset / PAGE_SIZE;
+ len = sg->length - offset;
+ offset = 0;
+ }
+ len = min(len, remainder);
+ ret = remap_pfn_range(vma, addr, page_to_pfn(page), len,
+ vma->vm_page_prot);
+ if (ret)
+ return ret;
+ addr += len;
+ if (addr >= vma->vm_end)
+ return 0;
+ }
+ return 0;
+}
+
+static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot)
+{
+ void *addr = vm_map_ram(pages, num, -1, pgprot);
+
+ if (!addr)
+ return -ENOMEM;
+ memset(addr, 0, PAGE_SIZE * num);
+ vm_unmap_ram(addr, num);
+
+ return 0;
+}
+
+static int ion_heap_sglist_zero(struct scatterlist *sgl, unsigned int nents,
+ pgprot_t pgprot)
+{
+ int p = 0;
+ int ret = 0;
+ struct sg_page_iter piter;
+ struct page *pages[32];
+
+ for_each_sg_page(sgl, &piter, nents, 0) {
+ pages[p++] = sg_page_iter_page(&piter);
+ if (p == ARRAY_SIZE(pages)) {
+ ret = ion_heap_clear_pages(pages, p, pgprot);
+ if (ret)
+ return ret;
+ p = 0;
+ }
+ }
+ if (p)
+ ret = ion_heap_clear_pages(pages, p, pgprot);
+
+ return ret;
+}
+
+int ion_heap_buffer_zero(struct ion_buffer *buffer)
+{
+ struct sg_table *table = buffer->sg_table;
+ pgprot_t pgprot;
+
+ if (buffer->flags & ION_FLAG_CACHED)
+ pgprot = PAGE_KERNEL;
+ else
+ pgprot = pgprot_writecombine(PAGE_KERNEL);
+
+ return ion_heap_sglist_zero(table->sgl, table->nents, pgprot);
+}
+
+int ion_heap_pages_zero(struct page *page, size_t size, pgprot_t pgprot)
+{
+ struct scatterlist sg;
+
+ sg_init_table(&sg, 1);
+ sg_set_page(&sg, page, size, 0);
+ return ion_heap_sglist_zero(&sg, 1, pgprot);
+}
+
+void ion_heap_freelist_add(struct ion_heap *heap, struct ion_buffer *buffer)
+{
+ spin_lock(&heap->free_lock);
+ list_add(&buffer->list, &heap->free_list);
+ heap->free_list_size += buffer->size;
+ spin_unlock(&heap->free_lock);
+ wake_up(&heap->waitqueue);
+}
+
+size_t ion_heap_freelist_size(struct ion_heap *heap)
+{
+ size_t size;
+
+ spin_lock(&heap->free_lock);
+ size = heap->free_list_size;
+ spin_unlock(&heap->free_lock);
+
+ return size;
+}
+
+static size_t _ion_heap_freelist_drain(struct ion_heap *heap, size_t size,
+ bool skip_pools)
+{
+ struct ion_buffer *buffer;
+ size_t total_drained = 0;
+
+ if (ion_heap_freelist_size(heap) == 0)
+ return 0;
+
+ spin_lock(&heap->free_lock);
+ if (size == 0)
+ size = heap->free_list_size;
+
+ while (!list_empty(&heap->free_list)) {
+ if (total_drained >= size)
+ break;
+ buffer = list_first_entry(&heap->free_list, struct ion_buffer,
+ list);
+ list_del(&buffer->list);
+ heap->free_list_size -= buffer->size;
+ if (skip_pools)
+ buffer->private_flags |= ION_PRIV_FLAG_SHRINKER_FREE;
+ total_drained += buffer->size;
+ spin_unlock(&heap->free_lock);
+ ion_buffer_destroy(buffer);
+ spin_lock(&heap->free_lock);
+ }
+ spin_unlock(&heap->free_lock);
+
+ return total_drained;
+}
+
+size_t ion_heap_freelist_drain(struct ion_heap *heap, size_t size)
+{
+ return _ion_heap_freelist_drain(heap, size, false);
+}
+
+size_t ion_heap_freelist_shrink(struct ion_heap *heap, size_t size)
+{
+ return _ion_heap_freelist_drain(heap, size, true);
+}
+
+static int ion_heap_deferred_free(void *data)
+{
+ struct ion_heap *heap = data;
+
+ while (true) {
+ struct ion_buffer *buffer;
+
+ wait_event_freezable(heap->waitqueue,
+ ion_heap_freelist_size(heap) > 0);
+
+ spin_lock(&heap->free_lock);
+ if (list_empty(&heap->free_list)) {
+ spin_unlock(&heap->free_lock);
+ continue;
+ }
+ buffer = list_first_entry(&heap->free_list, struct ion_buffer,
+ list);
+ list_del(&buffer->list);
+ heap->free_list_size -= buffer->size;
+ spin_unlock(&heap->free_lock);
+ ion_buffer_destroy(buffer);
+ }
+
+ return 0;
+}
+
+int ion_heap_init_deferred_free(struct ion_heap *heap)
+{
+ struct sched_param param = { .sched_priority = 0 };
+
+ INIT_LIST_HEAD(&heap->free_list);
+ heap->free_list_size = 0;
+ spin_lock_init(&heap->free_lock);
+ init_waitqueue_head(&heap->waitqueue);
+ heap->task = kthread_run(ion_heap_deferred_free, heap,
+ "%s", heap->name);
+ sched_setscheduler(heap->task, SCHED_IDLE, ¶m);
+ if (IS_ERR(heap->task)) {
+ pr_err("%s: creating thread for deferred free failed\n",
+ __func__);
+ return PTR_RET(heap->task);
+ }
+ return 0;
+}
+
+static int ion_heap_shrink(struct shrinker *shrinker, struct shrink_control *sc)
+{
+ struct ion_heap *heap = container_of(shrinker, struct ion_heap,
+ shrinker);
+ int total = 0;
+ int freed = 0;
+ int to_scan = sc->nr_to_scan;
+
+ if (to_scan == 0)
+ goto out;
+
+ /*
+ * shrink the free list first, no point in zeroing the memory if we're
+ * just going to reclaim it. Also, skip any possible page pooling.
+ */
+ if (heap->flags & ION_HEAP_FLAG_DEFER_FREE)
+ freed = ion_heap_freelist_shrink(heap, to_scan * PAGE_SIZE) /
+ PAGE_SIZE;
+
+ to_scan -= freed;
+ if (to_scan < 0)
+ to_scan = 0;
+
+out:
+ total = ion_heap_freelist_size(heap) / PAGE_SIZE;
+ if (heap->ops->shrink)
+ total += heap->ops->shrink(heap, sc->gfp_mask, to_scan);
+ return total;
+}
+
+void ion_heap_init_shrinker(struct ion_heap *heap)
+{
+ heap->shrinker.shrink = ion_heap_shrink;
+ heap->shrinker.seeks = DEFAULT_SEEKS;
+ heap->shrinker.batch = 0;
+ register_shrinker(&heap->shrinker);
+}
+
+struct ion_heap *ion_heap_create(struct ion_platform_heap *heap_data)
+{
+ struct ion_heap *heap = NULL;
+
+ switch (heap_data->type) {
+ case ION_HEAP_TYPE_SYSTEM_CONTIG:
+ heap = ion_system_contig_heap_create(heap_data);
+ break;
+ case ION_HEAP_TYPE_SYSTEM:
+ heap = ion_system_heap_create(heap_data);
+ break;
+ case ION_HEAP_TYPE_CARVEOUT:
+ heap = ion_carveout_heap_create(heap_data);
+ break;
+ case ION_HEAP_TYPE_CHUNK:
+ heap = ion_chunk_heap_create(heap_data);
+ break;
+ case ION_HEAP_TYPE_DMA:
+ heap = ion_cma_heap_create(heap_data);
+ break;
+ default:
+ pr_err("%s: Invalid heap type %d\n", __func__,
+ heap_data->type);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (IS_ERR_OR_NULL(heap)) {
+ pr_err("%s: error creating heap %s type %d base %lu size %zu\n",
+ __func__, heap_data->name, heap_data->type,
+ heap_data->base, heap_data->size);
+ return ERR_PTR(-EINVAL);
+ }
+
+ heap->name = heap_data->name;
+ heap->id = heap_data->id;
+ return heap;
+}
+
+void ion_heap_destroy(struct ion_heap *heap)
+{
+ if (!heap)
+ return;
+
+ switch (heap->type) {
+ case ION_HEAP_TYPE_SYSTEM_CONTIG:
+ ion_system_contig_heap_destroy(heap);
+ break;
+ case ION_HEAP_TYPE_SYSTEM:
+ ion_system_heap_destroy(heap);
+ break;
+ case ION_HEAP_TYPE_CARVEOUT:
+ ion_carveout_heap_destroy(heap);
+ break;
+ case ION_HEAP_TYPE_CHUNK:
+ ion_chunk_heap_destroy(heap);
+ break;
+ case ION_HEAP_TYPE_DMA:
+ ion_cma_heap_destroy(heap);
+ break;
+ default:
+ pr_err("%s: Invalid heap type %d\n", __func__,
+ heap->type);
+ }
+}
diff --git a/drivers/staging/android/ion/ion_page_pool.c b/drivers/staging/android/ion/ion_page_pool.c
new file mode 100644
index 0000000..f08c6db
--- /dev/null
+++ b/drivers/staging/android/ion/ion_page_pool.c
@@ -0,0 +1,198 @@
+/*
+ * drivers/gpu/ion/ion_mem_pool.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "ion_priv.h"
+
+struct ion_page_pool_item {
+ struct page *page;
+ struct list_head list;
+};
+
+static void *ion_page_pool_alloc_pages(struct ion_page_pool *pool)
+{
+ struct page *page = alloc_pages(pool->gfp_mask, pool->order);
+
+ if (!page)
+ return NULL;
+ ion_page_pool_alloc_set_cache_policy(pool, page);
+
+ ion_pages_sync_for_device(NULL, page, PAGE_SIZE << pool->order,
+ DMA_BIDIRECTIONAL);
+ return page;
+}
+
+static void ion_page_pool_free_pages(struct ion_page_pool *pool,
+ struct page *page)
+{
+ ion_page_pool_free_set_cache_policy(pool, page);
+ __free_pages(page, pool->order);
+}
+
+static int ion_page_pool_add(struct ion_page_pool *pool, struct page *page)
+{
+ struct ion_page_pool_item *item;
+
+ item = kmalloc(sizeof(struct ion_page_pool_item), GFP_KERNEL);
+ if (!item)
+ return -ENOMEM;
+
+ mutex_lock(&pool->mutex);
+ item->page = page;
+ if (PageHighMem(page)) {
+ list_add_tail(&item->list, &pool->high_items);
+ pool->high_count++;
+ } else {
+ list_add_tail(&item->list, &pool->low_items);
+ pool->low_count++;
+ }
+ mutex_unlock(&pool->mutex);
+ return 0;
+}
+
+static struct page *ion_page_pool_remove(struct ion_page_pool *pool, bool high)
+{
+ struct ion_page_pool_item *item;
+ struct page *page;
+
+ if (high) {
+ BUG_ON(!pool->high_count);
+ item = list_first_entry(&pool->high_items,
+ struct ion_page_pool_item, list);
+ pool->high_count--;
+ } else {
+ BUG_ON(!pool->low_count);
+ item = list_first_entry(&pool->low_items,
+ struct ion_page_pool_item, list);
+ pool->low_count--;
+ }
+
+ list_del(&item->list);
+ page = item->page;
+ kfree(item);
+ return page;
+}
+
+void *ion_page_pool_alloc(struct ion_page_pool *pool)
+{
+ struct page *page = NULL;
+
+ BUG_ON(!pool);
+
+ mutex_lock(&pool->mutex);
+ if (pool->high_count)
+ page = ion_page_pool_remove(pool, true);
+ else if (pool->low_count)
+ page = ion_page_pool_remove(pool, false);
+ mutex_unlock(&pool->mutex);
+
+ if (!page)
+ page = ion_page_pool_alloc_pages(pool);
+
+ return page;
+}
+
+void ion_page_pool_free(struct ion_page_pool *pool, struct page *page)
+{
+ int ret;
+
+ ret = ion_page_pool_add(pool, page);
+ if (ret)
+ ion_page_pool_free_pages(pool, page);
+}
+
+void ion_page_pool_free_immediate(struct ion_page_pool *pool, struct page *page)
+{
+ ion_page_pool_free_pages(pool, page);
+}
+
+static int ion_page_pool_total(struct ion_page_pool *pool, bool high)
+{
+ int total = 0;
+
+ total += high ? (pool->high_count + pool->low_count) *
+ (1 << pool->order) :
+ pool->low_count * (1 << pool->order);
+ return total;
+}
+
+int ion_page_pool_shrink(struct ion_page_pool *pool, gfp_t gfp_mask,
+ int nr_to_scan)
+{
+ int i;
+ bool high;
+
+ high = !!(gfp_mask & __GFP_HIGHMEM);
+
+ for (i = 0; i < nr_to_scan; i++) {
+ struct page *page;
+
+ mutex_lock(&pool->mutex);
+ if (pool->low_count) {
+ page = ion_page_pool_remove(pool, false);
+ } else if (high && pool->high_count) {
+ page = ion_page_pool_remove(pool, true);
+ } else {
+ mutex_unlock(&pool->mutex);
+ break;
+ }
+ mutex_unlock(&pool->mutex);
+ ion_page_pool_free_pages(pool, page);
+ }
+
+ return ion_page_pool_total(pool, high);
+}
+
+struct ion_page_pool *ion_page_pool_create(gfp_t gfp_mask, unsigned int order)
+{
+ struct ion_page_pool *pool = kmalloc(sizeof(struct ion_page_pool),
+ GFP_KERNEL);
+ if (!pool)
+ return NULL;
+ pool->high_count = 0;
+ pool->low_count = 0;
+ INIT_LIST_HEAD(&pool->low_items);
+ INIT_LIST_HEAD(&pool->high_items);
+ pool->gfp_mask = gfp_mask;
+ pool->order = order;
+ mutex_init(&pool->mutex);
+ plist_node_init(&pool->list, order);
+
+ return pool;
+}
+
+void ion_page_pool_destroy(struct ion_page_pool *pool)
+{
+ kfree(pool);
+}
+
+static int __init ion_page_pool_init(void)
+{
+ return 0;
+}
+
+static void __exit ion_page_pool_exit(void)
+{
+}
+
+module_init(ion_page_pool_init);
+module_exit(ion_page_pool_exit);
diff --git a/drivers/staging/android/ion/ion_priv.h b/drivers/staging/android/ion/ion_priv.h
new file mode 100644
index 0000000..13531d1
--- /dev/null
+++ b/drivers/staging/android/ion/ion_priv.h
@@ -0,0 +1,439 @@
+/*
+ * drivers/gpu/ion/ion_priv.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _ION_PRIV_H
+#define _ION_PRIV_H
+
+#include <linux/device.h>
+#include <linux/dma-direction.h>
+#include <linux/kref.h>
+#include <linux/mm_types.h>
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/shrinker.h>
+#include <linux/types.h>
+#ifdef CONFIG_ION_POOL_CACHE_POLICY
+#include <asm/cacheflush.h>
+#endif
+
+#include "ion.h"
+
+struct ion_buffer *ion_handle_buffer(struct ion_handle *handle);
+
+/**
+ * struct ion_buffer - metadata for a particular buffer
+ * @ref: refernce count
+ * @node: node in the ion_device buffers tree
+ * @dev: back pointer to the ion_device
+ * @heap: back pointer to the heap the buffer came from
+ * @flags: buffer specific flags
+ * @private_flags: internal buffer specific flags
+ * @size: size of the buffer
+ * @priv_virt: private data to the buffer representable as
+ * a void *
+ * @priv_phys: private data to the buffer representable as
+ * an ion_phys_addr_t (and someday a phys_addr_t)
+ * @lock: protects the buffers cnt fields
+ * @kmap_cnt: number of times the buffer is mapped to the kernel
+ * @vaddr: the kenrel mapping if kmap_cnt is not zero
+ * @dmap_cnt: number of times the buffer is mapped for dma
+ * @sg_table: the sg table for the buffer if dmap_cnt is not zero
+ * @pages: flat array of pages in the buffer -- used by fault
+ * handler and only valid for buffers that are faulted in
+ * @vmas: list of vma's mapping this buffer
+ * @handle_count: count of handles referencing this buffer
+ * @task_comm: taskcomm of last client to reference this buffer in a
+ * handle, used for debugging
+ * @pid: pid of last client to reference this buffer in a
+ * handle, used for debugging
+*/
+struct ion_buffer {
+ struct kref ref;
+ union {
+ struct rb_node node;
+ struct list_head list;
+ };
+ struct ion_device *dev;
+ struct ion_heap *heap;
+ unsigned long flags;
+ unsigned long private_flags;
+ size_t size;
+ union {
+ void *priv_virt;
+ ion_phys_addr_t priv_phys;
+ };
+ struct mutex lock;
+ int kmap_cnt;
+ void *vaddr;
+ int dmap_cnt;
+ struct sg_table *sg_table;
+ struct page **pages;
+ struct list_head vmas;
+ /* used to track orphaned buffers */
+ int handle_count;
+ char task_comm[TASK_COMM_LEN];
+ pid_t pid;
+};
+void ion_buffer_destroy(struct ion_buffer *buffer);
+
+/**
+ * struct ion_heap_ops - ops to operate on a given heap
+ * @allocate: allocate memory
+ * @free: free memory
+ * @phys get physical address of a buffer (only define on
+ * physically contiguous heaps)
+ * @map_dma map the memory for dma to a scatterlist
+ * @unmap_dma unmap the memory for dma
+ * @map_kernel map memory to the kernel
+ * @unmap_kernel unmap memory to the kernel
+ * @map_user map memory to userspace
+ *
+ * allocate, phys, and map_user return 0 on success, -errno on error.
+ * map_dma and map_kernel return pointer on success, ERR_PTR on
+ * error. @free will be called with ION_PRIV_FLAG_SHRINKER_FREE set in
+ * the buffer's private_flags when called from a shrinker. In that
+ * case, the pages being free'd must be truly free'd back to the
+ * system, not put in a page pool or otherwise cached.
+ */
+struct ion_heap_ops {
+ int (*allocate) (struct ion_heap *heap,
+ struct ion_buffer *buffer, unsigned long len,
+ unsigned long align, unsigned long flags);
+ void (*free) (struct ion_buffer *buffer);
+ int (*phys) (struct ion_heap *heap, struct ion_buffer *buffer,
+ ion_phys_addr_t *addr, size_t *len);
+ struct sg_table *(*map_dma) (struct ion_heap *heap,
+ struct ion_buffer *buffer);
+ void (*unmap_dma) (struct ion_heap *heap, struct ion_buffer *buffer);
+ void * (*map_kernel) (struct ion_heap *heap, struct ion_buffer *buffer);
+ void (*unmap_kernel) (struct ion_heap *heap, struct ion_buffer *buffer);
+ int (*map_user) (struct ion_heap *mapper, struct ion_buffer *buffer,
+ struct vm_area_struct *vma);
+ int (*shrink)(struct ion_heap *heap, gfp_t gfp_mask, int nr_to_scan);
+};
+
+/**
+ * heap flags - flags between the heaps and core ion code
+ */
+#define ION_HEAP_FLAG_DEFER_FREE (1 << 0)
+
+/**
+ * private flags - flags internal to ion
+ */
+/*
+ * Buffer is being freed from a shrinker function. Skip any possible
+ * heap-specific caching mechanism (e.g. page pools). Guarantees that
+ * any buffer storage that came from the system allocator will be
+ * returned to the system allocator.
+ */
+#define ION_PRIV_FLAG_SHRINKER_FREE (1 << 0)
+
+/**
+ * struct ion_heap - represents a heap in the system
+ * @node: rb node to put the heap on the device's tree of heaps
+ * @dev: back pointer to the ion_device
+ * @type: type of heap
+ * @ops: ops struct as above
+ * @flags: flags
+ * @id: id of heap, also indicates priority of this heap when
+ * allocating. These are specified by platform data and
+ * MUST be unique
+ * @name: used for debugging
+ * @shrinker: a shrinker for the heap
+ * @free_list: free list head if deferred free is used
+ * @free_list_size size of the deferred free list in bytes
+ * @lock: protects the free list
+ * @waitqueue: queue to wait on from deferred free thread
+ * @task: task struct of deferred free thread
+ * @debug_show: called when heap debug file is read to add any
+ * heap specific debug info to output
+ *
+ * Represents a pool of memory from which buffers can be made. In some
+ * systems the only heap is regular system memory allocated via vmalloc.
+ * On others, some blocks might require large physically contiguous buffers
+ * that are allocated from a specially reserved heap.
+ */
+struct ion_heap {
+ struct plist_node node;
+ struct ion_device *dev;
+ enum ion_heap_type type;
+ struct ion_heap_ops *ops;
+ unsigned long flags;
+ unsigned int id;
+ const char *name;
+ struct shrinker shrinker;
+ struct list_head free_list;
+ size_t free_list_size;
+ spinlock_t free_lock;
+ wait_queue_head_t waitqueue;
+ struct task_struct *task;
+
+ int (*debug_show)(struct ion_heap *heap, struct seq_file *, void *);
+};
+
+/**
+ * ion_buffer_cached - this ion buffer is cached
+ * @buffer: buffer
+ *
+ * indicates whether this ion buffer is cached
+ */
+bool ion_buffer_cached(struct ion_buffer *buffer);
+
+/**
+ * ion_buffer_fault_user_mappings - fault in user mappings of this buffer
+ * @buffer: buffer
+ *
+ * indicates whether userspace mappings of this buffer will be faulted
+ * in, this can affect how buffers are allocated from the heap.
+ */
+bool ion_buffer_fault_user_mappings(struct ion_buffer *buffer);
+
+/**
+ * ion_device_create - allocates and returns an ion device
+ * @custom_ioctl: arch specific ioctl function if applicable
+ *
+ * returns a valid device or -PTR_ERR
+ */
+struct ion_device *ion_device_create(long (*custom_ioctl)
+ (struct ion_client *client,
+ unsigned int cmd,
+ unsigned long arg));
+
+/**
+ * ion_device_destroy - free and device and it's resource
+ * @dev: the device
+ */
+void ion_device_destroy(struct ion_device *dev);
+
+/**
+ * ion_device_add_heap - adds a heap to the ion device
+ * @dev: the device
+ * @heap: the heap to add
+ */
+void ion_device_add_heap(struct ion_device *dev, struct ion_heap *heap);
+
+/**
+ * some helpers for common operations on buffers using the sg_table
+ * and vaddr fields
+ */
+void *ion_heap_map_kernel(struct ion_heap *, struct ion_buffer *);
+void ion_heap_unmap_kernel(struct ion_heap *, struct ion_buffer *);
+int ion_heap_map_user(struct ion_heap *, struct ion_buffer *,
+ struct vm_area_struct *);
+int ion_heap_buffer_zero(struct ion_buffer *buffer);
+int ion_heap_pages_zero(struct page *page, size_t size, pgprot_t pgprot);
+
+/**
+ * ion_heap_init_shrinker
+ * @heap: the heap
+ *
+ * If a heap sets the ION_HEAP_FLAG_DEFER_FREE flag or defines the shrink op
+ * this function will be called to setup a shrinker to shrink the freelists
+ * and call the heap's shrink op.
+ */
+void ion_heap_init_shrinker(struct ion_heap *heap);
+
+/**
+ * ion_heap_init_deferred_free -- initialize deferred free functionality
+ * @heap: the heap
+ *
+ * If a heap sets the ION_HEAP_FLAG_DEFER_FREE flag this function will
+ * be called to setup deferred frees. Calls to free the buffer will
+ * return immediately and the actual free will occur some time later
+ */
+int ion_heap_init_deferred_free(struct ion_heap *heap);
+
+/**
+ * ion_heap_freelist_add - add a buffer to the deferred free list
+ * @heap: the heap
+ * @buffer: the buffer
+ *
+ * Adds an item to the deferred freelist.
+ */
+void ion_heap_freelist_add(struct ion_heap *heap, struct ion_buffer *buffer);
+
+/**
+ * ion_heap_freelist_drain - drain the deferred free list
+ * @heap: the heap
+ * @size: ammount of memory to drain in bytes
+ *
+ * Drains the indicated amount of memory from the deferred freelist immediately.
+ * Returns the total amount freed. The total freed may be higher depending
+ * on the size of the items in the list, or lower if there is insufficient
+ * total memory on the freelist.
+ */
+size_t ion_heap_freelist_drain(struct ion_heap *heap, size_t size);
+
+/**
+ * ion_heap_freelist_shrink - drain the deferred free
+ * list, skipping any heap-specific
+ * pooling or caching mechanisms
+ *
+ * @heap: the heap
+ * @size: amount of memory to drain in bytes
+ *
+ * Drains the indicated amount of memory from the deferred freelist immediately.
+ * Returns the total amount freed. The total freed may be higher depending
+ * on the size of the items in the list, or lower if there is insufficient
+ * total memory on the freelist.
+ *
+ * Unlike with @ion_heap_freelist_drain, don't put any pages back into
+ * page pools or otherwise cache the pages. Everything must be
+ * genuinely free'd back to the system. If you're free'ing from a
+ * shrinker you probably want to use this. Note that this relies on
+ * the heap.ops.free callback honoring the ION_PRIV_FLAG_SHRINKER_FREE
+ * flag.
+ */
+size_t ion_heap_freelist_shrink(struct ion_heap *heap,
+ size_t size);
+
+/**
+ * ion_heap_freelist_size - returns the size of the freelist in bytes
+ * @heap: the heap
+ */
+size_t ion_heap_freelist_size(struct ion_heap *heap);
+
+
+/**
+ * functions for creating and destroying the built in ion heaps.
+ * architectures can add their own custom architecture specific
+ * heaps as appropriate.
+ */
+
+struct ion_heap *ion_heap_create(struct ion_platform_heap *);
+void ion_heap_destroy(struct ion_heap *);
+struct ion_heap *ion_system_heap_create(struct ion_platform_heap *);
+void ion_system_heap_destroy(struct ion_heap *);
+
+struct ion_heap *ion_system_contig_heap_create(struct ion_platform_heap *);
+void ion_system_contig_heap_destroy(struct ion_heap *);
+
+struct ion_heap *ion_carveout_heap_create(struct ion_platform_heap *);
+void ion_carveout_heap_destroy(struct ion_heap *);
+
+struct ion_heap *ion_chunk_heap_create(struct ion_platform_heap *);
+void ion_chunk_heap_destroy(struct ion_heap *);
+struct ion_heap *ion_cma_heap_create(struct ion_platform_heap *);
+void ion_cma_heap_destroy(struct ion_heap *);
+
+/**
+ * kernel api to allocate/free from carveout -- used when carveout is
+ * used to back an architecture specific custom heap
+ */
+ion_phys_addr_t ion_carveout_allocate(struct ion_heap *heap, unsigned long size,
+ unsigned long align);
+void ion_carveout_free(struct ion_heap *heap, ion_phys_addr_t addr,
+ unsigned long size);
+/**
+ * The carveout heap returns physical addresses, since 0 may be a valid
+ * physical address, this is used to indicate allocation failed
+ */
+#define ION_CARVEOUT_ALLOCATE_FAIL -1
+
+/**
+ * functions for creating and destroying a heap pool -- allows you
+ * to keep a pool of pre allocated memory to use from your heap. Keeping
+ * a pool of memory that is ready for dma, ie any cached mapping have been
+ * invalidated from the cache, provides a significant peformance benefit on
+ * many systems */
+
+/**
+ * struct ion_page_pool - pagepool struct
+ * @high_count: number of highmem items in the pool
+ * @low_count: number of lowmem items in the pool
+ * @high_items: list of highmem items
+ * @low_items: list of lowmem items
+ * @mutex: lock protecting this struct and especially the count
+ * item list
+ * @gfp_mask: gfp_mask to use from alloc
+ * @order: order of pages in the pool
+ * @list: plist node for list of pools
+ *
+ * Allows you to keep a pool of pre allocated pages to use from your heap.
+ * Keeping a pool of pages that is ready for dma, ie any cached mapping have
+ * been invalidated from the cache, provides a significant peformance benefit
+ * on many systems
+ */
+struct ion_page_pool {
+ int high_count;
+ int low_count;
+ struct list_head high_items;
+ struct list_head low_items;
+ struct mutex mutex;
+ gfp_t gfp_mask;
+ unsigned int order;
+ struct plist_node list;
+};
+
+struct ion_page_pool *ion_page_pool_create(gfp_t gfp_mask, unsigned int order);
+void ion_page_pool_destroy(struct ion_page_pool *);
+void *ion_page_pool_alloc(struct ion_page_pool *);
+void ion_page_pool_free(struct ion_page_pool *, struct page *);
+void ion_page_pool_free_immediate(struct ion_page_pool *, struct page *);
+
+#ifdef CONFIG_ION_POOL_CACHE_POLICY
+static inline void ion_page_pool_alloc_set_cache_policy
+ (struct ion_page_pool *pool,
+ struct page *page){
+ void *va = page_address(page);
+
+ if (va)
+ set_memory_wc((unsigned long)va, 1 << pool->order);
+}
+
+static inline void ion_page_pool_free_set_cache_policy
+ (struct ion_page_pool *pool,
+ struct page *page){
+ void *va = page_address(page);
+
+ if (va)
+ set_memory_wb((unsigned long)va, 1 << pool->order);
+
+}
+#else
+static inline void ion_page_pool_alloc_set_cache_policy
+ (struct ion_page_pool *pool,
+ struct page *page){ }
+
+static inline void ion_page_pool_free_set_cache_policy
+ (struct ion_page_pool *pool,
+ struct page *page){ }
+#endif
+
+
+/** ion_page_pool_shrink - shrinks the size of the memory cached in the pool
+ * @pool: the pool
+ * @gfp_mask: the memory type to reclaim
+ * @nr_to_scan: number of items to shrink in pages
+ *
+ * returns the number of items freed in pages
+ */
+int ion_page_pool_shrink(struct ion_page_pool *pool, gfp_t gfp_mask,
+ int nr_to_scan);
+
+/**
+ * ion_pages_sync_for_device - cache flush pages for use with the specified
+ * device
+ * @dev: the device the pages will be used with
+ * @page: the first page to be flushed
+ * @size: size in bytes of region to be flushed
+ * @dir: direction of dma transfer
+ */
+void ion_pages_sync_for_device(struct device *dev, struct page *page,
+ size_t size, enum dma_data_direction dir);
+
+#endif /* _ION_PRIV_H */
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
new file mode 100644
index 0000000..69c2168
--- /dev/null
+++ b/drivers/staging/android/ion/ion_system_heap.c
@@ -0,0 +1,453 @@
+/*
+ * drivers/gpu/ion/ion_system_heap.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <asm/page.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include "ion.h"
+#include "ion_priv.h"
+
+static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN |
+ __GFP_NORETRY) & ~__GFP_WAIT;
+static gfp_t low_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN);
+static const unsigned int orders[] = {8, 4, 0};
+static const int num_orders = ARRAY_SIZE(orders);
+static int order_to_index(unsigned int order)
+{
+ int i;
+
+ for (i = 0; i < num_orders; i++)
+ if (order == orders[i])
+ return i;
+ BUG();
+ return -1;
+}
+
+static unsigned int order_to_size(int order)
+{
+ return PAGE_SIZE << order;
+}
+
+struct ion_system_heap {
+ struct ion_heap heap;
+ struct ion_page_pool **pools;
+};
+
+struct page_info {
+ struct page *page;
+ unsigned int order;
+ struct list_head list;
+};
+
+static struct page *alloc_buffer_page(struct ion_system_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long order)
+{
+ bool cached = ion_buffer_cached(buffer);
+ struct ion_page_pool *pool = heap->pools[order_to_index(order)];
+ struct page *page;
+
+ if (!cached) {
+ page = ion_page_pool_alloc(pool);
+ } else {
+ gfp_t gfp_flags = low_order_gfp_flags;
+
+ if (order > 4)
+ gfp_flags = high_order_gfp_flags;
+ page = alloc_pages(gfp_flags, order);
+ if (!page)
+ return NULL;
+ ion_pages_sync_for_device(NULL, page, PAGE_SIZE << order,
+ DMA_BIDIRECTIONAL);
+ }
+ if (!page)
+ return NULL;
+
+ return page;
+}
+
+static void free_buffer_page(struct ion_system_heap *heap,
+ struct ion_buffer *buffer, struct page *page,
+ unsigned int order)
+{
+ bool cached = ion_buffer_cached(buffer);
+
+ if (!cached) {
+ struct ion_page_pool *pool = heap->pools[order_to_index(order)];
+ if (buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE)
+ ion_page_pool_free_immediate(pool, page);
+ else
+ ion_page_pool_free(pool, page);
+ } else {
+ __free_pages(page, order);
+ }
+}
+
+
+static struct page_info *alloc_largest_available(struct ion_system_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long size,
+ unsigned int max_order)
+{
+ struct page *page;
+ struct page_info *info;
+ int i;
+
+ info = kmalloc(sizeof(struct page_info), GFP_KERNEL);
+ if (!info)
+ return NULL;
+
+ for (i = 0; i < num_orders; i++) {
+ if (size < order_to_size(orders[i]))
+ continue;
+ if (max_order < orders[i])
+ continue;
+
+ page = alloc_buffer_page(heap, buffer, orders[i]);
+ if (!page)
+ continue;
+
+ info->page = page;
+ info->order = orders[i];
+ INIT_LIST_HEAD(&info->list);
+ return info;
+ }
+ kfree(info);
+
+ return NULL;
+}
+
+static int ion_system_heap_allocate(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long size, unsigned long align,
+ unsigned long flags)
+{
+ struct ion_system_heap *sys_heap = container_of(heap,
+ struct ion_system_heap,
+ heap);
+ struct sg_table *table;
+ struct scatterlist *sg;
+ int ret;
+ struct list_head pages;
+ struct page_info *info, *tmp_info;
+ int i = 0;
+ unsigned long size_remaining = PAGE_ALIGN(size);
+ unsigned int max_order = orders[0];
+
+ if (align > PAGE_SIZE)
+ return -EINVAL;
+
+ if (size / PAGE_SIZE > totalram_pages / 2)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&pages);
+ while (size_remaining > 0) {
+ info = alloc_largest_available(sys_heap, buffer, size_remaining,
+ max_order);
+ if (!info)
+ goto err;
+ list_add_tail(&info->list, &pages);
+ size_remaining -= (1 << info->order) * PAGE_SIZE;
+ max_order = info->order;
+ i++;
+ }
+ table = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
+ if (!table)
+ goto err;
+
+ ret = sg_alloc_table(table, i, GFP_KERNEL);
+ if (ret)
+ goto err1;
+
+ sg = table->sgl;
+ list_for_each_entry_safe(info, tmp_info, &pages, list) {
+ struct page *page = info->page;
+ sg_set_page(sg, page, (1 << info->order) * PAGE_SIZE, 0);
+ sg = sg_next(sg);
+ list_del(&info->list);
+ kfree(info);
+ }
+
+ buffer->priv_virt = table;
+ return 0;
+err1:
+ kfree(table);
+err:
+ list_for_each_entry_safe(info, tmp_info, &pages, list) {
+ free_buffer_page(sys_heap, buffer, info->page, info->order);
+ kfree(info);
+ }
+ return -ENOMEM;
+}
+
+static void ion_system_heap_free(struct ion_buffer *buffer)
+{
+ struct ion_heap *heap = buffer->heap;
+ struct ion_system_heap *sys_heap = container_of(heap,
+ struct ion_system_heap,
+ heap);
+ struct sg_table *table = buffer->sg_table;
+ bool cached = ion_buffer_cached(buffer);
+ struct scatterlist *sg;
+ LIST_HEAD(pages);
+ int i;
+
+ /* uncached pages come from the page pools, zero them before returning
+ for security purposes (other allocations are zerod at alloc time */
+ if (!cached && !(buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE))
+ ion_heap_buffer_zero(buffer);
+
+ for_each_sg(table->sgl, sg, table->nents, i)
+ free_buffer_page(sys_heap, buffer, sg_page(sg),
+ get_order(sg->length));
+ sg_free_table(table);
+ kfree(table);
+}
+
+static struct sg_table *ion_system_heap_map_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return buffer->priv_virt;
+}
+
+static void ion_system_heap_unmap_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return;
+}
+
+static int ion_system_heap_shrink(struct ion_heap *heap, gfp_t gfp_mask,
+ int nr_to_scan)
+{
+ struct ion_system_heap *sys_heap;
+ int nr_total = 0;
+ int i;
+
+ sys_heap = container_of(heap, struct ion_system_heap, heap);
+
+ for (i = 0; i < num_orders; i++) {
+ struct ion_page_pool *pool = sys_heap->pools[i];
+
+ nr_total += ion_page_pool_shrink(pool, gfp_mask, nr_to_scan);
+ }
+
+ return nr_total;
+}
+
+static struct ion_heap_ops system_heap_ops = {
+ .allocate = ion_system_heap_allocate,
+ .free = ion_system_heap_free,
+ .map_dma = ion_system_heap_map_dma,
+ .unmap_dma = ion_system_heap_unmap_dma,
+ .map_kernel = ion_heap_map_kernel,
+ .unmap_kernel = ion_heap_unmap_kernel,
+ .map_user = ion_heap_map_user,
+ .shrink = ion_system_heap_shrink,
+};
+
+static int ion_system_heap_debug_show(struct ion_heap *heap, struct seq_file *s,
+ void *unused)
+{
+
+ struct ion_system_heap *sys_heap = container_of(heap,
+ struct ion_system_heap,
+ heap);
+ int i;
+
+ for (i = 0; i < num_orders; i++) {
+ struct ion_page_pool *pool = sys_heap->pools[i];
+
+ seq_printf(s, "%d order %u highmem pages in pool = %lu total\n",
+ pool->high_count, pool->order,
+ (1 << pool->order) * PAGE_SIZE * pool->high_count);
+ seq_printf(s, "%d order %u lowmem pages in pool = %lu total\n",
+ pool->low_count, pool->order,
+ (1 << pool->order) * PAGE_SIZE * pool->low_count);
+ }
+ return 0;
+}
+
+struct ion_heap *ion_system_heap_create(struct ion_platform_heap *unused)
+{
+ struct ion_system_heap *heap;
+ int i;
+
+ heap = kzalloc(sizeof(struct ion_system_heap), GFP_KERNEL);
+ if (!heap)
+ return ERR_PTR(-ENOMEM);
+ heap->heap.ops = &system_heap_ops;
+ heap->heap.type = ION_HEAP_TYPE_SYSTEM;
+ heap->heap.flags = ION_HEAP_FLAG_DEFER_FREE;
+ heap->pools = kzalloc(sizeof(struct ion_page_pool *) * num_orders,
+ GFP_KERNEL);
+ if (!heap->pools)
+ goto err_alloc_pools;
+ for (i = 0; i < num_orders; i++) {
+ struct ion_page_pool *pool;
+ gfp_t gfp_flags = low_order_gfp_flags;
+
+ if (orders[i] > 4)
+ gfp_flags = high_order_gfp_flags;
+ pool = ion_page_pool_create(gfp_flags, orders[i]);
+ if (!pool)
+ goto err_create_pool;
+ heap->pools[i] = pool;
+ }
+
+ heap->heap.debug_show = ion_system_heap_debug_show;
+ return &heap->heap;
+err_create_pool:
+ for (i = 0; i < num_orders; i++)
+ if (heap->pools[i])
+ ion_page_pool_destroy(heap->pools[i]);
+ kfree(heap->pools);
+err_alloc_pools:
+ kfree(heap);
+ return ERR_PTR(-ENOMEM);
+}
+
+void ion_system_heap_destroy(struct ion_heap *heap)
+{
+ struct ion_system_heap *sys_heap = container_of(heap,
+ struct ion_system_heap,
+ heap);
+ int i;
+
+ for (i = 0; i < num_orders; i++)
+ ion_page_pool_destroy(sys_heap->pools[i]);
+ kfree(sys_heap->pools);
+ kfree(sys_heap);
+}
+
+static int ion_system_contig_heap_allocate(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ unsigned long len,
+ unsigned long align,
+ unsigned long flags)
+{
+ int order = get_order(len);
+ struct page *page;
+ struct sg_table *table;
+ unsigned long i;
+ int ret;
+
+ if (align > (PAGE_SIZE << order))
+ return -EINVAL;
+
+ page = alloc_pages(low_order_gfp_flags, order);
+ if (!page)
+ return -ENOMEM;
+
+ split_page(page, order);
+
+ len = PAGE_ALIGN(len);
+ for (i = len >> PAGE_SHIFT; i < (1 << order); i++)
+ __free_page(page + i);
+
+ table = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
+ if (!table) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = sg_alloc_table(table, 1, GFP_KERNEL);
+ if (ret)
+ goto out;
+
+ sg_set_page(table->sgl, page, len, 0);
+
+ buffer->priv_virt = table;
+
+ ion_pages_sync_for_device(NULL, page, len, DMA_BIDIRECTIONAL);
+
+ return 0;
+
+out:
+ for (i = 0; i < len >> PAGE_SHIFT; i++)
+ __free_page(page + i);
+ kfree(table);
+ return ret;
+}
+
+static void ion_system_contig_heap_free(struct ion_buffer *buffer)
+{
+ struct sg_table *table = buffer->priv_virt;
+ struct page *page = sg_page(table->sgl);
+ unsigned long pages = PAGE_ALIGN(buffer->size) >> PAGE_SHIFT;
+ unsigned long i;
+
+ for (i = 0; i < pages; i++)
+ __free_page(page + i);
+ sg_free_table(table);
+ kfree(table);
+}
+
+static int ion_system_contig_heap_phys(struct ion_heap *heap,
+ struct ion_buffer *buffer,
+ ion_phys_addr_t *addr, size_t *len)
+{
+ struct sg_table *table = buffer->priv_virt;
+ struct page *page = sg_page(table->sgl);
+ *addr = page_to_phys(page);
+ *len = buffer->size;
+ return 0;
+}
+
+static struct sg_table *ion_system_contig_heap_map_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+ return buffer->priv_virt;
+}
+
+static void ion_system_contig_heap_unmap_dma(struct ion_heap *heap,
+ struct ion_buffer *buffer)
+{
+}
+
+static struct ion_heap_ops kmalloc_ops = {
+ .allocate = ion_system_contig_heap_allocate,
+ .free = ion_system_contig_heap_free,
+ .phys = ion_system_contig_heap_phys,
+ .map_dma = ion_system_contig_heap_map_dma,
+ .unmap_dma = ion_system_contig_heap_unmap_dma,
+ .map_kernel = ion_heap_map_kernel,
+ .unmap_kernel = ion_heap_unmap_kernel,
+ .map_user = ion_heap_map_user,
+};
+
+struct ion_heap *ion_system_contig_heap_create(struct ion_platform_heap *unused)
+{
+ struct ion_heap *heap;
+
+ heap = kzalloc(sizeof(struct ion_heap), GFP_KERNEL);
+ if (!heap)
+ return ERR_PTR(-ENOMEM);
+ heap->ops = &kmalloc_ops;
+ heap->type = ION_HEAP_TYPE_SYSTEM_CONTIG;
+ return heap;
+}
+
+void ion_system_contig_heap_destroy(struct ion_heap *heap)
+{
+ kfree(heap);
+}
+
diff --git a/drivers/staging/android/ion/ion_test.c b/drivers/staging/android/ion/ion_test.c
new file mode 100644
index 0000000..654acb5
--- /dev/null
+++ b/drivers/staging/android/ion/ion_test.c
@@ -0,0 +1,282 @@
+/*
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) "ion-test: " fmt
+
+#include <linux/dma-buf.h>
+#include <linux/dma-direction.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+
+#include "ion.h"
+#include "../uapi/ion_test.h"
+
+#define u64_to_uptr(x) ((void __user *)(unsigned long)(x))
+
+struct ion_test_device {
+ struct miscdevice misc;
+};
+
+struct ion_test_data {
+ struct dma_buf *dma_buf;
+ struct device *dev;
+};
+
+static int ion_handle_test_dma(struct device *dev, struct dma_buf *dma_buf,
+ void __user *ptr, size_t offset, size_t size, bool write)
+{
+ int ret = 0;
+ struct dma_buf_attachment *attach;
+ struct sg_table *table;
+ pgprot_t pgprot = pgprot_writecombine(PAGE_KERNEL);
+ enum dma_data_direction dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+ struct sg_page_iter sg_iter;
+ unsigned long offset_page;
+
+ attach = dma_buf_attach(dma_buf, dev);
+ if (IS_ERR(attach))
+ return PTR_ERR(attach);
+
+ table = dma_buf_map_attachment(attach, dir);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ offset_page = offset >> PAGE_SHIFT;
+ offset %= PAGE_SIZE;
+
+ for_each_sg_page(table->sgl, &sg_iter, table->nents, offset_page) {
+ struct page *page = sg_page_iter_page(&sg_iter);
+ void *vaddr = vmap(&page, 1, VM_MAP, pgprot);
+ size_t to_copy = PAGE_SIZE - offset;
+
+ to_copy = min(to_copy, size);
+ if (!vaddr) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ if (write)
+ ret = copy_from_user(vaddr + offset, ptr, to_copy);
+ else
+ ret = copy_to_user(ptr, vaddr + offset, to_copy);
+
+ vunmap(vaddr);
+ if (ret) {
+ ret = -EFAULT;
+ goto err;
+ }
+ size -= to_copy;
+ if (!size)
+ break;
+ ptr += to_copy;
+ offset = 0;
+ }
+
+err:
+ dma_buf_unmap_attachment(attach, table, dir);
+ dma_buf_detach(dma_buf, attach);
+ return ret;
+}
+
+static int ion_handle_test_kernel(struct dma_buf *dma_buf, void __user *ptr,
+ size_t offset, size_t size, bool write)
+{
+ int ret;
+ unsigned long page_offset = offset >> PAGE_SHIFT;
+ size_t copy_offset = offset % PAGE_SIZE;
+ size_t copy_size = size;
+ enum dma_data_direction dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+ if (offset > dma_buf->size || size > dma_buf->size - offset)
+ return -EINVAL;
+
+ ret = dma_buf_begin_cpu_access(dma_buf, offset, size, dir);
+ if (ret)
+ return ret;
+
+ while (copy_size > 0) {
+ size_t to_copy;
+ void *vaddr = dma_buf_kmap(dma_buf, page_offset);
+
+ if (!vaddr)
+ goto err;
+
+ to_copy = min_t(size_t, PAGE_SIZE - copy_offset, copy_size);
+
+ if (write)
+ ret = copy_from_user(vaddr + copy_offset, ptr, to_copy);
+ else
+ ret = copy_to_user(ptr, vaddr + copy_offset, to_copy);
+
+ dma_buf_kunmap(dma_buf, page_offset, vaddr);
+ if (ret) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ copy_size -= to_copy;
+ ptr += to_copy;
+ page_offset++;
+ copy_offset = 0;
+ }
+err:
+ dma_buf_end_cpu_access(dma_buf, offset, size, dir);
+ return ret;
+}
+
+static long ion_test_ioctl(struct file *filp, unsigned int cmd,
+ unsigned long arg)
+{
+ struct ion_test_data *test_data = filp->private_data;
+ int ret = 0;
+
+ union {
+ struct ion_test_rw_data test_rw;
+ } data;
+
+ if (_IOC_SIZE(cmd) > sizeof(data))
+ return -EINVAL;
+
+ if (_IOC_DIR(cmd) & _IOC_WRITE)
+ if (copy_from_user(&data, (void __user *)arg, _IOC_SIZE(cmd)))
+ return -EFAULT;
+
+ switch (cmd) {
+ case ION_IOC_TEST_SET_FD:
+ {
+ struct dma_buf *dma_buf = NULL;
+ int fd = arg;
+
+ if (fd >= 0) {
+ dma_buf = dma_buf_get((int)arg);
+ if (IS_ERR(dma_buf))
+ return PTR_ERR(dma_buf);
+ }
+ if (test_data->dma_buf)
+ dma_buf_put(test_data->dma_buf);
+ test_data->dma_buf = dma_buf;
+ break;
+ }
+ case ION_IOC_TEST_DMA_MAPPING:
+ {
+ ret = ion_handle_test_dma(test_data->dev, test_data->dma_buf,
+ u64_to_uptr(data.test_rw.ptr),
+ data.test_rw.offset, data.test_rw.size,
+ data.test_rw.write);
+ break;
+ }
+ case ION_IOC_TEST_KERNEL_MAPPING:
+ {
+ ret = ion_handle_test_kernel(test_data->dma_buf,
+ u64_to_uptr(data.test_rw.ptr),
+ data.test_rw.offset, data.test_rw.size,
+ data.test_rw.write);
+ break;
+ }
+ default:
+ return -ENOTTY;
+ }
+
+ if (_IOC_DIR(cmd) & _IOC_READ) {
+ if (copy_to_user((void __user *)arg, &data, sizeof(data)))
+ return -EFAULT;
+ }
+ return ret;
+}
+
+static int ion_test_open(struct inode *inode, struct file *file)
+{
+ struct ion_test_data *data;
+ struct miscdevice *miscdev = file->private_data;
+
+ data = kzalloc(sizeof(struct ion_test_data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->dev = miscdev->parent;
+
+ file->private_data = data;
+
+ return 0;
+}
+
+static int ion_test_release(struct inode *inode, struct file *file)
+{
+ struct ion_test_data *data = file->private_data;
+
+ kfree(data);
+
+ return 0;
+}
+
+static const struct file_operations ion_test_fops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = ion_test_ioctl,
+ .compat_ioctl = ion_test_ioctl,
+ .open = ion_test_open,
+ .release = ion_test_release,
+};
+
+static int __init ion_test_probe(struct platform_device *pdev)
+{
+ int ret;
+ struct ion_test_device *testdev;
+
+ testdev = devm_kzalloc(&pdev->dev, sizeof(struct ion_test_device),
+ GFP_KERNEL);
+ if (!testdev)
+ return -ENOMEM;
+
+ testdev->misc.minor = MISC_DYNAMIC_MINOR;
+ testdev->misc.name = "ion-test";
+ testdev->misc.fops = &ion_test_fops;
+ testdev->misc.parent = &pdev->dev;
+ ret = misc_register(&testdev->misc);
+ if (ret) {
+ pr_err("failed to register misc device.\n");
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, testdev);
+
+ return 0;
+}
+
+static struct platform_driver ion_test_platform_driver = {
+ .driver = {
+ .name = "ion-test",
+ },
+};
+
+static int __init ion_test_init(void)
+{
+ platform_device_register_simple("ion-test", -1, NULL, 0);
+ return platform_driver_probe(&ion_test_platform_driver, ion_test_probe);
+}
+
+static void __exit ion_test_exit(void)
+{
+ platform_driver_unregister(&ion_test_platform_driver);
+}
+
+module_init(ion_test_init);
+module_exit(ion_test_exit);
diff --git a/drivers/staging/android/ion/tegra/Makefile b/drivers/staging/android/ion/tegra/Makefile
new file mode 100644
index 0000000..11cd003
--- /dev/null
+++ b/drivers/staging/android/ion/tegra/Makefile
@@ -0,0 +1 @@
+obj-y += tegra_ion.o
diff --git a/drivers/staging/android/ion/tegra/tegra_ion.c b/drivers/staging/android/ion/tegra/tegra_ion.c
new file mode 100644
index 0000000..3474c65
--- /dev/null
+++ b/drivers/staging/android/ion/tegra/tegra_ion.c
@@ -0,0 +1,84 @@
+/*
+ * drivers/gpu/tegra/tegra_ion.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include "../ion.h"
+#include "../ion_priv.h"
+
+static struct ion_device *idev;
+static int num_heaps;
+static struct ion_heap **heaps;
+
+static int tegra_ion_probe(struct platform_device *pdev)
+{
+ struct ion_platform_data *pdata = pdev->dev.platform_data;
+ int err;
+ int i;
+
+ num_heaps = pdata->nr;
+
+ heaps = kzalloc(sizeof(struct ion_heap *) * pdata->nr, GFP_KERNEL);
+
+ idev = ion_device_create(NULL);
+ if (IS_ERR_OR_NULL(idev)) {
+ kfree(heaps);
+ return PTR_ERR(idev);
+ }
+
+ /* create the heaps as specified in the board file */
+ for (i = 0; i < num_heaps; i++) {
+ struct ion_platform_heap *heap_data = &pdata->heaps[i];
+
+ heaps[i] = ion_heap_create(heap_data);
+ if (IS_ERR_OR_NULL(heaps[i])) {
+ err = PTR_ERR(heaps[i]);
+ goto err;
+ }
+ ion_device_add_heap(idev, heaps[i]);
+ }
+ platform_set_drvdata(pdev, idev);
+ return 0;
+err:
+ for (i = 0; i < num_heaps; i++) {
+ if (heaps[i])
+ ion_heap_destroy(heaps[i]);
+ }
+ kfree(heaps);
+ return err;
+}
+
+static int tegra_ion_remove(struct platform_device *pdev)
+{
+ struct ion_device *idev = platform_get_drvdata(pdev);
+ int i;
+
+ ion_device_destroy(idev);
+ for (i = 0; i < num_heaps; i++)
+ ion_heap_destroy(heaps[i]);
+ kfree(heaps);
+ return 0;
+}
+
+static struct platform_driver ion_driver = {
+ .probe = tegra_ion_probe,
+ .remove = tegra_ion_remove,
+ .driver = { .name = "ion-tegra" }
+};
+
+module_platform_driver(ion_driver);
+
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
deleted file mode 100644
index 34519ea..0000000
--- a/drivers/staging/android/logger.c
+++ /dev/null
@@ -1,851 +0,0 @@
-/*
- * drivers/misc/logger.c
- *
- * A Logging Subsystem
- *
- * Copyright (C) 2007-2008 Google, Inc.
- *
- * Robert Love <rlove@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) "logger: " fmt
-
-#include <linux/sched.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/uaccess.h>
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/time.h>
-#include <linux/vmalloc.h>
-#include <linux/aio.h>
-#include "logger.h"
-
-#include <asm/ioctls.h>
-
-/**
- * struct logger_log - represents a specific log, such as 'main' or 'radio'
- * @buffer: The actual ring buffer
- * @misc: The "misc" device representing the log
- * @wq: The wait queue for @readers
- * @readers: This log's readers
- * @mutex: The mutex that protects the @buffer
- * @w_off: The current write head offset
- * @head: The head, or location that readers start reading at.
- * @size: The size of the log
- * @logs: The list of log channels
- *
- * This structure lives from module insertion until module removal, so it does
- * not need additional reference counting. The structure is protected by the
- * mutex 'mutex'.
- */
-struct logger_log {
- unsigned char *buffer;
- struct miscdevice misc;
- wait_queue_head_t wq;
- struct list_head readers;
- struct mutex mutex;
- size_t w_off;
- size_t head;
- size_t size;
- struct list_head logs;
-};
-
-static LIST_HEAD(log_list);
-
-
-/**
- * struct logger_reader - a logging device open for reading
- * @log: The associated log
- * @list: The associated entry in @logger_log's list
- * @r_off: The current read head offset.
- * @r_all: Reader can read all entries
- * @r_ver: Reader ABI version
- *
- * This object lives from open to release, so we don't need additional
- * reference counting. The structure is protected by log->mutex.
- */
-struct logger_reader {
- struct logger_log *log;
- struct list_head list;
- size_t r_off;
- bool r_all;
- int r_ver;
-};
-
-/* logger_offset - returns index 'n' into the log via (optimized) modulus */
-static size_t logger_offset(struct logger_log *log, size_t n)
-{
- return n & (log->size - 1);
-}
-
-
-/*
- * file_get_log - Given a file structure, return the associated log
- *
- * This isn't aesthetic. We have several goals:
- *
- * 1) Need to quickly obtain the associated log during an I/O operation
- * 2) Readers need to maintain state (logger_reader)
- * 3) Writers need to be very fast (open() should be a near no-op)
- *
- * In the reader case, we can trivially go file->logger_reader->logger_log.
- * For a writer, we don't want to maintain a logger_reader, so we just go
- * file->logger_log. Thus what file->private_data points at depends on whether
- * or not the file was opened for reading. This function hides that dirtiness.
- */
-static inline struct logger_log *file_get_log(struct file *file)
-{
- if (file->f_mode & FMODE_READ) {
- struct logger_reader *reader = file->private_data;
- return reader->log;
- } else
- return file->private_data;
-}
-
-/*
- * get_entry_header - returns a pointer to the logger_entry header within
- * 'log' starting at offset 'off'. A temporary logger_entry 'scratch' must
- * be provided. Typically the return value will be a pointer within
- * 'logger->buf'. However, a pointer to 'scratch' may be returned if
- * the log entry spans the end and beginning of the circular buffer.
- */
-static struct logger_entry *get_entry_header(struct logger_log *log,
- size_t off, struct logger_entry *scratch)
-{
- size_t len = min(sizeof(struct logger_entry), log->size - off);
- if (len != sizeof(struct logger_entry)) {
- memcpy(((void *) scratch), log->buffer + off, len);
- memcpy(((void *) scratch) + len, log->buffer,
- sizeof(struct logger_entry) - len);
- return scratch;
- }
-
- return (struct logger_entry *) (log->buffer + off);
-}
-
-/*
- * get_entry_msg_len - Grabs the length of the message of the entry
- * starting from from 'off'.
- *
- * An entry length is 2 bytes (16 bits) in host endian order.
- * In the log, the length does not include the size of the log entry structure.
- * This function returns the size including the log entry structure.
- *
- * Caller needs to hold log->mutex.
- */
-static __u32 get_entry_msg_len(struct logger_log *log, size_t off)
-{
- struct logger_entry scratch;
- struct logger_entry *entry;
-
- entry = get_entry_header(log, off, &scratch);
- return entry->len;
-}
-
-static size_t get_user_hdr_len(int ver)
-{
- if (ver < 2)
- return sizeof(struct user_logger_entry_compat);
- else
- return sizeof(struct logger_entry);
-}
-
-static ssize_t copy_header_to_user(int ver, struct logger_entry *entry,
- char __user *buf)
-{
- void *hdr;
- size_t hdr_len;
- struct user_logger_entry_compat v1;
-
- if (ver < 2) {
- v1.len = entry->len;
- v1.__pad = 0;
- v1.pid = entry->pid;
- v1.tid = entry->tid;
- v1.sec = entry->sec;
- v1.nsec = entry->nsec;
- hdr = &v1;
- hdr_len = sizeof(struct user_logger_entry_compat);
- } else {
- hdr = entry;
- hdr_len = sizeof(struct logger_entry);
- }
-
- return copy_to_user(buf, hdr, hdr_len);
-}
-
-/*
- * do_read_log_to_user - reads exactly 'count' bytes from 'log' into the
- * user-space buffer 'buf'. Returns 'count' on success.
- *
- * Caller must hold log->mutex.
- */
-static ssize_t do_read_log_to_user(struct logger_log *log,
- struct logger_reader *reader,
- char __user *buf,
- size_t count)
-{
- struct logger_entry scratch;
- struct logger_entry *entry;
- size_t len;
- size_t msg_start;
-
- /*
- * First, copy the header to userspace, using the version of
- * the header requested
- */
- entry = get_entry_header(log, reader->r_off, &scratch);
- if (copy_header_to_user(reader->r_ver, entry, buf))
- return -EFAULT;
-
- count -= get_user_hdr_len(reader->r_ver);
- buf += get_user_hdr_len(reader->r_ver);
- msg_start = logger_offset(log,
- reader->r_off + sizeof(struct logger_entry));
-
- /*
- * We read from the msg in two disjoint operations. First, we read from
- * the current msg head offset up to 'count' bytes or to the end of
- * the log, whichever comes first.
- */
- len = min(count, log->size - msg_start);
- if (copy_to_user(buf, log->buffer + msg_start, len))
- return -EFAULT;
-
- /*
- * Second, we read any remaining bytes, starting back at the head of
- * the log.
- */
- if (count != len)
- if (copy_to_user(buf + len, log->buffer, count - len))
- return -EFAULT;
-
- reader->r_off = logger_offset(log, reader->r_off +
- sizeof(struct logger_entry) + count);
-
- return count + get_user_hdr_len(reader->r_ver);
-}
-
-/*
- * get_next_entry_by_uid - Starting at 'off', returns an offset into
- * 'log->buffer' which contains the first entry readable by 'euid'
- */
-static size_t get_next_entry_by_uid(struct logger_log *log,
- size_t off, kuid_t euid)
-{
- while (off != log->w_off) {
- struct logger_entry *entry;
- struct logger_entry scratch;
- size_t next_len;
-
- entry = get_entry_header(log, off, &scratch);
-
- if (uid_eq(entry->euid, euid))
- return off;
-
- next_len = sizeof(struct logger_entry) + entry->len;
- off = logger_offset(log, off + next_len);
- }
-
- return off;
-}
-
-/*
- * logger_read - our log's read() method
- *
- * Behavior:
- *
- * - O_NONBLOCK works
- * - If there are no log entries to read, blocks until log is written to
- * - Atomically reads exactly one log entry
- *
- * Will set errno to EINVAL if read
- * buffer is insufficient to hold next entry.
- */
-static ssize_t logger_read(struct file *file, char __user *buf,
- size_t count, loff_t *pos)
-{
- struct logger_reader *reader = file->private_data;
- struct logger_log *log = reader->log;
- ssize_t ret;
- DEFINE_WAIT(wait);
-
-start:
- while (1) {
- mutex_lock(&log->mutex);
-
- prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);
-
- ret = (log->w_off == reader->r_off);
- mutex_unlock(&log->mutex);
- if (!ret)
- break;
-
- if (file->f_flags & O_NONBLOCK) {
- ret = -EAGAIN;
- break;
- }
-
- if (signal_pending(current)) {
- ret = -EINTR;
- break;
- }
-
- schedule();
- }
-
- finish_wait(&log->wq, &wait);
- if (ret)
- return ret;
-
- mutex_lock(&log->mutex);
-
- if (!reader->r_all)
- reader->r_off = get_next_entry_by_uid(log,
- reader->r_off, current_euid());
-
- /* is there still something to read or did we race? */
- if (unlikely(log->w_off == reader->r_off)) {
- mutex_unlock(&log->mutex);
- goto start;
- }
-
- /* get the size of the next entry */
- ret = get_user_hdr_len(reader->r_ver) +
- get_entry_msg_len(log, reader->r_off);
- if (count < ret) {
- ret = -EINVAL;
- goto out;
- }
-
- /* get exactly one entry from the log */
- ret = do_read_log_to_user(log, reader, buf, ret);
-
-out:
- mutex_unlock(&log->mutex);
-
- return ret;
-}
-
-/*
- * get_next_entry - return the offset of the first valid entry at least 'len'
- * bytes after 'off'.
- *
- * Caller must hold log->mutex.
- */
-static size_t get_next_entry(struct logger_log *log, size_t off, size_t len)
-{
- size_t count = 0;
-
- do {
- size_t nr = sizeof(struct logger_entry) +
- get_entry_msg_len(log, off);
- off = logger_offset(log, off + nr);
- count += nr;
- } while (count < len);
-
- return off;
-}
-
-/*
- * is_between - is a < c < b, accounting for wrapping of a, b, and c
- * positions in the buffer
- *
- * That is, if a<b, check for c between a and b
- * and if a>b, check for c outside (not between) a and b
- *
- * |------- a xxxxxxxx b --------|
- * c^
- *
- * |xxxxx b --------- a xxxxxxxxx|
- * c^
- * or c^
- */
-static inline int is_between(size_t a, size_t b, size_t c)
-{
- if (a < b) {
- /* is c between a and b? */
- if (a < c && c <= b)
- return 1;
- } else {
- /* is c outside of b through a? */
- if (c <= b || a < c)
- return 1;
- }
-
- return 0;
-}
-
-/*
- * fix_up_readers - walk the list of all readers and "fix up" any who were
- * lapped by the writer; also do the same for the default "start head".
- * We do this by "pulling forward" the readers and start head to the first
- * entry after the new write head.
- *
- * The caller needs to hold log->mutex.
- */
-static void fix_up_readers(struct logger_log *log, size_t len)
-{
- size_t old = log->w_off;
- size_t new = logger_offset(log, old + len);
- struct logger_reader *reader;
-
- if (is_between(old, new, log->head))
- log->head = get_next_entry(log, log->head, len);
-
- list_for_each_entry(reader, &log->readers, list)
- if (is_between(old, new, reader->r_off))
- reader->r_off = get_next_entry(log, reader->r_off, len);
-}
-
-/*
- * do_write_log - writes 'len' bytes from 'buf' to 'log'
- *
- * The caller needs to hold log->mutex.
- */
-static void do_write_log(struct logger_log *log, const void *buf, size_t count)
-{
- size_t len;
-
- len = min(count, log->size - log->w_off);
- memcpy(log->buffer + log->w_off, buf, len);
-
- if (count != len)
- memcpy(log->buffer, buf + len, count - len);
-
- log->w_off = logger_offset(log, log->w_off + count);
-
-}
-
-/*
- * do_write_log_user - writes 'len' bytes from the user-space buffer 'buf' to
- * the log 'log'
- *
- * The caller needs to hold log->mutex.
- *
- * Returns 'count' on success, negative error code on failure.
- */
-static ssize_t do_write_log_from_user(struct logger_log *log,
- const void __user *buf, size_t count)
-{
- size_t len;
-
- len = min(count, log->size - log->w_off);
- if (len && copy_from_user(log->buffer + log->w_off, buf, len))
- return -EFAULT;
-
- if (count != len)
- if (copy_from_user(log->buffer, buf + len, count - len))
- /*
- * Note that by not updating w_off, this abandons the
- * portion of the new entry that *was* successfully
- * copied, just above. This is intentional to avoid
- * message corruption from missing fragments.
- */
- return -EFAULT;
-
- log->w_off = logger_offset(log, log->w_off + count);
-
- return count;
-}
-
-/*
- * logger_aio_write - our write method, implementing support for write(),
- * writev(), and aio_write(). Writes are our fast path, and we try to optimize
- * them above all else.
- */
-static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t ppos)
-{
- struct logger_log *log = file_get_log(iocb->ki_filp);
- size_t orig;
- struct logger_entry header;
- struct timespec now;
- ssize_t ret = 0;
-
- now = current_kernel_time();
-
- header.pid = current->tgid;
- header.tid = current->pid;
- header.sec = now.tv_sec;
- header.nsec = now.tv_nsec;
- header.euid = current_euid();
- header.len = min_t(size_t, iocb->ki_left, LOGGER_ENTRY_MAX_PAYLOAD);
- header.hdr_size = sizeof(struct logger_entry);
-
- /* null writes succeed, return zero */
- if (unlikely(!header.len))
- return 0;
-
- mutex_lock(&log->mutex);
-
- orig = log->w_off;
-
- /*
- * Fix up any readers, pulling them forward to the first readable
- * entry after (what will be) the new write offset. We do this now
- * because if we partially fail, we can end up with clobbered log
- * entries that encroach on readable buffer.
- */
- fix_up_readers(log, sizeof(struct logger_entry) + header.len);
-
- do_write_log(log, &header, sizeof(struct logger_entry));
-
- while (nr_segs-- > 0) {
- size_t len;
- ssize_t nr;
-
- /* figure out how much of this vector we can keep */
- len = min_t(size_t, iov->iov_len, header.len - ret);
-
- /* write out this segment's payload */
- nr = do_write_log_from_user(log, iov->iov_base, len);
- if (unlikely(nr < 0)) {
- log->w_off = orig;
- mutex_unlock(&log->mutex);
- return nr;
- }
-
- iov++;
- ret += nr;
- }
-
- mutex_unlock(&log->mutex);
-
- /* wake up any blocked readers */
- wake_up_interruptible(&log->wq);
-
- return ret;
-}
-
-static struct logger_log *get_log_from_minor(int minor)
-{
- struct logger_log *log;
-
- list_for_each_entry(log, &log_list, logs)
- if (log->misc.minor == minor)
- return log;
- return NULL;
-}
-
-/*
- * logger_open - the log's open() file operation
- *
- * Note how near a no-op this is in the write-only case. Keep it that way!
- */
-static int logger_open(struct inode *inode, struct file *file)
-{
- struct logger_log *log;
- int ret;
-
- ret = nonseekable_open(inode, file);
- if (ret)
- return ret;
-
- log = get_log_from_minor(MINOR(inode->i_rdev));
- if (!log)
- return -ENODEV;
-
- if (file->f_mode & FMODE_READ) {
- struct logger_reader *reader;
-
- reader = kmalloc(sizeof(struct logger_reader), GFP_KERNEL);
- if (!reader)
- return -ENOMEM;
-
- reader->log = log;
- reader->r_ver = 1;
- reader->r_all = in_egroup_p(inode->i_gid) ||
- capable(CAP_SYSLOG);
-
- INIT_LIST_HEAD(&reader->list);
-
- mutex_lock(&log->mutex);
- reader->r_off = log->head;
- list_add_tail(&reader->list, &log->readers);
- mutex_unlock(&log->mutex);
-
- file->private_data = reader;
- } else
- file->private_data = log;
-
- return 0;
-}
-
-/*
- * logger_release - the log's release file operation
- *
- * Note this is a total no-op in the write-only case. Keep it that way!
- */
-static int logger_release(struct inode *ignored, struct file *file)
-{
- if (file->f_mode & FMODE_READ) {
- struct logger_reader *reader = file->private_data;
- struct logger_log *log = reader->log;
-
- mutex_lock(&log->mutex);
- list_del(&reader->list);
- mutex_unlock(&log->mutex);
-
- kfree(reader);
- }
-
- return 0;
-}
-
-/*
- * logger_poll - the log's poll file operation, for poll/select/epoll
- *
- * Note we always return POLLOUT, because you can always write() to the log.
- * Note also that, strictly speaking, a return value of POLLIN does not
- * guarantee that the log is readable without blocking, as there is a small
- * chance that the writer can lap the reader in the interim between poll()
- * returning and the read() request.
- */
-static unsigned int logger_poll(struct file *file, poll_table *wait)
-{
- struct logger_reader *reader;
- struct logger_log *log;
- unsigned int ret = POLLOUT | POLLWRNORM;
-
- if (!(file->f_mode & FMODE_READ))
- return ret;
-
- reader = file->private_data;
- log = reader->log;
-
- poll_wait(file, &log->wq, wait);
-
- mutex_lock(&log->mutex);
- if (!reader->r_all)
- reader->r_off = get_next_entry_by_uid(log,
- reader->r_off, current_euid());
-
- if (log->w_off != reader->r_off)
- ret |= POLLIN | POLLRDNORM;
- mutex_unlock(&log->mutex);
-
- return ret;
-}
-
-static long logger_set_version(struct logger_reader *reader, void __user *arg)
-{
- int version;
- if (copy_from_user(&version, arg, sizeof(int)))
- return -EFAULT;
-
- if ((version < 1) || (version > 2))
- return -EINVAL;
-
- reader->r_ver = version;
- return 0;
-}
-
-static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- struct logger_log *log = file_get_log(file);
- struct logger_reader *reader;
- long ret = -EINVAL;
- void __user *argp = (void __user *) arg;
-
- mutex_lock(&log->mutex);
-
- switch (cmd) {
- case LOGGER_GET_LOG_BUF_SIZE:
- ret = log->size;
- break;
- case LOGGER_GET_LOG_LEN:
- if (!(file->f_mode & FMODE_READ)) {
- ret = -EBADF;
- break;
- }
- reader = file->private_data;
- if (log->w_off >= reader->r_off)
- ret = log->w_off - reader->r_off;
- else
- ret = (log->size - reader->r_off) + log->w_off;
- break;
- case LOGGER_GET_NEXT_ENTRY_LEN:
- if (!(file->f_mode & FMODE_READ)) {
- ret = -EBADF;
- break;
- }
- reader = file->private_data;
-
- if (!reader->r_all)
- reader->r_off = get_next_entry_by_uid(log,
- reader->r_off, current_euid());
-
- if (log->w_off != reader->r_off)
- ret = get_user_hdr_len(reader->r_ver) +
- get_entry_msg_len(log, reader->r_off);
- else
- ret = 0;
- break;
- case LOGGER_FLUSH_LOG:
- if (!(file->f_mode & FMODE_WRITE)) {
- ret = -EBADF;
- break;
- }
- if (!(in_egroup_p(file->f_dentry->d_inode->i_gid) ||
- capable(CAP_SYSLOG))) {
- ret = -EPERM;
- break;
- }
- list_for_each_entry(reader, &log->readers, list)
- reader->r_off = log->w_off;
- log->head = log->w_off;
- ret = 0;
- break;
- case LOGGER_GET_VERSION:
- if (!(file->f_mode & FMODE_READ)) {
- ret = -EBADF;
- break;
- }
- reader = file->private_data;
- ret = reader->r_ver;
- break;
- case LOGGER_SET_VERSION:
- if (!(file->f_mode & FMODE_READ)) {
- ret = -EBADF;
- break;
- }
- reader = file->private_data;
- ret = logger_set_version(reader, argp);
- break;
- }
-
- mutex_unlock(&log->mutex);
-
- return ret;
-}
-
-static const struct file_operations logger_fops = {
- .owner = THIS_MODULE,
- .read = logger_read,
- .aio_write = logger_aio_write,
- .poll = logger_poll,
- .unlocked_ioctl = logger_ioctl,
- .compat_ioctl = logger_ioctl,
- .open = logger_open,
- .release = logger_release,
-};
-
-/*
- * Log size must must be a power of two, and greater than
- * (LOGGER_ENTRY_MAX_PAYLOAD + sizeof(struct logger_entry)).
- */
-static int __init create_log(char *log_name, int size)
-{
- int ret = 0;
- struct logger_log *log;
- unsigned char *buffer;
-
- buffer = vmalloc(size);
- if (buffer == NULL)
- return -ENOMEM;
-
- log = kzalloc(sizeof(struct logger_log), GFP_KERNEL);
- if (log == NULL) {
- ret = -ENOMEM;
- goto out_free_buffer;
- }
- log->buffer = buffer;
-
- log->misc.minor = MISC_DYNAMIC_MINOR;
- log->misc.name = kstrdup(log_name, GFP_KERNEL);
- if (log->misc.name == NULL) {
- ret = -ENOMEM;
- goto out_free_log;
- }
-
- log->misc.fops = &logger_fops;
- log->misc.parent = NULL;
-
- init_waitqueue_head(&log->wq);
- INIT_LIST_HEAD(&log->readers);
- mutex_init(&log->mutex);
- log->w_off = 0;
- log->head = 0;
- log->size = size;
-
- INIT_LIST_HEAD(&log->logs);
- list_add_tail(&log->logs, &log_list);
-
- /* finally, initialize the misc device for this log */
- ret = misc_register(&log->misc);
- if (unlikely(ret)) {
- pr_err("failed to register misc device for log '%s'!\n",
- log->misc.name);
- goto out_free_log;
- }
-
- pr_info("created %luK log '%s'\n",
- (unsigned long) log->size >> 10, log->misc.name);
-
- return 0;
-
-out_free_log:
- kfree(log);
-
-out_free_buffer:
- vfree(buffer);
- return ret;
-}
-
-static int __init logger_init(void)
-{
- int ret;
-
- ret = create_log(LOGGER_LOG_MAIN, 256*1024);
- if (unlikely(ret))
- goto out;
-
- ret = create_log(LOGGER_LOG_EVENTS, 256*1024);
- if (unlikely(ret))
- goto out;
-
- ret = create_log(LOGGER_LOG_RADIO, 256*1024);
- if (unlikely(ret))
- goto out;
-
- ret = create_log(LOGGER_LOG_SYSTEM, 256*1024);
- if (unlikely(ret))
- goto out;
-
-out:
- return ret;
-}
-
-static void __exit logger_exit(void)
-{
- struct logger_log *current_log, *next_log;
-
- list_for_each_entry_safe(current_log, next_log, &log_list, logs) {
- /* we have to delete all the entry inside log_list */
- misc_deregister(¤t_log->misc);
- vfree(current_log->buffer);
- kfree(current_log->misc.name);
- list_del(¤t_log->logs);
- kfree(current_log);
- }
-}
-
-
-device_initcall(logger_init);
-module_exit(logger_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Love, <rlove@google.com>");
-MODULE_DESCRIPTION("Android Logger");
diff --git a/drivers/staging/android/logger.h b/drivers/staging/android/logger.h
deleted file mode 100644
index 70af7d8..0000000
--- a/drivers/staging/android/logger.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* include/linux/logger.h
- *
- * Copyright (C) 2007-2008 Google, Inc.
- * Author: Robert Love <rlove@android.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _LINUX_LOGGER_H
-#define _LINUX_LOGGER_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-/**
- * struct user_logger_entry_compat - defines a single entry that is given to a logger
- * @len: The length of the payload
- * @__pad: Two bytes of padding that appear to be required
- * @pid: The generating process' process ID
- * @tid: The generating process' thread ID
- * @sec: The number of seconds that have elapsed since the Epoch
- * @nsec: The number of nanoseconds that have elapsed since @sec
- * @msg: The message that is to be logged
- *
- * The userspace structure for version 1 of the logger_entry ABI.
- * This structure is returned to userspace unless the caller requests
- * an upgrade to a newer ABI version.
- */
-struct user_logger_entry_compat {
- __u16 len;
- __u16 __pad;
- __s32 pid;
- __s32 tid;
- __s32 sec;
- __s32 nsec;
- char msg[0];
-};
-
-/**
- * struct logger_entry - defines a single entry that is given to a logger
- * @len: The length of the payload
- * @hdr_size: sizeof(struct logger_entry_v2)
- * @pid: The generating process' process ID
- * @tid: The generating process' thread ID
- * @sec: The number of seconds that have elapsed since the Epoch
- * @nsec: The number of nanoseconds that have elapsed since @sec
- * @euid: Effective UID of logger
- * @msg: The message that is to be logged
- *
- * The structure for version 2 of the logger_entry ABI.
- * This structure is returned to userspace if ioctl(LOGGER_SET_VERSION)
- * is called with version >= 2
- */
-struct logger_entry {
- __u16 len;
- __u16 hdr_size;
- __s32 pid;
- __s32 tid;
- __s32 sec;
- __s32 nsec;
- kuid_t euid;
- char msg[0];
-};
-
-#define LOGGER_LOG_RADIO "log_radio" /* radio-related messages */
-#define LOGGER_LOG_EVENTS "log_events" /* system/hardware events */
-#define LOGGER_LOG_SYSTEM "log_system" /* system/framework messages */
-#define LOGGER_LOG_MAIN "log_main" /* everything else */
-
-#define LOGGER_ENTRY_MAX_PAYLOAD 4076
-
-#define __LOGGERIO 0xAE
-
-#define LOGGER_GET_LOG_BUF_SIZE _IO(__LOGGERIO, 1) /* size of log */
-#define LOGGER_GET_LOG_LEN _IO(__LOGGERIO, 2) /* used log len */
-#define LOGGER_GET_NEXT_ENTRY_LEN _IO(__LOGGERIO, 3) /* next entry len */
-#define LOGGER_FLUSH_LOG _IO(__LOGGERIO, 4) /* flush log */
-#define LOGGER_GET_VERSION _IO(__LOGGERIO, 5) /* abi version */
-#define LOGGER_SET_VERSION _IO(__LOGGERIO, 6) /* abi version */
-
-#endif /* _LINUX_LOGGER_H */
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index fe74494..3383b90 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -39,9 +39,11 @@
#include <linux/sched.h>
#include <linux/swap.h>
#include <linux/rcupdate.h>
-#include <linux/profile.h>
#include <linux/notifier.h>
+#define CREATE_TRACE_POINTS
+#include "trace/lowmemorykiller.h"
+
static uint32_t lowmem_debug_level = 1;
static short lowmem_adj[6] = {
0,
@@ -74,20 +76,22 @@
int tasksize;
int i;
short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
+ int minfree = 0;
int selected_tasksize = 0;
short selected_oom_score_adj;
int array_size = ARRAY_SIZE(lowmem_adj);
int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
int other_file = global_page_state(NR_FILE_PAGES) -
- global_page_state(NR_SHMEM);
+ global_page_state(NR_SHMEM) -
+ total_swapcache_pages();
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
- if (other_free < lowmem_minfree[i] &&
- other_file < lowmem_minfree[i]) {
+ minfree = lowmem_minfree[i];
+ if (other_free < minfree && other_file < minfree) {
min_score_adj = lowmem_adj[i];
break;
}
@@ -144,16 +148,28 @@
selected = p;
selected_tasksize = tasksize;
selected_oom_score_adj = oom_score_adj;
- lowmem_print(2, "select %d (%s), adj %hd, size %d, to kill\n",
- p->pid, p->comm, oom_score_adj, tasksize);
+ lowmem_print(2, "select '%s' (%d), adj %hd, size %d, to kill\n",
+ p->comm, p->pid, oom_score_adj, tasksize);
}
if (selected) {
- lowmem_print(1, "send sigkill to %d (%s), adj %hd, size %d\n",
- selected->pid, selected->comm,
- selected_oom_score_adj, selected_tasksize);
+ long cache_size = other_file * (long)(PAGE_SIZE / 1024);
+ long cache_limit = minfree * (long)(PAGE_SIZE / 1024);
+ long free = other_free * (long)(PAGE_SIZE / 1024);
+ trace_lowmemory_kill(selected, cache_size, cache_limit, free);
+ lowmem_print(1, "Killing '%s' (%d), adj %hd,\n" \
+ " to free %ldkB on behalf of '%s' (%d) because\n" \
+ " cache %ldkB is below limit %ldkB for oom_score_adj %hd\n" \
+ " Free memory is %ldkB above reserved\n",
+ selected->comm, selected->pid,
+ selected_oom_score_adj,
+ selected_tasksize * (long)(PAGE_SIZE / 1024),
+ current->comm, current->pid,
+ cache_size, cache_limit,
+ min_score_adj,
+ free);
lowmem_deathpending_timeout = jiffies + HZ;
- send_sig(SIGKILL, selected, 0);
set_tsk_thread_flag(selected, TIF_MEMDIE);
+ send_sig(SIGKILL, selected, 0);
rem -= selected_tasksize;
}
lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
@@ -178,9 +194,94 @@
unregister_shrinker(&lowmem_shrinker);
}
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+static short lowmem_oom_adj_to_oom_score_adj(short oom_adj)
+{
+ if (oom_adj == OOM_ADJUST_MAX)
+ return OOM_SCORE_ADJ_MAX;
+ else
+ return (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+}
+
+static void lowmem_autodetect_oom_adj_values(void)
+{
+ int i;
+ short oom_adj;
+ short oom_score_adj;
+ int array_size = ARRAY_SIZE(lowmem_adj);
+
+ if (lowmem_adj_size < array_size)
+ array_size = lowmem_adj_size;
+
+ if (array_size <= 0)
+ return;
+
+ oom_adj = lowmem_adj[array_size - 1];
+ if (oom_adj > OOM_ADJUST_MAX)
+ return;
+
+ oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+ if (oom_score_adj <= OOM_ADJUST_MAX)
+ return;
+
+ lowmem_print(1, "lowmem_shrink: convert oom_adj to oom_score_adj:\n");
+ for (i = 0; i < array_size; i++) {
+ oom_adj = lowmem_adj[i];
+ oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+ lowmem_adj[i] = oom_score_adj;
+ lowmem_print(1, "oom_adj %d => oom_score_adj %d\n",
+ oom_adj, oom_score_adj);
+ }
+}
+
+static int lowmem_adj_array_set(const char *val, const struct kernel_param *kp)
+{
+ int ret;
+
+ ret = param_array_ops.set(val, kp);
+
+ /* HACK: Autodetect oom_adj values in lowmem_adj array */
+ lowmem_autodetect_oom_adj_values();
+
+ return ret;
+}
+
+static int lowmem_adj_array_get(char *buffer, const struct kernel_param *kp)
+{
+ return param_array_ops.get(buffer, kp);
+}
+
+static void lowmem_adj_array_free(void *arg)
+{
+ param_array_ops.free(arg);
+}
+
+static struct kernel_param_ops lowmem_adj_array_ops = {
+ .set = lowmem_adj_array_set,
+ .get = lowmem_adj_array_get,
+ .free = lowmem_adj_array_free,
+};
+
+static const struct kparam_array __param_arr_adj = {
+ .max = ARRAY_SIZE(lowmem_adj),
+ .num = &lowmem_adj_size,
+ .ops = ¶m_ops_short,
+ .elemsize = sizeof(lowmem_adj[0]),
+ .elem = lowmem_adj,
+};
+#endif
+
module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+__module_param_call(MODULE_PARAM_PREFIX, adj,
+ &lowmem_adj_array_ops,
+ .arr = &__param_arr_adj,
+ S_IRUGO | S_IWUSR, -1);
+__MODULE_PARM_TYPE(adj, "array of short");
+#else
module_param_array_named(adj, lowmem_adj, short, &lowmem_adj_size,
S_IRUGO | S_IWUSR);
+#endif
module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
S_IRUGO | S_IWUSR);
module_param_named(debug_level, lowmem_debug_level, uint, S_IRUGO | S_IWUSR);
diff --git a/drivers/staging/android/sw_sync.c b/drivers/staging/android/sw_sync.c
index 4928f93b..820af5c 100644
--- a/drivers/staging/android/sw_sync.c
+++ b/drivers/staging/android/sw_sync.c
@@ -97,6 +97,7 @@
char *str, int size)
{
struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt;
+
snprintf(str, size, "%d", pt->value);
}
@@ -156,6 +157,7 @@
static int sw_sync_release(struct inode *inode, struct file *file)
{
struct sw_sync_timeline *obj = file->private_data;
+
sync_timeline_destroy(&obj->obj);
return 0;
}
diff --git a/drivers/staging/android/sw_sync.h b/drivers/staging/android/sw_sync.h
index 585040b..1a50669 100644
--- a/drivers/staging/android/sw_sync.h
+++ b/drivers/staging/android/sw_sync.h
@@ -18,10 +18,9 @@
#define _LINUX_SW_SYNC_H
#include <linux/types.h>
-
-#ifdef __KERNEL__
-
+#include <linux/kconfig.h>
#include "sync.h"
+#include "uapi/sw_sync.h"
struct sw_sync_timeline {
struct sync_timeline obj;
@@ -35,24 +34,26 @@
u32 value;
};
+#if IS_ENABLED(CONFIG_SW_SYNC)
struct sw_sync_timeline *sw_sync_timeline_create(const char *name);
void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc);
struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, u32 value);
+#else
+static inline struct sw_sync_timeline *sw_sync_timeline_create(const char *name)
+{
+ return NULL;
+}
-#endif /* __KERNEL __ */
+static inline void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc)
+{
+}
-struct sw_sync_create_fence_data {
- __u32 value;
- char name[32];
- __s32 fence; /* fd of new fence */
-};
-
-#define SW_SYNC_IOC_MAGIC 'W'
-
-#define SW_SYNC_IOC_CREATE_FENCE _IOWR(SW_SYNC_IOC_MAGIC, 0,\
- struct sw_sync_create_fence_data)
-#define SW_SYNC_IOC_INC _IOW(SW_SYNC_IOC_MAGIC, 1, __u32)
-
+static inline struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj,
+ u32 value)
+{
+ return NULL;
+}
+#endif /* IS_ENABLED(CONFIG_SW_SYNC) */
#endif /* _LINUX_SW_SYNC_H */
diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c
index 3893a35..61e6249 100644
--- a/drivers/staging/android/sync.c
+++ b/drivers/staging/android/sync.c
@@ -79,27 +79,27 @@
container_of(kref, struct sync_timeline, kref);
unsigned long flags;
- if (obj->ops->release_obj)
- obj->ops->release_obj(obj);
-
spin_lock_irqsave(&sync_timeline_list_lock, flags);
list_del(&obj->sync_timeline_list);
spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
+ if (obj->ops->release_obj)
+ obj->ops->release_obj(obj);
+
kfree(obj);
}
void sync_timeline_destroy(struct sync_timeline *obj)
{
obj->destroyed = true;
+ smp_wmb();
/*
- * If this is not the last reference, signal any children
- * that their parent is going away.
+ * signal any children that their parent is going away.
*/
+ sync_timeline_signal(obj);
- if (!kref_put(&obj->kref, sync_timeline_free))
- sync_timeline_signal(obj);
+ kref_put(&obj->kref, sync_timeline_free);
}
EXPORT_SYMBOL(sync_timeline_destroy);
@@ -384,6 +384,7 @@
list_for_each_safe(pos, n, &fence->pt_list_head) {
struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list);
+
sync_timeline_remove_pt(pt);
}
}
@@ -394,6 +395,7 @@
list_for_each_safe(pos, n, &fence->pt_list_head) {
struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list);
+
sync_pt_free(pt);
}
}
@@ -827,6 +829,7 @@
unsigned long arg)
{
struct sync_fence *fence = file->private_data;
+
switch (cmd) {
case SYNC_IOC_WAIT:
return sync_fence_ioctl_wait(fence, arg);
@@ -856,18 +859,21 @@
static void sync_print_pt(struct seq_file *s, struct sync_pt *pt, bool fence)
{
int status = pt->status;
+
seq_printf(s, " %s%spt %s",
fence ? pt->parent->name : "",
fence ? "_" : "",
sync_status_str(status));
if (pt->status) {
struct timeval tv = ktime_to_timeval(pt->timestamp);
+
seq_printf(s, "@%ld.%06ld", tv.tv_sec, tv.tv_usec);
}
if (pt->parent->ops->timeline_value_str &&
pt->parent->ops->pt_value_str) {
char value[64];
+
pt->parent->ops->pt_value_str(pt, value, sizeof(value));
seq_printf(s, ": %s", value);
if (fence) {
@@ -892,6 +898,7 @@
if (obj->ops->timeline_value_str) {
char value[64];
+
obj->ops->timeline_value_str(obj, value, sizeof(value));
seq_printf(s, ": %s", value);
} else if (obj->ops->print_obj) {
@@ -1001,6 +1008,7 @@
for (i = 0; i < s.count; i += DUMP_CHUNK) {
if ((s.count - i) > DUMP_CHUNK) {
char c = s.buf[i + DUMP_CHUNK];
+
s.buf[i + DUMP_CHUNK] = 0;
pr_cont("%s", s.buf + i);
s.buf[i + DUMP_CHUNK] = c;
diff --git a/drivers/staging/android/sync.h b/drivers/staging/android/sync.h
index 38ea986..75da9e8 100644
--- a/drivers/staging/android/sync.h
+++ b/drivers/staging/android/sync.h
@@ -14,14 +14,14 @@
#define _LINUX_SYNC_H
#include <linux/types.h>
-#ifdef __KERNEL__
-
#include <linux/kref.h>
#include <linux/ktime.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
+#include "uapi/sync.h"
+
struct sync_timeline;
struct sync_pt;
struct sync_fence;
@@ -341,86 +341,4 @@
*/
int sync_fence_wait(struct sync_fence *fence, long timeout);
-#endif /* __KERNEL__ */
-
-/**
- * struct sync_merge_data - data passed to merge ioctl
- * @fd2: file descriptor of second fence
- * @name: name of new fence
- * @fence: returns the fd of the new fence to userspace
- */
-struct sync_merge_data {
- __s32 fd2; /* fd of second fence */
- char name[32]; /* name of new fence */
- __s32 fence; /* fd on newly created fence */
-};
-
-/**
- * struct sync_pt_info - detailed sync_pt information
- * @len: length of sync_pt_info including any driver_data
- * @obj_name: name of parent sync_timeline
- * @driver_name: name of driver implmenting the parent
- * @status: status of the sync_pt 0:active 1:signaled <0:error
- * @timestamp_ns: timestamp of status change in nanoseconds
- * @driver_data: any driver dependant data
- */
-struct sync_pt_info {
- __u32 len;
- char obj_name[32];
- char driver_name[32];
- __s32 status;
- __u64 timestamp_ns;
-
- __u8 driver_data[0];
-};
-
-/**
- * struct sync_fence_info_data - data returned from fence info ioctl
- * @len: ioctl caller writes the size of the buffer its passing in.
- * ioctl returns length of sync_fence_data reutnred to userspace
- * including pt_info.
- * @name: name of fence
- * @status: status of fence. 1: signaled 0:active <0:error
- * @pt_info: a sync_pt_info struct for every sync_pt in the fence
- */
-struct sync_fence_info_data {
- __u32 len;
- char name[32];
- __s32 status;
-
- __u8 pt_info[0];
-};
-
-#define SYNC_IOC_MAGIC '>'
-
-/**
- * DOC: SYNC_IOC_WAIT - wait for a fence to signal
- *
- * pass timeout in milliseconds. Waits indefinitely timeout < 0.
- */
-#define SYNC_IOC_WAIT _IOW(SYNC_IOC_MAGIC, 0, __s32)
-
-/**
- * DOC: SYNC_IOC_MERGE - merge two fences
- *
- * Takes a struct sync_merge_data. Creates a new fence containing copies of
- * the sync_pts in both the calling fd and sync_merge_data.fd2. Returns the
- * new fence's fd in sync_merge_data.fence
- */
-#define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 1, struct sync_merge_data)
-
-/**
- * DOC: SYNC_IOC_FENCE_INFO - get detailed information on a fence
- *
- * Takes a struct sync_fence_info_data with extra space allocated for pt_info.
- * Caller should write the size of the buffer into len. On return, len is
- * updated to reflect the total size of the sync_fence_info_data including
- * pt_info.
- *
- * pt_info is a buffer containing sync_pt_infos for every sync_pt in the fence.
- * To itterate over the sync_pt_infos, use the sync_pt_info.len field.
- */
-#define SYNC_IOC_FENCE_INFO _IOWR(SYNC_IOC_MAGIC, 2,\
- struct sync_fence_info_data)
-
#endif /* _LINUX_SYNC_H */
diff --git a/drivers/staging/android/timed_gpio.c b/drivers/staging/android/timed_gpio.c
index e814514..ae9966d 100644
--- a/drivers/staging/android/timed_gpio.c
+++ b/drivers/staging/android/timed_gpio.c
@@ -51,6 +51,7 @@
if (hrtimer_active(&data->timer)) {
ktime_t r = hrtimer_get_remaining(&data->timer);
struct timeval t = ktime_to_timeval(r);
+
return t.tv_sec * 1000 + t.tv_usec / 1000;
} else
return 0;
diff --git a/drivers/staging/android/trace/lowmemorykiller.h b/drivers/staging/android/trace/lowmemorykiller.h
new file mode 100644
index 0000000..f43d3fa
--- /dev/null
+++ b/drivers/staging/android/trace/lowmemorykiller.h
@@ -0,0 +1,41 @@
+#undef TRACE_SYSTEM
+#define TRACE_INCLUDE_PATH ../../drivers/staging/android/trace
+#define TRACE_SYSTEM lowmemorykiller
+
+#if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOWMEMORYKILLER_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(lowmemory_kill,
+ TP_PROTO(struct task_struct *killed_task, long cache_size, \
+ long cache_limit, long free),
+
+ TP_ARGS(killed_task, cache_size, cache_limit, free),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(long, pagecache_size)
+ __field(long, pagecache_limit)
+ __field(long, free)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, killed_task->comm, TASK_COMM_LEN);
+ __entry->pid = killed_task->pid;
+ __entry->pagecache_size = cache_size;
+ __entry->pagecache_limit = cache_limit;
+ __entry->free = free;
+ ),
+
+ TP_printk("%s (%d), page cache %ldkB (limit %ldkB), free %ldKb",
+ __entry->comm, __entry->pid, __entry->pagecache_size,
+ __entry->pagecache_limit, __entry->free)
+);
+
+
+#endif /* if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ) */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/drivers/staging/android/uapi/ashmem.h b/drivers/staging/android/uapi/ashmem.h
new file mode 100644
index 0000000..13df42d
--- /dev/null
+++ b/drivers/staging/android/uapi/ashmem.h
@@ -0,0 +1,48 @@
+/*
+ * drivers/staging/android/uapi/ashmem.h
+ *
+ * Copyright 2008 Google Inc.
+ * Author: Robert Love
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#ifndef _UAPI_LINUX_ASHMEM_H
+#define _UAPI_LINUX_ASHMEM_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define ASHMEM_NAME_LEN 256
+
+#define ASHMEM_NAME_DEF "dev/ashmem"
+
+/* Return values from ASHMEM_PIN: Was the mapping purged while unpinned? */
+#define ASHMEM_NOT_PURGED 0
+#define ASHMEM_WAS_PURGED 1
+
+/* Return values from ASHMEM_GET_PIN_STATUS: Is the mapping pinned? */
+#define ASHMEM_IS_UNPINNED 0
+#define ASHMEM_IS_PINNED 1
+
+struct ashmem_pin {
+ __u32 offset; /* offset into region, in bytes, page-aligned */
+ __u32 len; /* length forward from offset, in bytes, page-aligned */
+};
+
+#define __ASHMEMIOC 0x77
+
+#define ASHMEM_SET_NAME _IOW(__ASHMEMIOC, 1, char[ASHMEM_NAME_LEN])
+#define ASHMEM_GET_NAME _IOR(__ASHMEMIOC, 2, char[ASHMEM_NAME_LEN])
+#define ASHMEM_SET_SIZE _IOW(__ASHMEMIOC, 3, size_t)
+#define ASHMEM_GET_SIZE _IO(__ASHMEMIOC, 4)
+#define ASHMEM_SET_PROT_MASK _IOW(__ASHMEMIOC, 5, unsigned long)
+#define ASHMEM_GET_PROT_MASK _IO(__ASHMEMIOC, 6)
+#define ASHMEM_PIN _IOW(__ASHMEMIOC, 7, struct ashmem_pin)
+#define ASHMEM_UNPIN _IOW(__ASHMEMIOC, 8, struct ashmem_pin)
+#define ASHMEM_GET_PIN_STATUS _IO(__ASHMEMIOC, 9)
+#define ASHMEM_PURGE_ALL_CACHES _IO(__ASHMEMIOC, 10)
+
+#endif /* _UAPI_LINUX_ASHMEM_H */
diff --git a/drivers/staging/android/uapi/ion.h b/drivers/staging/android/uapi/ion.h
new file mode 100644
index 0000000..f09e7c1
--- /dev/null
+++ b/drivers/staging/android/uapi/ion.h
@@ -0,0 +1,196 @@
+/*
+ * drivers/staging/android/uapi/ion.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_ION_H
+#define _UAPI_LINUX_ION_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+typedef int ion_user_handle_t;
+
+/**
+ * enum ion_heap_types - list of all possible types of heaps
+ * @ION_HEAP_TYPE_SYSTEM: memory allocated via vmalloc
+ * @ION_HEAP_TYPE_SYSTEM_CONTIG: memory allocated via kmalloc
+ * @ION_HEAP_TYPE_CARVEOUT: memory allocated from a prereserved
+ * carveout heap, allocations are physically
+ * contiguous
+ * @ION_HEAP_TYPE_DMA: memory allocated via DMA API
+ * @ION_NUM_HEAPS: helper for iterating over heaps, a bit mask
+ * is used to identify the heaps, so only 32
+ * total heap types are supported
+ */
+enum ion_heap_type {
+ ION_HEAP_TYPE_SYSTEM,
+ ION_HEAP_TYPE_SYSTEM_CONTIG,
+ ION_HEAP_TYPE_CARVEOUT,
+ ION_HEAP_TYPE_CHUNK,
+ ION_HEAP_TYPE_DMA,
+ ION_HEAP_TYPE_CUSTOM, /* must be last so device specific heaps always
+ are at the end of this enum */
+ ION_NUM_HEAPS = 16,
+};
+
+#define ION_HEAP_SYSTEM_MASK (1 << ION_HEAP_TYPE_SYSTEM)
+#define ION_HEAP_SYSTEM_CONTIG_MASK (1 << ION_HEAP_TYPE_SYSTEM_CONTIG)
+#define ION_HEAP_CARVEOUT_MASK (1 << ION_HEAP_TYPE_CARVEOUT)
+#define ION_HEAP_TYPE_DMA_MASK (1 << ION_HEAP_TYPE_DMA)
+
+#define ION_NUM_HEAP_IDS sizeof(unsigned int) * 8
+
+/**
+ * allocation flags - the lower 16 bits are used by core ion, the upper 16
+ * bits are reserved for use by the heaps themselves.
+ */
+#define ION_FLAG_CACHED 1 /* mappings of this buffer should be
+ cached, ion will do cache
+ maintenance when the buffer is
+ mapped for dma */
+#define ION_FLAG_CACHED_NEEDS_SYNC 2 /* mappings of this buffer will created
+ at mmap time, if this is set
+ caches must be managed manually */
+
+/**
+ * DOC: Ion Userspace API
+ *
+ * create a client by opening /dev/ion
+ * most operations handled via following ioctls
+ *
+ */
+
+/**
+ * struct ion_allocation_data - metadata passed from userspace for allocations
+ * @len: size of the allocation
+ * @align: required alignment of the allocation
+ * @heap_id_mask: mask of heap ids to allocate from
+ * @flags: flags passed to heap
+ * @handle: pointer that will be populated with a cookie to use to
+ * refer to this allocation
+ *
+ * Provided by userspace as an argument to the ioctl
+ */
+struct ion_allocation_data {
+ size_t len;
+ size_t align;
+ unsigned int heap_id_mask;
+ unsigned int flags;
+ ion_user_handle_t handle;
+};
+
+/**
+ * struct ion_fd_data - metadata passed to/from userspace for a handle/fd pair
+ * @handle: a handle
+ * @fd: a file descriptor representing that handle
+ *
+ * For ION_IOC_SHARE or ION_IOC_MAP userspace populates the handle field with
+ * the handle returned from ion alloc, and the kernel returns the file
+ * descriptor to share or map in the fd field. For ION_IOC_IMPORT, userspace
+ * provides the file descriptor and the kernel returns the handle.
+ */
+struct ion_fd_data {
+ ion_user_handle_t handle;
+ int fd;
+};
+
+/**
+ * struct ion_handle_data - a handle passed to/from the kernel
+ * @handle: a handle
+ */
+struct ion_handle_data {
+ ion_user_handle_t handle;
+};
+
+/**
+ * struct ion_custom_data - metadata passed to/from userspace for a custom ioctl
+ * @cmd: the custom ioctl function to call
+ * @arg: additional data to pass to the custom ioctl, typically a user
+ * pointer to a predefined structure
+ *
+ * This works just like the regular cmd and arg fields of an ioctl.
+ */
+struct ion_custom_data {
+ unsigned int cmd;
+ unsigned long arg;
+};
+
+#define ION_IOC_MAGIC 'I'
+
+/**
+ * DOC: ION_IOC_ALLOC - allocate memory
+ *
+ * Takes an ion_allocation_data struct and returns it with the handle field
+ * populated with the opaque handle for the allocation.
+ */
+#define ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \
+ struct ion_allocation_data)
+
+/**
+ * DOC: ION_IOC_FREE - free memory
+ *
+ * Takes an ion_handle_data struct and frees the handle.
+ */
+#define ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, struct ion_handle_data)
+
+/**
+ * DOC: ION_IOC_MAP - get a file descriptor to mmap
+ *
+ * Takes an ion_fd_data struct with the handle field populated with a valid
+ * opaque handle. Returns the struct with the fd field set to a file
+ * descriptor open in the current address space. This file descriptor
+ * can then be used as an argument to mmap.
+ */
+#define ION_IOC_MAP _IOWR(ION_IOC_MAGIC, 2, struct ion_fd_data)
+
+/**
+ * DOC: ION_IOC_SHARE - creates a file descriptor to use to share an allocation
+ *
+ * Takes an ion_fd_data struct with the handle field populated with a valid
+ * opaque handle. Returns the struct with the fd field set to a file
+ * descriptor open in the current address space. This file descriptor
+ * can then be passed to another process. The corresponding opaque handle can
+ * be retrieved via ION_IOC_IMPORT.
+ */
+#define ION_IOC_SHARE _IOWR(ION_IOC_MAGIC, 4, struct ion_fd_data)
+
+/**
+ * DOC: ION_IOC_IMPORT - imports a shared file descriptor
+ *
+ * Takes an ion_fd_data struct with the fd field populated with a valid file
+ * descriptor obtained from ION_IOC_SHARE and returns the struct with the handle
+ * filed set to the corresponding opaque handle.
+ */
+#define ION_IOC_IMPORT _IOWR(ION_IOC_MAGIC, 5, struct ion_fd_data)
+
+/**
+ * DOC: ION_IOC_SYNC - syncs a shared file descriptors to memory
+ *
+ * Deprecated in favor of using the dma_buf api's correctly (syncing
+ * will happend automatically when the buffer is mapped to a device).
+ * If necessary should be used after touching a cached buffer from the cpu,
+ * this will make the buffer in memory coherent.
+ */
+#define ION_IOC_SYNC _IOWR(ION_IOC_MAGIC, 7, struct ion_fd_data)
+
+/**
+ * DOC: ION_IOC_CUSTOM - call architecture specific ion ioctl
+ *
+ * Takes the argument of the architecture specific ioctl to call and
+ * passes appropriate userdata for that ioctl
+ */
+#define ION_IOC_CUSTOM _IOWR(ION_IOC_MAGIC, 6, struct ion_custom_data)
+
+#endif /* _UAPI_LINUX_ION_H */
diff --git a/drivers/staging/android/uapi/ion_test.h b/drivers/staging/android/uapi/ion_test.h
new file mode 100644
index 0000000..ffef06f
--- /dev/null
+++ b/drivers/staging/android/uapi/ion_test.h
@@ -0,0 +1,70 @@
+/*
+ * drivers/staging/android/uapi/ion.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_ION_TEST_H
+#define _UAPI_LINUX_ION_TEST_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * struct ion_test_rw_data - metadata passed to the kernel to read handle
+ * @ptr: a pointer to an area at least as large as size
+ * @offset: offset into the ion buffer to start reading
+ * @size: size to read or write
+ * @write: 1 to write, 0 to read
+ */
+struct ion_test_rw_data {
+ __u64 ptr;
+ __u64 offset;
+ __u64 size;
+ int write;
+ int __padding;
+};
+
+#define ION_IOC_MAGIC 'I'
+
+/**
+ * DOC: ION_IOC_TEST_SET_DMA_BUF - attach a dma buf to the test driver
+ *
+ * Attaches a dma buf fd to the test driver. Passing a second fd or -1 will
+ * release the first fd.
+ */
+#define ION_IOC_TEST_SET_FD \
+ _IO(ION_IOC_MAGIC, 0xf0)
+
+/**
+ * DOC: ION_IOC_TEST_DMA_MAPPING - read or write memory from a handle as DMA
+ *
+ * Reads or writes the memory from a handle using an uncached mapping. Can be
+ * used by unit tests to emulate a DMA engine as close as possible. Only
+ * expected to be used for debugging and testing, may not always be available.
+ */
+#define ION_IOC_TEST_DMA_MAPPING \
+ _IOW(ION_IOC_MAGIC, 0xf1, struct ion_test_rw_data)
+
+/**
+ * DOC: ION_IOC_TEST_KERNEL_MAPPING - read or write memory from a handle
+ *
+ * Reads or writes the memory from a handle using a kernel mapping. Can be
+ * used by unit tests to test heap map_kernel functions. Only expected to be
+ * used for debugging and testing, may not always be available.
+ */
+#define ION_IOC_TEST_KERNEL_MAPPING \
+ _IOW(ION_IOC_MAGIC, 0xf2, struct ion_test_rw_data)
+
+
+#endif /* _UAPI_LINUX_ION_H */
diff --git a/drivers/staging/android/uapi/sw_sync.h b/drivers/staging/android/uapi/sw_sync.h
new file mode 100644
index 0000000..9b5d486
--- /dev/null
+++ b/drivers/staging/android/uapi/sw_sync.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_SW_SYNC_H
+#define _UAPI_LINUX_SW_SYNC_H
+
+#include <linux/types.h>
+
+struct sw_sync_create_fence_data {
+ __u32 value;
+ char name[32];
+ __s32 fence; /* fd of new fence */
+};
+
+#define SW_SYNC_IOC_MAGIC 'W'
+
+#define SW_SYNC_IOC_CREATE_FENCE _IOWR(SW_SYNC_IOC_MAGIC, 0,\
+ struct sw_sync_create_fence_data)
+#define SW_SYNC_IOC_INC _IOW(SW_SYNC_IOC_MAGIC, 1, __u32)
+
+#endif /* _UAPI_LINUX_SW_SYNC_H */
diff --git a/drivers/staging/android/uapi/sync.h b/drivers/staging/android/uapi/sync.h
new file mode 100644
index 0000000..57fdaad
--- /dev/null
+++ b/drivers/staging/android/uapi/sync.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_SYNC_H
+#define _UAPI_LINUX_SYNC_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * struct sync_merge_data - data passed to merge ioctl
+ * @fd2: file descriptor of second fence
+ * @name: name of new fence
+ * @fence: returns the fd of the new fence to userspace
+ */
+struct sync_merge_data {
+ __s32 fd2; /* fd of second fence */
+ char name[32]; /* name of new fence */
+ __s32 fence; /* fd on newly created fence */
+};
+
+/**
+ * struct sync_pt_info - detailed sync_pt information
+ * @len: length of sync_pt_info including any driver_data
+ * @obj_name: name of parent sync_timeline
+ * @driver_name: name of driver implmenting the parent
+ * @status: status of the sync_pt 0:active 1:signaled <0:error
+ * @timestamp_ns: timestamp of status change in nanoseconds
+ * @driver_data: any driver dependant data
+ */
+struct sync_pt_info {
+ __u32 len;
+ char obj_name[32];
+ char driver_name[32];
+ __s32 status;
+ __u64 timestamp_ns;
+
+ __u8 driver_data[0];
+};
+
+/**
+ * struct sync_fence_info_data - data returned from fence info ioctl
+ * @len: ioctl caller writes the size of the buffer its passing in.
+ * ioctl returns length of sync_fence_data reutnred to userspace
+ * including pt_info.
+ * @name: name of fence
+ * @status: status of fence. 1: signaled 0:active <0:error
+ * @pt_info: a sync_pt_info struct for every sync_pt in the fence
+ */
+struct sync_fence_info_data {
+ __u32 len;
+ char name[32];
+ __s32 status;
+
+ __u8 pt_info[0];
+};
+
+#define SYNC_IOC_MAGIC '>'
+
+/**
+ * DOC: SYNC_IOC_WAIT - wait for a fence to signal
+ *
+ * pass timeout in milliseconds. Waits indefinitely timeout < 0.
+ */
+#define SYNC_IOC_WAIT _IOW(SYNC_IOC_MAGIC, 0, __s32)
+
+/**
+ * DOC: SYNC_IOC_MERGE - merge two fences
+ *
+ * Takes a struct sync_merge_data. Creates a new fence containing copies of
+ * the sync_pts in both the calling fd and sync_merge_data.fd2. Returns the
+ * new fence's fd in sync_merge_data.fence
+ */
+#define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 1, struct sync_merge_data)
+
+/**
+ * DOC: SYNC_IOC_FENCE_INFO - get detailed information on a fence
+ *
+ * Takes a struct sync_fence_info_data with extra space allocated for pt_info.
+ * Caller should write the size of the buffer into len. On return, len is
+ * updated to reflect the total size of the sync_fence_info_data including
+ * pt_info.
+ *
+ * pt_info is a buffer containing sync_pt_infos for every sync_pt in the fence.
+ * To itterate over the sync_pt_infos, use the sync_pt_info.len field.
+ */
+#define SYNC_IOC_FENCE_INFO _IOWR(SYNC_IOC_MAGIC, 2,\
+ struct sync_fence_info_data)
+
+#endif /* _UAPI_LINUX_SYNC_H */
diff --git a/drivers/staging/zram/Makefile b/drivers/staging/zram/Makefile
deleted file mode 100644
index 7f4a301..0000000
--- a/drivers/staging/zram/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zram-y := zram_drv.o zram_sysfs.o
-
-obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/staging/zram/zram.txt b/drivers/staging/zram/zram.txt
deleted file mode 100644
index 765d790..0000000
--- a/drivers/staging/zram/zram.txt
+++ /dev/null
@@ -1,77 +0,0 @@
-zram: Compressed RAM based block devices
-----------------------------------------
-
-Project home: http://compcache.googlecode.com/
-
-* Introduction
-
-The zram module creates RAM based block devices named /dev/zram<id>
-(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
-in memory itself. These disks allow very fast I/O and compression provides
-good amounts of memory savings. Some of the usecases include /tmp storage,
-use as swap disks, various caches under /var and maybe many more :)
-
-Statistics for individual zram devices are exported through sysfs nodes at
-/sys/block/zram<id>/
-
-* Usage
-
-Following shows a typical sequence of steps for using zram.
-
-1) Load Module:
- modprobe zram num_devices=4
- This creates 4 devices: /dev/zram{0,1,2,3}
- (num_devices parameter is optional. Default: 1)
-
-2) Set Disksize
- Set disk size by writing the value to sysfs node 'disksize'.
- The value can be either in bytes or you can use mem suffixes.
- Examples:
- # Initialize /dev/zram0 with 50MB disksize
- echo $((50*1024*1024)) > /sys/block/zram0/disksize
-
- # Using mem suffixes
- echo 256K > /sys/block/zram0/disksize
- echo 512M > /sys/block/zram0/disksize
- echo 1G > /sys/block/zram0/disksize
-
-3) Activate:
- mkswap /dev/zram0
- swapon /dev/zram0
-
- mkfs.ext4 /dev/zram1
- mount /dev/zram1 /tmp
-
-4) Stats:
- Per-device statistics are exported as various nodes under
- /sys/block/zram<id>/
- disksize
- num_reads
- num_writes
- invalid_io
- notify_free
- discard
- zero_pages
- orig_data_size
- compr_data_size
- mem_used_total
-
-5) Deactivate:
- swapoff /dev/zram0
- umount /dev/zram1
-
-6) Reset:
- Write any positive value to 'reset' sysfs node
- echo 1 > /sys/block/zram0/reset
- echo 1 > /sys/block/zram1/reset
-
- This frees all the memory allocated for the given device and
- resets the disksize to zero. You must set the disksize again
- before reusing the device.
-
-Please report any problems at:
- - Mailing list: linux-mm-cc at laptop dot org
- - Issue tracker: http://code.google.com/p/compcache/issues/list
-
-Nitin Gupta
-ngupta@vflare.org
diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c
deleted file mode 100644
index a333d44..0000000
--- a/drivers/staging/zram/zram_drv.c
+++ /dev/null
@@ -1,760 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#define KMSG_COMPONENT "zram"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#ifdef CONFIG_ZRAM_DEBUG
-#define DEBUG
-#endif
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/bio.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/buffer_head.h>
-#include <linux/device.h>
-#include <linux/genhd.h>
-#include <linux/highmem.h>
-#include <linux/slab.h>
-#include <linux/lzo.h>
-#include <linux/string.h>
-#include <linux/vmalloc.h>
-
-#include "zram_drv.h"
-
-/* Globals */
-static int zram_major;
-struct zram *zram_devices;
-
-/* Module params (documentation at end) */
-static unsigned int num_devices = 1;
-
-static void zram_stat64_add(struct zram *zram, u64 *v, u64 inc)
-{
- spin_lock(&zram->stat64_lock);
- *v = *v + inc;
- spin_unlock(&zram->stat64_lock);
-}
-
-static void zram_stat64_sub(struct zram *zram, u64 *v, u64 dec)
-{
- spin_lock(&zram->stat64_lock);
- *v = *v - dec;
- spin_unlock(&zram->stat64_lock);
-}
-
-static void zram_stat64_inc(struct zram *zram, u64 *v)
-{
- zram_stat64_add(zram, v, 1);
-}
-
-static int zram_test_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- return meta->table[index].flags & BIT(flag);
-}
-
-static void zram_set_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags |= BIT(flag);
-}
-
-static void zram_clear_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags &= ~BIT(flag);
-}
-
-static int page_zero_filled(void *ptr)
-{
- unsigned int pos;
- unsigned long *page;
-
- page = (unsigned long *)ptr;
-
- for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
- if (page[pos])
- return 0;
- }
-
- return 1;
-}
-
-static void zram_free_page(struct zram *zram, size_t index)
-{
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
- u16 size = meta->table[index].size;
-
- if (unlikely(!handle)) {
- /*
- * No memory is allocated for zero filled pages.
- * Simply clear zero page flag.
- */
- if (zram_test_flag(meta, index, ZRAM_ZERO)) {
- zram_clear_flag(meta, index, ZRAM_ZERO);
- zram->stats.pages_zero--;
- }
- return;
- }
-
- if (unlikely(size > max_zpage_size))
- zram->stats.bad_compress--;
-
- zs_free(meta->mem_pool, handle);
-
- if (size <= PAGE_SIZE / 2)
- zram->stats.good_compress--;
-
- zram_stat64_sub(zram, &zram->stats.compr_size,
- meta->table[index].size);
- zram->stats.pages_stored--;
-
- meta->table[index].handle = 0;
- meta->table[index].size = 0;
-}
-
-static void handle_zero_page(struct bio_vec *bvec)
-{
- struct page *page = bvec->bv_page;
- void *user_mem;
-
- user_mem = kmap_atomic(page);
- memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
- kunmap_atomic(user_mem);
-
- flush_dcache_page(page);
-}
-
-static inline int is_partial_io(struct bio_vec *bvec)
-{
- return bvec->bv_len != PAGE_SIZE;
-}
-
-static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
-{
- int ret = LZO_E_OK;
- size_t clen = PAGE_SIZE;
- unsigned char *cmem;
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
-
- if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
- memset(mem, 0, PAGE_SIZE);
- return 0;
- }
-
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
- if (meta->table[index].size == PAGE_SIZE)
- memcpy(mem, cmem, PAGE_SIZE);
- else
- ret = lzo1x_decompress_safe(cmem, meta->table[index].size,
- mem, &clen);
- zs_unmap_object(meta->mem_pool, handle);
-
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
- zram_stat64_inc(zram, &zram->stats.failed_reads);
- return ret;
- }
-
- return 0;
-}
-
-static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset, struct bio *bio)
-{
- int ret;
- struct page *page;
- unsigned char *user_mem, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
- page = bvec->bv_page;
-
- if (unlikely(!meta->table[index].handle) ||
- zram_test_flag(meta, index, ZRAM_ZERO)) {
- handle_zero_page(bvec);
- return 0;
- }
-
- if (is_partial_io(bvec))
- /* Use a temporary buffer to decompress the page */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
-
- user_mem = kmap_atomic(page);
- if (!is_partial_io(bvec))
- uncmem = user_mem;
-
- if (!uncmem) {
- pr_info("Unable to allocate temp memory\n");
- ret = -ENOMEM;
- goto out_cleanup;
- }
-
- ret = zram_decompress_page(zram, uncmem, index);
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK))
- goto out_cleanup;
-
- if (is_partial_io(bvec))
- memcpy(user_mem + bvec->bv_offset, uncmem + offset,
- bvec->bv_len);
-
- flush_dcache_page(page);
- ret = 0;
-out_cleanup:
- kunmap_atomic(user_mem);
- if (is_partial_io(bvec))
- kfree(uncmem);
- return ret;
-}
-
-static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset)
-{
- int ret = 0;
- size_t clen;
- unsigned long handle;
- struct page *page;
- unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
-
- page = bvec->bv_page;
- src = meta->compress_buffer;
-
- if (is_partial_io(bvec)) {
- /*
- * This is a partial IO. We need to read the full page
- * before to write the changes.
- */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
- if (!uncmem) {
- ret = -ENOMEM;
- goto out;
- }
- ret = zram_decompress_page(zram, uncmem, index);
- if (ret)
- goto out;
- }
-
- /*
- * System overwrites unused sectors. Free memory associated
- * with this sector now.
- */
- if (meta->table[index].handle ||
- zram_test_flag(meta, index, ZRAM_ZERO))
- zram_free_page(zram, index);
-
- user_mem = kmap_atomic(page);
-
- if (is_partial_io(bvec)) {
- memcpy(uncmem + offset, user_mem + bvec->bv_offset,
- bvec->bv_len);
- kunmap_atomic(user_mem);
- user_mem = NULL;
- } else {
- uncmem = user_mem;
- }
-
- if (page_zero_filled(uncmem)) {
- kunmap_atomic(user_mem);
- zram->stats.pages_zero++;
- zram_set_flag(meta, index, ZRAM_ZERO);
- ret = 0;
- goto out;
- }
-
- ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen,
- meta->compress_workmem);
-
- if (!is_partial_io(bvec)) {
- kunmap_atomic(user_mem);
- user_mem = NULL;
- uncmem = NULL;
- }
-
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Compression failed! err=%d\n", ret);
- goto out;
- }
-
- if (unlikely(clen > max_zpage_size)) {
- zram->stats.bad_compress++;
- clen = PAGE_SIZE;
- src = NULL;
- if (is_partial_io(bvec))
- src = uncmem;
- }
-
- handle = zs_malloc(meta->mem_pool, clen);
- if (!handle) {
- pr_info("Error allocating memory for compressed "
- "page: %u, size=%zu\n", index, clen);
- ret = -ENOMEM;
- goto out;
- }
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
-
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec))
- src = kmap_atomic(page);
- memcpy(cmem, src, clen);
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec))
- kunmap_atomic(src);
-
- zs_unmap_object(meta->mem_pool, handle);
-
- meta->table[index].handle = handle;
- meta->table[index].size = clen;
-
- /* Update stats */
- zram_stat64_add(zram, &zram->stats.compr_size, clen);
- zram->stats.pages_stored++;
- if (clen <= PAGE_SIZE / 2)
- zram->stats.good_compress++;
-
-out:
- if (is_partial_io(bvec))
- kfree(uncmem);
-
- if (ret)
- zram_stat64_inc(zram, &zram->stats.failed_writes);
- return ret;
-}
-
-static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, struct bio *bio, int rw)
-{
- int ret;
-
- if (rw == READ) {
- down_read(&zram->lock);
- ret = zram_bvec_read(zram, bvec, index, offset, bio);
- up_read(&zram->lock);
- } else {
- down_write(&zram->lock);
- ret = zram_bvec_write(zram, bvec, index, offset);
- up_write(&zram->lock);
- }
-
- return ret;
-}
-
-static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
-{
- if (*offset + bvec->bv_len >= PAGE_SIZE)
- (*index)++;
- *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
-}
-
-static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
-{
- int i, offset;
- u32 index;
- struct bio_vec *bvec;
-
- switch (rw) {
- case READ:
- zram_stat64_inc(zram, &zram->stats.num_reads);
- break;
- case WRITE:
- zram_stat64_inc(zram, &zram->stats.num_writes);
- break;
- }
-
- index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
- offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
-
- bio_for_each_segment(bvec, bio, i) {
- int max_transfer_size = PAGE_SIZE - offset;
-
- if (bvec->bv_len > max_transfer_size) {
- /*
- * zram_bvec_rw() can only make operation on a single
- * zram page. Split the bio vector.
- */
- struct bio_vec bv;
-
- bv.bv_page = bvec->bv_page;
- bv.bv_len = max_transfer_size;
- bv.bv_offset = bvec->bv_offset;
-
- if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
- goto out;
-
- bv.bv_len = bvec->bv_len - max_transfer_size;
- bv.bv_offset += max_transfer_size;
- if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
- goto out;
- } else
- if (zram_bvec_rw(zram, bvec, index, offset, bio, rw)
- < 0)
- goto out;
-
- update_position(&index, &offset, bvec);
- }
-
- set_bit(BIO_UPTODATE, &bio->bi_flags);
- bio_endio(bio, 0);
- return;
-
-out:
- bio_io_error(bio);
-}
-
-/*
- * Check if request is within bounds and aligned on zram logical blocks.
- */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
-{
- u64 start, end, bound;
-
- /* unaligned request */
- if (unlikely(bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
- return 0;
- if (unlikely(bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
- return 0;
-
- start = bio->bi_sector;
- end = start + (bio->bi_size >> SECTOR_SHIFT);
- bound = zram->disksize >> SECTOR_SHIFT;
- /* out of range range */
- if (unlikely(start >= bound || end > bound || start > end))
- return 0;
-
- /* I/O request is valid */
- return 1;
-}
-
-/*
- * Handler function for all zram I/O requests.
- */
-static void zram_make_request(struct request_queue *queue, struct bio *bio)
-{
- struct zram *zram = queue->queuedata;
-
- down_read(&zram->init_lock);
- if (unlikely(!zram->init_done))
- goto error;
-
- if (!valid_io_request(zram, bio)) {
- zram_stat64_inc(zram, &zram->stats.invalid_io);
- goto error;
- }
-
- __zram_make_request(zram, bio, bio_data_dir(bio));
- up_read(&zram->init_lock);
-
- return;
-
-error:
- up_read(&zram->init_lock);
- bio_io_error(bio);
-}
-
-static void __zram_reset_device(struct zram *zram)
-{
- size_t index;
- struct zram_meta *meta;
-
- if (!zram->init_done)
- return;
-
- meta = zram->meta;
- zram->init_done = 0;
-
- /* Free all pages that are still in this zram device */
- for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
- unsigned long handle = meta->table[index].handle;
- if (!handle)
- continue;
-
- zs_free(meta->mem_pool, handle);
- }
-
- zram_meta_free(zram->meta);
- zram->meta = NULL;
- /* Reset stats */
- memset(&zram->stats, 0, sizeof(zram->stats));
-
- zram->disksize = 0;
- set_capacity(zram->disk, 0);
-}
-
-void zram_reset_device(struct zram *zram)
-{
- down_write(&zram->init_lock);
- __zram_reset_device(zram);
- up_write(&zram->init_lock);
-}
-
-void zram_meta_free(struct zram_meta *meta)
-{
- zs_destroy_pool(meta->mem_pool);
- kfree(meta->compress_workmem);
- free_pages((unsigned long)meta->compress_buffer, 1);
- vfree(meta->table);
- kfree(meta);
-}
-
-struct zram_meta *zram_meta_alloc(u64 disksize)
-{
- size_t num_pages;
- struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
- if (!meta)
- goto out;
-
- meta->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
- if (!meta->compress_workmem)
- goto free_meta;
-
- meta->compress_buffer =
- (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
- if (!meta->compress_buffer) {
- pr_err("Error allocating compressor buffer space\n");
- goto free_workmem;
- }
-
- num_pages = disksize >> PAGE_SHIFT;
- meta->table = vzalloc(num_pages * sizeof(*meta->table));
- if (!meta->table) {
- pr_err("Error allocating zram address table\n");
- goto free_buffer;
- }
-
- meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
- if (!meta->mem_pool) {
- pr_err("Error creating memory pool\n");
- goto free_table;
- }
-
- return meta;
-
-free_table:
- vfree(meta->table);
-free_buffer:
- free_pages((unsigned long)meta->compress_buffer, 1);
-free_workmem:
- kfree(meta->compress_workmem);
-free_meta:
- kfree(meta);
- meta = NULL;
-out:
- return meta;
-}
-
-void zram_init_device(struct zram *zram, struct zram_meta *meta)
-{
- if (zram->disksize > 2 * (totalram_pages << PAGE_SHIFT)) {
- pr_info(
- "There is little point creating a zram of greater than "
- "twice the size of memory since we expect a 2:1 compression "
- "ratio. Note that zram uses about 0.1%% of the size of "
- "the disk when not in use so a huge zram is "
- "wasteful.\n"
- "\tMemory Size: %lu kB\n"
- "\tSize you selected: %llu kB\n"
- "Continuing anyway ...\n",
- (totalram_pages << PAGE_SHIFT) >> 10, zram->disksize >> 10
- );
- }
-
- /* zram devices sort of resembles non-rotational disks */
- queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
-
- zram->meta = meta;
- zram->init_done = 1;
-
- pr_debug("Initialization done!\n");
-}
-
-static void zram_slot_free_notify(struct block_device *bdev,
- unsigned long index)
-{
- struct zram *zram;
-
- zram = bdev->bd_disk->private_data;
- down_write(&zram->lock);
- zram_free_page(zram, index);
- up_write(&zram->lock);
- zram_stat64_inc(zram, &zram->stats.notify_free);
-}
-
-static const struct block_device_operations zram_devops = {
- .swap_slot_free_notify = zram_slot_free_notify,
- .owner = THIS_MODULE
-};
-
-static int create_device(struct zram *zram, int device_id)
-{
- int ret = -ENOMEM;
-
- init_rwsem(&zram->lock);
- init_rwsem(&zram->init_lock);
- spin_lock_init(&zram->stat64_lock);
-
- zram->queue = blk_alloc_queue(GFP_KERNEL);
- if (!zram->queue) {
- pr_err("Error allocating disk queue for device %d\n",
- device_id);
- goto out;
- }
-
- blk_queue_make_request(zram->queue, zram_make_request);
- zram->queue->queuedata = zram;
-
- /* gendisk structure */
- zram->disk = alloc_disk(1);
- if (!zram->disk) {
- pr_warn("Error allocating disk structure for device %d\n",
- device_id);
- goto out_free_queue;
- }
-
- zram->disk->major = zram_major;
- zram->disk->first_minor = device_id;
- zram->disk->fops = &zram_devops;
- zram->disk->queue = zram->queue;
- zram->disk->private_data = zram;
- snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
-
- /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
- set_capacity(zram->disk, 0);
-
- /*
- * To ensure that we always get PAGE_SIZE aligned
- * and n*PAGE_SIZED sized I/O requests.
- */
- blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
- blk_queue_logical_block_size(zram->disk->queue,
- ZRAM_LOGICAL_BLOCK_SIZE);
- blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
- blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-
- add_disk(zram->disk);
-
- ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
- if (ret < 0) {
- pr_warn("Error creating sysfs group");
- goto out_free_disk;
- }
-
- zram->init_done = 0;
- return 0;
-
-out_free_disk:
- del_gendisk(zram->disk);
- put_disk(zram->disk);
-out_free_queue:
- blk_cleanup_queue(zram->queue);
-out:
- return ret;
-}
-
-static void destroy_device(struct zram *zram)
-{
- sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
-
- if (zram->disk) {
- del_gendisk(zram->disk);
- put_disk(zram->disk);
- }
-
- if (zram->queue)
- blk_cleanup_queue(zram->queue);
-}
-
-unsigned int zram_get_num_devices(void)
-{
- return num_devices;
-}
-
-static int __init zram_init(void)
-{
- int ret, dev_id;
-
- if (num_devices > max_num_devices) {
- pr_warn("Invalid value for num_devices: %u\n",
- num_devices);
- ret = -EINVAL;
- goto out;
- }
-
- zram_major = register_blkdev(0, "zram");
- if (zram_major <= 0) {
- pr_warn("Unable to get major number\n");
- ret = -EBUSY;
- goto out;
- }
-
- /* Allocate the device array and initialize each one */
- zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
- if (!zram_devices) {
- ret = -ENOMEM;
- goto unregister;
- }
-
- for (dev_id = 0; dev_id < num_devices; dev_id++) {
- ret = create_device(&zram_devices[dev_id], dev_id);
- if (ret)
- goto free_devices;
- }
-
- pr_info("Created %u device(s) ...\n", num_devices);
-
- return 0;
-
-free_devices:
- while (dev_id)
- destroy_device(&zram_devices[--dev_id]);
- kfree(zram_devices);
-unregister:
- unregister_blkdev(zram_major, "zram");
-out:
- return ret;
-}
-
-static void __exit zram_exit(void)
-{
- int i;
- struct zram *zram;
-
- for (i = 0; i < num_devices; i++) {
- zram = &zram_devices[i];
-
- get_disk(zram->disk);
- destroy_device(zram);
- zram_reset_device(zram);
- put_disk(zram->disk);
- }
-
- unregister_blkdev(zram_major, "zram");
-
- kfree(zram_devices);
- pr_debug("Cleanup done!\n");
-}
-
-module_param(num_devices, uint, 0);
-MODULE_PARM_DESC(num_devices, "Number of zram devices");
-
-module_init(zram_init);
-module_exit(zram_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
-MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/staging/zram/zram_drv.h b/drivers/staging/zram/zram_drv.h
deleted file mode 100644
index d542eee..0000000
--- a/drivers/staging/zram/zram_drv.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#ifndef _ZRAM_DRV_H_
-#define _ZRAM_DRV_H_
-
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-
-#include "../zsmalloc/zsmalloc.h"
-
-/*
- * Some arbitrary value. This is just to catch
- * invalid value for num_devices module parameter.
- */
-static const unsigned max_num_devices = 32;
-
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
-#define SECTOR_SHIFT 9
-#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
-#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
-#define ZRAM_LOGICAL_BLOCK_SHIFT 12
-#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
-#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
- (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
-
-/* Flags for zram pages (table[page_no].flags) */
-enum zram_pageflags {
- /* Page consists entirely of zeros */
- ZRAM_ZERO,
-
- __NR_ZRAM_PAGEFLAGS,
-};
-
-/*-- Data structures */
-
-/* Allocated for each disk page */
-struct table {
- unsigned long handle;
- u16 size; /* object size (excluding header) */
- u8 count; /* object ref count (not yet used) */
- u8 flags;
-} __aligned(4);
-
-struct zram_stats {
- u64 compr_size; /* compressed size of pages stored */
- u64 num_reads; /* failed + successful */
- u64 num_writes; /* --do-- */
- u64 failed_reads; /* should NEVER! happen */
- u64 failed_writes; /* can happen when memory is too low */
- u64 invalid_io; /* non-page-aligned I/O requests */
- u64 notify_free; /* no. of swap slot free notifications */
- u32 pages_zero; /* no. of zero filled pages */
- u32 pages_stored; /* no. of pages currently stored */
- u32 good_compress; /* % of pages with compression ratio<=50% */
- u32 bad_compress; /* % of pages with compression ratio>=75% */
-};
-
-struct zram_meta {
- void *compress_workmem;
- void *compress_buffer;
- struct table *table;
- struct zs_pool *mem_pool;
-};
-
-struct zram {
- struct zram_meta *meta;
- spinlock_t stat64_lock; /* protect 64-bit stats */
- struct rw_semaphore lock; /* protect compression buffers, table,
- * 32bit stat counters against concurrent
- * notifications, reads and writes */
- struct request_queue *queue;
- struct gendisk *disk;
- int init_done;
- /* Prevent concurrent execution of device init, reset and R/W request */
- struct rw_semaphore init_lock;
- /*
- * This is the limit on amount of *uncompressed* worth of data
- * we can store in a disk.
- */
- u64 disksize; /* bytes */
-
- struct zram_stats stats;
-};
-
-extern struct zram *zram_devices;
-unsigned int zram_get_num_devices(void);
-#ifdef CONFIG_SYSFS
-extern struct attribute_group zram_disk_attr_group;
-#endif
-
-extern void zram_reset_device(struct zram *zram);
-extern struct zram_meta *zram_meta_alloc(u64 disksize);
-extern void zram_meta_free(struct zram_meta *meta);
-extern void zram_init_device(struct zram *zram, struct zram_meta *meta);
-
-#endif
diff --git a/drivers/staging/zram/zram_sysfs.c b/drivers/staging/zram/zram_sysfs.c
deleted file mode 100644
index dc76a3d..0000000
--- a/drivers/staging/zram/zram_sysfs.c
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com/
- */
-
-#include <linux/device.h>
-#include <linux/genhd.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-
-#include "zram_drv.h"
-
-static u64 zram_stat64_read(struct zram *zram, u64 *v)
-{
- u64 val;
-
- spin_lock(&zram->stat64_lock);
- val = *v;
- spin_unlock(&zram->stat64_lock);
-
- return val;
-}
-
-static struct zram *dev_to_zram(struct device *dev)
-{
- int i;
- struct zram *zram = NULL;
-
- for (i = 0; i < zram_get_num_devices(); i++) {
- zram = &zram_devices[i];
- if (disk_to_dev(zram->disk) == dev)
- break;
- }
-
- return zram;
-}
-
-static ssize_t disksize_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n", zram->disksize);
-}
-
-static ssize_t disksize_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- u64 disksize;
- struct zram_meta *meta;
- struct zram *zram = dev_to_zram(dev);
-
- disksize = memparse(buf, NULL);
- if (!disksize)
- return -EINVAL;
-
- disksize = PAGE_ALIGN(disksize);
- meta = zram_meta_alloc(disksize);
- down_write(&zram->init_lock);
- if (zram->init_done) {
- up_write(&zram->init_lock);
- zram_meta_free(meta);
- pr_info("Cannot change disksize for initialized device\n");
- return -EBUSY;
- }
-
- zram->disksize = disksize;
- set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
- zram_init_device(zram, meta);
- up_write(&zram->init_lock);
-
- return len;
-}
-
-static ssize_t initstate_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->init_done);
-}
-
-static ssize_t reset_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- int ret;
- unsigned short do_reset;
- struct zram *zram;
- struct block_device *bdev;
-
- zram = dev_to_zram(dev);
- bdev = bdget_disk(zram->disk, 0);
-
- /* Do not reset an active device! */
- if (bdev->bd_holders)
- return -EBUSY;
-
- ret = kstrtou16(buf, 10, &do_reset);
- if (ret)
- return ret;
-
- if (!do_reset)
- return -EINVAL;
-
- /* Make sure all pending I/O is finished */
- if (bdev)
- fsync_bdev(bdev);
-
- zram_reset_device(zram);
- return len;
-}
-
-static ssize_t num_reads_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.num_reads));
-}
-
-static ssize_t num_writes_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.num_writes));
-}
-
-static ssize_t invalid_io_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.invalid_io));
-}
-
-static ssize_t notify_free_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.notify_free));
-}
-
-static ssize_t zero_pages_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->stats.pages_zero);
-}
-
-static ssize_t orig_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)(zram->stats.pages_stored) << PAGE_SHIFT);
-}
-
-static ssize_t compr_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.compr_size));
-}
-
-static ssize_t mem_used_total_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val = 0;
- struct zram *zram = dev_to_zram(dev);
- struct zram_meta *meta = zram->meta;
-
- down_read(&zram->init_lock);
- if (zram->init_done)
- val = zs_get_total_size_bytes(meta->mem_pool);
- up_read(&zram->init_lock);
-
- return sprintf(buf, "%llu\n", val);
-}
-
-static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
- disksize_show, disksize_store);
-static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
-static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(num_reads, S_IRUGO, num_reads_show, NULL);
-static DEVICE_ATTR(num_writes, S_IRUGO, num_writes_show, NULL);
-static DEVICE_ATTR(invalid_io, S_IRUGO, invalid_io_show, NULL);
-static DEVICE_ATTR(notify_free, S_IRUGO, notify_free_show, NULL);
-static DEVICE_ATTR(zero_pages, S_IRUGO, zero_pages_show, NULL);
-static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(compr_data_size, S_IRUGO, compr_data_size_show, NULL);
-static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
-
-static struct attribute *zram_disk_attrs[] = {
- &dev_attr_disksize.attr,
- &dev_attr_initstate.attr,
- &dev_attr_reset.attr,
- &dev_attr_num_reads.attr,
- &dev_attr_num_writes.attr,
- &dev_attr_invalid_io.attr,
- &dev_attr_notify_free.attr,
- &dev_attr_zero_pages.attr,
- &dev_attr_orig_data_size.attr,
- &dev_attr_compr_data_size.attr,
- &dev_attr_mem_used_total.attr,
- NULL,
-};
-
-struct attribute_group zram_disk_attr_group = {
- .attrs = zram_disk_attrs,
-};
diff --git a/drivers/staging/zsmalloc/Kconfig b/drivers/staging/zsmalloc/Kconfig
deleted file mode 100644
index 7fab032..0000000
--- a/drivers/staging/zsmalloc/Kconfig
+++ /dev/null
@@ -1,10 +0,0 @@
-config ZSMALLOC
- bool "Memory allocator for compressed pages"
- default n
- help
- zsmalloc is a slab-based memory allocator designed to store
- compressed RAM pages. zsmalloc uses virtual memory mapping
- in order to reduce fragmentation. However, this results in a
- non-standard allocator interface where a handle, not a pointer, is
- returned by an alloc(). This handle must be mapped in order to
- access the allocated space.
diff --git a/drivers/staging/zsmalloc/Makefile b/drivers/staging/zsmalloc/Makefile
deleted file mode 100644
index b134848..0000000
--- a/drivers/staging/zsmalloc/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zsmalloc-y := zsmalloc-main.o
-
-obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
deleted file mode 100644
index 288f582..0000000
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ /dev/null
@@ -1,1073 +0,0 @@
-/*
- * zsmalloc memory allocator
- *
- * Copyright (C) 2011 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the license that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- */
-
-
-/*
- * This allocator is designed for use with zcache and zram. Thus, the
- * allocator is supposed to work well under low memory conditions. In
- * particular, it never attempts higher order page allocation which is
- * very likely to fail under memory pressure. On the other hand, if we
- * just use single (0-order) pages, it would suffer from very high
- * fragmentation -- any object of size PAGE_SIZE/2 or larger would occupy
- * an entire page. This was one of the major issues with its predecessor
- * (xvmalloc).
- *
- * To overcome these issues, zsmalloc allocates a bunch of 0-order pages
- * and links them together using various 'struct page' fields. These linked
- * pages act as a single higher-order page i.e. an object can span 0-order
- * page boundaries. The code refers to these linked pages as a single entity
- * called zspage.
- *
- * Following is how we use various fields and flags of underlying
- * struct page(s) to form a zspage.
- *
- * Usage of struct page fields:
- * page->first_page: points to the first component (0-order) page
- * page->index (union with page->freelist): offset of the first object
- * starting in this page. For the first page, this is
- * always 0, so we use this field (aka freelist) to point
- * to the first free object in zspage.
- * page->lru: links together all component pages (except the first page)
- * of a zspage
- *
- * For _first_ page only:
- *
- * page->private (union with page->first_page): refers to the
- * component page after the first page
- * page->freelist: points to the first free object in zspage.
- * Free objects are linked together using in-place
- * metadata.
- * page->objects: maximum number of objects we can store in this
- * zspage (class->zspage_order * PAGE_SIZE / class->size)
- * page->lru: links together first pages of various zspages.
- * Basically forming list of zspages in a fullness group.
- * page->mapping: class index and fullness group of the zspage
- *
- * Usage of struct page flags:
- * PG_private: identifies the first component page
- * PG_private2: identifies the last component page
- *
- */
-
-#ifdef CONFIG_ZSMALLOC_DEBUG
-#define DEBUG
-#endif
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/bitops.h>
-#include <linux/errno.h>
-#include <linux/highmem.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <asm/tlbflush.h>
-#include <asm/pgtable.h>
-#include <linux/cpumask.h>
-#include <linux/cpu.h>
-#include <linux/vmalloc.h>
-#include <linux/hardirq.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#include "zsmalloc.h"
-
-/*
- * This must be power of 2 and greater than of equal to sizeof(link_free).
- * These two conditions ensure that any 'struct link_free' itself doesn't
- * span more than 1 page which avoids complex case of mapping 2 pages simply
- * to restore link_free pointer values.
- */
-#define ZS_ALIGN 8
-
-/*
- * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
- * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
- */
-#define ZS_MAX_ZSPAGE_ORDER 2
-#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
-
-/*
- * Object location (<PFN>, <obj_idx>) is encoded as
- * as single (void *) handle value.
- *
- * Note that object index <obj_idx> is relative to system
- * page <PFN> it is stored in, so for each sub-page belonging
- * to a zspage, obj_idx starts with 0.
- *
- * This is made more complicated by various memory models and PAE.
- */
-
-#ifndef MAX_PHYSMEM_BITS
-#ifdef CONFIG_HIGHMEM64G
-#define MAX_PHYSMEM_BITS 36
-#else /* !CONFIG_HIGHMEM64G */
-/*
- * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
- * be PAGE_SHIFT
- */
-#define MAX_PHYSMEM_BITS BITS_PER_LONG
-#endif
-#endif
-#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
-#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
-#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
-
-#define MAX(a, b) ((a) >= (b) ? (a) : (b))
-/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
-#define ZS_MIN_ALLOC_SIZE \
- MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
-#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
-
-/*
- * On systems with 4K page size, this gives 254 size classes! There is a
- * trader-off here:
- * - Large number of size classes is potentially wasteful as free page are
- * spread across these classes
- * - Small number of size classes causes large internal fragmentation
- * - Probably its better to use specific size classes (empirically
- * determined). NOTE: all those class sizes must be set as multiple of
- * ZS_ALIGN to make sure link_free itself never has to span 2 pages.
- *
- * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
- * (reason above)
- */
-#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
-#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
- ZS_SIZE_CLASS_DELTA + 1)
-
-/*
- * We do not maintain any list for completely empty or full pages
- */
-enum fullness_group {
- ZS_ALMOST_FULL,
- ZS_ALMOST_EMPTY,
- _ZS_NR_FULLNESS_GROUPS,
-
- ZS_EMPTY,
- ZS_FULL
-};
-
-/*
- * We assign a page to ZS_ALMOST_EMPTY fullness group when:
- * n <= N / f, where
- * n = number of allocated objects
- * N = total number of objects zspage can store
- * f = 1/fullness_threshold_frac
- *
- * Similarly, we assign zspage to:
- * ZS_ALMOST_FULL when n > N / f
- * ZS_EMPTY when n == 0
- * ZS_FULL when n == N
- *
- * (see: fix_fullness_group())
- */
-static const int fullness_threshold_frac = 4;
-
-struct size_class {
- /*
- * Size of objects stored in this class. Must be multiple
- * of ZS_ALIGN.
- */
- int size;
- unsigned int index;
-
- /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
- int pages_per_zspage;
-
- spinlock_t lock;
-
- /* stats */
- u64 pages_allocated;
-
- struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
-};
-
-/*
- * Placed within free objects to form a singly linked list.
- * For every zspage, first_page->freelist gives head of this list.
- *
- * This must be power of 2 and less than or equal to ZS_ALIGN
- */
-struct link_free {
- /* Handle of next free chunk (encodes <PFN, obj_idx>) */
- void *next;
-};
-
-struct zs_pool {
- struct size_class size_class[ZS_SIZE_CLASSES];
-
- gfp_t flags; /* allocation flags used when growing pool */
-};
-
-/*
- * A zspage's class index and fullness group
- * are encoded in its (first)page->mapping
- */
-#define CLASS_IDX_BITS 28
-#define FULLNESS_BITS 4
-#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1)
-#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1)
-
-/*
- * By default, zsmalloc uses a copy-based object mapping method to access
- * allocations that span two pages. However, if a particular architecture
- * performs VM mapping faster than copying, then it should be added here
- * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
- * page table mapping rather than copying for object mapping.
-*/
-#if defined(CONFIG_ARM) && !defined(MODULE)
-#define USE_PGTABLE_MAPPING
-#endif
-
-struct mapping_area {
-#ifdef USE_PGTABLE_MAPPING
- struct vm_struct *vm; /* vm area for mapping object that span pages */
-#else
- char *vm_buf; /* copy buffer for objects that span pages */
-#endif
- char *vm_addr; /* address of kmap_atomic()'ed pages */
- enum zs_mapmode vm_mm; /* mapping mode */
-};
-
-
-/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
-static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
-
-static int is_first_page(struct page *page)
-{
- return PagePrivate(page);
-}
-
-static int is_last_page(struct page *page)
-{
- return PagePrivate2(page);
-}
-
-static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
- enum fullness_group *fullness)
-{
- unsigned long m;
- BUG_ON(!is_first_page(page));
-
- m = (unsigned long)page->mapping;
- *fullness = m & FULLNESS_MASK;
- *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
-}
-
-static void set_zspage_mapping(struct page *page, unsigned int class_idx,
- enum fullness_group fullness)
-{
- unsigned long m;
- BUG_ON(!is_first_page(page));
-
- m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
- (fullness & FULLNESS_MASK);
- page->mapping = (struct address_space *)m;
-}
-
-static int get_size_class_index(int size)
-{
- int idx = 0;
-
- if (likely(size > ZS_MIN_ALLOC_SIZE))
- idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
- ZS_SIZE_CLASS_DELTA);
-
- return idx;
-}
-
-static enum fullness_group get_fullness_group(struct page *page)
-{
- int inuse, max_objects;
- enum fullness_group fg;
- BUG_ON(!is_first_page(page));
-
- inuse = page->inuse;
- max_objects = page->objects;
-
- if (inuse == 0)
- fg = ZS_EMPTY;
- else if (inuse == max_objects)
- fg = ZS_FULL;
- else if (inuse <= max_objects / fullness_threshold_frac)
- fg = ZS_ALMOST_EMPTY;
- else
- fg = ZS_ALMOST_FULL;
-
- return fg;
-}
-
-static void insert_zspage(struct page *page, struct size_class *class,
- enum fullness_group fullness)
-{
- struct page **head;
-
- BUG_ON(!is_first_page(page));
-
- if (fullness >= _ZS_NR_FULLNESS_GROUPS)
- return;
-
- head = &class->fullness_list[fullness];
- if (*head)
- list_add_tail(&page->lru, &(*head)->lru);
-
- *head = page;
-}
-
-static void remove_zspage(struct page *page, struct size_class *class,
- enum fullness_group fullness)
-{
- struct page **head;
-
- BUG_ON(!is_first_page(page));
-
- if (fullness >= _ZS_NR_FULLNESS_GROUPS)
- return;
-
- head = &class->fullness_list[fullness];
- BUG_ON(!*head);
- if (list_empty(&(*head)->lru))
- *head = NULL;
- else if (*head == page)
- *head = (struct page *)list_entry((*head)->lru.next,
- struct page, lru);
-
- list_del_init(&page->lru);
-}
-
-static enum fullness_group fix_fullness_group(struct zs_pool *pool,
- struct page *page)
-{
- int class_idx;
- struct size_class *class;
- enum fullness_group currfg, newfg;
-
- BUG_ON(!is_first_page(page));
-
- get_zspage_mapping(page, &class_idx, &currfg);
- newfg = get_fullness_group(page);
- if (newfg == currfg)
- goto out;
-
- class = &pool->size_class[class_idx];
- remove_zspage(page, class, currfg);
- insert_zspage(page, class, newfg);
- set_zspage_mapping(page, class_idx, newfg);
-
-out:
- return newfg;
-}
-
-/*
- * We have to decide on how many pages to link together
- * to form a zspage for each size class. This is important
- * to reduce wastage due to unusable space left at end of
- * each zspage which is given as:
- * wastage = Zp - Zp % size_class
- * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
- *
- * For example, for size class of 3/8 * PAGE_SIZE, we should
- * link together 3 PAGE_SIZE sized pages to form a zspage
- * since then we can perfectly fit in 8 such objects.
- */
-static int get_pages_per_zspage(int class_size)
-{
- int i, max_usedpc = 0;
- /* zspage order which gives maximum used size per KB */
- int max_usedpc_order = 1;
-
- for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
- int zspage_size;
- int waste, usedpc;
-
- zspage_size = i * PAGE_SIZE;
- waste = zspage_size % class_size;
- usedpc = (zspage_size - waste) * 100 / zspage_size;
-
- if (usedpc > max_usedpc) {
- max_usedpc = usedpc;
- max_usedpc_order = i;
- }
- }
-
- return max_usedpc_order;
-}
-
-/*
- * A single 'zspage' is composed of many system pages which are
- * linked together using fields in struct page. This function finds
- * the first/head page, given any component page of a zspage.
- */
-static struct page *get_first_page(struct page *page)
-{
- if (is_first_page(page))
- return page;
- else
- return page->first_page;
-}
-
-static struct page *get_next_page(struct page *page)
-{
- struct page *next;
-
- if (is_last_page(page))
- next = NULL;
- else if (is_first_page(page))
- next = (struct page *)page->private;
- else
- next = list_entry(page->lru.next, struct page, lru);
-
- return next;
-}
-
-/*
- * Encode <page, obj_idx> as a single handle value.
- * On hardware platforms with physical memory starting at 0x0 the pfn
- * could be 0 so we ensure that the handle will never be 0 by adjusting the
- * encoded obj_idx value before encoding.
- */
-static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
-{
- unsigned long handle;
-
- if (!page) {
- BUG_ON(obj_idx);
- return NULL;
- }
-
- handle = page_to_pfn(page) << OBJ_INDEX_BITS;
- handle |= ((obj_idx + 1) & OBJ_INDEX_MASK);
-
- return (void *)handle;
-}
-
-/*
- * Decode <page, obj_idx> pair from the given object handle. We adjust the
- * decoded obj_idx back to its original value since it was adjusted in
- * obj_location_to_handle().
- */
-static void obj_handle_to_location(unsigned long handle, struct page **page,
- unsigned long *obj_idx)
-{
- *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
- *obj_idx = (handle & OBJ_INDEX_MASK) - 1;
-}
-
-static unsigned long obj_idx_to_offset(struct page *page,
- unsigned long obj_idx, int class_size)
-{
- unsigned long off = 0;
-
- if (!is_first_page(page))
- off = page->index;
-
- return off + obj_idx * class_size;
-}
-
-static void reset_page(struct page *page)
-{
- clear_bit(PG_private, &page->flags);
- clear_bit(PG_private_2, &page->flags);
- set_page_private(page, 0);
- page->mapping = NULL;
- page->freelist = NULL;
- page_mapcount_reset(page);
-}
-
-static void free_zspage(struct page *first_page)
-{
- struct page *nextp, *tmp, *head_extra;
-
- BUG_ON(!is_first_page(first_page));
- BUG_ON(first_page->inuse);
-
- head_extra = (struct page *)page_private(first_page);
-
- reset_page(first_page);
- __free_page(first_page);
-
- /* zspage with only 1 system page */
- if (!head_extra)
- return;
-
- list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
- list_del(&nextp->lru);
- reset_page(nextp);
- __free_page(nextp);
- }
- reset_page(head_extra);
- __free_page(head_extra);
-}
-
-/* Initialize a newly allocated zspage */
-static void init_zspage(struct page *first_page, struct size_class *class)
-{
- unsigned long off = 0;
- struct page *page = first_page;
-
- BUG_ON(!is_first_page(first_page));
- while (page) {
- struct page *next_page;
- struct link_free *link;
- unsigned int i, objs_on_page;
-
- /*
- * page->index stores offset of first object starting
- * in the page. For the first page, this is always 0,
- * so we use first_page->index (aka ->freelist) to store
- * head of corresponding zspage's freelist.
- */
- if (page != first_page)
- page->index = off;
-
- link = (struct link_free *)kmap_atomic(page) +
- off / sizeof(*link);
- objs_on_page = (PAGE_SIZE - off) / class->size;
-
- for (i = 1; i <= objs_on_page; i++) {
- off += class->size;
- if (off < PAGE_SIZE) {
- link->next = obj_location_to_handle(page, i);
- link += class->size / sizeof(*link);
- }
- }
-
- /*
- * We now come to the last (full or partial) object on this
- * page, which must point to the first object on the next
- * page (if present)
- */
- next_page = get_next_page(page);
- link->next = obj_location_to_handle(next_page, 0);
- kunmap_atomic(link);
- page = next_page;
- off = (off + class->size) % PAGE_SIZE;
- }
-}
-
-/*
- * Allocate a zspage for the given size class
- */
-static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
-{
- int i, error;
- struct page *first_page = NULL, *uninitialized_var(prev_page);
-
- /*
- * Allocate individual pages and link them together as:
- * 1. first page->private = first sub-page
- * 2. all sub-pages are linked together using page->lru
- * 3. each sub-page is linked to the first page using page->first_page
- *
- * For each size class, First/Head pages are linked together using
- * page->lru. Also, we set PG_private to identify the first page
- * (i.e. no other sub-page has this flag set) and PG_private_2 to
- * identify the last page.
- */
- error = -ENOMEM;
- for (i = 0; i < class->pages_per_zspage; i++) {
- struct page *page;
-
- page = alloc_page(flags);
- if (!page)
- goto cleanup;
-
- INIT_LIST_HEAD(&page->lru);
- if (i == 0) { /* first page */
- SetPagePrivate(page);
- set_page_private(page, 0);
- first_page = page;
- first_page->inuse = 0;
- }
- if (i == 1)
- first_page->private = (unsigned long)page;
- if (i >= 1)
- page->first_page = first_page;
- if (i >= 2)
- list_add(&page->lru, &prev_page->lru);
- if (i == class->pages_per_zspage - 1) /* last page */
- SetPagePrivate2(page);
- prev_page = page;
- }
-
- init_zspage(first_page, class);
-
- first_page->freelist = obj_location_to_handle(first_page, 0);
- /* Maximum number of objects we can store in this zspage */
- first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
-
- error = 0; /* Success */
-
-cleanup:
- if (unlikely(error) && first_page) {
- free_zspage(first_page);
- first_page = NULL;
- }
-
- return first_page;
-}
-
-static struct page *find_get_zspage(struct size_class *class)
-{
- int i;
- struct page *page;
-
- for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
- page = class->fullness_list[i];
- if (page)
- break;
- }
-
- return page;
-}
-
-#ifdef USE_PGTABLE_MAPPING
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm)
- return 0;
- area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
- if (!area->vm)
- return -ENOMEM;
- return 0;
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm)
- free_vm_area(area->vm);
- area->vm = NULL;
-}
-
-static inline void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
- area->vm_addr = area->vm->addr;
- return area->vm_addr + off;
-}
-
-static inline void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm_addr;
-
- unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* USE_PGTABLE_MAPPING */
-
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm_buf)
- return 0;
- area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
- if (!area->vm_buf)
- return -ENOMEM;
- return 0;
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm_buf)
- free_page((unsigned long)area->vm_buf);
- area->vm_buf = NULL;
-}
-
-static void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* disable page faults to match kmap_atomic() return conditions */
- pagefault_disable();
-
- /* no read fastpath */
- if (area->vm_mm == ZS_MM_WO)
- goto out;
-
- sizes[0] = PAGE_SIZE - off;
- sizes[1] = size - sizes[0];
-
- /* copy object to per-cpu buffer */
- addr = kmap_atomic(pages[0]);
- memcpy(buf, addr + off, sizes[0]);
- kunmap_atomic(addr);
- addr = kmap_atomic(pages[1]);
- memcpy(buf + sizes[0], addr, sizes[1]);
- kunmap_atomic(addr);
-out:
- return area->vm_buf;
-}
-
-static void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* no write fastpath */
- if (area->vm_mm == ZS_MM_RO)
- goto out;
-
- sizes[0] = PAGE_SIZE - off;
- sizes[1] = size - sizes[0];
-
- /* copy per-cpu buffer to object */
- addr = kmap_atomic(pages[0]);
- memcpy(addr + off, buf, sizes[0]);
- kunmap_atomic(addr);
- addr = kmap_atomic(pages[1]);
- memcpy(addr, buf + sizes[0], sizes[1]);
- kunmap_atomic(addr);
-
-out:
- /* enable page faults to match kunmap_atomic() return conditions */
- pagefault_enable();
-}
-
-#endif /* USE_PGTABLE_MAPPING */
-
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
- void *pcpu)
-{
- int ret, cpu = (long)pcpu;
- struct mapping_area *area;
-
- switch (action) {
- case CPU_UP_PREPARE:
- area = &per_cpu(zs_map_area, cpu);
- ret = __zs_cpu_up(area);
- if (ret)
- return notifier_from_errno(ret);
- break;
- case CPU_DEAD:
- case CPU_UP_CANCELED:
- area = &per_cpu(zs_map_area, cpu);
- __zs_cpu_down(area);
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block zs_cpu_nb = {
- .notifier_call = zs_cpu_notifier
-};
-
-static void zs_exit(void)
-{
- int cpu;
-
- for_each_online_cpu(cpu)
- zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
- unregister_cpu_notifier(&zs_cpu_nb);
-}
-
-static int zs_init(void)
-{
- int cpu, ret;
-
- register_cpu_notifier(&zs_cpu_nb);
- for_each_online_cpu(cpu) {
- ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
- if (notifier_to_errno(ret))
- goto fail;
- }
- return 0;
-fail:
- zs_exit();
- return notifier_to_errno(ret);
-}
-
-/**
- * zs_create_pool - Creates an allocation pool to work from.
- * @flags: allocation flags used to allocate pool metadata
- *
- * This function must be called before anything when using
- * the zsmalloc allocator.
- *
- * On success, a pointer to the newly created pool is returned,
- * otherwise NULL.
- */
-struct zs_pool *zs_create_pool(gfp_t flags)
-{
- int i, ovhd_size;
- struct zs_pool *pool;
-
- ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
- pool = kzalloc(ovhd_size, GFP_KERNEL);
- if (!pool)
- return NULL;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++) {
- int size;
- struct size_class *class;
-
- size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
- if (size > ZS_MAX_ALLOC_SIZE)
- size = ZS_MAX_ALLOC_SIZE;
-
- class = &pool->size_class[i];
- class->size = size;
- class->index = i;
- spin_lock_init(&class->lock);
- class->pages_per_zspage = get_pages_per_zspage(size);
-
- }
-
- pool->flags = flags;
-
- return pool;
-}
-EXPORT_SYMBOL_GPL(zs_create_pool);
-
-void zs_destroy_pool(struct zs_pool *pool)
-{
- int i;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++) {
- int fg;
- struct size_class *class = &pool->size_class[i];
-
- for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
- if (class->fullness_list[fg]) {
- pr_info("Freeing non-empty class with size "
- "%db, fullness group %d\n",
- class->size, fg);
- }
- }
- }
- kfree(pool);
-}
-EXPORT_SYMBOL_GPL(zs_destroy_pool);
-
-/**
- * zs_malloc - Allocate block of given size from pool.
- * @pool: pool to allocate from
- * @size: size of block to allocate
- *
- * On success, handle to the allocated object is returned,
- * otherwise 0.
- * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
- */
-unsigned long zs_malloc(struct zs_pool *pool, size_t size)
-{
- unsigned long obj;
- struct link_free *link;
- int class_idx;
- struct size_class *class;
-
- struct page *first_page, *m_page;
- unsigned long m_objidx, m_offset;
-
- if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
- return 0;
-
- class_idx = get_size_class_index(size);
- class = &pool->size_class[class_idx];
- BUG_ON(class_idx != class->index);
-
- spin_lock(&class->lock);
- first_page = find_get_zspage(class);
-
- if (!first_page) {
- spin_unlock(&class->lock);
- first_page = alloc_zspage(class, pool->flags);
- if (unlikely(!first_page))
- return 0;
-
- set_zspage_mapping(first_page, class->index, ZS_EMPTY);
- spin_lock(&class->lock);
- class->pages_allocated += class->pages_per_zspage;
- }
-
- obj = (unsigned long)first_page->freelist;
- obj_handle_to_location(obj, &m_page, &m_objidx);
- m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
-
- link = (struct link_free *)kmap_atomic(m_page) +
- m_offset / sizeof(*link);
- first_page->freelist = link->next;
- memset(link, POISON_INUSE, sizeof(*link));
- kunmap_atomic(link);
-
- first_page->inuse++;
- /* Now move the zspage to another fullness group, if required */
- fix_fullness_group(pool, first_page);
- spin_unlock(&class->lock);
-
- return obj;
-}
-EXPORT_SYMBOL_GPL(zs_malloc);
-
-void zs_free(struct zs_pool *pool, unsigned long obj)
-{
- struct link_free *link;
- struct page *first_page, *f_page;
- unsigned long f_objidx, f_offset;
-
- int class_idx;
- struct size_class *class;
- enum fullness_group fullness;
-
- if (unlikely(!obj))
- return;
-
- obj_handle_to_location(obj, &f_page, &f_objidx);
- first_page = get_first_page(f_page);
-
- get_zspage_mapping(first_page, &class_idx, &fullness);
- class = &pool->size_class[class_idx];
- f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
-
- spin_lock(&class->lock);
-
- /* Insert this object in containing zspage's freelist */
- link = (struct link_free *)((unsigned char *)kmap_atomic(f_page)
- + f_offset);
- link->next = first_page->freelist;
- kunmap_atomic(link);
- first_page->freelist = (void *)obj;
-
- first_page->inuse--;
- fullness = fix_fullness_group(pool, first_page);
-
- if (fullness == ZS_EMPTY)
- class->pages_allocated -= class->pages_per_zspage;
-
- spin_unlock(&class->lock);
-
- if (fullness == ZS_EMPTY)
- free_zspage(first_page);
-}
-EXPORT_SYMBOL_GPL(zs_free);
-
-/**
- * zs_map_object - get address of allocated object from handle.
- * @pool: pool from which the object was allocated
- * @handle: handle returned from zs_malloc
- *
- * Before using an object allocated from zs_malloc, it must be mapped using
- * this function. When done with the object, it must be unmapped using
- * zs_unmap_object.
- *
- * Only one object can be mapped per cpu at a time. There is no protection
- * against nested mappings.
- *
- * This function returns with preemption and page faults disabled.
-*/
-void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- enum zs_mapmode mm)
-{
- struct page *page;
- unsigned long obj_idx, off;
-
- unsigned int class_idx;
- enum fullness_group fg;
- struct size_class *class;
- struct mapping_area *area;
- struct page *pages[2];
-
- BUG_ON(!handle);
-
- /*
- * Because we use per-cpu mapping areas shared among the
- * pools/users, we can't allow mapping in interrupt context
- * because it can corrupt another users mappings.
- */
- BUG_ON(in_interrupt());
-
- obj_handle_to_location(handle, &page, &obj_idx);
- get_zspage_mapping(get_first_page(page), &class_idx, &fg);
- class = &pool->size_class[class_idx];
- off = obj_idx_to_offset(page, obj_idx, class->size);
-
- area = &get_cpu_var(zs_map_area);
- area->vm_mm = mm;
- if (off + class->size <= PAGE_SIZE) {
- /* this object is contained entirely within a page */
- area->vm_addr = kmap_atomic(page);
- return area->vm_addr + off;
- }
-
- /* this object spans two pages */
- pages[0] = page;
- pages[1] = get_next_page(page);
- BUG_ON(!pages[1]);
-
- return __zs_map_object(area, pages, off, class->size);
-}
-EXPORT_SYMBOL_GPL(zs_map_object);
-
-void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
-{
- struct page *page;
- unsigned long obj_idx, off;
-
- unsigned int class_idx;
- enum fullness_group fg;
- struct size_class *class;
- struct mapping_area *area;
-
- BUG_ON(!handle);
-
- obj_handle_to_location(handle, &page, &obj_idx);
- get_zspage_mapping(get_first_page(page), &class_idx, &fg);
- class = &pool->size_class[class_idx];
- off = obj_idx_to_offset(page, obj_idx, class->size);
-
- area = &__get_cpu_var(zs_map_area);
- if (off + class->size <= PAGE_SIZE)
- kunmap_atomic(area->vm_addr);
- else {
- struct page *pages[2];
-
- pages[0] = page;
- pages[1] = get_next_page(page);
- BUG_ON(!pages[1]);
-
- __zs_unmap_object(area, pages, off, class->size);
- }
- put_cpu_var(zs_map_area);
-}
-EXPORT_SYMBOL_GPL(zs_unmap_object);
-
-u64 zs_get_total_size_bytes(struct zs_pool *pool)
-{
- int i;
- u64 npages = 0;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++)
- npages += pool->size_class[i].pages_allocated;
-
- return npages << PAGE_SHIFT;
-}
-EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
-
-module_init(zs_init);
-module_exit(zs_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
diff --git a/drivers/switch/Kconfig b/drivers/switch/Kconfig
new file mode 100644
index 0000000..19404b6
--- /dev/null
+++ b/drivers/switch/Kconfig
@@ -0,0 +1,15 @@
+menuconfig SWITCH
+ tristate "Switch class support"
+ help
+ Say Y here to enable switch class support. This allows
+ monitoring switches by userspace via sysfs and uevent.
+
+if SWITCH
+
+config SWITCH_GPIO
+ tristate "GPIO Swith support"
+ depends on GPIOLIB
+ help
+ Say Y here to enable GPIO based switch support.
+
+endif # SWITCH
diff --git a/drivers/switch/Makefile b/drivers/switch/Makefile
new file mode 100644
index 0000000..f7606ed
--- /dev/null
+++ b/drivers/switch/Makefile
@@ -0,0 +1,4 @@
+# Switch Class Driver
+obj-$(CONFIG_SWITCH) += switch_class.o
+obj-$(CONFIG_SWITCH_GPIO) += switch_gpio.o
+
diff --git a/drivers/switch/switch_class.c b/drivers/switch/switch_class.c
new file mode 100644
index 0000000..e373b62
--- /dev/null
+++ b/drivers/switch/switch_class.c
@@ -0,0 +1,174 @@
+/*
+ * drivers/switch/switch_class.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/err.h>
+#include <linux/switch.h>
+
+struct class *switch_class;
+static atomic_t device_count;
+
+static ssize_t state_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct switch_dev *sdev = (struct switch_dev *)
+ dev_get_drvdata(dev);
+
+ if (sdev->print_state) {
+ int ret = sdev->print_state(sdev, buf);
+ if (ret >= 0)
+ return ret;
+ }
+ return sprintf(buf, "%d\n", sdev->state);
+}
+
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct switch_dev *sdev = (struct switch_dev *)
+ dev_get_drvdata(dev);
+
+ if (sdev->print_name) {
+ int ret = sdev->print_name(sdev, buf);
+ if (ret >= 0)
+ return ret;
+ }
+ return sprintf(buf, "%s\n", sdev->name);
+}
+
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+static DEVICE_ATTR(name, S_IRUGO, name_show, NULL);
+
+void switch_set_state(struct switch_dev *sdev, int state)
+{
+ char name_buf[120];
+ char state_buf[120];
+ char *prop_buf;
+ char *envp[3];
+ int env_offset = 0;
+ int length;
+
+ if (sdev->state != state) {
+ sdev->state = state;
+
+ prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
+ if (prop_buf) {
+ length = name_show(sdev->dev, NULL, prop_buf);
+ if (length > 0) {
+ if (prop_buf[length - 1] == '\n')
+ prop_buf[length - 1] = 0;
+ snprintf(name_buf, sizeof(name_buf),
+ "SWITCH_NAME=%s", prop_buf);
+ envp[env_offset++] = name_buf;
+ }
+ length = state_show(sdev->dev, NULL, prop_buf);
+ if (length > 0) {
+ if (prop_buf[length - 1] == '\n')
+ prop_buf[length - 1] = 0;
+ snprintf(state_buf, sizeof(state_buf),
+ "SWITCH_STATE=%s", prop_buf);
+ envp[env_offset++] = state_buf;
+ }
+ envp[env_offset] = NULL;
+ kobject_uevent_env(&sdev->dev->kobj, KOBJ_CHANGE, envp);
+ free_page((unsigned long)prop_buf);
+ } else {
+ printk(KERN_ERR "out of memory in switch_set_state\n");
+ kobject_uevent(&sdev->dev->kobj, KOBJ_CHANGE);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(switch_set_state);
+
+static int create_switch_class(void)
+{
+ if (!switch_class) {
+ switch_class = class_create(THIS_MODULE, "switch");
+ if (IS_ERR(switch_class))
+ return PTR_ERR(switch_class);
+ atomic_set(&device_count, 0);
+ }
+
+ return 0;
+}
+
+int switch_dev_register(struct switch_dev *sdev)
+{
+ int ret;
+
+ if (!switch_class) {
+ ret = create_switch_class();
+ if (ret < 0)
+ return ret;
+ }
+
+ sdev->index = atomic_inc_return(&device_count);
+ sdev->dev = device_create(switch_class, NULL,
+ MKDEV(0, sdev->index), NULL, sdev->name);
+ if (IS_ERR(sdev->dev))
+ return PTR_ERR(sdev->dev);
+
+ ret = device_create_file(sdev->dev, &dev_attr_state);
+ if (ret < 0)
+ goto err_create_file_1;
+ ret = device_create_file(sdev->dev, &dev_attr_name);
+ if (ret < 0)
+ goto err_create_file_2;
+
+ dev_set_drvdata(sdev->dev, sdev);
+ sdev->state = 0;
+ return 0;
+
+err_create_file_2:
+ device_remove_file(sdev->dev, &dev_attr_state);
+err_create_file_1:
+ device_destroy(switch_class, MKDEV(0, sdev->index));
+ printk(KERN_ERR "switch: Failed to register driver %s\n", sdev->name);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(switch_dev_register);
+
+void switch_dev_unregister(struct switch_dev *sdev)
+{
+ device_remove_file(sdev->dev, &dev_attr_name);
+ device_remove_file(sdev->dev, &dev_attr_state);
+ device_destroy(switch_class, MKDEV(0, sdev->index));
+ dev_set_drvdata(sdev->dev, NULL);
+}
+EXPORT_SYMBOL_GPL(switch_dev_unregister);
+
+static int __init switch_class_init(void)
+{
+ return create_switch_class();
+}
+
+static void __exit switch_class_exit(void)
+{
+ class_destroy(switch_class);
+}
+
+module_init(switch_class_init);
+module_exit(switch_class_exit);
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("Switch class driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/switch/switch_gpio.c b/drivers/switch/switch_gpio.c
new file mode 100644
index 0000000..621d62d
--- /dev/null
+++ b/drivers/switch/switch_gpio.c
@@ -0,0 +1,172 @@
+/*
+ * drivers/switch/switch_gpio.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/switch.h>
+#include <linux/workqueue.h>
+#include <linux/gpio.h>
+
+struct gpio_switch_data {
+ struct switch_dev sdev;
+ unsigned gpio;
+ const char *name_on;
+ const char *name_off;
+ const char *state_on;
+ const char *state_off;
+ int irq;
+ struct work_struct work;
+};
+
+static void gpio_switch_work(struct work_struct *work)
+{
+ int state;
+ struct gpio_switch_data *data =
+ container_of(work, struct gpio_switch_data, work);
+
+ state = gpio_get_value(data->gpio);
+ switch_set_state(&data->sdev, state);
+}
+
+static irqreturn_t gpio_irq_handler(int irq, void *dev_id)
+{
+ struct gpio_switch_data *switch_data =
+ (struct gpio_switch_data *)dev_id;
+
+ schedule_work(&switch_data->work);
+ return IRQ_HANDLED;
+}
+
+static ssize_t switch_gpio_print_state(struct switch_dev *sdev, char *buf)
+{
+ struct gpio_switch_data *switch_data =
+ container_of(sdev, struct gpio_switch_data, sdev);
+ const char *state;
+ if (switch_get_state(sdev))
+ state = switch_data->state_on;
+ else
+ state = switch_data->state_off;
+
+ if (state)
+ return sprintf(buf, "%s\n", state);
+ return -1;
+}
+
+static int gpio_switch_probe(struct platform_device *pdev)
+{
+ struct gpio_switch_platform_data *pdata = pdev->dev.platform_data;
+ struct gpio_switch_data *switch_data;
+ int ret = 0;
+
+ if (!pdata)
+ return -EBUSY;
+
+ switch_data = kzalloc(sizeof(struct gpio_switch_data), GFP_KERNEL);
+ if (!switch_data)
+ return -ENOMEM;
+
+ switch_data->sdev.name = pdata->name;
+ switch_data->gpio = pdata->gpio;
+ switch_data->name_on = pdata->name_on;
+ switch_data->name_off = pdata->name_off;
+ switch_data->state_on = pdata->state_on;
+ switch_data->state_off = pdata->state_off;
+ switch_data->sdev.print_state = switch_gpio_print_state;
+
+ ret = switch_dev_register(&switch_data->sdev);
+ if (ret < 0)
+ goto err_switch_dev_register;
+
+ ret = gpio_request(switch_data->gpio, pdev->name);
+ if (ret < 0)
+ goto err_request_gpio;
+
+ ret = gpio_direction_input(switch_data->gpio);
+ if (ret < 0)
+ goto err_set_gpio_input;
+
+ INIT_WORK(&switch_data->work, gpio_switch_work);
+
+ switch_data->irq = gpio_to_irq(switch_data->gpio);
+ if (switch_data->irq < 0) {
+ ret = switch_data->irq;
+ goto err_detect_irq_num_failed;
+ }
+
+ ret = request_irq(switch_data->irq, gpio_irq_handler,
+ IRQF_TRIGGER_LOW, pdev->name, switch_data);
+ if (ret < 0)
+ goto err_request_irq;
+
+ /* Perform initial detection */
+ gpio_switch_work(&switch_data->work);
+
+ return 0;
+
+err_request_irq:
+err_detect_irq_num_failed:
+err_set_gpio_input:
+ gpio_free(switch_data->gpio);
+err_request_gpio:
+ switch_dev_unregister(&switch_data->sdev);
+err_switch_dev_register:
+ kfree(switch_data);
+
+ return ret;
+}
+
+static int gpio_switch_remove(struct platform_device *pdev)
+{
+ struct gpio_switch_data *switch_data = platform_get_drvdata(pdev);
+
+ cancel_work_sync(&switch_data->work);
+ gpio_free(switch_data->gpio);
+ switch_dev_unregister(&switch_data->sdev);
+ kfree(switch_data);
+
+ return 0;
+}
+
+static struct platform_driver gpio_switch_driver = {
+ .probe = gpio_switch_probe,
+ .remove = gpio_switch_remove,
+ .driver = {
+ .name = "switch-gpio",
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init gpio_switch_init(void)
+{
+ return platform_driver_register(&gpio_switch_driver);
+}
+
+static void __exit gpio_switch_exit(void)
+{
+ platform_driver_unregister(&gpio_switch_driver);
+}
+
+module_init(gpio_switch_init);
+module_exit(gpio_switch_exit);
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("GPIO Switch driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1fabb22..57977ec 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -95,6 +95,9 @@
struct uart_state *state = tty->driver_data;
struct uart_port *port = state->uart_port;
+ if (port->ops->wake_peer)
+ port->ops->wake_peer(port);
+
if (!uart_circ_empty(&state->xmit) && state->xmit.buf &&
!tty->stopped && !tty->hw_stopped)
port->ops->start_tx(port);
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index f41aa0d..9de2eb2 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -818,6 +818,27 @@
For more information, see Documentation/usb/gadget_printer.txt
which includes sample code for accessing the device file.
+config USB_G_ANDROID
+ boolean "Android Composite Gadget"
+ depends on SND
+ select SND_PCM
+ select SND_RAWMIDI
+ select USB_F_ACM
+ select USB_LIBCOMPOSITE
+ select USB_U_SERIAL
+ help
+ The Android Composite Gadget supports multiple USB
+ functions: adb, acm, mass storage, mtp, accessory
+ and rndis.
+ Each function can be configured and enabled/disabled
+ dynamically from userspace through a sysfs interface.
+
+config USB_ANDROID_RNDIS_DWORD_ALIGNED
+ boolean "Use double word aligned"
+ depends on USB_G_ANDROID
+ help
+ Provides dword aligned for DMA controller.
+
if TTY
config USB_CDC_COMPOSITE
diff --git a/drivers/usb/gadget/Makefile b/drivers/usb/gadget/Makefile
index 6afd166..0ec50ae 100644
--- a/drivers/usb/gadget/Makefile
+++ b/drivers/usb/gadget/Makefile
@@ -65,6 +65,7 @@
g_webcam-y := webcam.o
g_ncm-y := ncm.o
g_acm_ms-y := acm_ms.o
+g_android-y := android.o
g_tcm_usb_gadget-y := tcm_usb_gadget.o
obj-$(CONFIG_USB_ZERO) += g_zero.o
@@ -84,4 +85,5 @@
obj-$(CONFIG_USB_G_WEBCAM) += g_webcam.o
obj-$(CONFIG_USB_G_NCM) += g_ncm.o
obj-$(CONFIG_USB_G_ACM_MS) += g_acm_ms.o
+obj-$(CONFIG_USB_G_ANDROID) += g_android.o
obj-$(CONFIG_USB_GADGET_TARGET) += tcm_usb_gadget.o
diff --git a/drivers/usb/gadget/android.c b/drivers/usb/gadget/android.c
new file mode 100644
index 0000000..61c5e58
--- /dev/null
+++ b/drivers/usb/gadget/android.c
@@ -0,0 +1,1587 @@
+/*
+ * Gadget Driver for Android
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ * Benoit Goby <benoit@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/utsname.h>
+#include <linux/platform_device.h>
+
+#include <linux/usb/ch9.h>
+#include <linux/usb/composite.h>
+#include <linux/usb/gadget.h>
+
+#include "gadget_chips.h"
+
+#include "f_fs.c"
+#include "f_audio_source.c"
+#include "f_midi.c"
+#include "f_mass_storage.c"
+#include "f_mtp.c"
+#include "f_accessory.c"
+#define USB_ETH_RNDIS y
+#include "f_rndis.c"
+#include "rndis.c"
+#include "u_ether.c"
+
+MODULE_AUTHOR("Mike Lockwood");
+MODULE_DESCRIPTION("Android Composite USB Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+
+static const char longname[] = "Gadget Android";
+
+/* Default vendor and product IDs, overridden by userspace */
+#define VENDOR_ID 0x18D1
+#define PRODUCT_ID 0x0001
+
+/* f_midi configuration */
+#define MIDI_INPUT_PORTS 1
+#define MIDI_OUTPUT_PORTS 1
+#define MIDI_BUFFER_SIZE 256
+#define MIDI_QUEUE_LENGTH 32
+
+struct android_usb_function {
+ char *name;
+ void *config;
+
+ struct device *dev;
+ char *dev_name;
+ struct device_attribute **attributes;
+
+ /* for android_dev.enabled_functions */
+ struct list_head enabled_list;
+
+ /* Optional: initialization during gadget bind */
+ int (*init)(struct android_usb_function *, struct usb_composite_dev *);
+ /* Optional: cleanup during gadget unbind */
+ void (*cleanup)(struct android_usb_function *);
+ /* Optional: called when the function is added the list of
+ * enabled functions */
+ void (*enable)(struct android_usb_function *);
+ /* Optional: called when it is removed */
+ void (*disable)(struct android_usb_function *);
+
+ int (*bind_config)(struct android_usb_function *,
+ struct usb_configuration *);
+
+ /* Optional: called when the configuration is removed */
+ void (*unbind_config)(struct android_usb_function *,
+ struct usb_configuration *);
+ /* Optional: handle ctrl requests before the device is configured */
+ int (*ctrlrequest)(struct android_usb_function *,
+ struct usb_composite_dev *,
+ const struct usb_ctrlrequest *);
+};
+
+struct android_dev {
+ struct android_usb_function **functions;
+ struct list_head enabled_functions;
+ struct usb_composite_dev *cdev;
+ struct device *dev;
+
+ void (*setup_complete)(struct usb_ep *ep,
+ struct usb_request *req);
+
+ bool enabled;
+ int disable_depth;
+ struct mutex mutex;
+ bool connected;
+ bool sw_connected;
+ struct work_struct work;
+ char ffs_aliases[256];
+};
+
+static struct class *android_class;
+static struct android_dev *_android_dev;
+static int android_bind_config(struct usb_configuration *c);
+static void android_unbind_config(struct usb_configuration *c);
+
+/* string IDs are assigned dynamically */
+#define STRING_MANUFACTURER_IDX 0
+#define STRING_PRODUCT_IDX 1
+#define STRING_SERIAL_IDX 2
+
+static char manufacturer_string[256];
+static char product_string[256];
+static char serial_string[256];
+
+/* String Table */
+static struct usb_string strings_dev[] = {
+ [STRING_MANUFACTURER_IDX].s = manufacturer_string,
+ [STRING_PRODUCT_IDX].s = product_string,
+ [STRING_SERIAL_IDX].s = serial_string,
+ { } /* end of list */
+};
+
+static struct usb_gadget_strings stringtab_dev = {
+ .language = 0x0409, /* en-us */
+ .strings = strings_dev,
+};
+
+static struct usb_gadget_strings *dev_strings[] = {
+ &stringtab_dev,
+ NULL,
+};
+
+static struct usb_device_descriptor device_desc = {
+ .bLength = sizeof(device_desc),
+ .bDescriptorType = USB_DT_DEVICE,
+ .bcdUSB = __constant_cpu_to_le16(0x0200),
+ .bDeviceClass = USB_CLASS_PER_INTERFACE,
+ .idVendor = __constant_cpu_to_le16(VENDOR_ID),
+ .idProduct = __constant_cpu_to_le16(PRODUCT_ID),
+ .bcdDevice = __constant_cpu_to_le16(0xffff),
+ .bNumConfigurations = 1,
+};
+
+static struct usb_configuration android_config_driver = {
+ .label = "android",
+ .unbind = android_unbind_config,
+ .bConfigurationValue = 1,
+ .bmAttributes = USB_CONFIG_ATT_ONE | USB_CONFIG_ATT_SELFPOWER,
+ .MaxPower = 500, /* 500ma */
+};
+
+static void android_work(struct work_struct *data)
+{
+ struct android_dev *dev = container_of(data, struct android_dev, work);
+ struct usb_composite_dev *cdev = dev->cdev;
+ char *disconnected[2] = { "USB_STATE=DISCONNECTED", NULL };
+ char *connected[2] = { "USB_STATE=CONNECTED", NULL };
+ char *configured[2] = { "USB_STATE=CONFIGURED", NULL };
+ char **uevent_envp = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (cdev->config)
+ uevent_envp = configured;
+ else if (dev->connected != dev->sw_connected)
+ uevent_envp = dev->connected ? connected : disconnected;
+ dev->sw_connected = dev->connected;
+ spin_unlock_irqrestore(&cdev->lock, flags);
+
+ if (uevent_envp) {
+ kobject_uevent_env(&dev->dev->kobj, KOBJ_CHANGE, uevent_envp);
+ pr_info("%s: sent uevent %s\n", __func__, uevent_envp[0]);
+ } else {
+ pr_info("%s: did not send uevent (%d %d %p)\n", __func__,
+ dev->connected, dev->sw_connected, cdev->config);
+ }
+}
+
+static void android_enable(struct android_dev *dev)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ if (WARN_ON(!dev->disable_depth))
+ return;
+
+ if (--dev->disable_depth == 0) {
+ usb_add_config(cdev, &android_config_driver,
+ android_bind_config);
+ usb_gadget_connect(cdev->gadget);
+ }
+}
+
+static void android_disable(struct android_dev *dev)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ if (dev->disable_depth++ == 0) {
+ usb_gadget_disconnect(cdev->gadget);
+ /* Cancel pending control requests */
+ usb_ep_dequeue(cdev->gadget->ep0, cdev->req);
+ usb_remove_config(cdev, &android_config_driver);
+ }
+}
+
+/*-------------------------------------------------------------------------*/
+/* Supported functions initialization */
+
+struct functionfs_config {
+ bool opened;
+ bool enabled;
+ struct ffs_data *data;
+};
+
+static int ffs_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ f->config = kzalloc(sizeof(struct functionfs_config), GFP_KERNEL);
+ if (!f->config)
+ return -ENOMEM;
+
+ return functionfs_init();
+}
+
+static void ffs_function_cleanup(struct android_usb_function *f)
+{
+ functionfs_cleanup();
+ kfree(f->config);
+}
+
+static void ffs_function_enable(struct android_usb_function *f)
+{
+ struct android_dev *dev = _android_dev;
+ struct functionfs_config *config = f->config;
+
+ config->enabled = true;
+
+ /* Disable the gadget until the function is ready */
+ if (!config->opened)
+ android_disable(dev);
+}
+
+static void ffs_function_disable(struct android_usb_function *f)
+{
+ struct android_dev *dev = _android_dev;
+ struct functionfs_config *config = f->config;
+
+ config->enabled = false;
+
+ /* Balance the disable that was called in closed_callback */
+ if (!config->opened)
+ android_enable(dev);
+}
+
+static int ffs_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct functionfs_config *config = f->config;
+ return functionfs_bind_config(c->cdev, c, config->data);
+}
+
+static ssize_t
+ffs_aliases_show(struct device *pdev, struct device_attribute *attr, char *buf)
+{
+ struct android_dev *dev = _android_dev;
+ int ret;
+
+ mutex_lock(&dev->mutex);
+ ret = sprintf(buf, "%s\n", dev->ffs_aliases);
+ mutex_unlock(&dev->mutex);
+
+ return ret;
+}
+
+static ssize_t
+ffs_aliases_store(struct device *pdev, struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ struct android_dev *dev = _android_dev;
+ char buff[256];
+
+ mutex_lock(&dev->mutex);
+
+ if (dev->enabled) {
+ mutex_unlock(&dev->mutex);
+ return -EBUSY;
+ }
+
+ strlcpy(buff, buf, sizeof(buff));
+ strlcpy(dev->ffs_aliases, strim(buff), sizeof(dev->ffs_aliases));
+
+ mutex_unlock(&dev->mutex);
+
+ return size;
+}
+
+static DEVICE_ATTR(aliases, S_IRUGO | S_IWUSR, ffs_aliases_show,
+ ffs_aliases_store);
+static struct device_attribute *ffs_function_attributes[] = {
+ &dev_attr_aliases,
+ NULL
+};
+
+static struct android_usb_function ffs_function = {
+ .name = "ffs",
+ .init = ffs_function_init,
+ .enable = ffs_function_enable,
+ .disable = ffs_function_disable,
+ .cleanup = ffs_function_cleanup,
+ .bind_config = ffs_function_bind_config,
+ .attributes = ffs_function_attributes,
+};
+
+static int functionfs_ready_callback(struct ffs_data *ffs)
+{
+ struct android_dev *dev = _android_dev;
+ struct functionfs_config *config = ffs_function.config;
+ int ret = 0;
+
+ mutex_lock(&dev->mutex);
+
+ ret = functionfs_bind(ffs, dev->cdev);
+ if (ret)
+ goto err;
+
+ config->data = ffs;
+ config->opened = true;
+
+ if (config->enabled)
+ android_enable(dev);
+
+err:
+ mutex_unlock(&dev->mutex);
+ return ret;
+}
+
+static void functionfs_closed_callback(struct ffs_data *ffs)
+{
+ struct android_dev *dev = _android_dev;
+ struct functionfs_config *config = ffs_function.config;
+
+ mutex_lock(&dev->mutex);
+
+ if (config->enabled)
+ android_disable(dev);
+
+ config->opened = false;
+ config->data = NULL;
+
+ functionfs_unbind(ffs);
+
+ mutex_unlock(&dev->mutex);
+}
+
+static void *functionfs_acquire_dev_callback(const char *dev_name)
+{
+ return 0;
+}
+
+static void functionfs_release_dev_callback(struct ffs_data *ffs_data)
+{
+}
+
+#define MAX_ACM_INSTANCES 4
+struct acm_function_config {
+ int instances;
+ int instances_on;
+ struct usb_function *f_acm[MAX_ACM_INSTANCES];
+ struct usb_function_instance *f_acm_inst[MAX_ACM_INSTANCES];
+};
+
+static int
+acm_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ int i;
+ int ret;
+ struct acm_function_config *config;
+
+ config = kzalloc(sizeof(struct acm_function_config), GFP_KERNEL);
+ if (!config)
+ return -ENOMEM;
+ f->config = config;
+
+ for (i = 0; i < MAX_ACM_INSTANCES; i++) {
+ config->f_acm_inst[i] = usb_get_function_instance("acm");
+ if (IS_ERR(config->f_acm_inst[i])) {
+ ret = PTR_ERR(config->f_acm_inst[i]);
+ goto err_usb_get_function_instance;
+ }
+ config->f_acm[i] = usb_get_function(config->f_acm_inst[i]);
+ if (IS_ERR(config->f_acm[i])) {
+ ret = PTR_ERR(config->f_acm[i]);
+ goto err_usb_get_function;
+ }
+ }
+ return 0;
+err_usb_get_function_instance:
+ while (i-- > 0) {
+ usb_put_function(config->f_acm[i]);
+err_usb_get_function:
+ usb_put_function_instance(config->f_acm_inst[i]);
+ }
+ return ret;
+}
+
+static void acm_function_cleanup(struct android_usb_function *f)
+{
+ int i;
+ struct acm_function_config *config = f->config;
+
+ for (i = 0; i < MAX_ACM_INSTANCES; i++) {
+ usb_put_function(config->f_acm[i]);
+ usb_put_function_instance(config->f_acm_inst[i]);
+ }
+ kfree(f->config);
+ f->config = NULL;
+}
+
+static int
+acm_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ int i;
+ int ret = 0;
+ struct acm_function_config *config = f->config;
+
+ config->instances_on = config->instances;
+ for (i = 0; i < config->instances_on; i++) {
+ ret = usb_add_function(c, config->f_acm[i]);
+ if (ret) {
+ pr_err("Could not bind acm%u config\n", i);
+ goto err_usb_add_function;
+ }
+ }
+
+ return 0;
+
+err_usb_add_function:
+ while (i-- > 0)
+ usb_remove_function(c, config->f_acm[i]);
+ return ret;
+}
+
+static void acm_function_unbind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ int i;
+ struct acm_function_config *config = f->config;
+
+ for (i = 0; i < config->instances_on; i++)
+ usb_remove_function(c, config->f_acm[i]);
+}
+
+static ssize_t acm_instances_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct acm_function_config *config = f->config;
+ return sprintf(buf, "%d\n", config->instances);
+}
+
+static ssize_t acm_instances_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct acm_function_config *config = f->config;
+ int value;
+
+ sscanf(buf, "%d", &value);
+ if (value > MAX_ACM_INSTANCES)
+ value = MAX_ACM_INSTANCES;
+ config->instances = value;
+ return size;
+}
+
+static DEVICE_ATTR(instances, S_IRUGO | S_IWUSR, acm_instances_show,
+ acm_instances_store);
+static struct device_attribute *acm_function_attributes[] = {
+ &dev_attr_instances,
+ NULL
+};
+
+static struct android_usb_function acm_function = {
+ .name = "acm",
+ .init = acm_function_init,
+ .cleanup = acm_function_cleanup,
+ .bind_config = acm_function_bind_config,
+ .unbind_config = acm_function_unbind_config,
+ .attributes = acm_function_attributes,
+};
+
+
+static int
+mtp_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ return mtp_setup();
+}
+
+static void mtp_function_cleanup(struct android_usb_function *f)
+{
+ mtp_cleanup();
+}
+
+static int
+mtp_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ return mtp_bind_config(c, false);
+}
+
+static int
+ptp_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ /* nothing to do - initialization is handled by mtp_function_init */
+ return 0;
+}
+
+static void ptp_function_cleanup(struct android_usb_function *f)
+{
+ /* nothing to do - cleanup is handled by mtp_function_cleanup */
+}
+
+static int
+ptp_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ return mtp_bind_config(c, true);
+}
+
+static int mtp_function_ctrlrequest(struct android_usb_function *f,
+ struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *c)
+{
+ return mtp_ctrlrequest(cdev, c);
+}
+
+static struct android_usb_function mtp_function = {
+ .name = "mtp",
+ .init = mtp_function_init,
+ .cleanup = mtp_function_cleanup,
+ .bind_config = mtp_function_bind_config,
+ .ctrlrequest = mtp_function_ctrlrequest,
+};
+
+/* PTP function is same as MTP with slightly different interface descriptor */
+static struct android_usb_function ptp_function = {
+ .name = "ptp",
+ .init = ptp_function_init,
+ .cleanup = ptp_function_cleanup,
+ .bind_config = ptp_function_bind_config,
+};
+
+
+struct rndis_function_config {
+ u8 ethaddr[ETH_ALEN];
+ u32 vendorID;
+ char manufacturer[256];
+ /* "Wireless" RNDIS; auto-detected by Windows */
+ bool wceis;
+ struct eth_dev *dev;
+};
+
+static int
+rndis_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ f->config = kzalloc(sizeof(struct rndis_function_config), GFP_KERNEL);
+ if (!f->config)
+ return -ENOMEM;
+ return 0;
+}
+
+static void rndis_function_cleanup(struct android_usb_function *f)
+{
+ kfree(f->config);
+ f->config = NULL;
+}
+
+static int
+rndis_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ int ret;
+ struct eth_dev *dev;
+ struct rndis_function_config *rndis = f->config;
+
+ if (!rndis) {
+ pr_err("%s: rndis_pdata\n", __func__);
+ return -1;
+ }
+
+ pr_info("%s MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", __func__,
+ rndis->ethaddr[0], rndis->ethaddr[1], rndis->ethaddr[2],
+ rndis->ethaddr[3], rndis->ethaddr[4], rndis->ethaddr[5]);
+
+ dev = gether_setup_name(c->cdev->gadget, rndis->ethaddr, "rndis");
+ if (IS_ERR(dev)) {
+ ret = PTR_ERR(dev);
+ pr_err("%s: gether_setup failed\n", __func__);
+ return ret;
+ }
+ rndis->dev = dev;
+
+ if (rndis->wceis) {
+ /* "Wireless" RNDIS; auto-detected by Windows */
+ rndis_iad_descriptor.bFunctionClass =
+ USB_CLASS_WIRELESS_CONTROLLER;
+ rndis_iad_descriptor.bFunctionSubClass = 0x01;
+ rndis_iad_descriptor.bFunctionProtocol = 0x03;
+ rndis_control_intf.bInterfaceClass =
+ USB_CLASS_WIRELESS_CONTROLLER;
+ rndis_control_intf.bInterfaceSubClass = 0x01;
+ rndis_control_intf.bInterfaceProtocol = 0x03;
+ }
+
+ return rndis_bind_config_vendor(c, rndis->ethaddr, rndis->vendorID,
+ rndis->manufacturer, rndis->dev);
+}
+
+static void rndis_function_unbind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct rndis_function_config *rndis = f->config;
+ gether_cleanup(rndis->dev);
+}
+
+static ssize_t rndis_manufacturer_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+ return sprintf(buf, "%s\n", config->manufacturer);
+}
+
+static ssize_t rndis_manufacturer_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+
+ if (size >= sizeof(config->manufacturer))
+ return -EINVAL;
+ if (sscanf(buf, "%s", config->manufacturer) == 1)
+ return size;
+ return -1;
+}
+
+static DEVICE_ATTR(manufacturer, S_IRUGO | S_IWUSR, rndis_manufacturer_show,
+ rndis_manufacturer_store);
+
+static ssize_t rndis_wceis_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+ return sprintf(buf, "%d\n", config->wceis);
+}
+
+static ssize_t rndis_wceis_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+ int value;
+
+ if (sscanf(buf, "%d", &value) == 1) {
+ config->wceis = value;
+ return size;
+ }
+ return -EINVAL;
+}
+
+static DEVICE_ATTR(wceis, S_IRUGO | S_IWUSR, rndis_wceis_show,
+ rndis_wceis_store);
+
+static ssize_t rndis_ethaddr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *rndis = f->config;
+ return sprintf(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n",
+ rndis->ethaddr[0], rndis->ethaddr[1], rndis->ethaddr[2],
+ rndis->ethaddr[3], rndis->ethaddr[4], rndis->ethaddr[5]);
+}
+
+static ssize_t rndis_ethaddr_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *rndis = f->config;
+
+ if (sscanf(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n",
+ (int *)&rndis->ethaddr[0], (int *)&rndis->ethaddr[1],
+ (int *)&rndis->ethaddr[2], (int *)&rndis->ethaddr[3],
+ (int *)&rndis->ethaddr[4], (int *)&rndis->ethaddr[5]) == 6)
+ return size;
+ return -EINVAL;
+}
+
+static DEVICE_ATTR(ethaddr, S_IRUGO | S_IWUSR, rndis_ethaddr_show,
+ rndis_ethaddr_store);
+
+static ssize_t rndis_vendorID_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+ return sprintf(buf, "%04x\n", config->vendorID);
+}
+
+static ssize_t rndis_vendorID_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct rndis_function_config *config = f->config;
+ int value;
+
+ if (sscanf(buf, "%04x", &value) == 1) {
+ config->vendorID = value;
+ return size;
+ }
+ return -EINVAL;
+}
+
+static DEVICE_ATTR(vendorID, S_IRUGO | S_IWUSR, rndis_vendorID_show,
+ rndis_vendorID_store);
+
+static struct device_attribute *rndis_function_attributes[] = {
+ &dev_attr_manufacturer,
+ &dev_attr_wceis,
+ &dev_attr_ethaddr,
+ &dev_attr_vendorID,
+ NULL
+};
+
+static struct android_usb_function rndis_function = {
+ .name = "rndis",
+ .init = rndis_function_init,
+ .cleanup = rndis_function_cleanup,
+ .bind_config = rndis_function_bind_config,
+ .unbind_config = rndis_function_unbind_config,
+ .attributes = rndis_function_attributes,
+};
+
+
+struct mass_storage_function_config {
+ struct fsg_config fsg;
+ struct fsg_common *common;
+};
+
+static int mass_storage_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ struct mass_storage_function_config *config;
+ struct fsg_common *common;
+ int err;
+
+ config = kzalloc(sizeof(struct mass_storage_function_config),
+ GFP_KERNEL);
+ if (!config)
+ return -ENOMEM;
+
+ config->fsg.nluns = 1;
+ config->fsg.luns[0].removable = 1;
+
+ common = fsg_common_init(NULL, cdev, &config->fsg);
+ if (IS_ERR(common)) {
+ kfree(config);
+ return PTR_ERR(common);
+ }
+
+ err = sysfs_create_link(&f->dev->kobj,
+ &common->luns[0].dev.kobj,
+ "lun");
+ if (err) {
+ kfree(config);
+ return err;
+ }
+
+ config->common = common;
+ f->config = config;
+ return 0;
+}
+
+static void mass_storage_function_cleanup(struct android_usb_function *f)
+{
+ kfree(f->config);
+ f->config = NULL;
+}
+
+static int mass_storage_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct mass_storage_function_config *config = f->config;
+ return fsg_bind_config(c->cdev, c, config->common);
+}
+
+static ssize_t mass_storage_inquiry_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct mass_storage_function_config *config = f->config;
+ return sprintf(buf, "%s\n", config->common->inquiry_string);
+}
+
+static ssize_t mass_storage_inquiry_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct mass_storage_function_config *config = f->config;
+ if (size >= sizeof(config->common->inquiry_string))
+ return -EINVAL;
+ if (sscanf(buf, "%s", config->common->inquiry_string) != 1)
+ return -EINVAL;
+ return size;
+}
+
+static DEVICE_ATTR(inquiry_string, S_IRUGO | S_IWUSR,
+ mass_storage_inquiry_show,
+ mass_storage_inquiry_store);
+
+static struct device_attribute *mass_storage_function_attributes[] = {
+ &dev_attr_inquiry_string,
+ NULL
+};
+
+static struct android_usb_function mass_storage_function = {
+ .name = "mass_storage",
+ .init = mass_storage_function_init,
+ .cleanup = mass_storage_function_cleanup,
+ .bind_config = mass_storage_function_bind_config,
+ .attributes = mass_storage_function_attributes,
+};
+
+
+static int accessory_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ return acc_setup();
+}
+
+static void accessory_function_cleanup(struct android_usb_function *f)
+{
+ acc_cleanup();
+}
+
+static int accessory_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ return acc_bind_config(c);
+}
+
+static int accessory_function_ctrlrequest(struct android_usb_function *f,
+ struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *c)
+{
+ return acc_ctrlrequest(cdev, c);
+}
+
+static struct android_usb_function accessory_function = {
+ .name = "accessory",
+ .init = accessory_function_init,
+ .cleanup = accessory_function_cleanup,
+ .bind_config = accessory_function_bind_config,
+ .ctrlrequest = accessory_function_ctrlrequest,
+};
+
+static int audio_source_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ struct audio_source_config *config;
+
+ config = kzalloc(sizeof(struct audio_source_config), GFP_KERNEL);
+ if (!config)
+ return -ENOMEM;
+ config->card = -1;
+ config->device = -1;
+ f->config = config;
+ return 0;
+}
+
+static void audio_source_function_cleanup(struct android_usb_function *f)
+{
+ kfree(f->config);
+}
+
+static int audio_source_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct audio_source_config *config = f->config;
+
+ return audio_source_bind_config(c, config);
+}
+
+static void audio_source_function_unbind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct audio_source_config *config = f->config;
+
+ config->card = -1;
+ config->device = -1;
+}
+
+static ssize_t audio_source_pcm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct audio_source_config *config = f->config;
+
+ /* print PCM card and device numbers */
+ return sprintf(buf, "%d %d\n", config->card, config->device);
+}
+
+static DEVICE_ATTR(pcm, S_IRUGO, audio_source_pcm_show, NULL);
+
+static struct device_attribute *audio_source_function_attributes[] = {
+ &dev_attr_pcm,
+ NULL
+};
+
+static struct android_usb_function audio_source_function = {
+ .name = "audio_source",
+ .init = audio_source_function_init,
+ .cleanup = audio_source_function_cleanup,
+ .bind_config = audio_source_function_bind_config,
+ .unbind_config = audio_source_function_unbind_config,
+ .attributes = audio_source_function_attributes,
+};
+
+static int midi_function_init(struct android_usb_function *f,
+ struct usb_composite_dev *cdev)
+{
+ struct midi_alsa_config *config;
+
+ config = kzalloc(sizeof(struct midi_alsa_config), GFP_KERNEL);
+ f->config = config;
+ if (!config)
+ return -ENOMEM;
+ config->card = -1;
+ config->device = -1;
+ return 0;
+}
+
+static void midi_function_cleanup(struct android_usb_function *f)
+{
+ kfree(f->config);
+}
+
+static int midi_function_bind_config(struct android_usb_function *f,
+ struct usb_configuration *c)
+{
+ struct midi_alsa_config *config = f->config;
+
+ return f_midi_bind_config(c, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
+ MIDI_INPUT_PORTS, MIDI_OUTPUT_PORTS, MIDI_BUFFER_SIZE,
+ MIDI_QUEUE_LENGTH, config);
+}
+
+static ssize_t midi_alsa_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct android_usb_function *f = dev_get_drvdata(dev);
+ struct midi_alsa_config *config = f->config;
+
+ /* print ALSA card and device numbers */
+ return sprintf(buf, "%d %d\n", config->card, config->device);
+}
+
+static DEVICE_ATTR(alsa, S_IRUGO, midi_alsa_show, NULL);
+
+static struct device_attribute *midi_function_attributes[] = {
+ &dev_attr_alsa,
+ NULL
+};
+
+static struct android_usb_function midi_function = {
+ .name = "midi",
+ .init = midi_function_init,
+ .cleanup = midi_function_cleanup,
+ .bind_config = midi_function_bind_config,
+ .attributes = midi_function_attributes,
+};
+
+static struct android_usb_function *supported_functions[] = {
+ &ffs_function,
+ &acm_function,
+ &mtp_function,
+ &ptp_function,
+ &rndis_function,
+ &mass_storage_function,
+ &accessory_function,
+ &audio_source_function,
+ &midi_function,
+ NULL
+};
+
+static int android_init_functions(struct android_usb_function **functions,
+ struct usb_composite_dev *cdev)
+{
+ struct android_dev *dev = _android_dev;
+ struct android_usb_function *f;
+ struct device_attribute **attrs;
+ struct device_attribute *attr;
+ int err;
+ int index = 0;
+
+ for (; (f = *functions++); index++) {
+ f->dev_name = kasprintf(GFP_KERNEL, "f_%s", f->name);
+ f->dev = device_create(android_class, dev->dev,
+ MKDEV(0, index), f, f->dev_name);
+ if (IS_ERR(f->dev)) {
+ pr_err("%s: Failed to create dev %s", __func__,
+ f->dev_name);
+ err = PTR_ERR(f->dev);
+ goto err_create;
+ }
+
+ if (f->init) {
+ err = f->init(f, cdev);
+ if (err) {
+ pr_err("%s: Failed to init %s", __func__,
+ f->name);
+ goto err_out;
+ }
+ }
+
+ attrs = f->attributes;
+ if (attrs) {
+ while ((attr = *attrs++) && !err)
+ err = device_create_file(f->dev, attr);
+ }
+ if (err) {
+ pr_err("%s: Failed to create function %s attributes",
+ __func__, f->name);
+ goto err_out;
+ }
+ }
+ return 0;
+
+err_out:
+ device_destroy(android_class, f->dev->devt);
+err_create:
+ kfree(f->dev_name);
+ return err;
+}
+
+static void android_cleanup_functions(struct android_usb_function **functions)
+{
+ struct android_usb_function *f;
+
+ while (*functions) {
+ f = *functions++;
+
+ if (f->dev) {
+ device_destroy(android_class, f->dev->devt);
+ kfree(f->dev_name);
+ }
+
+ if (f->cleanup)
+ f->cleanup(f);
+ }
+}
+
+static int
+android_bind_enabled_functions(struct android_dev *dev,
+ struct usb_configuration *c)
+{
+ struct android_usb_function *f;
+ int ret;
+
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+ ret = f->bind_config(f, c);
+ if (ret) {
+ pr_err("%s: %s failed", __func__, f->name);
+ return ret;
+ }
+ }
+ return 0;
+}
+
+static void
+android_unbind_enabled_functions(struct android_dev *dev,
+ struct usb_configuration *c)
+{
+ struct android_usb_function *f;
+
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+ if (f->unbind_config)
+ f->unbind_config(f, c);
+ }
+}
+
+static int android_enable_function(struct android_dev *dev, char *name)
+{
+ struct android_usb_function **functions = dev->functions;
+ struct android_usb_function *f;
+ while ((f = *functions++)) {
+ if (!strcmp(name, f->name)) {
+ list_add_tail(&f->enabled_list,
+ &dev->enabled_functions);
+ return 0;
+ }
+ }
+ return -EINVAL;
+}
+
+/*-------------------------------------------------------------------------*/
+/* /sys/class/android_usb/android%d/ interface */
+
+static ssize_t
+functions_show(struct device *pdev, struct device_attribute *attr, char *buf)
+{
+ struct android_dev *dev = dev_get_drvdata(pdev);
+ struct android_usb_function *f;
+ char *buff = buf;
+
+ mutex_lock(&dev->mutex);
+
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list)
+ buff += sprintf(buff, "%s,", f->name);
+
+ mutex_unlock(&dev->mutex);
+
+ if (buff != buf)
+ *(buff-1) = '\n';
+ return buff - buf;
+}
+
+static ssize_t
+functions_store(struct device *pdev, struct device_attribute *attr,
+ const char *buff, size_t size)
+{
+ struct android_dev *dev = dev_get_drvdata(pdev);
+ char *name;
+ char buf[256], *b;
+ char aliases[256], *a;
+ int err;
+ int is_ffs;
+ int ffs_enabled = 0;
+
+ mutex_lock(&dev->mutex);
+
+ if (dev->enabled) {
+ mutex_unlock(&dev->mutex);
+ return -EBUSY;
+ }
+
+ INIT_LIST_HEAD(&dev->enabled_functions);
+
+ strlcpy(buf, buff, sizeof(buf));
+ b = strim(buf);
+
+ while (b) {
+ name = strsep(&b, ",");
+ if (!name)
+ continue;
+
+ is_ffs = 0;
+ strlcpy(aliases, dev->ffs_aliases, sizeof(aliases));
+ a = aliases;
+
+ while (a) {
+ char *alias = strsep(&a, ",");
+ if (alias && !strcmp(name, alias)) {
+ is_ffs = 1;
+ break;
+ }
+ }
+
+ if (is_ffs) {
+ if (ffs_enabled)
+ continue;
+ err = android_enable_function(dev, "ffs");
+ if (err)
+ pr_err("android_usb: Cannot enable ffs (%d)",
+ err);
+ else
+ ffs_enabled = 1;
+ continue;
+ }
+
+ err = android_enable_function(dev, name);
+ if (err)
+ pr_err("android_usb: Cannot enable '%s' (%d)",
+ name, err);
+ }
+
+ mutex_unlock(&dev->mutex);
+
+ return size;
+}
+
+static ssize_t enable_show(struct device *pdev, struct device_attribute *attr,
+ char *buf)
+{
+ struct android_dev *dev = dev_get_drvdata(pdev);
+ return sprintf(buf, "%d\n", dev->enabled);
+}
+
+static ssize_t enable_store(struct device *pdev, struct device_attribute *attr,
+ const char *buff, size_t size)
+{
+ struct android_dev *dev = dev_get_drvdata(pdev);
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct android_usb_function *f;
+ int enabled = 0;
+
+
+ if (!cdev)
+ return -ENODEV;
+
+ mutex_lock(&dev->mutex);
+
+ sscanf(buff, "%d", &enabled);
+ if (enabled && !dev->enabled) {
+ /*
+ * Update values in composite driver's copy of
+ * device descriptor.
+ */
+ cdev->desc.idVendor = device_desc.idVendor;
+ cdev->desc.idProduct = device_desc.idProduct;
+ cdev->desc.bcdDevice = device_desc.bcdDevice;
+ cdev->desc.bDeviceClass = device_desc.bDeviceClass;
+ cdev->desc.bDeviceSubClass = device_desc.bDeviceSubClass;
+ cdev->desc.bDeviceProtocol = device_desc.bDeviceProtocol;
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+ if (f->enable)
+ f->enable(f);
+ }
+ android_enable(dev);
+ dev->enabled = true;
+ } else if (!enabled && dev->enabled) {
+ android_disable(dev);
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+ if (f->disable)
+ f->disable(f);
+ }
+ dev->enabled = false;
+ } else {
+ pr_err("android_usb: already %s\n",
+ dev->enabled ? "enabled" : "disabled");
+ }
+
+ mutex_unlock(&dev->mutex);
+ return size;
+}
+
+static ssize_t state_show(struct device *pdev, struct device_attribute *attr,
+ char *buf)
+{
+ struct android_dev *dev = dev_get_drvdata(pdev);
+ struct usb_composite_dev *cdev = dev->cdev;
+ char *state = "DISCONNECTED";
+ unsigned long flags;
+
+ if (!cdev)
+ goto out;
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (cdev->config)
+ state = "CONFIGURED";
+ else if (dev->connected)
+ state = "CONNECTED";
+ spin_unlock_irqrestore(&cdev->lock, flags);
+out:
+ return sprintf(buf, "%s\n", state);
+}
+
+#define DESCRIPTOR_ATTR(field, format_string) \
+static ssize_t \
+field ## _show(struct device *dev, struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return sprintf(buf, format_string, device_desc.field); \
+} \
+static ssize_t \
+field ## _store(struct device *dev, struct device_attribute *attr, \
+ const char *buf, size_t size) \
+{ \
+ int value; \
+ if (sscanf(buf, format_string, &value) == 1) { \
+ device_desc.field = value; \
+ return size; \
+ } \
+ return -1; \
+} \
+static DEVICE_ATTR(field, S_IRUGO | S_IWUSR, field ## _show, field ## _store);
+
+#define DESCRIPTOR_STRING_ATTR(field, buffer) \
+static ssize_t \
+field ## _show(struct device *dev, struct device_attribute *attr, \
+ char *buf) \
+{ \
+ return sprintf(buf, "%s", buffer); \
+} \
+static ssize_t \
+field ## _store(struct device *dev, struct device_attribute *attr, \
+ const char *buf, size_t size) \
+{ \
+ if (size >= sizeof(buffer)) \
+ return -EINVAL; \
+ return strlcpy(buffer, buf, sizeof(buffer)); \
+} \
+static DEVICE_ATTR(field, S_IRUGO | S_IWUSR, field ## _show, field ## _store);
+
+
+DESCRIPTOR_ATTR(idVendor, "%04x\n")
+DESCRIPTOR_ATTR(idProduct, "%04x\n")
+DESCRIPTOR_ATTR(bcdDevice, "%04x\n")
+DESCRIPTOR_ATTR(bDeviceClass, "%d\n")
+DESCRIPTOR_ATTR(bDeviceSubClass, "%d\n")
+DESCRIPTOR_ATTR(bDeviceProtocol, "%d\n")
+DESCRIPTOR_STRING_ATTR(iManufacturer, manufacturer_string)
+DESCRIPTOR_STRING_ATTR(iProduct, product_string)
+DESCRIPTOR_STRING_ATTR(iSerial, serial_string)
+
+static DEVICE_ATTR(functions, S_IRUGO | S_IWUSR, functions_show,
+ functions_store);
+static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR, enable_show, enable_store);
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+
+static struct device_attribute *android_usb_attributes[] = {
+ &dev_attr_idVendor,
+ &dev_attr_idProduct,
+ &dev_attr_bcdDevice,
+ &dev_attr_bDeviceClass,
+ &dev_attr_bDeviceSubClass,
+ &dev_attr_bDeviceProtocol,
+ &dev_attr_iManufacturer,
+ &dev_attr_iProduct,
+ &dev_attr_iSerial,
+ &dev_attr_functions,
+ &dev_attr_enable,
+ &dev_attr_state,
+ NULL
+};
+
+/*-------------------------------------------------------------------------*/
+/* Composite driver */
+
+static int android_bind_config(struct usb_configuration *c)
+{
+ struct android_dev *dev = _android_dev;
+ int ret = 0;
+
+ ret = android_bind_enabled_functions(dev, c);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void android_unbind_config(struct usb_configuration *c)
+{
+ struct android_dev *dev = _android_dev;
+
+ android_unbind_enabled_functions(dev, c);
+}
+
+static int android_bind(struct usb_composite_dev *cdev)
+{
+ struct android_dev *dev = _android_dev;
+ struct usb_gadget *gadget = cdev->gadget;
+ int id, ret;
+
+ /* Save the default handler */
+ dev->setup_complete = cdev->req->complete;
+
+ /*
+ * Start disconnected. Userspace will connect the gadget once
+ * it is done configuring the functions.
+ */
+ usb_gadget_disconnect(gadget);
+
+ ret = android_init_functions(dev->functions, cdev);
+ if (ret)
+ return ret;
+
+ /* Allocate string descriptor numbers ... note that string
+ * contents can be overridden by the composite_dev glue.
+ */
+ id = usb_string_id(cdev);
+ if (id < 0)
+ return id;
+ strings_dev[STRING_MANUFACTURER_IDX].id = id;
+ device_desc.iManufacturer = id;
+
+ id = usb_string_id(cdev);
+ if (id < 0)
+ return id;
+ strings_dev[STRING_PRODUCT_IDX].id = id;
+ device_desc.iProduct = id;
+
+ /* Default strings - should be updated by userspace */
+ strncpy(manufacturer_string, "Android", sizeof(manufacturer_string)-1);
+ strncpy(product_string, "Android", sizeof(product_string) - 1);
+ strncpy(serial_string, "0123456789ABCDEF", sizeof(serial_string) - 1);
+
+ id = usb_string_id(cdev);
+ if (id < 0)
+ return id;
+ strings_dev[STRING_SERIAL_IDX].id = id;
+ device_desc.iSerialNumber = id;
+
+ usb_gadget_set_selfpowered(gadget);
+ dev->cdev = cdev;
+
+ return 0;
+}
+
+static int android_usb_unbind(struct usb_composite_dev *cdev)
+{
+ struct android_dev *dev = _android_dev;
+
+ cancel_work_sync(&dev->work);
+ android_cleanup_functions(dev->functions);
+ return 0;
+}
+
+/* HACK: android needs to override setup for accessory to work */
+static int (*composite_setup_func)(struct usb_gadget *gadget, const struct usb_ctrlrequest *c);
+
+static int
+android_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *c)
+{
+ struct android_dev *dev = _android_dev;
+ struct usb_composite_dev *cdev = get_gadget_data(gadget);
+ struct usb_request *req = cdev->req;
+ struct android_usb_function *f;
+ int value = -EOPNOTSUPP;
+ unsigned long flags;
+
+ req->zero = 0;
+ req->length = 0;
+ req->complete = dev->setup_complete;
+ gadget->ep0->driver_data = cdev;
+
+ list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+ if (f->ctrlrequest) {
+ value = f->ctrlrequest(f, cdev, c);
+ if (value >= 0)
+ break;
+ }
+ }
+
+ /* Special case the accessory function.
+ * It needs to handle control requests before it is enabled.
+ */
+ if (value < 0)
+ value = acc_ctrlrequest(cdev, c);
+
+ if (value < 0)
+ value = composite_setup_func(gadget, c);
+
+ spin_lock_irqsave(&cdev->lock, flags);
+ if (!dev->connected) {
+ dev->connected = 1;
+ schedule_work(&dev->work);
+ } else if (c->bRequest == USB_REQ_SET_CONFIGURATION &&
+ cdev->config) {
+ schedule_work(&dev->work);
+ }
+ spin_unlock_irqrestore(&cdev->lock, flags);
+
+ return value;
+}
+
+static void android_disconnect(struct usb_composite_dev *cdev)
+{
+ struct android_dev *dev = _android_dev;
+
+ /* accessory HID support can be active while the
+ accessory function is not actually enabled,
+ so we need to inform it when we are disconnected.
+ */
+ acc_disconnect();
+
+ dev->connected = 0;
+ schedule_work(&dev->work);
+}
+
+static struct usb_composite_driver android_usb_driver = {
+ .name = "android_usb",
+ .dev = &device_desc,
+ .strings = dev_strings,
+ .bind = android_bind,
+ .unbind = android_usb_unbind,
+ .disconnect = android_disconnect,
+ .max_speed = USB_SPEED_HIGH,
+};
+
+static int android_create_device(struct android_dev *dev)
+{
+ struct device_attribute **attrs = android_usb_attributes;
+ struct device_attribute *attr;
+ int err;
+
+ dev->dev = device_create(android_class, NULL,
+ MKDEV(0, 0), NULL, "android0");
+ if (IS_ERR(dev->dev))
+ return PTR_ERR(dev->dev);
+
+ dev_set_drvdata(dev->dev, dev);
+
+ while ((attr = *attrs++)) {
+ err = device_create_file(dev->dev, attr);
+ if (err) {
+ device_destroy(android_class, dev->dev->devt);
+ return err;
+ }
+ }
+ return 0;
+}
+
+
+static int __init init(void)
+{
+ struct android_dev *dev;
+ int err;
+
+ android_class = class_create(THIS_MODULE, "android_usb");
+ if (IS_ERR(android_class))
+ return PTR_ERR(android_class);
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev) {
+ err = -ENOMEM;
+ goto err_dev;
+ }
+
+ dev->disable_depth = 1;
+ dev->functions = supported_functions;
+ INIT_LIST_HEAD(&dev->enabled_functions);
+ INIT_WORK(&dev->work, android_work);
+ mutex_init(&dev->mutex);
+
+ err = android_create_device(dev);
+ if (err) {
+ pr_err("%s: failed to create android device %d", __func__, err);
+ goto err_create;
+ }
+
+ _android_dev = dev;
+
+ err = usb_composite_probe(&android_usb_driver);
+ if (err) {
+ pr_err("%s: failed to probe driver %d", __func__, err);
+ goto err_probe;
+ }
+
+ /* HACK: exchange composite's setup with ours */
+ composite_setup_func = android_usb_driver.gadget_driver.setup;
+ android_usb_driver.gadget_driver.setup = android_setup;
+
+ return 0;
+
+err_probe:
+ device_destroy(android_class, dev->dev->devt);
+err_create:
+ kfree(dev);
+err_dev:
+ class_destroy(android_class);
+ return err;
+}
+late_initcall(init);
+
+static void __exit cleanup(void)
+{
+ usb_composite_unregister(&android_usb_driver);
+ class_destroy(android_class);
+ kfree(_android_dev);
+ _android_dev = NULL;
+}
+module_exit(cleanup);
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index a660716..6a87860 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -812,7 +812,7 @@
}
EXPORT_SYMBOL_GPL(usb_add_config);
-static void remove_config(struct usb_composite_dev *cdev,
+static void unbind_config(struct usb_composite_dev *cdev,
struct usb_configuration *config)
{
while (!list_empty(&config->functions)) {
@@ -827,7 +827,6 @@
/* may free memory for "f" */
}
}
- list_del(&config->list);
if (config->unbind) {
DBG(cdev, "unbind config '%s'/%p\n", config->label, config);
config->unbind(config);
@@ -854,9 +853,11 @@
if (cdev->config == config)
reset_config(cdev);
+ list_del(&config->list);
+
spin_unlock_irqrestore(&cdev->lock, flags);
- remove_config(cdev, config);
+ unbind_config(cdev, config);
}
/*-------------------------------------------------------------------------*/
@@ -1525,7 +1526,8 @@
struct usb_configuration *c;
c = list_first_entry(&cdev->configs,
struct usb_configuration, list);
- remove_config(cdev, c);
+ list_del(&c->list);
+ unbind_config(cdev, c);
}
if (cdev->driver->unbind && unbind_driver)
cdev->driver->unbind(cdev);
diff --git a/drivers/usb/gadget/f_accessory.c b/drivers/usb/gadget/f_accessory.c
new file mode 100644
index 0000000..97f1a2f
--- /dev/null
+++ b/drivers/usb/gadget/f_accessory.c
@@ -0,0 +1,1206 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/hid.h>
+#include <linux/hiddev.h>
+#include <linux/usb.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_accessory.h>
+
+#define BULK_BUFFER_SIZE 16384
+#define ACC_STRING_SIZE 256
+
+#define PROTOCOL_VERSION 2
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX 0
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+
+struct acc_hid_dev {
+ struct list_head list;
+ struct hid_device *hid;
+ struct acc_dev *dev;
+ /* accessory defined ID */
+ int id;
+ /* HID report descriptor */
+ u8 *report_desc;
+ /* length of HID report descriptor */
+ int report_desc_len;
+ /* number of bytes of report_desc we have received so far */
+ int report_desc_offset;
+};
+
+struct acc_dev {
+ struct usb_function function;
+ struct usb_composite_dev *cdev;
+ spinlock_t lock;
+
+ struct usb_ep *ep_in;
+ struct usb_ep *ep_out;
+
+ /* set to 1 when we connect */
+ int online:1;
+ /* Set to 1 when we disconnect.
+ * Not cleared until our file is closed.
+ */
+ int disconnected:1;
+
+ /* strings sent by the host */
+ char manufacturer[ACC_STRING_SIZE];
+ char model[ACC_STRING_SIZE];
+ char description[ACC_STRING_SIZE];
+ char version[ACC_STRING_SIZE];
+ char uri[ACC_STRING_SIZE];
+ char serial[ACC_STRING_SIZE];
+
+ /* for acc_complete_set_string */
+ int string_index;
+
+ /* set to 1 if we have a pending start request */
+ int start_requested;
+
+ int audio_mode;
+
+ /* synchronize access to our device file */
+ atomic_t open_excl;
+
+ struct list_head tx_idle;
+
+ wait_queue_head_t read_wq;
+ wait_queue_head_t write_wq;
+ struct usb_request *rx_req[RX_REQ_MAX];
+ int rx_done;
+
+ /* delayed work for handling ACCESSORY_START */
+ struct delayed_work start_work;
+
+ /* worker for registering and unregistering hid devices */
+ struct work_struct hid_work;
+
+ /* list of active HID devices */
+ struct list_head hid_list;
+
+ /* list of new HID devices to register */
+ struct list_head new_hid_list;
+
+ /* list of dead HID devices to unregister */
+ struct list_head dead_hid_list;
+};
+
+static struct usb_interface_descriptor acc_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 2,
+ .bInterfaceClass = USB_CLASS_VENDOR_SPEC,
+ .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC,
+ .bInterfaceProtocol = 0,
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_descriptor_header *fs_acc_descs[] = {
+ (struct usb_descriptor_header *) &acc_interface_desc,
+ (struct usb_descriptor_header *) &acc_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &acc_fullspeed_out_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_acc_descs[] = {
+ (struct usb_descriptor_header *) &acc_interface_desc,
+ (struct usb_descriptor_header *) &acc_highspeed_in_desc,
+ (struct usb_descriptor_header *) &acc_highspeed_out_desc,
+ NULL,
+};
+
+static struct usb_string acc_string_defs[] = {
+ [INTERFACE_STRING_INDEX].s = "Android Accessory Interface",
+ { }, /* end of list */
+};
+
+static struct usb_gadget_strings acc_string_table = {
+ .language = 0x0409, /* en-US */
+ .strings = acc_string_defs,
+};
+
+static struct usb_gadget_strings *acc_strings[] = {
+ &acc_string_table,
+ NULL,
+};
+
+/* temporary variable used between acc_open() and acc_gadget_bind() */
+static struct acc_dev *_acc_dev;
+
+static inline struct acc_dev *func_to_dev(struct usb_function *f)
+{
+ return container_of(f, struct acc_dev, function);
+}
+
+static struct usb_request *acc_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+ if (!req)
+ return NULL;
+
+ /* now allocate buffers for the requests */
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+
+ return req;
+}
+
+static void acc_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+/* add a request to the tail of a list */
+static void req_put(struct acc_dev *dev, struct list_head *head,
+ struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_add_tail(&req->list, head);
+ spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request *req_get(struct acc_dev *dev, struct list_head *head)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (list_empty(head)) {
+ req = 0;
+ } else {
+ req = list_first_entry(head, struct usb_request, list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return req;
+}
+
+static void acc_set_disconnected(struct acc_dev *dev)
+{
+ dev->online = 0;
+ dev->disconnected = 1;
+}
+
+static void acc_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = _acc_dev;
+
+ if (req->status == -ESHUTDOWN) {
+ pr_debug("acc_complete_in set disconnected");
+ acc_set_disconnected(dev);
+ }
+
+ req_put(dev, &dev->tx_idle, req);
+
+ wake_up(&dev->write_wq);
+}
+
+static void acc_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = _acc_dev;
+
+ dev->rx_done = 1;
+ if (req->status == -ESHUTDOWN) {
+ pr_debug("acc_complete_out set disconnected");
+ acc_set_disconnected(dev);
+ }
+
+ wake_up(&dev->read_wq);
+}
+
+static void acc_complete_set_string(struct usb_ep *ep, struct usb_request *req)
+{
+ struct acc_dev *dev = ep->driver_data;
+ char *string_dest = NULL;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_set_string, err %d\n", req->status);
+ return;
+ }
+
+ switch (dev->string_index) {
+ case ACCESSORY_STRING_MANUFACTURER:
+ string_dest = dev->manufacturer;
+ break;
+ case ACCESSORY_STRING_MODEL:
+ string_dest = dev->model;
+ break;
+ case ACCESSORY_STRING_DESCRIPTION:
+ string_dest = dev->description;
+ break;
+ case ACCESSORY_STRING_VERSION:
+ string_dest = dev->version;
+ break;
+ case ACCESSORY_STRING_URI:
+ string_dest = dev->uri;
+ break;
+ case ACCESSORY_STRING_SERIAL:
+ string_dest = dev->serial;
+ break;
+ }
+ if (string_dest) {
+ unsigned long flags;
+
+ if (length >= ACC_STRING_SIZE)
+ length = ACC_STRING_SIZE - 1;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ memcpy(string_dest, req->buf, length);
+ /* ensure zero termination */
+ string_dest[length] = 0;
+ spin_unlock_irqrestore(&dev->lock, flags);
+ } else {
+ pr_err("unknown accessory string index %d\n",
+ dev->string_index);
+ }
+}
+
+static void acc_complete_set_hid_report_desc(struct usb_ep *ep,
+ struct usb_request *req)
+{
+ struct acc_hid_dev *hid = req->context;
+ struct acc_dev *dev = hid->dev;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_set_hid_report_desc, err %d\n",
+ req->status);
+ return;
+ }
+
+ memcpy(hid->report_desc + hid->report_desc_offset, req->buf, length);
+ hid->report_desc_offset += length;
+ if (hid->report_desc_offset == hid->report_desc_len) {
+ /* After we have received the entire report descriptor
+ * we schedule work to initialize the HID device
+ */
+ schedule_work(&dev->hid_work);
+ }
+}
+
+static void acc_complete_send_hid_event(struct usb_ep *ep,
+ struct usb_request *req)
+{
+ struct acc_hid_dev *hid = req->context;
+ int length = req->actual;
+
+ if (req->status != 0) {
+ pr_err("acc_complete_send_hid_event, err %d\n", req->status);
+ return;
+ }
+
+ hid_report_raw_event(hid->hid, HID_INPUT_REPORT, req->buf, length, 1);
+}
+
+static int acc_hid_parse(struct hid_device *hid)
+{
+ struct acc_hid_dev *hdev = hid->driver_data;
+
+ hid_parse_report(hid, hdev->report_desc, hdev->report_desc_len);
+ return 0;
+}
+
+static int acc_hid_start(struct hid_device *hid)
+{
+ return 0;
+}
+
+static void acc_hid_stop(struct hid_device *hid)
+{
+}
+
+static int acc_hid_open(struct hid_device *hid)
+{
+ return 0;
+}
+
+static void acc_hid_close(struct hid_device *hid)
+{
+}
+
+static struct hid_ll_driver acc_hid_ll_driver = {
+ .parse = acc_hid_parse,
+ .start = acc_hid_start,
+ .stop = acc_hid_stop,
+ .open = acc_hid_open,
+ .close = acc_hid_close,
+};
+
+static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev,
+ int id, int desc_len)
+{
+ struct acc_hid_dev *hdev;
+
+ hdev = kzalloc(sizeof(*hdev), GFP_ATOMIC);
+ if (!hdev)
+ return NULL;
+ hdev->report_desc = kzalloc(desc_len, GFP_ATOMIC);
+ if (!hdev->report_desc) {
+ kfree(hdev);
+ return NULL;
+ }
+ hdev->dev = dev;
+ hdev->id = id;
+ hdev->report_desc_len = desc_len;
+
+ return hdev;
+}
+
+static struct acc_hid_dev *acc_hid_get(struct list_head *list, int id)
+{
+ struct acc_hid_dev *hid;
+
+ list_for_each_entry(hid, list, list) {
+ if (hid->id == id)
+ return hid;
+ }
+ return NULL;
+}
+
+static int acc_register_hid(struct acc_dev *dev, int id, int desc_length)
+{
+ struct acc_hid_dev *hid;
+ unsigned long flags;
+
+ /* report descriptor length must be > 0 */
+ if (desc_length <= 0)
+ return -EINVAL;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ /* replace HID if one already exists with this ID */
+ hid = acc_hid_get(&dev->hid_list, id);
+ if (!hid)
+ hid = acc_hid_get(&dev->new_hid_list, id);
+ if (hid)
+ list_move(&hid->list, &dev->dead_hid_list);
+
+ hid = acc_hid_new(dev, id, desc_length);
+ if (!hid) {
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return -ENOMEM;
+ }
+
+ list_add(&hid->list, &dev->new_hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* schedule work to register the HID device */
+ schedule_work(&dev->hid_work);
+ return 0;
+}
+
+static int acc_unregister_hid(struct acc_dev *dev, int id)
+{
+ struct acc_hid_dev *hid;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->hid_list, id);
+ if (!hid)
+ hid = acc_hid_get(&dev->new_hid_list, id);
+ if (!hid) {
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return -EINVAL;
+ }
+
+ list_move(&hid->list, &dev->dead_hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ schedule_work(&dev->hid_work);
+ return 0;
+}
+
+static int create_bulk_endpoints(struct acc_dev *dev,
+ struct usb_endpoint_descriptor *in_desc,
+ struct usb_endpoint_descriptor *out_desc)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ struct usb_ep *ep;
+ int i;
+
+ DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+ ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_in = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_out got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_out = ep;
+
+ /* now allocate requests for our endpoints */
+ for (i = 0; i < TX_REQ_MAX; i++) {
+ req = acc_request_new(dev->ep_in, BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = acc_complete_in;
+ req_put(dev, &dev->tx_idle, req);
+ }
+ for (i = 0; i < RX_REQ_MAX; i++) {
+ req = acc_request_new(dev->ep_out, BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = acc_complete_out;
+ dev->rx_req[i] = req;
+ }
+
+ return 0;
+
+fail:
+ pr_err("acc_bind() could not allocate requests\n");
+ while ((req = req_get(dev, &dev->tx_idle)))
+ acc_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ acc_request_free(dev->rx_req[i], dev->ep_out);
+ return -1;
+}
+
+static ssize_t acc_read(struct file *fp, char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct acc_dev *dev = fp->private_data;
+ struct usb_request *req;
+ ssize_t r = count;
+ unsigned xfer;
+ int ret = 0;
+
+ pr_debug("acc_read(%zu)\n", count);
+
+ if (dev->disconnected) {
+ pr_debug("acc_read disconnected");
+ return -ENODEV;
+ }
+
+ if (count > BULK_BUFFER_SIZE)
+ count = BULK_BUFFER_SIZE;
+
+ /* we will block until we're online */
+ pr_debug("acc_read: waiting for online\n");
+ ret = wait_event_interruptible(dev->read_wq, dev->online);
+ if (ret < 0) {
+ r = ret;
+ goto done;
+ }
+
+ if (dev->rx_done) {
+ // last req cancelled. try to get it.
+ req = dev->rx_req[0];
+ goto copy_data;
+ }
+
+requeue_req:
+ /* queue a request */
+ req = dev->rx_req[0];
+ req->length = count;
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ goto done;
+ } else {
+ pr_debug("rx %p queue\n", req);
+ }
+
+ /* wait for a request to complete */
+ ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+ if (ret < 0) {
+ r = ret;
+ ret = usb_ep_dequeue(dev->ep_out, req);
+ if (ret != 0) {
+ // cancel failed. There can be a data already received.
+ // it will be retrieved in the next read.
+ pr_debug("acc_read: cancelling failed %d", ret);
+ }
+ goto done;
+ }
+
+copy_data:
+ dev->rx_done = 0;
+ if (dev->online) {
+ /* If we got a 0-len packet, throw it back and try again. */
+ if (req->actual == 0)
+ goto requeue_req;
+
+ pr_debug("rx %p %u\n", req, req->actual);
+ xfer = (req->actual < count) ? req->actual : count;
+ r = xfer;
+ if (copy_to_user(buf, req->buf, xfer))
+ r = -EFAULT;
+ } else
+ r = -EIO;
+
+done:
+ pr_debug("acc_read returning %zd\n", r);
+ return r;
+}
+
+static ssize_t acc_write(struct file *fp, const char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct acc_dev *dev = fp->private_data;
+ struct usb_request *req = 0;
+ ssize_t r = count;
+ unsigned xfer;
+ int ret;
+
+ pr_debug("acc_write(%zu)\n", count);
+
+ if (!dev->online || dev->disconnected) {
+ pr_debug("acc_write disconnected or not online");
+ return -ENODEV;
+ }
+
+ while (count > 0) {
+ if (!dev->online) {
+ pr_debug("acc_write dev->error\n");
+ r = -EIO;
+ break;
+ }
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ ((req = req_get(dev, &dev->tx_idle)) || !dev->online));
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > BULK_BUFFER_SIZE) {
+ xfer = BULK_BUFFER_SIZE;
+ /* ZLP, They will be more TX requests so not yet. */
+ req->zero = 0;
+ } else {
+ xfer = count;
+ /* If the data length is a multple of the
+ * maxpacket size then send a zero length packet(ZLP).
+ */
+ req->zero = ((xfer % dev->ep_in->maxpacket) == 0);
+ }
+ if (copy_from_user(req->buf, buf, xfer)) {
+ r = -EFAULT;
+ break;
+ }
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ pr_debug("acc_write: xfer error %d\n", ret);
+ r = -EIO;
+ break;
+ }
+
+ buf += xfer;
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ req_put(dev, &dev->tx_idle, req);
+
+ pr_debug("acc_write returning %zd\n", r);
+ return r;
+}
+
+static long acc_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+ struct acc_dev *dev = fp->private_data;
+ char *src = NULL;
+ int ret;
+
+ switch (code) {
+ case ACCESSORY_GET_STRING_MANUFACTURER:
+ src = dev->manufacturer;
+ break;
+ case ACCESSORY_GET_STRING_MODEL:
+ src = dev->model;
+ break;
+ case ACCESSORY_GET_STRING_DESCRIPTION:
+ src = dev->description;
+ break;
+ case ACCESSORY_GET_STRING_VERSION:
+ src = dev->version;
+ break;
+ case ACCESSORY_GET_STRING_URI:
+ src = dev->uri;
+ break;
+ case ACCESSORY_GET_STRING_SERIAL:
+ src = dev->serial;
+ break;
+ case ACCESSORY_IS_START_REQUESTED:
+ return dev->start_requested;
+ case ACCESSORY_GET_AUDIO_MODE:
+ return dev->audio_mode;
+ }
+ if (!src)
+ return -EINVAL;
+
+ ret = strlen(src) + 1;
+ if (copy_to_user((void __user *)value, src, ret))
+ ret = -EFAULT;
+ return ret;
+}
+
+static int acc_open(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "acc_open\n");
+ if (atomic_xchg(&_acc_dev->open_excl, 1))
+ return -EBUSY;
+
+ _acc_dev->disconnected = 0;
+ fp->private_data = _acc_dev;
+ return 0;
+}
+
+static int acc_release(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "acc_release\n");
+
+ WARN_ON(!atomic_xchg(&_acc_dev->open_excl, 0));
+ _acc_dev->disconnected = 0;
+ return 0;
+}
+
+/* file operations for /dev/usb_accessory */
+static const struct file_operations acc_fops = {
+ .owner = THIS_MODULE,
+ .read = acc_read,
+ .write = acc_write,
+ .unlocked_ioctl = acc_ioctl,
+ .open = acc_open,
+ .release = acc_release,
+};
+
+static int acc_hid_probe(struct hid_device *hdev,
+ const struct hid_device_id *id)
+{
+ int ret;
+
+ ret = hid_parse(hdev);
+ if (ret)
+ return ret;
+ return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
+static struct miscdevice acc_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "usb_accessory",
+ .fops = &acc_fops,
+};
+
+static const struct hid_device_id acc_hid_table[] = {
+ { HID_USB_DEVICE(HID_ANY_ID, HID_ANY_ID) },
+ { }
+};
+
+static struct hid_driver acc_hid_driver = {
+ .name = "USB accessory",
+ .id_table = acc_hid_table,
+ .probe = acc_hid_probe,
+};
+
+static int acc_ctrlrequest(struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct acc_dev *dev = _acc_dev;
+ int value = -EOPNOTSUPP;
+ struct acc_hid_dev *hid;
+ int offset;
+ u8 b_requestType = ctrl->bRequestType;
+ u8 b_request = ctrl->bRequest;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+ unsigned long flags;
+
+/*
+ printk(KERN_INFO "acc_ctrlrequest "
+ "%02x.%02x v%04x i%04x l%u\n",
+ b_requestType, b_request,
+ w_value, w_index, w_length);
+*/
+
+ if (b_requestType == (USB_DIR_OUT | USB_TYPE_VENDOR)) {
+ if (b_request == ACCESSORY_START) {
+ dev->start_requested = 1;
+ schedule_delayed_work(
+ &dev->start_work, msecs_to_jiffies(10));
+ value = 0;
+ } else if (b_request == ACCESSORY_SEND_STRING) {
+ dev->string_index = w_index;
+ cdev->gadget->ep0->driver_data = dev;
+ cdev->req->complete = acc_complete_set_string;
+ value = w_length;
+ } else if (b_request == ACCESSORY_SET_AUDIO_MODE &&
+ w_index == 0 && w_length == 0) {
+ dev->audio_mode = w_value;
+ value = 0;
+ } else if (b_request == ACCESSORY_REGISTER_HID) {
+ value = acc_register_hid(dev, w_value, w_index);
+ } else if (b_request == ACCESSORY_UNREGISTER_HID) {
+ value = acc_unregister_hid(dev, w_value);
+ } else if (b_request == ACCESSORY_SET_HID_REPORT_DESC) {
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->new_hid_list, w_value);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ if (!hid) {
+ value = -EINVAL;
+ goto err;
+ }
+ offset = w_index;
+ if (offset != hid->report_desc_offset
+ || offset + w_length > hid->report_desc_len) {
+ value = -EINVAL;
+ goto err;
+ }
+ cdev->req->context = hid;
+ cdev->req->complete = acc_complete_set_hid_report_desc;
+ value = w_length;
+ } else if (b_request == ACCESSORY_SEND_HID_EVENT) {
+ spin_lock_irqsave(&dev->lock, flags);
+ hid = acc_hid_get(&dev->hid_list, w_value);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ if (!hid) {
+ value = -EINVAL;
+ goto err;
+ }
+ cdev->req->context = hid;
+ cdev->req->complete = acc_complete_send_hid_event;
+ value = w_length;
+ }
+ } else if (b_requestType == (USB_DIR_IN | USB_TYPE_VENDOR)) {
+ if (b_request == ACCESSORY_GET_PROTOCOL) {
+ *((u16 *)cdev->req->buf) = PROTOCOL_VERSION;
+ value = sizeof(u16);
+
+ /* clear any string left over from a previous session */
+ memset(dev->manufacturer, 0, sizeof(dev->manufacturer));
+ memset(dev->model, 0, sizeof(dev->model));
+ memset(dev->description, 0, sizeof(dev->description));
+ memset(dev->version, 0, sizeof(dev->version));
+ memset(dev->uri, 0, sizeof(dev->uri));
+ memset(dev->serial, 0, sizeof(dev->serial));
+ dev->start_requested = 0;
+ dev->audio_mode = 0;
+ }
+ }
+
+ if (value >= 0) {
+ cdev->req->zero = 0;
+ cdev->req->length = value;
+ value = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+ if (value < 0)
+ ERROR(cdev, "%s setup response queue error\n",
+ __func__);
+ }
+
+err:
+ if (value == -EOPNOTSUPP)
+ VDBG(cdev,
+ "unknown class-specific control req "
+ "%02x.%02x v%04x i%04x l%u\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+ return value;
+}
+
+static int
+acc_function_bind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct acc_dev *dev = func_to_dev(f);
+ int id;
+ int ret;
+
+ DBG(cdev, "acc_function_bind dev: %p\n", dev);
+
+ ret = hid_register_driver(&acc_hid_driver);
+ if (ret)
+ return ret;
+
+ dev->start_requested = 0;
+
+ /* allocate interface ID(s) */
+ id = usb_interface_id(c, f);
+ if (id < 0)
+ return id;
+ acc_interface_desc.bInterfaceNumber = id;
+
+ /* allocate endpoints */
+ ret = create_bulk_endpoints(dev, &acc_fullspeed_in_desc,
+ &acc_fullspeed_out_desc);
+ if (ret)
+ return ret;
+
+ /* support high speed hardware */
+ if (gadget_is_dualspeed(c->cdev->gadget)) {
+ acc_highspeed_in_desc.bEndpointAddress =
+ acc_fullspeed_in_desc.bEndpointAddress;
+ acc_highspeed_out_desc.bEndpointAddress =
+ acc_fullspeed_out_desc.bEndpointAddress;
+ }
+
+ DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+ gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+ f->name, dev->ep_in->name, dev->ep_out->name);
+ return 0;
+}
+
+static void
+kill_all_hid_devices(struct acc_dev *dev)
+{
+ struct acc_hid_dev *hid;
+ struct list_head *entry, *temp;
+ unsigned long flags;
+
+ /* do nothing if usb accessory device doesn't exist */
+ if (!dev)
+ return;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_for_each_safe(entry, temp, &dev->hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ list_add(&hid->list, &dev->dead_hid_list);
+ }
+ list_for_each_safe(entry, temp, &dev->new_hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ list_add(&hid->list, &dev->dead_hid_list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ schedule_work(&dev->hid_work);
+}
+
+static void
+acc_hid_unbind(struct acc_dev *dev)
+{
+ hid_unregister_driver(&acc_hid_driver);
+ kill_all_hid_devices(dev);
+}
+
+static void
+acc_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_request *req;
+ int i;
+
+ while ((req = req_get(dev, &dev->tx_idle)))
+ acc_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ acc_request_free(dev->rx_req[i], dev->ep_out);
+
+ acc_hid_unbind(dev);
+}
+
+static void acc_start_work(struct work_struct *data)
+{
+ char *envp[2] = { "ACCESSORY=START", NULL };
+ kobject_uevent_env(&acc_device.this_device->kobj, KOBJ_CHANGE, envp);
+}
+
+static int acc_hid_init(struct acc_hid_dev *hdev)
+{
+ struct hid_device *hid;
+ int ret;
+
+ hid = hid_allocate_device();
+ if (IS_ERR(hid))
+ return PTR_ERR(hid);
+
+ hid->ll_driver = &acc_hid_ll_driver;
+ hid->dev.parent = acc_device.this_device;
+
+ hid->bus = BUS_USB;
+ hid->vendor = HID_ANY_ID;
+ hid->product = HID_ANY_ID;
+ hid->driver_data = hdev;
+ ret = hid_add_device(hid);
+ if (ret) {
+ pr_err("can't add hid device: %d\n", ret);
+ hid_destroy_device(hid);
+ return ret;
+ }
+
+ hdev->hid = hid;
+ return 0;
+}
+
+static void acc_hid_delete(struct acc_hid_dev *hid)
+{
+ kfree(hid->report_desc);
+ kfree(hid);
+}
+
+static void acc_hid_work(struct work_struct *data)
+{
+ struct acc_dev *dev = _acc_dev;
+ struct list_head *entry, *temp;
+ struct acc_hid_dev *hid;
+ struct list_head new_list, dead_list;
+ unsigned long flags;
+
+ INIT_LIST_HEAD(&new_list);
+
+ spin_lock_irqsave(&dev->lock, flags);
+
+ /* copy hids that are ready for initialization to new_list */
+ list_for_each_safe(entry, temp, &dev->new_hid_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ if (hid->report_desc_offset == hid->report_desc_len)
+ list_move(&hid->list, &new_list);
+ }
+
+ if (list_empty(&dev->dead_hid_list)) {
+ INIT_LIST_HEAD(&dead_list);
+ } else {
+ /* move all of dev->dead_hid_list to dead_list */
+ dead_list.prev = dev->dead_hid_list.prev;
+ dead_list.next = dev->dead_hid_list.next;
+ dead_list.next->prev = &dead_list;
+ dead_list.prev->next = &dead_list;
+ INIT_LIST_HEAD(&dev->dead_hid_list);
+ }
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* register new HID devices */
+ list_for_each_safe(entry, temp, &new_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ if (acc_hid_init(hid)) {
+ pr_err("can't add HID device %p\n", hid);
+ acc_hid_delete(hid);
+ } else {
+ spin_lock_irqsave(&dev->lock, flags);
+ list_move(&hid->list, &dev->hid_list);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ }
+ }
+
+ /* remove dead HID devices */
+ list_for_each_safe(entry, temp, &dead_list) {
+ hid = list_entry(entry, struct acc_hid_dev, list);
+ list_del(&hid->list);
+ if (hid->hid)
+ hid_destroy_device(hid->hid);
+ acc_hid_delete(hid);
+ }
+}
+
+static int acc_function_set_alt(struct usb_function *f,
+ unsigned intf, unsigned alt)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ DBG(cdev, "acc_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_out);
+ if (ret) {
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+
+ dev->online = 1;
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+ return 0;
+}
+
+static void acc_function_disable(struct usb_function *f)
+{
+ struct acc_dev *dev = func_to_dev(f);
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ DBG(cdev, "acc_function_disable\n");
+ acc_set_disconnected(dev);
+ usb_ep_disable(dev->ep_in);
+ usb_ep_disable(dev->ep_out);
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+
+ VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int acc_bind_config(struct usb_configuration *c)
+{
+ struct acc_dev *dev = _acc_dev;
+ int ret;
+
+ printk(KERN_INFO "acc_bind_config\n");
+
+ /* allocate a string ID for our interface */
+ if (acc_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+ ret = usb_string_id(c->cdev);
+ if (ret < 0)
+ return ret;
+ acc_string_defs[INTERFACE_STRING_INDEX].id = ret;
+ acc_interface_desc.iInterface = ret;
+ }
+
+ dev->cdev = c->cdev;
+ dev->function.name = "accessory";
+ dev->function.strings = acc_strings,
+ dev->function.fs_descriptors = fs_acc_descs;
+ dev->function.hs_descriptors = hs_acc_descs;
+ dev->function.bind = acc_function_bind;
+ dev->function.unbind = acc_function_unbind;
+ dev->function.set_alt = acc_function_set_alt;
+ dev->function.disable = acc_function_disable;
+
+ return usb_add_function(c, &dev->function);
+}
+
+static int acc_setup(void)
+{
+ struct acc_dev *dev;
+ int ret;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ return -ENOMEM;
+
+ spin_lock_init(&dev->lock);
+ init_waitqueue_head(&dev->read_wq);
+ init_waitqueue_head(&dev->write_wq);
+ atomic_set(&dev->open_excl, 0);
+ INIT_LIST_HEAD(&dev->tx_idle);
+ INIT_LIST_HEAD(&dev->hid_list);
+ INIT_LIST_HEAD(&dev->new_hid_list);
+ INIT_LIST_HEAD(&dev->dead_hid_list);
+ INIT_DELAYED_WORK(&dev->start_work, acc_start_work);
+ INIT_WORK(&dev->hid_work, acc_hid_work);
+
+ /* _acc_dev must be set before calling usb_gadget_register_driver */
+ _acc_dev = dev;
+
+ ret = misc_register(&acc_device);
+ if (ret)
+ goto err;
+
+ return 0;
+
+err:
+ kfree(dev);
+ pr_err("USB accessory gadget driver failed to initialize\n");
+ return ret;
+}
+
+static void acc_disconnect(void)
+{
+ /* unregister all HID devices if USB is disconnected */
+ kill_all_hid_devices(_acc_dev);
+}
+
+static void acc_cleanup(void)
+{
+ misc_deregister(&acc_device);
+ kfree(_acc_dev);
+ _acc_dev = NULL;
+}
diff --git a/drivers/usb/gadget/f_audio_source.c b/drivers/usb/gadget/f_audio_source.c
new file mode 100644
index 0000000..07a1a3c
--- /dev/null
+++ b/drivers/usb/gadget/f_audio_source.c
@@ -0,0 +1,834 @@
+/*
+ * Gadget Function Driver for USB audio source device
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/usb/audio.h>
+#include <linux/wait.h>
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+
+#define SAMPLE_RATE 44100
+#define FRAMES_PER_MSEC (SAMPLE_RATE / 1000)
+
+#define IN_EP_MAX_PACKET_SIZE 256
+
+/* Number of requests to allocate */
+#define IN_EP_REQ_COUNT 4
+
+#define AUDIO_AC_INTERFACE 0
+#define AUDIO_AS_INTERFACE 1
+#define AUDIO_NUM_INTERFACES 2
+
+/* B.3.1 Standard AC Interface Descriptor */
+static struct usb_interface_descriptor audio_ac_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bNumEndpoints = 0,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+};
+
+DECLARE_UAC_AC_HEADER_DESCRIPTOR(2);
+
+#define UAC_DT_AC_HEADER_LENGTH UAC_DT_AC_HEADER_SIZE(AUDIO_NUM_INTERFACES)
+/* 1 input terminal, 1 output terminal and 1 feature unit */
+#define UAC_DT_TOTAL_LENGTH (UAC_DT_AC_HEADER_LENGTH \
+ + UAC_DT_INPUT_TERMINAL_SIZE + UAC_DT_OUTPUT_TERMINAL_SIZE \
+ + UAC_DT_FEATURE_UNIT_SIZE(0))
+/* B.3.2 Class-Specific AC Interface Descriptor */
+static struct uac1_ac_header_descriptor_2 audio_ac_header_desc = {
+ .bLength = UAC_DT_AC_HEADER_LENGTH,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_HEADER,
+ .bcdADC = __constant_cpu_to_le16(0x0100),
+ .wTotalLength = __constant_cpu_to_le16(UAC_DT_TOTAL_LENGTH),
+ .bInCollection = AUDIO_NUM_INTERFACES,
+ .baInterfaceNr = {
+ [0] = AUDIO_AC_INTERFACE,
+ [1] = AUDIO_AS_INTERFACE,
+ }
+};
+
+#define INPUT_TERMINAL_ID 1
+static struct uac_input_terminal_descriptor audio_input_terminal_desc = {
+ .bLength = UAC_DT_INPUT_TERMINAL_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_INPUT_TERMINAL,
+ .bTerminalID = INPUT_TERMINAL_ID,
+ .wTerminalType = UAC_INPUT_TERMINAL_MICROPHONE,
+ .bAssocTerminal = 0,
+ .wChannelConfig = 0x3,
+};
+
+DECLARE_UAC_FEATURE_UNIT_DESCRIPTOR(0);
+
+#define FEATURE_UNIT_ID 2
+static struct uac_feature_unit_descriptor_0 audio_feature_unit_desc = {
+ .bLength = UAC_DT_FEATURE_UNIT_SIZE(0),
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_FEATURE_UNIT,
+ .bUnitID = FEATURE_UNIT_ID,
+ .bSourceID = INPUT_TERMINAL_ID,
+ .bControlSize = 2,
+};
+
+#define OUTPUT_TERMINAL_ID 3
+static struct uac1_output_terminal_descriptor audio_output_terminal_desc = {
+ .bLength = UAC_DT_OUTPUT_TERMINAL_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_OUTPUT_TERMINAL,
+ .bTerminalID = OUTPUT_TERMINAL_ID,
+ .wTerminalType = UAC_TERMINAL_STREAMING,
+ .bAssocTerminal = FEATURE_UNIT_ID,
+ .bSourceID = FEATURE_UNIT_ID,
+};
+
+/* B.4.1 Standard AS Interface Descriptor */
+static struct usb_interface_descriptor audio_as_interface_alt_0_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bAlternateSetting = 0,
+ .bNumEndpoints = 0,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+static struct usb_interface_descriptor audio_as_interface_alt_1_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bAlternateSetting = 1,
+ .bNumEndpoints = 1,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+/* B.4.2 Class-Specific AS Interface Descriptor */
+static struct uac1_as_header_descriptor audio_as_header_desc = {
+ .bLength = UAC_DT_AS_HEADER_SIZE,
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_AS_GENERAL,
+ .bTerminalLink = INPUT_TERMINAL_ID,
+ .bDelay = 1,
+ .wFormatTag = UAC_FORMAT_TYPE_I_PCM,
+};
+
+DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1);
+
+static struct uac_format_type_i_discrete_descriptor_1 audio_as_type_i_desc = {
+ .bLength = UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1),
+ .bDescriptorType = USB_DT_CS_INTERFACE,
+ .bDescriptorSubtype = UAC_FORMAT_TYPE,
+ .bFormatType = UAC_FORMAT_TYPE_I,
+ .bSubframeSize = 2,
+ .bBitResolution = 16,
+ .bSamFreqType = 1,
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor audio_hs_as_in_ep_desc = {
+ .bLength = USB_DT_ENDPOINT_AUDIO_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_SYNC_SYNC
+ | USB_ENDPOINT_XFER_ISOC,
+ .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+ .bInterval = 4, /* poll 1 per millisecond */
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor audio_fs_as_in_ep_desc = {
+ .bLength = USB_DT_ENDPOINT_AUDIO_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_SYNC_SYNC
+ | USB_ENDPOINT_XFER_ISOC,
+ .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+ .bInterval = 1, /* poll 1 per millisecond */
+};
+
+/* Class-specific AS ISO OUT Endpoint Descriptor */
+static struct uac_iso_endpoint_descriptor audio_as_iso_in_desc = {
+ .bLength = UAC_ISO_ENDPOINT_DESC_SIZE,
+ .bDescriptorType = USB_DT_CS_ENDPOINT,
+ .bDescriptorSubtype = UAC_EP_GENERAL,
+ .bmAttributes = 1,
+ .bLockDelayUnits = 1,
+ .wLockDelay = __constant_cpu_to_le16(1),
+};
+
+static struct usb_descriptor_header *hs_audio_desc[] = {
+ (struct usb_descriptor_header *)&audio_ac_interface_desc,
+ (struct usb_descriptor_header *)&audio_ac_header_desc,
+
+ (struct usb_descriptor_header *)&audio_input_terminal_desc,
+ (struct usb_descriptor_header *)&audio_output_terminal_desc,
+ (struct usb_descriptor_header *)&audio_feature_unit_desc,
+
+ (struct usb_descriptor_header *)&audio_as_interface_alt_0_desc,
+ (struct usb_descriptor_header *)&audio_as_interface_alt_1_desc,
+ (struct usb_descriptor_header *)&audio_as_header_desc,
+
+ (struct usb_descriptor_header *)&audio_as_type_i_desc,
+
+ (struct usb_descriptor_header *)&audio_hs_as_in_ep_desc,
+ (struct usb_descriptor_header *)&audio_as_iso_in_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *fs_audio_desc[] = {
+ (struct usb_descriptor_header *)&audio_ac_interface_desc,
+ (struct usb_descriptor_header *)&audio_ac_header_desc,
+
+ (struct usb_descriptor_header *)&audio_input_terminal_desc,
+ (struct usb_descriptor_header *)&audio_output_terminal_desc,
+ (struct usb_descriptor_header *)&audio_feature_unit_desc,
+
+ (struct usb_descriptor_header *)&audio_as_interface_alt_0_desc,
+ (struct usb_descriptor_header *)&audio_as_interface_alt_1_desc,
+ (struct usb_descriptor_header *)&audio_as_header_desc,
+
+ (struct usb_descriptor_header *)&audio_as_type_i_desc,
+
+ (struct usb_descriptor_header *)&audio_fs_as_in_ep_desc,
+ (struct usb_descriptor_header *)&audio_as_iso_in_desc,
+ NULL,
+};
+
+static struct snd_pcm_hardware audio_hw_info = {
+ .info = SNDRV_PCM_INFO_MMAP |
+ SNDRV_PCM_INFO_MMAP_VALID |
+ SNDRV_PCM_INFO_BATCH |
+ SNDRV_PCM_INFO_INTERLEAVED |
+ SNDRV_PCM_INFO_BLOCK_TRANSFER,
+
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
+ .channels_min = 2,
+ .channels_max = 2,
+ .rate_min = SAMPLE_RATE,
+ .rate_max = SAMPLE_RATE,
+
+ .buffer_bytes_max = 1024 * 1024,
+ .period_bytes_min = 64,
+ .period_bytes_max = 512 * 1024,
+ .periods_min = 2,
+ .periods_max = 1024,
+};
+
+/*-------------------------------------------------------------------------*/
+
+struct audio_source_config {
+ int card;
+ int device;
+};
+
+struct audio_dev {
+ struct usb_function func;
+ struct snd_card *card;
+ struct snd_pcm *pcm;
+ struct snd_pcm_substream *substream;
+
+ struct list_head idle_reqs;
+ struct usb_ep *in_ep;
+
+ spinlock_t lock;
+
+ /* beginning, end and current position in our buffer */
+ void *buffer_start;
+ void *buffer_end;
+ void *buffer_pos;
+
+ /* byte size of a "period" */
+ unsigned int period;
+ /* bytes sent since last call to snd_pcm_period_elapsed */
+ unsigned int period_offset;
+ /* time we started playing */
+ ktime_t start_time;
+ /* number of frames sent since start_time */
+ s64 frames_sent;
+};
+
+static inline struct audio_dev *func_to_audio(struct usb_function *f)
+{
+ return container_of(f, struct audio_dev, func);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static struct usb_request *audio_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+ if (!req)
+ return NULL;
+
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+ req->length = buffer_size;
+ return req;
+}
+
+static void audio_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+static void audio_req_put(struct audio_dev *audio, struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ list_add_tail(&req->list, &audio->idle_reqs);
+ spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static struct usb_request *audio_req_get(struct audio_dev *audio)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ if (list_empty(&audio->idle_reqs)) {
+ req = 0;
+ } else {
+ req = list_first_entry(&audio->idle_reqs, struct usb_request,
+ list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&audio->lock, flags);
+ return req;
+}
+
+/* send the appropriate number of packets to match our bitrate */
+static void audio_send(struct audio_dev *audio)
+{
+ struct snd_pcm_runtime *runtime;
+ struct usb_request *req;
+ int length, length1, length2, ret;
+ s64 msecs;
+ s64 frames;
+ ktime_t now;
+
+ /* audio->substream will be null if we have been closed */
+ if (!audio->substream)
+ return;
+ /* audio->buffer_pos will be null if we have been stopped */
+ if (!audio->buffer_pos)
+ return;
+
+ runtime = audio->substream->runtime;
+
+ /* compute number of frames to send */
+ now = ktime_get();
+ msecs = ktime_to_ns(now) - ktime_to_ns(audio->start_time);
+ do_div(msecs, 1000000);
+ frames = msecs * SAMPLE_RATE;
+ do_div(frames, 1000);
+
+ /* Readjust our frames_sent if we fall too far behind.
+ * If we get too far behind it is better to drop some frames than
+ * to keep sending data too fast in an attempt to catch up.
+ */
+ if (frames - audio->frames_sent > 10 * FRAMES_PER_MSEC)
+ audio->frames_sent = frames - FRAMES_PER_MSEC;
+
+ frames -= audio->frames_sent;
+
+ /* We need to send something to keep the pipeline going */
+ if (frames <= 0)
+ frames = FRAMES_PER_MSEC;
+
+ while (frames > 0) {
+ req = audio_req_get(audio);
+ if (!req)
+ break;
+
+ length = frames_to_bytes(runtime, frames);
+ if (length > IN_EP_MAX_PACKET_SIZE)
+ length = IN_EP_MAX_PACKET_SIZE;
+
+ if (audio->buffer_pos + length > audio->buffer_end)
+ length1 = audio->buffer_end - audio->buffer_pos;
+ else
+ length1 = length;
+ memcpy(req->buf, audio->buffer_pos, length1);
+ if (length1 < length) {
+ /* Wrap around and copy remaining length
+ * at beginning of buffer.
+ */
+ length2 = length - length1;
+ memcpy(req->buf + length1, audio->buffer_start,
+ length2);
+ audio->buffer_pos = audio->buffer_start + length2;
+ } else {
+ audio->buffer_pos += length1;
+ if (audio->buffer_pos >= audio->buffer_end)
+ audio->buffer_pos = audio->buffer_start;
+ }
+
+ req->length = length;
+ ret = usb_ep_queue(audio->in_ep, req, GFP_ATOMIC);
+ if (ret < 0) {
+ pr_err("usb_ep_queue failed ret: %d\n", ret);
+ audio_req_put(audio, req);
+ break;
+ }
+
+ frames -= bytes_to_frames(runtime, length);
+ audio->frames_sent += bytes_to_frames(runtime, length);
+ }
+}
+
+static void audio_control_complete(struct usb_ep *ep, struct usb_request *req)
+{
+ /* nothing to do here */
+}
+
+static void audio_data_complete(struct usb_ep *ep, struct usb_request *req)
+{
+ struct audio_dev *audio = req->context;
+
+ pr_debug("audio_data_complete req->status %d req->actual %d\n",
+ req->status, req->actual);
+
+ audio_req_put(audio, req);
+
+ if (!audio->buffer_start || req->status)
+ return;
+
+ audio->period_offset += req->actual;
+ if (audio->period_offset >= audio->period) {
+ snd_pcm_period_elapsed(audio->substream);
+ audio->period_offset = 0;
+ }
+ audio_send(audio);
+}
+
+static int audio_set_endpoint_req(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl)
+{
+ int value = -EOPNOTSUPP;
+ u16 ep = le16_to_cpu(ctrl->wIndex);
+ u16 len = le16_to_cpu(ctrl->wLength);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+
+ pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+ ctrl->bRequest, w_value, len, ep);
+
+ switch (ctrl->bRequest) {
+ case UAC_SET_CUR:
+ case UAC_SET_MIN:
+ case UAC_SET_MAX:
+ case UAC_SET_RES:
+ value = len;
+ break;
+ default:
+ break;
+ }
+
+ return value;
+}
+
+static int audio_get_endpoint_req(struct usb_function *f,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int value = -EOPNOTSUPP;
+ u8 ep = ((le16_to_cpu(ctrl->wIndex) >> 8) & 0xFF);
+ u16 len = le16_to_cpu(ctrl->wLength);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u8 *buf = cdev->req->buf;
+
+ pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+ ctrl->bRequest, w_value, len, ep);
+
+ if (w_value == UAC_EP_CS_ATTR_SAMPLE_RATE << 8) {
+ switch (ctrl->bRequest) {
+ case UAC_GET_CUR:
+ case UAC_GET_MIN:
+ case UAC_GET_MAX:
+ case UAC_GET_RES:
+ /* return our sample rate */
+ buf[0] = (u8)SAMPLE_RATE;
+ buf[1] = (u8)(SAMPLE_RATE >> 8);
+ buf[2] = (u8)(SAMPLE_RATE >> 16);
+ value = 3;
+ break;
+ default:
+ break;
+ }
+ }
+
+ return value;
+}
+
+static int
+audio_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
+{
+ struct usb_composite_dev *cdev = f->config->cdev;
+ struct usb_request *req = cdev->req;
+ int value = -EOPNOTSUPP;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+
+ /* composite driver infrastructure handles everything; interface
+ * activation uses set_alt().
+ */
+ switch (ctrl->bRequestType) {
+ case USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+ value = audio_set_endpoint_req(f, ctrl);
+ break;
+
+ case USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+ value = audio_get_endpoint_req(f, ctrl);
+ break;
+ }
+
+ /* respond with data transfer or status phase? */
+ if (value >= 0) {
+ pr_debug("audio req%02x.%02x v%04x i%04x l%d\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+ req->zero = 0;
+ req->length = value;
+ req->complete = audio_control_complete;
+ value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC);
+ if (value < 0)
+ pr_err("audio response on err %d\n", value);
+ }
+
+ /* device either stalls (value < 0) or reports success */
+ return value;
+}
+
+static int audio_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
+{
+ struct audio_dev *audio = func_to_audio(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ pr_debug("audio_set_alt intf %d, alt %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, audio->in_ep);
+ if (ret)
+ return ret;
+
+ usb_ep_enable(audio->in_ep);
+ return 0;
+}
+
+static void audio_disable(struct usb_function *f)
+{
+ struct audio_dev *audio = func_to_audio(f);
+
+ pr_debug("audio_disable\n");
+ usb_ep_disable(audio->in_ep);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static void audio_build_desc(struct audio_dev *audio)
+{
+ u8 *sam_freq;
+ int rate;
+
+ /* Set channel numbers */
+ audio_input_terminal_desc.bNrChannels = 2;
+ audio_as_type_i_desc.bNrChannels = 2;
+
+ /* Set sample rates */
+ rate = SAMPLE_RATE;
+ sam_freq = audio_as_type_i_desc.tSamFreq[0];
+ memcpy(sam_freq, &rate, 3);
+}
+
+/* audio function driver setup/binding */
+static int
+audio_bind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct audio_dev *audio = func_to_audio(f);
+ int status;
+ struct usb_ep *ep;
+ struct usb_request *req;
+ int i;
+
+ audio_build_desc(audio);
+
+ /* allocate instance-specific interface IDs, and patch descriptors */
+ status = usb_interface_id(c, f);
+ if (status < 0)
+ goto fail;
+ audio_ac_interface_desc.bInterfaceNumber = status;
+
+ /* AUDIO_AC_INTERFACE */
+ audio_ac_header_desc.baInterfaceNr[0] = status;
+
+ status = usb_interface_id(c, f);
+ if (status < 0)
+ goto fail;
+ audio_as_interface_alt_0_desc.bInterfaceNumber = status;
+ audio_as_interface_alt_1_desc.bInterfaceNumber = status;
+
+ /* AUDIO_AS_INTERFACE */
+ audio_ac_header_desc.baInterfaceNr[1] = status;
+
+ status = -ENODEV;
+
+ /* allocate our endpoint */
+ ep = usb_ep_autoconfig(cdev->gadget, &audio_fs_as_in_ep_desc);
+ if (!ep)
+ goto fail;
+ audio->in_ep = ep;
+ ep->driver_data = audio; /* claim */
+
+ if (gadget_is_dualspeed(c->cdev->gadget))
+ audio_hs_as_in_ep_desc.bEndpointAddress =
+ audio_fs_as_in_ep_desc.bEndpointAddress;
+
+ f->fs_descriptors = fs_audio_desc;
+ f->hs_descriptors = hs_audio_desc;
+
+ for (i = 0, status = 0; i < IN_EP_REQ_COUNT && status == 0; i++) {
+ req = audio_request_new(ep, IN_EP_MAX_PACKET_SIZE);
+ if (req) {
+ req->context = audio;
+ req->complete = audio_data_complete;
+ audio_req_put(audio, req);
+ } else
+ status = -ENOMEM;
+ }
+
+fail:
+ return status;
+}
+
+static void
+audio_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct audio_dev *audio = func_to_audio(f);
+ struct usb_request *req;
+
+ while ((req = audio_req_get(audio)))
+ audio_request_free(req, audio->in_ep);
+
+ snd_card_free_when_closed(audio->card);
+ audio->card = NULL;
+ audio->pcm = NULL;
+ audio->substream = NULL;
+ audio->in_ep = NULL;
+}
+
+static void audio_pcm_playback_start(struct audio_dev *audio)
+{
+ audio->start_time = ktime_get();
+ audio->frames_sent = 0;
+ audio_send(audio);
+}
+
+static void audio_pcm_playback_stop(struct audio_dev *audio)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ audio->buffer_start = 0;
+ audio->buffer_end = 0;
+ audio->buffer_pos = 0;
+ spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static int audio_pcm_open(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = substream->private_data;
+
+ runtime->private_data = audio;
+ runtime->hw = audio_hw_info;
+ snd_pcm_limit_hw_rates(runtime);
+ runtime->hw.channels_max = 2;
+
+ audio->substream = substream;
+ return 0;
+}
+
+static int audio_pcm_close(struct snd_pcm_substream *substream)
+{
+ struct audio_dev *audio = substream->private_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&audio->lock, flags);
+ audio->substream = NULL;
+ spin_unlock_irqrestore(&audio->lock, flags);
+
+ return 0;
+}
+
+static int audio_pcm_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params)
+{
+ unsigned int channels = params_channels(params);
+ unsigned int rate = params_rate(params);
+
+ if (rate != SAMPLE_RATE)
+ return -EINVAL;
+ if (channels != 2)
+ return -EINVAL;
+
+ return snd_pcm_lib_alloc_vmalloc_buffer(substream,
+ params_buffer_bytes(params));
+}
+
+static int audio_pcm_hw_free(struct snd_pcm_substream *substream)
+{
+ return snd_pcm_lib_free_vmalloc_buffer(substream);
+}
+
+static int audio_pcm_prepare(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = runtime->private_data;
+
+ audio->period = snd_pcm_lib_period_bytes(substream);
+ audio->period_offset = 0;
+ audio->buffer_start = runtime->dma_area;
+ audio->buffer_end = audio->buffer_start
+ + snd_pcm_lib_buffer_bytes(substream);
+ audio->buffer_pos = audio->buffer_start;
+
+ return 0;
+}
+
+static snd_pcm_uframes_t audio_pcm_pointer(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct audio_dev *audio = runtime->private_data;
+ ssize_t bytes = audio->buffer_pos - audio->buffer_start;
+
+ /* return offset of next frame to fill in our buffer */
+ return bytes_to_frames(runtime, bytes);
+}
+
+static int audio_pcm_playback_trigger(struct snd_pcm_substream *substream,
+ int cmd)
+{
+ struct audio_dev *audio = substream->runtime->private_data;
+ int ret = 0;
+
+ switch (cmd) {
+ case SNDRV_PCM_TRIGGER_START:
+ case SNDRV_PCM_TRIGGER_RESUME:
+ audio_pcm_playback_start(audio);
+ break;
+
+ case SNDRV_PCM_TRIGGER_STOP:
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ audio_pcm_playback_stop(audio);
+ break;
+
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static struct audio_dev _audio_dev = {
+ .func = {
+ .name = "audio_source",
+ .bind = audio_bind,
+ .unbind = audio_unbind,
+ .set_alt = audio_set_alt,
+ .setup = audio_setup,
+ .disable = audio_disable,
+ },
+ .lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock),
+ .idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs),
+};
+
+static struct snd_pcm_ops audio_playback_ops = {
+ .open = audio_pcm_open,
+ .close = audio_pcm_close,
+ .ioctl = snd_pcm_lib_ioctl,
+ .hw_params = audio_pcm_hw_params,
+ .hw_free = audio_pcm_hw_free,
+ .prepare = audio_pcm_prepare,
+ .trigger = audio_pcm_playback_trigger,
+ .pointer = audio_pcm_pointer,
+};
+
+int audio_source_bind_config(struct usb_configuration *c,
+ struct audio_source_config *config)
+{
+ struct audio_dev *audio;
+ struct snd_card *card;
+ struct snd_pcm *pcm;
+ int err;
+
+ config->card = -1;
+ config->device = -1;
+
+ audio = &_audio_dev;
+
+ err = snd_card_create(SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
+ THIS_MODULE, 0, &card);
+ if (err)
+ return err;
+
+ snd_card_set_dev(card, &c->cdev->gadget->dev);
+
+ err = snd_pcm_new(card, "USB audio source", 0, 1, 0, &pcm);
+ if (err)
+ goto pcm_fail;
+ pcm->private_data = audio;
+ pcm->info_flags = 0;
+ audio->pcm = pcm;
+
+ strlcpy(pcm->name, "USB gadget audio", sizeof(pcm->name));
+
+ snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &audio_playback_ops);
+ snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
+ NULL, 0, 64 * 1024);
+
+ strlcpy(card->driver, "audio_source", sizeof(card->driver));
+ strlcpy(card->shortname, card->driver, sizeof(card->shortname));
+ strlcpy(card->longname, "USB accessory audio source",
+ sizeof(card->longname));
+
+ err = snd_card_register(card);
+ if (err)
+ goto register_fail;
+
+ err = usb_add_function(c, &audio->func);
+ if (err)
+ goto add_fail;
+
+ config->card = pcm->card->number;
+ config->device = pcm->device;
+ audio->card = card;
+ return 0;
+
+add_fail:
+register_fail:
+pcm_fail:
+ snd_card_free(audio->card);
+ return err;
+}
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 84219f6..c36f660 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1563,7 +1563,12 @@
spin_lock_irqsave(&func->ffs->eps_lock, flags);
do {
struct usb_endpoint_descriptor *ds;
- ds = ep->descs[ep->descs[1] ? 1 : 0];
+ int desc_idx = ffs->gadget->speed == USB_SPEED_HIGH ? 1 : 0;
+ ds = ep->descs[desc_idx];
+ if (!ds) {
+ ret = -EINVAL;
+ break;
+ }
ep->ep->driver_data = ep;
ep->ep->desc = ds;
diff --git a/drivers/usb/gadget/f_midi.c b/drivers/usb/gadget/f_midi.c
index 263e721..b0bce7e 100644
--- a/drivers/usb/gadget/f_midi.c
+++ b/drivers/usb/gadget/f_midi.c
@@ -65,6 +65,11 @@
uint8_t data[2];
};
+struct midi_alsa_config {
+ int card;
+ int device;
+};
+
struct f_midi {
struct usb_function func;
struct usb_gadget *gadget;
@@ -97,7 +102,7 @@
DECLARE_USB_MS_ENDPOINT_DESCRIPTOR(16);
/* B.3.1 Standard AC Interface Descriptor */
-static struct usb_interface_descriptor ac_interface_desc __initdata = {
+static struct usb_interface_descriptor ac_interface_desc /* __initdata */ = {
.bLength = USB_DT_INTERFACE_SIZE,
.bDescriptorType = USB_DT_INTERFACE,
/* .bInterfaceNumber = DYNAMIC */
@@ -108,7 +113,7 @@
};
/* B.3.2 Class-Specific AC Interface Descriptor */
-static struct uac1_ac_header_descriptor_1 ac_header_desc __initdata = {
+static struct uac1_ac_header_descriptor_1 ac_header_desc /* __initdata */ = {
.bLength = UAC_DT_AC_HEADER_SIZE(1),
.bDescriptorType = USB_DT_CS_INTERFACE,
.bDescriptorSubtype = USB_MS_HEADER,
@@ -119,7 +124,7 @@
};
/* B.4.1 Standard MS Interface Descriptor */
-static struct usb_interface_descriptor ms_interface_desc __initdata = {
+static struct usb_interface_descriptor ms_interface_desc /* __initdata */ = {
.bLength = USB_DT_INTERFACE_SIZE,
.bDescriptorType = USB_DT_INTERFACE,
/* .bInterfaceNumber = DYNAMIC */
@@ -130,7 +135,7 @@
};
/* B.4.2 Class-Specific MS Interface Descriptor */
-static struct usb_ms_header_descriptor ms_header_desc __initdata = {
+static struct usb_ms_header_descriptor ms_header_desc /* __initdata */ = {
.bLength = USB_DT_MS_HEADER_SIZE,
.bDescriptorType = USB_DT_CS_INTERFACE,
.bDescriptorSubtype = USB_MS_HEADER,
@@ -191,7 +196,7 @@
NULL,
};
-static struct usb_request *alloc_ep_req(struct usb_ep *ep, unsigned length)
+static struct usb_request *midi_alloc_ep_req(struct usb_ep *ep, unsigned length)
{
struct usb_request *req;
@@ -207,7 +212,7 @@
return req;
}
-static void free_ep_req(struct usb_ep *ep, struct usb_request *req)
+static void midi_free_ep_req(struct usb_ep *ep, struct usb_request *req)
{
kfree(req->buf);
usb_ep_free_request(ep, req);
@@ -278,7 +283,7 @@
if (ep == midi->out_ep)
f_midi_handle_out_data(ep, req);
- free_ep_req(ep, req);
+ midi_free_ep_req(ep, req);
return;
case -EOVERFLOW: /* buffer overrun on read means that
@@ -365,7 +370,7 @@
/* allocate a bunch of read buffers and queue them all at once. */
for (i = 0; i < midi->qlen && err == 0; i++) {
struct usb_request *req =
- alloc_ep_req(midi->out_ep, midi->buflen);
+ midi_alloc_ep_req(midi->out_ep, midi->buflen);
if (req == NULL)
return -ENOMEM;
@@ -409,7 +414,7 @@
card = midi->card;
midi->card = NULL;
if (card)
- snd_card_free(card);
+ snd_card_free_when_closed(card);
kfree(midi->id);
midi->id = NULL;
@@ -546,10 +551,10 @@
return;
if (!req)
- req = alloc_ep_req(ep, midi->buflen);
+ req = midi_alloc_ep_req(ep, midi->buflen);
if (!req) {
- ERROR(midi, "gmidi_transmit: alloc_ep_request failed\n");
+ ERROR(midi, "gmidi_transmit: midi_alloc_ep_request failed\n");
return;
}
req->length = 0;
@@ -575,7 +580,7 @@
if (req->length > 0)
usb_ep_queue(ep, req, GFP_ATOMIC);
else
- free_ep_req(ep, req);
+ midi_free_ep_req(ep, req);
}
static void f_midi_in_tasklet(unsigned long data)
@@ -733,7 +738,7 @@
/* MIDI function driver setup/binding */
-static int __init
+static int /* __init */
f_midi_bind(struct usb_configuration *c, struct usb_function *f)
{
struct usb_descriptor_header **midi_function;
@@ -923,16 +928,22 @@
*
* Returns zero on success, else negative errno.
*/
-int __init f_midi_bind_config(struct usb_configuration *c,
+int /* __init */ f_midi_bind_config(struct usb_configuration *c,
int index, char *id,
unsigned int in_ports,
unsigned int out_ports,
unsigned int buflen,
- unsigned int qlen)
+ unsigned int qlen,
+ struct midi_alsa_config* config)
{
struct f_midi *midi;
int status, i;
+ if (config) {
+ config->card = -1;
+ config->device = -1;
+ }
+
/* sanity check */
if (in_ports > MAX_PORTS || out_ports > MAX_PORTS)
return -EINVAL;
@@ -961,6 +972,10 @@
tasklet_init(&midi->tasklet, f_midi_in_tasklet, (unsigned long) midi);
/* set up ALSA midi devices */
+ midi->id = kstrdup(id, GFP_KERNEL);
+ midi->index = index;
+ midi->buflen = buflen;
+ midi->qlen = qlen;
midi->in_ports = in_ports;
midi->out_ports = out_ports;
status = f_midi_register_card(midi);
@@ -974,15 +989,16 @@
midi->func.set_alt = f_midi_set_alt;
midi->func.disable = f_midi_disable;
- midi->id = kstrdup(id, GFP_KERNEL);
- midi->index = index;
- midi->buflen = buflen;
- midi->qlen = qlen;
-
status = usb_add_function(c, &midi->func);
if (status)
goto setup_fail;
+
+ if (config) {
+ config->card = midi->rmidi->card->number;
+ config->device = midi->rmidi->device;
+ }
+
return 0;
setup_fail:
diff --git a/drivers/usb/gadget/f_mtp.c b/drivers/usb/gadget/f_mtp.c
new file mode 100644
index 0000000..620aeaa
--- /dev/null
+++ b/drivers/usb/gadget/f_mtp.c
@@ -0,0 +1,1287 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/usb.h>
+#include <linux/usb_usual.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_mtp.h>
+
+#define MTP_BULK_BUFFER_SIZE 16384
+#define INTR_BUFFER_SIZE 28
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX 0
+
+/* values for mtp_dev.state */
+#define STATE_OFFLINE 0 /* initial state, disconnected */
+#define STATE_READY 1 /* ready for userspace calls */
+#define STATE_BUSY 2 /* processing userspace calls */
+#define STATE_CANCELED 3 /* transaction canceled by host */
+#define STATE_ERROR 4 /* error from completion routine */
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+#define INTR_REQ_MAX 5
+
+/* ID for Microsoft MTP OS String */
+#define MTP_OS_STRING_ID 0xEE
+
+/* MTP class reqeusts */
+#define MTP_REQ_CANCEL 0x64
+#define MTP_REQ_GET_EXT_EVENT_DATA 0x65
+#define MTP_REQ_RESET 0x66
+#define MTP_REQ_GET_DEVICE_STATUS 0x67
+
+/* constants for device status */
+#define MTP_RESPONSE_OK 0x2001
+#define MTP_RESPONSE_DEVICE_BUSY 0x2019
+
+static const char mtp_shortname[] = "mtp_usb";
+
+struct mtp_dev {
+ struct usb_function function;
+ struct usb_composite_dev *cdev;
+ spinlock_t lock;
+
+ struct usb_ep *ep_in;
+ struct usb_ep *ep_out;
+ struct usb_ep *ep_intr;
+
+ int state;
+
+ /* synchronize access to our device file */
+ atomic_t open_excl;
+ /* to enforce only one ioctl at a time */
+ atomic_t ioctl_excl;
+
+ struct list_head tx_idle;
+ struct list_head intr_idle;
+
+ wait_queue_head_t read_wq;
+ wait_queue_head_t write_wq;
+ wait_queue_head_t intr_wq;
+ struct usb_request *rx_req[RX_REQ_MAX];
+ int rx_done;
+
+ /* for processing MTP_SEND_FILE, MTP_RECEIVE_FILE and
+ * MTP_SEND_FILE_WITH_HEADER ioctls on a work queue
+ */
+ struct workqueue_struct *wq;
+ struct work_struct send_file_work;
+ struct work_struct receive_file_work;
+ struct file *xfer_file;
+ loff_t xfer_file_offset;
+ int64_t xfer_file_length;
+ unsigned xfer_send_header;
+ uint16_t xfer_command;
+ uint32_t xfer_transaction_id;
+ int xfer_result;
+};
+
+static struct usb_interface_descriptor mtp_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 3,
+ .bInterfaceClass = USB_CLASS_VENDOR_SPEC,
+ .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC,
+ .bInterfaceProtocol = 0,
+};
+
+static struct usb_interface_descriptor ptp_interface_desc = {
+ .bLength = USB_DT_INTERFACE_SIZE,
+ .bDescriptorType = USB_DT_INTERFACE,
+ .bInterfaceNumber = 0,
+ .bNumEndpoints = 3,
+ .bInterfaceClass = USB_CLASS_STILL_IMAGE,
+ .bInterfaceSubClass = 1,
+ .bInterfaceProtocol = 1,
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+ .wMaxPacketSize = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_in_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_out_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_OUT,
+ .bmAttributes = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_intr_desc = {
+ .bLength = USB_DT_ENDPOINT_SIZE,
+ .bDescriptorType = USB_DT_ENDPOINT,
+ .bEndpointAddress = USB_DIR_IN,
+ .bmAttributes = USB_ENDPOINT_XFER_INT,
+ .wMaxPacketSize = __constant_cpu_to_le16(INTR_BUFFER_SIZE),
+ .bInterval = 6,
+};
+
+static struct usb_descriptor_header *fs_mtp_descs[] = {
+ (struct usb_descriptor_header *) &mtp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_mtp_descs[] = {
+ (struct usb_descriptor_header *) &mtp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *fs_ptp_descs[] = {
+ (struct usb_descriptor_header *) &ptp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_descriptor_header *hs_ptp_descs[] = {
+ (struct usb_descriptor_header *) &ptp_interface_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+ (struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+ (struct usb_descriptor_header *) &mtp_intr_desc,
+ NULL,
+};
+
+static struct usb_string mtp_string_defs[] = {
+ /* Naming interface "MTP" so libmtp will recognize us */
+ [INTERFACE_STRING_INDEX].s = "MTP",
+ { }, /* end of list */
+};
+
+static struct usb_gadget_strings mtp_string_table = {
+ .language = 0x0409, /* en-US */
+ .strings = mtp_string_defs,
+};
+
+static struct usb_gadget_strings *mtp_strings[] = {
+ &mtp_string_table,
+ NULL,
+};
+
+/* Microsoft MTP OS String */
+static u8 mtp_os_string[] = {
+ 18, /* sizeof(mtp_os_string) */
+ USB_DT_STRING,
+ /* Signature field: "MSFT100" */
+ 'M', 0, 'S', 0, 'F', 0, 'T', 0, '1', 0, '0', 0, '0', 0,
+ /* vendor code */
+ 1,
+ /* padding */
+ 0
+};
+
+/* Microsoft Extended Configuration Descriptor Header Section */
+struct mtp_ext_config_desc_header {
+ __le32 dwLength;
+ __u16 bcdVersion;
+ __le16 wIndex;
+ __u8 bCount;
+ __u8 reserved[7];
+};
+
+/* Microsoft Extended Configuration Descriptor Function Section */
+struct mtp_ext_config_desc_function {
+ __u8 bFirstInterfaceNumber;
+ __u8 bInterfaceCount;
+ __u8 compatibleID[8];
+ __u8 subCompatibleID[8];
+ __u8 reserved[6];
+};
+
+/* MTP Extended Configuration Descriptor */
+struct {
+ struct mtp_ext_config_desc_header header;
+ struct mtp_ext_config_desc_function function;
+} mtp_ext_config_desc = {
+ .header = {
+ .dwLength = __constant_cpu_to_le32(sizeof(mtp_ext_config_desc)),
+ .bcdVersion = __constant_cpu_to_le16(0x0100),
+ .wIndex = __constant_cpu_to_le16(4),
+ .bCount = __constant_cpu_to_le16(1),
+ },
+ .function = {
+ .bFirstInterfaceNumber = 0,
+ .bInterfaceCount = 1,
+ .compatibleID = { 'M', 'T', 'P' },
+ },
+};
+
+struct mtp_device_status {
+ __le16 wLength;
+ __le16 wCode;
+};
+
+struct mtp_data_header {
+ /* length of packet, including this header */
+ __le32 length;
+ /* container type (2 for data packet) */
+ __le16 type;
+ /* MTP command code */
+ __le16 command;
+ /* MTP transaction ID */
+ __le32 transaction_id;
+};
+
+/* temporary variable used between mtp_open() and mtp_gadget_bind() */
+static struct mtp_dev *_mtp_dev;
+
+static inline struct mtp_dev *func_to_mtp(struct usb_function *f)
+{
+ return container_of(f, struct mtp_dev, function);
+}
+
+static struct usb_request *mtp_request_new(struct usb_ep *ep, int buffer_size)
+{
+ struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+ if (!req)
+ return NULL;
+
+ /* now allocate buffers for the requests */
+ req->buf = kmalloc(buffer_size, GFP_KERNEL);
+ if (!req->buf) {
+ usb_ep_free_request(ep, req);
+ return NULL;
+ }
+
+ return req;
+}
+
+static void mtp_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+ if (req) {
+ kfree(req->buf);
+ usb_ep_free_request(ep, req);
+ }
+}
+
+static inline int mtp_lock(atomic_t *excl)
+{
+ if (atomic_inc_return(excl) == 1) {
+ return 0;
+ } else {
+ atomic_dec(excl);
+ return -1;
+ }
+}
+
+static inline void mtp_unlock(atomic_t *excl)
+{
+ atomic_dec(excl);
+}
+
+/* add a request to the tail of a list */
+static void mtp_req_put(struct mtp_dev *dev, struct list_head *head,
+ struct usb_request *req)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ list_add_tail(&req->list, head);
+ spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request
+*mtp_req_get(struct mtp_dev *dev, struct list_head *head)
+{
+ unsigned long flags;
+ struct usb_request *req;
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (list_empty(head)) {
+ req = 0;
+ } else {
+ req = list_first_entry(head, struct usb_request, list);
+ list_del(&req->list);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+ return req;
+}
+
+static void mtp_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ wake_up(&dev->write_wq);
+}
+
+static void mtp_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ dev->rx_done = 1;
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ wake_up(&dev->read_wq);
+}
+
+static void mtp_complete_intr(struct usb_ep *ep, struct usb_request *req)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (req->status != 0)
+ dev->state = STATE_ERROR;
+
+ mtp_req_put(dev, &dev->intr_idle, req);
+
+ wake_up(&dev->intr_wq);
+}
+
+static int mtp_create_bulk_endpoints(struct mtp_dev *dev,
+ struct usb_endpoint_descriptor *in_desc,
+ struct usb_endpoint_descriptor *out_desc,
+ struct usb_endpoint_descriptor *intr_desc)
+{
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ struct usb_ep *ep;
+ int i;
+
+ DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+ ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_in = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for mtp ep_out got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_out = ep;
+
+ ep = usb_ep_autoconfig(cdev->gadget, intr_desc);
+ if (!ep) {
+ DBG(cdev, "usb_ep_autoconfig for ep_intr failed\n");
+ return -ENODEV;
+ }
+ DBG(cdev, "usb_ep_autoconfig for mtp ep_intr got %s\n", ep->name);
+ ep->driver_data = dev; /* claim the endpoint */
+ dev->ep_intr = ep;
+
+ /* now allocate requests for our endpoints */
+ for (i = 0; i < TX_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_in, MTP_BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_in;
+ mtp_req_put(dev, &dev->tx_idle, req);
+ }
+ for (i = 0; i < RX_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_out, MTP_BULK_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_out;
+ dev->rx_req[i] = req;
+ }
+ for (i = 0; i < INTR_REQ_MAX; i++) {
+ req = mtp_request_new(dev->ep_intr, INTR_BUFFER_SIZE);
+ if (!req)
+ goto fail;
+ req->complete = mtp_complete_intr;
+ mtp_req_put(dev, &dev->intr_idle, req);
+ }
+
+ return 0;
+
+fail:
+ printk(KERN_ERR "mtp_bind() could not allocate requests\n");
+ return -1;
+}
+
+static ssize_t mtp_read(struct file *fp, char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req;
+ ssize_t r = count;
+ unsigned xfer;
+ int ret = 0;
+
+ DBG(cdev, "mtp_read(%zu)\n", count);
+
+ if (count > MTP_BULK_BUFFER_SIZE)
+ return -EINVAL;
+
+ /* we will block until we're online */
+ DBG(cdev, "mtp_read: waiting for online state\n");
+ ret = wait_event_interruptible(dev->read_wq,
+ dev->state != STATE_OFFLINE);
+ if (ret < 0) {
+ r = ret;
+ goto done;
+ }
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ return -ECANCELED;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+requeue_req:
+ /* queue a request */
+ req = dev->rx_req[0];
+ req->length = count;
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ goto done;
+ } else {
+ DBG(cdev, "rx %p queue\n", req);
+ }
+
+ /* wait for a request to complete */
+ ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+ if (ret < 0) {
+ r = ret;
+ usb_ep_dequeue(dev->ep_out, req);
+ goto done;
+ }
+ if (dev->state == STATE_BUSY) {
+ /* If we got a 0-len packet, throw it back and try again. */
+ if (req->actual == 0)
+ goto requeue_req;
+
+ DBG(cdev, "rx %p %d\n", req, req->actual);
+ xfer = (req->actual < count) ? req->actual : count;
+ r = xfer;
+ if (copy_to_user(buf, req->buf, xfer))
+ r = -EFAULT;
+ } else
+ r = -EIO;
+
+done:
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ r = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+
+ DBG(cdev, "mtp_read returning %zd\n", r);
+ return r;
+}
+
+static ssize_t mtp_write(struct file *fp, const char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req = 0;
+ ssize_t r = count;
+ unsigned xfer;
+ int sendZLP = 0;
+ int ret;
+
+ DBG(cdev, "mtp_write(%zu)\n", count);
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ return -ECANCELED;
+ }
+ if (dev->state == STATE_OFFLINE) {
+ spin_unlock_irq(&dev->lock);
+ return -ENODEV;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+ /* we need to send a zero length packet to signal the end of transfer
+ * if the transfer size is aligned to a packet boundary.
+ */
+ if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+ sendZLP = 1;
+
+ while (count > 0 || sendZLP) {
+ /* so we exit after sending ZLP */
+ if (count == 0)
+ sendZLP = 0;
+
+ if (dev->state != STATE_BUSY) {
+ DBG(cdev, "mtp_write dev->error\n");
+ r = -EIO;
+ break;
+ }
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ ((req = mtp_req_get(dev, &dev->tx_idle))
+ || dev->state != STATE_BUSY));
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > MTP_BULK_BUFFER_SIZE)
+ xfer = MTP_BULK_BUFFER_SIZE;
+ else
+ xfer = count;
+ if (xfer && copy_from_user(req->buf, buf, xfer)) {
+ r = -EFAULT;
+ break;
+ }
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ DBG(cdev, "mtp_write: xfer error %d\n", ret);
+ r = -EIO;
+ break;
+ }
+
+ buf += xfer;
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ r = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+
+ DBG(cdev, "mtp_write returning %zd\n", r);
+ return r;
+}
+
+/* read from a local file and write to USB */
+static void send_file_work(struct work_struct *data)
+{
+ struct mtp_dev *dev = container_of(data, struct mtp_dev,
+ send_file_work);
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *req = 0;
+ struct mtp_data_header *header;
+ struct file *filp;
+ loff_t offset;
+ int64_t count;
+ int xfer, ret, hdr_size;
+ int r = 0;
+ int sendZLP = 0;
+
+ /* read our parameters */
+ smp_rmb();
+ filp = dev->xfer_file;
+ offset = dev->xfer_file_offset;
+ count = dev->xfer_file_length;
+
+ DBG(cdev, "send_file_work(%lld %lld)\n", offset, count);
+
+ if (dev->xfer_send_header) {
+ hdr_size = sizeof(struct mtp_data_header);
+ count += hdr_size;
+ } else {
+ hdr_size = 0;
+ }
+
+ /* we need to send a zero length packet to signal the end of transfer
+ * if the transfer size is aligned to a packet boundary.
+ */
+ if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+ sendZLP = 1;
+
+ while (count > 0 || sendZLP) {
+ /* so we exit after sending ZLP */
+ if (count == 0)
+ sendZLP = 0;
+
+ /* get an idle tx request to use */
+ req = 0;
+ ret = wait_event_interruptible(dev->write_wq,
+ (req = mtp_req_get(dev, &dev->tx_idle))
+ || dev->state != STATE_BUSY);
+ if (dev->state == STATE_CANCELED) {
+ r = -ECANCELED;
+ break;
+ }
+ if (!req) {
+ r = ret;
+ break;
+ }
+
+ if (count > MTP_BULK_BUFFER_SIZE)
+ xfer = MTP_BULK_BUFFER_SIZE;
+ else
+ xfer = count;
+
+ if (hdr_size) {
+ /* prepend MTP data header */
+ header = (struct mtp_data_header *)req->buf;
+ header->length = __cpu_to_le32(count);
+ header->type = __cpu_to_le16(2); /* data packet */
+ header->command = __cpu_to_le16(dev->xfer_command);
+ header->transaction_id =
+ __cpu_to_le32(dev->xfer_transaction_id);
+ }
+
+ ret = vfs_read(filp, req->buf + hdr_size, xfer - hdr_size,
+ &offset);
+ if (ret < 0) {
+ r = ret;
+ break;
+ }
+ xfer = ret + hdr_size;
+ hdr_size = 0;
+
+ req->length = xfer;
+ ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+ if (ret < 0) {
+ DBG(cdev, "send_file_work: xfer error %d\n", ret);
+ dev->state = STATE_ERROR;
+ r = -EIO;
+ break;
+ }
+
+ count -= xfer;
+
+ /* zero this so we don't try to free it on error exit */
+ req = 0;
+ }
+
+ if (req)
+ mtp_req_put(dev, &dev->tx_idle, req);
+
+ DBG(cdev, "send_file_work returning %d\n", r);
+ /* write the result */
+ dev->xfer_result = r;
+ smp_wmb();
+}
+
+/* read from USB and write to a local file */
+static void receive_file_work(struct work_struct *data)
+{
+ struct mtp_dev *dev = container_of(data, struct mtp_dev,
+ receive_file_work);
+ struct usb_composite_dev *cdev = dev->cdev;
+ struct usb_request *read_req = NULL, *write_req = NULL;
+ struct file *filp;
+ loff_t offset;
+ int64_t count;
+ int ret, cur_buf = 0;
+ int r = 0;
+
+ /* read our parameters */
+ smp_rmb();
+ filp = dev->xfer_file;
+ offset = dev->xfer_file_offset;
+ count = dev->xfer_file_length;
+
+ DBG(cdev, "receive_file_work(%lld)\n", count);
+
+ while (count > 0 || write_req) {
+ if (count > 0) {
+ /* queue a request */
+ read_req = dev->rx_req[cur_buf];
+ cur_buf = (cur_buf + 1) % RX_REQ_MAX;
+
+ read_req->length = (count > MTP_BULK_BUFFER_SIZE
+ ? MTP_BULK_BUFFER_SIZE : count);
+ dev->rx_done = 0;
+ ret = usb_ep_queue(dev->ep_out, read_req, GFP_KERNEL);
+ if (ret < 0) {
+ r = -EIO;
+ dev->state = STATE_ERROR;
+ break;
+ }
+ }
+
+ if (write_req) {
+ DBG(cdev, "rx %p %d\n", write_req, write_req->actual);
+ ret = vfs_write(filp, write_req->buf, write_req->actual,
+ &offset);
+ DBG(cdev, "vfs_write %d\n", ret);
+ if (ret != write_req->actual) {
+ r = -EIO;
+ dev->state = STATE_ERROR;
+ break;
+ }
+ write_req = NULL;
+ }
+
+ if (read_req) {
+ /* wait for our last read to complete */
+ ret = wait_event_interruptible(dev->read_wq,
+ dev->rx_done || dev->state != STATE_BUSY);
+ if (dev->state == STATE_CANCELED) {
+ r = -ECANCELED;
+ if (!dev->rx_done)
+ usb_ep_dequeue(dev->ep_out, read_req);
+ break;
+ }
+ /* if xfer_file_length is 0xFFFFFFFF, then we read until
+ * we get a zero length packet
+ */
+ if (count != 0xFFFFFFFF)
+ count -= read_req->actual;
+ if (read_req->actual < read_req->length) {
+ /*
+ * short packet is used to signal EOF for
+ * sizes > 4 gig
+ */
+ DBG(cdev, "got short packet\n");
+ count = 0;
+ }
+
+ write_req = read_req;
+ read_req = NULL;
+ }
+ }
+
+ DBG(cdev, "receive_file_work returning %d\n", r);
+ /* write the result */
+ dev->xfer_result = r;
+ smp_wmb();
+}
+
+static int mtp_send_event(struct mtp_dev *dev, struct mtp_event *event)
+{
+ struct usb_request *req = NULL;
+ int ret;
+ int length = event->length;
+
+ DBG(dev->cdev, "mtp_send_event(%zu)\n", event->length);
+
+ if (length < 0 || length > INTR_BUFFER_SIZE)
+ return -EINVAL;
+ if (dev->state == STATE_OFFLINE)
+ return -ENODEV;
+
+ ret = wait_event_interruptible_timeout(dev->intr_wq,
+ (req = mtp_req_get(dev, &dev->intr_idle)),
+ msecs_to_jiffies(1000));
+ if (!req)
+ return -ETIME;
+
+ if (copy_from_user(req->buf, (void __user *)event->data, length)) {
+ mtp_req_put(dev, &dev->intr_idle, req);
+ return -EFAULT;
+ }
+ req->length = length;
+ ret = usb_ep_queue(dev->ep_intr, req, GFP_KERNEL);
+ if (ret)
+ mtp_req_put(dev, &dev->intr_idle, req);
+
+ return ret;
+}
+
+static long mtp_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+ struct mtp_dev *dev = fp->private_data;
+ struct file *filp = NULL;
+ int ret = -EINVAL;
+
+ if (mtp_lock(&dev->ioctl_excl))
+ return -EBUSY;
+
+ switch (code) {
+ case MTP_SEND_FILE:
+ case MTP_RECEIVE_FILE:
+ case MTP_SEND_FILE_WITH_HEADER:
+ {
+ struct mtp_file_range mfr;
+ struct work_struct *work;
+
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED) {
+ /* report cancelation to userspace */
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+ ret = -ECANCELED;
+ goto out;
+ }
+ if (dev->state == STATE_OFFLINE) {
+ spin_unlock_irq(&dev->lock);
+ ret = -ENODEV;
+ goto out;
+ }
+ dev->state = STATE_BUSY;
+ spin_unlock_irq(&dev->lock);
+
+ if (copy_from_user(&mfr, (void __user *)value, sizeof(mfr))) {
+ ret = -EFAULT;
+ goto fail;
+ }
+ /* hold a reference to the file while we are working with it */
+ filp = fget(mfr.fd);
+ if (!filp) {
+ ret = -EBADF;
+ goto fail;
+ }
+
+ /* write the parameters */
+ dev->xfer_file = filp;
+ dev->xfer_file_offset = mfr.offset;
+ dev->xfer_file_length = mfr.length;
+ smp_wmb();
+
+ if (code == MTP_SEND_FILE_WITH_HEADER) {
+ work = &dev->send_file_work;
+ dev->xfer_send_header = 1;
+ dev->xfer_command = mfr.command;
+ dev->xfer_transaction_id = mfr.transaction_id;
+ } else if (code == MTP_SEND_FILE) {
+ work = &dev->send_file_work;
+ dev->xfer_send_header = 0;
+ } else {
+ work = &dev->receive_file_work;
+ }
+
+ /* We do the file transfer on a work queue so it will run
+ * in kernel context, which is necessary for vfs_read and
+ * vfs_write to use our buffers in the kernel address space.
+ */
+ queue_work(dev->wq, work);
+ /* wait for operation to complete */
+ flush_workqueue(dev->wq);
+ fput(filp);
+
+ /* read the result */
+ smp_rmb();
+ ret = dev->xfer_result;
+ break;
+ }
+ case MTP_SEND_EVENT:
+ {
+ struct mtp_event event;
+ /* return here so we don't change dev->state below,
+ * which would interfere with bulk transfer state.
+ */
+ if (copy_from_user(&event, (void __user *)value, sizeof(event)))
+ ret = -EFAULT;
+ else
+ ret = mtp_send_event(dev, &event);
+ goto out;
+ }
+ }
+
+fail:
+ spin_lock_irq(&dev->lock);
+ if (dev->state == STATE_CANCELED)
+ ret = -ECANCELED;
+ else if (dev->state != STATE_OFFLINE)
+ dev->state = STATE_READY;
+ spin_unlock_irq(&dev->lock);
+out:
+ mtp_unlock(&dev->ioctl_excl);
+ DBG(dev->cdev, "ioctl returning %d\n", ret);
+ return ret;
+}
+
+static int mtp_open(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "mtp_open\n");
+ if (mtp_lock(&_mtp_dev->open_excl))
+ return -EBUSY;
+
+ /* clear any error condition */
+ if (_mtp_dev->state != STATE_OFFLINE)
+ _mtp_dev->state = STATE_READY;
+
+ fp->private_data = _mtp_dev;
+ return 0;
+}
+
+static int mtp_release(struct inode *ip, struct file *fp)
+{
+ printk(KERN_INFO "mtp_release\n");
+
+ mtp_unlock(&_mtp_dev->open_excl);
+ return 0;
+}
+
+/* file operations for /dev/mtp_usb */
+static const struct file_operations mtp_fops = {
+ .owner = THIS_MODULE,
+ .read = mtp_read,
+ .write = mtp_write,
+ .unlocked_ioctl = mtp_ioctl,
+ .open = mtp_open,
+ .release = mtp_release,
+};
+
+static struct miscdevice mtp_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = mtp_shortname,
+ .fops = &mtp_fops,
+};
+
+static int mtp_ctrlrequest(struct usb_composite_dev *cdev,
+ const struct usb_ctrlrequest *ctrl)
+{
+ struct mtp_dev *dev = _mtp_dev;
+ int value = -EOPNOTSUPP;
+ u16 w_index = le16_to_cpu(ctrl->wIndex);
+ u16 w_value = le16_to_cpu(ctrl->wValue);
+ u16 w_length = le16_to_cpu(ctrl->wLength);
+ unsigned long flags;
+
+ VDBG(cdev, "mtp_ctrlrequest "
+ "%02x.%02x v%04x i%04x l%u\n",
+ ctrl->bRequestType, ctrl->bRequest,
+ w_value, w_index, w_length);
+
+ /* Handle MTP OS string */
+ if (ctrl->bRequestType ==
+ (USB_DIR_IN | USB_TYPE_STANDARD | USB_RECIP_DEVICE)
+ && ctrl->bRequest == USB_REQ_GET_DESCRIPTOR
+ && (w_value >> 8) == USB_DT_STRING
+ && (w_value & 0xFF) == MTP_OS_STRING_ID) {
+ value = (w_length < sizeof(mtp_os_string)
+ ? w_length : sizeof(mtp_os_string));
+ memcpy(cdev->req->buf, mtp_os_string, value);
+ } else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_VENDOR) {
+ /* Handle MTP OS descriptor */
+ DBG(cdev, "vendor request: %d index: %d value: %d length: %d\n",
+ ctrl->bRequest, w_index, w_value, w_length);
+
+ if (ctrl->bRequest == 1
+ && (ctrl->bRequestType & USB_DIR_IN)
+ && (w_index == 4 || w_index == 5)) {
+ value = (w_length < sizeof(mtp_ext_config_desc) ?
+ w_length : sizeof(mtp_ext_config_desc));
+ memcpy(cdev->req->buf, &mtp_ext_config_desc, value);
+ }
+ } else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+ DBG(cdev, "class request: %d index: %d value: %d length: %d\n",
+ ctrl->bRequest, w_index, w_value, w_length);
+
+ if (ctrl->bRequest == MTP_REQ_CANCEL && w_index == 0
+ && w_value == 0) {
+ DBG(cdev, "MTP_REQ_CANCEL\n");
+
+ spin_lock_irqsave(&dev->lock, flags);
+ if (dev->state == STATE_BUSY) {
+ dev->state = STATE_CANCELED;
+ wake_up(&dev->read_wq);
+ wake_up(&dev->write_wq);
+ }
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ /* We need to queue a request to read the remaining
+ * bytes, but we don't actually need to look at
+ * the contents.
+ */
+ value = w_length;
+ } else if (ctrl->bRequest == MTP_REQ_GET_DEVICE_STATUS
+ && w_index == 0 && w_value == 0) {
+ struct mtp_device_status *status = cdev->req->buf;
+ status->wLength =
+ __constant_cpu_to_le16(sizeof(*status));
+
+ DBG(cdev, "MTP_REQ_GET_DEVICE_STATUS\n");
+ spin_lock_irqsave(&dev->lock, flags);
+ /* device status is "busy" until we report
+ * the cancelation to userspace
+ */
+ if (dev->state == STATE_CANCELED)
+ status->wCode =
+ __cpu_to_le16(MTP_RESPONSE_DEVICE_BUSY);
+ else
+ status->wCode =
+ __cpu_to_le16(MTP_RESPONSE_OK);
+ spin_unlock_irqrestore(&dev->lock, flags);
+ value = sizeof(*status);
+ }
+ }
+
+ /* respond with data transfer or status phase? */
+ if (value >= 0) {
+ int rc;
+ cdev->req->zero = value < w_length;
+ cdev->req->length = value;
+ rc = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+ if (rc < 0)
+ ERROR(cdev, "%s: response queue error\n", __func__);
+ }
+ return value;
+}
+
+static int
+mtp_function_bind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct usb_composite_dev *cdev = c->cdev;
+ struct mtp_dev *dev = func_to_mtp(f);
+ int id;
+ int ret;
+
+ dev->cdev = cdev;
+ DBG(cdev, "mtp_function_bind dev: %p\n", dev);
+
+ /* allocate interface ID(s) */
+ id = usb_interface_id(c, f);
+ if (id < 0)
+ return id;
+ mtp_interface_desc.bInterfaceNumber = id;
+
+ /* allocate endpoints */
+ ret = mtp_create_bulk_endpoints(dev, &mtp_fullspeed_in_desc,
+ &mtp_fullspeed_out_desc, &mtp_intr_desc);
+ if (ret)
+ return ret;
+
+ /* support high speed hardware */
+ if (gadget_is_dualspeed(c->cdev->gadget)) {
+ mtp_highspeed_in_desc.bEndpointAddress =
+ mtp_fullspeed_in_desc.bEndpointAddress;
+ mtp_highspeed_out_desc.bEndpointAddress =
+ mtp_fullspeed_out_desc.bEndpointAddress;
+ }
+
+ DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+ gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+ f->name, dev->ep_in->name, dev->ep_out->name);
+ return 0;
+}
+
+static void
+mtp_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_request *req;
+ int i;
+
+ while ((req = mtp_req_get(dev, &dev->tx_idle)))
+ mtp_request_free(req, dev->ep_in);
+ for (i = 0; i < RX_REQ_MAX; i++)
+ mtp_request_free(dev->rx_req[i], dev->ep_out);
+ while ((req = mtp_req_get(dev, &dev->intr_idle)))
+ mtp_request_free(req, dev->ep_intr);
+ dev->state = STATE_OFFLINE;
+}
+
+static int mtp_function_set_alt(struct usb_function *f,
+ unsigned intf, unsigned alt)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_composite_dev *cdev = f->config->cdev;
+ int ret;
+
+ DBG(cdev, "mtp_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_in);
+ if (ret)
+ return ret;
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_out);
+ if (ret) {
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+
+ ret = config_ep_by_speed(cdev->gadget, f, dev->ep_intr);
+ if (ret)
+ return ret;
+
+ ret = usb_ep_enable(dev->ep_intr);
+ if (ret) {
+ usb_ep_disable(dev->ep_out);
+ usb_ep_disable(dev->ep_in);
+ return ret;
+ }
+ dev->state = STATE_READY;
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+ return 0;
+}
+
+static void mtp_function_disable(struct usb_function *f)
+{
+ struct mtp_dev *dev = func_to_mtp(f);
+ struct usb_composite_dev *cdev = dev->cdev;
+
+ DBG(cdev, "mtp_function_disable\n");
+ dev->state = STATE_OFFLINE;
+ usb_ep_disable(dev->ep_in);
+ usb_ep_disable(dev->ep_out);
+ usb_ep_disable(dev->ep_intr);
+
+ /* readers may be blocked waiting for us to go online */
+ wake_up(&dev->read_wq);
+
+ VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int mtp_bind_config(struct usb_configuration *c, bool ptp_config)
+{
+ struct mtp_dev *dev = _mtp_dev;
+ int ret = 0;
+
+ printk(KERN_INFO "mtp_bind_config\n");
+
+ /* allocate a string ID for our interface */
+ if (mtp_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+ ret = usb_string_id(c->cdev);
+ if (ret < 0)
+ return ret;
+ mtp_string_defs[INTERFACE_STRING_INDEX].id = ret;
+ mtp_interface_desc.iInterface = ret;
+ }
+
+ dev->cdev = c->cdev;
+ dev->function.name = "mtp";
+ dev->function.strings = mtp_strings;
+ if (ptp_config) {
+ dev->function.fs_descriptors = fs_ptp_descs;
+ dev->function.hs_descriptors = hs_ptp_descs;
+ } else {
+ dev->function.fs_descriptors = fs_mtp_descs;
+ dev->function.hs_descriptors = hs_mtp_descs;
+ }
+ dev->function.bind = mtp_function_bind;
+ dev->function.unbind = mtp_function_unbind;
+ dev->function.set_alt = mtp_function_set_alt;
+ dev->function.disable = mtp_function_disable;
+
+ return usb_add_function(c, &dev->function);
+}
+
+static int mtp_setup(void)
+{
+ struct mtp_dev *dev;
+ int ret;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ return -ENOMEM;
+
+ spin_lock_init(&dev->lock);
+ init_waitqueue_head(&dev->read_wq);
+ init_waitqueue_head(&dev->write_wq);
+ init_waitqueue_head(&dev->intr_wq);
+ atomic_set(&dev->open_excl, 0);
+ atomic_set(&dev->ioctl_excl, 0);
+ INIT_LIST_HEAD(&dev->tx_idle);
+ INIT_LIST_HEAD(&dev->intr_idle);
+
+ dev->wq = create_singlethread_workqueue("f_mtp");
+ if (!dev->wq) {
+ ret = -ENOMEM;
+ goto err1;
+ }
+ INIT_WORK(&dev->send_file_work, send_file_work);
+ INIT_WORK(&dev->receive_file_work, receive_file_work);
+
+ _mtp_dev = dev;
+
+ ret = misc_register(&mtp_device);
+ if (ret)
+ goto err2;
+
+ return 0;
+
+err2:
+ destroy_workqueue(dev->wq);
+err1:
+ _mtp_dev = NULL;
+ kfree(dev);
+ printk(KERN_ERR "mtp gadget driver failed to initialize\n");
+ return ret;
+}
+
+static void mtp_cleanup(void)
+{
+ struct mtp_dev *dev = _mtp_dev;
+
+ if (!dev)
+ return;
+
+ misc_deregister(&mtp_device);
+ destroy_workqueue(dev->wq);
+ _mtp_dev = NULL;
+ kfree(dev);
+}
diff --git a/drivers/usb/gadget/f_rndis.c b/drivers/usb/gadget/f_rndis.c
index 36e8c44..5c274f1 100644
--- a/drivers/usb/gadget/f_rndis.c
+++ b/drivers/usb/gadget/f_rndis.c
@@ -25,7 +25,6 @@
#include "u_ether.h"
#include "rndis.h"
-
/*
* This function is an RNDIS Ethernet port -- a Microsoft protocol that's
* been promoted instead of the standard CDC Ethernet. The published RNDIS
@@ -67,6 +66,16 @@
* - MS-Windows drivers sometimes emit undocumented requests.
*/
+static unsigned int rndis_dl_max_pkt_per_xfer = 3;
+module_param(rndis_dl_max_pkt_per_xfer, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(rndis_dl_max_pkt_per_xfer,
+ "Maximum packets per transfer for DL aggregation");
+
+static unsigned int rndis_ul_max_pkt_per_xfer = 3;
+module_param(rndis_ul_max_pkt_per_xfer, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(rndis_ul_max_pkt_per_xfer,
+ "Maximum packets per transfer for UL aggregation");
+
struct f_rndis {
struct gether port;
u8 ctrl_id, data_id;
@@ -448,6 +457,7 @@
{
struct f_rndis *rndis = req->context;
int status;
+ rndis_init_msg_type *buf;
/* received RNDIS command from USB_CDC_SEND_ENCAPSULATED_COMMAND */
// spin_lock(&dev->lock);
@@ -455,6 +465,21 @@
if (status < 0)
pr_err("RNDIS command error %d, %d/%d\n",
status, req->actual, req->length);
+
+ buf = (rndis_init_msg_type *)req->buf;
+
+ if (buf->MessageType == RNDIS_MSG_INIT) {
+ if (buf->MaxTransferSize > 2048)
+ rndis->port.multi_pkt_xfer = 1;
+ else
+ rndis->port.multi_pkt_xfer = 0;
+ pr_info("%s: MaxTransferSize: %d : Multi_pkt_txr: %s\n",
+ __func__, buf->MaxTransferSize,
+ rndis->port.multi_pkt_xfer ? "enabled" :
+ "disabled");
+ if (rndis_dl_max_pkt_per_xfer <= 1)
+ rndis->port.multi_pkt_xfer = 0;
+ }
// spin_unlock(&dev->lock);
}
@@ -748,6 +773,7 @@
rndis_set_param_medium(rndis->config, RNDIS_MEDIUM_802_3, 0);
rndis_set_host_mac(rndis->config, rndis->ethaddr);
+ rndis_set_max_pkt_xfer(rndis->config, rndis_ul_max_pkt_per_xfer);
if (rndis->manufacturer && rndis->vendorID &&
rndis_set_param_vendor(rndis->config, rndis->vendorID,
@@ -821,12 +847,12 @@
if (!can_support_rndis(c) || !ethaddr)
return -EINVAL;
- if (rndis_string_defs[0].id == 0) {
- /* ... and setup RNDIS itself */
- status = rndis_init();
- if (status < 0)
- return status;
+ /* setup RNDIS itself */
+ status = rndis_init();
+ if (status < 0)
+ return status;
+ if (rndis_string_defs[0].id == 0) {
status = usb_string_ids_tab(c->cdev, rndis_string_defs);
if (status)
return status;
@@ -854,6 +880,8 @@
rndis->port.header_len = sizeof(struct rndis_packet_msg_type);
rndis->port.wrap = rndis_add_header;
rndis->port.unwrap = rndis_rm_hdr;
+ rndis->port.ul_max_pkts_per_xfer = rndis_ul_max_pkt_per_xfer;
+ rndis->port.dl_max_pkts_per_xfer = rndis_dl_max_pkt_per_xfer;
rndis->port.func.name = "rndis";
rndis->port.func.strings = rndis_strings;
diff --git a/drivers/usb/gadget/rndis.c b/drivers/usb/gadget/rndis.c
index 1e4cfb0..cb2767d 100644
--- a/drivers/usb/gadget/rndis.c
+++ b/drivers/usb/gadget/rndis.c
@@ -59,6 +59,16 @@
#define RNDIS_MAX_CONFIGS 1
+int rndis_ul_max_pkt_per_xfer_rcvd;
+module_param(rndis_ul_max_pkt_per_xfer_rcvd, int, S_IRUGO);
+MODULE_PARM_DESC(rndis_ul_max_pkt_per_xfer_rcvd,
+ "Max num of REMOTE_NDIS_PACKET_MSGs received in a single transfer");
+
+int rndis_ul_max_xfer_size_rcvd;
+module_param(rndis_ul_max_xfer_size_rcvd, int, S_IRUGO);
+MODULE_PARM_DESC(rndis_ul_max_xfer_size_rcvd,
+ "Max size of bus transfer received");
+
static rndis_params rndis_per_dev_params[RNDIS_MAX_CONFIGS];
@@ -585,12 +595,12 @@
resp->MinorVersion = cpu_to_le32(RNDIS_MINOR_VERSION);
resp->DeviceFlags = cpu_to_le32(RNDIS_DF_CONNECTIONLESS);
resp->Medium = cpu_to_le32(RNDIS_MEDIUM_802_3);
- resp->MaxPacketsPerTransfer = cpu_to_le32(1);
- resp->MaxTransferSize = cpu_to_le32(
- params->dev->mtu
+ resp->MaxPacketsPerTransfer = cpu_to_le32(params->max_pkt_per_xfer);
+ resp->MaxTransferSize = cpu_to_le32(params->max_pkt_per_xfer *
+ (params->dev->mtu
+ sizeof(struct ethhdr)
+ sizeof(struct rndis_packet_msg_type)
- + 22);
+ + 22));
resp->PacketAlignmentFactor = cpu_to_le32(0);
resp->AFListOffset = cpu_to_le32(0);
resp->AFListSize = cpu_to_le32(0);
@@ -686,6 +696,12 @@
rndis_reset_cmplt_type *resp;
rndis_resp_t *r;
struct rndis_params *params = rndis_per_dev_params + configNr;
+ u32 length;
+ u8 *xbuf;
+
+ /* drain the response queue */
+ while ((xbuf = rndis_get_next_response(configNr, &length)))
+ rndis_free_response(configNr, xbuf);
r = rndis_add_response(configNr, sizeof(rndis_reset_cmplt_type));
if (!r)
@@ -910,6 +926,8 @@
rndis_per_dev_params[configNr].dev = dev;
rndis_per_dev_params[configNr].filter = cdc_filter;
+ rndis_ul_max_xfer_size_rcvd = 0;
+ rndis_ul_max_pkt_per_xfer_rcvd = 0;
return 0;
}
@@ -936,6 +954,13 @@
return 0;
}
+void rndis_set_max_pkt_xfer(u8 configNr, u8 max_pkt_per_xfer)
+{
+ pr_debug("%s:\n", __func__);
+
+ rndis_per_dev_params[configNr].max_pkt_per_xfer = max_pkt_per_xfer;
+}
+
void rndis_add_hdr(struct sk_buff *skb)
{
struct rndis_packet_msg_type *header;
@@ -1008,23 +1033,73 @@
struct sk_buff *skb,
struct sk_buff_head *list)
{
- /* tmp points to a struct rndis_packet_msg_type */
- __le32 *tmp = (void *)skb->data;
+ int num_pkts = 1;
- /* MessageType, MessageLength */
- if (cpu_to_le32(RNDIS_MSG_PACKET)
- != get_unaligned(tmp++)) {
- dev_kfree_skb_any(skb);
- return -EINVAL;
- }
- tmp++;
+ if (skb->len > rndis_ul_max_xfer_size_rcvd)
+ rndis_ul_max_xfer_size_rcvd = skb->len;
- /* DataOffset, DataLength */
- if (!skb_pull(skb, get_unaligned_le32(tmp++) + 8)) {
- dev_kfree_skb_any(skb);
- return -EOVERFLOW;
+ while (skb->len) {
+ struct rndis_packet_msg_type *hdr;
+ struct sk_buff *skb2;
+ u32 msg_len, data_offset, data_len;
+
+ /* some rndis hosts send extra byte to avoid zlp, ignore it */
+ if (skb->len == 1) {
+ dev_kfree_skb_any(skb);
+ return 0;
+ }
+
+ if (skb->len < sizeof *hdr) {
+ pr_err("invalid rndis pkt: skblen:%u hdr_len:%u",
+ skb->len, sizeof *hdr);
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+ }
+
+ hdr = (void *)skb->data;
+ msg_len = le32_to_cpu(hdr->MessageLength);
+ data_offset = le32_to_cpu(hdr->DataOffset);
+ data_len = le32_to_cpu(hdr->DataLength);
+
+ if (skb->len < msg_len ||
+ ((data_offset + data_len + 8) > msg_len)) {
+ pr_err("invalid rndis message: %d/%d/%d/%d, len:%d\n",
+ le32_to_cpu(hdr->MessageType),
+ msg_len, data_offset, data_len, skb->len);
+ dev_kfree_skb_any(skb);
+ return -EOVERFLOW;
+ }
+ if (le32_to_cpu(hdr->MessageType) != RNDIS_MSG_PACKET) {
+ pr_err("invalid rndis message: %d/%d/%d/%d, len:%d\n",
+ le32_to_cpu(hdr->MessageType),
+ msg_len, data_offset, data_len, skb->len);
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+ }
+
+ skb_pull(skb, data_offset + 8);
+
+ if (msg_len == skb->len) {
+ skb_trim(skb, data_len);
+ break;
+ }
+
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (!skb2) {
+ pr_err("%s:skb clone failed\n", __func__);
+ dev_kfree_skb_any(skb);
+ return -ENOMEM;
+ }
+
+ skb_pull(skb, msg_len - sizeof *hdr);
+ skb_trim(skb2, data_len);
+ skb_queue_tail(list, skb2);
+
+ num_pkts++;
}
- skb_trim(skb, get_unaligned_le32(tmp++));
+
+ if (num_pkts > rndis_ul_max_pkt_per_xfer_rcvd)
+ rndis_ul_max_pkt_per_xfer_rcvd = num_pkts;
skb_queue_tail(list, skb);
return 0;
@@ -1127,11 +1202,15 @@
#endif /* CONFIG_USB_GADGET_DEBUG_FILES */
+static bool rndis_initialized;
int rndis_init(void)
{
u8 i;
+ if (rndis_initialized)
+ return 0;
+
for (i = 0; i < RNDIS_MAX_CONFIGS; i++) {
#ifdef CONFIG_USB_GADGET_DEBUG_FILES
char name [20];
@@ -1158,6 +1237,7 @@
INIT_LIST_HEAD(&(rndis_per_dev_params[i].resp_queue));
}
+ rndis_initialized = true;
return 0;
}
@@ -1166,7 +1246,13 @@
#ifdef CONFIG_USB_GADGET_DEBUG_FILES
u8 i;
char name[20];
+#endif
+ if (!rndis_initialized)
+ return;
+ rndis_initialized = false;
+
+#ifdef CONFIG_USB_GADGET_DEBUG_FILES
for (i = 0; i < RNDIS_MAX_CONFIGS; i++) {
sprintf(name, NAME_TEMPLATE, i);
remove_proc_entry(name, NULL);
diff --git a/drivers/usb/gadget/rndis.h b/drivers/usb/gadget/rndis.h
index 0647f2f..12045b3 100644
--- a/drivers/usb/gadget/rndis.h
+++ b/drivers/usb/gadget/rndis.h
@@ -189,6 +189,7 @@
struct net_device *dev;
u32 vendorID;
+ u8 max_pkt_per_xfer;
const char *vendorDescr;
void (*resp_avail)(void *v);
void *v;
@@ -204,6 +205,7 @@
int rndis_set_param_vendor (u8 configNr, u32 vendorID,
const char *vendorDescr);
int rndis_set_param_medium (u8 configNr, u32 medium, u32 speed);
+void rndis_set_max_pkt_xfer(u8 configNr, u8 max_pkt_per_xfer);
void rndis_add_hdr (struct sk_buff *skb);
int rndis_rm_hdr(struct gether *port, struct sk_buff *skb,
struct sk_buff_head *list);
diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c
index 4b76124..14f587e 100644
--- a/drivers/usb/gadget/u_ether.c
+++ b/drivers/usb/gadget/u_ether.c
@@ -48,6 +48,8 @@
#define UETH__VERSION "29-May-2008"
+static struct workqueue_struct *uether_wq;
+
struct eth_dev {
/* lock is held while accessing port_usb
*/
@@ -59,17 +61,25 @@
spinlock_t req_lock; /* guard {rx,tx}_reqs */
struct list_head tx_reqs, rx_reqs;
- atomic_t tx_qlen;
+ unsigned tx_qlen;
+/* Minimum number of TX USB request queued to UDC */
+#define TX_REQ_THRESHOLD 5
+ int no_tx_req_used;
+ int tx_skb_hold_count;
+ u32 tx_req_bufsize;
struct sk_buff_head rx_frames;
unsigned header_len;
+ unsigned ul_max_pkts_per_xfer;
+ unsigned dl_max_pkts_per_xfer;
struct sk_buff *(*wrap)(struct gether *, struct sk_buff *skb);
int (*unwrap)(struct gether *,
struct sk_buff *skb,
struct sk_buff_head *list);
struct work_struct work;
+ struct work_struct rx_work;
unsigned long todo;
#define WORK_RX_MEMORY 0
@@ -84,7 +94,7 @@
#define DEFAULT_QLEN 2 /* double buffering by default */
-static unsigned qmult = 5;
+static unsigned qmult = 10;
module_param(qmult, uint, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(qmult, "queue length multiplier at high/super speed");
@@ -226,9 +236,13 @@
size += out->maxpacket - 1;
size -= size % out->maxpacket;
+ if (dev->ul_max_pkts_per_xfer)
+ size *= dev->ul_max_pkts_per_xfer;
+
if (dev->port_usb->is_fixed)
size = max_t(size_t, size, dev->port_usb->fixed_out_len);
+ DBG(dev, "%s: size: %d\n", __func__, size);
skb = alloc_skb(size + NET_IP_ALIGN, gfp_flags);
if (skb == NULL) {
DBG(dev, "no rx skb\n");
@@ -254,18 +268,16 @@
DBG(dev, "rx submit --> %d\n", retval);
if (skb)
dev_kfree_skb_any(skb);
- spin_lock_irqsave(&dev->req_lock, flags);
- list_add(&req->list, &dev->rx_reqs);
- spin_unlock_irqrestore(&dev->req_lock, flags);
}
return retval;
}
static void rx_complete(struct usb_ep *ep, struct usb_request *req)
{
- struct sk_buff *skb = req->context, *skb2;
+ struct sk_buff *skb = req->context;
struct eth_dev *dev = ep->driver_data;
int status = req->status;
+ bool queue = 0;
switch (status) {
@@ -281,6 +293,10 @@
status = dev->unwrap(dev->port_usb,
skb,
&dev->rx_frames);
+ if (status == -EINVAL)
+ dev->net->stats.rx_errors++;
+ else if (status == -EOVERFLOW)
+ dev->net->stats.rx_over_errors++;
} else {
dev_kfree_skb_any(skb);
status = -ENOTCONN;
@@ -289,30 +305,9 @@
} else {
skb_queue_tail(&dev->rx_frames, skb);
}
- skb = NULL;
- skb2 = skb_dequeue(&dev->rx_frames);
- while (skb2) {
- if (status < 0
- || ETH_HLEN > skb2->len
- || skb2->len > VLAN_ETH_FRAME_LEN) {
- dev->net->stats.rx_errors++;
- dev->net->stats.rx_length_errors++;
- DBG(dev, "rx length %d\n", skb2->len);
- dev_kfree_skb_any(skb2);
- goto next_frame;
- }
- skb2->protocol = eth_type_trans(skb2, dev->net);
- dev->net->stats.rx_packets++;
- dev->net->stats.rx_bytes += skb2->len;
-
- /* no buffer copies needed, unless hardware can't
- * use skb buffers.
- */
- status = netif_rx(skb2);
-next_frame:
- skb2 = skb_dequeue(&dev->rx_frames);
- }
+ if (!status)
+ queue = 1;
break;
/* software-driven interface shutdown */
@@ -335,22 +330,20 @@
/* FALLTHROUGH */
default:
+ queue = 1;
+ dev_kfree_skb_any(skb);
dev->net->stats.rx_errors++;
DBG(dev, "rx status %d\n", status);
break;
}
- if (skb)
- dev_kfree_skb_any(skb);
- if (!netif_running(dev->net)) {
clean:
- spin_lock(&dev->req_lock);
- list_add(&req->list, &dev->rx_reqs);
- spin_unlock(&dev->req_lock);
- req = NULL;
- }
- if (req)
- rx_submit(dev, req, GFP_ATOMIC);
+ spin_lock(&dev->req_lock);
+ list_add(&req->list, &dev->rx_reqs);
+ spin_unlock(&dev->req_lock);
+
+ if (queue)
+ queue_work(uether_wq, &dev->rx_work);
}
static int prealloc(struct list_head *list, struct usb_ep *ep, unsigned n)
@@ -415,16 +408,24 @@
{
struct usb_request *req;
unsigned long flags;
+ int req_cnt = 0;
/* fill unused rxq slots with some skb */
spin_lock_irqsave(&dev->req_lock, flags);
while (!list_empty(&dev->rx_reqs)) {
+ /* break the nexus of continuous completion and re-submission*/
+ if (++req_cnt > qlen(dev->gadget))
+ break;
+
req = container_of(dev->rx_reqs.next,
struct usb_request, list);
list_del_init(&req->list);
spin_unlock_irqrestore(&dev->req_lock, flags);
if (rx_submit(dev, req, gfp_flags) < 0) {
+ spin_lock_irqsave(&dev->req_lock, flags);
+ list_add(&req->list, &dev->rx_reqs);
+ spin_unlock_irqrestore(&dev->req_lock, flags);
defer_kevent(dev, WORK_RX_MEMORY);
return;
}
@@ -434,6 +435,36 @@
spin_unlock_irqrestore(&dev->req_lock, flags);
}
+static void process_rx_w(struct work_struct *work)
+{
+ struct eth_dev *dev = container_of(work, struct eth_dev, rx_work);
+ struct sk_buff *skb;
+ int status = 0;
+
+ if (!dev->port_usb)
+ return;
+
+ while ((skb = skb_dequeue(&dev->rx_frames))) {
+ if (status < 0
+ || ETH_HLEN > skb->len
+ || skb->len > ETH_FRAME_LEN) {
+ dev->net->stats.rx_errors++;
+ dev->net->stats.rx_length_errors++;
+ DBG(dev, "rx length %d\n", skb->len);
+ dev_kfree_skb_any(skb);
+ continue;
+ }
+ skb->protocol = eth_type_trans(skb, dev->net);
+ dev->net->stats.rx_packets++;
+ dev->net->stats.rx_bytes += skb->len;
+
+ status = netif_rx_ni(skb);
+ }
+
+ if (netif_running(dev->net))
+ rx_fill(dev, GFP_KERNEL);
+}
+
static void eth_work(struct work_struct *work)
{
struct eth_dev *dev = container_of(work, struct eth_dev, work);
@@ -451,6 +482,11 @@
{
struct sk_buff *skb = req->context;
struct eth_dev *dev = ep->driver_data;
+ struct net_device *net = dev->net;
+ struct usb_request *new_req;
+ struct usb_ep *in;
+ int length;
+ int retval;
switch (req->status) {
default:
@@ -461,16 +497,74 @@
case -ESHUTDOWN: /* disconnect etc */
break;
case 0:
- dev->net->stats.tx_bytes += skb->len;
+ if (!req->zero)
+ dev->net->stats.tx_bytes += req->length-1;
+ else
+ dev->net->stats.tx_bytes += req->length;
}
dev->net->stats.tx_packets++;
spin_lock(&dev->req_lock);
- list_add(&req->list, &dev->tx_reqs);
- spin_unlock(&dev->req_lock);
- dev_kfree_skb_any(skb);
+ list_add_tail(&req->list, &dev->tx_reqs);
- atomic_dec(&dev->tx_qlen);
+ if (dev->port_usb->multi_pkt_xfer) {
+ dev->no_tx_req_used--;
+ req->length = 0;
+ in = dev->port_usb->in_ep;
+
+ if (!list_empty(&dev->tx_reqs)) {
+ new_req = container_of(dev->tx_reqs.next,
+ struct usb_request, list);
+ list_del(&new_req->list);
+ spin_unlock(&dev->req_lock);
+ if (new_req->length > 0) {
+ length = new_req->length;
+
+ /* NCM requires no zlp if transfer is
+ * dwNtbInMaxSize */
+ if (dev->port_usb->is_fixed &&
+ length == dev->port_usb->fixed_in_len &&
+ (length % in->maxpacket) == 0)
+ new_req->zero = 0;
+ else
+ new_req->zero = 1;
+
+ /* use zlp framing on tx for strict CDC-Ether
+ * conformance, though any robust network rx
+ * path ignores extra padding. and some hardware
+ * doesn't like to write zlps.
+ */
+ if (new_req->zero && !dev->zlp &&
+ (length % in->maxpacket) == 0) {
+ new_req->zero = 0;
+ length++;
+ }
+
+ new_req->length = length;
+ retval = usb_ep_queue(in, new_req, GFP_ATOMIC);
+ switch (retval) {
+ default:
+ DBG(dev, "tx queue err %d\n", retval);
+ break;
+ case 0:
+ spin_lock(&dev->req_lock);
+ dev->no_tx_req_used++;
+ spin_unlock(&dev->req_lock);
+ net->trans_start = jiffies;
+ }
+ } else {
+ spin_lock(&dev->req_lock);
+ list_add(&new_req->list, &dev->tx_reqs);
+ spin_unlock(&dev->req_lock);
+ }
+ } else {
+ spin_unlock(&dev->req_lock);
+ }
+ } else {
+ spin_unlock(&dev->req_lock);
+ dev_kfree_skb_any(skb);
+ }
+
if (netif_carrier_ok(dev->net))
netif_wake_queue(dev->net);
}
@@ -480,6 +574,26 @@
return cdc_filter & USB_CDC_PACKET_TYPE_PROMISCUOUS;
}
+static void alloc_tx_buffer(struct eth_dev *dev)
+{
+ struct list_head *act;
+ struct usb_request *req;
+
+ dev->tx_req_bufsize = (dev->dl_max_pkts_per_xfer *
+ (dev->net->mtu
+ + sizeof(struct ethhdr)
+ /* size of rndis_packet_msg_type */
+ + 44
+ + 22));
+
+ list_for_each(act, &dev->tx_reqs) {
+ req = container_of(act, struct usb_request, list);
+ if (!req->buf)
+ req->buf = kmalloc(dev->tx_req_bufsize,
+ GFP_ATOMIC);
+ }
+}
+
static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
struct net_device *net)
{
@@ -506,6 +620,10 @@
return NETDEV_TX_OK;
}
+ /* Allocate memory for tx_reqs to support multi packet transfer */
+ if (dev->port_usb->multi_pkt_xfer && !dev->tx_req_bufsize)
+ alloc_tx_buffer(dev);
+
/* apply outgoing CDC or RNDIS filters */
if (!is_promisc(cdc_filter)) {
u8 *dest = skb->data;
@@ -560,11 +678,39 @@
spin_unlock_irqrestore(&dev->lock, flags);
if (!skb)
goto drop;
-
- length = skb->len;
}
- req->buf = skb->data;
- req->context = skb;
+
+ spin_lock_irqsave(&dev->req_lock, flags);
+ dev->tx_skb_hold_count++;
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+
+ if (dev->port_usb->multi_pkt_xfer) {
+ memcpy(req->buf + req->length, skb->data, skb->len);
+ req->length = req->length + skb->len;
+ length = req->length;
+ dev_kfree_skb_any(skb);
+
+ spin_lock_irqsave(&dev->req_lock, flags);
+ if (dev->tx_skb_hold_count < dev->dl_max_pkts_per_xfer) {
+ if (dev->no_tx_req_used > TX_REQ_THRESHOLD) {
+ list_add(&req->list, &dev->tx_reqs);
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+ goto success;
+ }
+ }
+
+ dev->no_tx_req_used++;
+ spin_unlock_irqrestore(&dev->req_lock, flags);
+
+ spin_lock_irqsave(&dev->lock, flags);
+ dev->tx_skb_hold_count = 0;
+ spin_unlock_irqrestore(&dev->lock, flags);
+ } else {
+ length = skb->len;
+ req->buf = skb->data;
+ req->context = skb;
+ }
+
req->complete = tx_complete;
/* NCM requires no zlp if transfer is dwNtbInMaxSize */
@@ -579,17 +725,26 @@
* though any robust network rx path ignores extra padding.
* and some hardware doesn't like to write zlps.
*/
- if (req->zero && !dev->zlp && (length % in->maxpacket) == 0)
+ if (req->zero && !dev->zlp && (length % in->maxpacket) == 0) {
+ req->zero = 0;
length++;
+ }
req->length = length;
- /* throttle high/super speed IRQ rate back slightly */
- if (gadget_is_dualspeed(dev->gadget))
- req->no_interrupt = (dev->gadget->speed == USB_SPEED_HIGH ||
- dev->gadget->speed == USB_SPEED_SUPER)
- ? ((atomic_read(&dev->tx_qlen) % qmult) != 0)
- : 0;
+ /* throttle highspeed IRQ rate back slightly */
+ if (gadget_is_dualspeed(dev->gadget) &&
+ (dev->gadget->speed == USB_SPEED_HIGH)) {
+ dev->tx_qlen++;
+ if (dev->tx_qlen == (qmult/2)) {
+ req->no_interrupt = 0;
+ dev->tx_qlen = 0;
+ } else {
+ req->no_interrupt = 1;
+ }
+ } else {
+ req->no_interrupt = 0;
+ }
retval = usb_ep_queue(in, req, GFP_ATOMIC);
switch (retval) {
@@ -598,11 +753,11 @@
break;
case 0:
net->trans_start = jiffies;
- atomic_inc(&dev->tx_qlen);
}
if (retval) {
- dev_kfree_skb_any(skb);
+ if (!dev->port_usb->multi_pkt_xfer)
+ dev_kfree_skb_any(skb);
drop:
dev->net->stats.tx_dropped++;
spin_lock_irqsave(&dev->req_lock, flags);
@@ -611,6 +766,7 @@
list_add(&req->list, &dev->tx_reqs);
spin_unlock_irqrestore(&dev->req_lock, flags);
}
+success:
return NETDEV_TX_OK;
}
@@ -624,7 +780,7 @@
rx_fill(dev, gfp_flags);
/* and open the tx floodgates */
- atomic_set(&dev->tx_qlen, 0);
+ dev->tx_qlen = 0;
netif_wake_queue(dev->net);
}
@@ -697,6 +853,8 @@
/*-------------------------------------------------------------------------*/
+static u8 host_ethaddr[ETH_ALEN];
+
/* initial value, changed by "ifconfig usb0 hw ether xx:xx:xx:xx:xx:xx" */
static char *dev_addr;
module_param(dev_addr, charp, S_IRUGO);
@@ -728,6 +886,17 @@
return 1;
}
+static int get_host_ether_addr(u8 *str, u8 *dev_addr)
+{
+ memcpy(dev_addr, str, ETH_ALEN);
+ if (is_valid_ether_addr(dev_addr))
+ return 0;
+
+ random_ether_addr(dev_addr);
+ memcpy(str, dev_addr, ETH_ALEN);
+ return 1;
+}
+
static const struct net_device_ops eth_netdev_ops = {
.ndo_open = eth_open,
.ndo_stop = eth_stop,
@@ -770,6 +939,7 @@
spin_lock_init(&dev->lock);
spin_lock_init(&dev->req_lock);
INIT_WORK(&dev->work, eth_work);
+ INIT_WORK(&dev->rx_work, process_rx_w);
INIT_LIST_HEAD(&dev->tx_reqs);
INIT_LIST_HEAD(&dev->rx_reqs);
@@ -782,9 +952,11 @@
if (get_ether_addr(dev_addr, net->dev_addr))
dev_warn(&g->dev,
"using random %s ethernet address\n", "self");
- if (get_ether_addr(host_addr, dev->host_mac))
- dev_warn(&g->dev,
- "using random %s ethernet address\n", "host");
+
+ if (get_host_ether_addr(host_ethaddr, dev->host_mac))
+ dev_warn(&g->dev, "using random %s ethernet address\n", "host");
+ else
+ dev_warn(&g->dev, "using previous %s ethernet address\n", "host");
if (ethaddr)
memcpy(ethaddr, dev->host_mac, ETH_ALEN);
@@ -882,8 +1054,13 @@
dev->header_len = link->header_len;
dev->unwrap = link->unwrap;
dev->wrap = link->wrap;
+ dev->ul_max_pkts_per_xfer = link->ul_max_pkts_per_xfer;
+ dev->dl_max_pkts_per_xfer = link->dl_max_pkts_per_xfer;
spin_lock(&dev->lock);
+ dev->tx_skb_hold_count = 0;
+ dev->no_tx_req_used = 0;
+ dev->tx_req_bufsize = 0;
dev->port_usb = link;
if (netif_running(dev->net)) {
if (link->open)
@@ -927,6 +1104,7 @@
{
struct eth_dev *dev = link->ioport;
struct usb_request *req;
+ struct sk_buff *skb;
WARN_ON(!dev);
if (!dev)
@@ -949,6 +1127,8 @@
list_del(&req->list);
spin_unlock(&dev->req_lock);
+ if (link->multi_pkt_xfer)
+ kfree(req->buf);
usb_ep_free_request(link->in_ep, req);
spin_lock(&dev->req_lock);
}
@@ -968,6 +1148,12 @@
spin_lock(&dev->req_lock);
}
spin_unlock(&dev->req_lock);
+
+ spin_lock(&dev->rx_frames.lock);
+ while ((skb = __skb_dequeue(&dev->rx_frames)))
+ dev_kfree_skb_any(skb);
+ spin_unlock(&dev->rx_frames.lock);
+
link->out_ep->driver_data = NULL;
link->out_ep->desc = NULL;
@@ -980,3 +1166,23 @@
dev->port_usb = NULL;
spin_unlock(&dev->lock);
}
+
+static int __init gether_init(void)
+{
+ uether_wq = create_singlethread_workqueue("uether");
+ if (!uether_wq) {
+ pr_err("%s: Unable to create workqueue: uether\n", __func__);
+ return -ENOMEM;
+ }
+ return 0;
+}
+module_init(gether_init);
+
+static void __exit gether_exit(void)
+{
+ destroy_workqueue(uether_wq);
+
+}
+module_exit(gether_exit);
+MODULE_DESCRIPTION("ethernet over USB driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/gadget/u_ether.h b/drivers/usb/gadget/u_ether.h
index 0252233..67eda50 100644
--- a/drivers/usb/gadget/u_ether.h
+++ b/drivers/usb/gadget/u_ether.h
@@ -54,6 +54,9 @@
bool is_fixed;
u32 fixed_out_len;
u32 fixed_in_len;
+ unsigned ul_max_pkts_per_xfer;
+ unsigned dl_max_pkts_per_xfer;
+ bool multi_pkt_xfer;
struct sk_buff *(*wrap)(struct gether *port,
struct sk_buff *skb);
int (*unwrap)(struct gether *port,
diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
index b369292..7206808 100644
--- a/drivers/usb/gadget/u_serial.c
+++ b/drivers/usb/gadget/u_serial.c
@@ -1126,6 +1126,7 @@
tty_dev = tty_port_register_device(&ports[port_num].port->port,
gs_tty_driver, port_num, NULL);
+
if (IS_ERR(tty_dev)) {
struct gs_port *port;
pr_err("%s: failed to register tty for port %d, err %ld\n",
diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c
index 817a26c..58a8613 100644
--- a/drivers/usb/gadget/udc-core.c
+++ b/drivers/usb/gadget/udc-core.c
@@ -335,7 +335,15 @@
driver->unbind(udc->gadget);
goto err1;
}
- usb_gadget_connect(udc->gadget);
+ /*
+ * HACK: The Android gadget driver disconnects the gadget
+ * on bind and expects the gadget to stay disconnected until
+ * it calls usb_gadget_connect when userspace is ready. Remove
+ * the call to usb_gadget_connect bellow to avoid enabling the
+ * pullup before userspace is ready.
+ *
+ * usb_gadget_connect(udc->gadget);
+ */
kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
return 0;
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 2311b1e..700d572 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -16,6 +16,14 @@
If you're not sure if this applies to you, it probably doesn't;
say N here.
+config USB_OTG_WAKELOCK
+ bool "Hold a wakelock when USB connected"
+ depends on WAKELOCK
+ select USB_OTG_UTILS
+ help
+ Select this to automatically hold a wakelock when USB is
+ connected, preventing suspend.
+
if USB_PHY
#
@@ -210,4 +218,13 @@
Provides read/write operations to the ULPI phy register set for
controllers with a viewport register (e.g. Chipidea/ARC controllers).
+config DUAL_ROLE_USB_INTF
+ bool "Generic DUAL ROLE sysfs interface"
+ depends on SYSFS && USB_PHY
+ help
+ A generic sysfs interface to track and change the state of
+ dual role usb phys. The usb phy drivers can register to
+ this interface to expose it capabilities to the userspace
+ and thereby allowing userspace to change the port mode.
+
endif # USB_PHY
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index a9169cb..c70afde 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -5,7 +5,9 @@
ccflags-$(CONFIG_USB_DEBUG) := -DDEBUG
obj-$(CONFIG_USB_PHY) += phy.o
+obj-$(CONFIG_USB_OTG_WAKELOCK) += otg-wakelock.o
+obj-$(CONFIG_DUAL_ROLE_USB_INTF) += class-dual-role.o
# transceiver drivers, keep the list sorted
obj-$(CONFIG_AB8500_USB) += phy-ab8500-usb.o
diff --git a/drivers/usb/phy/class-dual-role.c b/drivers/usb/phy/class-dual-role.c
new file mode 100644
index 0000000..51fcb54
--- /dev/null
+++ b/drivers/usb/phy/class-dual-role.c
@@ -0,0 +1,529 @@
+/*
+ * class-dual-role.c
+ *
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/usb/class-dual-role.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+
+#define DUAL_ROLE_NOTIFICATION_TIMEOUT 2000
+
+static ssize_t dual_role_store_property(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count);
+static ssize_t dual_role_show_property(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+
+#define DUAL_ROLE_ATTR(_name) \
+{ \
+ .attr = { .name = #_name }, \
+ .show = dual_role_show_property, \
+ .store = dual_role_store_property, \
+}
+
+static struct device_attribute dual_role_attrs[] = {
+ DUAL_ROLE_ATTR(supported_modes),
+ DUAL_ROLE_ATTR(mode),
+ DUAL_ROLE_ATTR(power_role),
+ DUAL_ROLE_ATTR(data_role),
+ DUAL_ROLE_ATTR(powers_vconn),
+};
+
+struct class *dual_role_class;
+EXPORT_SYMBOL_GPL(dual_role_class);
+
+static struct device_type dual_role_dev_type;
+
+static char *kstrdupcase(const char *str, gfp_t gfp, bool to_upper)
+{
+ char *ret, *ustr;
+
+ ustr = ret = kmalloc(strlen(str) + 1, gfp);
+
+ if (!ret)
+ return NULL;
+
+ while (*str)
+ *ustr++ = to_upper ? toupper(*str++) : tolower(*str++);
+
+ *ustr = 0;
+
+ return ret;
+}
+
+static void dual_role_changed_work(struct work_struct *work)
+{
+ struct dual_role_phy_instance *dual_role =
+ container_of(work, struct dual_role_phy_instance,
+ changed_work);
+
+ dev_dbg(&dual_role->dev, "%s\n", __func__);
+ kobject_uevent(&dual_role->dev.kobj, KOBJ_CHANGE);
+}
+
+void dual_role_instance_changed(struct dual_role_phy_instance *dual_role)
+{
+ dev_dbg(&dual_role->dev, "%s\n", __func__);
+ pm_wakeup_event(&dual_role->dev, DUAL_ROLE_NOTIFICATION_TIMEOUT);
+ schedule_work(&dual_role->changed_work);
+}
+EXPORT_SYMBOL_GPL(dual_role_instance_changed);
+
+int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val)
+{
+ return dual_role->desc->get_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_get_property);
+
+int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val)
+{
+ if (!dual_role->desc->set_property)
+ return -ENODEV;
+
+ return dual_role->desc->set_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_set_property);
+
+int dual_role_property_is_writeable(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop)
+{
+ if (!dual_role->desc->property_is_writeable)
+ return -ENODEV;
+
+ return dual_role->desc->property_is_writeable(dual_role, prop);
+}
+EXPORT_SYMBOL_GPL(dual_role_property_is_writeable);
+
+static void dual_role_dev_release(struct device *dev)
+{
+ struct dual_role_phy_instance *dual_role =
+ container_of(dev, struct dual_role_phy_instance, dev);
+ pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
+ kfree(dual_role);
+}
+
+static struct dual_role_phy_instance *__must_check
+__dual_role_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ struct device *dev;
+ struct dual_role_phy_instance *dual_role;
+ int rc;
+
+ dual_role = kzalloc(sizeof(*dual_role), GFP_KERNEL);
+ if (!dual_role)
+ return ERR_PTR(-ENOMEM);
+
+ dev = &dual_role->dev;
+
+ device_initialize(dev);
+
+ dev->class = dual_role_class;
+ dev->type = &dual_role_dev_type;
+ dev->parent = parent;
+ dev->release = dual_role_dev_release;
+ dev_set_drvdata(dev, dual_role);
+ dual_role->desc = desc;
+
+ rc = dev_set_name(dev, "%s", desc->name);
+ if (rc)
+ goto dev_set_name_failed;
+
+ INIT_WORK(&dual_role->changed_work, dual_role_changed_work);
+
+ rc = device_init_wakeup(dev, true);
+ if (rc)
+ goto wakeup_init_failed;
+
+ rc = device_add(dev);
+ if (rc)
+ goto device_add_failed;
+
+ dual_role_instance_changed(dual_role);
+
+ return dual_role;
+
+device_add_failed:
+ device_init_wakeup(dev, false);
+wakeup_init_failed:
+dev_set_name_failed:
+ put_device(dev);
+ kfree(dual_role);
+
+ return ERR_PTR(rc);
+}
+
+static void dual_role_instance_unregister(struct dual_role_phy_instance
+ *dual_role)
+{
+ cancel_work_sync(&dual_role->changed_work);
+ device_init_wakeup(&dual_role->dev, false);
+ device_unregister(&dual_role->dev);
+}
+
+static void devm_dual_role_release(struct device *dev, void *res)
+{
+ struct dual_role_phy_instance **dual_role = res;
+
+ dual_role_instance_unregister(*dual_role);
+}
+
+struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ struct dual_role_phy_instance **ptr, *dual_role;
+
+ ptr = devres_alloc(devm_dual_role_release, sizeof(*ptr), GFP_KERNEL);
+
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+ dual_role = __dual_role_register(parent, desc);
+ if (IS_ERR(dual_role)) {
+ devres_free(ptr);
+ } else {
+ *ptr = dual_role;
+ devres_add(parent, ptr);
+ }
+ return dual_role;
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_register);
+
+static int devm_dual_role_match(struct device *dev, void *res, void *data)
+{
+ struct dual_role_phy_instance **r = res;
+
+ if (WARN_ON(!r || !*r))
+ return 0;
+
+ return *r == data;
+}
+
+void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role)
+{
+ int rc;
+
+ rc = devres_release(dev, devm_dual_role_release,
+ devm_dual_role_match, dual_role);
+ WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_unregister);
+
+void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role)
+{
+ return dual_role->drv_data;
+}
+EXPORT_SYMBOL_GPL(dual_role_get_drvdata);
+
+/***************** Device attribute functions **************************/
+
+/* port type */
+static char *supported_modes_text[] = {
+ "ufp dfp", "dfp", "ufp"
+};
+
+/* current mode */
+static char *mode_text[] = {
+ "ufp", "dfp", "none"
+};
+
+/* Power role */
+static char *pr_text[] = {
+ "source", "sink", "none"
+};
+
+/* Data role */
+static char *dr_text[] = {
+ "host", "device", "none"
+};
+
+/* Vconn supply */
+static char *vconn_supply_text[] = {
+ "n", "y"
+};
+
+static ssize_t dual_role_show_property(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ ssize_t ret = 0;
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ const ptrdiff_t off = attr - dual_role_attrs;
+ unsigned int value;
+
+ if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+ value = dual_role->desc->supported_modes;
+ } else {
+ ret = dual_role_get_property(dual_role, off, &value);
+
+ if (ret < 0) {
+ if (ret == -ENODATA)
+ dev_dbg(dev,
+ "driver has no data for `%s' property\n",
+ attr->attr.name);
+ else if (ret != -ENODEV)
+ dev_err(dev,
+ "driver failed to report `%s' property: %zd\n",
+ attr->attr.name, ret);
+ return ret;
+ }
+ }
+
+ if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL !=
+ ARRAY_SIZE(supported_modes_text));
+ if (value < DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ supported_modes_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_MODE) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_MODE_TOTAL !=
+ ARRAY_SIZE(mode_text));
+ if (value < DUAL_ROLE_PROP_MODE_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ mode_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_PR) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_PR_TOTAL != ARRAY_SIZE(pr_text));
+ if (value < DUAL_ROLE_PROP_PR_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ pr_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_DR) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_DR_TOTAL != ARRAY_SIZE(dr_text));
+ if (value < DUAL_ROLE_PROP_DR_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ dr_text[value]);
+ else
+ return -EIO;
+ } else if (off == DUAL_ROLE_PROP_VCONN_SUPPLY) {
+ BUILD_BUG_ON(DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL !=
+ ARRAY_SIZE(vconn_supply_text));
+ if (value < DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL)
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ vconn_supply_text[value]);
+ else
+ return -EIO;
+ } else
+ return -EIO;
+}
+
+static ssize_t dual_role_store_property(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ ssize_t ret;
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ const ptrdiff_t off = attr - dual_role_attrs;
+ unsigned int value;
+ int total, i;
+ char *dup_buf, **text_array;
+ bool result = false;
+
+ dup_buf = kstrdupcase(buf, GFP_KERNEL, false);
+ switch (off) {
+ case DUAL_ROLE_PROP_MODE:
+ total = DUAL_ROLE_PROP_MODE_TOTAL;
+ text_array = mode_text;
+ break;
+ case DUAL_ROLE_PROP_PR:
+ total = DUAL_ROLE_PROP_PR_TOTAL;
+ text_array = pr_text;
+ break;
+ case DUAL_ROLE_PROP_DR:
+ total = DUAL_ROLE_PROP_DR_TOTAL;
+ text_array = dr_text;
+ break;
+ case DUAL_ROLE_PROP_VCONN_SUPPLY:
+ ret = strtobool(dup_buf, &result);
+ value = result;
+ if (!ret)
+ goto setprop;
+ default:
+ ret = -EINVAL;
+ goto error;
+ }
+
+ for (i = 0; i <= total; i++) {
+ if (i == total) {
+ ret = -ENOTSUPP;
+ goto error;
+ }
+ if (!strncmp(*(text_array + i), dup_buf,
+ strlen(*(text_array + i)))) {
+ value = i;
+ break;
+ }
+ }
+
+setprop:
+ ret = dual_role->desc->set_property(dual_role, off, &value);
+
+error:
+ kfree(dup_buf);
+
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static umode_t dual_role_attr_is_visible(struct kobject *kobj,
+ struct attribute *attr, int attrno)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+ int i;
+
+ if (attrno == DUAL_ROLE_PROP_SUPPORTED_MODES)
+ return mode;
+
+ for (i = 0; i < dual_role->desc->num_properties; i++) {
+ int property = dual_role->desc->properties[i];
+
+ if (property == attrno) {
+ if (dual_role->desc->property_is_writeable &&
+ dual_role_property_is_writeable(dual_role, property)
+ > 0)
+ mode |= S_IWUSR;
+
+ return mode;
+ }
+ }
+
+ return 0;
+}
+
+static struct attribute *__dual_role_attrs[ARRAY_SIZE(dual_role_attrs) + 1];
+
+static struct attribute_group dual_role_attr_group = {
+ .attrs = __dual_role_attrs,
+ .is_visible = dual_role_attr_is_visible,
+};
+
+static const struct attribute_group *dual_role_attr_groups[] = {
+ &dual_role_attr_group,
+ NULL,
+};
+
+void dual_role_init_attrs(struct device_type *dev_type)
+{
+ int i;
+
+ dev_type->groups = dual_role_attr_groups;
+
+ for (i = 0; i < ARRAY_SIZE(dual_role_attrs); i++)
+ __dual_role_attrs[i] = &dual_role_attrs[i].attr;
+}
+
+int dual_role_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+ int ret = 0, j;
+ char *prop_buf;
+ char *attrname;
+
+ dev_dbg(dev, "uevent\n");
+
+ if (!dual_role || !dual_role->desc) {
+ dev_dbg(dev, "No dual_role phy yet\n");
+ return ret;
+ }
+
+ dev_dbg(dev, "DUAL_ROLE_NAME=%s\n", dual_role->desc->name);
+
+ ret = add_uevent_var(env, "DUAL_ROLE_NAME=%s", dual_role->desc->name);
+ if (ret)
+ return ret;
+
+ prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
+ if (!prop_buf)
+ return -ENOMEM;
+
+ for (j = 0; j < dual_role->desc->num_properties; j++) {
+ struct device_attribute *attr;
+ char *line;
+
+ attr = &dual_role_attrs[dual_role->desc->properties[j]];
+
+ ret = dual_role_show_property(dev, attr, prop_buf);
+ if (ret == -ENODEV || ret == -ENODATA) {
+ ret = 0;
+ continue;
+ }
+
+ if (ret < 0)
+ goto out;
+ line = strnchr(prop_buf, PAGE_SIZE, '\n');
+ if (line)
+ *line = 0;
+
+ attrname = kstrdupcase(attr->attr.name, GFP_KERNEL, true);
+ if (!attrname)
+ ret = -ENOMEM;
+
+ dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
+
+ ret = add_uevent_var(env, "DUAL_ROLE_%s=%s", attrname,
+ prop_buf);
+ kfree(attrname);
+ if (ret)
+ goto out;
+ }
+
+out:
+ free_page((unsigned long)prop_buf);
+
+ return ret;
+}
+
+/******************* Module Init ***********************************/
+
+static int __init dual_role_class_init(void)
+{
+ dual_role_class = class_create(THIS_MODULE, "dual_role_usb");
+
+ if (IS_ERR(dual_role_class))
+ return PTR_ERR(dual_role_class);
+
+ dual_role_class->dev_uevent = dual_role_uevent;
+ dual_role_init_attrs(&dual_role_dev_type);
+
+ return 0;
+}
+
+static void __exit dual_role_class_exit(void)
+{
+ class_destroy(dual_role_class);
+}
+
+subsys_initcall(dual_role_class_init);
+module_exit(dual_role_class_exit);
diff --git a/drivers/usb/phy/otg-wakelock.c b/drivers/usb/phy/otg-wakelock.c
new file mode 100644
index 0000000..479376b
--- /dev/null
+++ b/drivers/usb/phy/otg-wakelock.c
@@ -0,0 +1,173 @@
+/*
+ * otg-wakelock.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/wakelock.h>
+#include <linux/spinlock.h>
+#include <linux/usb/otg.h>
+
+#define TEMPORARY_HOLD_TIME 2000
+
+static bool enabled = true;
+static struct usb_phy *otgwl_xceiv;
+static struct notifier_block otgwl_nb;
+
+/*
+ * otgwl_spinlock is held while the VBUS lock is grabbed or dropped and the
+ * held field is updated to match.
+ */
+
+static DEFINE_SPINLOCK(otgwl_spinlock);
+
+/*
+ * Only one lock, but since these 3 fields are associated with each other...
+ */
+
+struct otgwl_lock {
+ char name[40];
+ struct wake_lock wakelock;
+ bool held;
+};
+
+/*
+ * VBUS present lock. Also used as a timed lock on charger
+ * connect/disconnect and USB host disconnect, to allow the system
+ * to react to the change in power.
+ */
+
+static struct otgwl_lock vbus_lock;
+
+static void otgwl_hold(struct otgwl_lock *lock)
+{
+ if (!lock->held) {
+ wake_lock(&lock->wakelock);
+ lock->held = true;
+ }
+}
+
+static void otgwl_temporary_hold(struct otgwl_lock *lock)
+{
+ wake_lock_timeout(&lock->wakelock,
+ msecs_to_jiffies(TEMPORARY_HOLD_TIME));
+ lock->held = false;
+}
+
+static void otgwl_drop(struct otgwl_lock *lock)
+{
+ if (lock->held) {
+ wake_unlock(&lock->wakelock);
+ lock->held = false;
+ }
+}
+
+static void otgwl_handle_event(unsigned long event)
+{
+ unsigned long irqflags;
+
+ spin_lock_irqsave(&otgwl_spinlock, irqflags);
+
+ if (!enabled) {
+ otgwl_drop(&vbus_lock);
+ spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+ return;
+ }
+
+ switch (event) {
+ case USB_EVENT_VBUS:
+ case USB_EVENT_ENUMERATED:
+ otgwl_hold(&vbus_lock);
+ break;
+
+ case USB_EVENT_NONE:
+ case USB_EVENT_ID:
+ case USB_EVENT_CHARGER:
+ otgwl_temporary_hold(&vbus_lock);
+ break;
+
+ default:
+ break;
+ }
+
+ spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+}
+
+static int otgwl_otg_notifications(struct notifier_block *nb,
+ unsigned long event, void *unused)
+{
+ otgwl_handle_event(event);
+ return NOTIFY_OK;
+}
+
+static int set_enabled(const char *val, const struct kernel_param *kp)
+{
+ int rv = param_set_bool(val, kp);
+
+ if (rv)
+ return rv;
+
+ if (otgwl_xceiv)
+ otgwl_handle_event(otgwl_xceiv->last_event);
+
+ return 0;
+}
+
+static struct kernel_param_ops enabled_param_ops = {
+ .set = set_enabled,
+ .get = param_get_bool,
+};
+
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0644);
+MODULE_PARM_DESC(enabled, "enable wakelock when VBUS present");
+
+static int __init otg_wakelock_init(void)
+{
+ int ret;
+ struct usb_phy *phy;
+
+ phy = usb_get_phy(USB_PHY_TYPE_USB2);
+
+ if (IS_ERR(phy)) {
+ pr_err("%s: No USB transceiver found\n", __func__);
+ return PTR_ERR(phy);
+ }
+ otgwl_xceiv = phy;
+
+ snprintf(vbus_lock.name, sizeof(vbus_lock.name), "vbus-%s",
+ dev_name(otgwl_xceiv->dev));
+ wake_lock_init(&vbus_lock.wakelock, WAKE_LOCK_SUSPEND,
+ vbus_lock.name);
+
+ otgwl_nb.notifier_call = otgwl_otg_notifications;
+ ret = usb_register_notifier(otgwl_xceiv, &otgwl_nb);
+
+ if (ret) {
+ pr_err("%s: usb_register_notifier on transceiver %s"
+ " failed\n", __func__,
+ dev_name(otgwl_xceiv->dev));
+ otgwl_xceiv = NULL;
+ wake_lock_destroy(&vbus_lock.wakelock);
+ return ret;
+ }
+
+ otgwl_handle_event(otgwl_xceiv->last_event);
+ return ret;
+}
+
+late_initcall(otg_wakelock_init);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 2e937bd..0669dac 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -2475,6 +2475,7 @@
source "drivers/video/exynos/Kconfig"
source "drivers/video/mmp/Kconfig"
source "drivers/video/backlight/Kconfig"
+source "drivers/video/adf/Kconfig"
if VT
source "drivers/video/console/Kconfig"
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index e8bae8d..2babdef 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -12,6 +12,7 @@
modedb.o fbcvt.o
fb-objs := $(fb-y)
+obj-$(CONFIG_ADF) += adf/
obj-$(CONFIG_VT) += console/
obj-$(CONFIG_LOGO) += logo/
obj-y += backlight/
diff --git a/drivers/video/adf/Kconfig b/drivers/video/adf/Kconfig
new file mode 100644
index 0000000..33858b7
--- /dev/null
+++ b/drivers/video/adf/Kconfig
@@ -0,0 +1,14 @@
+menuconfig ADF
+ depends on SYNC
+ depends on DMA_SHARED_BUFFER
+ tristate "Atomic Display Framework"
+
+menuconfig ADF_FBDEV
+ depends on ADF
+ depends on FB
+ tristate "Helper for implementing the fbdev API in ADF drivers"
+
+menuconfig ADF_MEMBLOCK
+ depends on ADF
+ depends on HAVE_MEMBLOCK
+ tristate "Helper for using memblocks as buffers in ADF drivers"
diff --git a/drivers/video/adf/Makefile b/drivers/video/adf/Makefile
new file mode 100644
index 0000000..78d0915
--- /dev/null
+++ b/drivers/video/adf/Makefile
@@ -0,0 +1,15 @@
+ccflags-y := -Idrivers/staging/android
+
+CFLAGS_adf.o := -I$(src)
+
+obj-$(CONFIG_ADF) += adf.o \
+ adf_client.o \
+ adf_fops.o \
+ adf_format.o \
+ adf_sysfs.o
+
+obj-$(CONFIG_COMPAT) += adf_fops32.o
+
+obj-$(CONFIG_ADF_FBDEV) += adf_fbdev.o
+
+obj-$(CONFIG_ADF_MEMBLOCK) += adf_memblock.o
diff --git a/drivers/video/adf/adf.c b/drivers/video/adf/adf.c
new file mode 100644
index 0000000..42c30c0
--- /dev/null
+++ b/drivers/video/adf/adf.c
@@ -0,0 +1,1188 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ * adf_modeinfo_{set_name,set_vrefresh} modified from
+ * drivers/gpu/drm/drm_modes.c
+ * adf_format_validate_yuv modified from framebuffer_check in
+ * drivers/gpu/drm/drm_crtc.c
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <video/adf_format.h>
+
+#include "sw_sync.h"
+#include "sync.h"
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+#define CREATE_TRACE_POINTS
+#include "adf_trace.h"
+
+#define ADF_SHORT_FENCE_TIMEOUT (1 * MSEC_PER_SEC)
+#define ADF_LONG_FENCE_TIMEOUT (10 * MSEC_PER_SEC)
+
+static DEFINE_IDR(adf_devices);
+
+static void adf_fence_wait(struct adf_device *dev, struct sync_fence *fence)
+{
+ /* sync_fence_wait() dumps debug information on timeout. Experience
+ has shown that if the pipeline gets stuck, a short timeout followed
+ by a longer one provides useful information for debugging. */
+ int err = sync_fence_wait(fence, ADF_SHORT_FENCE_TIMEOUT);
+ if (err >= 0)
+ return;
+
+ if (err == -ETIME)
+ err = sync_fence_wait(fence, ADF_LONG_FENCE_TIMEOUT);
+
+ if (err < 0)
+ dev_warn(&dev->base.dev, "error waiting on fence: %d\n", err);
+}
+
+void adf_buffer_cleanup(struct adf_buffer *buf)
+{
+ size_t i;
+ for (i = 0; i < ARRAY_SIZE(buf->dma_bufs); i++)
+ if (buf->dma_bufs[i])
+ dma_buf_put(buf->dma_bufs[i]);
+
+ if (buf->acquire_fence)
+ sync_fence_put(buf->acquire_fence);
+}
+
+void adf_buffer_mapping_cleanup(struct adf_buffer_mapping *mapping,
+ struct adf_buffer *buf)
+{
+ /* calling adf_buffer_mapping_cleanup() is safe even if mapping is
+ uninitialized or partially-initialized, as long as it was
+ zeroed on allocation */
+ size_t i;
+ for (i = 0; i < ARRAY_SIZE(mapping->sg_tables); i++) {
+ if (mapping->sg_tables[i])
+ dma_buf_unmap_attachment(mapping->attachments[i],
+ mapping->sg_tables[i], DMA_TO_DEVICE);
+ if (mapping->attachments[i])
+ dma_buf_detach(buf->dma_bufs[i],
+ mapping->attachments[i]);
+ }
+}
+
+void adf_post_cleanup(struct adf_device *dev, struct adf_pending_post *post)
+{
+ size_t i;
+
+ if (post->state)
+ dev->ops->state_free(dev, post->state);
+
+ for (i = 0; i < post->config.n_bufs; i++) {
+ adf_buffer_mapping_cleanup(&post->config.mappings[i],
+ &post->config.bufs[i]);
+ adf_buffer_cleanup(&post->config.bufs[i]);
+ }
+
+ kfree(post->config.custom_data);
+ kfree(post->config.mappings);
+ kfree(post->config.bufs);
+ kfree(post);
+}
+
+static void adf_sw_advance_timeline(struct adf_device *dev)
+{
+#ifdef CONFIG_SW_SYNC
+ sw_sync_timeline_inc(dev->timeline, 1);
+#else
+ BUG();
+#endif
+}
+
+static void adf_post_work_func(struct kthread_work *work)
+{
+ struct adf_device *dev =
+ container_of(work, struct adf_device, post_work);
+ struct adf_pending_post *post, *next;
+ struct list_head saved_list;
+
+ mutex_lock(&dev->post_lock);
+ memcpy(&saved_list, &dev->post_list, sizeof(saved_list));
+ list_replace_init(&dev->post_list, &saved_list);
+ mutex_unlock(&dev->post_lock);
+
+ list_for_each_entry_safe(post, next, &saved_list, head) {
+ int i;
+
+ for (i = 0; i < post->config.n_bufs; i++) {
+ struct sync_fence *fence =
+ post->config.bufs[i].acquire_fence;
+ if (fence)
+ adf_fence_wait(dev, fence);
+ }
+
+ dev->ops->post(dev, &post->config, post->state);
+
+ if (dev->ops->advance_timeline)
+ dev->ops->advance_timeline(dev, &post->config,
+ post->state);
+ else
+ adf_sw_advance_timeline(dev);
+
+ list_del(&post->head);
+ if (dev->onscreen)
+ adf_post_cleanup(dev, dev->onscreen);
+ dev->onscreen = post;
+ }
+}
+
+void adf_attachment_free(struct adf_attachment_list *attachment)
+{
+ list_del(&attachment->head);
+ kfree(attachment);
+}
+
+struct adf_event_refcount *adf_obj_find_event_refcount(struct adf_obj *obj,
+ enum adf_event_type type)
+{
+ struct rb_root *root = &obj->event_refcount;
+ struct rb_node **new = &(root->rb_node);
+ struct rb_node *parent = NULL;
+ struct adf_event_refcount *refcount;
+
+ while (*new) {
+ refcount = container_of(*new, struct adf_event_refcount, node);
+ parent = *new;
+
+ if (refcount->type > type)
+ new = &(*new)->rb_left;
+ else if (refcount->type < type)
+ new = &(*new)->rb_right;
+ else
+ return refcount;
+ }
+
+ refcount = kzalloc(sizeof(*refcount), GFP_KERNEL);
+ if (!refcount)
+ return NULL;
+ refcount->type = type;
+
+ rb_link_node(&refcount->node, parent, new);
+ rb_insert_color(&refcount->node, root);
+ return refcount;
+}
+
+/**
+ * adf_event_get - increase the refcount for an event
+ *
+ * @obj: the object that produces the event
+ * @type: the event type
+ *
+ * ADF will call the object's set_event() op if needed. ops are allowed
+ * to sleep, so adf_event_get() must NOT be called from an atomic context.
+ *
+ * Returns 0 if successful, or -%EINVAL if the object does not support the
+ * requested event type.
+ */
+int adf_event_get(struct adf_obj *obj, enum adf_event_type type)
+{
+ struct adf_event_refcount *refcount;
+ int old_refcount;
+ int ret;
+
+ ret = adf_obj_check_supports_event(obj, type);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&obj->event_lock);
+
+ refcount = adf_obj_find_event_refcount(obj, type);
+ if (!refcount) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ old_refcount = refcount->refcount++;
+
+ if (old_refcount == 0) {
+ obj->ops->set_event(obj, type, true);
+ trace_adf_event_enable(obj, type);
+ }
+
+done:
+ mutex_unlock(&obj->event_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_event_get);
+
+/**
+ * adf_event_put - decrease the refcount for an event
+ *
+ * @obj: the object that produces the event
+ * @type: the event type
+ *
+ * ADF will call the object's set_event() op if needed. ops are allowed
+ * to sleep, so adf_event_put() must NOT be called from an atomic context.
+ *
+ * Returns 0 if successful, -%EINVAL if the object does not support the
+ * requested event type, or -%EALREADY if the refcount is already 0.
+ */
+int adf_event_put(struct adf_obj *obj, enum adf_event_type type)
+{
+ struct adf_event_refcount *refcount;
+ int old_refcount;
+ int ret;
+
+ ret = adf_obj_check_supports_event(obj, type);
+ if (ret < 0)
+ return ret;
+
+
+ mutex_lock(&obj->event_lock);
+
+ refcount = adf_obj_find_event_refcount(obj, type);
+ if (!refcount) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ old_refcount = refcount->refcount--;
+
+ if (WARN_ON(old_refcount == 0)) {
+ refcount->refcount++;
+ ret = -EALREADY;
+ } else if (old_refcount == 1) {
+ obj->ops->set_event(obj, type, false);
+ trace_adf_event_disable(obj, type);
+ }
+
+done:
+ mutex_unlock(&obj->event_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_event_put);
+
+/**
+ * adf_vsync_wait - wait for a vsync event on a display interface
+ *
+ * @intf: the display interface
+ * @timeout: timeout in jiffies (0 = wait indefinitely)
+ *
+ * adf_vsync_wait() may sleep, so it must NOT be called from an atomic context.
+ *
+ * This function returns -%ERESTARTSYS if it is interrupted by a signal.
+ * If @timeout == 0 then this function returns 0 on vsync. If @timeout > 0 then
+ * this function returns the number of remaining jiffies or -%ETIMEDOUT on
+ * timeout.
+ */
+int adf_vsync_wait(struct adf_interface *intf, long timeout)
+{
+ ktime_t timestamp;
+ int ret;
+ unsigned long flags;
+
+ read_lock_irqsave(&intf->vsync_lock, flags);
+ timestamp = intf->vsync_timestamp;
+ read_unlock_irqrestore(&intf->vsync_lock, flags);
+
+ adf_vsync_get(intf);
+ if (timeout) {
+ ret = wait_event_interruptible_timeout(intf->vsync_wait,
+ !ktime_equal(timestamp,
+ intf->vsync_timestamp),
+ msecs_to_jiffies(timeout));
+ if (ret == 0 && ktime_equal(timestamp, intf->vsync_timestamp))
+ ret = -ETIMEDOUT;
+ } else {
+ ret = wait_event_interruptible(intf->vsync_wait,
+ !ktime_equal(timestamp,
+ intf->vsync_timestamp));
+ }
+ adf_vsync_put(intf);
+
+ return ret;
+}
+EXPORT_SYMBOL(adf_vsync_wait);
+
+static void adf_event_queue(struct adf_obj *obj, struct adf_event *event)
+{
+ struct adf_file *file;
+ unsigned long flags;
+
+ trace_adf_event(obj, event->type);
+
+ spin_lock_irqsave(&obj->file_lock, flags);
+
+ list_for_each_entry(file, &obj->file_list, head)
+ if (test_bit(event->type, file->event_subscriptions))
+ adf_file_queue_event(file, event);
+
+ spin_unlock_irqrestore(&obj->file_lock, flags);
+}
+
+/**
+ * adf_event_notify - notify userspace of a driver-private event
+ *
+ * @obj: the ADF object that produced the event
+ * @event: the event
+ *
+ * adf_event_notify() may be called safely from an atomic context. It will
+ * copy @event if needed, so @event may point to a variable on the stack.
+ *
+ * Drivers must NOT call adf_event_notify() for vsync and hotplug events.
+ * ADF provides adf_vsync_notify() and
+ * adf_hotplug_notify_{connected,disconnected}() for these events.
+ */
+int adf_event_notify(struct adf_obj *obj, struct adf_event *event)
+{
+ if (WARN_ON(event->type == ADF_EVENT_VSYNC ||
+ event->type == ADF_EVENT_HOTPLUG))
+ return -EINVAL;
+
+ adf_event_queue(obj, event);
+ return 0;
+}
+EXPORT_SYMBOL(adf_event_notify);
+
+/**
+ * adf_vsync_notify - notify ADF of a display interface's vsync event
+ *
+ * @intf: the display interface
+ * @timestamp: the time the vsync occurred
+ *
+ * adf_vsync_notify() may be called safely from an atomic context.
+ */
+void adf_vsync_notify(struct adf_interface *intf, ktime_t timestamp)
+{
+ unsigned long flags;
+ struct adf_vsync_event event;
+
+ write_lock_irqsave(&intf->vsync_lock, flags);
+ intf->vsync_timestamp = timestamp;
+ write_unlock_irqrestore(&intf->vsync_lock, flags);
+
+ wake_up_interruptible_all(&intf->vsync_wait);
+
+ event.base.type = ADF_EVENT_VSYNC;
+ event.base.length = sizeof(event);
+ event.timestamp = ktime_to_ns(timestamp);
+ adf_event_queue(&intf->base, &event.base);
+}
+EXPORT_SYMBOL(adf_vsync_notify);
+
+void adf_hotplug_notify(struct adf_interface *intf, bool connected,
+ struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+ unsigned long flags;
+ struct adf_hotplug_event event;
+ struct drm_mode_modeinfo *old_modelist;
+
+ write_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+ old_modelist = intf->modelist;
+ intf->hotplug_detect = connected;
+ intf->modelist = modelist;
+ intf->n_modes = n_modes;
+ write_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+ kfree(old_modelist);
+
+ event.base.length = sizeof(event);
+ event.base.type = ADF_EVENT_HOTPLUG;
+ event.connected = connected;
+ adf_event_queue(&intf->base, &event.base);
+}
+
+/**
+ * adf_hotplug_notify_connected - notify ADF of a display interface being
+ * connected to a display
+ *
+ * @intf: the display interface
+ * @modelist: hardware modes supported by display
+ * @n_modes: length of modelist
+ *
+ * @modelist is copied as needed, so it may point to a variable on the stack.
+ *
+ * adf_hotplug_notify_connected() may NOT be called safely from an atomic
+ * context.
+ *
+ * Returns 0 on success or error code (<0) on error.
+ */
+int adf_hotplug_notify_connected(struct adf_interface *intf,
+ struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+ struct drm_mode_modeinfo *modelist_copy;
+
+ if (n_modes > ADF_MAX_MODES)
+ return -ENOMEM;
+
+ modelist_copy = kzalloc(sizeof(modelist_copy[0]) * n_modes,
+ GFP_KERNEL);
+ if (!modelist_copy)
+ return -ENOMEM;
+ memcpy(modelist_copy, modelist, sizeof(modelist_copy[0]) * n_modes);
+
+ adf_hotplug_notify(intf, true, modelist_copy, n_modes);
+ return 0;
+}
+EXPORT_SYMBOL(adf_hotplug_notify_connected);
+
+/**
+ * adf_hotplug_notify_disconnected - notify ADF of a display interface being
+ * disconnected from a display
+ *
+ * @intf: the display interface
+ *
+ * adf_hotplug_notify_disconnected() may be called safely from an atomic
+ * context.
+ */
+void adf_hotplug_notify_disconnected(struct adf_interface *intf)
+{
+ adf_hotplug_notify(intf, false, NULL, 0);
+}
+EXPORT_SYMBOL(adf_hotplug_notify_disconnected);
+
+static int adf_obj_init(struct adf_obj *obj, enum adf_obj_type type,
+ struct idr *idr, struct adf_device *parent,
+ const struct adf_obj_ops *ops, const char *fmt, va_list args)
+{
+ int ret;
+
+ if (ops && ops->supports_event && !ops->set_event) {
+ pr_err("%s: %s implements supports_event but not set_event\n",
+ __func__, adf_obj_type_str(type));
+ return -EINVAL;
+ }
+
+ ret = idr_alloc(idr, obj, 0, 0, GFP_KERNEL);
+ if (ret < 0) {
+ pr_err("%s: allocating object id failed: %d\n", __func__, ret);
+ return ret;
+ }
+ obj->id = ret;
+
+ vscnprintf(obj->name, sizeof(obj->name), fmt, args);
+
+ obj->type = type;
+ obj->ops = ops;
+ obj->parent = parent;
+ mutex_init(&obj->event_lock);
+ obj->event_refcount = RB_ROOT;
+ spin_lock_init(&obj->file_lock);
+ INIT_LIST_HEAD(&obj->file_list);
+ return 0;
+}
+
+static void adf_obj_destroy(struct adf_obj *obj, struct idr *idr)
+{
+ struct rb_node *node = rb_first(&obj->event_refcount);
+
+ while (node) {
+ struct adf_event_refcount *refcount =
+ container_of(node, struct adf_event_refcount,
+ node);
+ rb_erase(&refcount->node, &obj->event_refcount);
+ kfree(refcount);
+ node = rb_first(&obj->event_refcount);
+ }
+
+ mutex_destroy(&obj->event_lock);
+ idr_remove(idr, obj->id);
+}
+
+/**
+ * adf_device_init - initialize ADF-internal data for a display device
+ * and create sysfs entries
+ *
+ * @dev: the display device
+ * @parent: the device's parent device
+ * @ops: the device's associated ops
+ * @fmt: formatting string for the display device's name
+ *
+ * @fmt specifies the device's sysfs filename and the name returned to
+ * userspace through the %ADF_GET_DEVICE_DATA ioctl.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_device_init(struct adf_device *dev, struct device *parent,
+ const struct adf_device_ops *ops, const char *fmt, ...)
+{
+ int ret;
+ va_list args;
+
+ if (!ops->validate || !ops->post) {
+ pr_err("%s: device must implement validate and post\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ if (!ops->complete_fence && !ops->advance_timeline) {
+ if (!IS_ENABLED(CONFIG_SW_SYNC)) {
+ pr_err("%s: device requires sw_sync but it is not enabled in the kernel\n",
+ __func__);
+ return -EINVAL;
+ }
+ } else if (!(ops->complete_fence && ops->advance_timeline)) {
+ pr_err("%s: device must implement both complete_fence and advance_timeline, or implement neither\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ memset(dev, 0, sizeof(*dev));
+
+ va_start(args, fmt);
+ ret = adf_obj_init(&dev->base, ADF_OBJ_DEVICE, &adf_devices, dev,
+ &ops->base, fmt, args);
+ va_end(args);
+ if (ret < 0)
+ return ret;
+
+ dev->dev = parent;
+ dev->ops = ops;
+ idr_init(&dev->overlay_engines);
+ idr_init(&dev->interfaces);
+ mutex_init(&dev->client_lock);
+ INIT_LIST_HEAD(&dev->post_list);
+ mutex_init(&dev->post_lock);
+ init_kthread_worker(&dev->post_worker);
+ INIT_LIST_HEAD(&dev->attached);
+ INIT_LIST_HEAD(&dev->attach_allowed);
+
+ dev->post_thread = kthread_run(kthread_worker_fn,
+ &dev->post_worker, dev->base.name);
+ if (IS_ERR(dev->post_thread)) {
+ ret = PTR_ERR(dev->post_thread);
+ dev->post_thread = NULL;
+
+ pr_err("%s: failed to run config posting thread: %d\n",
+ __func__, ret);
+ goto err;
+ }
+ init_kthread_work(&dev->post_work, adf_post_work_func);
+
+ ret = adf_device_sysfs_init(dev);
+ if (ret < 0)
+ goto err;
+
+ return 0;
+
+err:
+ adf_device_destroy(dev);
+ return ret;
+}
+EXPORT_SYMBOL(adf_device_init);
+
+/**
+ * adf_device_destroy - clean up ADF-internal data for a display device
+ *
+ * @dev: the display device
+ */
+void adf_device_destroy(struct adf_device *dev)
+{
+ struct adf_attachment_list *entry, *next;
+
+ idr_destroy(&dev->interfaces);
+ idr_destroy(&dev->overlay_engines);
+
+ if (dev->post_thread) {
+ flush_kthread_worker(&dev->post_worker);
+ kthread_stop(dev->post_thread);
+ }
+
+ if (dev->onscreen)
+ adf_post_cleanup(dev, dev->onscreen);
+ adf_device_sysfs_destroy(dev);
+ list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+ adf_attachment_free(entry);
+ }
+ list_for_each_entry_safe(entry, next, &dev->attached, head) {
+ adf_attachment_free(entry);
+ }
+ mutex_destroy(&dev->post_lock);
+ mutex_destroy(&dev->client_lock);
+
+ if (dev->timeline)
+ sync_timeline_destroy(&dev->timeline->obj);
+
+ adf_obj_destroy(&dev->base, &adf_devices);
+}
+EXPORT_SYMBOL(adf_device_destroy);
+
+/**
+ * adf_interface_init - initialize ADF-internal data for a display interface
+ * and create sysfs entries
+ *
+ * @intf: the display interface
+ * @dev: the interface's "parent" display device
+ * @type: interface type (see enum @adf_interface_type)
+ * @idx: which interface of type @type;
+ * e.g. interface DSI.1 -> @type=%ADF_INTF_TYPE_DSI, @idx=1
+ * @flags: informational flags (bitmask of %ADF_INTF_FLAG_* values)
+ * @ops: the interface's associated ops
+ * @fmt: formatting string for the display interface's name
+ *
+ * @dev must have previously been initialized with adf_device_init().
+ *
+ * @fmt affects the name returned to userspace through the
+ * %ADF_GET_INTERFACE_DATA ioctl. It does not affect the sysfs filename,
+ * which is derived from @dev's name.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_interface_init(struct adf_interface *intf, struct adf_device *dev,
+ enum adf_interface_type type, u32 idx, u32 flags,
+ const struct adf_interface_ops *ops, const char *fmt, ...)
+{
+ int ret;
+ va_list args;
+ const u32 allowed_flags = ADF_INTF_FLAG_PRIMARY |
+ ADF_INTF_FLAG_EXTERNAL;
+
+ if (dev->n_interfaces == ADF_MAX_INTERFACES) {
+ pr_err("%s: parent device %s has too many interfaces\n",
+ __func__, dev->base.name);
+ return -ENOMEM;
+ }
+
+ if (type >= ADF_INTF_MEMORY && type <= ADF_INTF_TYPE_DEVICE_CUSTOM) {
+ pr_err("%s: invalid interface type %u\n", __func__, type);
+ return -EINVAL;
+ }
+
+ if (flags & ~allowed_flags) {
+ pr_err("%s: invalid interface flags 0x%X\n", __func__,
+ flags & ~allowed_flags);
+ return -EINVAL;
+ }
+
+ memset(intf, 0, sizeof(*intf));
+
+ va_start(args, fmt);
+ ret = adf_obj_init(&intf->base, ADF_OBJ_INTERFACE, &dev->interfaces,
+ dev, ops ? &ops->base : NULL, fmt, args);
+ va_end(args);
+ if (ret < 0)
+ return ret;
+
+ intf->type = type;
+ intf->idx = idx;
+ intf->flags = flags;
+ intf->ops = ops;
+ intf->dpms_state = DRM_MODE_DPMS_OFF;
+ init_waitqueue_head(&intf->vsync_wait);
+ rwlock_init(&intf->vsync_lock);
+ rwlock_init(&intf->hotplug_modelist_lock);
+
+ ret = adf_interface_sysfs_init(intf);
+ if (ret < 0)
+ goto err;
+ dev->n_interfaces++;
+
+ return 0;
+
+err:
+ adf_obj_destroy(&intf->base, &dev->interfaces);
+ return ret;
+}
+EXPORT_SYMBOL(adf_interface_init);
+
+/**
+ * adf_interface_destroy - clean up ADF-internal data for a display interface
+ *
+ * @intf: the display interface
+ */
+void adf_interface_destroy(struct adf_interface *intf)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ struct adf_attachment_list *entry, *next;
+
+ mutex_lock(&dev->client_lock);
+ list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+ if (entry->attachment.interface == intf) {
+ adf_attachment_free(entry);
+ dev->n_attach_allowed--;
+ }
+ }
+ list_for_each_entry_safe(entry, next, &dev->attached, head) {
+ if (entry->attachment.interface == intf) {
+ adf_device_detach_op(dev,
+ entry->attachment.overlay_engine, intf);
+ adf_attachment_free(entry);
+ dev->n_attached--;
+ }
+ }
+ kfree(intf->modelist);
+ adf_interface_sysfs_destroy(intf);
+ adf_obj_destroy(&intf->base, &dev->interfaces);
+ dev->n_interfaces--;
+ mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_interface_destroy);
+
+static bool adf_overlay_engine_has_custom_formats(
+ const struct adf_overlay_engine_ops *ops)
+{
+ size_t i;
+ for (i = 0; i < ops->n_supported_formats; i++)
+ if (!adf_format_is_standard(ops->supported_formats[i]))
+ return true;
+ return false;
+}
+
+/**
+ * adf_overlay_engine_init - initialize ADF-internal data for an
+ * overlay engine and create sysfs entries
+ *
+ * @eng: the overlay engine
+ * @dev: the overlay engine's "parent" display device
+ * @ops: the overlay engine's associated ops
+ * @fmt: formatting string for the overlay engine's name
+ *
+ * @dev must have previously been initialized with adf_device_init().
+ *
+ * @fmt affects the name returned to userspace through the
+ * %ADF_GET_OVERLAY_ENGINE_DATA ioctl. It does not affect the sysfs filename,
+ * which is derived from @dev's name.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_overlay_engine_init(struct adf_overlay_engine *eng,
+ struct adf_device *dev,
+ const struct adf_overlay_engine_ops *ops, const char *fmt, ...)
+{
+ int ret;
+ va_list args;
+
+ if (!ops->supported_formats) {
+ pr_err("%s: overlay engine must support at least one format\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ if (ops->n_supported_formats > ADF_MAX_SUPPORTED_FORMATS) {
+ pr_err("%s: overlay engine supports too many formats\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ if (adf_overlay_engine_has_custom_formats(ops) &&
+ !dev->ops->validate_custom_format) {
+ pr_err("%s: overlay engine has custom formats but parent device %s does not implement validate_custom_format\n",
+ __func__, dev->base.name);
+ return -EINVAL;
+ }
+
+ memset(eng, 0, sizeof(*eng));
+
+ va_start(args, fmt);
+ ret = adf_obj_init(&eng->base, ADF_OBJ_OVERLAY_ENGINE,
+ &dev->overlay_engines, dev, &ops->base, fmt, args);
+ va_end(args);
+ if (ret < 0)
+ return ret;
+
+ eng->ops = ops;
+
+ ret = adf_overlay_engine_sysfs_init(eng);
+ if (ret < 0)
+ goto err;
+
+ return 0;
+
+err:
+ adf_obj_destroy(&eng->base, &dev->overlay_engines);
+ return ret;
+}
+EXPORT_SYMBOL(adf_overlay_engine_init);
+
+/**
+ * adf_interface_destroy - clean up ADF-internal data for an overlay engine
+ *
+ * @eng: the overlay engine
+ */
+void adf_overlay_engine_destroy(struct adf_overlay_engine *eng)
+{
+ struct adf_device *dev = adf_overlay_engine_parent(eng);
+ struct adf_attachment_list *entry, *next;
+
+ mutex_lock(&dev->client_lock);
+ list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+ if (entry->attachment.overlay_engine == eng) {
+ adf_attachment_free(entry);
+ dev->n_attach_allowed--;
+ }
+ }
+ list_for_each_entry_safe(entry, next, &dev->attached, head) {
+ if (entry->attachment.overlay_engine == eng) {
+ adf_device_detach_op(dev, eng,
+ entry->attachment.interface);
+ adf_attachment_free(entry);
+ dev->n_attached--;
+ }
+ }
+ adf_overlay_engine_sysfs_destroy(eng);
+ adf_obj_destroy(&eng->base, &dev->overlay_engines);
+ mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_overlay_engine_destroy);
+
+struct adf_attachment_list *adf_attachment_find(struct list_head *list,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ struct adf_attachment_list *entry;
+ list_for_each_entry(entry, list, head) {
+ if (entry->attachment.interface == intf &&
+ entry->attachment.overlay_engine == eng)
+ return entry;
+ }
+ return NULL;
+}
+
+int adf_attachment_validate(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ struct adf_device *intf_dev = adf_interface_parent(intf);
+ struct adf_device *eng_dev = adf_overlay_engine_parent(eng);
+
+ if (intf_dev != dev) {
+ dev_err(&dev->base.dev, "can't attach interface %s belonging to device %s\n",
+ intf->base.name, intf_dev->base.name);
+ return -EINVAL;
+ }
+
+ if (eng_dev != dev) {
+ dev_err(&dev->base.dev, "can't attach overlay engine %s belonging to device %s\n",
+ eng->base.name, eng_dev->base.name);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * adf_attachment_allow - add a new entry to the list of allowed
+ * attachments
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * adf_attachment_allow() indicates that the underlying display hardware allows
+ * @intf to scan out @eng's output. It is intended to be called at
+ * driver initialization for each supported overlay engine + interface pair.
+ *
+ * Returns 0 on success, -%EALREADY if the entry already exists, or -errno on
+ * any other failure.
+ */
+int adf_attachment_allow(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ int ret;
+ struct adf_attachment_list *entry = NULL;
+
+ ret = adf_attachment_validate(dev, eng, intf);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&dev->client_lock);
+
+ if (dev->n_attach_allowed == ADF_MAX_ATTACHMENTS) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ if (adf_attachment_find(&dev->attach_allowed, eng, intf)) {
+ ret = -EALREADY;
+ goto done;
+ }
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ entry->attachment.interface = intf;
+ entry->attachment.overlay_engine = eng;
+ list_add_tail(&entry->head, &dev->attach_allowed);
+ dev->n_attach_allowed++;
+
+done:
+ mutex_unlock(&dev->client_lock);
+ if (ret < 0)
+ kfree(entry);
+
+ return ret;
+}
+EXPORT_SYMBOL(adf_attachment_allow);
+
+/**
+ * adf_obj_type_str - string representation of an adf_obj_type
+ *
+ * @type: the object type
+ */
+const char *adf_obj_type_str(enum adf_obj_type type)
+{
+ switch (type) {
+ case ADF_OBJ_OVERLAY_ENGINE:
+ return "overlay engine";
+
+ case ADF_OBJ_INTERFACE:
+ return "interface";
+
+ case ADF_OBJ_DEVICE:
+ return "device";
+
+ default:
+ return "unknown";
+ }
+}
+EXPORT_SYMBOL(adf_obj_type_str);
+
+/**
+ * adf_interface_type_str - string representation of an adf_interface's type
+ *
+ * @intf: the interface
+ */
+const char *adf_interface_type_str(struct adf_interface *intf)
+{
+ switch (intf->type) {
+ case ADF_INTF_DSI:
+ return "DSI";
+
+ case ADF_INTF_eDP:
+ return "eDP";
+
+ case ADF_INTF_DPI:
+ return "DPI";
+
+ case ADF_INTF_VGA:
+ return "VGA";
+
+ case ADF_INTF_DVI:
+ return "DVI";
+
+ case ADF_INTF_HDMI:
+ return "HDMI";
+
+ case ADF_INTF_MEMORY:
+ return "memory";
+
+ default:
+ if (intf->type >= ADF_INTF_TYPE_DEVICE_CUSTOM) {
+ if (intf->ops && intf->ops->type_str)
+ return intf->ops->type_str(intf);
+ return "custom";
+ }
+ return "unknown";
+ }
+}
+EXPORT_SYMBOL(adf_interface_type_str);
+
+/**
+ * adf_event_type_str - string representation of an adf_event_type
+ *
+ * @obj: ADF object that produced the event
+ * @type: event type
+ */
+const char *adf_event_type_str(struct adf_obj *obj, enum adf_event_type type)
+{
+ switch (type) {
+ case ADF_EVENT_VSYNC:
+ return "vsync";
+
+ case ADF_EVENT_HOTPLUG:
+ return "hotplug";
+
+ default:
+ if (type >= ADF_EVENT_DEVICE_CUSTOM) {
+ if (obj->ops && obj->ops->event_type_str)
+ return obj->ops->event_type_str(obj, type);
+ return "custom";
+ }
+ return "unknown";
+ }
+}
+EXPORT_SYMBOL(adf_event_type_str);
+
+/**
+ * adf_format_str - string representation of an ADF/DRM fourcc format
+ *
+ * @format: format fourcc
+ * @buf: target buffer for the format's string representation
+ */
+void adf_format_str(u32 format, char buf[ADF_FORMAT_STR_SIZE])
+{
+ buf[0] = format & 0xFF;
+ buf[1] = (format >> 8) & 0xFF;
+ buf[2] = (format >> 16) & 0xFF;
+ buf[3] = (format >> 24) & 0xFF;
+ buf[4] = '\0';
+}
+EXPORT_SYMBOL(adf_format_str);
+
+/**
+ * adf_format_validate_yuv - validate the number and size of planes in buffers
+ * with a custom YUV format.
+ *
+ * @dev: ADF device performing the validation
+ * @buf: buffer to validate
+ * @num_planes: expected number of planes
+ * @hsub: expected horizontal chroma subsampling factor, in pixels
+ * @vsub: expected vertical chroma subsampling factor, in pixels
+ * @cpp: expected bytes per pixel for each plane (length @num_planes)
+ *
+ * adf_format_validate_yuv() is intended to be called as a helper from @dev's
+ * validate_custom_format() op.
+ *
+ * Returns 0 if @buf has the expected number of planes and each plane
+ * has sufficient size, or -EINVAL otherwise.
+ */
+int adf_format_validate_yuv(struct adf_device *dev, struct adf_buffer *buf,
+ u8 num_planes, u8 hsub, u8 vsub, u8 cpp[])
+{
+ u8 i;
+
+ if (num_planes != buf->n_planes) {
+ char format_str[ADF_FORMAT_STR_SIZE];
+ adf_format_str(buf->format, format_str);
+ dev_err(&dev->base.dev, "%u planes expected for format %s but %u planes provided\n",
+ num_planes, format_str, buf->n_planes);
+ return -EINVAL;
+ }
+
+ if (buf->w == 0 || buf->w % hsub) {
+ dev_err(&dev->base.dev, "bad buffer width %u\n", buf->w);
+ return -EINVAL;
+ }
+
+ if (buf->h == 0 || buf->h % vsub) {
+ dev_err(&dev->base.dev, "bad buffer height %u\n", buf->h);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < num_planes; i++) {
+ u32 width = buf->w / (i != 0 ? hsub : 1);
+ u32 height = buf->h / (i != 0 ? vsub : 1);
+ u8 cpp = adf_format_plane_cpp(buf->format, i);
+ u32 last_line_size;
+
+ if (buf->pitch[i] < (u64) width * cpp) {
+ dev_err(&dev->base.dev, "plane %u pitch is shorter than buffer width (pitch = %u, width = %u, bpp = %u)\n",
+ i, buf->pitch[i], width, cpp * 8);
+ return -EINVAL;
+ }
+
+ switch (dev->ops->quirks.buffer_padding) {
+ case ADF_BUFFER_PADDED_TO_PITCH:
+ last_line_size = buf->pitch[i];
+ break;
+
+ case ADF_BUFFER_UNPADDED:
+ last_line_size = width * cpp;
+ break;
+
+ default:
+ BUG();
+ }
+
+ if ((u64) (height - 1) * buf->pitch[i] + last_line_size +
+ buf->offset[i] > buf->dma_bufs[i]->size) {
+ dev_err(&dev->base.dev, "plane %u buffer too small (height = %u, pitch = %u, offset = %u, size = %zu)\n",
+ i, height, buf->pitch[i],
+ buf->offset[i], buf->dma_bufs[i]->size);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(adf_format_validate_yuv);
+
+/**
+ * adf_modeinfo_set_name - sets the name of a mode from its display resolution
+ *
+ * @mode: mode
+ *
+ * adf_modeinfo_set_name() fills in @mode->name in the format
+ * "[hdisplay]x[vdisplay](i)". It is intended to help drivers create
+ * ADF/DRM-style modelists from other mode formats.
+ */
+void adf_modeinfo_set_name(struct drm_mode_modeinfo *mode)
+{
+ bool interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE;
+
+ snprintf(mode->name, DRM_DISPLAY_MODE_LEN, "%dx%d%s",
+ mode->hdisplay, mode->vdisplay,
+ interlaced ? "i" : "");
+}
+EXPORT_SYMBOL(adf_modeinfo_set_name);
+
+/**
+ * adf_modeinfo_set_vrefresh - sets the vrefresh of a mode from its other
+ * timing data
+ *
+ * @mode: mode
+ *
+ * adf_modeinfo_set_vrefresh() calculates @mode->vrefresh from
+ * @mode->{h,v}display and @mode->flags. It is intended to help drivers
+ * create ADF/DRM-style modelists from other mode formats.
+ */
+void adf_modeinfo_set_vrefresh(struct drm_mode_modeinfo *mode)
+{
+ int refresh = 0;
+ unsigned int calc_val;
+
+ if (mode->vrefresh > 0)
+ return;
+
+ if (mode->htotal <= 0 || mode->vtotal <= 0)
+ return;
+
+ /* work out vrefresh the value will be x1000 */
+ calc_val = (mode->clock * 1000);
+ calc_val /= mode->htotal;
+ refresh = (calc_val + mode->vtotal / 2) / mode->vtotal;
+
+ if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+ refresh *= 2;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ refresh /= 2;
+ if (mode->vscan > 1)
+ refresh /= mode->vscan;
+
+ mode->vrefresh = refresh;
+}
+EXPORT_SYMBOL(adf_modeinfo_set_vrefresh);
+
+static int __init adf_init(void)
+{
+ int err;
+
+ err = adf_sysfs_init();
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static void __exit adf_exit(void)
+{
+ adf_sysfs_destroy();
+}
+
+module_init(adf_init);
+module_exit(adf_exit);
diff --git a/drivers/video/adf/adf.h b/drivers/video/adf/adf.h
new file mode 100644
index 0000000..3bcf1fa
--- /dev/null
+++ b/drivers/video/adf/adf.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_H
+#define __VIDEO_ADF_ADF_H
+
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <video/adf.h>
+#include "sync.h"
+
+struct adf_event_refcount {
+ struct rb_node node;
+ enum adf_event_type type;
+ int refcount;
+};
+
+void adf_buffer_cleanup(struct adf_buffer *buf);
+void adf_buffer_mapping_cleanup(struct adf_buffer_mapping *mapping,
+ struct adf_buffer *buf);
+void adf_post_cleanup(struct adf_device *dev, struct adf_pending_post *post);
+
+struct adf_attachment_list *adf_attachment_find(struct list_head *list,
+ struct adf_overlay_engine *eng, struct adf_interface *intf);
+int adf_attachment_validate(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf);
+void adf_attachment_free(struct adf_attachment_list *attachment);
+
+struct adf_event_refcount *adf_obj_find_event_refcount(struct adf_obj *obj,
+ enum adf_event_type type);
+
+static inline int adf_obj_check_supports_event(struct adf_obj *obj,
+ enum adf_event_type type)
+{
+ if (!obj->ops || !obj->ops->supports_event)
+ return -EOPNOTSUPP;
+ if (!obj->ops->supports_event(obj, type))
+ return -EINVAL;
+ return 0;
+}
+
+static inline int adf_device_attach_op(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ if (!dev->ops->attach)
+ return 0;
+
+ return dev->ops->attach(dev, eng, intf);
+}
+
+static inline int adf_device_detach_op(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ if (!dev->ops->detach)
+ return 0;
+
+ return dev->ops->detach(dev, eng, intf);
+}
+
+#endif /* __VIDEO_ADF_ADF_H */
diff --git a/drivers/video/adf/adf_client.c b/drivers/video/adf/adf_client.c
new file mode 100644
index 0000000..8061d8e
--- /dev/null
+++ b/drivers/video/adf/adf_client.c
@@ -0,0 +1,811 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "sw_sync.h"
+
+#include <video/adf.h>
+#include <video/adf_client.h>
+#include <video/adf_format.h>
+
+#include "adf.h"
+
+static inline bool vsync_active(u8 state)
+{
+ return state == DRM_MODE_DPMS_ON || state == DRM_MODE_DPMS_STANDBY;
+}
+
+/**
+ * adf_interface_blank - set interface's DPMS state
+ *
+ * @intf: the interface
+ * @state: one of %DRM_MODE_DPMS_*
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_blank(struct adf_interface *intf, u8 state)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ u8 prev_state;
+ bool disable_vsync;
+ bool enable_vsync;
+ int ret = 0;
+ struct adf_event_refcount *vsync_refcount;
+
+ if (!intf->ops || !intf->ops->blank)
+ return -EOPNOTSUPP;
+
+ if (state > DRM_MODE_DPMS_OFF)
+ return -EINVAL;
+
+ mutex_lock(&dev->client_lock);
+ if (state != DRM_MODE_DPMS_ON)
+ flush_kthread_worker(&dev->post_worker);
+ mutex_lock(&intf->base.event_lock);
+
+ vsync_refcount = adf_obj_find_event_refcount(&intf->base,
+ ADF_EVENT_VSYNC);
+ if (!vsync_refcount) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ prev_state = intf->dpms_state;
+ if (prev_state == state) {
+ ret = -EBUSY;
+ goto done;
+ }
+
+ disable_vsync = vsync_active(prev_state) &&
+ !vsync_active(state) &&
+ vsync_refcount->refcount;
+ enable_vsync = !vsync_active(prev_state) &&
+ vsync_active(state) &&
+ vsync_refcount->refcount;
+
+ if (disable_vsync)
+ intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+ false);
+
+ ret = intf->ops->blank(intf, state);
+ if (ret < 0) {
+ if (disable_vsync)
+ intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+ true);
+ goto done;
+ }
+
+ if (enable_vsync)
+ intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+ true);
+
+ intf->dpms_state = state;
+done:
+ mutex_unlock(&intf->base.event_lock);
+ mutex_unlock(&dev->client_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_interface_blank);
+
+/**
+ * adf_interface_blank - get interface's current DPMS state
+ *
+ * @intf: the interface
+ *
+ * Returns one of %DRM_MODE_DPMS_*.
+ */
+u8 adf_interface_dpms_state(struct adf_interface *intf)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ u8 dpms_state;
+
+ mutex_lock(&dev->client_lock);
+ dpms_state = intf->dpms_state;
+ mutex_unlock(&dev->client_lock);
+
+ return dpms_state;
+}
+EXPORT_SYMBOL(adf_interface_dpms_state);
+
+/**
+ * adf_interface_current_mode - get interface's current display mode
+ *
+ * @intf: the interface
+ * @mode: returns the current mode
+ */
+void adf_interface_current_mode(struct adf_interface *intf,
+ struct drm_mode_modeinfo *mode)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+
+ mutex_lock(&dev->client_lock);
+ memcpy(mode, &intf->current_mode, sizeof(*mode));
+ mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_interface_current_mode);
+
+/**
+ * adf_interface_modelist - get interface's modelist
+ *
+ * @intf: the interface
+ * @modelist: storage for the modelist (optional)
+ * @n_modes: length of @modelist
+ *
+ * If @modelist is not NULL, adf_interface_modelist() will copy up to @n_modes
+ * modelist entries into @modelist.
+ *
+ * Returns the length of the modelist.
+ */
+size_t adf_interface_modelist(struct adf_interface *intf,
+ struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+ unsigned long flags;
+ size_t retval;
+
+ read_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+ if (modelist)
+ memcpy(modelist, intf->modelist, sizeof(modelist[0]) *
+ min(n_modes, intf->n_modes));
+ retval = intf->n_modes;
+ read_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+ return retval;
+}
+EXPORT_SYMBOL(adf_interface_modelist);
+
+/**
+ * adf_interface_set_mode - set interface's display mode
+ *
+ * @intf: the interface
+ * @mode: the new mode
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_set_mode(struct adf_interface *intf,
+ struct drm_mode_modeinfo *mode)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ int ret = 0;
+
+ if (!intf->ops || !intf->ops->modeset)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&dev->client_lock);
+ flush_kthread_worker(&dev->post_worker);
+
+ ret = intf->ops->modeset(intf, mode);
+ if (ret < 0)
+ goto done;
+
+ memcpy(&intf->current_mode, mode, sizeof(*mode));
+done:
+ mutex_unlock(&dev->client_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_interface_set_mode);
+
+/**
+ * adf_interface_screen_size - get size of screen connected to interface
+ *
+ * @intf: the interface
+ * @width_mm: returns the screen width in mm
+ * @height_mm: returns the screen width in mm
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_get_screen_size(struct adf_interface *intf, u16 *width_mm,
+ u16 *height_mm)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ int ret;
+
+ if (!intf->ops || !intf->ops->screen_size)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&dev->client_lock);
+ ret = intf->ops->screen_size(intf, width_mm, height_mm);
+ mutex_unlock(&dev->client_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(adf_interface_get_screen_size);
+
+/**
+ * adf_overlay_engine_supports_format - returns whether a format is in an
+ * overlay engine's supported list
+ *
+ * @eng: the overlay engine
+ * @format: format fourcc
+ */
+bool adf_overlay_engine_supports_format(struct adf_overlay_engine *eng,
+ u32 format)
+{
+ size_t i;
+ for (i = 0; i < eng->ops->n_supported_formats; i++)
+ if (format == eng->ops->supported_formats[i])
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL(adf_overlay_engine_supports_format);
+
+static int adf_buffer_validate(struct adf_buffer *buf)
+{
+ struct adf_overlay_engine *eng = buf->overlay_engine;
+ struct device *dev = &eng->base.dev;
+ struct adf_device *parent = adf_overlay_engine_parent(eng);
+ u8 hsub, vsub, num_planes, cpp[ADF_MAX_PLANES], i;
+
+ if (!adf_overlay_engine_supports_format(eng, buf->format)) {
+ char format_str[ADF_FORMAT_STR_SIZE];
+ adf_format_str(buf->format, format_str);
+ dev_err(dev, "unsupported format %s\n", format_str);
+ return -EINVAL;
+ }
+
+ if (!adf_format_is_standard(buf->format))
+ return parent->ops->validate_custom_format(parent, buf);
+
+ hsub = adf_format_horz_chroma_subsampling(buf->format);
+ vsub = adf_format_vert_chroma_subsampling(buf->format);
+ num_planes = adf_format_num_planes(buf->format);
+ for (i = 0; i < num_planes; i++)
+ cpp[i] = adf_format_plane_cpp(buf->format, i);
+
+ return adf_format_validate_yuv(parent, buf, num_planes, hsub, vsub,
+ cpp);
+}
+
+static int adf_buffer_map(struct adf_device *dev, struct adf_buffer *buf,
+ struct adf_buffer_mapping *mapping)
+{
+ int ret = 0;
+ size_t i;
+
+ for (i = 0; i < buf->n_planes; i++) {
+ struct dma_buf_attachment *attachment;
+ struct sg_table *sg_table;
+
+ attachment = dma_buf_attach(buf->dma_bufs[i], dev->dev);
+ if (IS_ERR(attachment)) {
+ ret = PTR_ERR(attachment);
+ dev_err(&dev->base.dev, "attaching plane %zu failed: %d\n",
+ i, ret);
+ goto done;
+ }
+ mapping->attachments[i] = attachment;
+
+ sg_table = dma_buf_map_attachment(attachment, DMA_TO_DEVICE);
+ if (IS_ERR(sg_table)) {
+ ret = PTR_ERR(sg_table);
+ dev_err(&dev->base.dev, "mapping plane %zu failed: %d",
+ i, ret);
+ goto done;
+ } else if (!sg_table) {
+ ret = -ENOMEM;
+ dev_err(&dev->base.dev, "mapping plane %zu failed\n",
+ i);
+ goto done;
+ }
+ mapping->sg_tables[i] = sg_table;
+ }
+
+done:
+ if (ret < 0)
+ adf_buffer_mapping_cleanup(mapping, buf);
+
+ return ret;
+}
+
+static struct sync_fence *adf_sw_complete_fence(struct adf_device *dev)
+{
+ struct sync_pt *pt;
+ struct sync_fence *complete_fence;
+
+ if (!dev->timeline) {
+ dev->timeline = sw_sync_timeline_create(dev->base.name);
+ if (!dev->timeline)
+ return ERR_PTR(-ENOMEM);
+ dev->timeline_max = 1;
+ }
+
+ dev->timeline_max++;
+ pt = sw_sync_pt_create(dev->timeline, dev->timeline_max);
+ if (!pt)
+ goto err_pt_create;
+ complete_fence = sync_fence_create(dev->base.name, pt);
+ if (!complete_fence)
+ goto err_fence_create;
+
+ return complete_fence;
+
+err_fence_create:
+ sync_pt_free(pt);
+err_pt_create:
+ dev->timeline_max--;
+ return ERR_PTR(-ENOSYS);
+}
+
+/**
+ * adf_device_post - flip to a new set of buffers
+ *
+ * @dev: device targeted by the flip
+ * @intfs: interfaces targeted by the flip
+ * @n_intfs: number of targeted interfaces
+ * @bufs: description of buffers displayed
+ * @n_bufs: number of buffers displayed
+ * @custom_data: driver-private data
+ * @custom_data_size: size of driver-private data
+ *
+ * adf_device_post() will copy @intfs, @bufs, and @custom_data, so they may
+ * point to variables on the stack. adf_device_post() also takes its own
+ * reference on each of the dma-bufs in @bufs. The adf_device_post_nocopy()
+ * variant transfers ownership of these resources to ADF instead.
+ *
+ * On success, returns a sync fence which signals when the buffers are removed
+ * from the screen. On failure, returns ERR_PTR(-errno).
+ */
+struct sync_fence *adf_device_post(struct adf_device *dev,
+ struct adf_interface **intfs, size_t n_intfs,
+ struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+ size_t custom_data_size)
+{
+ struct adf_interface **intfs_copy = NULL;
+ struct adf_buffer *bufs_copy = NULL;
+ void *custom_data_copy = NULL;
+ struct sync_fence *ret;
+ size_t i;
+
+ intfs_copy = kzalloc(sizeof(intfs_copy[0]) * n_intfs, GFP_KERNEL);
+ if (!intfs_copy)
+ return ERR_PTR(-ENOMEM);
+
+ bufs_copy = kzalloc(sizeof(bufs_copy[0]) * n_bufs, GFP_KERNEL);
+ if (!bufs_copy) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err_alloc;
+ }
+
+ custom_data_copy = kzalloc(custom_data_size, GFP_KERNEL);
+ if (!custom_data_copy) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err_alloc;
+ }
+
+ for (i = 0; i < n_bufs; i++) {
+ size_t j;
+ for (j = 0; j < bufs[i].n_planes; j++)
+ get_dma_buf(bufs[i].dma_bufs[j]);
+ }
+
+ memcpy(intfs_copy, intfs, sizeof(intfs_copy[0]) * n_intfs);
+ memcpy(bufs_copy, bufs, sizeof(bufs_copy[0]) * n_bufs);
+ memcpy(custom_data_copy, custom_data, custom_data_size);
+
+ ret = adf_device_post_nocopy(dev, intfs_copy, n_intfs, bufs_copy,
+ n_bufs, custom_data_copy, custom_data_size);
+ if (IS_ERR(ret))
+ goto err_post;
+
+ return ret;
+
+err_post:
+ for (i = 0; i < n_bufs; i++) {
+ size_t j;
+ for (j = 0; j < bufs[i].n_planes; j++)
+ dma_buf_put(bufs[i].dma_bufs[j]);
+ }
+err_alloc:
+ kfree(custom_data_copy);
+ kfree(bufs_copy);
+ kfree(intfs_copy);
+ return ret;
+}
+EXPORT_SYMBOL(adf_device_post);
+
+/**
+ * adf_device_post_nocopy - flip to a new set of buffers
+ *
+ * adf_device_post_nocopy() has the same behavior as adf_device_post(),
+ * except ADF does not copy @intfs, @bufs, or @custom_data, and it does
+ * not take an extra reference on the dma-bufs in @bufs.
+ *
+ * @intfs, @bufs, and @custom_data must point to buffers allocated by
+ * kmalloc(). On success, ADF takes ownership of these buffers and the dma-bufs
+ * in @bufs, and will kfree()/dma_buf_put() them when they are no longer needed.
+ * On failure, adf_device_post_nocopy() does NOT take ownership of these
+ * buffers or the dma-bufs, and the caller must clean them up.
+ *
+ * adf_device_post_nocopy() is mainly intended for implementing ADF's ioctls.
+ * Clients may find the nocopy variant useful in limited cases, but most should
+ * call adf_device_post() instead.
+ */
+struct sync_fence *adf_device_post_nocopy(struct adf_device *dev,
+ struct adf_interface **intfs, size_t n_intfs,
+ struct adf_buffer *bufs, size_t n_bufs,
+ void *custom_data, size_t custom_data_size)
+{
+ struct adf_pending_post *cfg;
+ struct adf_buffer_mapping *mappings;
+ struct sync_fence *ret;
+ size_t i;
+ int err;
+
+ cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+ if (!cfg)
+ return ERR_PTR(-ENOMEM);
+
+ mappings = kzalloc(sizeof(mappings[0]) * n_bufs, GFP_KERNEL);
+ if (!mappings) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err_alloc;
+ }
+
+ mutex_lock(&dev->client_lock);
+
+ for (i = 0; i < n_bufs; i++) {
+ err = adf_buffer_validate(&bufs[i]);
+ if (err < 0) {
+ ret = ERR_PTR(err);
+ goto err_buf;
+ }
+
+ err = adf_buffer_map(dev, &bufs[i], &mappings[i]);
+ if (err < 0) {
+ ret = ERR_PTR(err);
+ goto err_buf;
+ }
+ }
+
+ INIT_LIST_HEAD(&cfg->head);
+ cfg->config.n_bufs = n_bufs;
+ cfg->config.bufs = bufs;
+ cfg->config.mappings = mappings;
+ cfg->config.custom_data = custom_data;
+ cfg->config.custom_data_size = custom_data_size;
+
+ err = dev->ops->validate(dev, &cfg->config, &cfg->state);
+ if (err < 0) {
+ ret = ERR_PTR(err);
+ goto err_buf;
+ }
+
+ mutex_lock(&dev->post_lock);
+
+ if (dev->ops->complete_fence)
+ ret = dev->ops->complete_fence(dev, &cfg->config,
+ cfg->state);
+ else
+ ret = adf_sw_complete_fence(dev);
+
+ if (IS_ERR(ret))
+ goto err_fence;
+
+ list_add_tail(&cfg->head, &dev->post_list);
+ queue_kthread_work(&dev->post_worker, &dev->post_work);
+ mutex_unlock(&dev->post_lock);
+ mutex_unlock(&dev->client_lock);
+ kfree(intfs);
+ return ret;
+
+err_fence:
+ mutex_unlock(&dev->post_lock);
+
+err_buf:
+ for (i = 0; i < n_bufs; i++)
+ adf_buffer_mapping_cleanup(&mappings[i], &bufs[i]);
+
+ mutex_unlock(&dev->client_lock);
+ kfree(mappings);
+
+err_alloc:
+ kfree(cfg);
+ return ret;
+}
+EXPORT_SYMBOL(adf_device_post_nocopy);
+
+static void adf_attachment_list_to_array(struct adf_device *dev,
+ struct list_head *src, struct adf_attachment *dst, size_t size)
+{
+ struct adf_attachment_list *entry;
+ size_t i = 0;
+
+ if (!dst)
+ return;
+
+ list_for_each_entry(entry, src, head) {
+ if (i == size)
+ return;
+ dst[i] = entry->attachment;
+ i++;
+ }
+}
+
+/**
+ * adf_device_attachments - get device's list of active attachments
+ *
+ * @dev: the device
+ * @attachments: storage for the attachment list (optional)
+ * @n_attachments: length of @attachments
+ *
+ * If @attachments is not NULL, adf_device_attachments() will copy up to
+ * @n_attachments entries into @attachments.
+ *
+ * Returns the length of the active attachment list.
+ */
+size_t adf_device_attachments(struct adf_device *dev,
+ struct adf_attachment *attachments, size_t n_attachments)
+{
+ size_t retval;
+
+ mutex_lock(&dev->client_lock);
+ adf_attachment_list_to_array(dev, &dev->attached, attachments,
+ n_attachments);
+ retval = dev->n_attached;
+ mutex_unlock(&dev->client_lock);
+
+ return retval;
+}
+EXPORT_SYMBOL(adf_device_attachments);
+
+/**
+ * adf_device_attachments_allowed - get device's list of allowed attachments
+ *
+ * @dev: the device
+ * @attachments: storage for the attachment list (optional)
+ * @n_attachments: length of @attachments
+ *
+ * If @attachments is not NULL, adf_device_attachments_allowed() will copy up to
+ * @n_attachments entries into @attachments.
+ *
+ * Returns the length of the allowed attachment list.
+ */
+size_t adf_device_attachments_allowed(struct adf_device *dev,
+ struct adf_attachment *attachments, size_t n_attachments)
+{
+ size_t retval;
+
+ mutex_lock(&dev->client_lock);
+ adf_attachment_list_to_array(dev, &dev->attach_allowed, attachments,
+ n_attachments);
+ retval = dev->n_attach_allowed;
+ mutex_unlock(&dev->client_lock);
+
+ return retval;
+}
+EXPORT_SYMBOL(adf_device_attachments_allowed);
+
+/**
+ * adf_device_attached - return whether an overlay engine and interface are
+ * attached
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ */
+bool adf_device_attached(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf)
+{
+ struct adf_attachment_list *attachment;
+
+ mutex_lock(&dev->client_lock);
+ attachment = adf_attachment_find(&dev->attached, eng, intf);
+ mutex_unlock(&dev->client_lock);
+
+ return attachment != NULL;
+}
+EXPORT_SYMBOL(adf_device_attached);
+
+/**
+ * adf_device_attach_allowed - return whether the ADF device supports attaching
+ * an overlay engine and interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ */
+bool adf_device_attach_allowed(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+ struct adf_attachment_list *attachment;
+
+ mutex_lock(&dev->client_lock);
+ attachment = adf_attachment_find(&dev->attach_allowed, eng, intf);
+ mutex_unlock(&dev->client_lock);
+
+ return attachment != NULL;
+}
+EXPORT_SYMBOL(adf_device_attach_allowed);
+/**
+ * adf_device_attach - attach an overlay engine to an interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * Returns 0 on success, -%EINVAL if attaching @intf and @eng is not allowed,
+ * -%EALREADY if @intf and @eng are already attached, or -errno on any other
+ * failure.
+ */
+int adf_device_attach(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf)
+{
+ int ret;
+ struct adf_attachment_list *attachment = NULL;
+
+ ret = adf_attachment_validate(dev, eng, intf);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&dev->client_lock);
+
+ if (dev->n_attached == ADF_MAX_ATTACHMENTS) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ if (!adf_attachment_find(&dev->attach_allowed, eng, intf)) {
+ ret = -EINVAL;
+ goto done;
+ }
+
+ if (adf_attachment_find(&dev->attached, eng, intf)) {
+ ret = -EALREADY;
+ goto done;
+ }
+
+ ret = adf_device_attach_op(dev, eng, intf);
+ if (ret < 0)
+ goto done;
+
+ attachment = kzalloc(sizeof(*attachment), GFP_KERNEL);
+ if (!attachment) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ attachment->attachment.interface = intf;
+ attachment->attachment.overlay_engine = eng;
+ list_add_tail(&attachment->head, &dev->attached);
+ dev->n_attached++;
+
+done:
+ mutex_unlock(&dev->client_lock);
+ if (ret < 0)
+ kfree(attachment);
+
+ return ret;
+}
+EXPORT_SYMBOL(adf_device_attach);
+
+/**
+ * adf_device_detach - detach an overlay engine from an interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * Returns 0 on success, -%EINVAL if @intf and @eng are not attached,
+ * or -errno on any other failure.
+ */
+int adf_device_detach(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf)
+{
+ int ret;
+ struct adf_attachment_list *attachment;
+
+ ret = adf_attachment_validate(dev, eng, intf);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&dev->client_lock);
+
+ attachment = adf_attachment_find(&dev->attached, eng, intf);
+ if (!attachment) {
+ ret = -EINVAL;
+ goto done;
+ }
+
+ ret = adf_device_detach_op(dev, eng, intf);
+ if (ret < 0)
+ goto done;
+
+ adf_attachment_free(attachment);
+ dev->n_attached--;
+done:
+ mutex_unlock(&dev->client_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_device_detach);
+
+/**
+ * adf_interface_simple_buffer_alloc - allocate a simple buffer
+ *
+ * @intf: target interface
+ * @w: width in pixels
+ * @h: height in pixels
+ * @format: format fourcc
+ * @dma_buf: returns the allocated buffer
+ * @offset: returns the byte offset of the allocated buffer's first pixel
+ * @pitch: returns the allocated buffer's pitch
+ *
+ * See &struct adf_simple_buffer_alloc for a description of simple buffers and
+ * their limitations.
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_simple_buffer_alloc(struct adf_interface *intf, u16 w, u16 h,
+ u32 format, struct dma_buf **dma_buf, u32 *offset, u32 *pitch)
+{
+ if (!intf->ops || !intf->ops->alloc_simple_buffer)
+ return -EOPNOTSUPP;
+
+ if (!adf_format_is_rgb(format))
+ return -EINVAL;
+
+ return intf->ops->alloc_simple_buffer(intf, w, h, format, dma_buf,
+ offset, pitch);
+}
+EXPORT_SYMBOL(adf_interface_simple_buffer_alloc);
+
+/**
+ * adf_interface_simple_post - flip to a single buffer
+ *
+ * @intf: interface targeted by the flip
+ * @buf: buffer to display
+ *
+ * adf_interface_simple_post() can be used generically for simple display
+ * configurations, since the client does not need to provide any driver-private
+ * configuration data.
+ *
+ * adf_interface_simple_post() has the same copying semantics as
+ * adf_device_post().
+ *
+ * On success, returns a sync fence which signals when the buffer is removed
+ * from the screen. On failure, returns ERR_PTR(-errno).
+ */
+struct sync_fence *adf_interface_simple_post(struct adf_interface *intf,
+ struct adf_buffer *buf)
+{
+ size_t custom_data_size = 0;
+ void *custom_data = NULL;
+ struct sync_fence *ret;
+
+ if (intf->ops && intf->ops->describe_simple_post) {
+ int err;
+
+ custom_data = kzalloc(ADF_MAX_CUSTOM_DATA_SIZE, GFP_KERNEL);
+ if (!custom_data) {
+ ret = ERR_PTR(-ENOMEM);
+ goto done;
+ }
+
+ err = intf->ops->describe_simple_post(intf, buf, custom_data,
+ &custom_data_size);
+ if (err < 0) {
+ ret = ERR_PTR(err);
+ goto done;
+ }
+ }
+
+ ret = adf_device_post(adf_interface_parent(intf), &intf, 1, buf, 1,
+ custom_data, custom_data_size);
+done:
+ kfree(custom_data);
+ return ret;
+}
+EXPORT_SYMBOL(adf_interface_simple_post);
diff --git a/drivers/video/adf/adf_fbdev.c b/drivers/video/adf/adf_fbdev.c
new file mode 100644
index 0000000..a5b53bc
--- /dev/null
+++ b/drivers/video/adf/adf_fbdev.c
@@ -0,0 +1,665 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/vmalloc.h>
+
+#include <video/adf.h>
+#include <video/adf_client.h>
+#include <video/adf_fbdev.h>
+#include <video/adf_format.h>
+
+#include "adf.h"
+
+struct adf_fbdev_format {
+ u32 fourcc;
+ u32 bpp;
+ u32 r_length;
+ u32 g_length;
+ u32 b_length;
+ u32 a_length;
+ u32 r_offset;
+ u32 g_offset;
+ u32 b_offset;
+ u32 a_offset;
+};
+
+static const struct adf_fbdev_format format_table[] = {
+ {DRM_FORMAT_RGB332, 8, 3, 3, 2, 0, 5, 2, 0, 0},
+ {DRM_FORMAT_BGR233, 8, 3, 3, 2, 0, 0, 3, 5, 0},
+
+ {DRM_FORMAT_XRGB4444, 16, 4, 4, 4, 0, 8, 4, 0, 0},
+ {DRM_FORMAT_XBGR4444, 16, 4, 4, 4, 0, 0, 4, 8, 0},
+ {DRM_FORMAT_RGBX4444, 16, 4, 4, 4, 0, 12, 8, 4, 0},
+ {DRM_FORMAT_BGRX4444, 16, 4, 4, 4, 0, 0, 4, 8, 0},
+
+ {DRM_FORMAT_ARGB4444, 16, 4, 4, 4, 4, 8, 4, 0, 12},
+ {DRM_FORMAT_ABGR4444, 16, 4, 4, 4, 4, 0, 4, 8, 12},
+ {DRM_FORMAT_RGBA4444, 16, 4, 4, 4, 4, 12, 8, 4, 0},
+ {DRM_FORMAT_BGRA4444, 16, 4, 4, 4, 4, 0, 4, 8, 0},
+
+ {DRM_FORMAT_XRGB1555, 16, 5, 5, 5, 0, 10, 5, 0, 0},
+ {DRM_FORMAT_XBGR1555, 16, 5, 5, 5, 0, 0, 5, 10, 0},
+ {DRM_FORMAT_RGBX5551, 16, 5, 5, 5, 0, 11, 6, 1, 0},
+ {DRM_FORMAT_BGRX5551, 16, 5, 5, 5, 0, 1, 6, 11, 0},
+
+ {DRM_FORMAT_ARGB1555, 16, 5, 5, 5, 1, 10, 5, 0, 15},
+ {DRM_FORMAT_ABGR1555, 16, 5, 5, 5, 1, 0, 5, 10, 15},
+ {DRM_FORMAT_RGBA5551, 16, 5, 5, 5, 1, 11, 6, 1, 0},
+ {DRM_FORMAT_BGRA5551, 16, 5, 5, 5, 1, 1, 6, 11, 0},
+
+ {DRM_FORMAT_RGB565, 16, 5, 6, 5, 0, 11, 5, 0, 0},
+ {DRM_FORMAT_BGR565, 16, 5, 6, 5, 0, 0, 5, 11, 0},
+
+ {DRM_FORMAT_RGB888, 24, 8, 8, 8, 0, 16, 8, 0, 0},
+ {DRM_FORMAT_BGR888, 24, 8, 8, 8, 0, 0, 8, 16, 0},
+
+ {DRM_FORMAT_XRGB8888, 32, 8, 8, 8, 0, 16, 8, 0, 0},
+ {DRM_FORMAT_XBGR8888, 32, 8, 8, 8, 0, 0, 8, 16, 0},
+ {DRM_FORMAT_RGBX8888, 32, 8, 8, 8, 0, 24, 16, 8, 0},
+ {DRM_FORMAT_BGRX8888, 32, 8, 8, 8, 0, 8, 16, 24, 0},
+
+ {DRM_FORMAT_ARGB8888, 32, 8, 8, 8, 8, 16, 8, 0, 24},
+ {DRM_FORMAT_ABGR8888, 32, 8, 8, 8, 8, 0, 8, 16, 24},
+ {DRM_FORMAT_RGBA8888, 32, 8, 8, 8, 8, 24, 16, 8, 0},
+ {DRM_FORMAT_BGRA8888, 32, 8, 8, 8, 8, 8, 16, 24, 0},
+
+ {DRM_FORMAT_XRGB2101010, 32, 10, 10, 10, 0, 20, 10, 0, 0},
+ {DRM_FORMAT_XBGR2101010, 32, 10, 10, 10, 0, 0, 10, 20, 0},
+ {DRM_FORMAT_RGBX1010102, 32, 10, 10, 10, 0, 22, 12, 2, 0},
+ {DRM_FORMAT_BGRX1010102, 32, 10, 10, 10, 0, 2, 12, 22, 0},
+
+ {DRM_FORMAT_ARGB2101010, 32, 10, 10, 10, 2, 20, 10, 0, 30},
+ {DRM_FORMAT_ABGR2101010, 32, 10, 10, 10, 2, 0, 10, 20, 30},
+ {DRM_FORMAT_RGBA1010102, 32, 10, 10, 10, 2, 22, 12, 2, 0},
+ {DRM_FORMAT_BGRA1010102, 32, 10, 10, 10, 2, 2, 12, 22, 0},
+};
+
+static u32 drm_fourcc_from_fb_var(struct fb_var_screeninfo *var)
+{
+ size_t i;
+ for (i = 0; i < ARRAY_SIZE(format_table); i++) {
+ const struct adf_fbdev_format *f = &format_table[i];
+ if (var->red.length == f->r_length &&
+ var->red.offset == f->r_offset &&
+ var->green.length == f->g_length &&
+ var->green.offset == f->g_offset &&
+ var->blue.length == f->b_length &&
+ var->blue.offset == f->b_offset &&
+ var->transp.length == f->a_length &&
+ (var->transp.length == 0 ||
+ var->transp.offset == f->a_offset))
+ return f->fourcc;
+ }
+
+ return 0;
+}
+
+static const struct adf_fbdev_format *fbdev_format_info(u32 format)
+{
+ size_t i;
+ for (i = 0; i < ARRAY_SIZE(format_table); i++) {
+ const struct adf_fbdev_format *f = &format_table[i];
+ if (f->fourcc == format)
+ return f;
+ }
+
+ BUG();
+}
+
+void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+ struct fb_videomode *vmode)
+{
+ memset(vmode, 0, sizeof(*vmode));
+
+ vmode->refresh = mode->vrefresh;
+
+ vmode->xres = mode->hdisplay;
+ vmode->yres = mode->vdisplay;
+
+ vmode->pixclock = mode->clock ? KHZ2PICOS(mode->clock) : 0;
+ vmode->left_margin = mode->htotal - mode->hsync_end;
+ vmode->right_margin = mode->hsync_start - mode->hdisplay;
+ vmode->upper_margin = mode->vtotal - mode->vsync_end;
+ vmode->lower_margin = mode->vsync_start - mode->vdisplay;
+ vmode->hsync_len = mode->hsync_end - mode->hsync_start;
+ vmode->vsync_len = mode->vsync_end - mode->vsync_start;
+
+ vmode->sync = 0;
+ if (mode->flags & DRM_MODE_FLAG_PHSYNC)
+ vmode->sync |= FB_SYNC_HOR_HIGH_ACT;
+ if (mode->flags & DRM_MODE_FLAG_PVSYNC)
+ vmode->sync |= FB_SYNC_VERT_HIGH_ACT;
+ if (mode->flags & DRM_MODE_FLAG_PCSYNC)
+ vmode->sync |= FB_SYNC_COMP_HIGH_ACT;
+ if (mode->flags & DRM_MODE_FLAG_BCAST)
+ vmode->sync |= FB_SYNC_BROADCAST;
+
+ vmode->vmode = 0;
+ if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+ vmode->vmode |= FB_VMODE_INTERLACED;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ vmode->vmode |= FB_VMODE_DOUBLE;
+}
+EXPORT_SYMBOL(adf_modeinfo_to_fb_videomode);
+
+void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+ struct drm_mode_modeinfo *mode)
+{
+ memset(mode, 0, sizeof(*mode));
+
+ mode->hdisplay = vmode->xres;
+ mode->hsync_start = mode->hdisplay + vmode->right_margin;
+ mode->hsync_end = mode->hsync_start + vmode->hsync_len;
+ mode->htotal = mode->hsync_end + vmode->left_margin;
+
+ mode->vdisplay = vmode->yres;
+ mode->vsync_start = mode->vdisplay + vmode->lower_margin;
+ mode->vsync_end = mode->vsync_start + vmode->vsync_len;
+ mode->vtotal = mode->vsync_end + vmode->upper_margin;
+
+ mode->clock = vmode->pixclock ? PICOS2KHZ(vmode->pixclock) : 0;
+
+ mode->flags = 0;
+ if (vmode->sync & FB_SYNC_HOR_HIGH_ACT)
+ mode->flags |= DRM_MODE_FLAG_PHSYNC;
+ if (vmode->sync & FB_SYNC_VERT_HIGH_ACT)
+ mode->flags |= DRM_MODE_FLAG_PVSYNC;
+ if (vmode->sync & FB_SYNC_COMP_HIGH_ACT)
+ mode->flags |= DRM_MODE_FLAG_PCSYNC;
+ if (vmode->sync & FB_SYNC_BROADCAST)
+ mode->flags |= DRM_MODE_FLAG_BCAST;
+ if (vmode->vmode & FB_VMODE_INTERLACED)
+ mode->flags |= DRM_MODE_FLAG_INTERLACE;
+ if (vmode->vmode & FB_VMODE_DOUBLE)
+ mode->flags |= DRM_MODE_FLAG_DBLSCAN;
+
+ if (vmode->refresh)
+ mode->vrefresh = vmode->refresh;
+ else
+ adf_modeinfo_set_vrefresh(mode);
+
+ if (vmode->name)
+ strlcpy(mode->name, vmode->name, sizeof(mode->name));
+ else
+ adf_modeinfo_set_name(mode);
+}
+EXPORT_SYMBOL(adf_modeinfo_from_fb_videomode);
+
+static int adf_fbdev_post(struct adf_fbdev *fbdev)
+{
+ struct adf_buffer buf;
+ struct sync_fence *complete_fence;
+ int ret = 0;
+
+ memset(&buf, 0, sizeof(buf));
+ buf.overlay_engine = fbdev->eng;
+ buf.w = fbdev->info->var.xres;
+ buf.h = fbdev->info->var.yres;
+ buf.format = fbdev->format;
+ buf.dma_bufs[0] = fbdev->dma_buf;
+ buf.offset[0] = fbdev->offset +
+ fbdev->info->var.yoffset * fbdev->pitch +
+ fbdev->info->var.xoffset *
+ (fbdev->info->var.bits_per_pixel / 8);
+ buf.pitch[0] = fbdev->pitch;
+ buf.n_planes = 1;
+
+ complete_fence = adf_interface_simple_post(fbdev->intf, &buf);
+ if (IS_ERR(complete_fence)) {
+ ret = PTR_ERR(complete_fence);
+ goto done;
+ }
+
+ sync_fence_put(complete_fence);
+done:
+ return ret;
+}
+
+static const u16 vga_palette[][3] = {
+ {0x0000, 0x0000, 0x0000},
+ {0x0000, 0x0000, 0xAAAA},
+ {0x0000, 0xAAAA, 0x0000},
+ {0x0000, 0xAAAA, 0xAAAA},
+ {0xAAAA, 0x0000, 0x0000},
+ {0xAAAA, 0x0000, 0xAAAA},
+ {0xAAAA, 0x5555, 0x0000},
+ {0xAAAA, 0xAAAA, 0xAAAA},
+ {0x5555, 0x5555, 0x5555},
+ {0x5555, 0x5555, 0xFFFF},
+ {0x5555, 0xFFFF, 0x5555},
+ {0x5555, 0xFFFF, 0xFFFF},
+ {0xFFFF, 0x5555, 0x5555},
+ {0xFFFF, 0x5555, 0xFFFF},
+ {0xFFFF, 0xFFFF, 0x5555},
+ {0xFFFF, 0xFFFF, 0xFFFF},
+};
+
+static int adf_fb_alloc(struct adf_fbdev *fbdev)
+{
+ int ret;
+
+ ret = adf_interface_simple_buffer_alloc(fbdev->intf,
+ fbdev->default_xres_virtual,
+ fbdev->default_yres_virtual,
+ fbdev->default_format,
+ &fbdev->dma_buf, &fbdev->offset, &fbdev->pitch);
+ if (ret < 0) {
+ dev_err(fbdev->info->dev, "allocating fb failed: %d\n", ret);
+ return ret;
+ }
+
+ fbdev->vaddr = dma_buf_vmap(fbdev->dma_buf);
+ if (!fbdev->vaddr) {
+ ret = -ENOMEM;
+ dev_err(fbdev->info->dev, "vmapping fb failed\n");
+ goto err_vmap;
+ }
+ fbdev->info->fix.line_length = fbdev->pitch;
+ fbdev->info->var.xres_virtual = fbdev->default_xres_virtual;
+ fbdev->info->var.yres_virtual = fbdev->default_yres_virtual;
+ fbdev->info->fix.smem_len = fbdev->dma_buf->size;
+ fbdev->info->screen_base = fbdev->vaddr;
+
+ return 0;
+
+err_vmap:
+ dma_buf_put(fbdev->dma_buf);
+ return ret;
+}
+
+static void adf_fb_destroy(struct adf_fbdev *fbdev)
+{
+ dma_buf_vunmap(fbdev->dma_buf, fbdev->vaddr);
+ dma_buf_put(fbdev->dma_buf);
+}
+
+static void adf_fbdev_set_format(struct adf_fbdev *fbdev, u32 format)
+{
+ size_t i;
+ const struct adf_fbdev_format *info = fbdev_format_info(format);
+ for (i = 0; i < ARRAY_SIZE(vga_palette); i++) {
+ u16 r = vga_palette[i][0];
+ u16 g = vga_palette[i][1];
+ u16 b = vga_palette[i][2];
+
+ r >>= (16 - info->r_length);
+ g >>= (16 - info->g_length);
+ b >>= (16 - info->b_length);
+
+ fbdev->pseudo_palette[i] =
+ (r << info->r_offset) |
+ (g << info->g_offset) |
+ (b << info->b_offset);
+
+ if (info->a_length) {
+ u16 a = BIT(info->a_length) - 1;
+ fbdev->pseudo_palette[i] |= (a << info->a_offset);
+ }
+ }
+
+ fbdev->info->var.bits_per_pixel = adf_format_bpp(format);
+ fbdev->info->var.red.length = info->r_length;
+ fbdev->info->var.red.offset = info->r_offset;
+ fbdev->info->var.green.length = info->g_length;
+ fbdev->info->var.green.offset = info->g_offset;
+ fbdev->info->var.blue.length = info->b_length;
+ fbdev->info->var.blue.offset = info->b_offset;
+ fbdev->info->var.transp.length = info->a_length;
+ fbdev->info->var.transp.offset = info->a_offset;
+ fbdev->format = format;
+}
+
+static void adf_fbdev_fill_modelist(struct adf_fbdev *fbdev)
+{
+ struct drm_mode_modeinfo *modelist;
+ struct fb_videomode fbmode;
+ size_t n_modes, i;
+ int ret = 0;
+
+ n_modes = adf_interface_modelist(fbdev->intf, NULL, 0);
+ modelist = kzalloc(sizeof(modelist[0]) * n_modes, GFP_KERNEL);
+ if (!modelist) {
+ dev_warn(fbdev->info->dev, "allocating new modelist failed; keeping old modelist\n");
+ return;
+ }
+ adf_interface_modelist(fbdev->intf, modelist, n_modes);
+
+ fb_destroy_modelist(&fbdev->info->modelist);
+
+ for (i = 0; i < n_modes; i++) {
+ adf_modeinfo_to_fb_videomode(&modelist[i], &fbmode);
+ ret = fb_add_videomode(&fbmode, &fbdev->info->modelist);
+ if (ret < 0)
+ dev_warn(fbdev->info->dev, "adding mode %s to modelist failed: %d\n",
+ modelist[i].name, ret);
+ }
+
+ kfree(modelist);
+}
+
+/**
+ * adf_fbdev_open - default implementation of fbdev open op
+ */
+int adf_fbdev_open(struct fb_info *info, int user)
+{
+ struct adf_fbdev *fbdev = info->par;
+ int ret;
+
+ mutex_lock(&fbdev->refcount_lock);
+
+ if (unlikely(fbdev->refcount == UINT_MAX)) {
+ ret = -EMFILE;
+ goto done;
+ }
+
+ if (!fbdev->refcount) {
+ struct drm_mode_modeinfo mode;
+ struct fb_videomode fbmode;
+ struct adf_device *dev = adf_interface_parent(fbdev->intf);
+
+ ret = adf_device_attach(dev, fbdev->eng, fbdev->intf);
+ if (ret < 0 && ret != -EALREADY)
+ goto done;
+
+ ret = adf_fb_alloc(fbdev);
+ if (ret < 0)
+ goto done;
+
+ adf_interface_current_mode(fbdev->intf, &mode);
+ adf_modeinfo_to_fb_videomode(&mode, &fbmode);
+ fb_videomode_to_var(&fbdev->info->var, &fbmode);
+
+ adf_fbdev_set_format(fbdev, fbdev->default_format);
+ adf_fbdev_fill_modelist(fbdev);
+ }
+
+ ret = adf_fbdev_post(fbdev);
+ if (ret < 0) {
+ if (!fbdev->refcount)
+ adf_fb_destroy(fbdev);
+ goto done;
+ }
+
+ fbdev->refcount++;
+done:
+ mutex_unlock(&fbdev->refcount_lock);
+ return ret;
+}
+EXPORT_SYMBOL(adf_fbdev_open);
+
+/**
+ * adf_fbdev_release - default implementation of fbdev release op
+ */
+int adf_fbdev_release(struct fb_info *info, int user)
+{
+ struct adf_fbdev *fbdev = info->par;
+ mutex_lock(&fbdev->refcount_lock);
+ BUG_ON(!fbdev->refcount);
+ fbdev->refcount--;
+ if (!fbdev->refcount)
+ adf_fb_destroy(fbdev);
+ mutex_unlock(&fbdev->refcount_lock);
+ return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_release);
+
+/**
+ * adf_fbdev_check_var - default implementation of fbdev check_var op
+ */
+int adf_fbdev_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+ struct adf_fbdev *fbdev = info->par;
+ bool valid_format = true;
+ u32 format = drm_fourcc_from_fb_var(var);
+ u32 pitch = var->xres_virtual * var->bits_per_pixel / 8;
+
+ if (!format) {
+ dev_dbg(info->dev, "%s: unrecognized format\n", __func__);
+ valid_format = false;
+ }
+
+ if (valid_format && var->grayscale) {
+ dev_dbg(info->dev, "%s: grayscale modes not supported\n",
+ __func__);
+ valid_format = false;
+ }
+
+ if (valid_format && var->nonstd) {
+ dev_dbg(info->dev, "%s: nonstandard formats not supported\n",
+ __func__);
+ valid_format = false;
+ }
+
+ if (valid_format && !adf_overlay_engine_supports_format(fbdev->eng,
+ format)) {
+ char format_str[ADF_FORMAT_STR_SIZE];
+ adf_format_str(format, format_str);
+ dev_dbg(info->dev, "%s: format %s not supported by overlay engine %s\n",
+ __func__, format_str, fbdev->eng->base.name);
+ valid_format = false;
+ }
+
+ if (valid_format && pitch > fbdev->pitch) {
+ dev_dbg(info->dev, "%s: fb pitch too small for var (pitch = %u, xres_virtual = %u, bits_per_pixel = %u)\n",
+ __func__, fbdev->pitch, var->xres_virtual,
+ var->bits_per_pixel);
+ valid_format = false;
+ }
+
+ if (valid_format && var->yres_virtual > fbdev->default_yres_virtual) {
+ dev_dbg(info->dev, "%s: fb height too small for var (h = %u, yres_virtual = %u)\n",
+ __func__, fbdev->default_yres_virtual,
+ var->yres_virtual);
+ valid_format = false;
+ }
+
+ if (valid_format) {
+ var->activate = info->var.activate;
+ var->height = info->var.height;
+ var->width = info->var.width;
+ var->accel_flags = info->var.accel_flags;
+ var->rotate = info->var.rotate;
+ var->colorspace = info->var.colorspace;
+ /* userspace can't change these */
+ } else {
+ /* if any part of the format is invalid then fixing it up is
+ impractical, so save just the modesetting bits and
+ overwrite everything else */
+ struct fb_videomode mode;
+ fb_var_to_videomode(&mode, var);
+ memcpy(var, &info->var, sizeof(*var));
+ fb_videomode_to_var(var, &mode);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_check_var);
+
+/**
+ * adf_fbdev_set_par - default implementation of fbdev set_par op
+ */
+int adf_fbdev_set_par(struct fb_info *info)
+{
+ struct adf_fbdev *fbdev = info->par;
+ struct adf_interface *intf = fbdev->intf;
+ struct fb_videomode vmode;
+ struct drm_mode_modeinfo mode;
+ int ret;
+ u32 format = drm_fourcc_from_fb_var(&info->var);
+
+ fb_var_to_videomode(&vmode, &info->var);
+ adf_modeinfo_from_fb_videomode(&vmode, &mode);
+ ret = adf_interface_set_mode(intf, &mode);
+ if (ret < 0)
+ return ret;
+
+ ret = adf_fbdev_post(fbdev);
+ if (ret < 0)
+ return ret;
+
+ if (format != fbdev->format)
+ adf_fbdev_set_format(fbdev, format);
+
+ return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_set_par);
+
+/**
+ * adf_fbdev_blank - default implementation of fbdev blank op
+ */
+int adf_fbdev_blank(int blank, struct fb_info *info)
+{
+ struct adf_fbdev *fbdev = info->par;
+ struct adf_interface *intf = fbdev->intf;
+ u8 dpms_state;
+
+ switch (blank) {
+ case FB_BLANK_UNBLANK:
+ dpms_state = DRM_MODE_DPMS_ON;
+ break;
+ case FB_BLANK_NORMAL:
+ dpms_state = DRM_MODE_DPMS_STANDBY;
+ break;
+ case FB_BLANK_VSYNC_SUSPEND:
+ dpms_state = DRM_MODE_DPMS_SUSPEND;
+ break;
+ case FB_BLANK_HSYNC_SUSPEND:
+ dpms_state = DRM_MODE_DPMS_STANDBY;
+ break;
+ case FB_BLANK_POWERDOWN:
+ dpms_state = DRM_MODE_DPMS_OFF;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return adf_interface_blank(intf, dpms_state);
+}
+EXPORT_SYMBOL(adf_fbdev_blank);
+
+/**
+ * adf_fbdev_pan_display - default implementation of fbdev pan_display op
+ */
+int adf_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+ struct adf_fbdev *fbdev = info->par;
+ return adf_fbdev_post(fbdev);
+}
+EXPORT_SYMBOL(adf_fbdev_pan_display);
+
+/**
+ * adf_fbdev_mmap - default implementation of fbdev mmap op
+ */
+int adf_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+ struct adf_fbdev *fbdev = info->par;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ return dma_buf_mmap(fbdev->dma_buf, vma, 0);
+}
+EXPORT_SYMBOL(adf_fbdev_mmap);
+
+/**
+ * adf_fbdev_init - initialize helper to wrap ADF device in fbdev API
+ *
+ * @fbdev: the fbdev helper
+ * @interface: the ADF interface that will display the framebuffer
+ * @eng: the ADF overlay engine that will scan out the framebuffer
+ * @xres_virtual: the virtual width of the framebuffer
+ * @yres_virtual: the virtual height of the framebuffer
+ * @format: the format of the framebuffer
+ * @fbops: the device's fbdev ops
+ * @fmt: formatting for the framebuffer identification string
+ * @...: variable arguments
+ *
+ * @format must be a standard, non-indexed RGB format, i.e.,
+ * adf_format_is_rgb(@format) && @format != @DRM_FORMAT_C8.
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_fbdev_init(struct adf_fbdev *fbdev, struct adf_interface *interface,
+ struct adf_overlay_engine *eng,
+ u16 xres_virtual, u16 yres_virtual, u32 format,
+ struct fb_ops *fbops, const char *fmt, ...)
+{
+ struct adf_device *parent = adf_interface_parent(interface);
+ struct device *dev = &parent->base.dev;
+ u16 width_mm, height_mm;
+ va_list args;
+ int ret;
+
+ if (!adf_format_is_rgb(format) ||
+ format == DRM_FORMAT_C8) {
+ dev_err(dev, "fbdev helper does not support format %u\n",
+ format);
+ return -EINVAL;
+ }
+
+ memset(fbdev, 0, sizeof(*fbdev));
+ fbdev->intf = interface;
+ fbdev->eng = eng;
+ fbdev->info = framebuffer_alloc(0, dev);
+ if (!fbdev->info) {
+ dev_err(dev, "allocating framebuffer device failed\n");
+ return -ENOMEM;
+ }
+ mutex_init(&fbdev->refcount_lock);
+ fbdev->default_xres_virtual = xres_virtual;
+ fbdev->default_yres_virtual = yres_virtual;
+ fbdev->default_format = format;
+
+ fbdev->info->flags = FBINFO_FLAG_DEFAULT;
+ ret = adf_interface_get_screen_size(interface, &width_mm, &height_mm);
+ if (ret < 0) {
+ width_mm = 0;
+ height_mm = 0;
+ }
+ fbdev->info->var.width = width_mm;
+ fbdev->info->var.height = height_mm;
+ fbdev->info->var.activate = FB_ACTIVATE_VBL;
+ va_start(args, fmt);
+ vsnprintf(fbdev->info->fix.id, sizeof(fbdev->info->fix.id), fmt, args);
+ va_end(args);
+ fbdev->info->fix.type = FB_TYPE_PACKED_PIXELS;
+ fbdev->info->fix.visual = FB_VISUAL_TRUECOLOR;
+ fbdev->info->fix.xpanstep = 1;
+ fbdev->info->fix.ypanstep = 1;
+ INIT_LIST_HEAD(&fbdev->info->modelist);
+ fbdev->info->fbops = fbops;
+ fbdev->info->pseudo_palette = fbdev->pseudo_palette;
+ fbdev->info->par = fbdev;
+
+ ret = register_framebuffer(fbdev->info);
+ if (ret < 0) {
+ dev_err(dev, "registering framebuffer failed: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_init);
+
+/**
+ * adf_fbdev_destroy - destroy helper to wrap ADF device in fbdev API
+ *
+ * @fbdev: the fbdev helper
+ */
+void adf_fbdev_destroy(struct adf_fbdev *fbdev)
+{
+ unregister_framebuffer(fbdev->info);
+ BUG_ON(fbdev->refcount);
+ mutex_destroy(&fbdev->refcount_lock);
+ framebuffer_release(fbdev->info);
+}
+EXPORT_SYMBOL(adf_fbdev_destroy);
diff --git a/drivers/video/adf/adf_fops.c b/drivers/video/adf/adf_fops.c
new file mode 100644
index 0000000..7fbf33e
--- /dev/null
+++ b/drivers/video/adf/adf_fops.c
@@ -0,0 +1,957 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/circ_buf.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <video/adf_client.h>
+#include <video/adf_format.h>
+
+#include "sw_sync.h"
+#include "sync.h"
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+#ifdef CONFIG_COMPAT
+#include "adf_fops32.h"
+#endif
+
+static int adf_obj_set_event(struct adf_obj *obj, struct adf_file *file,
+ struct adf_set_event __user *arg)
+{
+ struct adf_set_event data;
+ bool enabled;
+ unsigned long flags;
+ int err;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ err = adf_obj_check_supports_event(obj, data.type);
+ if (err < 0)
+ return err;
+
+ spin_lock_irqsave(&obj->file_lock, flags);
+ if (data.enabled)
+ enabled = test_and_set_bit(data.type,
+ file->event_subscriptions);
+ else
+ enabled = test_and_clear_bit(data.type,
+ file->event_subscriptions);
+ spin_unlock_irqrestore(&obj->file_lock, flags);
+
+ if (data.enabled == enabled)
+ return -EALREADY;
+
+ if (data.enabled)
+ adf_event_get(obj, data.type);
+ else
+ adf_event_put(obj, data.type);
+
+ return 0;
+}
+
+static int adf_obj_copy_custom_data_to_user(struct adf_obj *obj,
+ void __user *dst, size_t *dst_size)
+{
+ void *custom_data;
+ size_t custom_data_size;
+ int ret;
+
+ if (!obj->ops || !obj->ops->custom_data) {
+ dev_dbg(&obj->dev, "%s: no custom_data op\n", __func__);
+ return 0;
+ }
+
+ custom_data = kzalloc(ADF_MAX_CUSTOM_DATA_SIZE, GFP_KERNEL);
+ if (!custom_data)
+ return -ENOMEM;
+
+ ret = obj->ops->custom_data(obj, custom_data, &custom_data_size);
+ if (ret < 0)
+ goto done;
+
+ if (copy_to_user(dst, custom_data, min(*dst_size, custom_data_size))) {
+ ret = -EFAULT;
+ goto done;
+ }
+ *dst_size = custom_data_size;
+
+done:
+ kfree(custom_data);
+ return ret;
+}
+
+static int adf_eng_get_data(struct adf_overlay_engine *eng,
+ struct adf_overlay_engine_data __user *arg)
+{
+ struct adf_device *dev = adf_overlay_engine_parent(eng);
+ struct adf_overlay_engine_data data;
+ size_t n_supported_formats;
+ u32 *supported_formats = NULL;
+ int ret = 0;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ strlcpy(data.name, eng->base.name, sizeof(data.name));
+
+ if (data.n_supported_formats > ADF_MAX_SUPPORTED_FORMATS)
+ return -EINVAL;
+
+ n_supported_formats = data.n_supported_formats;
+ data.n_supported_formats = eng->ops->n_supported_formats;
+
+ if (n_supported_formats) {
+ supported_formats = kzalloc(n_supported_formats *
+ sizeof(supported_formats[0]), GFP_KERNEL);
+ if (!supported_formats)
+ return -ENOMEM;
+ }
+
+ memcpy(supported_formats, eng->ops->supported_formats,
+ sizeof(u32) * min(n_supported_formats,
+ eng->ops->n_supported_formats));
+
+ mutex_lock(&dev->client_lock);
+ ret = adf_obj_copy_custom_data_to_user(&eng->base, arg->custom_data,
+ &data.custom_data_size);
+ mutex_unlock(&dev->client_lock);
+
+ if (ret < 0)
+ goto done;
+
+ if (copy_to_user(arg, &data, sizeof(data))) {
+ ret = -EFAULT;
+ goto done;
+ }
+
+ if (supported_formats && copy_to_user(arg->supported_formats,
+ supported_formats,
+ n_supported_formats * sizeof(supported_formats[0])))
+ ret = -EFAULT;
+
+done:
+ kfree(supported_formats);
+ return ret;
+}
+
+static int adf_buffer_import(struct adf_device *dev,
+ struct adf_buffer_config __user *cfg, struct adf_buffer *buf)
+{
+ struct adf_buffer_config user_buf;
+ size_t i;
+ int ret = 0;
+
+ if (copy_from_user(&user_buf, cfg, sizeof(user_buf)))
+ return -EFAULT;
+
+ memset(buf, 0, sizeof(*buf));
+
+ if (user_buf.n_planes > ADF_MAX_PLANES) {
+ dev_err(&dev->base.dev, "invalid plane count %u\n",
+ user_buf.n_planes);
+ return -EINVAL;
+ }
+
+ buf->overlay_engine = idr_find(&dev->overlay_engines,
+ user_buf.overlay_engine);
+ if (!buf->overlay_engine) {
+ dev_err(&dev->base.dev, "invalid overlay engine id %u\n",
+ user_buf.overlay_engine);
+ return -ENOENT;
+ }
+
+ buf->w = user_buf.w;
+ buf->h = user_buf.h;
+ buf->format = user_buf.format;
+ for (i = 0; i < user_buf.n_planes; i++) {
+ buf->dma_bufs[i] = dma_buf_get(user_buf.fd[i]);
+ if (IS_ERR(buf->dma_bufs[i])) {
+ ret = PTR_ERR(buf->dma_bufs[i]);
+ dev_err(&dev->base.dev, "importing dma_buf fd %d failed: %d\n",
+ user_buf.fd[i], ret);
+ buf->dma_bufs[i] = NULL;
+ goto done;
+ }
+ buf->offset[i] = user_buf.offset[i];
+ buf->pitch[i] = user_buf.pitch[i];
+ }
+ buf->n_planes = user_buf.n_planes;
+
+ if (user_buf.acquire_fence >= 0) {
+ buf->acquire_fence = sync_fence_fdget(user_buf.acquire_fence);
+ if (!buf->acquire_fence) {
+ dev_err(&dev->base.dev, "getting fence fd %d failed\n",
+ user_buf.acquire_fence);
+ ret = -EINVAL;
+ goto done;
+ }
+ }
+
+done:
+ if (ret < 0)
+ adf_buffer_cleanup(buf);
+ return ret;
+}
+
+static int adf_device_post_config(struct adf_device *dev,
+ struct adf_post_config __user *arg)
+{
+ struct sync_fence *complete_fence;
+ int complete_fence_fd;
+ struct adf_buffer *bufs = NULL;
+ struct adf_interface **intfs = NULL;
+ size_t n_intfs, n_bufs, i;
+ void *custom_data = NULL;
+ size_t custom_data_size;
+ int ret = 0;
+
+ complete_fence_fd = get_unused_fd();
+ if (complete_fence_fd < 0)
+ return complete_fence_fd;
+
+ if (get_user(n_intfs, &arg->n_interfaces)) {
+ ret = -EFAULT;
+ goto err_get_user;
+ }
+
+ if (n_intfs > ADF_MAX_INTERFACES) {
+ ret = -EINVAL;
+ goto err_get_user;
+ }
+
+ if (get_user(n_bufs, &arg->n_bufs)) {
+ ret = -EFAULT;
+ goto err_get_user;
+ }
+
+ if (n_bufs > ADF_MAX_BUFFERS) {
+ ret = -EINVAL;
+ goto err_get_user;
+ }
+
+ if (get_user(custom_data_size, &arg->custom_data_size)) {
+ ret = -EFAULT;
+ goto err_get_user;
+ }
+
+ if (custom_data_size > ADF_MAX_CUSTOM_DATA_SIZE) {
+ ret = -EINVAL;
+ goto err_get_user;
+ }
+
+ if (n_intfs) {
+ intfs = kmalloc(sizeof(intfs[0]) * n_intfs, GFP_KERNEL);
+ if (!intfs) {
+ ret = -ENOMEM;
+ goto err_get_user;
+ }
+ }
+
+ for (i = 0; i < n_intfs; i++) {
+ u32 intf_id;
+ if (get_user(intf_id, &arg->interfaces[i])) {
+ ret = -EFAULT;
+ goto err_get_user;
+ }
+
+ intfs[i] = idr_find(&dev->interfaces, intf_id);
+ if (!intfs[i]) {
+ ret = -EINVAL;
+ goto err_get_user;
+ }
+ }
+
+ if (n_bufs) {
+ bufs = kzalloc(sizeof(bufs[0]) * n_bufs, GFP_KERNEL);
+ if (!bufs) {
+ ret = -ENOMEM;
+ goto err_get_user;
+ }
+ }
+
+ for (i = 0; i < n_bufs; i++) {
+ ret = adf_buffer_import(dev, &arg->bufs[i], &bufs[i]);
+ if (ret < 0) {
+ memset(&bufs[i], 0, sizeof(bufs[i]));
+ goto err_import;
+ }
+ }
+
+ if (custom_data_size) {
+ custom_data = kzalloc(custom_data_size, GFP_KERNEL);
+ if (!custom_data) {
+ ret = -ENOMEM;
+ goto err_import;
+ }
+
+ if (copy_from_user(custom_data, arg->custom_data,
+ custom_data_size)) {
+ ret = -EFAULT;
+ goto err_import;
+ }
+ }
+
+ if (put_user(complete_fence_fd, &arg->complete_fence)) {
+ ret = -EFAULT;
+ goto err_import;
+ }
+
+ complete_fence = adf_device_post_nocopy(dev, intfs, n_intfs, bufs,
+ n_bufs, custom_data, custom_data_size);
+ if (IS_ERR(complete_fence)) {
+ ret = PTR_ERR(complete_fence);
+ goto err_import;
+ }
+
+ sync_fence_install(complete_fence, complete_fence_fd);
+ return 0;
+
+err_import:
+ for (i = 0; i < n_bufs; i++)
+ adf_buffer_cleanup(&bufs[i]);
+
+err_get_user:
+ kfree(custom_data);
+ kfree(bufs);
+ kfree(intfs);
+ put_unused_fd(complete_fence_fd);
+ return ret;
+}
+
+static int adf_intf_simple_post_config(struct adf_interface *intf,
+ struct adf_simple_post_config __user *arg)
+{
+ struct adf_device *dev = intf->base.parent;
+ struct sync_fence *complete_fence;
+ int complete_fence_fd;
+ struct adf_buffer buf;
+ int ret = 0;
+
+ complete_fence_fd = get_unused_fd();
+ if (complete_fence_fd < 0)
+ return complete_fence_fd;
+
+ ret = adf_buffer_import(dev, &arg->buf, &buf);
+ if (ret < 0)
+ goto err_import;
+
+ if (put_user(complete_fence_fd, &arg->complete_fence)) {
+ ret = -EFAULT;
+ goto err_put_user;
+ }
+
+ complete_fence = adf_interface_simple_post(intf, &buf);
+ if (IS_ERR(complete_fence)) {
+ ret = PTR_ERR(complete_fence);
+ goto err_put_user;
+ }
+
+ sync_fence_install(complete_fence, complete_fence_fd);
+ return 0;
+
+err_put_user:
+ adf_buffer_cleanup(&buf);
+err_import:
+ put_unused_fd(complete_fence_fd);
+ return ret;
+}
+
+static int adf_intf_simple_buffer_alloc(struct adf_interface *intf,
+ struct adf_simple_buffer_alloc __user *arg)
+{
+ struct adf_simple_buffer_alloc data;
+ struct dma_buf *dma_buf;
+ int ret = 0;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ data.fd = get_unused_fd_flags(O_CLOEXEC);
+ if (data.fd < 0)
+ return data.fd;
+
+ ret = adf_interface_simple_buffer_alloc(intf, data.w, data.h,
+ data.format, &dma_buf, &data.offset, &data.pitch);
+ if (ret < 0)
+ goto err_alloc;
+
+ if (copy_to_user(arg, &data, sizeof(*arg))) {
+ ret = -EFAULT;
+ goto err_copy;
+ }
+
+ fd_install(data.fd, dma_buf->file);
+ return 0;
+
+err_copy:
+ dma_buf_put(dma_buf);
+
+err_alloc:
+ put_unused_fd(data.fd);
+ return ret;
+}
+
+static int adf_copy_attachment_list_to_user(
+ struct adf_attachment_config __user *to, size_t n_to,
+ struct adf_attachment *from, size_t n_from)
+{
+ struct adf_attachment_config *temp;
+ size_t n = min(n_to, n_from);
+ size_t i;
+ int ret = 0;
+
+ if (!n)
+ return 0;
+
+ temp = kzalloc(n * sizeof(temp[0]), GFP_KERNEL);
+ if (!temp)
+ return -ENOMEM;
+
+ for (i = 0; i < n; i++) {
+ temp[i].interface = from[i].interface->base.id;
+ temp[i].overlay_engine = from[i].overlay_engine->base.id;
+ }
+
+ if (copy_to_user(to, temp, n * sizeof(to[0]))) {
+ ret = -EFAULT;
+ goto done;
+ }
+
+done:
+ kfree(temp);
+ return ret;
+}
+
+static int adf_device_get_data(struct adf_device *dev,
+ struct adf_device_data __user *arg)
+{
+ struct adf_device_data data;
+ size_t n_attach;
+ struct adf_attachment *attach = NULL;
+ size_t n_allowed_attach;
+ struct adf_attachment *allowed_attach = NULL;
+ int ret = 0;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ if (data.n_attachments > ADF_MAX_ATTACHMENTS ||
+ data.n_allowed_attachments > ADF_MAX_ATTACHMENTS)
+ return -EINVAL;
+
+ strlcpy(data.name, dev->base.name, sizeof(data.name));
+
+ if (data.n_attachments) {
+ attach = kzalloc(data.n_attachments * sizeof(attach[0]),
+ GFP_KERNEL);
+ if (!attach)
+ return -ENOMEM;
+ }
+ n_attach = adf_device_attachments(dev, attach, data.n_attachments);
+
+ if (data.n_allowed_attachments) {
+ allowed_attach = kzalloc(data.n_allowed_attachments *
+ sizeof(allowed_attach[0]), GFP_KERNEL);
+ if (!allowed_attach) {
+ ret = -ENOMEM;
+ goto done;
+ }
+ }
+ n_allowed_attach = adf_device_attachments_allowed(dev, allowed_attach,
+ data.n_allowed_attachments);
+
+ mutex_lock(&dev->client_lock);
+ ret = adf_obj_copy_custom_data_to_user(&dev->base, arg->custom_data,
+ &data.custom_data_size);
+ mutex_unlock(&dev->client_lock);
+
+ if (ret < 0)
+ goto done;
+
+ ret = adf_copy_attachment_list_to_user(arg->attachments,
+ data.n_attachments, attach, n_attach);
+ if (ret < 0)
+ goto done;
+
+ ret = adf_copy_attachment_list_to_user(arg->allowed_attachments,
+ data.n_allowed_attachments, allowed_attach,
+ n_allowed_attach);
+ if (ret < 0)
+ goto done;
+
+ data.n_attachments = n_attach;
+ data.n_allowed_attachments = n_allowed_attach;
+
+ if (copy_to_user(arg, &data, sizeof(data)))
+ ret = -EFAULT;
+
+done:
+ kfree(allowed_attach);
+ kfree(attach);
+ return ret;
+}
+
+static int adf_device_handle_attachment(struct adf_device *dev,
+ struct adf_attachment_config __user *arg, bool attach)
+{
+ struct adf_attachment_config data;
+ struct adf_overlay_engine *eng;
+ struct adf_interface *intf;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ eng = idr_find(&dev->overlay_engines, data.overlay_engine);
+ if (!eng) {
+ dev_err(&dev->base.dev, "invalid overlay engine id %u\n",
+ data.overlay_engine);
+ return -EINVAL;
+ }
+
+ intf = idr_find(&dev->interfaces, data.interface);
+ if (!intf) {
+ dev_err(&dev->base.dev, "invalid interface id %u\n",
+ data.interface);
+ return -EINVAL;
+ }
+
+ if (attach)
+ return adf_device_attach(dev, eng, intf);
+ else
+ return adf_device_detach(dev, eng, intf);
+}
+
+static int adf_intf_set_mode(struct adf_interface *intf,
+ struct drm_mode_modeinfo __user *arg)
+{
+ struct drm_mode_modeinfo mode;
+
+ if (copy_from_user(&mode, arg, sizeof(mode)))
+ return -EFAULT;
+
+ return adf_interface_set_mode(intf, &mode);
+}
+
+static int adf_intf_get_data(struct adf_interface *intf,
+ struct adf_interface_data __user *arg)
+{
+ struct adf_device *dev = adf_interface_parent(intf);
+ struct adf_interface_data data;
+ struct drm_mode_modeinfo *modelist;
+ size_t modelist_size;
+ int err;
+ int ret = 0;
+ unsigned long flags;
+
+ if (copy_from_user(&data, arg, sizeof(data)))
+ return -EFAULT;
+
+ strlcpy(data.name, intf->base.name, sizeof(data.name));
+
+ data.type = intf->type;
+ data.id = intf->idx;
+ data.flags = intf->flags;
+
+ err = adf_interface_get_screen_size(intf, &data.width_mm,
+ &data.height_mm);
+ if (err < 0) {
+ data.width_mm = 0;
+ data.height_mm = 0;
+ }
+
+ modelist = kmalloc(sizeof(modelist[0]) * ADF_MAX_MODES, GFP_KERNEL);
+ if (!modelist)
+ return -ENOMEM;
+
+ mutex_lock(&dev->client_lock);
+ read_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+ data.hotplug_detect = intf->hotplug_detect;
+ modelist_size = min(data.n_available_modes, intf->n_modes) *
+ sizeof(intf->modelist[0]);
+ memcpy(modelist, intf->modelist, modelist_size);
+ data.n_available_modes = intf->n_modes;
+ read_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+ if (copy_to_user(arg->available_modes, modelist, modelist_size)) {
+ ret = -EFAULT;
+ goto done;
+ }
+
+ data.dpms_state = intf->dpms_state;
+ memcpy(&data.current_mode, &intf->current_mode,
+ sizeof(intf->current_mode));
+
+ ret = adf_obj_copy_custom_data_to_user(&intf->base, arg->custom_data,
+ &data.custom_data_size);
+done:
+ mutex_unlock(&dev->client_lock);
+ kfree(modelist);
+
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(arg, &data, sizeof(data)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
+static inline long adf_obj_custom_ioctl(struct adf_obj *obj, unsigned int cmd,
+ unsigned long arg)
+{
+ if (obj->ops && obj->ops->ioctl)
+ return obj->ops->ioctl(obj, cmd, arg);
+ return -ENOTTY;
+}
+
+static long adf_overlay_engine_ioctl(struct adf_overlay_engine *eng,
+ struct adf_file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case ADF_SET_EVENT:
+ return adf_obj_set_event(&eng->base, file,
+ (struct adf_set_event __user *)arg);
+
+ case ADF_GET_OVERLAY_ENGINE_DATA:
+ return adf_eng_get_data(eng,
+ (struct adf_overlay_engine_data __user *)arg);
+
+ case ADF_BLANK:
+ case ADF_POST_CONFIG:
+ case ADF_SET_MODE:
+ case ADF_GET_DEVICE_DATA:
+ case ADF_GET_INTERFACE_DATA:
+ case ADF_SIMPLE_POST_CONFIG:
+ case ADF_SIMPLE_BUFFER_ALLOC:
+ case ADF_ATTACH:
+ case ADF_DETACH:
+ return -EINVAL;
+
+ default:
+ return adf_obj_custom_ioctl(&eng->base, cmd, arg);
+ }
+}
+
+static long adf_interface_ioctl(struct adf_interface *intf,
+ struct adf_file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case ADF_SET_EVENT:
+ return adf_obj_set_event(&intf->base, file,
+ (struct adf_set_event __user *)arg);
+
+ case ADF_BLANK:
+ return adf_interface_blank(intf, arg);
+
+ case ADF_SET_MODE:
+ return adf_intf_set_mode(intf,
+ (struct drm_mode_modeinfo __user *)arg);
+
+ case ADF_GET_INTERFACE_DATA:
+ return adf_intf_get_data(intf,
+ (struct adf_interface_data __user *)arg);
+
+ case ADF_SIMPLE_POST_CONFIG:
+ return adf_intf_simple_post_config(intf,
+ (struct adf_simple_post_config __user *)arg);
+
+ case ADF_SIMPLE_BUFFER_ALLOC:
+ return adf_intf_simple_buffer_alloc(intf,
+ (struct adf_simple_buffer_alloc __user *)arg);
+
+ case ADF_POST_CONFIG:
+ case ADF_GET_DEVICE_DATA:
+ case ADF_GET_OVERLAY_ENGINE_DATA:
+ case ADF_ATTACH:
+ case ADF_DETACH:
+ return -EINVAL;
+
+ default:
+ return adf_obj_custom_ioctl(&intf->base, cmd, arg);
+ }
+}
+
+static long adf_device_ioctl(struct adf_device *dev, struct adf_file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case ADF_SET_EVENT:
+ return adf_obj_set_event(&dev->base, file,
+ (struct adf_set_event __user *)arg);
+
+ case ADF_POST_CONFIG:
+ return adf_device_post_config(dev,
+ (struct adf_post_config __user *)arg);
+
+ case ADF_GET_DEVICE_DATA:
+ return adf_device_get_data(dev,
+ (struct adf_device_data __user *)arg);
+
+ case ADF_ATTACH:
+ return adf_device_handle_attachment(dev,
+ (struct adf_attachment_config __user *)arg,
+ true);
+
+ case ADF_DETACH:
+ return adf_device_handle_attachment(dev,
+ (struct adf_attachment_config __user *)arg,
+ false);
+
+ case ADF_BLANK:
+ case ADF_SET_MODE:
+ case ADF_GET_INTERFACE_DATA:
+ case ADF_GET_OVERLAY_ENGINE_DATA:
+ case ADF_SIMPLE_POST_CONFIG:
+ case ADF_SIMPLE_BUFFER_ALLOC:
+ return -EINVAL;
+
+ default:
+ return adf_obj_custom_ioctl(&dev->base, cmd, arg);
+ }
+}
+
+static int adf_file_open(struct inode *inode, struct file *file)
+{
+ struct adf_obj *obj;
+ struct adf_file *fpriv = NULL;
+ unsigned long flags;
+ int ret = 0;
+
+ obj = adf_obj_sysfs_find(iminor(inode));
+ if (!obj)
+ return -ENODEV;
+
+ dev_dbg(&obj->dev, "opening %s\n", dev_name(&obj->dev));
+
+ if (!try_module_get(obj->parent->ops->owner)) {
+ dev_err(&obj->dev, "getting owner module failed\n");
+ return -ENODEV;
+ }
+
+ fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
+ if (!fpriv) {
+ ret = -ENOMEM;
+ goto done;
+ }
+
+ INIT_LIST_HEAD(&fpriv->head);
+ fpriv->obj = obj;
+ init_waitqueue_head(&fpriv->event_wait);
+
+ file->private_data = fpriv;
+
+ if (obj->ops && obj->ops->open) {
+ ret = obj->ops->open(obj, inode, file);
+ if (ret < 0)
+ goto done;
+ }
+
+ spin_lock_irqsave(&obj->file_lock, flags);
+ list_add_tail(&fpriv->head, &obj->file_list);
+ spin_unlock_irqrestore(&obj->file_lock, flags);
+
+done:
+ if (ret < 0) {
+ kfree(fpriv);
+ module_put(obj->parent->ops->owner);
+ }
+ return ret;
+}
+
+static int adf_file_release(struct inode *inode, struct file *file)
+{
+ struct adf_file *fpriv = file->private_data;
+ struct adf_obj *obj = fpriv->obj;
+ enum adf_event_type event_type;
+ unsigned long flags;
+
+ if (obj->ops && obj->ops->release)
+ obj->ops->release(obj, inode, file);
+
+ spin_lock_irqsave(&obj->file_lock, flags);
+ list_del(&fpriv->head);
+ spin_unlock_irqrestore(&obj->file_lock, flags);
+
+ for_each_set_bit(event_type, fpriv->event_subscriptions,
+ ADF_EVENT_TYPE_MAX) {
+ adf_event_put(obj, event_type);
+ }
+
+ kfree(fpriv);
+ module_put(obj->parent->ops->owner);
+
+ dev_dbg(&obj->dev, "released %s\n", dev_name(&obj->dev));
+ return 0;
+}
+
+long adf_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct adf_file *fpriv = file->private_data;
+ struct adf_obj *obj = fpriv->obj;
+ long ret = -EINVAL;
+
+ dev_dbg(&obj->dev, "%s ioctl %u\n", dev_name(&obj->dev), _IOC_NR(cmd));
+
+ switch (obj->type) {
+ case ADF_OBJ_OVERLAY_ENGINE:
+ ret = adf_overlay_engine_ioctl(adf_obj_to_overlay_engine(obj),
+ fpriv, cmd, arg);
+ break;
+
+ case ADF_OBJ_INTERFACE:
+ ret = adf_interface_ioctl(adf_obj_to_interface(obj), fpriv, cmd,
+ arg);
+ break;
+
+ case ADF_OBJ_DEVICE:
+ ret = adf_device_ioctl(adf_obj_to_device(obj), fpriv, cmd, arg);
+ break;
+ }
+
+ return ret;
+}
+
+static inline bool adf_file_event_available(struct adf_file *fpriv)
+{
+ int head = fpriv->event_head;
+ int tail = fpriv->event_tail;
+ return CIRC_CNT(head, tail, sizeof(fpriv->event_buf)) != 0;
+}
+
+void adf_file_queue_event(struct adf_file *fpriv, struct adf_event *event)
+{
+ int head = fpriv->event_head;
+ int tail = fpriv->event_tail;
+ size_t space = CIRC_SPACE(head, tail, sizeof(fpriv->event_buf));
+ size_t space_to_end =
+ CIRC_SPACE_TO_END(head, tail, sizeof(fpriv->event_buf));
+
+ if (space < event->length) {
+ dev_dbg(&fpriv->obj->dev,
+ "insufficient buffer space for event %u\n",
+ event->type);
+ return;
+ }
+
+ if (space_to_end >= event->length) {
+ memcpy(fpriv->event_buf + head, event, event->length);
+ } else {
+ memcpy(fpriv->event_buf + head, event, space_to_end);
+ memcpy(fpriv->event_buf, (u8 *)event + space_to_end,
+ event->length - space_to_end);
+ }
+
+ smp_wmb();
+ fpriv->event_head = (fpriv->event_head + event->length) &
+ (sizeof(fpriv->event_buf) - 1);
+ wake_up_interruptible_all(&fpriv->event_wait);
+}
+
+static ssize_t adf_file_copy_to_user(struct adf_file *fpriv,
+ char __user *buffer, size_t buffer_size)
+{
+ int head, tail;
+ u8 *event_buf;
+ size_t cnt, cnt_to_end, copy_size = 0;
+ ssize_t ret = 0;
+ unsigned long flags;
+
+ event_buf = kmalloc(min(buffer_size, sizeof(fpriv->event_buf)),
+ GFP_KERNEL);
+ if (!event_buf)
+ return -ENOMEM;
+
+ spin_lock_irqsave(&fpriv->obj->file_lock, flags);
+
+ if (!adf_file_event_available(fpriv))
+ goto out;
+
+ head = fpriv->event_head;
+ tail = fpriv->event_tail;
+
+ cnt = CIRC_CNT(head, tail, sizeof(fpriv->event_buf));
+ cnt_to_end = CIRC_CNT_TO_END(head, tail, sizeof(fpriv->event_buf));
+ copy_size = min(buffer_size, cnt);
+
+ if (cnt_to_end >= copy_size) {
+ memcpy(event_buf, fpriv->event_buf + tail, copy_size);
+ } else {
+ memcpy(event_buf, fpriv->event_buf + tail, cnt_to_end);
+ memcpy(event_buf + cnt_to_end, fpriv->event_buf,
+ copy_size - cnt_to_end);
+ }
+
+ fpriv->event_tail = (fpriv->event_tail + copy_size) &
+ (sizeof(fpriv->event_buf) - 1);
+
+out:
+ spin_unlock_irqrestore(&fpriv->obj->file_lock, flags);
+ if (copy_size) {
+ if (copy_to_user(buffer, event_buf, copy_size))
+ ret = -EFAULT;
+ else
+ ret = copy_size;
+ }
+ kfree(event_buf);
+ return ret;
+}
+
+ssize_t adf_file_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *offset)
+{
+ struct adf_file *fpriv = filp->private_data;
+ int err;
+
+ err = wait_event_interruptible(fpriv->event_wait,
+ adf_file_event_available(fpriv));
+ if (err < 0)
+ return err;
+
+ return adf_file_copy_to_user(fpriv, buffer, count);
+}
+
+unsigned int adf_file_poll(struct file *filp, struct poll_table_struct *wait)
+{
+ struct adf_file *fpriv = filp->private_data;
+ unsigned int mask = 0;
+
+ poll_wait(filp, &fpriv->event_wait, wait);
+
+ if (adf_file_event_available(fpriv))
+ mask |= POLLIN | POLLRDNORM;
+
+ return mask;
+}
+
+const struct file_operations adf_fops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = adf_file_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = adf_file_compat_ioctl,
+#endif
+ .open = adf_file_open,
+ .release = adf_file_release,
+ .llseek = default_llseek,
+ .read = adf_file_read,
+ .poll = adf_file_poll,
+};
diff --git a/drivers/video/adf/adf_fops.h b/drivers/video/adf/adf_fops.h
new file mode 100644
index 0000000..90a3a74
--- /dev/null
+++ b/drivers/video/adf/adf_fops.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_FOPS_H
+#define __VIDEO_ADF_ADF_FOPS_H
+
+#include <linux/bitmap.h>
+#include <linux/fs.h>
+
+extern const struct file_operations adf_fops;
+
+struct adf_file {
+ struct list_head head;
+ struct adf_obj *obj;
+
+ DECLARE_BITMAP(event_subscriptions, ADF_EVENT_TYPE_MAX);
+ u8 event_buf[4096];
+ int event_head;
+ int event_tail;
+ wait_queue_head_t event_wait;
+};
+
+void adf_file_queue_event(struct adf_file *file, struct adf_event *event);
+long adf_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+#endif /* __VIDEO_ADF_ADF_FOPS_H */
diff --git a/drivers/video/adf/adf_fops32.c b/drivers/video/adf/adf_fops32.c
new file mode 100644
index 0000000..d299a81
--- /dev/null
+++ b/drivers/video/adf/adf_fops32.c
@@ -0,0 +1,217 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/uaccess.h>
+#include <video/adf.h>
+
+#include "adf_fops.h"
+#include "adf_fops32.h"
+
+long adf_compat_post_config(struct file *file,
+ struct adf_post_config32 __user *arg)
+{
+ struct adf_post_config32 cfg32;
+ struct adf_post_config __user *cfg;
+ int ret;
+
+ if (copy_from_user(&cfg32, arg, sizeof(cfg32)))
+ return -EFAULT;
+
+ cfg = compat_alloc_user_space(sizeof(*cfg));
+ if (!access_ok(VERIFY_WRITE, cfg, sizeof(*cfg)))
+ return -EFAULT;
+
+ if (put_user(cfg32.n_interfaces, &cfg->n_interfaces) ||
+ put_user(compat_ptr(cfg32.interfaces),
+ &cfg->interfaces) ||
+ put_user(cfg32.n_bufs, &cfg->n_bufs) ||
+ put_user(compat_ptr(cfg32.bufs), &cfg->bufs) ||
+ put_user(cfg32.custom_data_size,
+ &cfg->custom_data_size) ||
+ put_user(compat_ptr(cfg32.custom_data),
+ &cfg->custom_data))
+ return -EFAULT;
+
+ ret = adf_file_ioctl(file, ADF_POST_CONFIG, (unsigned long)cfg);
+ if (ret < 0)
+ return ret;
+
+ if (copy_in_user(&arg->complete_fence, &cfg->complete_fence,
+ sizeof(cfg->complete_fence)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long adf_compat_get_device_data(struct file *file,
+ struct adf_device_data32 __user *arg)
+{
+ struct adf_device_data32 data32;
+ struct adf_device_data __user *data;
+ int ret;
+
+ if (copy_from_user(&data32, arg, sizeof(data32)))
+ return -EFAULT;
+
+ data = compat_alloc_user_space(sizeof(*data));
+ if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+ return -EFAULT;
+
+ if (put_user(data32.n_attachments, &data->n_attachments) ||
+ put_user(compat_ptr(data32.attachments),
+ &data->attachments) ||
+ put_user(data32.n_allowed_attachments,
+ &data->n_allowed_attachments) ||
+ put_user(compat_ptr(data32.allowed_attachments),
+ &data->allowed_attachments) ||
+ put_user(data32.custom_data_size,
+ &data->custom_data_size) ||
+ put_user(compat_ptr(data32.custom_data),
+ &data->custom_data))
+ return -EFAULT;
+
+ ret = adf_file_ioctl(file, ADF_GET_DEVICE_DATA, (unsigned long)data);
+ if (ret < 0)
+ return ret;
+
+ if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+ copy_in_user(&arg->n_attachments, &data->n_attachments,
+ sizeof(arg->n_attachments)) ||
+ copy_in_user(&arg->n_allowed_attachments,
+ &data->n_allowed_attachments,
+ sizeof(arg->n_allowed_attachments)) ||
+ copy_in_user(&arg->custom_data_size,
+ &data->custom_data_size,
+ sizeof(arg->custom_data_size)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long adf_compat_get_interface_data(struct file *file,
+ struct adf_interface_data32 __user *arg)
+{
+ struct adf_interface_data32 data32;
+ struct adf_interface_data __user *data;
+ int ret;
+
+ if (copy_from_user(&data32, arg, sizeof(data32)))
+ return -EFAULT;
+
+ data = compat_alloc_user_space(sizeof(*data));
+ if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+ return -EFAULT;
+
+ if (put_user(data32.n_available_modes, &data->n_available_modes) ||
+ put_user(compat_ptr(data32.available_modes),
+ &data->available_modes) ||
+ put_user(data32.custom_data_size,
+ &data->custom_data_size) ||
+ put_user(compat_ptr(data32.custom_data),
+ &data->custom_data))
+ return -EFAULT;
+
+ ret = adf_file_ioctl(file, ADF_GET_INTERFACE_DATA, (unsigned long)data);
+ if (ret < 0)
+ return ret;
+
+ if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+ copy_in_user(&arg->type, &data->type,
+ sizeof(arg->type)) ||
+ copy_in_user(&arg->id, &data->id, sizeof(arg->id)) ||
+ copy_in_user(&arg->flags, &data->flags,
+ sizeof(arg->flags)) ||
+ copy_in_user(&arg->dpms_state, &data->dpms_state,
+ sizeof(arg->dpms_state)) ||
+ copy_in_user(&arg->hotplug_detect,
+ &data->hotplug_detect,
+ sizeof(arg->hotplug_detect)) ||
+ copy_in_user(&arg->width_mm, &data->width_mm,
+ sizeof(arg->width_mm)) ||
+ copy_in_user(&arg->height_mm, &data->height_mm,
+ sizeof(arg->height_mm)) ||
+ copy_in_user(&arg->current_mode, &data->current_mode,
+ sizeof(arg->current_mode)) ||
+ copy_in_user(&arg->n_available_modes,
+ &data->n_available_modes,
+ sizeof(arg->n_available_modes)) ||
+ copy_in_user(&arg->custom_data_size,
+ &data->custom_data_size,
+ sizeof(arg->custom_data_size)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long adf_compat_get_overlay_engine_data(struct file *file,
+ struct adf_overlay_engine_data32 __user *arg)
+{
+ struct adf_overlay_engine_data32 data32;
+ struct adf_overlay_engine_data __user *data;
+ int ret;
+
+ if (copy_from_user(&data32, arg, sizeof(data32)))
+ return -EFAULT;
+
+ data = compat_alloc_user_space(sizeof(*data));
+ if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+ return -EFAULT;
+
+ if (put_user(data32.n_supported_formats, &data->n_supported_formats) ||
+ put_user(compat_ptr(data32.supported_formats),
+ &data->supported_formats) ||
+ put_user(data32.custom_data_size,
+ &data->custom_data_size) ||
+ put_user(compat_ptr(data32.custom_data),
+ &data->custom_data))
+ return -EFAULT;
+
+ ret = adf_file_ioctl(file, ADF_GET_OVERLAY_ENGINE_DATA,
+ (unsigned long)data);
+ if (ret < 0)
+ return ret;
+
+ if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+ copy_in_user(&arg->n_supported_formats,
+ &data->n_supported_formats,
+ sizeof(arg->n_supported_formats)) ||
+ copy_in_user(&arg->custom_data_size,
+ &data->custom_data_size,
+ sizeof(arg->custom_data_size)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long adf_file_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ switch (cmd) {
+ case ADF_POST_CONFIG32:
+ return adf_compat_post_config(file, compat_ptr(arg));
+
+ case ADF_GET_DEVICE_DATA32:
+ return adf_compat_get_device_data(file, compat_ptr(arg));
+
+ case ADF_GET_INTERFACE_DATA32:
+ return adf_compat_get_interface_data(file, compat_ptr(arg));
+
+ case ADF_GET_OVERLAY_ENGINE_DATA32:
+ return adf_compat_get_overlay_engine_data(file,
+ compat_ptr(arg));
+
+ default:
+ return adf_file_ioctl(file, cmd, arg);
+ }
+}
diff --git a/drivers/video/adf/adf_fops32.h b/drivers/video/adf/adf_fops32.h
new file mode 100644
index 0000000..64034ce
--- /dev/null
+++ b/drivers/video/adf/adf_fops32.h
@@ -0,0 +1,78 @@
+#ifndef __VIDEO_ADF_ADF_FOPS32_H
+#define __VIDEO_ADF_ADF_FOPS32_H
+
+#include <linux/compat.h>
+#include <linux/ioctl.h>
+
+#include <video/adf.h>
+
+#define ADF_POST_CONFIG32 \
+ _IOW(ADF_IOCTL_TYPE, 2, struct adf_post_config32)
+#define ADF_GET_DEVICE_DATA32 \
+ _IOR(ADF_IOCTL_TYPE, 4, struct adf_device_data32)
+#define ADF_GET_INTERFACE_DATA32 \
+ _IOR(ADF_IOCTL_TYPE, 5, struct adf_interface_data32)
+#define ADF_GET_OVERLAY_ENGINE_DATA32 \
+ _IOR(ADF_IOCTL_TYPE, 6, struct adf_overlay_engine_data32)
+
+struct adf_post_config32 {
+ compat_size_t n_interfaces;
+ compat_uptr_t interfaces;
+
+ compat_size_t n_bufs;
+ compat_uptr_t bufs;
+
+ compat_size_t custom_data_size;
+ compat_uptr_t custom_data;
+
+ __s32 complete_fence;
+};
+
+struct adf_device_data32 {
+ char name[ADF_NAME_LEN];
+
+ compat_size_t n_attachments;
+ compat_uptr_t attachments;
+
+ compat_size_t n_allowed_attachments;
+ compat_uptr_t allowed_attachments;
+
+ compat_size_t custom_data_size;
+ compat_uptr_t custom_data;
+};
+
+struct adf_interface_data32 {
+ char name[ADF_NAME_LEN];
+
+ __u8 type;
+ __u32 id;
+ /* e.g. type=ADF_INTF_TYPE_DSI, id=1 => DSI.1 */
+ __u32 flags;
+
+ __u8 dpms_state;
+ __u8 hotplug_detect;
+ __u16 width_mm;
+ __u16 height_mm;
+
+ struct drm_mode_modeinfo current_mode;
+ compat_size_t n_available_modes;
+ compat_uptr_t available_modes;
+
+ compat_size_t custom_data_size;
+ compat_uptr_t custom_data;
+};
+
+struct adf_overlay_engine_data32 {
+ char name[ADF_NAME_LEN];
+
+ compat_size_t n_supported_formats;
+ compat_uptr_t supported_formats;
+
+ compat_size_t custom_data_size;
+ compat_uptr_t custom_data;
+};
+
+long adf_file_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg);
+
+#endif /* __VIDEO_ADF_ADF_FOPS32_H */
diff --git a/drivers/video/adf/adf_format.c b/drivers/video/adf/adf_format.c
new file mode 100644
index 0000000..e3f22c7
--- /dev/null
+++ b/drivers/video/adf/adf_format.c
@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ * modified from drivers/gpu/drm/drm_crtc.c
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <drm/drm_fourcc.h>
+#include <video/adf_format.h>
+
+bool adf_format_is_standard(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_C8:
+ case DRM_FORMAT_RGB332:
+ case DRM_FORMAT_BGR233:
+ case DRM_FORMAT_XRGB4444:
+ case DRM_FORMAT_XBGR4444:
+ case DRM_FORMAT_RGBX4444:
+ case DRM_FORMAT_BGRX4444:
+ case DRM_FORMAT_ARGB4444:
+ case DRM_FORMAT_ABGR4444:
+ case DRM_FORMAT_RGBA4444:
+ case DRM_FORMAT_BGRA4444:
+ case DRM_FORMAT_XRGB1555:
+ case DRM_FORMAT_XBGR1555:
+ case DRM_FORMAT_RGBX5551:
+ case DRM_FORMAT_BGRX5551:
+ case DRM_FORMAT_ARGB1555:
+ case DRM_FORMAT_ABGR1555:
+ case DRM_FORMAT_RGBA5551:
+ case DRM_FORMAT_BGRA5551:
+ case DRM_FORMAT_RGB565:
+ case DRM_FORMAT_BGR565:
+ case DRM_FORMAT_RGB888:
+ case DRM_FORMAT_BGR888:
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_XBGR8888:
+ case DRM_FORMAT_RGBX8888:
+ case DRM_FORMAT_BGRX8888:
+ case DRM_FORMAT_ARGB8888:
+ case DRM_FORMAT_ABGR8888:
+ case DRM_FORMAT_RGBA8888:
+ case DRM_FORMAT_BGRA8888:
+ case DRM_FORMAT_XRGB2101010:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_RGBX1010102:
+ case DRM_FORMAT_BGRX1010102:
+ case DRM_FORMAT_ARGB2101010:
+ case DRM_FORMAT_ABGR2101010:
+ case DRM_FORMAT_RGBA1010102:
+ case DRM_FORMAT_BGRA1010102:
+ case DRM_FORMAT_YUYV:
+ case DRM_FORMAT_YVYU:
+ case DRM_FORMAT_UYVY:
+ case DRM_FORMAT_VYUY:
+ case DRM_FORMAT_AYUV:
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV61:
+ case DRM_FORMAT_YUV410:
+ case DRM_FORMAT_YVU410:
+ case DRM_FORMAT_YUV411:
+ case DRM_FORMAT_YVU411:
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_YUV422:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YUV444:
+ case DRM_FORMAT_YVU444:
+ return true;
+ default:
+ return false;
+ }
+}
+EXPORT_SYMBOL(adf_format_is_standard);
+
+bool adf_format_is_rgb(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_C8:
+ case DRM_FORMAT_RGB332:
+ case DRM_FORMAT_BGR233:
+ case DRM_FORMAT_XRGB1555:
+ case DRM_FORMAT_XBGR1555:
+ case DRM_FORMAT_RGBX5551:
+ case DRM_FORMAT_BGRX5551:
+ case DRM_FORMAT_ARGB1555:
+ case DRM_FORMAT_ABGR1555:
+ case DRM_FORMAT_RGBA5551:
+ case DRM_FORMAT_BGRA5551:
+ case DRM_FORMAT_RGB565:
+ case DRM_FORMAT_BGR565:
+ case DRM_FORMAT_RGB888:
+ case DRM_FORMAT_BGR888:
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_XBGR8888:
+ case DRM_FORMAT_RGBX8888:
+ case DRM_FORMAT_BGRX8888:
+ case DRM_FORMAT_XRGB2101010:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_RGBX1010102:
+ case DRM_FORMAT_BGRX1010102:
+ case DRM_FORMAT_ARGB2101010:
+ case DRM_FORMAT_ABGR2101010:
+ case DRM_FORMAT_RGBA1010102:
+ case DRM_FORMAT_BGRA1010102:
+ case DRM_FORMAT_ARGB8888:
+ case DRM_FORMAT_ABGR8888:
+ case DRM_FORMAT_RGBA8888:
+ case DRM_FORMAT_BGRA8888:
+ return true;
+
+ default:
+ return false;
+ }
+}
+EXPORT_SYMBOL(adf_format_is_rgb);
+
+u8 adf_format_num_planes(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_YUV410:
+ case DRM_FORMAT_YVU410:
+ case DRM_FORMAT_YUV411:
+ case DRM_FORMAT_YVU411:
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_YUV422:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YUV444:
+ case DRM_FORMAT_YVU444:
+ return 3;
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV61:
+ return 2;
+ default:
+ return 1;
+ }
+}
+EXPORT_SYMBOL(adf_format_num_planes);
+
+u8 adf_format_bpp(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_C8:
+ case DRM_FORMAT_RGB332:
+ case DRM_FORMAT_BGR233:
+ return 8;
+
+ case DRM_FORMAT_XRGB1555:
+ case DRM_FORMAT_XBGR1555:
+ case DRM_FORMAT_RGBX5551:
+ case DRM_FORMAT_BGRX5551:
+ case DRM_FORMAT_ARGB1555:
+ case DRM_FORMAT_ABGR1555:
+ case DRM_FORMAT_RGBA5551:
+ case DRM_FORMAT_BGRA5551:
+ case DRM_FORMAT_RGB565:
+ case DRM_FORMAT_BGR565:
+ return 16;
+
+ case DRM_FORMAT_RGB888:
+ case DRM_FORMAT_BGR888:
+ return 24;
+
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_XBGR8888:
+ case DRM_FORMAT_RGBX8888:
+ case DRM_FORMAT_BGRX8888:
+ case DRM_FORMAT_XRGB2101010:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_RGBX1010102:
+ case DRM_FORMAT_BGRX1010102:
+ case DRM_FORMAT_ARGB2101010:
+ case DRM_FORMAT_ABGR2101010:
+ case DRM_FORMAT_RGBA1010102:
+ case DRM_FORMAT_BGRA1010102:
+ case DRM_FORMAT_ARGB8888:
+ case DRM_FORMAT_ABGR8888:
+ case DRM_FORMAT_RGBA8888:
+ case DRM_FORMAT_BGRA8888:
+ return 32;
+
+ default:
+ pr_debug("%s: unsupported pixel format %u\n", __func__, format);
+ return 0;
+ }
+}
+EXPORT_SYMBOL(adf_format_bpp);
+
+u8 adf_format_plane_cpp(u32 format, int plane)
+{
+ if (plane >= adf_format_num_planes(format))
+ return 0;
+
+ switch (format) {
+ case DRM_FORMAT_YUYV:
+ case DRM_FORMAT_YVYU:
+ case DRM_FORMAT_UYVY:
+ case DRM_FORMAT_VYUY:
+ return 2;
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV61:
+ return plane ? 2 : 1;
+ case DRM_FORMAT_YUV410:
+ case DRM_FORMAT_YVU410:
+ case DRM_FORMAT_YUV411:
+ case DRM_FORMAT_YVU411:
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_YUV422:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YUV444:
+ case DRM_FORMAT_YVU444:
+ return 1;
+ default:
+ return adf_format_bpp(format) / 8;
+ }
+}
+EXPORT_SYMBOL(adf_format_plane_cpp);
+
+u8 adf_format_horz_chroma_subsampling(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_YUV411:
+ case DRM_FORMAT_YVU411:
+ case DRM_FORMAT_YUV410:
+ case DRM_FORMAT_YVU410:
+ return 4;
+ case DRM_FORMAT_YUYV:
+ case DRM_FORMAT_YVYU:
+ case DRM_FORMAT_UYVY:
+ case DRM_FORMAT_VYUY:
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV61:
+ case DRM_FORMAT_YUV422:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YVU420:
+ return 2;
+ default:
+ return 1;
+ }
+}
+EXPORT_SYMBOL(adf_format_horz_chroma_subsampling);
+
+u8 adf_format_vert_chroma_subsampling(u32 format)
+{
+ switch (format) {
+ case DRM_FORMAT_YUV410:
+ case DRM_FORMAT_YVU410:
+ return 4;
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ return 2;
+ default:
+ return 1;
+ }
+}
+EXPORT_SYMBOL(adf_format_vert_chroma_subsampling);
diff --git a/drivers/video/adf/adf_memblock.c b/drivers/video/adf/adf_memblock.c
new file mode 100644
index 0000000..e73a7d5
--- /dev/null
+++ b/drivers/video/adf/adf_memblock.c
@@ -0,0 +1,160 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+struct adf_memblock_pdata {
+ phys_addr_t base;
+};
+
+static struct sg_table *adf_memblock_map(struct dma_buf_attachment *attach,
+ enum dma_data_direction direction)
+{
+ struct adf_memblock_pdata *pdata = attach->dmabuf->priv;
+ unsigned long pfn = PFN_DOWN(pdata->base);
+ struct page *page = pfn_to_page(pfn);
+ struct sg_table *table;
+ int nents, ret;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return ERR_PTR(-ENOMEM);
+
+ ret = sg_alloc_table(table, 1, GFP_KERNEL);
+ if (ret < 0)
+ goto err_alloc;
+
+ sg_set_page(table->sgl, page, attach->dmabuf->size, 0);
+
+ nents = dma_map_sg(attach->dev, table->sgl, 1, direction);
+ if (!nents) {
+ ret = -EINVAL;
+ goto err_map;
+ }
+
+ return table;
+
+err_map:
+ sg_free_table(table);
+err_alloc:
+ kfree(table);
+ return ERR_PTR(ret);
+}
+
+static void adf_memblock_unmap(struct dma_buf_attachment *attach,
+ struct sg_table *table, enum dma_data_direction direction)
+{
+ dma_unmap_sg(attach->dev, table->sgl, 1, direction);
+ sg_free_table(table);
+}
+
+static void __init_memblock adf_memblock_release(struct dma_buf *buf)
+{
+ struct adf_memblock_pdata *pdata = buf->priv;
+ int err = memblock_free(pdata->base, buf->size);
+
+ if (err < 0)
+ pr_warn("%s: freeing memblock failed: %d\n", __func__, err);
+ kfree(pdata);
+}
+
+static void *adf_memblock_do_kmap(struct dma_buf *buf, unsigned long pgoffset,
+ bool atomic)
+{
+ struct adf_memblock_pdata *pdata = buf->priv;
+ unsigned long pfn = PFN_DOWN(pdata->base) + pgoffset;
+ struct page *page = pfn_to_page(pfn);
+
+ if (atomic)
+ return kmap_atomic(page);
+ else
+ return kmap(page);
+}
+
+static void *adf_memblock_kmap_atomic(struct dma_buf *buf,
+ unsigned long pgoffset)
+{
+ return adf_memblock_do_kmap(buf, pgoffset, true);
+}
+
+static void adf_memblock_kunmap_atomic(struct dma_buf *buf,
+ unsigned long pgoffset, void *vaddr)
+{
+ kunmap_atomic(vaddr);
+}
+
+static void *adf_memblock_kmap(struct dma_buf *buf, unsigned long pgoffset)
+{
+ return adf_memblock_do_kmap(buf, pgoffset, false);
+}
+
+static void adf_memblock_kunmap(struct dma_buf *buf, unsigned long pgoffset,
+ void *vaddr)
+{
+ kunmap(vaddr);
+}
+
+static int adf_memblock_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
+{
+ struct adf_memblock_pdata *pdata = buf->priv;
+
+ return remap_pfn_range(vma, vma->vm_start, PFN_DOWN(pdata->base),
+ vma->vm_end - vma->vm_start, vma->vm_page_prot);
+}
+
+struct dma_buf_ops adf_memblock_ops = {
+ .map_dma_buf = adf_memblock_map,
+ .unmap_dma_buf = adf_memblock_unmap,
+ .release = adf_memblock_release,
+ .kmap_atomic = adf_memblock_kmap_atomic,
+ .kunmap_atomic = adf_memblock_kunmap_atomic,
+ .kmap = adf_memblock_kmap,
+ .kunmap = adf_memblock_kunmap,
+ .mmap = adf_memblock_mmap,
+};
+
+/**
+ * adf_memblock_export - export a memblock reserved area as a dma-buf
+ *
+ * @base: base physical address
+ * @size: memblock size
+ * @flags: mode flags for the dma-buf's file
+ *
+ * @base and @size must be page-aligned.
+ *
+ * Returns a dma-buf on success or ERR_PTR(-errno) on failure.
+ */
+struct dma_buf *adf_memblock_export(phys_addr_t base, size_t size, int flags)
+{
+ struct adf_memblock_pdata *pdata;
+ struct dma_buf *buf;
+
+ if (PAGE_ALIGN(base) != base || PAGE_ALIGN(size) != size)
+ return ERR_PTR(-EINVAL);
+
+ pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ return ERR_PTR(-ENOMEM);
+
+ pdata->base = base;
+ buf = dma_buf_export(pdata, &adf_memblock_ops, size, flags);
+ if (IS_ERR(buf))
+ kfree(pdata);
+
+ return buf;
+}
+EXPORT_SYMBOL(adf_memblock_export);
diff --git a/drivers/video/adf/adf_sysfs.c b/drivers/video/adf/adf_sysfs.c
new file mode 100644
index 0000000..8c659c7
--- /dev/null
+++ b/drivers/video/adf/adf_sysfs.c
@@ -0,0 +1,296 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <video/adf_client.h>
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+static struct class *adf_class;
+static int adf_major;
+static DEFINE_IDR(adf_minors);
+
+#define dev_to_adf_interface(p) \
+ adf_obj_to_interface(container_of(p, struct adf_obj, dev))
+
+static ssize_t dpms_state_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ return scnprintf(buf, PAGE_SIZE, "%u\n",
+ adf_interface_dpms_state(intf));
+}
+
+static ssize_t dpms_state_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ u8 dpms_state;
+ int err;
+
+ err = kstrtou8(buf, 0, &dpms_state);
+ if (err < 0)
+ return err;
+
+ err = adf_interface_blank(intf, dpms_state);
+ if (err < 0)
+ return err;
+
+ return count;
+}
+
+static ssize_t current_mode_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ struct drm_mode_modeinfo mode;
+
+ adf_interface_current_mode(intf, &mode);
+
+ if (mode.name[0]) {
+ return scnprintf(buf, PAGE_SIZE, "%s\n", mode.name);
+ } else {
+ bool interlaced = !!(mode.flags & DRM_MODE_FLAG_INTERLACE);
+ return scnprintf(buf, PAGE_SIZE, "%ux%u%s\n", mode.hdisplay,
+ mode.vdisplay, interlaced ? "i" : "");
+ }
+}
+
+static ssize_t type_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ return scnprintf(buf, PAGE_SIZE, "%s\n",
+ adf_interface_type_str(intf));
+}
+
+static ssize_t vsync_timestamp_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ ktime_t timestamp;
+ unsigned long flags;
+
+ read_lock_irqsave(&intf->vsync_lock, flags);
+ memcpy(×tamp, &intf->vsync_timestamp, sizeof(timestamp));
+ read_unlock_irqrestore(&intf->vsync_lock, flags);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", ktime_to_ns(timestamp));
+}
+
+static ssize_t hotplug_detect_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct adf_interface *intf = dev_to_adf_interface(dev);
+ return scnprintf(buf, PAGE_SIZE, "%u\n", intf->hotplug_detect);
+}
+
+static struct device_attribute adf_interface_attrs[] = {
+ __ATTR(dpms_state, S_IRUGO|S_IWUSR, dpms_state_show, dpms_state_store),
+ __ATTR_RO(current_mode),
+ __ATTR_RO(hotplug_detect),
+ __ATTR_RO(type),
+ __ATTR_RO(vsync_timestamp),
+};
+
+int adf_obj_sysfs_init(struct adf_obj *obj, struct device *parent)
+{
+ int ret = idr_alloc(&adf_minors, obj, 0, 0, GFP_KERNEL);
+ if (ret < 0) {
+ pr_err("%s: allocating adf minor failed: %d\n", __func__,
+ ret);
+ return ret;
+ }
+
+ obj->minor = ret;
+ obj->dev.parent = parent;
+ obj->dev.class = adf_class;
+ obj->dev.devt = MKDEV(adf_major, obj->minor);
+
+ ret = device_register(&obj->dev);
+ if (ret < 0) {
+ pr_err("%s: registering adf object failed: %d\n", __func__,
+ ret);
+ goto err_device_register;
+ }
+
+ return 0;
+
+err_device_register:
+ idr_remove(&adf_minors, obj->minor);
+ return ret;
+}
+
+static char *adf_device_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+ return kasprintf(GFP_KERNEL, "adf%d", obj->id);
+}
+
+static char *adf_interface_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+ struct adf_interface *intf = adf_obj_to_interface(obj);
+ struct adf_device *parent = adf_interface_parent(intf);
+ return kasprintf(GFP_KERNEL, "adf-interface%d.%d",
+ parent->base.id, intf->base.id);
+}
+
+static char *adf_overlay_engine_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+ struct adf_overlay_engine *eng = adf_obj_to_overlay_engine(obj);
+ struct adf_device *parent = adf_overlay_engine_parent(eng);
+ return kasprintf(GFP_KERNEL, "adf-overlay-engine%d.%d",
+ parent->base.id, eng->base.id);
+}
+
+static void adf_noop_release(struct device *dev)
+{
+}
+
+static struct device_type adf_device_type = {
+ .name = "adf_device",
+ .devnode = adf_device_devnode,
+ .release = adf_noop_release,
+};
+
+static struct device_type adf_interface_type = {
+ .name = "adf_interface",
+ .devnode = adf_interface_devnode,
+ .release = adf_noop_release,
+};
+
+static struct device_type adf_overlay_engine_type = {
+ .name = "adf_overlay_engine",
+ .devnode = adf_overlay_engine_devnode,
+ .release = adf_noop_release,
+};
+
+int adf_device_sysfs_init(struct adf_device *dev)
+{
+ dev->base.dev.type = &adf_device_type;
+ dev_set_name(&dev->base.dev, "%s", dev->base.name);
+ return adf_obj_sysfs_init(&dev->base, dev->dev);
+}
+
+int adf_interface_sysfs_init(struct adf_interface *intf)
+{
+ struct adf_device *parent = adf_interface_parent(intf);
+ size_t i, j;
+ int ret;
+
+ intf->base.dev.type = &adf_interface_type;
+ dev_set_name(&intf->base.dev, "%s-interface%d", parent->base.name,
+ intf->base.id);
+
+ ret = adf_obj_sysfs_init(&intf->base, &parent->base.dev);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < ARRAY_SIZE(adf_interface_attrs); i++) {
+ ret = device_create_file(&intf->base.dev,
+ &adf_interface_attrs[i]);
+ if (ret < 0) {
+ dev_err(&intf->base.dev, "creating sysfs attribute %s failed: %d\n",
+ adf_interface_attrs[i].attr.name, ret);
+ goto err;
+ }
+ }
+
+ return 0;
+
+err:
+ for (j = 0; j < i; j++)
+ device_remove_file(&intf->base.dev, &adf_interface_attrs[j]);
+ return ret;
+}
+
+int adf_overlay_engine_sysfs_init(struct adf_overlay_engine *eng)
+{
+ struct adf_device *parent = adf_overlay_engine_parent(eng);
+
+ eng->base.dev.type = &adf_overlay_engine_type;
+ dev_set_name(&eng->base.dev, "%s-overlay-engine%d", parent->base.name,
+ eng->base.id);
+
+ return adf_obj_sysfs_init(&eng->base, &parent->base.dev);
+}
+
+struct adf_obj *adf_obj_sysfs_find(int minor)
+{
+ return idr_find(&adf_minors, minor);
+}
+
+void adf_obj_sysfs_destroy(struct adf_obj *obj)
+{
+ idr_remove(&adf_minors, obj->minor);
+ device_unregister(&obj->dev);
+}
+
+void adf_device_sysfs_destroy(struct adf_device *dev)
+{
+ adf_obj_sysfs_destroy(&dev->base);
+}
+
+void adf_interface_sysfs_destroy(struct adf_interface *intf)
+{
+ size_t i;
+
+ for (i = 0; i < ARRAY_SIZE(adf_interface_attrs); i++)
+ device_remove_file(&intf->base.dev, &adf_interface_attrs[i]);
+ adf_obj_sysfs_destroy(&intf->base);
+}
+
+void adf_overlay_engine_sysfs_destroy(struct adf_overlay_engine *eng)
+{
+ adf_obj_sysfs_destroy(&eng->base);
+}
+
+int adf_sysfs_init(void)
+{
+ struct class *class;
+ int ret;
+
+ class = class_create(THIS_MODULE, "adf");
+ if (IS_ERR(class)) {
+ ret = PTR_ERR(class);
+ pr_err("%s: creating class failed: %d\n", __func__, ret);
+ return ret;
+ }
+
+ ret = register_chrdev(0, "adf", &adf_fops);
+ if (ret < 0) {
+ pr_err("%s: registering device failed: %d\n", __func__, ret);
+ goto err_chrdev;
+ }
+
+ adf_class = class;
+ adf_major = ret;
+ return 0;
+
+err_chrdev:
+ class_destroy(adf_class);
+ return ret;
+}
+
+void adf_sysfs_destroy(void)
+{
+ idr_destroy(&adf_minors);
+ class_destroy(adf_class);
+}
diff --git a/drivers/video/adf/adf_sysfs.h b/drivers/video/adf/adf_sysfs.h
new file mode 100644
index 0000000..0613ac3
--- /dev/null
+++ b/drivers/video/adf/adf_sysfs.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_SYSFS_H
+#define __VIDEO_ADF_ADF_SYSFS_H
+
+struct adf_device;
+struct adf_interface;
+struct adf_overlay_engine;
+
+int adf_device_sysfs_init(struct adf_device *dev);
+void adf_device_sysfs_destroy(struct adf_device *dev);
+int adf_interface_sysfs_init(struct adf_interface *intf);
+void adf_interface_sysfs_destroy(struct adf_interface *intf);
+int adf_overlay_engine_sysfs_init(struct adf_overlay_engine *eng);
+void adf_overlay_engine_sysfs_destroy(struct adf_overlay_engine *eng);
+struct adf_obj *adf_obj_sysfs_find(int minor);
+
+int adf_sysfs_init(void);
+void adf_sysfs_destroy(void);
+
+#endif /* __VIDEO_ADF_ADF_SYSFS_H */
diff --git a/drivers/video/adf/adf_trace.h b/drivers/video/adf/adf_trace.h
new file mode 100644
index 0000000..3cb2a84
--- /dev/null
+++ b/drivers/video/adf/adf_trace.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM adf
+
+#if !defined(__VIDEO_ADF_ADF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VIDEO_ADF_ADF_TRACE_H
+
+#include <linux/tracepoint.h>
+#include <video/adf.h>
+
+TRACE_EVENT(adf_event,
+ TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+ TP_ARGS(obj, type),
+
+ TP_STRUCT__entry(
+ __string(name, obj->name)
+ __field(enum adf_event_type, type)
+ __array(char, type_str, 32)
+ ),
+ TP_fast_assign(
+ __assign_str(name, obj->name);
+ __entry->type = type;
+ strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+ sizeof(__entry->type_str));
+ ),
+ TP_printk("obj=%s type=%u (%s)",
+ __get_str(name),
+ __entry->type,
+ __entry->type_str)
+);
+
+TRACE_EVENT(adf_event_enable,
+ TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+ TP_ARGS(obj, type),
+
+ TP_STRUCT__entry(
+ __string(name, obj->name)
+ __field(enum adf_event_type, type)
+ __array(char, type_str, 32)
+ ),
+ TP_fast_assign(
+ __assign_str(name, obj->name);
+ __entry->type = type;
+ strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+ sizeof(__entry->type_str));
+ ),
+ TP_printk("obj=%s type=%u (%s)",
+ __get_str(name),
+ __entry->type,
+ __entry->type_str)
+);
+
+TRACE_EVENT(adf_event_disable,
+ TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+ TP_ARGS(obj, type),
+
+ TP_STRUCT__entry(
+ __string(name, obj->name)
+ __field(enum adf_event_type, type)
+ __array(char, type_str, 32)
+ ),
+ TP_fast_assign(
+ __assign_str(name, obj->name);
+ __entry->type = type;
+ strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+ sizeof(__entry->type_str));
+ ),
+ TP_printk("obj=%s type=%u (%s)",
+ __get_str(name),
+ __entry->type,
+ __entry->type_str)
+);
+
+#endif /* __VIDEO_ADF_ADF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE adf_trace
+#include <trace/define_trace.h>
diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c
index e033491..ab29939 100644
--- a/drivers/w1/masters/ds2482.c
+++ b/drivers/w1/masters/ds2482.c
@@ -18,6 +18,8 @@
#include <linux/slab.h>
#include <linux/i2c.h>
#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/platform_data/ds2482.h>
#include <asm/delay.h>
#include "../w1.h"
@@ -84,7 +86,8 @@
static int ds2482_probe(struct i2c_client *client,
const struct i2c_device_id *id);
static int ds2482_remove(struct i2c_client *client);
-
+static int ds2482_suspend(struct device *dev);
+static int ds2482_resume(struct device *dev);
/**
* Driver data (common to all clients)
@@ -94,10 +97,16 @@
{ }
};
+static const struct dev_pm_ops ds2482_pm_ops = {
+ .suspend = ds2482_suspend,
+ .resume = ds2482_resume,
+};
+
static struct i2c_driver ds2482_driver = {
.driver = {
.owner = THIS_MODULE,
.name = "ds2482",
+ .pm = &ds2482_pm_ops,
},
.probe = ds2482_probe,
.remove = ds2482_remove,
@@ -119,6 +128,7 @@
struct ds2482_data {
struct i2c_client *client;
struct mutex access_lock;
+ int slpz_gpio;
/* 1-wire interface(s) */
int w1_count; /* 1 or 8 */
@@ -444,11 +454,31 @@
return retval;
}
+static int ds2482_suspend(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct ds2482_data *data = i2c_get_clientdata(client);
+
+ if (data->slpz_gpio >= 0)
+ gpio_set_value(data->slpz_gpio, 0);
+ return 0;
+}
+
+static int ds2482_resume(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct ds2482_data *data = i2c_get_clientdata(client);
+
+ if (data->slpz_gpio >= 0)
+ gpio_set_value(data->slpz_gpio, 1);
+ return 0;
+}
static int ds2482_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
struct ds2482_data *data;
+ struct ds2482_platform_data *pdata;
int err = -ENODEV;
int temp1;
int idx;
@@ -515,6 +545,16 @@
}
}
+ pdata = client->dev.platform_data;
+ data->slpz_gpio = pdata ? pdata->slpz_gpio : -1;
+
+ if (data->slpz_gpio >= 0) {
+ err = gpio_request_one(data->slpz_gpio, GPIOF_OUT_INIT_HIGH,
+ "ds2482.slpz");
+ if (err < 0)
+ goto exit_w1_remove;
+ }
+
return 0;
exit_w1_remove:
@@ -539,6 +579,11 @@
w1_remove_master_device(&data->w1_ch[idx].w1_bm);
}
+ if (data->slpz_gpio >= 0) {
+ gpio_set_value(data->slpz_gpio, 0);
+ gpio_free(data->slpz_gpio);
+ }
+
/* Free the memory */
kfree(data);
return 0;
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 055562c..9ff073f 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -148,13 +148,14 @@
* @offset: offset in the page
*/
-static void v9fs_invalidate_page(struct page *page, unsigned long offset)
+static void v9fs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
/*
* If called with zero offset, we should release
* the private state assocated with the page
*/
- if (offset == 0)
+ if (offset == 0 && length == PAGE_CACHE_SIZE)
v9fs_fscache_invalidate_page(page);
}
diff --git a/fs/Kconfig b/fs/Kconfig
index c229f82..7d46f87 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -188,6 +188,7 @@
source "fs/adfs/Kconfig"
source "fs/affs/Kconfig"
source "fs/ecryptfs/Kconfig"
+source "fs/sdcardfs/Kconfig"
source "fs/hfs/Kconfig"
source "fs/hfsplus/Kconfig"
source "fs/befs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 4fe6df3..77c70106 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -3,7 +3,7 @@
#
# 14 Sep 2000, Christoph Hellwig <hch@infradead.org>
# Rewritten to use lists instead of if-statements.
-#
+#
obj-y := open.o read_write.o file_table.o super.o \
char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
@@ -59,7 +59,7 @@
obj-$(CONFIG_PROFILING) += dcookies.o
obj-$(CONFIG_DLM) += dlm/
-
+
# Do not add any filesystems before this line
obj-$(CONFIG_FSCACHE) += fscache/
obj-$(CONFIG_REISERFS_FS) += reiserfs/
@@ -82,6 +82,7 @@
obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+
obj-$(CONFIG_HFS_FS) += hfs/
obj-$(CONFIG_ECRYPT_FS) += ecryptfs/
+obj-$(CONFIG_SDCARD_FS) += sdcardfs/
obj-$(CONFIG_VXFS_FS) += freevxfs/
obj-$(CONFIG_NFS_FS) += nfs/
obj-$(CONFIG_EXPORTFS) += exportfs/
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 0ff4bae..479ef5a 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -213,6 +213,7 @@
static int adfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_NODIRATIME;
return parse_options(sb, data);
}
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 45161a8..01c6e07 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -549,6 +549,7 @@
pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data);
+ sync_filesystem(sb);
*flags |= MS_NODIRATIME;
memcpy(volume, sbi->s_volume, 32);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 8f6e923..66d50fe 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -19,7 +19,8 @@
#include "internal.h"
static int afs_readpage(struct file *file, struct page *page);
-static void afs_invalidatepage(struct page *page, unsigned long offset);
+static void afs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);
static int afs_launder_page(struct page *page);
@@ -310,16 +311,17 @@
* - release a page and clean up its private data if offset is 0 (indicating
* the entire page)
*/
-static void afs_invalidatepage(struct page *page, unsigned long offset)
+static void afs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
- _enter("{%lu},%lu", page->index, offset);
+ _enter("{%lu},%u,%u", page->index, offset, length);
BUG_ON(!PageLocked(page));
/* we clean up only if the entire page is being invalidated */
- if (offset == 0) {
+ if (offset == 0 && length == PAGE_CACHE_SIZE) {
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index f95dddc..7192a7e 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -908,6 +908,7 @@
static int
befs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
if (!(*flags & MS_RDONLY))
return -EINVAL;
return 0;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9612a01..e1b2084 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1013,7 +1013,8 @@
return try_release_extent_buffer(page);
}
-static void btree_invalidatepage(struct page *page, unsigned long offset)
+static void btree_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct extent_io_tree *tree;
tree = &BTRFS_I(page->mapping->host)->io_tree;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index be7e31a..70c2369 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2960,7 +2960,7 @@
pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index ||
(page->index == end_index && !pg_offset)) {
- page->mapping->a_ops->invalidatepage(page, 0);
+ page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
unlock_page(page);
return 0;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b5d13c4..5907f66 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7543,7 +7543,8 @@
return __btrfs_releasepage(page, gfp_flags & GFP_NOFS);
}
-static void btrfs_invalidatepage(struct page *page, unsigned long offset)
+static void btrfs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
struct extent_io_tree *tree;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 68891ff..feecdfb 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1248,6 +1248,7 @@
unsigned int old_metadata_ratio = fs_info->metadata_ratio;
int ret;
+ sync_filesystem(sb);
btrfs_remount_prepare(fs_info);
ret = btrfs_parse_options(root, data);
diff --git a/fs/buffer.c b/fs/buffer.c
index 83fedaa..d761211 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1458,7 +1458,8 @@
* block_invalidatepage - invalidate part or all of a buffer-backed page
*
* @page: the page which is affected
- * @offset: the index of the truncation point
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
*
* block_invalidatepage() is called when all or part of the page has become
* invalidated by a truncate operation.
@@ -1469,15 +1470,22 @@
* point. Because the caller is about to free (and possibly reuse) those
* blocks on-disk.
*/
-void block_invalidatepage(struct page *page, unsigned long offset)
+void block_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct buffer_head *head, *bh, *next;
unsigned int curr_off = 0;
+ unsigned int stop = length + offset;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
goto out;
+ /*
+ * Check for overflow
+ */
+ BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+
head = page_buffers(page);
bh = head;
do {
@@ -1485,6 +1493,12 @@
next = bh->b_this_page;
/*
+ * Are we still fully in range ?
+ */
+ if (next_off > stop)
+ goto out;
+
+ /*
* is this block fully invalidated?
*/
if (offset <= curr_off)
@@ -1505,6 +1519,7 @@
}
EXPORT_SYMBOL(block_invalidatepage);
+
/*
* We attach and possibly dirty the buffers atomically wrt
* __set_page_dirty_buffers() via private_lock. try_to_free_buffers
@@ -2853,7 +2868,7 @@
* they may have been added in ext3_writepage(). Make them
* freeable here, so the page does not leak.
*/
- do_invalidatepage(page, 0);
+ do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
unlock_page(page);
return 0; /* don't care */
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 5da06f0..1070554 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -143,7 +143,8 @@
* dirty page counters appropriately. Only called if there is private
* data on the page.
*/
-static void ceph_invalidatepage(struct page *page, unsigned long offset)
+static void ceph_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode;
struct ceph_inode_info *ci;
@@ -168,7 +169,7 @@
ci = ceph_inode(inode);
if (offset == 0) {
- dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
+ dout("%p invalidatepage %p idx %lu full dirty page %u\n",
inode, page, page->index, offset);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 3752b9f..0d7daf7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -521,6 +521,7 @@
static int cifs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_NODIRATIME;
return 0;
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index f4a8577..4e7cc89 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3577,11 +3577,12 @@
return cifs_fscache_release_page(page, gfp);
}
-static void cifs_invalidate_page(struct page *page, unsigned long offset)
+static void cifs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host);
- if (offset == 0)
+ if (offset == 0 && length == PAGE_CACHE_SIZE)
cifs_fscache_invalidate_page(page, &cifsi->vfs_inode);
}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index bfbf470..b70aa7c 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -447,7 +447,7 @@
{
int error;
- error = wait_event_freezekillable(server->response_q,
+ error = wait_event_freezekillable_unsafe(server->response_q,
midQ->mid_state != MID_REQUEST_SUBMITTED);
if (error < 0)
return -ERESTARTSYS;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index b7d3a05..fc66861 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -391,8 +391,7 @@
if (!host_file->f_op)
return -ENOTDIR;
- if (host_file->f_op->readdir)
- {
+ if (host_file->f_op->readdir) {
/* potemkin case: we were handed a directory inode.
* We can't use vfs_readdir because we have to keep the file
* position in sync between the coda_file and the host_file.
@@ -410,8 +409,20 @@
coda_file->f_pos = host_file->f_pos;
mutex_unlock(&host_inode->i_mutex);
- }
- else /* Venus: we must read Venus dirents from a file */
+ } else if (host_file->f_op->iterate) {
+ struct inode *host_inode = file_inode(host_file);
+ struct dir_context *ctx = buf;
+
+ mutex_lock(&host_inode->i_mutex);
+ ret = -ENOENT;
+ if (!IS_DEADDIR(host_inode)) {
+ ret = host_file->f_op->iterate(host_file, ctx);
+ file_accessed(host_file);
+ }
+ mutex_unlock(&host_inode->i_mutex);
+
+ coda_file->f_pos = ctx->pos;
+ } else /* Venus: we must read Venus dirents from a file */
ret = coda_venus_readdir(coda_file, buf, filldir);
return ret;
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 4dcc0d8..0aa4c4d 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -96,6 +96,7 @@
static int coda_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_NOATIME;
return 0;
}
diff --git a/fs/compat.c b/fs/compat.c
index fc3b55d..6af20de 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -832,6 +832,7 @@
};
struct compat_readdir_callback {
+ struct dir_context ctx;
struct compat_old_linux_dirent __user *dirent;
int result;
};
@@ -873,15 +874,15 @@
{
int error;
struct fd f = fdget(fd);
- struct compat_readdir_callback buf;
+ struct compat_readdir_callback buf = {
+ .ctx.actor = compat_fillonedir,
+ .dirent = dirent
+ };
if (!f.file)
return -EBADF;
- buf.result = 0;
- buf.dirent = dirent;
-
- error = vfs_readdir(f.file, compat_fillonedir, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (buf.result)
error = buf.result;
@@ -897,6 +898,7 @@
};
struct compat_getdents_callback {
+ struct dir_context ctx;
struct compat_linux_dirent __user *current_dir;
struct compat_linux_dirent __user *previous;
int count;
@@ -951,7 +953,11 @@
{
struct fd f;
struct compat_linux_dirent __user * lastdirent;
- struct compat_getdents_callback buf;
+ struct compat_getdents_callback buf = {
+ .ctx.actor = compat_filldir,
+ .current_dir = dirent,
+ .count = count
+ };
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
@@ -961,17 +967,12 @@
if (!f.file)
return -EBADF;
- buf.current_dir = dirent;
- buf.previous = NULL;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(f.file, compat_filldir, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
- if (put_user(f.file->f_pos, &lastdirent->d_off))
+ if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
@@ -983,6 +984,7 @@
#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64
struct compat_getdents_callback64 {
+ struct dir_context ctx;
struct linux_dirent64 __user *current_dir;
struct linux_dirent64 __user *previous;
int count;
@@ -1036,7 +1038,11 @@
{
struct fd f;
struct linux_dirent64 __user * lastdirent;
- struct compat_getdents_callback64 buf;
+ struct compat_getdents_callback64 buf = {
+ .ctx.actor = compat_filldir64,
+ .current_dir = dirent,
+ .count = count
+ };
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
@@ -1046,17 +1052,12 @@
if (!f.file)
return -EBADF;
- buf.current_dir = dirent;
- buf.previous = NULL;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(f.file, compat_filldir64, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
- typeof(lastdirent->d_off) d_off = f.file->f_pos;
+ typeof(lastdirent->d_off) d_off = buf.ctx.pos;
if (__put_user_unaligned(d_off, &lastdirent->d_off))
error = -EFAULT;
else
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e..4d24d17 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@
#define ELF_HWCAP COMPAT_ELF_HWCAP
#endif
+#ifdef COMPAT_ELF_HWCAP2
+#undef ELF_HWCAP2
+#define ELF_HWCAP2 COMPAT_ELF_HWCAP2
+#endif
+
#ifdef COMPAT_ARCH_DLINFO
#undef ARCH_DLINFO
#define ARCH_DLINFO COMPAT_ARCH_DLINFO
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 35b1c7b..c014858 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -227,6 +227,7 @@
static int cramfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 26d7fff..84378f0 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -218,6 +218,7 @@
int err;
struct debugfs_fs_info *fsi = sb->s_fs_info;
+ sync_filesystem(sb);
err = debugfs_parse_options(data, &fsi->mount_opts);
if (err)
goto fail;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 61af24e..91ea0e9 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -313,6 +313,7 @@
struct pts_fs_info *fsi = DEVPTS_SB(sb);
struct pts_mount_opts *opts = &fsi->mount_opts;
+ sync_filesystem(sb);
err = parse_mount_options(data, PARSE_REMOUNT, opts);
/*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 7ab90f5..8b31b9f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -127,6 +127,7 @@
spinlock_t bio_lock; /* protects BIO fields below */
int page_errors; /* errno from get_user_pages() */
int is_async; /* is IO async ? */
+ bool defer_completion; /* defer AIO completion to workqueue? */
int io_error; /* IO error in completion path */
unsigned long refcount; /* direct_io_worker() and bios */
struct bio *bio_list; /* singly linked via bi_private */
@@ -141,7 +142,10 @@
* allocation time. Don't add new fields after pages[] unless you
* wish that they not be zeroed.
*/
- struct page *pages[DIO_PAGES]; /* page buffer */
+ union {
+ struct page *pages[DIO_PAGES]; /* page buffer */
+ struct work_struct complete_work;/* deferred AIO completion */
+ };
} ____cacheline_aligned_in_smp;
static struct kmem_cache *dio_cache __read_mostly;
@@ -221,16 +225,16 @@
* dio_complete() - called when all DIO BIO I/O has been completed
* @offset: the byte offset in the file of the completed operation
*
- * This releases locks as dictated by the locking type, lets interested parties
- * know that a DIO operation has completed, and calculates the resulting return
- * code for the operation.
+ * This drops i_dio_count, lets interested parties know that a DIO operation
+ * has completed, and calculates the resulting return code for the operation.
*
* It lets the filesystem know if it registered an interest earlier via
* get_block. Pass the private field of the map buffer_head so that
* filesystems can use it to hold additional state between get_block calls and
* dio_complete.
*/
-static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
+ bool is_async)
{
ssize_t transferred = 0;
@@ -258,19 +262,26 @@
if (ret == 0)
ret = transferred;
- if (dio->end_io && dio->result) {
- dio->end_io(dio->iocb, offset, transferred,
- dio->private, ret, is_async);
- } else {
- inode_dio_done(dio->inode);
- if (is_async)
- aio_complete(dio->iocb, ret, 0);
- }
+ if (dio->end_io && dio->result)
+ dio->end_io(dio->iocb, offset, transferred, dio->private);
+ inode_dio_done(dio->inode);
+ if (is_async)
+ aio_complete(dio->iocb, ret, 0);
+
+ kmem_cache_free(dio_cache, dio);
return ret;
}
+static void dio_aio_complete_work(struct work_struct *work)
+{
+ struct dio *dio = container_of(work, struct dio, complete_work);
+
+ dio_complete(dio, dio->iocb->ki_pos, 0, true);
+}
+
static int dio_bio_complete(struct dio *dio, struct bio *bio);
+
/*
* Asynchronous IO callback.
*/
@@ -290,8 +301,13 @@
spin_unlock_irqrestore(&dio->bio_lock, flags);
if (remaining == 0) {
- dio_complete(dio, dio->iocb->ki_pos, 0, true);
- kmem_cache_free(dio_cache, dio);
+ if (dio->result && dio->defer_completion) {
+ INIT_WORK(&dio->complete_work, dio_aio_complete_work);
+ queue_work(dio->inode->i_sb->s_dio_done_wq,
+ &dio->complete_work);
+ } else {
+ dio_complete(dio, dio->iocb->ki_pos, 0, true);
+ }
}
}
@@ -511,6 +527,41 @@
}
/*
+ * Create workqueue for deferred direct IO completions. We allocate the
+ * workqueue when it's first needed. This avoids creating workqueue for
+ * filesystems that don't need it and also allows us to create the workqueue
+ * late enough so the we can include s_id in the name of the workqueue.
+ */
+static int sb_init_dio_done_wq(struct super_block *sb)
+{
+ struct workqueue_struct *wq = alloc_workqueue("dio/%s",
+ WQ_MEM_RECLAIM, 0,
+ sb->s_id);
+ if (!wq)
+ return -ENOMEM;
+ /*
+ * This has to be atomic as more DIOs can race to create the workqueue
+ */
+ cmpxchg(&sb->s_dio_done_wq, NULL, wq);
+ /* Someone created workqueue before us? Free ours... */
+ if (wq != sb->s_dio_done_wq)
+ destroy_workqueue(wq);
+ return 0;
+}
+
+static int dio_set_defer_completion(struct dio *dio)
+{
+ struct super_block *sb = dio->inode->i_sb;
+
+ if (dio->defer_completion)
+ return 0;
+ dio->defer_completion = true;
+ if (!sb->s_dio_done_wq)
+ return sb_init_dio_done_wq(sb);
+ return 0;
+}
+
+/*
* Call into the fs to map some more disk blocks. We record the current number
* of available blocks at sdio->blocks_available. These are in units of the
* fs blocksize, (1 << inode->i_blkbits).
@@ -581,6 +632,9 @@
/* Store for completion */
dio->private = map_bh->b_private;
+
+ if (ret == 0 && buffer_defer_completion(map_bh))
+ ret = dio_set_defer_completion(dio);
}
return ret;
}
@@ -1269,7 +1323,6 @@
if (drop_refcount(dio) == 0) {
retval = dio_complete(dio, offset, retval, false);
- kmem_cache_free(dio_cache, dio);
} else
BUG_ON(retval != -EIOCBQUEUED);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index d4644cc..125457c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -68,6 +68,7 @@
}
struct ecryptfs_getdents_callback {
+ struct dir_context ctx;
void *dirent;
struct dentry *dentry;
filldir_t filldir;
@@ -115,18 +116,19 @@
int rc;
struct file *lower_file;
struct inode *inode;
- struct ecryptfs_getdents_callback buf;
+ struct ecryptfs_getdents_callback buf = {
+ .dirent = dirent,
+ .dentry = file->f_path.dentry,
+ .filldir = filldir,
+ .filldir_called = 0,
+ .entries_written = 0,
+ .ctx.actor = ecryptfs_filldir
+ };
lower_file = ecryptfs_file_to_lower(file);
lower_file->f_pos = file->f_pos;
inode = file_inode(file);
- memset(&buf, 0, sizeof(buf));
- buf.dirent = dirent;
- buf.dentry = file->f_path.dentry;
- buf.filldir = filldir;
- buf.filldir_called = 0;
- buf.entries_written = 0;
- rc = vfs_readdir(lower_file, ecryptfs_filldir, (void *)&buf);
+ rc = iterate_dir(lower_file, &buf.ctx);
file->f_pos = lower_file->f_pos;
if (rc < 0)
goto out;
diff --git a/fs/efs/super.c b/fs/efs/super.c
index c6f57a7..4709692 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -113,6 +113,7 @@
static int efs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index deecc72..0cff443 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,6 +34,7 @@
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <linux/device.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/mman.h>
@@ -1602,7 +1603,8 @@
}
spin_unlock_irqrestore(&ep->lock, flags);
- if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
+ if (!freezable_schedule_hrtimeout_range(to, slack,
+ HRTIMER_MODE_ABS))
timed_out = 1;
spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/exec.c b/fs/exec.c
index acbd7ac..5496531 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1220,7 +1220,7 @@
/*
* determine how safe it is to execute the proposed program
* - the caller must hold ->cred_guard_mutex to protect against
- * PTRACE_ATTACH
+ * PTRACE_ATTACH or seccomp thread-sync
*/
static int check_unsafe_exec(struct linux_binprm *bprm)
{
@@ -1239,7 +1239,7 @@
* This isn't strictly necessary, but it makes it harder for LSMs to
* mess up.
*/
- if (current->no_new_privs)
+ if (task_no_new_privs(current))
bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
n_fs = 1;
@@ -1279,7 +1279,7 @@
if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
return;
- if (current->no_new_privs)
+ if (task_no_new_privs(current))
return;
inode = file_inode(bprm->file);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index d1f80ab..2ec8eb1 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -953,9 +953,11 @@
return 0;
}
-static void exofs_invalidatepage(struct page *page, unsigned long offset)
+static void exofs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
- EXOFS_DBGMSG("page 0x%lx offset 0x%lx\n", page->index, offset);
+ EXOFS_DBGMSG("page 0x%lx offset 0x%x length 0x%x\n",
+ page->index, offset, length);
WARN_ON(1);
}
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index b4eec4c..dc4784b 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -212,6 +212,7 @@
}
struct getdents_callback {
+ struct dir_context ctx;
char *name; /* name that was found. It already points to a
buffer NAME_MAX+1 is size */
unsigned long ino; /* the inum we are looking for */
@@ -254,7 +255,11 @@
struct inode *dir = path->dentry->d_inode;
int error;
struct file *file;
- struct getdents_callback buffer;
+ struct getdents_callback buffer = {
+ .ctx.actor = filldir_one,
+ .name = name,
+ .ino = child->d_inode->i_ino
+ };
error = -ENOTDIR;
if (!dir || !S_ISDIR(dir->i_mode))
@@ -271,17 +276,14 @@
goto out;
error = -EINVAL;
- if (!file->f_op->readdir)
+ if (!file->f_op->readdir && !file->f_op->iterate)
goto out_close;
- buffer.name = name;
- buffer.ino = child->d_inode->i_ino;
- buffer.found = 0;
buffer.sequence = 0;
while (1) {
int old_seq = buffer.sequence;
- error = vfs_readdir(file, filldir_one, &buffer);
+ error = iterate_dir(file, &buffer.ctx);
if (buffer.found) {
error = 0;
break;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 20d6697..d260115 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1254,6 +1254,7 @@
unsigned long old_sb_flags;
int err;
+ sync_filesystem(sb);
spin_lock(&sbi->s_lock);
/* Store the old options */
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 23c7128..b6e5934 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1825,7 +1825,8 @@
return mpage_readpages(mapping, pages, nr_pages, ext3_get_block);
}
-static void ext3_invalidatepage(struct page *page, unsigned long offset)
+static void ext3_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
journal_t *journal = EXT3_JOURNAL(page->mapping->host);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 882d4bd..b1e30be 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2588,6 +2588,8 @@
int i;
#endif
+ sync_filesystem(sb);
+
/* Store the original options */
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index efea5d5..af1a90a 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -64,6 +64,24 @@
If you are not using a security module that requires using
extended attributes for file security labels, say N.
+config EXT4_FS_ENCRYPTION
+ bool "Ext4 Encryption"
+ depends on EXT4_FS
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_ECB
+ select CRYPTO_XTS
+ select CRYPTO_CTS
+ select CRYPTO_CTR
+ select CRYPTO_SHA256
+ select KEYS
+ select ENCRYPTED_KEYS
+ help
+ Enable encryption of ext4 files and directories. This
+ feature is similar to ecryptfs, but it is more memory
+ efficient since it avoids caching the encrypted and
+ decrypted pages in the page cache.
+
config EXT4_DEBUG
bool "EXT4 debugging support"
depends on EXT4_FS
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 0310fec..75285ea 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -8,7 +8,9 @@
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
mmp.o indirect.o extents_status.o xattr.o xattr_user.o \
- xattr_trusted.o inline.o
+ xattr_trusted.o inline.o readpage.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
+ext4-$(CONFIG_EXT4_FS_ENCRYPTION) += crypto_policy.o crypto.o \
+ crypto_key.o crypto_fname.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 39a54a0..d40c8db 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -152,13 +152,6 @@
struct posix_acl *acl;
int retval;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return NULL;
-
- acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
-
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
@@ -196,7 +189,7 @@
* inode->i_mutex: down unless called from ext4_new_inode
*/
static int
-ext4_set_acl(handle_t *handle, struct inode *inode, int type,
+__ext4_set_acl(handle_t *handle, struct inode *inode, int type,
struct posix_acl *acl)
{
int name_index;
@@ -204,9 +197,6 @@
size_t size = 0;
int error;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
-
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
@@ -248,6 +238,25 @@
return error;
}
+int
+ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+ handle_t *handle;
+ int error, retries = 0;
+
+retry:
+ handle = ext4_journal_start(inode, EXT4_HT_XATTR,
+ ext4_jbd2_credits_xattr(inode));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ error = __ext4_set_acl(handle, inode, type, acl);
+ ext4_journal_stop(handle);
+ if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+ return error;
+}
+
/*
* Initialize the ACLs of a new inode. Called from ext4_new_inode.
*
@@ -257,199 +266,23 @@
int
ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
{
- struct posix_acl *acl = NULL;
- int error = 0;
-
- if (!S_ISLNK(inode->i_mode)) {
- if (test_opt(dir->i_sb, POSIX_ACL)) {
- acl = ext4_get_acl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- }
- if (!acl)
- inode->i_mode &= ~current_umask();
- }
- if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
- if (S_ISDIR(inode->i_mode)) {
- error = ext4_set_acl(handle, inode,
- ACL_TYPE_DEFAULT, acl);
- if (error)
- goto cleanup;
- }
- error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
- if (error < 0)
- return error;
-
- if (error > 0) {
- /* This is an extended ACL */
- error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
- }
- }
-cleanup:
- posix_acl_release(acl);
- return error;
-}
-
-/*
- * Does chmod for an inode that may have an Access Control List. The
- * inode->i_mode field must be updated to the desired value by the caller
- * before calling this function.
- * Returns 0 on success, or a negative error number.
- *
- * We change the ACL rather than storing some ACL entries in the file
- * mode permission bits (which would be more efficient), because that
- * would break once additional permissions (like ACL_APPEND, ACL_DELETE
- * for directories) are added. There are no more bits available in the
- * file mode.
- *
- * inode->i_mutex: down
- */
-int
-ext4_acl_chmod(struct inode *inode)
-{
- struct posix_acl *acl;
- handle_t *handle;
- int retries = 0;
+ struct posix_acl *default_acl, *acl;
int error;
-
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return 0;
- acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
- error = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
if (error)
return error;
-retry:
- handle = ext4_journal_start(inode, EXT4_HT_XATTR,
- ext4_jbd2_credits_xattr(inode));
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- ext4_std_error(inode->i_sb, error);
- goto out;
+
+ if (default_acl) {
+ error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT,
+ default_acl);
+ posix_acl_release(default_acl);
}
- error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
- ext4_journal_stop(handle);
- if (error == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-out:
- posix_acl_release(acl);
- return error;
-}
-
-/*
- * Extended attribute handlers
- */
-static size_t
-ext4_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_len)
- memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
- return size;
-}
-
-static size_t
-ext4_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_len)
- memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
- return size;
-}
-
-static int
-ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
- size_t size, int type)
-{
- struct posix_acl *acl;
- int error;
-
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return -EOPNOTSUPP;
-
- acl = ext4_get_acl(dentry->d_inode, type);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl == NULL)
- return -ENODATA;
- error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
- posix_acl_release(acl);
-
- return error;
-}
-
-static int
-ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags, int type)
-{
- struct inode *inode = dentry->d_inode;
- handle_t *handle;
- struct posix_acl *acl;
- int error, retries = 0;
-
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return -EOPNOTSUPP;
- if (!inode_owner_or_capable(inode))
- return -EPERM;
-
- if (value) {
- acl = posix_acl_from_xattr(&init_user_ns, value, size);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- else if (acl) {
- error = posix_acl_valid(acl);
- if (error)
- goto release_and_out;
- }
- } else
- acl = NULL;
-
-retry:
- handle = ext4_journal_start(inode, EXT4_HT_XATTR,
- ext4_jbd2_credits_xattr(inode));
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- goto release_and_out;
+ if (acl) {
+ if (!error)
+ error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS,
+ acl);
+ posix_acl_release(acl);
}
- error = ext4_set_acl(handle, inode, type, acl);
- ext4_journal_stop(handle);
- if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-
-release_and_out:
- posix_acl_release(acl);
return error;
}
-
-const struct xattr_handler ext4_xattr_acl_access_handler = {
- .prefix = POSIX_ACL_XATTR_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .list = ext4_xattr_list_acl_access,
- .get = ext4_xattr_get_acl,
- .set = ext4_xattr_set_acl,
-};
-
-const struct xattr_handler ext4_xattr_acl_default_handler = {
- .prefix = POSIX_ACL_XATTR_DEFAULT,
- .flags = ACL_TYPE_DEFAULT,
- .list = ext4_xattr_list_acl_default,
- .get = ext4_xattr_get_acl,
- .set = ext4_xattr_set_acl,
-};
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 18cb39e..da2c795 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -55,18 +55,13 @@
/* acl.c */
struct posix_acl *ext4_get_acl(struct inode *inode, int type);
-extern int ext4_acl_chmod(struct inode *);
+int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
#else /* CONFIG_EXT4_FS_POSIX_ACL */
#include <linux/sched.h>
#define ext4_get_acl NULL
-
-static inline int
-ext4_acl_chmod(struct inode *inode)
-{
- return 0;
-}
+#define ext4_set_acl NULL
static inline int
ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 3742e4c..83a6f49 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -83,9 +83,9 @@
/* Return the number of clusters used for file system metadata; this
* represents the overhead needed by the file system.
*/
-unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned num_clusters;
int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
@@ -176,27 +176,35 @@
}
/* Initializes an uninitialized block bitmap */
-void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static int ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
int flex_bg = 0;
+ struct ext4_group_info *grp;
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_group_clusters_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
- return;
+ grp = ext4_get_group_info(sb, block_group);
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ int count;
+ count = ext4_free_inodes_count(sb, gdp);
+ percpu_counter_sub(&sbi->s_freeinodes_counter,
+ count);
+ }
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ return -EIO;
}
memset(bh->b_data, 0, sb->s_blocksize);
@@ -234,6 +242,7 @@
sb->s_blocksize * 8, bh->b_data);
ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
ext4_group_desc_csum_set(sb, block_group, gdp);
+ return 0;
}
/* Return the number of free blocks in a block group. It is used when
@@ -305,9 +314,10 @@
*/
static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
- unsigned int block_group,
+ ext4_group_t block_group,
struct buffer_head *bh)
{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
ext4_fsblk_t blk;
@@ -327,14 +337,14 @@
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
@@ -342,20 +352,23 @@
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
- offset + EXT4_SB(sb)->s_itb_per_group,
- offset);
- if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
+ EXT4_B2C(sbi, offset));
+ if (next_zero_bit <
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group))
/* bad bitmap for inode tables */
return blk;
return 0;
}
-void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- unsigned int block_group,
- struct buffer_head *bh)
+static void ext4_validate_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *desc,
+ ext4_group_t block_group,
+ struct buffer_head *bh)
{
ext4_fsblk_t blk;
+ struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
if (buffer_verified(bh))
return;
@@ -366,12 +379,20 @@
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
block_group, blk);
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
set_buffer_verified(bh);
@@ -417,11 +438,15 @@
}
ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- ext4_init_block_bitmap(sb, bh, block_group, desc);
+ int err;
+
+ err = ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
+ if (err)
+ ext4_error(sb, "Checksum bad for grp %u", block_group);
return bh;
}
ext4_unlock_group(sb, block_group);
@@ -445,7 +470,10 @@
return bh;
verify:
ext4_validate_block_bitmap(sb, desc, block_group, bh);
- return bh;
+ if (buffer_verified(bh))
+ return bh;
+ put_bh(bh);
+ return NULL;
}
/* Returns 0 on success, 1 on error */
@@ -469,7 +497,8 @@
clear_buffer_new(bh);
/* Panic or remount fs read-only if block bitmap is invalid */
ext4_validate_block_bitmap(sb, desc, block_group, bh);
- return 0;
+ /* ...but check for error just in case errors=continue. */
+ return !buffer_verified(bh);
}
struct buffer_head *
@@ -611,10 +640,8 @@
* Account for the allocated meta blocks. We will never
* fail EDQUOT for metdata, but we do account for it.
*/
- if (!(*errp) &&
- ext4_test_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED)) {
+ if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_alloc_block_nofail(inode,
EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
@@ -634,6 +661,7 @@
struct ext4_group_desc *gdp;
ext4_group_t i;
ext4_group_t ngroups = ext4_get_groups_count(sb);
+ struct ext4_group_info *grp;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
@@ -649,14 +677,18 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_group_clusters(sb, gdp);
+ grp = NULL;
+ if (EXT4_SB(sb)->s_group_info)
+ grp = ext4_get_group_info(sb, i);
+ if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ desc_count += ext4_free_group_clusters(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
continue;
x = ext4_count_free(bitmap_bh->b_data,
- EXT4_BLOCKS_PER_GROUP(sb) / 8);
+ EXT4_CLUSTERS_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
@@ -673,7 +705,11 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_group_clusters(sb, gdp);
+ grp = NULL;
+ if (EXT4_SB(sb)->s_group_info)
+ grp = ext4_get_group_info(sb, i);
+ if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ desc_count += ext4_free_group_clusters(sb, gdp);
}
return desc_count;
@@ -682,21 +718,15 @@
static inline int test_root(ext4_group_t a, int b)
{
- int num = b;
-
- while (a > num)
- num *= b;
- return num == a;
-}
-
-static int ext4_group_sparse(ext4_group_t group)
-{
- if (group <= 1)
- return 1;
- if (!(group & 1))
- return 0;
- return (test_root(group, 7) || test_root(group, 5) ||
- test_root(group, 3));
+ while (1) {
+ if (a < b)
+ return 0;
+ if (a == b)
+ return 1;
+ if ((a % b) != 0)
+ return 0;
+ a = a / b;
+ }
}
/**
@@ -709,11 +739,26 @@
*/
int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
- !ext4_group_sparse(group))
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ if (group == 0)
+ return 1;
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) {
+ if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
+ group == le32_to_cpu(es->s_backup_bgs[1]))
+ return 1;
return 0;
- return 1;
+ }
+ if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER))
+ return 1;
+ if (!(group & 1))
+ return 0;
+ if (test_root(group, 3) || (test_root(group, 5)) ||
+ test_root(group, 7))
+ return 1;
+
+ return 0;
}
static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index 3285aa5..b610779 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -24,8 +24,7 @@
__u32 provided, calculated;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return 1;
provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
@@ -46,8 +45,7 @@
__u32 csum;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
@@ -65,8 +63,7 @@
struct ext4_sb_info *sbi = EXT4_SB(sb);
int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return 1;
provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo);
@@ -91,8 +88,7 @@
__u32 csum;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return;
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 3f11656..41eb9dc 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -180,37 +180,12 @@
/* Called when the filesystem is unmounted */
void ext4_release_system_zone(struct super_block *sb)
{
- struct rb_node *n = EXT4_SB(sb)->system_blks.rb_node;
- struct rb_node *parent;
- struct ext4_system_zone *entry;
+ struct ext4_system_zone *entry, *n;
- while (n) {
- /* Do the node's children first */
- if (n->rb_left) {
- n = n->rb_left;
- continue;
- }
- if (n->rb_right) {
- n = n->rb_right;
- continue;
- }
- /*
- * The node has no children; free it, and then zero
- * out parent's link to it. Finally go to the
- * beginning of the loop and try to free the parent
- * node.
- */
- parent = rb_parent(n);
- entry = rb_entry(n, struct ext4_system_zone, node);
+ rbtree_postorder_for_each_entry_safe(entry, n,
+ &EXT4_SB(sb)->system_blks, node)
kmem_cache_free(ext4_system_zone_cachep, entry);
- if (!parent)
- EXT4_SB(sb)->system_blks = RB_ROOT;
- else if (parent->rb_left == n)
- parent->rb_left = NULL;
- else if (parent->rb_right == n)
- parent->rb_right = NULL;
- n = parent;
- }
+
EXT4_SB(sb)->system_blks = RB_ROOT;
}
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
new file mode 100644
index 0000000..e086ac4
--- /dev/null
+++ b/fs/ext4/crypto.c
@@ -0,0 +1,475 @@
+/*
+ * linux/fs/ext4/crypto.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption functions for ext4
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/user-type.h>
+#include <keys/encrypted-type.h>
+#include <linux/crypto.h>
+#include <linux/ecryptfs.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+
+#include "ext4_extents.h"
+#include "xattr.h"
+
+/* Encryption added and removed here! (L: */
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+ "Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+ "Number of crypto contexts to preallocate");
+
+static mempool_t *ext4_bounce_page_pool;
+
+static LIST_HEAD(ext4_free_crypto_ctxs);
+static DEFINE_SPINLOCK(ext4_crypto_ctx_lock);
+
+static struct kmem_cache *ext4_crypto_ctx_cachep;
+struct kmem_cache *ext4_crypt_info_cachep;
+
+/**
+ * ext4_release_crypto_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
+{
+ unsigned long flags;
+
+ if (ctx->flags & EXT4_WRITE_PATH_FL && ctx->w.bounce_page)
+ mempool_free(ctx->w.bounce_page, ext4_bounce_page_pool);
+ ctx->w.bounce_page = NULL;
+ ctx->w.control_page = NULL;
+ if (ctx->flags & EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+ kmem_cache_free(ext4_crypto_ctx_cachep, ctx);
+ } else {
+ spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
+ list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
+ spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
+ }
+}
+
+/**
+ * ext4_get_crypto_ctx() - Gets an encryption context
+ * @inode: The inode for which we are doing the crypto
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
+{
+ struct ext4_crypto_ctx *ctx = NULL;
+ int res = 0;
+ unsigned long flags;
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+
+ if (ci == NULL)
+ return ERR_PTR(-ENOKEY);
+
+ /*
+ * We first try getting the ctx from a free list because in
+ * the common case the ctx will have an allocated and
+ * initialized crypto tfm, so it's probably a worthwhile
+ * optimization. For the bounce page, we first try getting it
+ * from the kernel allocator because that's just about as fast
+ * as getting it from a list and because a cache of free pages
+ * should generally be a "last resort" option for a filesystem
+ * to be able to do its job.
+ */
+ spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
+ ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs,
+ struct ext4_crypto_ctx, free_list);
+ if (ctx)
+ list_del(&ctx->free_list);
+ spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
+ if (!ctx) {
+ ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
+ if (!ctx) {
+ res = -ENOMEM;
+ goto out;
+ }
+ ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ } else {
+ ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ }
+ ctx->flags &= ~EXT4_WRITE_PATH_FL;
+
+out:
+ if (res) {
+ if (!IS_ERR_OR_NULL(ctx))
+ ext4_release_crypto_ctx(ctx);
+ ctx = ERR_PTR(res);
+ }
+ return ctx;
+}
+
+struct workqueue_struct *ext4_read_workqueue;
+static DEFINE_MUTEX(crypto_init);
+
+/**
+ * ext4_exit_crypto() - Shutdown the ext4 encryption system
+ */
+void ext4_exit_crypto(void)
+{
+ struct ext4_crypto_ctx *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &ext4_free_crypto_ctxs, free_list)
+ kmem_cache_free(ext4_crypto_ctx_cachep, pos);
+ INIT_LIST_HEAD(&ext4_free_crypto_ctxs);
+ if (ext4_bounce_page_pool)
+ mempool_destroy(ext4_bounce_page_pool);
+ ext4_bounce_page_pool = NULL;
+ if (ext4_read_workqueue)
+ destroy_workqueue(ext4_read_workqueue);
+ ext4_read_workqueue = NULL;
+ if (ext4_crypto_ctx_cachep)
+ kmem_cache_destroy(ext4_crypto_ctx_cachep);
+ ext4_crypto_ctx_cachep = NULL;
+ if (ext4_crypt_info_cachep)
+ kmem_cache_destroy(ext4_crypt_info_cachep);
+ ext4_crypt_info_cachep = NULL;
+}
+
+/**
+ * ext4_init_crypto() - Set up for ext4 encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int ext4_init_crypto(void)
+{
+ int i, res = -ENOMEM;
+
+ mutex_lock(&crypto_init);
+ if (ext4_read_workqueue)
+ goto already_initialized;
+ ext4_read_workqueue = alloc_workqueue("ext4_crypto", WQ_HIGHPRI, 0);
+ if (!ext4_read_workqueue)
+ goto fail;
+
+ ext4_crypto_ctx_cachep = KMEM_CACHE(ext4_crypto_ctx,
+ SLAB_RECLAIM_ACCOUNT);
+ if (!ext4_crypto_ctx_cachep)
+ goto fail;
+
+ ext4_crypt_info_cachep = KMEM_CACHE(ext4_crypt_info,
+ SLAB_RECLAIM_ACCOUNT);
+ if (!ext4_crypt_info_cachep)
+ goto fail;
+
+ for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+ struct ext4_crypto_ctx *ctx;
+
+ ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
+ if (!ctx) {
+ res = -ENOMEM;
+ goto fail;
+ }
+ list_add(&ctx->free_list, &ext4_free_crypto_ctxs);
+ }
+
+ ext4_bounce_page_pool =
+ mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+ if (!ext4_bounce_page_pool) {
+ res = -ENOMEM;
+ goto fail;
+ }
+already_initialized:
+ mutex_unlock(&crypto_init);
+ return 0;
+fail:
+ ext4_exit_crypto();
+ mutex_unlock(&crypto_init);
+ return res;
+}
+
+void ext4_restore_control_page(struct page *data_page)
+{
+ struct ext4_crypto_ctx *ctx =
+ (struct ext4_crypto_ctx *)page_private(data_page);
+
+ set_page_private(data_page, (unsigned long)NULL);
+ ClearPagePrivate(data_page);
+ unlock_page(data_page);
+ ext4_release_crypto_ctx(ctx);
+}
+
+/**
+ * ext4_crypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void ext4_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+typedef enum {
+ EXT4_DECRYPT = 0,
+ EXT4_ENCRYPT,
+} ext4_direction_t;
+
+static int ext4_page_crypto(struct ext4_crypto_ctx *ctx,
+ struct inode *inode,
+ ext4_direction_t rw,
+ pgoff_t index,
+ struct page *src_page,
+ struct page *dest_page)
+
+{
+ u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist dst, src;
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_request_alloc() failed\n",
+ __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(
+ req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_crypt_complete, &ecr);
+
+ BUILD_BUG_ON(EXT4_XTS_TWEAK_SIZE < sizeof(index));
+ memcpy(xts_tweak, &index, sizeof(index));
+ memset(&xts_tweak[sizeof(index)], 0,
+ EXT4_XTS_TWEAK_SIZE - sizeof(index));
+
+ sg_init_table(&dst, 1);
+ sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+ sg_init_table(&src, 1);
+ sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
+ ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+ xts_tweak);
+ if (rw == EXT4_DECRYPT)
+ res = crypto_ablkcipher_decrypt(req);
+ else
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ ablkcipher_request_free(req);
+ if (res) {
+ printk_ratelimited(
+ KERN_ERR
+ "%s: crypto_ablkcipher_encrypt() returned %d\n",
+ __func__, res);
+ return res;
+ }
+ return 0;
+}
+
+static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
+{
+ ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, GFP_NOWAIT);
+ if (ctx->w.bounce_page == NULL)
+ return ERR_PTR(-ENOMEM);
+ ctx->flags |= EXT4_WRITE_PATH_FL;
+ return ctx->w.bounce_page;
+}
+
+/**
+ * ext4_encrypt() - Encrypts a page
+ * @inode: The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path. The caller must call
+ * ext4_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *ext4_encrypt(struct inode *inode,
+ struct page *plaintext_page)
+{
+ struct ext4_crypto_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ int err;
+
+ BUG_ON(!PageLocked(plaintext_page));
+
+ ctx = ext4_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return (struct page *) ctx;
+
+ /* The encryption operation will require a bounce page. */
+ ciphertext_page = alloc_bounce_page(ctx);
+ if (IS_ERR(ciphertext_page))
+ goto errout;
+ ctx->w.control_page = plaintext_page;
+ err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, plaintext_page->index,
+ plaintext_page, ciphertext_page);
+ if (err) {
+ ciphertext_page = ERR_PTR(err);
+ errout:
+ ext4_release_crypto_ctx(ctx);
+ return ciphertext_page;
+ }
+ SetPagePrivate(ciphertext_page);
+ set_page_private(ciphertext_page, (unsigned long)ctx);
+ lock_page(ciphertext_page);
+ return ciphertext_page;
+}
+
+/**
+ * ext4_decrypt() - Decrypts a page in-place
+ * @ctx: The encryption context.
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+
+ return ext4_page_crypto(ctx, page->mapping->host,
+ EXT4_DECRYPT, page->index, page, page);
+}
+
+/*
+ * Convenience function which takes care of allocating and
+ * deallocating the encryption context
+ */
+int ext4_decrypt_one(struct inode *inode, struct page *page)
+{
+ int ret;
+
+ struct ext4_crypto_ctx *ctx = ext4_get_crypto_ctx(inode);
+
+ if (!ctx)
+ return -ENOMEM;
+ ret = ext4_decrypt(ctx, page);
+ ext4_release_crypto_ctx(ctx);
+ return ret;
+}
+
+int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ struct ext4_crypto_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ struct bio *bio;
+ ext4_lblk_t lblk = ex->ee_block;
+ ext4_fsblk_t pblk = ext4_ext_pblock(ex);
+ unsigned int len = ext4_ext_get_actual_len(ex);
+ int err = 0;
+
+ BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
+
+ ctx = ext4_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ ciphertext_page = alloc_bounce_page(ctx);
+ if (IS_ERR(ciphertext_page)) {
+ err = PTR_ERR(ciphertext_page);
+ goto errout;
+ }
+
+ while (len--) {
+ err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk,
+ ZERO_PAGE(0), ciphertext_page);
+ if (err)
+ goto errout;
+
+ bio = bio_alloc(GFP_KERNEL, 1);
+ if (!bio) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ bio->bi_bdev = inode->i_sb->s_bdev;
+ bio->bi_sector = pblk;
+ err = bio_add_page(bio, ciphertext_page,
+ inode->i_sb->s_blocksize, 0);
+ if (err) {
+ bio_put(bio);
+ goto errout;
+ }
+ err = submit_bio_wait(WRITE, bio);
+ bio_put(bio);
+ if (err)
+ goto errout;
+ }
+ err = 0;
+errout:
+ ext4_release_crypto_ctx(ctx);
+ return err;
+}
+
+bool ext4_valid_contents_enc_mode(uint32_t mode)
+{
+ return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS);
+}
+
+/**
+ * ext4_validate_encryption_key_size() - Validate the encryption key size
+ * @mode: The key mode.
+ * @size: The key size to validate.
+ *
+ * Return: The validated key size for @mode. Zero if invalid.
+ */
+uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
+{
+ if (size == ext4_encryption_key_size(mode))
+ return size;
+ return 0;
+}
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
new file mode 100644
index 0000000..7dc4eb5
--- /dev/null
+++ b/fs/ext4/crypto_fname.c
@@ -0,0 +1,469 @@
+/*
+ * linux/fs/ext4/crypto_fname.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains functions for filename crypto management in ext4
+ *
+ * Written by Uday Savagaonkar, 2014.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ */
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/crypto.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+
+#include "ext4.h"
+#include "ext4_crypto.h"
+#include "xattr.h"
+
+/**
+ * ext4_dir_crypt_complete() -
+ */
+static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+bool ext4_valid_filenames_enc_mode(uint32_t mode)
+{
+ return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS);
+}
+
+static unsigned max_name_len(struct inode *inode)
+{
+ return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
+ EXT4_NAME_LEN;
+}
+
+/**
+ * ext4_fname_encrypt() -
+ *
+ * This function encrypts the input filename, and returns the length of the
+ * ciphertext. Errors are returned as negative numbers. We trust the caller to
+ * allocate sufficient memory to oname string.
+ */
+static int ext4_fname_encrypt(struct inode *inode,
+ const struct qstr *iname,
+ struct ext4_str *oname)
+{
+ u32 ciphertext_len;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+ char iv[EXT4_CRYPTO_BLOCK_SIZE];
+ struct scatterlist src_sg, dst_sg;
+ int padding = 4 << (ci->ci_flags & EXT4_POLICY_FLAGS_PAD_MASK);
+ char *workbuf, buf[32], *alloc_buf = NULL;
+ unsigned lim = max_name_len(inode);
+
+ if (iname->len <= 0 || iname->len > lim)
+ return -EIO;
+
+ ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ?
+ EXT4_CRYPTO_BLOCK_SIZE : iname->len;
+ ciphertext_len = ext4_fname_crypto_round_up(ciphertext_len, padding);
+ ciphertext_len = (ciphertext_len > lim)
+ ? lim : ciphertext_len;
+
+ if (ciphertext_len <= sizeof(buf)) {
+ workbuf = buf;
+ } else {
+ alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
+ if (!alloc_buf)
+ return -ENOMEM;
+ workbuf = alloc_buf;
+ }
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(
+ KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
+ kfree(alloc_buf);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_dir_crypt_complete, &ecr);
+
+ /* Copy the input */
+ memcpy(workbuf, iname->name, iname->len);
+ if (iname->len < ciphertext_len)
+ memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
+
+ /* Initialize IV */
+ memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
+
+ /* Create encryption request */
+ sg_init_one(&src_sg, workbuf, ciphertext_len);
+ sg_init_one(&dst_sg, oname->name, ciphertext_len);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ kfree(alloc_buf);
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(
+ KERN_ERR "%s: Error (error code %d)\n", __func__, res);
+ }
+ oname->len = ciphertext_len;
+ return res;
+}
+
+/*
+ * ext4_fname_decrypt()
+ * This function decrypts the input filename, and returns
+ * the length of the plaintext.
+ * Errors are returned as negative numbers.
+ * We trust the caller to allocate sufficient memory to oname string.
+ */
+static int ext4_fname_decrypt(struct inode *inode,
+ const struct ext4_str *iname,
+ struct ext4_str *oname)
+{
+ struct ext4_str tmp_in[2], tmp_out[1];
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist src_sg, dst_sg;
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+ char iv[EXT4_CRYPTO_BLOCK_SIZE];
+ unsigned lim = max_name_len(inode);
+
+ if (iname->len <= 0 || iname->len > lim)
+ return -EIO;
+
+ tmp_in[0].name = iname->name;
+ tmp_in[0].len = iname->len;
+ tmp_out[0].name = oname->name;
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(
+ KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ ext4_dir_crypt_complete, &ecr);
+
+ /* Initialize IV */
+ memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
+
+ /* Create encryption request */
+ sg_init_one(&src_sg, iname->name, iname->len);
+ sg_init_one(&dst_sg, oname->name, oname->len);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+ res = crypto_ablkcipher_decrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(
+ KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
+ __func__, res);
+ return res;
+ }
+
+ oname->len = strnlen(oname->name, iname->len);
+ return oname->len;
+}
+
+static const char *lookup_table =
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+/**
+ * ext4_fname_encode_digest() -
+ *
+ * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
+ * The encoded string is roughly 4/3 times the size of the input string.
+ */
+static int digest_encode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ char *cp = dst;
+
+ while (i < len) {
+ ac += (((unsigned char) src[i]) << bits);
+ bits += 8;
+ do {
+ *cp++ = lookup_table[ac & 0x3f];
+ ac >>= 6;
+ bits -= 6;
+ } while (bits >= 6);
+ i++;
+ }
+ if (bits)
+ *cp++ = lookup_table[ac & 0x3f];
+ return cp - dst;
+}
+
+static int digest_decode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ const char *p;
+ char *cp = dst;
+
+ while (i < len) {
+ p = strchr(lookup_table, src[i]);
+ if (p == NULL || src[i] == 0)
+ return -2;
+ ac += (p - lookup_table) << bits;
+ bits += 6;
+ if (bits >= 8) {
+ *cp++ = ac & 0xff;
+ ac >>= 8;
+ bits -= 8;
+ }
+ i++;
+ }
+ if (ac)
+ return -1;
+ return cp - dst;
+}
+
+/**
+ * ext4_fname_crypto_round_up() -
+ *
+ * Return: The next multiple of block size
+ */
+u32 ext4_fname_crypto_round_up(u32 size, u32 blksize)
+{
+ return ((size+blksize-1)/blksize)*blksize;
+}
+
+unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen)
+{
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+ int padding = 32;
+
+ if (ci)
+ padding = 4 << (ci->ci_flags & EXT4_POLICY_FLAGS_PAD_MASK);
+ if (ilen < EXT4_CRYPTO_BLOCK_SIZE)
+ ilen = EXT4_CRYPTO_BLOCK_SIZE;
+ return ext4_fname_crypto_round_up(ilen, padding);
+}
+
+/*
+ * ext4_fname_crypto_alloc_buffer() -
+ *
+ * Allocates an output buffer that is sufficient for the crypto operation
+ * specified by the context and the direction.
+ */
+int ext4_fname_crypto_alloc_buffer(struct inode *inode,
+ u32 ilen, struct ext4_str *crypto_str)
+{
+ unsigned int olen = ext4_fname_encrypted_size(inode, ilen);
+
+ crypto_str->len = olen;
+ if (olen < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2)
+ olen = EXT4_FNAME_CRYPTO_DIGEST_SIZE*2;
+ /* Allocated buffer can hold one more character to null-terminate the
+ * string */
+ crypto_str->name = kmalloc(olen+1, GFP_NOFS);
+ if (!(crypto_str->name))
+ return -ENOMEM;
+ return 0;
+}
+
+/**
+ * ext4_fname_crypto_free_buffer() -
+ *
+ * Frees the buffer allocated for crypto operation.
+ */
+void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str)
+{
+ if (!crypto_str)
+ return;
+ kfree(crypto_str->name);
+ crypto_str->name = NULL;
+}
+
+/**
+ * ext4_fname_disk_to_usr() - converts a filename from disk space to user space
+ */
+int _ext4_fname_disk_to_usr(struct inode *inode,
+ struct dx_hash_info *hinfo,
+ const struct ext4_str *iname,
+ struct ext4_str *oname)
+{
+ char buf[24];
+ int ret;
+
+ if (iname->len < 3) {
+ /*Check for . and .. */
+ if (iname->name[0] == '.' && iname->name[iname->len-1] == '.') {
+ oname->name[0] = '.';
+ oname->name[iname->len-1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+ }
+ if (EXT4_I(inode)->i_crypt_info)
+ return ext4_fname_decrypt(inode, iname, oname);
+
+ if (iname->len <= EXT4_FNAME_CRYPTO_DIGEST_SIZE) {
+ ret = digest_encode(iname->name, iname->len, oname->name);
+ oname->len = ret;
+ return ret;
+ }
+ if (hinfo) {
+ memcpy(buf, &hinfo->hash, 4);
+ memcpy(buf+4, &hinfo->minor_hash, 4);
+ } else
+ memset(buf, 0, 8);
+ memcpy(buf + 8, iname->name + iname->len - 16, 16);
+ oname->name[0] = '_';
+ ret = digest_encode(buf, 24, oname->name+1);
+ oname->len = ret + 1;
+ return ret + 1;
+}
+
+int ext4_fname_disk_to_usr(struct inode *inode,
+ struct dx_hash_info *hinfo,
+ const struct ext4_dir_entry_2 *de,
+ struct ext4_str *oname)
+{
+ struct ext4_str iname = {.name = (unsigned char *) de->name,
+ .len = de->name_len };
+
+ return _ext4_fname_disk_to_usr(inode, hinfo, &iname, oname);
+}
+
+
+/**
+ * ext4_fname_usr_to_disk() - converts a filename from user space to disk space
+ */
+int ext4_fname_usr_to_disk(struct inode *inode,
+ const struct qstr *iname,
+ struct ext4_str *oname)
+{
+ int res;
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+
+ if (iname->len < 3) {
+ /*Check for . and .. */
+ if (iname->name[0] == '.' &&
+ iname->name[iname->len-1] == '.') {
+ oname->name[0] = '.';
+ oname->name[iname->len-1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+ }
+ if (ci) {
+ res = ext4_fname_encrypt(inode, iname, oname);
+ return res;
+ }
+ /* Without a proper key, a user is not allowed to modify the filenames
+ * in a directory. Consequently, a user space name cannot be mapped to
+ * a disk-space name */
+ return -EACCES;
+}
+
+int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct ext4_filename *fname)
+{
+ struct ext4_crypt_info *ci;
+ int ret = 0, bigname = 0;
+
+ memset(fname, 0, sizeof(struct ext4_filename));
+ fname->usr_fname = iname;
+
+ if (!ext4_encrypted_inode(dir) ||
+ ((iname->name[0] == '.') &&
+ ((iname->len == 1) ||
+ ((iname->name[1] == '.') && (iname->len == 2))))) {
+ fname->disk_name.name = (unsigned char *) iname->name;
+ fname->disk_name.len = iname->len;
+ return 0;
+ }
+ ret = ext4_get_encryption_info(dir);
+ if (ret)
+ return ret;
+ ci = EXT4_I(dir)->i_crypt_info;
+ if (ci) {
+ ret = ext4_fname_crypto_alloc_buffer(dir, iname->len,
+ &fname->crypto_buf);
+ if (ret < 0)
+ return ret;
+ ret = ext4_fname_encrypt(dir, iname, &fname->crypto_buf);
+ if (ret < 0)
+ goto errout;
+ fname->disk_name.name = fname->crypto_buf.name;
+ fname->disk_name.len = fname->crypto_buf.len;
+ return 0;
+ }
+ if (!lookup)
+ return -EACCES;
+
+ /* We don't have the key and we are doing a lookup; decode the
+ * user-supplied name
+ */
+ if (iname->name[0] == '_')
+ bigname = 1;
+ if ((bigname && (iname->len != 33)) ||
+ (!bigname && (iname->len > 43)))
+ return -ENOENT;
+
+ fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
+ if (fname->crypto_buf.name == NULL)
+ return -ENOMEM;
+ ret = digest_decode(iname->name + bigname, iname->len - bigname,
+ fname->crypto_buf.name);
+ if (ret < 0) {
+ ret = -ENOENT;
+ goto errout;
+ }
+ fname->crypto_buf.len = ret;
+ if (bigname) {
+ memcpy(&fname->hinfo.hash, fname->crypto_buf.name, 4);
+ memcpy(&fname->hinfo.minor_hash, fname->crypto_buf.name + 4, 4);
+ } else {
+ fname->disk_name.name = fname->crypto_buf.name;
+ fname->disk_name.len = fname->crypto_buf.len;
+ }
+ return 0;
+errout:
+ kfree(fname->crypto_buf.name);
+ fname->crypto_buf.name = NULL;
+ return ret;
+}
+
+void ext4_fname_free_filename(struct ext4_filename *fname)
+{
+ kfree(fname->crypto_buf.name);
+ fname->crypto_buf.name = NULL;
+ fname->usr_fname = NULL;
+ fname->disk_name.name = NULL;
+}
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
new file mode 100644
index 0000000..2cc4c80
--- /dev/null
+++ b/fs/ext4/crypto_key.c
@@ -0,0 +1,260 @@
+/*
+ * linux/fs/ext4/crypto_key.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions for ext4
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+ struct ext4_completion_result *ecr = req->data;
+
+ if (rc == -EINPROGRESS)
+ return;
+
+ ecr->res = rc;
+ complete(&ecr->completion);
+}
+
+/**
+ * ext4_derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivatio.
+ * @source_key: Source key to which to apply derivation.
+ * @derived_key: Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
+ char source_key[EXT4_AES_256_XTS_KEY_SIZE],
+ char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
+{
+ int res = 0;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_EXT4_COMPLETION_RESULT(ecr);
+ struct scatterlist src_sg, dst_sg;
+ struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
+ 0);
+
+ if (IS_ERR(tfm)) {
+ res = PTR_ERR(tfm);
+ tfm = NULL;
+ goto out;
+ }
+ crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ res = -ENOMEM;
+ goto out;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ derive_crypt_complete, &ecr);
+ res = crypto_ablkcipher_setkey(tfm, deriving_key,
+ EXT4_AES_128_ECB_KEY_SIZE);
+ if (res < 0)
+ goto out;
+ sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
+ sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+ EXT4_AES_256_XTS_KEY_SIZE, NULL);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+
+out:
+ if (req)
+ ablkcipher_request_free(req);
+ if (tfm)
+ crypto_free_ablkcipher(tfm);
+ return res;
+}
+
+void ext4_free_crypt_info(struct ext4_crypt_info *ci)
+{
+ if (!ci)
+ return;
+
+ if (ci->ci_keyring_key)
+ key_put(ci->ci_keyring_key);
+ crypto_free_ablkcipher(ci->ci_ctfm);
+ kmem_cache_free(ext4_crypt_info_cachep, ci);
+}
+
+void ext4_free_encryption_info(struct inode *inode,
+ struct ext4_crypt_info *ci)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_crypt_info *prev;
+
+ if (ci == NULL)
+ ci = ACCESS_ONCE(ei->i_crypt_info);
+ if (ci == NULL)
+ return;
+ prev = cmpxchg(&ei->i_crypt_info, ci, NULL);
+ if (prev != ci)
+ return;
+
+ ext4_free_crypt_info(ci);
+}
+
+int _ext4_get_encryption_info(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_crypt_info *crypt_info;
+ char full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+ (EXT4_KEY_DESCRIPTOR_SIZE * 2) + 1];
+ struct key *keyring_key = NULL;
+ struct ext4_encryption_key *master_key;
+ struct ext4_encryption_context ctx;
+ struct user_key_payload *ukp;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct crypto_ablkcipher *ctfm;
+ const char *cipher_str;
+ char raw_key[EXT4_MAX_KEY_SIZE];
+ char mode;
+ int res;
+
+ if (!ext4_read_workqueue) {
+ res = ext4_init_crypto();
+ if (res)
+ return res;
+ }
+
+retry:
+ crypt_info = ACCESS_ONCE(ei->i_crypt_info);
+ if (crypt_info) {
+ if (!crypt_info->ci_keyring_key ||
+ key_validate(crypt_info->ci_keyring_key) == 0)
+ return 0;
+ ext4_free_encryption_info(inode, crypt_info);
+ goto retry;
+ }
+
+ res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx));
+ if (res < 0) {
+ if (!DUMMY_ENCRYPTION_ENABLED(sbi))
+ return res;
+ ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
+ ctx.filenames_encryption_mode =
+ EXT4_ENCRYPTION_MODE_AES_256_CTS;
+ ctx.flags = 0;
+ } else if (res != sizeof(ctx))
+ return -EINVAL;
+ res = 0;
+
+ crypt_info = kmem_cache_alloc(ext4_crypt_info_cachep, GFP_KERNEL);
+ if (!crypt_info)
+ return -ENOMEM;
+
+ crypt_info->ci_flags = ctx.flags;
+ crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+ crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+ crypt_info->ci_ctfm = NULL;
+ crypt_info->ci_keyring_key = NULL;
+ memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+ sizeof(crypt_info->ci_master_key));
+ if (S_ISREG(inode->i_mode))
+ mode = crypt_info->ci_data_mode;
+ else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ mode = crypt_info->ci_filename_mode;
+ else
+ BUG();
+ switch (mode) {
+ case EXT4_ENCRYPTION_MODE_AES_256_XTS:
+ cipher_str = "xts(aes)";
+ break;
+ case EXT4_ENCRYPTION_MODE_AES_256_CTS:
+ cipher_str = "cts(cbc(aes))";
+ break;
+ default:
+ printk_once(KERN_WARNING
+ "ext4: unsupported key mode %d (ino %u)\n",
+ mode, (unsigned) inode->i_ino);
+ res = -ENOKEY;
+ goto out;
+ }
+ if (DUMMY_ENCRYPTION_ENABLED(sbi)) {
+ memset(raw_key, 0x42, EXT4_AES_256_XTS_KEY_SIZE);
+ goto got_key;
+ }
+ memcpy(full_key_descriptor, EXT4_KEY_DESC_PREFIX,
+ EXT4_KEY_DESC_PREFIX_SIZE);
+ sprintf(full_key_descriptor + EXT4_KEY_DESC_PREFIX_SIZE,
+ "%*phN", EXT4_KEY_DESCRIPTOR_SIZE,
+ ctx.master_key_descriptor);
+ full_key_descriptor[EXT4_KEY_DESC_PREFIX_SIZE +
+ (2 * EXT4_KEY_DESCRIPTOR_SIZE)] = '\0';
+ keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+ if (IS_ERR(keyring_key)) {
+ res = PTR_ERR(keyring_key);
+ keyring_key = NULL;
+ goto out;
+ }
+ crypt_info->ci_keyring_key = keyring_key;
+ BUG_ON(keyring_key->type != &key_type_logon);
+ ukp = ((struct user_key_payload *)keyring_key->payload.data);
+ if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
+ res = -EINVAL;
+ goto out;
+ }
+ master_key = (struct ext4_encryption_key *)ukp->data;
+ BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE !=
+ EXT4_KEY_DERIVATION_NONCE_SIZE);
+ BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE);
+ res = ext4_derive_key_aes(ctx.nonce, master_key->raw,
+ raw_key);
+got_key:
+ ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+ if (!ctfm || IS_ERR(ctfm)) {
+ res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+ printk(KERN_DEBUG
+ "%s: error %d (inode %u) allocating crypto tfm\n",
+ __func__, res, (unsigned) inode->i_ino);
+ goto out;
+ }
+ crypt_info->ci_ctfm = ctfm;
+ crypto_ablkcipher_clear_flags(ctfm, ~0);
+ crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+ CRYPTO_TFM_REQ_WEAK_KEY);
+ res = crypto_ablkcipher_setkey(ctfm, raw_key,
+ ext4_encryption_key_size(mode));
+ if (res)
+ goto out;
+ memset(raw_key, 0, sizeof(raw_key));
+ if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) != NULL) {
+ ext4_free_crypt_info(crypt_info);
+ goto retry;
+ }
+ return 0;
+
+out:
+ if (res == -ENOKEY)
+ res = 0;
+ ext4_free_crypt_info(crypt_info);
+ memset(raw_key, 0, sizeof(raw_key));
+ return res;
+}
+
+int ext4_has_encryption_key(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ return (ei->i_crypt_info != NULL);
+}
diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c
new file mode 100644
index 0000000..02c4e5d
--- /dev/null
+++ b/fs/ext4/crypto_policy.c
@@ -0,0 +1,215 @@
+/*
+ * linux/fs/ext4/crypto_policy.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption policy functions for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "ext4.h"
+#include "xattr.h"
+
+static int ext4_inode_has_encryption_context(struct inode *inode)
+{
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0);
+ return (res > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int ext4_is_encryption_context_consistent_with_policy(
+ struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx));
+ if (res != sizeof(ctx))
+ return 0;
+ return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (ctx.flags ==
+ policy->flags) &&
+ (ctx.contents_encryption_mode ==
+ policy->contents_encryption_mode) &&
+ (ctx.filenames_encryption_mode ==
+ policy->filenames_encryption_mode));
+}
+
+static int ext4_create_encryption_context_from_policy(
+ struct inode *inode, const struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+ int res = 0;
+
+ res = ext4_convert_inline_data(inode);
+ if (res)
+ return res;
+
+ ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+ memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid contents encryption mode %d\n", __func__,
+ policy->contents_encryption_mode);
+ return -EINVAL;
+ }
+ if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid filenames encryption mode %d\n", __func__,
+ policy->filenames_encryption_mode);
+ return -EINVAL;
+ }
+ if (policy->flags & ~EXT4_POLICY_FLAGS_VALID)
+ return -EINVAL;
+ ctx.contents_encryption_mode = policy->contents_encryption_mode;
+ ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+ ctx.flags = policy->flags;
+ BUILD_BUG_ON(sizeof(ctx.nonce) != EXT4_KEY_DERIVATION_NONCE_SIZE);
+ get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+
+ res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), 0);
+ if (!res)
+ ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+ return res;
+}
+
+int ext4_process_policy(const struct ext4_encryption_policy *policy,
+ struct inode *inode)
+{
+ if (policy->version != 0)
+ return -EINVAL;
+
+ if (!ext4_inode_has_encryption_context(inode)) {
+ if (!S_ISDIR(inode->i_mode))
+ return -EINVAL;
+ if (!ext4_empty_dir(inode))
+ return -ENOTEMPTY;
+ return ext4_create_encryption_context_from_policy(inode,
+ policy);
+ }
+
+ if (ext4_is_encryption_context_consistent_with_policy(inode, policy))
+ return 0;
+
+ printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+ __func__);
+ return -EINVAL;
+}
+
+int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
+{
+ struct ext4_encryption_context ctx;
+
+ int res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx));
+ if (res != sizeof(ctx))
+ return -ENOENT;
+ if (ctx.format != EXT4_ENCRYPTION_CONTEXT_FORMAT_V1)
+ return -EINVAL;
+ policy->version = 0;
+ policy->contents_encryption_mode = ctx.contents_encryption_mode;
+ policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+ policy->flags = ctx.flags;
+ memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ return 0;
+}
+
+int ext4_is_child_context_consistent_with_parent(struct inode *parent,
+ struct inode *child)
+{
+ struct ext4_crypt_info *parent_ci, *child_ci;
+ int res;
+
+ if ((parent == NULL) || (child == NULL)) {
+ pr_err("parent %p child %p\n", parent, child);
+ BUG_ON(1);
+ }
+ /* no restrictions if the parent directory is not encrypted */
+ if (!ext4_encrypted_inode(parent))
+ return 1;
+ /* if the child directory is not encrypted, this is always a problem */
+ if (!ext4_encrypted_inode(child))
+ return 0;
+ res = ext4_get_encryption_info(parent);
+ if (res)
+ return 0;
+ res = ext4_get_encryption_info(child);
+ if (res)
+ return 0;
+ parent_ci = EXT4_I(parent)->i_crypt_info;
+ child_ci = EXT4_I(child)->i_crypt_info;
+ if (!parent_ci && !child_ci)
+ return 1;
+ if (!parent_ci || !child_ci)
+ return 0;
+
+ return (memcmp(parent_ci->ci_master_key,
+ child_ci->ci_master_key,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+ (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+ (parent_ci->ci_flags == child_ci->ci_flags));
+}
+
+/**
+ * ext4_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child: Child inode that inherits the context from @parent.
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int ext4_inherit_context(struct inode *parent, struct inode *child)
+{
+ struct ext4_encryption_context ctx;
+ struct ext4_crypt_info *ci;
+ int res;
+
+ res = ext4_get_encryption_info(parent);
+ if (res < 0)
+ return res;
+ ci = EXT4_I(parent)->i_crypt_info;
+ if (ci == NULL)
+ return -ENOKEY;
+
+ ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1;
+ if (DUMMY_ENCRYPTION_ENABLED(EXT4_SB(parent->i_sb))) {
+ ctx.contents_encryption_mode = EXT4_ENCRYPTION_MODE_AES_256_XTS;
+ ctx.filenames_encryption_mode =
+ EXT4_ENCRYPTION_MODE_AES_256_CTS;
+ ctx.flags = 0;
+ memset(ctx.master_key_descriptor, 0x42,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ res = 0;
+ } else {
+ ctx.contents_encryption_mode = ci->ci_data_mode;
+ ctx.filenames_encryption_mode = ci->ci_filename_mode;
+ ctx.flags = ci->ci_flags;
+ memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+ EXT4_KEY_DESCRIPTOR_SIZE);
+ }
+ get_random_bytes(ctx.nonce, EXT4_KEY_DERIVATION_NONCE_SIZE);
+ res = ext4_xattr_set(child, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), 0);
+ if (!res) {
+ ext4_set_inode_flag(child, EXT4_INODE_ENCRYPT);
+ ext4_clear_inode_state(child, EXT4_STATE_MAY_INLINE_DATA);
+ res = ext4_get_encryption_info(child);
+ }
+ return res;
+}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index f8d56e4..2d3e900 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -29,12 +29,11 @@
#include "ext4.h"
#include "xattr.h"
-static int ext4_dx_readdir(struct file *filp,
- void *dirent, filldir_t filldir);
+static int ext4_dx_readdir(struct file *, struct dir_context *);
/**
* Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
* indexing).
*
* Return 1 if it is a dx dir, 0 if not
@@ -103,79 +102,80 @@
return 1;
}
-static int ext4_readdir(struct file *filp,
- void *dirent, filldir_t filldir)
+static int ext4_readdir(struct file *file, struct dir_context *ctx)
{
- int error = 0;
unsigned int offset;
- int i, stored;
+ int i;
struct ext4_dir_entry_2 *de;
int err;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
- int ret = 0;
+ struct buffer_head *bh = NULL;
int dir_has_error = 0;
+ struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
if (is_dx_dir(inode)) {
- err = ext4_dx_readdir(filp, dirent, filldir);
+ err = ext4_dx_readdir(file, ctx);
if (err != ERR_BAD_DX_DIR) {
- ret = err;
- goto out;
+ return err;
}
/*
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- ext4_clear_inode_flag(file_inode(filp),
+ ext4_clear_inode_flag(file_inode(file),
EXT4_INODE_INDEX);
}
if (ext4_has_inline_data(inode)) {
int has_inline_data = 1;
- ret = ext4_read_inline_dir(filp, dirent, filldir,
+ err = ext4_read_inline_dir(file, ctx,
&has_inline_data);
if (has_inline_data)
- return ret;
+ return err;
}
- stored = 0;
- offset = filp->f_pos & (sb->s_blocksize - 1);
+ if (ext4_encrypted_inode(inode)) {
+ err = ext4_fname_crypto_alloc_buffer(inode, EXT4_NAME_LEN,
+ &fname_crypto_str);
+ if (err < 0)
+ return err;
+ }
- while (!error && !stored && filp->f_pos < inode->i_size) {
+ offset = ctx->pos & (sb->s_blocksize - 1);
+
+ while (ctx->pos < inode->i_size) {
struct ext4_map_blocks map;
- struct buffer_head *bh = NULL;
- map.m_lblk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
+ map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
map.m_len = 1;
err = ext4_map_blocks(NULL, inode, &map, 0);
if (err > 0) {
pgoff_t index = map.m_pblk >>
(PAGE_CACHE_SHIFT - inode->i_blkbits);
- if (!ra_has_index(&filp->f_ra, index))
+ if (!ra_has_index(&file->f_ra, index))
page_cache_sync_readahead(
sb->s_bdev->bd_inode->i_mapping,
- &filp->f_ra, filp,
+ &file->f_ra, file,
index, 1);
- filp->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
- bh = ext4_bread(NULL, inode, map.m_lblk, 0, &err);
+ file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
+ bh = ext4_bread(NULL, inode, map.m_lblk, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
}
- /*
- * We ignore I/O errors on directories so users have a chance
- * of recovering data when there's a bad sector
- */
if (!bh) {
if (!dir_has_error) {
- EXT4_ERROR_FILE(filp, 0,
+ EXT4_ERROR_FILE(file, 0,
"directory contains a "
"hole at offset %llu",
- (unsigned long long) filp->f_pos);
+ (unsigned long long) ctx->pos);
dir_has_error = 1;
}
/* corrupt size? Maybe no more blocks to read */
- if (filp->f_pos > inode->i_blocks << 9)
+ if (ctx->pos > inode->i_blocks << 9)
break;
- filp->f_pos += sb->s_blocksize - offset;
+ ctx->pos += sb->s_blocksize - offset;
continue;
}
@@ -183,21 +183,21 @@
if (!buffer_verified(bh) &&
!ext4_dirent_csum_verify(inode,
(struct ext4_dir_entry *)bh->b_data)) {
- EXT4_ERROR_FILE(filp, 0, "directory fails checksum "
+ EXT4_ERROR_FILE(file, 0, "directory fails checksum "
"at offset %llu",
- (unsigned long long)filp->f_pos);
- filp->f_pos += sb->s_blocksize - offset;
+ (unsigned long long)ctx->pos);
+ ctx->pos += sb->s_blocksize - offset;
brelse(bh);
+ bh = NULL;
continue;
}
set_buffer_verified(bh);
-revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
- if (filp->f_version != inode->i_version) {
+ if (file->f_version != inode->i_version) {
for (i = 0; i < sb->s_blocksize && i < offset; ) {
de = (struct ext4_dir_entry_2 *)
(bh->b_data + i);
@@ -214,57 +214,66 @@
sb->s_blocksize);
}
offset = i;
- filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+ ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
| offset;
- filp->f_version = inode->i_version;
+ file->f_version = inode->i_version;
}
- while (!error && filp->f_pos < inode->i_size
+ while (ctx->pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
- if (ext4_check_dir_entry(inode, filp, de, bh,
+ if (ext4_check_dir_entry(inode, file, de, bh,
bh->b_data, bh->b_size,
offset)) {
/*
- * On error, skip the f_pos to the next block
+ * On error, skip to the next block
*/
- filp->f_pos = (filp->f_pos |
+ ctx->pos = (ctx->pos |
(sb->s_blocksize - 1)) + 1;
- brelse(bh);
- ret = stored;
- goto out;
+ break;
}
offset += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
if (le32_to_cpu(de->inode)) {
- /* We might block in the next section
- * if the data destination is
- * currently swapped out. So, use a
- * version stamp to detect whether or
- * not the directory has been modified
- * during the copy operation.
- */
- u64 version = filp->f_version;
+ if (!ext4_encrypted_inode(inode)) {
+ if (!dir_emit(ctx, de->name,
+ de->name_len,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type)))
+ goto done;
+ } else {
+ int save_len = fname_crypto_str.len;
- error = filldir(dirent, de->name,
- de->name_len,
- filp->f_pos,
- le32_to_cpu(de->inode),
- get_dtype(sb, de->file_type));
- if (error)
- break;
- if (version != filp->f_version)
- goto revalidate;
- stored++;
+ /* Directory is encrypted */
+ err = ext4_fname_disk_to_usr(inode,
+ NULL, de, &fname_crypto_str);
+ fname_crypto_str.len = save_len;
+ if (err < 0)
+ goto errout;
+ if (!dir_emit(ctx,
+ fname_crypto_str.name, err,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type)))
+ goto done;
+ }
}
- filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
+ ctx->pos += ext4_rec_len_from_disk(de->rec_len,
sb->s_blocksize);
}
- offset = 0;
+ if ((ctx->pos < inode->i_size) && !dir_relax(inode))
+ goto done;
brelse(bh);
+ bh = NULL;
+ offset = 0;
}
-out:
- return ret;
+done:
+ err = 0;
+errout:
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ ext4_fname_crypto_free_buffer(&fname_crypto_str);
+#endif
+ brelse(bh);
+ return err;
}
static inline int is_32bit_api(void)
@@ -370,41 +379,16 @@
*/
static void free_rb_tree_fname(struct rb_root *root)
{
- struct rb_node *n = root->rb_node;
- struct rb_node *parent;
- struct fname *fname;
+ struct fname *fname, *next;
- while (n) {
- /* Do the node's children first */
- if (n->rb_left) {
- n = n->rb_left;
- continue;
- }
- if (n->rb_right) {
- n = n->rb_right;
- continue;
- }
- /*
- * The node has no children; free it, and then zero
- * out parent's link to it. Finally go to the
- * beginning of the loop and try to free the parent
- * node.
- */
- parent = rb_parent(n);
- fname = rb_entry(n, struct fname, rb_hash);
+ rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash)
while (fname) {
struct fname *old = fname;
fname = fname->next;
kfree(old);
}
- if (!parent)
- *root = RB_ROOT;
- else if (parent->rb_left == n)
- parent->rb_left = NULL;
- else if (parent->rb_right == n)
- parent->rb_right = NULL;
- n = parent;
- }
+
+ *root = RB_ROOT;
}
@@ -429,10 +413,15 @@
/*
* Given a directory entry, enter it into the fname rb tree.
+ *
+ * When filename encryption is enabled, the dirent will hold the
+ * encrypted filename, while the htree will hold decrypted filename.
+ * The decrypted filename is passed in via ent_name. parameter.
*/
int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
- struct ext4_dir_entry_2 *dirent)
+ struct ext4_dir_entry_2 *dirent,
+ struct ext4_str *ent_name)
{
struct rb_node **p, *parent = NULL;
struct fname *fname, *new_fn;
@@ -443,17 +432,17 @@
p = &info->root.rb_node;
/* Create and allocate the fname structure */
- len = sizeof(struct fname) + dirent->name_len + 1;
+ len = sizeof(struct fname) + ent_name->len + 1;
new_fn = kzalloc(len, GFP_KERNEL);
if (!new_fn)
return -ENOMEM;
new_fn->hash = hash;
new_fn->minor_hash = minor_hash;
new_fn->inode = le32_to_cpu(dirent->inode);
- new_fn->name_len = dirent->name_len;
+ new_fn->name_len = ent_name->len;
new_fn->file_type = dirent->file_type;
- memcpy(new_fn->name, dirent->name, dirent->name_len);
- new_fn->name[dirent->name_len] = 0;
+ memcpy(new_fn->name, ent_name->name, ent_name->len);
+ new_fn->name[ent_name->len] = 0;
while (*p) {
parent = *p;
@@ -492,16 +481,12 @@
* for all entres on the fname linked list. (Normally there is only
* one entry on the linked list, unless there are 62 bit hash collisions.)
*/
-static int call_filldir(struct file *filp, void *dirent,
- filldir_t filldir, struct fname *fname)
+static int call_filldir(struct file *file, struct dir_context *ctx,
+ struct fname *fname)
{
- struct dir_private_info *info = filp->private_data;
- loff_t curr_pos;
- struct inode *inode = file_inode(filp);
- struct super_block *sb;
- int error;
-
- sb = inode->i_sb;
+ struct dir_private_info *info = file->private_data;
+ struct inode *inode = file_inode(file);
+ struct super_block *sb = inode->i_sb;
if (!fname) {
ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: "
@@ -509,47 +494,44 @@
inode->i_ino, current->comm);
return 0;
}
- curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
+ ctx->pos = hash2pos(file, fname->hash, fname->minor_hash);
while (fname) {
- error = filldir(dirent, fname->name,
- fname->name_len, curr_pos,
+ if (!dir_emit(ctx, fname->name,
+ fname->name_len,
fname->inode,
- get_dtype(sb, fname->file_type));
- if (error) {
- filp->f_pos = curr_pos;
+ get_dtype(sb, fname->file_type))) {
info->extra_fname = fname;
- return error;
+ return 1;
}
fname = fname->next;
}
return 0;
}
-static int ext4_dx_readdir(struct file *filp,
- void *dirent, filldir_t filldir)
+static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
{
- struct dir_private_info *info = filp->private_data;
- struct inode *inode = file_inode(filp);
+ struct dir_private_info *info = file->private_data;
+ struct inode *inode = file_inode(file);
struct fname *fname;
int ret;
if (!info) {
- info = ext4_htree_create_dir_info(filp, filp->f_pos);
+ info = ext4_htree_create_dir_info(file, ctx->pos);
if (!info)
return -ENOMEM;
- filp->private_data = info;
+ file->private_data = info;
}
- if (filp->f_pos == ext4_get_htree_eof(filp))
+ if (ctx->pos == ext4_get_htree_eof(file))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
- if (info->last_pos != filp->f_pos) {
+ if (info->last_pos != ctx->pos) {
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp, filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
+ info->curr_hash = pos2maj_hash(file, ctx->pos);
+ info->curr_minor_hash = pos2min_hash(file, ctx->pos);
}
/*
@@ -557,7 +539,7 @@
* chain, return them first.
*/
if (info->extra_fname) {
- if (call_filldir(filp, dirent, filldir, info->extra_fname))
+ if (call_filldir(file, ctx, info->extra_fname))
goto finished;
info->extra_fname = NULL;
goto next_node;
@@ -571,17 +553,17 @@
* cached entries.
*/
if ((!info->curr_node) ||
- (filp->f_version != inode->i_version)) {
+ (file->f_version != inode->i_version)) {
info->curr_node = NULL;
free_rb_tree_fname(&info->root);
- filp->f_version = inode->i_version;
- ret = ext4_htree_fill_tree(filp, info->curr_hash,
+ file->f_version = inode->i_version;
+ ret = ext4_htree_fill_tree(file, info->curr_hash,
info->curr_minor_hash,
&info->next_hash);
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = ext4_get_htree_eof(filp);
+ ctx->pos = ext4_get_htree_eof(file);
break;
}
info->curr_node = rb_first(&info->root);
@@ -590,7 +572,7 @@
fname = rb_entry(info->curr_node, struct fname, rb_hash);
info->curr_hash = fname->hash;
info->curr_minor_hash = fname->minor_hash;
- if (call_filldir(filp, dirent, filldir, fname))
+ if (call_filldir(file, ctx, fname))
break;
next_node:
info->curr_node = rb_next(info->curr_node);
@@ -601,7 +583,7 @@
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = ext4_get_htree_eof(filp);
+ ctx->pos = ext4_get_htree_eof(file);
break;
}
info->curr_hash = info->next_hash;
@@ -609,7 +591,14 @@
}
}
finished:
- info->last_pos = filp->f_pos;
+ info->last_pos = ctx->pos;
+ return 0;
+}
+
+static int ext4_dir_open(struct inode * inode, struct file * filp)
+{
+ if (ext4_encrypted_inode(inode))
+ return ext4_get_encryption_info(inode) ? -EACCES : 0;
return 0;
}
@@ -621,14 +610,40 @@
return 0;
}
+int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
+ int buf_size)
+{
+ struct ext4_dir_entry_2 *de;
+ int nlen, rlen;
+ unsigned int offset = 0;
+ char *top;
+
+ de = (struct ext4_dir_entry_2 *)buf;
+ top = buf + buf_size;
+ while ((char *) de < top) {
+ if (ext4_check_dir_entry(dir, NULL, de, bh,
+ buf, buf_size, offset))
+ return -EIO;
+ nlen = EXT4_DIR_REC_LEN(de->name_len);
+ rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
+ de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
+ offset += rlen;
+ }
+ if ((char *) de > top)
+ return -EIO;
+
+ return 0;
+}
+
const struct file_operations ext4_dir_operations = {
.llseek = ext4_dir_llseek,
.read = generic_read_dir,
- .readdir = ext4_readdir,
+ .iterate = ext4_readdir,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
#endif
.fsync = ext4_sync_file,
+ .open = ext4_dir_open,
.release = ext4_release_dir,
};
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 046e3e9..9c3cc32 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -30,7 +30,9 @@
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
+#include <linux/ratelimit.h>
#include <crypto/hash.h>
+#include <linux/falloc.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
@@ -157,7 +159,6 @@
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
-#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
@@ -168,7 +169,7 @@
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
+ EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -178,38 +179,25 @@
};
/*
- * For delayed allocation tracking
- */
-struct mpage_da_data {
- struct inode *inode;
- sector_t b_blocknr; /* start block number of extent */
- size_t b_size; /* size of extent */
- unsigned long b_state; /* state of the extent */
- unsigned long first_page, next_page; /* extent of pages */
- struct writeback_control *wbc;
- int io_done;
- int pages_written;
- int retval;
-};
-
-/*
* Flags for ext4_io_end->flags
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
-#define EXT4_IO_END_ERROR 0x0002
-#define EXT4_IO_END_DIRECT 0x0004
/*
- * For converting uninitialized extents on a work queue.
+ * For converting unwritten extents on a work queue. 'handle' is used for
+ * buffered writeback.
*/
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
+ handle_t *handle; /* handle reserved for extent
+ * conversion */
struct inode *inode; /* file being written to */
+ struct bio *bio; /* Linked list of completed
+ * bios covering the extent */
unsigned int flag; /* unwritten or not */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
- struct kiocb *iocb; /* iocb struct for AIO */
- int result; /* error value for AIO */
+ atomic_t count; /* reference counter */
} ext4_io_end_t;
struct ext4_io_submit {
@@ -386,7 +374,8 @@
#define EXT4_DIRTY_FL 0x00000100
#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */
-#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */
+ /* nb: was previously EXT2_ECOMPR_FL */
+#define EXT4_ENCRYPT_FL 0x00000800 /* encrypted file */
/* End compression flags --- maybe not all used */
#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */
#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */
@@ -443,7 +432,7 @@
EXT4_INODE_DIRTY = 8,
EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
EXT4_INODE_NOCOMPR = 10, /* Don't compress */
- EXT4_INODE_ECOMPR = 11, /* Compression error */
+ EXT4_INODE_ENCRYPT = 11, /* Encrypted file */
/* End compression flags --- maybe not all used */
EXT4_INODE_INDEX = 12, /* hash-indexed directory */
EXT4_INODE_IMAGIC = 13, /* AFS directory */
@@ -488,7 +477,7 @@
CHECK_FLAG_VALUE(DIRTY);
CHECK_FLAG_VALUE(COMPRBLK);
CHECK_FLAG_VALUE(NOCOMPR);
- CHECK_FLAG_VALUE(ECOMPR);
+ CHECK_FLAG_VALUE(ENCRYPT);
CHECK_FLAG_VALUE(INDEX);
CHECK_FLAG_VALUE(IMAGIC);
CHECK_FLAG_VALUE(JOURNAL_DATA);
@@ -549,26 +538,26 @@
/*
* Flags used by ext4_map_blocks()
*/
- /* Allocate any needed blocks and/or convert an unitialized
+ /* Allocate any needed blocks and/or convert an unwritten
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
- /* Request the creation of an unitialized extent */
-#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
-#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
+ /* Request the creation of an unwritten extent */
+#define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
- unitialized extents if not allocated, split the uninitialized
+ unwritten extents if not allocated, split the unwritten
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Eventual metadata allocation (due to growing extent tree)
* should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
@@ -580,6 +569,20 @@
#define EXT4_GET_BLOCKS_NO_LOCK 0x0100
/* Do not put hole in extent cache */
#define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200
+ /* Convert written extents to unwritten */
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0400
+
+/*
+ * The bit position of these flags must not overlap with any of the
+ * EXT4_GET_BLOCKS_*. They are used by ext4_find_extent(),
+ * read_extent_tree_block(), ext4_split_extent_at(),
+ * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
+ * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
+ * caching the extents when reading from the extent tree while a
+ * truncate or punch hole operation is in progress.
+ */
+#define EXT4_EX_NOCACHE 0x40000000
+#define EXT4_EX_FORCE_CACHE 0x20000000
/*
* Flags used by ext4_free_blocks
@@ -590,12 +593,15 @@
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
-#define EXT4_FREE_BLOCKS_RESERVE 0x0040
-/*
- * Flags used by ext4_discard_partial_page_buffers
- */
-#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
+/* Encryption algorithms */
+#define EXT4_ENCRYPTION_MODE_INVALID 0
+#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1
+#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2
+#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3
+#define EXT4_ENCRYPTION_MODE_AES_256_CTS 4
+
+#include "ext4_crypto.h"
/*
* ioctl commands
@@ -617,6 +623,10 @@
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)
#define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64)
#define EXT4_IOC_SWAP_BOOT _IO('f', 17)
+#define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18)
+#define EXT4_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct ext4_encryption_policy)
+#define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
+#define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -937,6 +947,8 @@
struct inode vfs_inode;
struct jbd2_inode *jinode;
+ spinlock_t i_raw_lock; /* protects updates to the raw inode */
+
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
@@ -951,7 +963,9 @@
struct ext4_es_tree i_es_tree;
rwlock_t i_es_lock;
struct list_head i_es_lru;
+ unsigned int i_es_all_nr; /* protected by i_es_lock */
unsigned int i_es_lru_nr; /* protected by i_es_lock */
+ unsigned long i_touch_when; /* jiffies of last accessing */
/* ialloc */
ext4_group_t i_last_alloc_group;
@@ -976,12 +990,20 @@
qsize_t i_reserved_quota;
#endif
- /* completed IOs that might need unwritten extents handling */
- struct list_head i_completed_io_list;
+ /* Lock protecting lists below */
spinlock_t i_completed_io_lock;
+ /*
+ * Completed IOs that need unwritten extents handling and have
+ * transaction reserved
+ */
+ struct list_head i_rsv_conversion_list;
+ /*
+ * Completed IOs that need unwritten extents handling and don't have
+ * transaction reserved
+ */
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
atomic_t i_unwritten; /* Nr. of inflight conversions pending */
- struct work_struct i_unwritten_work; /* deferred extent conversion */
+ struct work_struct i_rsv_conversion_work;
spinlock_t i_block_reservation_lock;
@@ -994,6 +1016,11 @@
/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
__u32 i_csum_seed;
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ /* Encryption params */
+ struct ext4_crypt_info *i_crypt_info;
+#endif
};
/*
@@ -1053,6 +1080,8 @@
#define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group
size of blocksize * 8
blocks */
+#define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated
+ file systems */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
@@ -1184,7 +1213,8 @@
__le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
__u8 s_log_groups_per_flex; /* FLEX_BG group size */
__u8 s_checksum_type; /* metadata checksum algorithm used */
- __le16 s_reserved_pad;
+ __u8 s_encryption_level; /* versioning level for encryption */
+ __u8 s_reserved_pad; /* Padding to next 32bits */
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
__le32 s_snapshot_inum; /* Inode number of active snapshot */
__le32 s_snapshot_id; /* sequential ID of active snapshot */
@@ -1209,7 +1239,11 @@
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
- __le32 s_reserved[108]; /* Padding to the end of the block */
+ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
+ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */
+ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
+ __le32 s_lpf_ino; /* Location of the lost+found inode */
+ __le32 s_reserved[100]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
@@ -1220,8 +1254,19 @@
/*
* run-time mount flags
*/
-#define EXT4_MF_MNTDIR_SAMPLED 0x0001
-#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
+#define EXT4_MF_MNTDIR_SAMPLED 0x0001
+#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
+#define EXT4_MF_TEST_DUMMY_ENCRYPTION 0x0004
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \
+ EXT4_MF_TEST_DUMMY_ENCRYPTION))
+#else
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
+#endif
+
+/* Number of quota types we support */
+#define EXT4_MAXQUOTAS 2
/*
* fourth extended-fs super-block data in memory
@@ -1286,7 +1331,7 @@
u32 s_min_batch_time;
struct block_device *journal_bdev;
#ifdef CONFIG_QUOTA
- char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
+ char *s_qf_names[EXT4_MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
#endif
unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
@@ -1318,7 +1363,6 @@
unsigned int s_mb_stats;
unsigned int s_mb_order2_reqs;
unsigned int s_mb_group_prealloc;
- unsigned int s_max_writeback_mb_bump;
unsigned int s_max_dir_size_kb;
/* where last allocation was done - for stream allocation */
unsigned long s_mb_last_group;
@@ -1354,8 +1398,8 @@
struct flex_groups *s_flex_groups;
ext4_group_t s_flex_groups_allocated;
- /* workqueue for dio unwritten */
- struct workqueue_struct *dio_unwritten_wq;
+ /* workqueue for reserved extent conversions (buffered io) */
+ struct workqueue_struct *rsv_conversion_wq;
/* timer for periodic error stats printing */
struct timer_list s_err_report;
@@ -1380,8 +1424,14 @@
/* Reclaim extents from extent status tree */
struct shrinker s_es_shrinker;
struct list_head s_es_lru;
- struct percpu_counter s_extent_cache_cnt;
+ struct ext4_es_stats s_es_stats;
+ struct mb_cache *s_mb_cache;
spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
+
+ /* Ratelimit ext4 messages. */
+ struct ratelimit_state s_err_ratelimit_state;
+ struct ratelimit_state s_warning_ratelimit_state;
+ struct ratelimit_state s_msg_ratelimit_state;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1442,11 +1492,11 @@
EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
EXT4_STATE_NEWENTRY, /* File just added to dir */
- EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */
EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read
nolocking */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
EXT4_STATE_ORDERED_MODE, /* data=ordered mode */
+ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
@@ -1463,7 +1513,18 @@
clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
}
+/* Add these declarations here only so that these functions can be
+ * found by name. Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_flag(struct inode *inode, int bit);
+static inline void ext4_set_inode_flag(struct inode *inode, int bit);
+static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
EXT4_INODE_BIT_FNS(flag, flags, 0)
+
+/* Add these declarations here only so that these functions can be
+ * found by name. Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_state(struct inode *inode, int bit);
+static inline void ext4_set_inode_state(struct inode *inode, int bit);
+static inline void ext4_clear_inode_state(struct inode *inode, int bit);
#if (BITS_PER_LONG < 64)
EXT4_INODE_BIT_FNS(state, state_flags, 0)
@@ -1486,6 +1547,18 @@
#define EXT4_SB(sb) (sb)
#endif
+/*
+ * Returns true if the inode is inode is encrypted
+ */
+static inline int ext4_encrypted_inode(struct inode *inode)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
+#else
+ return 0;
+#endif
+}
+
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
/*
@@ -1537,6 +1610,7 @@
#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
@@ -1569,6 +1643,7 @@
#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000
#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1592,8 +1667,9 @@
EXT4_FEATURE_INCOMPAT_EXTENTS| \
EXT4_FEATURE_INCOMPAT_64BIT| \
EXT4_FEATURE_INCOMPAT_FLEX_BG| \
- EXT4_FEATURE_INCOMPAT_MMP | \
- EXT4_FEATURE_INCOMPAT_INLINE_DATA)
+ EXT4_FEATURE_INCOMPAT_MMP | \
+ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
+ EXT4_FEATURE_INCOMPAT_ENCRYPT)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -1813,6 +1889,17 @@
*/
#define HASH_NB_ALWAYS 1
+struct ext4_filename {
+ const struct qstr *usr_fname;
+ struct ext4_str disk_name;
+ struct dx_hash_info hinfo;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ struct ext4_str crypto_buf;
+#endif
+};
+
+#define fname_name(p) ((p)->disk_name.name)
+#define fname_len(p) ((p)->disk_name.len)
/*
* Describe an inode's exact location on disk and in memory
@@ -1855,7 +1942,7 @@
/*
* Special error return code only used by dx_probe() and its callers.
*/
-#define ERR_BAD_DX_DIR -75000
+#define ERR_BAD_DX_DIR (-(MAX_ERRNO - 1))
/*
* Timeout and state flag for lazy initialization inode thread.
@@ -1985,10 +2072,6 @@
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_fsblk_t block);
-extern void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- unsigned int block_group,
- struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
@@ -2017,18 +2100,135 @@
struct buffer_head *bh);
extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
-extern void ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
-extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
+/* crypto_policy.c */
+int ext4_is_child_context_consistent_with_parent(struct inode *parent,
+ struct inode *child);
+int ext4_inherit_context(struct inode *parent, struct inode *child);
+void ext4_to_hex(char *dst, char *src, size_t src_size);
+int ext4_process_policy(const struct ext4_encryption_policy *policy,
+ struct inode *inode);
+int ext4_get_policy(struct inode *inode,
+ struct ext4_encryption_policy *policy);
+
+/* crypto.c */
+extern struct kmem_cache *ext4_crypt_info_cachep;
+bool ext4_valid_contents_enc_mode(uint32_t mode);
+uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
+extern struct workqueue_struct *ext4_read_workqueue;
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode);
+void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
+void ext4_restore_control_page(struct page *data_page);
+struct page *ext4_encrypt(struct inode *inode,
+ struct page *plaintext_page);
+int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page);
+int ext4_decrypt_one(struct inode *inode, struct page *page);
+int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+int ext4_init_crypto(void);
+void ext4_exit_crypto(void);
+static inline int ext4_sb_has_crypto(struct super_block *sb)
+{
+ return EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT);
+}
+#else
+static inline int ext4_init_crypto(void) { return 0; }
+static inline void ext4_exit_crypto(void) { }
+static inline int ext4_sb_has_crypto(struct super_block *sb)
+{
+ return 0;
+}
+#endif
+
+/* crypto_fname.c */
+bool ext4_valid_filenames_enc_mode(uint32_t mode);
+u32 ext4_fname_crypto_round_up(u32 size, u32 blksize);
+unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen);
+int ext4_fname_crypto_alloc_buffer(struct inode *inode,
+ u32 ilen, struct ext4_str *crypto_str);
+int _ext4_fname_disk_to_usr(struct inode *inode,
+ struct dx_hash_info *hinfo,
+ const struct ext4_str *iname,
+ struct ext4_str *oname);
+int ext4_fname_disk_to_usr(struct inode *inode,
+ struct dx_hash_info *hinfo,
+ const struct ext4_dir_entry_2 *de,
+ struct ext4_str *oname);
+int ext4_fname_usr_to_disk(struct inode *inode,
+ const struct qstr *iname,
+ struct ext4_str *oname);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str);
+int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct ext4_filename *fname);
+void ext4_fname_free_filename(struct ext4_filename *fname);
+#else
+static inline
+int ext4_setup_fname_crypto(struct inode *inode)
+{
+ return 0;
+}
+static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { }
+static inline int ext4_fname_setup_filename(struct inode *dir,
+ const struct qstr *iname,
+ int lookup, struct ext4_filename *fname)
+{
+ fname->usr_fname = iname;
+ fname->disk_name.name = (unsigned char *) iname->name;
+ fname->disk_name.len = iname->len;
+ return 0;
+}
+static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
+#endif
+
+
+/* crypto_key.c */
+void ext4_free_crypt_info(struct ext4_crypt_info *ci);
+void ext4_free_encryption_info(struct inode *inode, struct ext4_crypt_info *ci);
+int _ext4_get_encryption_info(struct inode *inode);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+int ext4_has_encryption_key(struct inode *inode);
+
+static inline int ext4_get_encryption_info(struct inode *inode)
+{
+ struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
+
+ if (!ci ||
+ (ci->ci_keyring_key &&
+ (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED) |
+ (1 << KEY_FLAG_DEAD)))))
+ return _ext4_get_encryption_info(inode);
+ return 0;
+}
+
+static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
+{
+ return EXT4_I(inode)->i_crypt_info;
+}
+
+#else
+static inline int ext4_has_encryption_key(struct inode *inode)
+{
+ return 0;
+}
+static inline int ext4_get_encryption_info(struct inode *inode)
+{
+ return 0;
+}
+static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
+{
+ return NULL;
+}
+#endif
+
+
/* dir.c */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
struct file *,
@@ -2039,18 +2239,20 @@
unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
(de), (bh), (buf), (size), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
- __u32 minor_hash,
- struct ext4_dir_entry_2 *dirent);
+ __u32 minor_hash,
+ struct ext4_dir_entry_2 *dirent,
+ struct ext4_str *ent_name);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
struct buffer_head *bh,
void *buf, int buf_size,
- const char *name, int namelen,
+ struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de);
-void ext4_insert_dentry(struct inode *inode,
- struct ext4_dir_entry_2 *de,
- int buf_size,
- const char *name, int namelen);
+int ext4_insert_dentry(struct inode *dir,
+ struct inode *inode,
+ struct ext4_dir_entry_2 *de,
+ int buf_size,
+ struct ext4_filename *fname);
static inline void ext4_update_dx_flag(struct inode *inode)
{
if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
@@ -2069,10 +2271,11 @@
return ext4_filetype_table[filetype];
}
+extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
+ void *buf, int buf_size);
/* fsync.c */
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
-extern int ext4_flush_unwritten_io(struct inode *);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
@@ -2123,13 +2326,13 @@
ext4_group_t i, struct ext4_group_desc *desc);
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count);
-extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *,
+ unsigned long blkdev_flags);
/* inode.c */
-struct buffer_head *ext4_getblk(handle_t *, struct inode *,
- ext4_lblk_t, int, int *);
-struct buffer_head *ext4_bread(handle_t *, struct inode *,
- ext4_lblk_t, int, int *);
+int ext4_inode_is_fast_symlink(struct inode *inode);
+struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
+struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
@@ -2160,9 +2363,10 @@
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_inode_attach_jinode(struct inode *inode);
extern int ext4_can_truncate(struct inode *inode);
extern void ext4_truncate(struct inode *);
-extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
+extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
extern void ext4_get_inode_flags(struct ext4_inode_info *);
@@ -2170,9 +2374,8 @@
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_discard_partial_page_buffers(handle_t *handle,
- struct address_space *mapping, loff_t from,
- loff_t length, int flags);
+extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
+ loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -2182,13 +2385,13 @@
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs);
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
-extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
+extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
-extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t first, ext4_lblk_t stop);
+extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+ ext4_lblk_t start, ext4_lblk_t end);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -2205,13 +2408,14 @@
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
__u32 start_minor_hash, __u32 *next_hash);
-extern int search_dir(struct buffer_head *bh,
- char *search_buf,
- int buf_size,
- struct inode *dir,
- const struct qstr *d_name,
- unsigned int offset,
- struct ext4_dir_entry_2 **res_dir);
+extern int ext4_search_dir(struct buffer_head *bh,
+ char *search_buf,
+ int buf_size,
+ struct inode *dir,
+ struct ext4_filename *fname,
+ const struct qstr *d_name,
+ unsigned int offset,
+ struct ext4_dir_entry_2 **res_dir);
extern int ext4_generic_delete_entry(handle_t *handle,
struct inode *dir,
struct ext4_dir_entry_2 *de_del,
@@ -2219,6 +2423,7 @@
void *entry_buf,
int buf_size,
int csum_size);
+extern int ext4_empty_dir(struct inode *inode);
/* resize.c */
extern int ext4_group_add(struct super_block *sb,
@@ -2230,8 +2435,6 @@
/* super.c */
extern int ext4_calculate_overhead(struct super_block *sb);
-extern int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb);
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
@@ -2240,42 +2443,96 @@
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
+
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
const char *, ...);
-#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
- __LINE__, ## message)
extern __printf(5, 6)
-void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
const char *, ...);
extern __printf(5, 6)
-void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
const char *, ...);
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
extern __printf(4, 5)
void __ext4_abort(struct super_block *, const char *, unsigned int,
const char *, ...);
-#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
- __LINE__, ## message)
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
const char *, ...);
-#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
- __LINE__, ## message)
extern __printf(3, 4)
-void ext4_msg(struct super_block *, const char *, const char *, ...);
+void __ext4_msg(struct super_block *, const char *, const char *, ...);
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
const char *, unsigned int, const char *);
-#define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \
- __LINE__, msg)
extern __printf(7, 8)
void __ext4_grp_locked_error(const char *, unsigned int,
struct super_block *, ext4_group_t,
unsigned long, ext4_fsblk_t,
const char *, ...);
-#define ext4_grp_locked_error(sb, grp, message...) \
- __ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
+
+#ifdef CONFIG_PRINTK
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...) \
+ __ext4_error_inode(inode, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error_file(file, func, line, block, fmt, ...) \
+ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error(sb, fmt, ...) \
+ __ext4_error(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_abort(sb, fmt, ...) \
+ __ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_warning(sb, fmt, ...) \
+ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_msg(sb, level, fmt, ...) \
+ __ext4_msg(sb, level, fmt, ##__VA_ARGS__)
+#define dump_mmp_msg(sb, mmp, msg) \
+ __dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \
+ __ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
+ fmt, ##__VA_ARGS__)
+
+#else
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_error_inode(inode, "", 0, block, " "); \
+} while (0)
+#define ext4_error_file(file, func, line, block, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_error_file(file, "", 0, block, " "); \
+} while (0)
+#define ext4_error(sb, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_error(sb, "", 0, " "); \
+} while (0)
+#define ext4_abort(sb, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_abort(sb, "", 0, " "); \
+} while (0)
+#define ext4_warning(sb, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_warning(sb, "", 0, " "); \
+} while (0)
+#define ext4_msg(sb, level, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_msg(sb, "", " "); \
+} while (0)
+#define dump_mmp_msg(sb, mmp, msg) \
+ __dump_mmp_msg(sb, mmp, "", 0, "")
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __ext4_grp_locked_error("", 0, sb, grp, ino, block, " "); \
+} while (0)
+
+#endif
+
extern void ext4_update_dynamic_rev(struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
@@ -2326,6 +2583,14 @@
(EXT4_SB(sb)->s_chksum_driver != NULL);
}
+static inline int ext4_has_metadata_csum(struct super_block *sb)
+{
+ WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+ !EXT4_SB(sb)->s_chksum_driver);
+
+ return (EXT4_SB(sb)->s_chksum_driver != NULL);
+}
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
@@ -2386,6 +2651,7 @@
{
struct ext4_group_info ***grp_info;
long indexv, indexh;
+ BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
grp_info = EXT4_SB(sb)->s_group_info;
indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
@@ -2432,16 +2698,31 @@
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
+/* Update i_disksize. Requires i_mutex to avoid races with truncate */
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
- /*
- * XXX: replace with spinlock if seen contended -bzzz
- */
+ WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
+ !mutex_is_locked(&inode->i_mutex));
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = newsize;
up_write(&EXT4_I(inode)->i_data_sem);
- return ;
+}
+
+/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
+{
+ int changed = 0;
+
+ if (newsize > inode->i_size) {
+ i_size_write(inode, newsize);
+ changed = 1;
+ }
+ if (newsize > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, newsize);
+ changed |= 2;
+ }
+ return changed;
}
struct ext4_group_info {
@@ -2464,9 +2745,15 @@
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
+#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \
+ (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \
+ (test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
@@ -2543,19 +2830,10 @@
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
-extern void ext4_unwritten_wait(struct inode *inode);
/* inline.c */
-extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
- struct ext4_iloc *iloc,
- void *buffer, loff_t pos,
- unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
@@ -2583,13 +2861,15 @@
extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
unsigned len, unsigned copied,
struct page *page);
-extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
+extern int ext4_try_add_inline_entry(handle_t *handle,
+ struct ext4_filename *fname,
+ struct dentry *dentry,
struct inode *inode);
extern int ext4_try_create_inline_dir(handle_t *handle,
struct inode *parent,
struct inode *inode);
extern int ext4_read_inline_dir(struct file *filp,
- void *dirent, filldir_t filldir,
+ struct dir_context *ctx,
int *has_inline_data);
extern int htree_inlinedir_to_tree(struct file *dir_file,
struct inode *dir, ext4_lblk_t block,
@@ -2597,6 +2877,7 @@
__u32 start_hash, __u32 start_minor_hash,
int *has_inline_data);
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+ struct ext4_filename *fname,
const struct qstr *d_name,
struct ext4_dir_entry_2 **res_dir,
int *has_inline_data);
@@ -2619,6 +2900,12 @@
extern int ext4_convert_inline_data(struct inode *inode);
+static inline int ext4_has_inline_data(struct inode *inode)
+{
+ return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
+ EXT4_I(inode)->i_inline_off;
+}
+
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
@@ -2650,6 +2937,10 @@
de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}
+/* readpages.c */
+extern int ext4_mpage_readpages(struct address_space *mapping,
+ struct list_head *pages, struct page *page,
+ unsigned nr_pages);
/* symlink.c */
extern const struct inode_operations ext4_symlink_inode_operations;
@@ -2670,10 +2961,15 @@
struct ext4_ext_path;
struct ext4_extent;
+/*
+ * Maximum number of logical blocks in a file; ext4_extent's ee_block is
+ * __le32.
+ */
+#define EXT_MAX_BLOCKS 0xffffffff
+
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
-extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
- int chunk);
+extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern void ext4_ext_truncate(handle_t *, struct inode *);
@@ -2683,8 +2979,8 @@
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
-extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- ssize_t len);
+extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
+ loff_t offset, ssize_t len);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
@@ -2697,65 +2993,66 @@
struct ext4_extent *ex1,
struct ext4_extent *ex2);
extern int ext4_ext_insert_extent(handle_t *, struct inode *,
- struct ext4_ext_path *,
+ struct ext4_ext_path **,
struct ext4_extent *, int);
-extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
- struct ext4_ext_path *);
+extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
+ struct ext4_ext_path **,
+ int flags);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
extern int ext4_find_delalloc_range(struct inode *inode,
ext4_lblk_t lblk_start,
ext4_lblk_t lblk_end);
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
+extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
-
+extern int ext4_ext_precache(struct inode *inode);
+extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
+extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
+ struct inode *inode2, ext4_lblk_t lblk1,
+ ext4_lblk_t lblk2, ext4_lblk_t count,
+ int mark_unwritten,int *err);
/* move_extent.c */
extern void ext4_double_down_write_data_sem(struct inode *first,
struct inode *second);
extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
struct inode *donor_inode);
-void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
-void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 start_orig, __u64 start_donor,
__u64 len, __u64 *moved_len);
/* page-io.c */
extern int __init ext4_init_pageio(void);
-extern void ext4_add_complete_io(ext4_io_end_t *io_end);
extern void ext4_exit_pageio(void);
-extern void ext4_ioend_shutdown(struct inode *);
-extern void ext4_free_io_end(ext4_io_end_t *io);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
-extern void ext4_end_io_work(struct work_struct *work);
+extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
+extern int ext4_put_io_end(ext4_io_end_t *io_end);
+extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
+extern void ext4_io_submit_init(struct ext4_io_submit *io,
+ struct writeback_control *wbc);
+extern void ext4_end_io_rsv_work(struct work_struct *work);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc);
+ struct writeback_control *wbc,
+ bool keep_towrite);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
-extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
-extern int ext4_mmp_csum_verify(struct super_block *sb,
- struct mmp_struct *mmp);
-/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+/*
+ * Note that these flags will never ever appear in a buffer_head's state flag.
+ * See EXT4_MAP_... to see where this is used.
+ */
enum ext4_state_bits {
- BH_Uninit /* blocks are allocated but uninitialized on disk */
- = BH_JBDPrivateStart,
- BH_AllocFromCluster, /* allocated blocks were part of already
- * allocated cluster. Note that this flag will
- * never, ever appear in a buffer_head's state
- * flag. See EXT4_MAP_FROM_CLUSTER to see where
- * this is used. */
+ BH_AllocFromCluster /* allocated blocks were part of already
+ * allocated cluster. */
+ = BH_JBDPrivateStart
};
-BUFFER_FNS(Uninit, uninit)
-TAS_BUFFER_FNS(Uninit, uninit)
-
/*
* Add new method to test whether block and inode bitmaps are properly
* initialized. With uninit_bg reading the block from disk is not enough
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
new file mode 100644
index 0000000..ac7d4e8
--- /dev/null
+++ b/fs/ext4/ext4_crypto.h
@@ -0,0 +1,159 @@
+/*
+ * linux/fs/ext4/ext4_crypto.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption header content for ext4
+ *
+ * Written by Michael Halcrow, 2015.
+ */
+
+#ifndef _EXT4_CRYPTO_H
+#define _EXT4_CRYPTO_H
+
+#include <linux/fs.h>
+
+#define EXT4_KEY_DESCRIPTOR_SIZE 8
+
+/* Policy provided via an ioctl on the topmost directory */
+struct ext4_encryption_policy {
+ char version;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+} __attribute__((__packed__));
+
+#define EXT4_ENCRYPTION_CONTEXT_FORMAT_V1 1
+#define EXT4_KEY_DERIVATION_NONCE_SIZE 16
+
+#define EXT4_POLICY_FLAGS_PAD_4 0x00
+#define EXT4_POLICY_FLAGS_PAD_8 0x01
+#define EXT4_POLICY_FLAGS_PAD_16 0x02
+#define EXT4_POLICY_FLAGS_PAD_32 0x03
+#define EXT4_POLICY_FLAGS_PAD_MASK 0x03
+#define EXT4_POLICY_FLAGS_VALID 0x03
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ * 1 byte: Protector format (1 = this version)
+ * 1 byte: File contents encryption mode
+ * 1 byte: File names encryption mode
+ * 1 byte: Reserved
+ * 8 bytes: Master Key descriptor
+ * 16 bytes: Encryption Key derivation nonce
+ */
+struct ext4_encryption_context {
+ char format;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[EXT4_KEY_DESCRIPTOR_SIZE];
+ char nonce[EXT4_KEY_DERIVATION_NONCE_SIZE];
+} __attribute__((__packed__));
+
+/* Encryption parameters */
+#define EXT4_XTS_TWEAK_SIZE 16
+#define EXT4_AES_128_ECB_KEY_SIZE 16
+#define EXT4_AES_256_GCM_KEY_SIZE 32
+#define EXT4_AES_256_CBC_KEY_SIZE 32
+#define EXT4_AES_256_CTS_KEY_SIZE 32
+#define EXT4_AES_256_XTS_KEY_SIZE 64
+#define EXT4_MAX_KEY_SIZE 64
+
+#define EXT4_KEY_DESC_PREFIX "ext4:"
+#define EXT4_KEY_DESC_PREFIX_SIZE 5
+
+/* This is passed in from userspace into the kernel keyring */
+struct ext4_encryption_key {
+ __u32 mode;
+ char raw[EXT4_MAX_KEY_SIZE];
+ __u32 size;
+} __attribute__((__packed__));
+
+struct ext4_crypt_info {
+ char ci_data_mode;
+ char ci_filename_mode;
+ char ci_flags;
+ struct crypto_ablkcipher *ci_ctfm;
+ struct key *ci_keyring_key;
+ char ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
+};
+
+#define EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
+#define EXT4_WRITE_PATH_FL 0x00000002
+
+struct ext4_crypto_ctx {
+ union {
+ struct {
+ struct page *bounce_page; /* Ciphertext page */
+ struct page *control_page; /* Original page */
+ } w;
+ struct {
+ struct bio *bio;
+ struct work_struct work;
+ } r;
+ struct list_head free_list; /* Free list */
+ };
+ char flags; /* Flags */
+ char mode; /* Encryption mode for tfm */
+};
+
+struct ext4_completion_result {
+ struct completion completion;
+ int res;
+};
+
+#define DECLARE_EXT4_COMPLETION_RESULT(ecr) \
+ struct ext4_completion_result ecr = { \
+ COMPLETION_INITIALIZER((ecr).completion), 0 }
+
+static inline int ext4_encryption_key_size(int mode)
+{
+ switch (mode) {
+ case EXT4_ENCRYPTION_MODE_AES_256_XTS:
+ return EXT4_AES_256_XTS_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_GCM:
+ return EXT4_AES_256_GCM_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_CBC:
+ return EXT4_AES_256_CBC_KEY_SIZE;
+ case EXT4_ENCRYPTION_MODE_AES_256_CTS:
+ return EXT4_AES_256_CTS_KEY_SIZE;
+ default:
+ BUG();
+ }
+ return 0;
+}
+
+#define EXT4_FNAME_NUM_SCATTER_ENTRIES 4
+#define EXT4_CRYPTO_BLOCK_SIZE 16
+#define EXT4_FNAME_CRYPTO_DIGEST_SIZE 32
+
+struct ext4_str {
+ unsigned char *name;
+ u32 len;
+};
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct ext4_encrypted_symlink_data {
+ __le16 len;
+ char encrypted_path[1];
+} __attribute__((__packed__));
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 encrypted_symlink_data_len(u32 l)
+{
+ if (l < EXT4_CRYPTO_BLOCK_SIZE)
+ l = EXT4_CRYPTO_BLOCK_SIZE;
+ return (l + sizeof(struct ext4_encrypted_symlink_data) - 1);
+}
+
+#endif /* _EXT4_CRYPTO_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 51bc821..3c93815 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -123,6 +123,7 @@
struct ext4_ext_path {
ext4_fsblk_t p_block;
__u16 p_depth;
+ __u16 p_maxdepth;
struct ext4_extent *p_ext;
struct ext4_extent_idx *p_idx;
struct ext4_extent_header *p_hdr;
@@ -134,30 +135,24 @@
*/
/*
- * Maximum number of logical blocks in a file; ext4_extent's ee_block is
- * __le32.
- */
-#define EXT_MAX_BLOCKS 0xffffffff
-
-/*
* EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
* initialized extent. This is 2^15 and not (2^16 - 1), since we use the
* MSB of ee_len field in the extent datastructure to signify if this
- * particular extent is an initialized extent or an uninitialized (i.e.
+ * particular extent is an initialized extent or an unwritten (i.e.
* preallocated).
- * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
- * uninitialized extent.
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
* If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
- * uninitialized one. In other words, if MSB of ee_len is set, it is an
- * uninitialized extent with only one special scenario when ee_len = 0x8000.
- * In this case we can not have an uninitialized extent of zero length and
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
* thus we make it as a special case of initialized extent with 0x8000 length.
* This way we get better extent-to-group alignment for initialized extents.
* Hence, the maximum number of blocks we can have in an *initialized*
- * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
*/
#define EXT_INIT_MAX_LEN (1UL << 15)
-#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1)
+#define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1)
#define EXT_FIRST_EXTENT(__hdr__) \
@@ -193,14 +188,14 @@
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
-static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
{
- /* We can not have an uninitialized extent of zero length! */
+ /* We can not have an unwritten extent of zero length! */
BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
}
-static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
{
/* Extent with ee_len of 0x8000 is treated as an initialized extent */
return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 1be3996..3445035 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -38,31 +38,43 @@
/*
* Wrappers for jbd2_journal_start/end.
*/
-handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
- int type, int nblocks)
+static int ext4_journal_check_start(struct super_block *sb)
{
journal_t *journal;
might_sleep();
-
- trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY)
- return ERR_PTR(-EROFS);
-
+ return -EROFS;
WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
- if (!journal)
- return ext4_get_nojournal();
/*
* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly.
*/
- if (is_journal_aborted(journal)) {
+ if (journal && is_journal_aborted(journal)) {
ext4_abort(sb, "Detected aborted journal");
- return ERR_PTR(-EROFS);
+ return -EROFS;
}
- return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line);
+ return 0;
+}
+
+handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
+ int type, int blocks, int rsv_blocks)
+{
+ journal_t *journal;
+ int err;
+
+ trace_ext4_journal_start(sb, blocks, rsv_blocks, _RET_IP_);
+ err = ext4_journal_check_start(sb);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ journal = EXT4_SB(sb)->s_journal;
+ if (!journal)
+ return ext4_get_nojournal();
+ return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS,
+ type, line);
}
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
@@ -86,9 +98,34 @@
return err;
}
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn, struct buffer_head *bh,
- handle_t *handle, int err)
+handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
+ int type)
+{
+ struct super_block *sb;
+ int err;
+
+ if (!ext4_handle_valid(handle))
+ return ext4_get_nojournal();
+
+ sb = handle->h_journal->j_private;
+ trace_ext4_journal_start_reserved(sb, handle->h_buffer_credits,
+ _RET_IP_);
+ err = ext4_journal_check_start(sb);
+ if (err < 0) {
+ jbd2_journal_free_reserved(handle);
+ return ERR_PTR(err);
+ }
+
+ err = jbd2_journal_start_reserved(handle, type, line);
+ if (err < 0)
+ return ERR_PTR(err);
+ return handle;
+}
+
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+ const char *err_fn,
+ struct buffer_head *bh,
+ handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
@@ -219,10 +256,20 @@
set_buffer_prio(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
- /* Errors can only happen if there is a bug */
- if (WARN_ON_ONCE(err)) {
+ /* Errors can only happen due to aborted journal or a nasty bug */
+ if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
+ if (inode == NULL) {
+ pr_err("EXT4: jbd2_journal_dirty_metadata "
+ "failed: handle type %u started at "
+ "line %u, credits %u/%u, errcode %d",
+ handle->h_type,
+ handle->h_line_no,
+ handle->h_requested_credits,
+ handle->h_buffer_credits, err);
+ return err;
+ }
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"journal_dirty_metadata failed: "
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index c8c6885..9c5b49f 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -102,9 +102,9 @@
#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
#endif
-#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
static inline int ext4_jbd2_credits_xattr(struct inode *inode)
{
@@ -134,7 +134,8 @@
#define EXT4_HT_MIGRATE 8
#define EXT4_HT_MOVE_EXTENTS 9
#define EXT4_HT_XATTR 10
-#define EXT4_HT_MAX 11
+#define EXT4_HT_EXT_CONVERT 11
+#define EXT4_HT_MAX 12
/**
* struct ext4_journal_cb_entry - Base structure for callback information.
@@ -196,7 +197,7 @@
* ext4_journal_callback_del: delete a registered callback
* @handle: active journal transaction handle on which callback was registered
* @jce: registered journal callback entry to unregister
- * Return true if object was sucessfully removed
+ * Return true if object was successfully removed
*/
static inline bool ext4_journal_callback_try_del(handle_t *handle,
struct ext4_journal_cb_entry *jce)
@@ -230,10 +231,6 @@
/*
* Wrapper functions with which ext4 calls into JBD.
*/
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn,
- struct buffer_head *bh, handle_t *handle, int err);
-
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh);
@@ -265,7 +262,7 @@
__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
- int type, int nblocks);
+ int type, int blocks, int rsv_blocks);
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
@@ -300,21 +297,37 @@
}
#define ext4_journal_start_sb(sb, type, nblocks) \
- __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks))
+ __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0)
#define ext4_journal_start(inode, type, nblocks) \
- __ext4_journal_start((inode), __LINE__, (type), (nblocks))
+ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0)
+
+#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \
+ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks))
static inline handle_t *__ext4_journal_start(struct inode *inode,
unsigned int line, int type,
- int nblocks)
+ int blocks, int rsv_blocks)
{
- return __ext4_journal_start_sb(inode->i_sb, line, type, nblocks);
+ return __ext4_journal_start_sb(inode->i_sb, line, type, blocks,
+ rsv_blocks);
}
#define ext4_journal_stop(handle) \
__ext4_journal_stop(__func__, __LINE__, (handle))
+#define ext4_journal_start_reserved(handle, type) \
+ __ext4_journal_start_reserved((handle), __LINE__, (type))
+
+handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
+ int type);
+
+static inline void ext4_journal_free_reserved(handle_t *handle)
+{
+ if (ext4_handle_valid(handle))
+ jbd2_journal_free_reserved(handle);
+}
+
static inline handle_t *ext4_journal_current_handle(void)
{
return journal_current_handle();
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7eea761..7a2aa5d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -37,7 +37,6 @@
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/slab.h>
-#include <linux/falloc.h>
#include <asm/uaccess.h>
#include <linux/fiemap.h>
#include "ext4_jbd2.h"
@@ -51,8 +50,8 @@
*/
#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
+#define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */
+#define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */
#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
@@ -74,8 +73,7 @@
{
struct ext4_extent_tail *et;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return 1;
et = find_ext4_extent_tail(eh);
@@ -89,8 +87,7 @@
{
struct ext4_extent_tail *et;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return;
et = find_ext4_extent_tail(eh);
@@ -99,14 +96,14 @@
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_map_blocks *map,
int split_flag,
int flags);
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags);
@@ -144,6 +141,7 @@
{
if (path->p_bh) {
/* path points to block */
+ BUFFER_TRACE(path->p_bh, "get_write_access");
return ext4_journal_get_write_access(handle, path->p_bh);
}
/* path points to leaf/index in inode body */
@@ -161,6 +159,8 @@
struct inode *inode, struct ext4_ext_path *path)
{
int err;
+
+ WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
if (path->p_bh) {
ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh));
/* path points to block */
@@ -289,6 +289,20 @@
return size;
}
+static inline int
+ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path **ppath, ext4_lblk_t lblk,
+ int nofail)
+{
+ struct ext4_ext_path *path = *ppath;
+ int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
+
+ return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ?
+ EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0,
+ EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO |
+ (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
+}
+
/*
* Calculate the number of metadata blocks needed
* to allocate @blocks
@@ -428,7 +442,7 @@
static int __ext4_ext_check(const char *function, unsigned int line,
struct inode *inode, struct ext4_extent_header *eh,
- int depth)
+ int depth, ext4_fsblk_t pblk)
{
const char *error_msg;
int max = 0;
@@ -472,43 +486,150 @@
corrupted:
ext4_error_inode(inode, function, line, 0,
- "bad header/extent: %s - magic %x, "
- "entries %u, max %u(%u), depth %u(%u)",
- error_msg, le16_to_cpu(eh->eh_magic),
- le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
- max, le16_to_cpu(eh->eh_depth), depth);
-
+ "pblk %llu bad header/extent: %s - magic %x, "
+ "entries %u, max %u(%u), depth %u(%u)",
+ (unsigned long long) pblk, error_msg,
+ le16_to_cpu(eh->eh_magic),
+ le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+ max, le16_to_cpu(eh->eh_depth), depth);
return -EIO;
}
-#define ext4_ext_check(inode, eh, depth) \
- __ext4_ext_check(__func__, __LINE__, inode, eh, depth)
+#define ext4_ext_check(inode, eh, depth, pblk) \
+ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk))
int ext4_ext_check_inode(struct inode *inode)
{
- return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode));
+ return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
}
-static int __ext4_ext_check_block(const char *function, unsigned int line,
- struct inode *inode,
- struct ext4_extent_header *eh,
- int depth,
- struct buffer_head *bh)
+static struct buffer_head *
+__read_extent_tree_block(const char *function, unsigned int line,
+ struct inode *inode, ext4_fsblk_t pblk, int depth,
+ int flags)
{
- int ret;
+ struct buffer_head *bh;
+ int err;
- if (buffer_verified(bh))
- return 0;
- ret = ext4_ext_check(inode, eh, depth);
- if (ret)
- return ret;
+ bh = sb_getblk(inode->i_sb, pblk);
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
+
+ if (!bh_uptodate_or_lock(bh)) {
+ trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
+ err = bh_submit_read(bh);
+ if (err < 0)
+ goto errout;
+ }
+ if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
+ return bh;
+ err = __ext4_ext_check(function, line, inode,
+ ext_block_hdr(bh), depth, pblk);
+ if (err)
+ goto errout;
set_buffer_verified(bh);
+ /*
+ * If this is a leaf block, cache all of its entries
+ */
+ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
+ struct ext4_extent_header *eh = ext_block_hdr(bh);
+ struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+ ext4_lblk_t prev = 0;
+ int i;
+
+ for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+ unsigned int status = EXTENT_STATUS_WRITTEN;
+ ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+ int len = ext4_ext_get_actual_len(ex);
+
+ if (prev && (prev != lblk))
+ ext4_es_cache_extent(inode, prev,
+ lblk - prev, ~0,
+ EXTENT_STATUS_HOLE);
+
+ if (ext4_ext_is_unwritten(ex))
+ status = EXTENT_STATUS_UNWRITTEN;
+ ext4_es_cache_extent(inode, lblk, len,
+ ext4_ext_pblock(ex), status);
+ prev = lblk + len;
+ }
+ }
+ return bh;
+errout:
+ put_bh(bh);
+ return ERR_PTR(err);
+
+}
+
+#define read_extent_tree_block(inode, pblk, depth, flags) \
+ __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \
+ (depth), (flags))
+
+/*
+ * This function is called to cache a file's extent information in the
+ * extent status tree
+ */
+int ext4_ext_precache(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_ext_path *path = NULL;
+ struct buffer_head *bh;
+ int i = 0, depth, ret = 0;
+
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return 0; /* not an extent-mapped inode */
+
+ down_read(&ei->i_data_sem);
+ depth = ext_depth(inode);
+
+ path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+ GFP_NOFS);
+ if (path == NULL) {
+ up_read(&ei->i_data_sem);
+ return -ENOMEM;
+ }
+
+ /* Don't cache anything if there are no external extent blocks */
+ if (depth == 0)
+ goto out;
+ path[0].p_hdr = ext_inode_hdr(inode);
+ ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
+ if (ret)
+ goto out;
+ path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr);
+ while (i >= 0) {
+ /*
+ * If this is a leaf block or we've reached the end of
+ * the index block, go up
+ */
+ if ((i == depth) ||
+ path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) {
+ brelse(path[i].p_bh);
+ path[i].p_bh = NULL;
+ i--;
+ continue;
+ }
+ bh = read_extent_tree_block(inode,
+ ext4_idx_pblock(path[i].p_idx++),
+ depth - i - 1,
+ EXT4_EX_FORCE_CACHE);
+ if (IS_ERR(bh)) {
+ ret = PTR_ERR(bh);
+ break;
+ }
+ i++;
+ path[i].p_bh = bh;
+ path[i].p_hdr = ext_block_hdr(bh);
+ path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr);
+ }
+ ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
+out:
+ up_read(&ei->i_data_sem);
+ ext4_ext_drop_refs(path);
+ kfree(path);
return ret;
}
-#define ext4_ext_check_block(inode, eh, depth, bh) \
- __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh)
-
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
{
@@ -522,7 +643,7 @@
} else if (path->p_ext) {
ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
- ext4_ext_is_uninitialized(path->p_ext),
+ ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
@@ -548,7 +669,7 @@
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug("\n");
@@ -579,7 +700,7 @@
ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
newblock);
ex++;
@@ -594,9 +715,11 @@
void ext4_ext_drop_refs(struct ext4_ext_path *path)
{
- int depth = path->p_depth;
- int i;
+ int depth, i;
+ if (!path)
+ return;
+ depth = path->p_depth;
for (i = 0; i <= depth; i++, path++)
if (path->p_bh) {
brelse(path->p_bh);
@@ -704,7 +827,7 @@
ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
- ext4_ext_is_uninitialized(path->p_ext),
+ ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
@@ -740,24 +863,32 @@
}
struct ext4_ext_path *
-ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
- struct ext4_ext_path *path)
+ext4_find_extent(struct inode *inode, ext4_lblk_t block,
+ struct ext4_ext_path **orig_path, int flags)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
- short int depth, i, ppos = 0, alloc = 0;
+ struct ext4_ext_path *path = orig_path ? *orig_path : NULL;
+ short int depth, i, ppos = 0;
int ret;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
- /* account possible depth increase */
+ if (path) {
+ ext4_ext_drop_refs(path);
+ if (depth > path[0].p_maxdepth) {
+ kfree(path);
+ *orig_path = path = NULL;
+ }
+ }
if (!path) {
+ /* account possible depth increase */
path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 2),
GFP_NOFS);
- if (!path)
+ if (unlikely(!path))
return ERR_PTR(-ENOMEM);
- alloc = 1;
+ path[0].p_maxdepth = depth + 1;
}
path[0].p_hdr = eh;
path[0].p_bh = NULL;
@@ -773,20 +904,13 @@
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
- bh = sb_getblk(inode->i_sb, path[ppos].p_block);
- if (unlikely(!bh)) {
- ret = -ENOMEM;
+ bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
+ flags);
+ if (unlikely(IS_ERR(bh))) {
+ ret = PTR_ERR(bh);
goto err;
}
- if (!bh_uptodate_or_lock(bh)) {
- trace_ext4_ext_load_extent(inode, block,
- path[ppos].p_block);
- ret = bh_submit_read(bh);
- if (ret < 0) {
- put_bh(bh);
- goto err;
- }
- }
+
eh = ext_block_hdr(bh);
ppos++;
if (unlikely(ppos > depth)) {
@@ -798,11 +922,6 @@
}
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
- i--;
-
- ret = ext4_ext_check_block(inode, eh, i, bh);
- if (ret < 0)
- goto err;
}
path[ppos].p_depth = i;
@@ -821,8 +940,9 @@
err:
ext4_ext_drop_refs(path);
- if (alloc)
- kfree(path);
+ kfree(path);
+ if (orig_path)
+ *orig_path = NULL;
return ERR_PTR(ret);
}
@@ -1149,16 +1269,24 @@
* just created block
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
- unsigned int flags,
- struct ext4_extent *newext)
+ unsigned int flags)
{
struct ext4_extent_header *neh;
struct buffer_head *bh;
- ext4_fsblk_t newblock;
+ ext4_fsblk_t newblock, goal = 0;
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
int err = 0;
- newblock = ext4_ext_new_meta_block(handle, inode, NULL,
- newext, &err, flags);
+ /* Try to prepend new index to old one */
+ if (ext_depth(inode))
+ goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode)));
+ if (goal > le32_to_cpu(es->s_first_data_block)) {
+ flags |= EXT4_MB_HINT_TRY_GOAL;
+ goal--;
+ } else
+ goal = ext4_inode_to_goal_block(inode);
+ newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
+ NULL, &err);
if (newblock == 0)
return err;
@@ -1223,10 +1351,12 @@
* if no free index is found, then it requests in-depth growing.
*/
static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
- unsigned int flags,
- struct ext4_ext_path *path,
+ unsigned int mb_flags,
+ unsigned int gb_flags,
+ struct ext4_ext_path **ppath,
struct ext4_extent *newext)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_ext_path *curp;
int depth, i, err = 0;
@@ -1245,28 +1375,26 @@
if (EXT_HAS_FREE_INDEX(curp)) {
/* if we found index with free entry, then use that
* entry: create all needed subtree and add new leaf */
- err = ext4_ext_split(handle, inode, flags, path, newext, i);
+ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i);
if (err)
goto out;
/* refill path */
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode,
+ path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path);
+ ppath, gb_flags);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, flags, newext);
+ err = ext4_ext_grow_indepth(handle, inode, mb_flags);
if (err)
goto out;
/* refill path */
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode,
+ path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path);
+ ppath, gb_flags);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -1437,29 +1565,21 @@
ix++;
block = ext4_idx_pblock(ix);
while (++depth < path->p_depth) {
- bh = sb_bread(inode->i_sb, block);
- if (bh == NULL)
- return -EIO;
- eh = ext_block_hdr(bh);
/* subtract from p_depth to get proper eh_depth */
- if (ext4_ext_check_block(inode, eh,
- path->p_depth - depth, bh)) {
- put_bh(bh);
- return -EIO;
- }
+ bh = read_extent_tree_block(inode, block,
+ path->p_depth - depth, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
+ eh = ext_block_hdr(bh);
ix = EXT_FIRST_INDEX(eh);
block = ext4_idx_pblock(ix);
put_bh(bh);
}
- bh = sb_bread(inode->i_sb, block);
- if (bh == NULL)
- return -EIO;
+ bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
eh = ext_block_hdr(bh);
- if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) {
- put_bh(bh);
- return -EIO;
- }
ex = EXT_FIRST_EXTENT(eh);
found_extent:
*logical = le32_to_cpu(ex->ee_block);
@@ -1477,7 +1597,7 @@
* allocated block. Thus, index entries have to be consistent
* with leaves.
*/
-static ext4_lblk_t
+ext4_lblk_t
ext4_ext_next_allocated_block(struct ext4_ext_path *path)
{
int depth;
@@ -1603,22 +1723,17 @@
ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
struct ext4_extent *ex2)
{
- unsigned short ext1_ee_len, ext2_ee_len, max_len;
+ unsigned short ext1_ee_len, ext2_ee_len;
/*
* Make sure that both extents are initialized. We don't merge
- * uninitialized extents so that we can be sure that end_io code has
+ * unwritten extents so that we can be sure that end_io code has
* the extent that was written properly split out and conversion to
* initialized is trivial.
*/
- if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
+ if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
- if (ext4_ext_is_uninitialized(ex1))
- max_len = EXT_UNINIT_MAX_LEN;
- else
- max_len = EXT_INIT_MAX_LEN;
-
ext1_ee_len = ext4_ext_get_actual_len(ex1);
ext2_ee_len = ext4_ext_get_actual_len(ex2);
@@ -1631,7 +1746,12 @@
* as an RO_COMPAT feature, refuse to merge to extents if
* this can result in the top bit of ee_len being set.
*/
- if (ext1_ee_len + ext2_ee_len > max_len)
+ if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
+ return 0;
+ if (ext4_ext_is_unwritten(ex1) &&
+ (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
+ atomic_read(&EXT4_I(inode)->i_unwritten) ||
+ (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@@ -1656,8 +1776,7 @@
{
struct ext4_extent_header *eh;
unsigned int depth, len;
- int merge_done = 0;
- int uninitialized = 0;
+ int merge_done = 0, unwritten;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
@@ -1667,12 +1786,11 @@
if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
break;
/* merge with next extent! */
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(ex + 1));
- if (uninitialized)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
if (ex + 1 < EXT_LAST_EXTENT(eh)) {
len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1722,6 +1840,7 @@
sizeof(struct ext4_extent_idx);
s += sizeof(struct ext4_extent_header);
+ path[1].p_maxdepth = path[0].p_maxdepth;
memcpy(path[0].p_hdr, path[1].p_hdr, s);
path[0].p_depth = 0;
path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) +
@@ -1730,8 +1849,7 @@
brelse(path[1].p_bh);
ext4_free_blocks(handle, inode, NULL, blk, 1,
- EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET |
- EXT4_FREE_BLOCKS_RESERVE);
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
}
/*
@@ -1817,18 +1935,20 @@
* creating new leaf in the no-space case.
*/
int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path,
- struct ext4_extent *newext, int flag)
+ struct ext4_ext_path **ppath,
+ struct ext4_extent *newext, int gb_flags)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_extent_header *eh;
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
- unsigned uninitialized = 0;
- int flags = 0;
+ int mb_flags = 0, unwritten;
+ if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ mb_flags |= EXT4_MB_DELALLOC_RESERVED;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
return -EIO;
@@ -1842,12 +1962,12 @@
}
/* try to insert block into found extent and return */
- if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) {
+ if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) {
/*
* Try to see whether we should rather test the extent on
* right from ex, or from the left of ex. This is because
- * ext4_ext_find_extent() can return either extent on the
+ * ext4_find_extent() can return either extent on the
* left, or on the right from the searched position. This
* will make merging more effective.
*/
@@ -1867,29 +1987,21 @@
if (ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
-
- /*
- * ext4_can_extents_be_merged should have checked
- * that either both extents are uninitialized, or
- * both aren't. Thus we need to check only one of
- * them here.
- */
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninitialized)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -1901,10 +2013,10 @@
ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
@@ -1912,20 +2024,13 @@
if (err)
return err;
- /*
- * ext4_can_extents_be_merged should have checked
- * that either both extents are uninitialized, or
- * both aren't. Thus we need to check only one of
- * them here.
- */
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninitialized)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -1945,7 +2050,7 @@
if (next != EXT_MAX_BLOCKS) {
ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
- npath = ext4_ext_find_extent(inode, next, NULL);
+ npath = ext4_find_extent(inode, next, NULL, 0);
if (IS_ERR(npath))
return PTR_ERR(npath);
BUG_ON(npath->p_depth != path->p_depth);
@@ -1964,9 +2069,10 @@
* There is no free space in the found leaf.
* We're gonna add a new leaf in the tree.
*/
- if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL)
- flags = EXT4_MB_USE_RESERVED;
- err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
+ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
+ mb_flags |= EXT4_MB_USE_RESERVED;
+ err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
+ ppath, newext);
if (err)
goto cleanup;
depth = ext_depth(inode);
@@ -1984,7 +2090,7 @@
ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext));
nearex = EXT_FIRST_EXTENT(eh);
} else {
@@ -1995,7 +2101,7 @@
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
nearex++;
@@ -2006,7 +2112,7 @@
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
}
@@ -2016,7 +2122,7 @@
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
len, nearex, nearex + 1);
memmove(nearex + 1, nearex,
@@ -2032,7 +2138,7 @@
merge:
/* try to merge extents */
- if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
+ if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(handle, inode, path, nearex);
@@ -2044,10 +2150,8 @@
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
cleanup:
- if (npath) {
- ext4_ext_drop_refs(npath);
- kfree(npath);
- }
+ ext4_ext_drop_refs(npath);
+ kfree(npath);
return err;
}
@@ -2069,13 +2173,7 @@
/* find extent for this block */
down_read(&EXT4_I(inode)->i_data_sem);
- if (path && ext_depth(inode) != depth) {
- /* depth was changed. we have to realloc path */
- kfree(path);
- path = NULL;
- }
-
- path = ext4_ext_find_extent(inode, block, path);
+ path = ext4_find_extent(inode, block, &path, 0);
if (IS_ERR(path)) {
up_read(&EXT4_I(inode)->i_data_sem);
err = PTR_ERR(path);
@@ -2092,7 +2190,6 @@
}
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
- ext4_ext_drop_refs(path);
flags = 0;
exists = 0;
@@ -2138,7 +2235,7 @@
es.es_lblk = le32_to_cpu(ex->ee_block);
es.es_len = ext4_ext_get_actual_len(ex);
es.es_pblk = ext4_ext_pblock(ex);
- if (ext4_ext_is_uninitialized(ex))
+ if (ext4_ext_is_unwritten(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
}
@@ -2150,7 +2247,8 @@
next_del = ext4_find_delayed_extent(inode, &es);
if (!exists && next_del) {
exists = 1;
- flags |= FIEMAP_EXTENT_DELALLOC;
+ flags |= (FIEMAP_EXTENT_DELALLOC |
+ FIEMAP_EXTENT_UNKNOWN);
}
up_read(&EXT4_I(inode)->i_data_sem);
@@ -2201,11 +2299,8 @@
block = es.es_lblk + es.es_len;
}
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
-
+ ext4_ext_drop_refs(path);
+ kfree(path);
return err;
}
@@ -2219,8 +2314,8 @@
ext4_lblk_t block)
{
int depth = ext_depth(inode);
- unsigned long len;
- ext4_lblk_t lblock;
+ unsigned long len = 0;
+ ext4_lblk_t lblock = 0;
struct ext4_extent *ex;
ex = path[depth].p_ext;
@@ -2257,7 +2352,6 @@
ext4_es_insert_extent(inode, lblock, len, ~0,
EXTENT_STATUS_HOLE);
} else {
- lblock = len = 0;
BUG();
}
@@ -2353,17 +2447,15 @@
}
/*
- * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ * How many index/leaf blocks need to change/allocate to add @extents extents?
*
- * if nrblocks are fit in a single extent (chunk flag is 1), then
- * in the worse case, each tree level index/leaf need to be changed
- * if the tree split due to insert a new extent, then the old tree
- * index/leaf need to be updated too
+ * If we add a single extent, then in the worse case, each tree level
+ * index/leaf need to be changed in case of the tree split.
*
- * If the nrblocks are discontiguous, they could cause
- * the whole tree split more than once, but this is really rare.
+ * If more extents are inserted, they could cause the whole tree split more
+ * than once, but this is really rare.
*/
-int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+int ext4_ext_index_trans_blocks(struct inode *inode, int extents)
{
int index;
int depth;
@@ -2374,7 +2466,7 @@
depth = ext_depth(inode);
- if (chunk)
+ if (extents <= 1)
index = depth * 2;
else
index = depth * 3;
@@ -2382,20 +2474,24 @@
return index;
}
+static inline int get_default_free_blocks_flags(struct inode *inode)
+{
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
+ else if (ext4_should_journal_data(inode))
+ return EXT4_FREE_BLOCKS_FORGET;
+ return 0;
+}
+
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
- ext4_fsblk_t *partial_cluster,
+ long long *partial_cluster,
ext4_lblk_t from, ext4_lblk_t to)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
ext4_fsblk_t pblk;
- int flags = 0;
-
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
- else if (ext4_should_journal_data(inode))
- flags |= EXT4_FREE_BLOCKS_FORGET;
+ int flags = get_default_free_blocks_flags(inode);
/*
* For bigalloc file systems, we never free a partial cluster
@@ -2413,7 +2509,8 @@
* partial cluster here.
*/
pblk = ext4_ext_pblock(ex) + ee_len - 1;
- if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ if ((*partial_cluster > 0) &&
+ (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, *partial_cluster),
sbi->s_cluster_ratio, flags);
@@ -2439,41 +2536,46 @@
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
+ unsigned int unaligned;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
pblk = ext4_ext_pblock(ex) + ee_len - num;
- ext_debug("free last %u blocks starting %llu\n", num, pblk);
+ /*
+ * Usually we want to free partial cluster at the end of the
+ * extent, except for the situation when the cluster is still
+ * used by any other extent (partial_cluster is negative).
+ */
+ if (*partial_cluster < 0 &&
+ -(*partial_cluster) == EXT4_B2C(sbi, pblk + num - 1))
+ flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER;
+
+ ext_debug("free last %u blocks starting %llu partial %lld\n",
+ num, pblk, *partial_cluster);
ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
/*
* If the block range to be freed didn't start at the
* beginning of a cluster, and we removed the entire
- * extent, save the partial cluster here, since we
- * might need to delete if we determine that the
- * truncate operation has removed all of the blocks in
- * the cluster.
+ * extent and the cluster is not used by any other extent,
+ * save the partial cluster here, since we might need to
+ * delete if we determine that the truncate operation has
+ * removed all of the blocks in the cluster.
+ *
+ * On the other hand, if we did not manage to free the whole
+ * extent, we have to mark the cluster as used (store negative
+ * cluster number in partial_cluster).
*/
- if (EXT4_PBLK_COFF(sbi, pblk) &&
- (ee_len == num))
+ unaligned = EXT4_PBLK_COFF(sbi, pblk);
+ if (unaligned && (ee_len == num) &&
+ (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
*partial_cluster = EXT4_B2C(sbi, pblk);
- else
+ else if (unaligned)
+ *partial_cluster = -((long long)EXT4_B2C(sbi, pblk));
+ else if (*partial_cluster > 0)
*partial_cluster = 0;
- } else if (from == le32_to_cpu(ex->ee_block)
- && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
- /* head removal */
- ext4_lblk_t num;
- ext4_fsblk_t start;
-
- num = to - from;
- start = ext4_ext_pblock(ex);
-
- ext_debug("free first %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, NULL, start, num, flags);
-
- } else {
- printk(KERN_INFO "strange request: removal(2) "
- "%u-%u from %u:%u\n",
- from, to, le32_to_cpu(ex->ee_block), ee_len);
- }
+ } else
+ ext4_error(sbi->s_sb, "strange request: removal(2) "
+ "%u-%u from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), ee_len);
return 0;
}
@@ -2486,12 +2588,16 @@
* @handle: The journal handle
* @inode: The files inode
* @path: The path to the leaf
+ * @partial_cluster: The cluster which we'll have to free if all extents
+ * has been released from it. It gets negative in case
+ * that the cluster is still used.
* @start: The first block to remove
* @end: The last block to remove
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+ struct ext4_ext_path *path,
+ long long *partial_cluster,
ext4_lblk_t start, ext4_lblk_t end)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2502,8 +2608,9 @@
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
- unsigned uninitialized = 0;
+ unsigned unwritten = 0;
struct ext4_extent *ex;
+ ext4_fsblk_t pblk;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %u in leaf to %u\n", start, end);
@@ -2515,7 +2622,9 @@
return -EIO;
}
/* find where to start removing */
- ex = EXT_LAST_EXTENT(eh);
+ ex = path[depth].p_ext;
+ if (!ex)
+ ex = EXT_LAST_EXTENT(eh);
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2546,13 +2655,13 @@
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ if (ext4_ext_is_unwritten(ex))
+ unwritten = 1;
else
- uninitialized = 0;
+ unwritten = 0;
ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
- uninitialized, ex_ee_len);
+ unwritten, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
@@ -2563,6 +2672,16 @@
/* If this extent is beyond the end of the hole, skip it */
if (end < ex_ee_block) {
+ /*
+ * We're going to skip this extent and move to another,
+ * so if this extent is not cluster aligned we have
+ * to mark the current cluster as used to avoid
+ * accidentally freeing it later on
+ */
+ pblk = ext4_ext_pblock(ex);
+ if (EXT4_PBLK_COFF(sbi, pblk))
+ *partial_cluster =
+ -((long long)EXT4_B2C(sbi, pblk));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2614,11 +2733,11 @@
ex->ee_len = cpu_to_le16(num);
/*
- * Do not mark uninitialized if all the blocks in the
+ * Do not mark unwritten if all the blocks in the
* extent have been removed.
*/
- if (uninitialized && num)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten && num)
+ ext4_ext_mark_unwritten(ex);
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2638,7 +2757,7 @@
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- } else
+ } else if (*partial_cluster > 0)
*partial_cluster = 0;
err = ext4_ext_dirty(handle, inode, path + depth);
@@ -2656,17 +2775,18 @@
err = ext4_ext_correct_indexes(handle, inode, path);
/*
- * If there is still a entry in the leaf node, check to see if
- * it references the partial cluster. This is the only place
- * where it could; if it doesn't, we can free the cluster.
+ * If there's a partial cluster and at least one extent remains in
+ * the leaf, free the partial cluster if it isn't shared with the
+ * current extent. If there's a partial cluster and no extents
+ * remain in the leaf, it can't be freed here. It can only be
+ * freed when it's possible to determine if it's not shared with
+ * any other extent - when the next leaf is processed or when space
+ * removal is complete.
*/
- if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+ if (*partial_cluster > 0 && eh->eh_entries &&
(EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
*partial_cluster)) {
- int flags = EXT4_FREE_BLOCKS_FORGET;
-
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
+ int flags = get_default_free_blocks_flags(inode);
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, *partial_cluster),
@@ -2710,7 +2830,7 @@
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
struct ext4_ext_path *path = NULL;
- ext4_fsblk_t partial_cluster = 0;
+ long long partial_cluster = 0;
handle_t *handle;
int i = 0, err = 0;
@@ -2722,7 +2842,7 @@
return PTR_ERR(handle);
again:
- trace_ext4_ext_remove_space(inode, start, depth);
+ trace_ext4_ext_remove_space(inode, start, end, depth);
/*
* Check if we are removing extents inside the extent tree. If that
@@ -2736,7 +2856,7 @@
ext4_lblk_t ee_block;
/* find extent for this block */
- path = ext4_ext_find_extent(inode, end, NULL);
+ path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path)) {
ext4_journal_stop(handle);
return PTR_ERR(path);
@@ -2764,23 +2884,14 @@
*/
if (end >= ee_block &&
end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
- int split_flag = 0;
-
- if (ext4_ext_is_uninitialized(ex))
- split_flag = EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2;
-
/*
* Split the extent in two so that 'end' is the last
* block in the first new extent. Also we should not
* fail removing space due to ENOSPC so try to use
* reserved block if that happens.
*/
- err = ext4_split_extent_at(handle, inode, path,
- end + 1, split_flag,
- EXT4_GET_BLOCKS_PRE_IO |
- EXT4_GET_BLOCKS_METADATA_NOFAIL);
-
+ err = ext4_force_split_extent_at(handle, inode, &path,
+ end + 1, 1);
if (err < 0)
goto out;
}
@@ -2802,11 +2913,11 @@
ext4_journal_stop(handle);
return -ENOMEM;
}
- path[0].p_depth = depth;
+ path[0].p_maxdepth = path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
i = 0;
- if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+ if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) {
err = -EIO;
goto out;
}
@@ -2853,21 +2964,21 @@
ext_debug("move to level %d (block %llu)\n",
i + 1, ext4_idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
- bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx));
- if (!bh) {
+ bh = read_extent_tree_block(inode,
+ ext4_idx_pblock(path[i].p_idx), depth - i - 1,
+ EXT4_EX_NOCACHE);
+ if (IS_ERR(bh)) {
/* should we reset i_size? */
- err = -EIO;
+ err = PTR_ERR(bh);
break;
}
+ /* Yield here to deal with large extent trees.
+ * Should be a no-op if we did IO above. */
+ cond_resched();
if (WARN_ON(i + 1 > depth)) {
err = -EIO;
break;
}
- if (ext4_ext_check_block(inode, ext_block_hdr(bh),
- depth - i - 1, bh)) {
- err = -EIO;
- break;
- }
path[i + 1].p_bh = bh;
/* save actual number of indexes since this
@@ -2890,17 +3001,14 @@
}
}
- trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
- path->p_hdr->eh_entries);
+ trace_ext4_ext_remove_space_done(inode, start, end, depth,
+ partial_cluster, path->p_hdr->eh_entries);
/* If we still have something in the partial cluster and we have removed
* even the first extent, then we should free the blocks in the partial
* cluster as well. */
- if (partial_cluster && path->p_hdr->eh_entries == 0) {
- int flags = EXT4_FREE_BLOCKS_FORGET;
-
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
+ if (partial_cluster > 0 && path->p_hdr->eh_entries == 0) {
+ int flags = get_default_free_blocks_flags(inode);
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(EXT4_SB(sb), partial_cluster),
@@ -2925,10 +3033,9 @@
out:
ext4_ext_drop_refs(path);
kfree(path);
- if (err == -EAGAIN) {
- path = NULL;
+ path = NULL;
+ if (err == -EAGAIN)
goto again;
- }
ext4_journal_stop(handle);
return err;
@@ -2985,6 +3092,23 @@
#endif
}
+static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
+{
+ ext4_lblk_t ee_block;
+ ext4_fsblk_t ee_pblock;
+ unsigned int ee_len;
+
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext4_ext_pblock(ex);
+
+ if (ee_len == 0)
+ return 0;
+
+ return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+ EXTENT_STATUS_WRITTEN);
+}
+
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
@@ -2995,6 +3119,9 @@
ee_len = ext4_ext_get_actual_len(ex);
ee_pblock = ext4_ext_pblock(ex);
+ if (ext4_encrypted_inode(inode))
+ return ext4_encrypted_zeroout(inode, ex);
+
ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
if (ret > 0)
ret = 0;
@@ -3010,7 +3137,7 @@
* @path: the path to the extent
* @split: the logical block where the extent is splitted.
* @split_flags: indicates if the extent could be zeroout if split fails, and
- * the states(init or uninit) of new extents.
+ * the states(init or unwritten) of new extents.
* @flags: flags used to insert new extent to extent tree.
*
*
@@ -3025,11 +3152,12 @@
*/
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_fsblk_t newblock;
ext4_lblk_t ee_block;
struct ext4_extent *ex, newex, orig_ex, zero_ex;
@@ -3052,10 +3180,10 @@
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
- BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+ BUG_ON(!ext4_ext_is_unwritten(ex) &&
split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2));
+ EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3067,8 +3195,8 @@
* then we just change the state of the extent, and splitting
* is not needed.
*/
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex);
else
ext4_ext_mark_initialized(ex);
@@ -3082,8 +3210,8 @@
/* case a */
memcpy(&orig_ex, ex, sizeof(orig_ex));
ex->ee_len = cpu_to_le16(split - ee_block);
- if (split_flag & EXT4_EXT_MARK_UNINIT1)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT1)
+ ext4_ext_mark_unwritten(ex);
/*
* path may lead to new leaf, not to original leaf any more
@@ -3097,10 +3225,10 @@
ex2->ee_block = cpu_to_le32(split);
ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block));
ext4_ext_store_pblock(ex2, newblock);
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex2);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex2);
- err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+ err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
if (split_flag & EXT4_EXT_DATA_VALID1) {
@@ -3137,7 +3265,7 @@
goto fix_extent_len;
/* update extent status tree */
- err = ext4_es_zeroout(inode, &zero_ex);
+ err = ext4_zeroout_es(inode, &zero_ex);
goto out;
} else if (err)
@@ -3149,7 +3277,7 @@
fix_extent_len:
ex->ee_len = orig_ex.ee_len;
- ext4_ext_dirty(handle, inode, path + depth);
+ ext4_ext_dirty(handle, inode, path + path->p_depth);
return err;
}
@@ -3157,7 +3285,7 @@
* ext4_split_extents() splits an extent and mark extent which is covered
* by @map as split_flags indicates
*
- * It may result in splitting the extent into multiple extents (upto three)
+ * It may result in splitting the extent into multiple extents (up to three)
* There are three possibilities:
* a> There is no split required
* b> Splits in two extents: Split is happening at either end of the extent
@@ -3166,16 +3294,17 @@
*/
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_map_blocks *map,
int split_flag,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
unsigned int ee_len, depth;
int err = 0;
- int uninitialized;
+ int unwritten;
int split_flag1, flags1;
int allocated = map->m_len;
@@ -3183,17 +3312,17 @@
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- uninitialized = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
- if (uninitialized)
- split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2;
+ if (unwritten)
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2;
if (split_flag & EXT4_EXT_DATA_VALID2)
split_flag1 |= EXT4_EXT_DATA_VALID1;
- err = ext4_split_extent_at(handle, inode, path,
+ err = ext4_split_extent_at(handle, inode, ppath,
map->m_lblk + map->m_len, split_flag1, flags1);
if (err)
goto out;
@@ -3204,23 +3333,27 @@
* Update path is required because previous ext4_split_extent_at() may
* result in split of original leaf or extent zeroout.
*/
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path);
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
- uninitialized = ext4_ext_is_uninitialized(ex);
+ if (!ex) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) map->m_lblk);
+ return -EIO;
+ }
+ unwritten = ext4_ext_is_unwritten(ex);
split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
- if (uninitialized) {
- split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+ if (unwritten) {
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT2);
+ EXT4_EXT_MARK_UNWRIT2);
}
- err = ext4_split_extent_at(handle, inode, path,
+ err = ext4_split_extent_at(handle, inode, ppath,
map->m_lblk, split_flag1, flags);
if (err)
goto out;
@@ -3233,16 +3366,16 @@
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
- * to an uninitialized extent. It may result in splitting the uninitialized
+ * to an unwritten extent. It may result in splitting the unwritten
* extent into multiple extents (up to three - one initialized and two
- * uninitialized).
+ * unwritten).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* Pre-conditions:
- * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' is unwritten.
* - The extent pointed to by 'path' contains a superset
* of the logical span [map->m_lblk, map->m_lblk + map->m_len).
*
@@ -3254,9 +3387,10 @@
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
@@ -3288,12 +3422,12 @@
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/* Pre-conditions */
- BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!ext4_ext_is_unwritten(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
/*
* Attempt to transfer newly initialized blocks from the currently
- * uninitialized extent to its neighbor. This is much cheaper
+ * unwritten extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
* memmove() calls. Transferring to the left is the common case in
* steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
@@ -3329,7 +3463,7 @@
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
(prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3344,7 +3478,7 @@
ex->ee_block = cpu_to_le32(ee_block + map_len);
ext4_ext_store_pblock(ex, ee_pblk + map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
@@ -3375,7 +3509,7 @@
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((map->m_lblk + map_len) == next_lblk) && /*C2*/
((ee_pblk + ee_len) == next_pblk) && /*C3*/
(next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3390,7 +3524,7 @@
abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(next_len + map_len);
@@ -3412,7 +3546,7 @@
WARN_ON(map->m_lblk < ee_block);
/*
* It is safe to convert extent to initialized via explicit
- * zeroout only if extent is fully insde i_size or new_size.
+ * zeroout only if extent is fully inside i_size or new_size.
*/
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
@@ -3480,55 +3614,57 @@
}
}
- allocated = ext4_split_extent(handle, inode, path,
- &split_map, split_flag, flags);
- if (allocated < 0)
- err = allocated;
-
+ err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag,
+ flags);
+ if (err > 0)
+ err = 0;
out:
/* If we have gotten a failure, don't zero out status tree */
if (!err)
- err = ext4_es_zeroout(inode, &zero_ex);
+ err = ext4_zeroout_es(inode, &zero_ex);
return err ? err : allocated;
}
/*
* This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
- * to an uninitialized extent.
+ * to an unwritten extent.
*
- * Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple initialized/uninitialized extents (up to three)
+ * Writing to an unwritten extent may result in splitting the unwritten
+ * extent into multiple initialized/unwritten extents (up to three)
* There are three possibilities:
- * a> There is no split required: Entire extent should be uninitialized
+ * a> There is no split required: Entire extent should be unwritten
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
+ * This works the same way in the case of initialized -> unwritten conversion.
+ *
* One of more index blocks maybe needed if the extent tree grow after
- * the uninitialized extent split. To prevent ENOSPC occur at the IO
- * complete, we need to split the uninitialized extent before DIO submit
- * the IO. The uninitialized extent called at this time will be split
- * into three uninitialized extent(at most). After IO complete, the part
+ * the unwritten extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the unwritten extent before DIO submit
+ * the IO. The unwritten extent called at this time will be split
+ * into three unwritten extent(at most). After IO complete, the part
* being filled will be convert to initialized by the end_io callback function
* via ext4_convert_unwritten_extents().
*
- * Returns the size of uninitialized extent to be written on success.
+ * Returns the size of unwritten extent to be written on success.
*/
-static int ext4_split_unwritten_extents(handle_t *handle,
+static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_lblk_t eof_block;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
unsigned int ee_len;
int split_flag = 0, depth;
- ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
- "block %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)map->m_lblk, map->m_len);
+ ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
+ __func__, inode->i_ino,
+ (unsigned long long)map->m_lblk, map->m_len);
eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
inode->i_sb->s_blocksize_bits;
@@ -3543,19 +3679,25 @@
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
- split_flag |= EXT4_EXT_MARK_UNINIT2;
- if (flags & EXT4_GET_BLOCKS_CONVERT)
- split_flag |= EXT4_EXT_DATA_VALID2;
+ /* Convert to unwritten */
+ if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
+ split_flag |= EXT4_EXT_DATA_VALID1;
+ /* Convert to initialized */
+ } else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+ split_flag |= ee_block + ee_len <= eof_block ?
+ EXT4_EXT_MAY_ZEROOUT : 0;
+ split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
+ }
flags |= EXT4_GET_BLOCKS_PRE_IO;
- return ext4_split_extent(handle, inode, path, map, split_flag, flags);
+ return ext4_split_extent(handle, inode, ppath, map, split_flag, flags);
}
static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path)
+ struct ext4_ext_path **ppath)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_extent *ex;
ext4_lblk_t ee_block;
unsigned int ee_len;
@@ -3584,16 +3726,13 @@
inode->i_ino, (unsigned long long)ee_block, ee_len,
(unsigned long long)map->m_lblk, map->m_len);
#endif
- err = ext4_split_unwritten_extents(handle, inode, map, path,
- EXT4_GET_BLOCKS_CONVERT);
+ err = ext4_split_convert_extents(handle, inode, map, ppath,
+ EXT4_GET_BLOCKS_CONVERT);
if (err < 0)
- goto out;
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- goto out;
- }
+ return err;
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
}
@@ -3786,34 +3925,109 @@
}
static int
-ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+convert_initialized_extent(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map,
+ struct ext4_ext_path **ppath, int flags,
+ unsigned int allocated, ext4_fsblk_t newblock)
+{
+ struct ext4_ext_path *path = *ppath;
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+ unsigned int ee_len;
+ int depth;
+ int err = 0;
+
+ /*
+ * Make sure that the extent is no bigger than we support with
+ * unwritten extent
+ */
+ if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
+ map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
+
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
+
+ ext_debug("%s: inode %lu, logical"
+ "block %llu, max_blocks %u\n", __func__, inode->i_ino,
+ (unsigned long long)ee_block, ee_len);
+
+ if (ee_block != map->m_lblk || ee_len > map->m_len) {
+ err = ext4_split_convert_extents(handle, inode, map, ppath,
+ EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+ if (err < 0)
+ return err;
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ if (!ex) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) map->m_lblk);
+ return -EIO;
+ }
+ }
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ return err;
+ /* first mark the extent as unwritten */
+ ext4_ext_mark_unwritten(ex);
+
+ /* note: ext4_ext_correct_indexes() isn't needed here because
+ * borders are not changed
+ */
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+
+ /* Mark modified extent as dirty */
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (err)
+ return err;
+ ext4_ext_show_leaf(inode, path);
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len);
+ if (err)
+ return err;
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ map->m_len = allocated;
+ return allocated;
+}
+
+static int
+ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path, int flags,
+ struct ext4_ext_path **ppath, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
{
+ struct ext4_ext_path *path = *ppath;
int ret = 0;
int err = 0;
ext4_io_end_t *io = ext4_inode_aio(inode);
- ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
+ ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
"block %llu, max_blocks %u, flags %x, allocated %u\n",
inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
flags, allocated);
ext4_ext_show_leaf(inode, path);
/*
- * When writing into uninitialized space, we should not fail to
+ * When writing into unwritten space, we should not fail to
* allocate metadata blocks for the new extent block if needed.
*/
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
- trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
+ trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
/* get_block() before submit the IO, split the extent */
- if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- ret = ext4_split_unwritten_extents(handle, inode, map,
- path, flags);
+ if (flags & EXT4_GET_BLOCKS_PRE_IO) {
+ ret = ext4_split_convert_extents(handle, inode, map, ppath,
+ flags | EXT4_GET_BLOCKS_CONVERT);
if (ret <= 0)
goto out;
/*
@@ -3826,14 +4040,12 @@
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
map->m_flags |= EXT4_MAP_UNWRITTEN;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
- if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+ if (flags & EXT4_GET_BLOCKS_CONVERT) {
ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
- path);
+ ppath);
if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
err = check_eofblocks_fl(handle, inode, map->m_lblk,
@@ -3841,6 +4053,7 @@
} else
err = ret;
map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
@@ -3851,7 +4064,7 @@
* repeat fallocate creation request
* we already have an unwritten extent
*/
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
}
@@ -3870,7 +4083,7 @@
}
/* buffered write, writepage time, convert*/
- ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags);
+ ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out:
@@ -3927,10 +4140,6 @@
map->m_pblk = newblock;
map->m_len = allocated;
out2:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
return err ? err : allocated;
}
@@ -4075,7 +4284,7 @@
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* find extent for this block */
- path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
+ path = ext4_find_extent(inode, map->m_lblk, NULL, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
@@ -4087,7 +4296,7 @@
/*
* consistent leaf must not be empty;
* this situation is possible, though, _during_ tree modification;
- * this is why assert can't be put in ext4_ext_find_extent()
+ * this is why assert can't be put in ext4_find_extent()
*/
if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
EXT4_ERROR_INODE(inode, "bad extent address "
@@ -4104,8 +4313,9 @@
ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
unsigned short ee_len;
+
/*
- * Uninitialized extents are treated as holes, except that
+ * unwritten extents are treated as holes, except that
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
@@ -4120,17 +4330,27 @@
ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
ee_block, ee_len, newblock);
- if (!ext4_ext_is_uninitialized(ex))
+ /*
+ * If the extent is initialized check whether the
+ * caller wants to convert it to unwritten.
+ */
+ if ((!ext4_ext_is_unwritten(ex)) &&
+ (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
+ allocated = convert_initialized_extent(
+ handle, inode, map, &path,
+ flags, allocated, newblock);
+ goto out2;
+ } else if (!ext4_ext_is_unwritten(ex))
goto out;
- ret = ext4_ext_handle_uninitialized_extents(
- handle, inode, map, path, flags,
+ ret = ext4_ext_handle_unwritten_extents(
+ handle, inode, map, &path, flags,
allocated, newblock);
if (ret < 0)
err = ret;
else
allocated = ret;
- goto out3;
+ goto out2;
}
}
@@ -4161,7 +4381,7 @@
/*
* If we are doing bigalloc, check to see if the extent returned
- * by ext4_ext_find_extent() implies a cluster we can use.
+ * by ext4_find_extent() implies a cluster we can use.
*/
if (cluster_offset && ex &&
get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
@@ -4195,15 +4415,15 @@
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
- * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
- * EXT_UNINIT_MAX_LEN.
+ * EXT_INIT_MAX_LEN and for an unwritten extent this limit is
+ * EXT_UNWRITTEN_MAX_LEN.
*/
if (map->m_len > EXT_INIT_MAX_LEN &&
- !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+ !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_INIT_MAX_LEN;
- else if (map->m_len > EXT_UNINIT_MAX_LEN &&
- (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
- map->m_len = EXT_UNINIT_MAX_LEN;
+ else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
+ (flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
+ map->m_len = EXT_UNWRITTEN_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
newex.ee_len = cpu_to_le16(map->m_len);
@@ -4236,6 +4456,8 @@
ar.flags = 0;
if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
ar.flags |= EXT4_MB_HINT_NOPREALLOC;
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ar.flags |= EXT4_MB_DELALLOC_RESERVED;
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
@@ -4251,21 +4473,19 @@
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
- /* Mark uninitialized */
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
- ext4_ext_mark_uninitialized(&newex);
+ /* Mark unwritten */
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
+ ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
- * uninitialized extent. To avoid unnecessary conversion,
+ * unwritten extent. To avoid unnecessary conversion,
* here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform conversion when IO is done.
*/
- if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+ if (flags & EXT4_GET_BLOCKS_PRE_IO)
set_unwritten = 1;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
}
err = 0;
@@ -4273,7 +4493,7 @@
err = check_eofblocks_fl(handle, inode, map->m_lblk,
path, ar.len);
if (!err)
- err = ext4_ext_insert_extent(handle, inode, path,
+ err = ext4_ext_insert_extent(handle, inode, &path,
&newex, flags);
if (!err && set_unwritten) {
@@ -4291,8 +4511,8 @@
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_discard_preallocations(inode);
- ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
- ext4_ext_get_actual_len(&newex), fb_flags);
+ ext4_free_blocks(handle, inode, NULL, newblock,
+ EXT4_C2B(sbi, allocated_clusters), fb_flags);
goto out2;
}
@@ -4392,9 +4612,9 @@
/*
* Cache the extent and update transaction to commit on fdatasync only
- * when it is _not_ an uninitialized extent.
+ * when it is _not_ an unwritten extent.
*/
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
@@ -4406,14 +4626,12 @@
map->m_pblk = newblock;
map->m_len = allocated;
out2:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
+ ext4_ext_drop_refs(path);
+ kfree(path);
-out3:
- trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated);
-
+ trace_ext4_ext_map_blocks_exit(inode, flags, map,
+ err ? err : allocated);
+ ext4_es_lru_add(inode);
return err ? err : allocated;
}
@@ -4451,34 +4669,240 @@
ext4_std_error(inode->i_sb, err);
}
-static void ext4_falloc_update_inode(struct inode *inode,
- int mode, loff_t new_size, int update_ctime)
+static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
+ ext4_lblk_t len, loff_t new_size,
+ int flags, int mode)
{
- struct timespec now;
+ struct inode *inode = file_inode(file);
+ handle_t *handle;
+ int ret = 0;
+ int ret2 = 0;
+ int retries = 0;
+ struct ext4_map_blocks map;
+ unsigned int credits;
+ loff_t epos;
- if (update_ctime) {
- now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_ctime, &now))
- inode->i_ctime = now;
- }
+ map.m_lblk = offset;
+ map.m_len = len;
/*
- * Update only when preallocation was requested beyond
- * the file size.
+ * Don't normalize the request if it can fit in one extent so
+ * that it doesn't get unnecessarily split into multiple
+ * extents.
*/
- if (!(mode & FALLOC_FL_KEEP_SIZE)) {
- if (new_size > i_size_read(inode))
- i_size_write(inode, new_size);
- if (new_size > EXT4_I(inode)->i_disksize)
- ext4_update_i_disksize(inode, new_size);
+ if (len <= EXT_UNWRITTEN_MAX_LEN)
+ flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
+ /*
+ * credits to insert 1 extent into extent tree
+ */
+ credits = ext4_chunk_trans_blocks(inode, len);
+
+retry:
+ while (ret >= 0 && len) {
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ break;
+ }
+ ret = ext4_map_blocks(handle, inode, &map, flags);
+ if (ret <= 0) {
+ ext4_debug("inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ inode->i_ino, map.m_lblk,
+ map.m_len, ret);
+ ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_journal_stop(handle);
+ break;
+ }
+ map.m_lblk += ret;
+ map.m_len = len = len - ret;
+ epos = (loff_t)map.m_lblk << inode->i_blkbits;
+ inode->i_ctime = ext4_current_time(inode);
+ if (new_size) {
+ if (epos > new_size)
+ epos = new_size;
+ if (ext4_update_inode_size(inode, epos) & 0x1)
+ inode->i_mtime = inode->i_ctime;
+ } else {
+ if (epos > inode->i_size)
+ ext4_set_inode_flag(inode,
+ EXT4_INODE_EOFBLOCKS);
+ }
+ ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_journal_stop(handle);
+ if (ret2)
+ break;
+ }
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ ret = 0;
+ goto retry;
+ }
+
+ return ret > 0 ? ret2 : ret;
+}
+
+static long ext4_zero_range(struct file *file, loff_t offset,
+ loff_t len, int mode)
+{
+ struct inode *inode = file_inode(file);
+ handle_t *handle = NULL;
+ unsigned int max_blocks;
+ loff_t new_size = 0;
+ int ret = 0;
+ int flags;
+ int credits;
+ int partial_begin, partial_end;
+ loff_t start, end;
+ ext4_lblk_t lblk;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned int blkbits = inode->i_blkbits;
+
+ trace_ext4_zero_range(inode, offset, len, mode);
+
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Write out all dirty pages to avoid race conditions
+ * Then release them.
+ */
+ if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ ret = filemap_write_and_wait_range(mapping, offset,
+ offset + len - 1);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Round up offset. This is not fallocate, we neet to zero out
+ * blocks, so convert interior block aligned part of the range to
+ * unwritten and possibly manually zero out unaligned parts of the
+ * range.
+ */
+ start = round_up(offset, 1 << blkbits);
+ end = round_down((offset + len), 1 << blkbits);
+
+ if (start < offset || end > offset + len)
+ return -EINVAL;
+ partial_begin = offset & ((1 << blkbits) - 1);
+ partial_end = (offset + len) & ((1 << blkbits) - 1);
+
+ lblk = start >> blkbits;
+ max_blocks = (end >> blkbits);
+ if (max_blocks < lblk)
+ max_blocks = 0;
+ else
+ max_blocks -= lblk;
+
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
+ EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+ EXT4_EX_NOCACHE;
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+
+ mutex_lock(&inode->i_mutex);
+
+ /*
+ * Indirect files do not support unwritten extnets
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ ret = -EOPNOTSUPP;
+ goto out_mutex;
+ }
+
+ if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+ offset + len > i_size_read(inode)) {
+ new_size = offset + len;
+ ret = inode_newsize_ok(inode, new_size);
+ if (ret)
+ goto out_mutex;
+ /*
+ * If we have a partial block after EOF we have to allocate
+ * the entire block.
+ */
+ if (partial_end)
+ max_blocks += 1;
+ }
+
+ if (max_blocks > 0) {
+
+ /* Now release the pages and zero block aligned part of pages*/
+ truncate_pagecache_range(inode, start, end - 1);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+ flags, mode);
+ if (ret)
+ goto out_dio;
+ /*
+ * Remove entire range from the extent status tree.
+ *
+ * ext4_es_remove_extent(inode, lblk, max_blocks) is
+ * NOT sufficient. I'm not sure why this is the case,
+ * but let's be conservative and remove the extent
+ * status tree for the entire inode. There should be
+ * no outstanding delalloc extents thanks to the
+ * filemap_write_and_wait_range() call above.
+ */
+ ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
+ if (ret)
+ goto out_dio;
+ }
+ if (!partial_begin && !partial_end)
+ goto out_dio;
+
+ /*
+ * In worst case we have to writeout two nonadjacent unwritten
+ * blocks and update the inode
+ */
+ credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1;
+ if (ext4_should_journal_data(inode))
+ credits += 2;
+ handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ ext4_std_error(inode->i_sb, ret);
+ goto out_dio;
+ }
+
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ if (new_size) {
+ ext4_update_inode_size(inode, new_size);
} else {
/*
- * Mark that we allocate beyond EOF so the subsequent truncate
- * can proceed even if the new size is the same as i_size.
- */
- if (new_size > i_size_read(inode))
+ * Mark that we allocate beyond EOF so the subsequent truncate
+ * can proceed even if the new size is the same as i_size.
+ */
+ if ((offset + len) > i_size_read(inode))
ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}
+ ext4_mark_inode_dirty(handle, inode);
+ /* Zero out partial block at the edges of the range */
+ ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+
+ if (file->f_flags & O_SYNC)
+ ext4_handle_sync(handle);
+
+ ext4_journal_stop(handle);
+out_dio:
+ ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
}
/*
@@ -4491,22 +4915,34 @@
long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
- handle_t *handle;
- loff_t new_size;
+ loff_t new_size = 0;
unsigned int max_blocks;
int ret = 0;
- int ret2 = 0;
- int retries = 0;
int flags;
- struct ext4_map_blocks map;
- unsigned int credits, blkbits = inode->i_blkbits;
+ ext4_lblk_t lblk;
+ unsigned int blkbits = inode->i_blkbits;
+
+ /*
+ * Encrypted inodes can't handle collapse range or insert
+ * range since we would need to re-encrypt blocks with a
+ * different IV or XTS tweak (which are based on the logical
+ * block number).
+ *
+ * XXX It's not clear why zero range isn't working, but we'll
+ * leave it disabled for encrypted inodes for now. This is a
+ * bug we should fix....
+ */
+ if (ext4_encrypted_inode(inode) &&
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)))
+ return -EOPNOTSUPP;
/* Return error if mode is not supported */
- if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
if (mode & FALLOC_FL_PUNCH_HOLE)
- return ext4_punch_hole(file, offset, len);
+ return ext4_punch_hole(inode, offset, len);
ret = ext4_convert_inline_data(inode);
if (ret)
@@ -4519,83 +4955,48 @@
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
+ if (mode & FALLOC_FL_COLLAPSE_RANGE)
+ return ext4_collapse_range(inode, offset, len);
+
+ if (mode & FALLOC_FL_ZERO_RANGE)
+ return ext4_zero_range(file, offset, len, mode);
+
trace_ext4_fallocate_enter(inode, offset, len, mode);
- map.m_lblk = offset >> blkbits;
+ lblk = offset >> blkbits;
/*
* We can't just convert len to max_blocks because
* If blocksize = 4096 offset = 3072 and len = 2048
*/
max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- - map.m_lblk;
- /*
- * credits to insert 1 extent into extent tree
- */
- credits = ext4_chunk_trans_blocks(inode, max_blocks);
- mutex_lock(&inode->i_mutex);
- ret = inode_newsize_ok(inode, (len + offset));
- if (ret) {
- mutex_unlock(&inode->i_mutex);
- trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
- return ret;
- }
- flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ - lblk;
+
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
- /*
- * Don't normalize the request if it can fit in one extent so
- * that it doesn't get unnecessarily split into multiple
- * extents.
- */
- if (len <= EXT_UNINIT_MAX_LEN << blkbits)
- flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
-retry:
- while (ret >= 0 && ret < max_blocks) {
- map.m_lblk = map.m_lblk + ret;
- map.m_len = max_blocks = max_blocks - ret;
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
- credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- break;
- }
- ret = ext4_map_blocks(handle, inode, &map, flags);
- if (ret <= 0) {
-#ifdef EXT4FS_DEBUG
- ext4_warning(inode->i_sb,
- "inode #%lu: block %u: len %u: "
- "ext4_ext_map_blocks returned %d",
- inode->i_ino, map.m_lblk,
- map.m_len, ret);
-#endif
- ext4_mark_inode_dirty(handle, inode);
- ret2 = ext4_journal_stop(handle);
- break;
- }
- if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
- blkbits) >> blkbits))
- new_size = offset + len;
- else
- new_size = ((loff_t) map.m_lblk + ret) << blkbits;
+ mutex_lock(&inode->i_mutex);
- ext4_falloc_update_inode(inode, mode, new_size,
- (map.m_flags & EXT4_MAP_NEW));
- ext4_mark_inode_dirty(handle, inode);
- if ((file->f_flags & O_SYNC) && ret >= max_blocks)
- ext4_handle_sync(handle);
- ret2 = ext4_journal_stop(handle);
- if (ret2)
- break;
+ if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+ offset + len > i_size_read(inode)) {
+ new_size = offset + len;
+ ret = inode_newsize_ok(inode, new_size);
+ if (ret)
+ goto out;
}
- if (ret == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries)) {
- ret = 0;
- goto retry;
+
+ ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+ flags, mode);
+ if (ret)
+ goto out;
+
+ if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
+ ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+ EXT4_I(inode)->i_sync_tid);
}
+out:
mutex_unlock(&inode->i_mutex);
- trace_ext4_fallocate_exit(inode, offset, max_blocks,
- ret > 0 ? ret2 : ret);
- return ret > 0 ? ret2 : ret;
+ trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+ return ret;
}
/*
@@ -4608,10 +5009,9 @@
* function, to convert the fallocated extents after IO is completed.
* Returns 0 on success.
*/
-int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- ssize_t len)
+int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
+ loff_t offset, ssize_t len)
{
- handle_t *handle;
unsigned int max_blocks;
int ret = 0;
int ret2 = 0;
@@ -4626,16 +5026,32 @@
max_blocks = ((EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) -
map.m_lblk);
/*
- * credits to insert 1 extent into extent tree
+ * This is somewhat ugly but the idea is clear: When transaction is
+ * reserved, everything goes into it. Otherwise we rather start several
+ * smaller transactions for conversion of each extent separately.
*/
- credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ if (handle) {
+ handle = ext4_journal_start_reserved(handle,
+ EXT4_HT_EXT_CONVERT);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ credits = 0;
+ } else {
+ /*
+ * credits to insert 1 extent into extent tree
+ */
+ credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ }
while (ret >= 0 && ret < max_blocks) {
map.m_lblk += ret;
map.m_len = (max_blocks -= ret);
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- break;
+ if (credits) {
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ break;
+ }
}
ret = ext4_map_blocks(handle, inode, &map,
EXT4_GET_BLOCKS_IO_CONVERT_EXT);
@@ -4646,10 +5062,13 @@
inode->i_ino, map.m_lblk,
map.m_len, ret);
ext4_mark_inode_dirty(handle, inode);
- ret2 = ext4_journal_stop(handle);
- if (ret <= 0 || ret2 )
+ if (credits)
+ ret2 = ext4_journal_stop(handle);
+ if (ret <= 0 || ret2)
break;
}
+ if (!credits)
+ ret2 = ext4_journal_stop(handle);
return ret > 0 ? ret2 : ret;
}
@@ -4752,6 +5171,12 @@
return error;
}
+ if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+ error = ext4_ext_precache(inode);
+ if (error)
+ return error;
+ }
+
/* fallback to generic here if not in extents fmt */
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
@@ -4779,6 +5204,519 @@
error = ext4_fill_fiemap_extents(inode, start_blk,
len_blks, fieinfo);
}
-
+ ext4_es_lru_add(inode);
return error;
}
+
+/*
+ * ext4_access_path:
+ * Function to access the path buffer for marking it dirty.
+ * It also checks if there are sufficient credits left in the journal handle
+ * to update path.
+ */
+static int
+ext4_access_path(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ int credits, err;
+
+ if (!ext4_handle_valid(handle))
+ return 0;
+
+ /*
+ * Check if need to extend journal credits
+ * 3 for leaf, sb, and inode plus 2 (bmap and group
+ * descriptor) for each block group; assume two block
+ * groups
+ */
+ if (handle->h_buffer_credits < 7) {
+ credits = ext4_writepage_trans_blocks(inode);
+ err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+ /* EAGAIN is success */
+ if (err && err != -EAGAIN)
+ return err;
+ }
+
+ err = ext4_ext_get_access(handle, inode, path);
+ return err;
+}
+
+/*
+ * ext4_ext_shift_path_extents:
+ * Shift the extents of a path structure lying between path[depth].p_ext
+ * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift
+ * from starting block for each extent.
+ */
+static int
+ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
+ struct inode *inode, handle_t *handle,
+ ext4_lblk_t *start)
+{
+ int depth, err = 0;
+ struct ext4_extent *ex_start, *ex_last;
+ bool update = 0;
+ depth = path->p_depth;
+
+ while (depth >= 0) {
+ if (depth == path->p_depth) {
+ ex_start = path[depth].p_ext;
+ if (!ex_start)
+ return -EIO;
+
+ ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+ if (!ex_last)
+ return -EIO;
+
+ err = ext4_access_path(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
+ update = 1;
+
+ *start = le32_to_cpu(ex_last->ee_block) +
+ ext4_ext_get_actual_len(ex_last);
+
+ while (ex_start <= ex_last) {
+ le32_add_cpu(&ex_start->ee_block, -shift);
+ /* Try to merge to the left. */
+ if ((ex_start >
+ EXT_FIRST_EXTENT(path[depth].p_hdr)) &&
+ ext4_ext_try_to_merge_right(inode,
+ path, ex_start - 1))
+ ex_last--;
+ else
+ ex_start++;
+ }
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ if (--depth < 0 || !update)
+ break;
+ }
+
+ /* Update index too */
+ err = ext4_access_path(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ le32_add_cpu(&path[depth].p_idx->ei_block, -shift);
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ /* we are done if current index is not a starting index */
+ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
+ break;
+
+ depth--;
+ }
+
+out:
+ return err;
+}
+
+/*
+ * ext4_ext_shift_extents:
+ * All the extents which lies in the range from start to the last allocated
+ * block for the file are shifted downwards by shift blocks.
+ * On success, 0 is returned, error otherwise.
+ */
+static int
+ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
+ ext4_lblk_t start, ext4_lblk_t shift)
+{
+ struct ext4_ext_path *path;
+ int ret = 0, depth;
+ struct ext4_extent *extent;
+ ext4_lblk_t stop_block;
+ ext4_lblk_t ex_start, ex_end;
+
+ /* Let path point to the last extent */
+ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (!extent)
+ goto out;
+
+ stop_block = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
+
+ /* Nothing to shift, if hole is at the end of file */
+ if (start >= stop_block)
+ goto out;
+
+ /*
+ * Don't start shifting extents until we make sure the hole is big
+ * enough to accomodate the shift.
+ */
+ path = ext4_find_extent(inode, start - 1, &path, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (extent) {
+ ex_start = le32_to_cpu(extent->ee_block);
+ ex_end = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
+ } else {
+ ex_start = 0;
+ ex_end = 0;
+ }
+
+ if ((start == ex_start && shift > ex_start) ||
+ (shift > start - ex_end))
+ return -EINVAL;
+
+ /* Its safe to start updating extents */
+ while (start < stop_block) {
+ path = ext4_find_extent(inode, start, &path, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (!extent) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) start);
+ return -EIO;
+ }
+ if (start > le32_to_cpu(extent->ee_block)) {
+ /* Hole, move to the next extent */
+ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) {
+ path[depth].p_ext++;
+ } else {
+ start = ext4_ext_next_allocated_block(path);
+ continue;
+ }
+ }
+ ret = ext4_ext_shift_path_extents(path, shift, inode,
+ handle, &start);
+ if (ret)
+ break;
+ }
+out:
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ return ret;
+}
+
+/*
+ * ext4_collapse_range:
+ * This implements the fallocate's collapse range functionality for ext4
+ * Returns: 0 and non-zero on error.
+ */
+int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct super_block *sb = inode->i_sb;
+ ext4_lblk_t punch_start, punch_stop;
+ handle_t *handle;
+ unsigned int credits;
+ loff_t new_size, ioffset;
+ loff_t oldsize = i_size_read(inode);
+ int ret;
+
+ /* Collapse range works only on fs block size aligned offsets. */
+ if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
+ len & (EXT4_CLUSTER_SIZE(sb) - 1))
+ return -EINVAL;
+
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ trace_ext4_collapse_range(inode, offset, len);
+
+ punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+ punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Need to round down offset to be aligned with page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+
+ /* Write out all dirty pages */
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+ LLONG_MAX);
+ if (ret)
+ return ret;
+
+ /* Take mutex lock */
+ mutex_lock(&inode->i_mutex);
+
+ /*
+ * There is no need to overlap collapse range with EOF, in which case
+ * it is effectively a truncate operation
+ */
+ if (offset + len >= oldsize) {
+ ret = -EINVAL;
+ goto out_mutex;
+ }
+
+ /* Currently just for extent based files */
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ ret = -EOPNOTSUPP;
+ goto out_mutex;
+ }
+
+ truncate_pagecache(inode, oldsize, ioffset);
+
+ /* Wait for existing dio to complete */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ credits = ext4_writepage_trans_blocks(inode);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_dio;
+ }
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
+
+ ret = ext4_es_remove_extent(inode, punch_start,
+ EXT_MAX_BLOCKS - punch_start);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+ ext4_discard_preallocations(inode);
+
+ ret = ext4_ext_shift_extents(inode, handle, punch_stop,
+ punch_stop - punch_start);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ new_size = i_size_read(inode) - len;
+ i_size_write(inode, new_size);
+ EXT4_I(inode)->i_disksize = new_size;
+
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+
+out_stop:
+ ext4_journal_stop(handle);
+out_dio:
+ ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
+/**
+ * ext4_swap_extents - Swap extents between two inodes
+ *
+ * @inode1: First inode
+ * @inode2: Second inode
+ * @lblk1: Start block for first inode
+ * @lblk2: Start block for second inode
+ * @count: Number of blocks to swap
+ * @mark_unwritten: Mark second inode's extents as unwritten after swap
+ * @erp: Pointer to save error value
+ *
+ * This helper routine does exactly what is promise "swap extents". All other
+ * stuff such as page-cache locking consistency, bh mapping consistency or
+ * extent's data copying must be performed by caller.
+ * Locking:
+ * i_mutex is held for both inodes
+ * i_data_sem is locked for write for both inodes
+ * Assumptions:
+ * All pages from requested range are locked for both inodes
+ */
+int
+ext4_swap_extents(handle_t *handle, struct inode *inode1,
+ struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2,
+ ext4_lblk_t count, int unwritten, int *erp)
+{
+ struct ext4_ext_path *path1 = NULL;
+ struct ext4_ext_path *path2 = NULL;
+ int replaced_count = 0;
+
+ BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem));
+ BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem));
+ BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+ BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+
+ *erp = ext4_es_remove_extent(inode1, lblk1, count);
+ if (unlikely(*erp))
+ return 0;
+ *erp = ext4_es_remove_extent(inode2, lblk2, count);
+ if (unlikely(*erp))
+ return 0;
+
+ while (count) {
+ struct ext4_extent *ex1, *ex2, tmp_ex;
+ ext4_lblk_t e1_blk, e2_blk;
+ int e1_len, e2_len, len;
+ int split = 0;
+
+ path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE);
+ if (unlikely(IS_ERR(path1))) {
+ *erp = PTR_ERR(path1);
+ path1 = NULL;
+ finish:
+ count = 0;
+ goto repeat;
+ }
+ path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE);
+ if (unlikely(IS_ERR(path2))) {
+ *erp = PTR_ERR(path2);
+ path2 = NULL;
+ goto finish;
+ }
+ ex1 = path1[path1->p_depth].p_ext;
+ ex2 = path2[path2->p_depth].p_ext;
+ /* Do we have somthing to swap ? */
+ if (unlikely(!ex2 || !ex1))
+ goto finish;
+
+ e1_blk = le32_to_cpu(ex1->ee_block);
+ e2_blk = le32_to_cpu(ex2->ee_block);
+ e1_len = ext4_ext_get_actual_len(ex1);
+ e2_len = ext4_ext_get_actual_len(ex2);
+
+ /* Hole handling */
+ if (!in_range(lblk1, e1_blk, e1_len) ||
+ !in_range(lblk2, e2_blk, e2_len)) {
+ ext4_lblk_t next1, next2;
+
+ /* if hole after extent, then go to next extent */
+ next1 = ext4_ext_next_allocated_block(path1);
+ next2 = ext4_ext_next_allocated_block(path2);
+ /* If hole before extent, then shift to that extent */
+ if (e1_blk > lblk1)
+ next1 = e1_blk;
+ if (e2_blk > lblk2)
+ next2 = e1_blk;
+ /* Do we have something to swap */
+ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS)
+ goto finish;
+ /* Move to the rightest boundary */
+ len = next1 - lblk1;
+ if (len < next2 - lblk2)
+ len = next2 - lblk2;
+ if (len > count)
+ len = count;
+ lblk1 += len;
+ lblk2 += len;
+ count -= len;
+ goto repeat;
+ }
+
+ /* Prepare left boundary */
+ if (e1_blk < lblk1) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode1,
+ &path1, lblk1, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ if (e2_blk < lblk2) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode2,
+ &path2, lblk2, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ /* ext4_split_extent_at() may result in leaf extent split,
+ * path must to be revalidated. */
+ if (split)
+ goto repeat;
+
+ /* Prepare right boundary */
+ len = count;
+ if (len > e1_blk + e1_len - lblk1)
+ len = e1_blk + e1_len - lblk1;
+ if (len > e2_blk + e2_len - lblk2)
+ len = e2_blk + e2_len - lblk2;
+
+ if (len != e1_len) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode1,
+ &path1, lblk1 + len, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ if (len != e2_len) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode2,
+ &path2, lblk2 + len, 0);
+ if (*erp)
+ goto finish;
+ }
+ /* ext4_split_extent_at() may result in leaf extent split,
+ * path must to be revalidated. */
+ if (split)
+ goto repeat;
+
+ BUG_ON(e2_len != e1_len);
+ *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+ *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+
+ /* Both extents are fully inside boundaries. Swap it now */
+ tmp_ex = *ex1;
+ ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2));
+ ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex));
+ ex1->ee_len = cpu_to_le16(e2_len);
+ ex2->ee_len = cpu_to_le16(e1_len);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex2);
+ if (ext4_ext_is_unwritten(&tmp_ex))
+ ext4_ext_mark_unwritten(ex1);
+
+ ext4_ext_try_to_merge(handle, inode2, path2, ex2);
+ ext4_ext_try_to_merge(handle, inode1, path1, ex1);
+ *erp = ext4_ext_dirty(handle, inode2, path2 +
+ path2->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+ *erp = ext4_ext_dirty(handle, inode1, path1 +
+ path1->p_depth);
+ /*
+ * Looks scarry ah..? second inode already points to new blocks,
+ * and it was successfully dirtied. But luckily error may happen
+ * only due to journal error, so full transaction will be
+ * aborted anyway.
+ */
+ if (unlikely(*erp))
+ goto finish;
+ lblk1 += len;
+ lblk2 += len;
+ replaced_count += len;
+ count -= len;
+
+ repeat:
+ ext4_ext_drop_refs(path1);
+ kfree(path1);
+ ext4_ext_drop_refs(path2);
+ kfree(path2);
+ path1 = path2 = NULL;
+ }
+ return replaced_count;
+}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 1fefeb7..66ef2d7 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -10,9 +10,11 @@
* Ext4 extents status tree core functions.
*/
#include <linux/rbtree.h>
+#include <linux/list_sort.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
#include "ext4.h"
#include "extents_status.h"
-#include "ext4_extents.h"
#include <trace/events/ext4.h>
@@ -147,6 +149,8 @@
ext4_lblk_t end);
static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
int nr_to_scan);
+static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+ struct ext4_inode_info *locked_ei);
int __init ext4_init_es(void)
{
@@ -182,7 +186,7 @@
while (node) {
struct extent_status *es;
es = rb_entry(node, struct extent_status, rb_node);
- printk(KERN_DEBUG " [%u/%u) %llu %llx",
+ printk(KERN_DEBUG " [%u/%u) %llu %x",
es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
node = rb_next(node);
@@ -260,7 +264,7 @@
if (tree->cache_es) {
es1 = tree->cache_es;
if (in_range(lblk, es1->es_lblk, es1->es_len)) {
- es_debug("%u cached by [%u/%u) %llu %llx\n",
+ es_debug("%u cached by [%u/%u) %llu %x\n",
lblk, es1->es_lblk, es1->es_len,
ext4_es_pblock(es1), ext4_es_status(es1));
goto out;
@@ -291,7 +295,6 @@
read_unlock(&EXT4_I(inode)->i_es_lock);
- ext4_es_lru_add(inode);
trace_ext4_es_find_delayed_extent_range_exit(inode, es);
}
@@ -312,19 +315,27 @@
*/
if (!ext4_es_is_delayed(es)) {
EXT4_I(inode)->i_es_lru_nr++;
- percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ percpu_counter_inc(&EXT4_SB(inode->i_sb)->
+ s_es_stats.es_stats_lru_cnt);
}
+ EXT4_I(inode)->i_es_all_nr++;
+ percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+
return es;
}
static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
{
+ EXT4_I(inode)->i_es_all_nr--;
+ percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+
/* Decrease the lru counter when this es is not delayed */
if (!ext4_es_is_delayed(es)) {
BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
EXT4_I(inode)->i_es_lru_nr--;
- percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ percpu_counter_dec(&EXT4_SB(inode->i_sb)->
+ s_es_stats.es_stats_lru_cnt);
}
kmem_cache_free(ext4_es_cachep, es);
@@ -343,8 +354,14 @@
if (ext4_es_status(es1) != ext4_es_status(es2))
return 0;
- if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
+ if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
+ pr_warn("ES assertion failed when merging extents. "
+ "The sum of lengths of es1 (%d) and es2 (%d) "
+ "is bigger than allowed file size (%d)\n",
+ es1->es_len, es2->es_len, EXT_MAX_BLOCKS);
+ WARN_ON(1);
return 0;
+ }
if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
return 0;
@@ -407,6 +424,8 @@
}
#ifdef ES_AGGRESSIVE_TEST
+#include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */
+
static void ext4_es_insert_extent_ext_check(struct inode *inode,
struct extent_status *es)
{
@@ -417,7 +436,7 @@
unsigned short ee_len;
int depth, ee_status, es_status;
- path = ext4_ext_find_extent(inode, es->es_lblk, NULL);
+ path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path))
return;
@@ -430,7 +449,7 @@
ee_start = ext4_ext_pblock(ex);
ee_len = ext4_ext_get_actual_len(ex);
- ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+ ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
es_status = ext4_es_is_unwritten(es) ? 1 : 0;
/*
@@ -439,11 +458,11 @@
*/
if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
if (in_range(es->es_lblk, ee_block, ee_len)) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu we can find an extent "
"at block [%d/%d/%llu/%c], but we "
- "want to add an delayed/hole extent "
- "[%d/%d/%llu/%llx]\n",
+ "want to add a delayed/hole extent "
+ "[%d/%d/%llu/%x]\n",
inode->i_ino, ee_block, ee_len,
ee_start, ee_status ? 'u' : 'w',
es->es_lblk, es->es_len,
@@ -458,7 +477,7 @@
*/
if (es->es_lblk < ee_block ||
ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
@@ -468,7 +487,7 @@
}
if (ee_status ^ es_status) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
@@ -481,19 +500,17 @@
* that we don't want to add an written/unwritten extent.
*/
if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"can't find an extent at block %d but we want "
- "to add an written/unwritten extent "
- "[%d/%d/%llu/%llx]\n", inode->i_ino,
+ "to add a written/unwritten extent "
+ "[%d/%d/%llu/%x]\n", inode->i_ino,
es->es_lblk, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
}
}
out:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
+ ext4_ext_drop_refs(path);
+ kfree(path);
}
static void ext4_es_insert_extent_ind_check(struct inode *inode,
@@ -519,21 +536,21 @@
* We want to add a delayed/hole extent but this
* block has been allocated.
*/
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"We can find blocks but we want to add a "
- "delayed/hole extent [%d/%d/%llu/%llx]\n",
+ "delayed/hole extent [%d/%d/%llu/%x]\n",
inode->i_ino, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
return;
} else if (ext4_es_is_written(es)) {
if (retval != es->es_len) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu retval %d != es_len %d\n",
inode->i_ino, retval, es->es_len);
return;
}
if (map.m_pblk != ext4_es_pblock(es)) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu m_pblk %llu != "
"es_pblk %llu\n",
inode->i_ino, map.m_pblk,
@@ -549,9 +566,9 @@
}
} else if (retval == 0) {
if (ext4_es_is_written(es)) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"We can't find the block but we want to add "
- "an written extent [%d/%d/%llu/%llx]\n",
+ "a written extent [%d/%d/%llu/%x]\n",
inode->i_ino, es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
return;
@@ -632,22 +649,20 @@
}
/*
- * ext4_es_insert_extent() adds a space to a extent status tree.
- *
- * ext4_es_insert_extent is called by ext4_da_write_begin and
- * ext4_es_remove_extent.
+ * ext4_es_insert_extent() adds information to an inode's extent
+ * status tree.
*
* Return 0 on success, error code on failure.
*/
int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned long long status)
+ unsigned int status)
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
int err = 0;
- es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n",
+ es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
lblk, len, pblk, status, inode->i_ino);
if (!len)
@@ -655,18 +670,9 @@
BUG_ON(end < lblk);
- if ((status & EXTENT_STATUS_DELAYED) &&
- (status & EXTENT_STATUS_WRITTEN)) {
- ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
- " delayed and written which can potentially "
- " cause data loss.\n", lblk, len);
- WARN_ON(1);
- }
-
newes.es_lblk = lblk;
newes.es_len = len;
- ext4_es_store_pblock(&newes, pblk);
- ext4_es_store_status(&newes, status);
+ ext4_es_store_pblock_status(&newes, pblk, status);
trace_ext4_es_insert_extent(inode, &newes);
ext4_es_insert_extent_check(inode, &newes);
@@ -675,18 +681,54 @@
err = __es_remove_extent(inode, lblk, end);
if (err != 0)
goto error;
+retry:
err = __es_insert_extent(inode, &newes);
+ if (err == -ENOMEM && __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
+ EXT4_I(inode)))
+ goto retry;
+ if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
+ err = 0;
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
- ext4_es_lru_add(inode);
ext4_es_print_tree(inode);
return err;
}
/*
+ * ext4_es_cache_extent() inserts information into the extent status
+ * tree if and only if there isn't information about the range in
+ * question already.
+ */
+void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status)
+{
+ struct extent_status *es;
+ struct extent_status newes;
+ ext4_lblk_t end = lblk + len - 1;
+
+ newes.es_lblk = lblk;
+ newes.es_len = len;
+ ext4_es_store_pblock_status(&newes, pblk, status);
+ trace_ext4_es_cache_extent(inode, &newes);
+
+ if (!len)
+ return;
+
+ BUG_ON(end < lblk);
+
+ write_lock(&EXT4_I(inode)->i_es_lock);
+
+ es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk);
+ if (!es || es->es_lblk > end)
+ __es_insert_extent(inode, &newes);
+ write_unlock(&EXT4_I(inode)->i_es_lock);
+}
+
+/*
* ext4_es_lookup_extent() looks up an extent in extent status tree.
*
* ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
@@ -697,6 +739,7 @@
struct extent_status *es)
{
struct ext4_es_tree *tree;
+ struct ext4_es_stats *stats;
struct extent_status *es1 = NULL;
struct rb_node *node;
int found = 0;
@@ -733,16 +776,19 @@
}
out:
+ stats = &EXT4_SB(inode->i_sb)->s_es_stats;
if (found) {
BUG_ON(!es1);
es->es_lblk = es1->es_lblk;
es->es_len = es1->es_len;
es->es_pblk = es1->es_pblk;
+ stats->es_stats_cache_hits++;
+ } else {
+ stats->es_stats_cache_misses++;
}
read_unlock(&EXT4_I(inode)->i_es_lock);
- ext4_es_lru_add(inode);
trace_ext4_es_lookup_extent_exit(inode, es, found);
return found;
}
@@ -756,8 +802,10 @@
struct extent_status orig_es;
ext4_lblk_t len1, len2;
ext4_fsblk_t block;
- int err = 0;
+ int err;
+retry:
+ err = 0;
es = __es_tree_search(&tree->root, lblk);
if (!es)
goto out;
@@ -781,17 +829,21 @@
newes.es_lblk = end + 1;
newes.es_len = len2;
+ block = 0x7FDEADBEEFULL;
if (ext4_es_is_written(&orig_es) ||
- ext4_es_is_unwritten(&orig_es)) {
+ ext4_es_is_unwritten(&orig_es))
block = ext4_es_pblock(&orig_es) +
orig_es.es_len - len2;
- ext4_es_store_pblock(&newes, block);
- }
- ext4_es_store_status(&newes, ext4_es_status(&orig_es));
+ ext4_es_store_pblock_status(&newes, block,
+ ext4_es_status(&orig_es));
err = __es_insert_extent(inode, &newes);
if (err) {
es->es_lblk = orig_es.es_lblk;
es->es_len = orig_es.es_len;
+ if ((err == -ENOMEM) &&
+ __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
+ EXT4_I(inode)))
+ goto retry;
goto out;
}
} else {
@@ -869,85 +921,312 @@
return err;
}
-int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
+static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
+ struct list_head *b)
{
- ext4_lblk_t ee_block;
- ext4_fsblk_t ee_pblock;
- unsigned int ee_len;
+ struct ext4_inode_info *eia, *eib;
+ eia = list_entry(a, struct ext4_inode_info, i_es_lru);
+ eib = list_entry(b, struct ext4_inode_info, i_es_lru);
- ee_block = le32_to_cpu(ex->ee_block);
- ee_len = ext4_ext_get_actual_len(ex);
- ee_pblock = ext4_ext_pblock(ex);
-
- if (ee_len == 0)
+ if (ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
+ !ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
+ return 1;
+ if (!ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
+ ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
+ return -1;
+ if (eia->i_touch_when == eib->i_touch_when)
return 0;
-
- return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
- EXTENT_STATUS_WRITTEN);
+ if (time_after(eia->i_touch_when, eib->i_touch_when))
+ return 1;
+ else
+ return -1;
}
-static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+ struct ext4_inode_info *locked_ei)
+{
+ struct ext4_inode_info *ei;
+ struct ext4_es_stats *es_stats;
+ struct list_head *cur, *tmp;
+ LIST_HEAD(skipped);
+ ktime_t start_time;
+ u64 scan_time;
+ int nr_shrunk = 0;
+ int retried = 0, skip_precached = 1, nr_skipped = 0;
+
+ es_stats = &sbi->s_es_stats;
+ start_time = ktime_get();
+ spin_lock(&sbi->s_es_lru_lock);
+
+retry:
+ list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+ int shrunk;
+
+ /*
+ * If we have already reclaimed all extents from extent
+ * status tree, just stop the loop immediately.
+ */
+ if (percpu_counter_read_positive(
+ &es_stats->es_stats_lru_cnt) == 0)
+ break;
+
+ ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
+
+ /*
+ * Skip the inode that is newer than the last_sorted
+ * time. Normally we try hard to avoid shrinking
+ * precached inodes, but we will as a last resort.
+ */
+ if ((es_stats->es_stats_last_sorted < ei->i_touch_when) ||
+ (skip_precached && ext4_test_inode_state(&ei->vfs_inode,
+ EXT4_STATE_EXT_PRECACHED))) {
+ nr_skipped++;
+ list_move_tail(cur, &skipped);
+ continue;
+ }
+
+ if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+ !write_trylock(&ei->i_es_lock))
+ continue;
+
+ shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
+ if (ei->i_es_lru_nr == 0)
+ list_del_init(&ei->i_es_lru);
+ write_unlock(&ei->i_es_lock);
+
+ nr_shrunk += shrunk;
+ nr_to_scan -= shrunk;
+ if (nr_to_scan == 0)
+ break;
+ }
+
+ /* Move the newer inodes into the tail of the LRU list. */
+ list_splice_tail(&skipped, &sbi->s_es_lru);
+ INIT_LIST_HEAD(&skipped);
+
+ /*
+ * If we skipped any inodes, and we weren't able to make any
+ * forward progress, sort the list and try again.
+ */
+ if ((nr_shrunk == 0) && nr_skipped && !retried) {
+ retried++;
+ list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
+ es_stats->es_stats_last_sorted = jiffies;
+ ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info,
+ i_es_lru);
+ /*
+ * If there are no non-precached inodes left on the
+ * list, start releasing precached extents.
+ */
+ if (ext4_test_inode_state(&ei->vfs_inode,
+ EXT4_STATE_EXT_PRECACHED))
+ skip_precached = 0;
+ goto retry;
+ }
+
+ spin_unlock(&sbi->s_es_lru_lock);
+
+ if (locked_ei && nr_shrunk == 0)
+ nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan);
+
+ scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+ if (likely(es_stats->es_stats_scan_time))
+ es_stats->es_stats_scan_time = (scan_time +
+ es_stats->es_stats_scan_time*3) / 4;
+ else
+ es_stats->es_stats_scan_time = scan_time;
+ if (scan_time > es_stats->es_stats_max_scan_time)
+ es_stats->es_stats_max_scan_time = scan_time;
+ if (likely(es_stats->es_stats_shrunk))
+ es_stats->es_stats_shrunk = (nr_shrunk +
+ es_stats->es_stats_shrunk*3) / 4;
+ else
+ es_stats->es_stats_shrunk = nr_shrunk;
+
+ trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, skip_precached,
+ nr_skipped, retried);
+ return nr_shrunk;
+}
+
+static unsigned long ext4_es_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ unsigned long nr;
+ struct ext4_sb_info *sbi;
+
+ sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker);
+ nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+ trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr);
+ return nr;
+}
+
+static unsigned long ext4_es_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct ext4_sb_info *sbi = container_of(shrink,
struct ext4_sb_info, s_es_shrinker);
- struct ext4_inode_info *ei;
- struct list_head *cur, *tmp, scanned;
int nr_to_scan = sc->nr_to_scan;
- int ret, nr_shrunk = 0;
+ int ret, nr_shrunk;
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
- trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
+ ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+ trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
if (!nr_to_scan)
return ret;
- INIT_LIST_HEAD(&scanned);
+ nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
+ trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
+ return percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+}
+
+static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ if (sc->nr_to_scan)
+ return ext4_es_scan(shrink, sc);
+ else
+ return ext4_es_count(shrink, sc);
+}
+
+static void *ext4_es_seq_shrinker_info_start(struct seq_file *seq, loff_t *pos)
+{
+ return *pos ? NULL : SEQ_START_TOKEN;
+}
+
+static void *
+ext4_es_seq_shrinker_info_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ return NULL;
+}
+
+static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v)
+{
+ struct ext4_sb_info *sbi = seq->private;
+ struct ext4_es_stats *es_stats = &sbi->s_es_stats;
+ struct ext4_inode_info *ei, *max = NULL;
+ unsigned int inode_cnt = 0;
+
+ if (v != SEQ_START_TOKEN)
+ return 0;
+
+ /* here we just find an inode that has the max nr. of objects */
spin_lock(&sbi->s_es_lru_lock);
- list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
- list_move_tail(cur, &scanned);
-
- ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
-
- read_lock(&ei->i_es_lock);
- if (ei->i_es_lru_nr == 0) {
- read_unlock(&ei->i_es_lock);
- continue;
- }
- read_unlock(&ei->i_es_lock);
-
- write_lock(&ei->i_es_lock);
- ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
- write_unlock(&ei->i_es_lock);
-
- nr_shrunk += ret;
- nr_to_scan -= ret;
- if (nr_to_scan == 0)
- break;
+ list_for_each_entry(ei, &sbi->s_es_lru, i_es_lru) {
+ inode_cnt++;
+ if (max && max->i_es_all_nr < ei->i_es_all_nr)
+ max = ei;
+ else if (!max)
+ max = ei;
}
- list_splice_tail(&scanned, &sbi->s_es_lru);
spin_unlock(&sbi->s_es_lru_lock);
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
- trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
+ seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n",
+ percpu_counter_sum_positive(&es_stats->es_stats_all_cnt),
+ percpu_counter_sum_positive(&es_stats->es_stats_lru_cnt));
+ seq_printf(seq, " %lu/%lu cache hits/misses\n",
+ es_stats->es_stats_cache_hits,
+ es_stats->es_stats_cache_misses);
+ if (es_stats->es_stats_last_sorted != 0)
+ seq_printf(seq, " %u ms last sorted interval\n",
+ jiffies_to_msecs(jiffies -
+ es_stats->es_stats_last_sorted));
+ if (inode_cnt)
+ seq_printf(seq, " %d inodes on lru list\n", inode_cnt);
+
+ seq_printf(seq, "average:\n %llu us scan time\n",
+ div_u64(es_stats->es_stats_scan_time, 1000));
+ seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk);
+ if (inode_cnt)
+ seq_printf(seq,
+ "maximum:\n %lu inode (%u objects, %u reclaimable)\n"
+ " %llu us max scan time\n",
+ max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_lru_nr,
+ div_u64(es_stats->es_stats_max_scan_time, 1000));
+
+ return 0;
+}
+
+static void ext4_es_seq_shrinker_info_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations ext4_es_seq_shrinker_info_ops = {
+ .start = ext4_es_seq_shrinker_info_start,
+ .next = ext4_es_seq_shrinker_info_next,
+ .stop = ext4_es_seq_shrinker_info_stop,
+ .show = ext4_es_seq_shrinker_info_show,
+};
+
+static int
+ext4_es_seq_shrinker_info_open(struct inode *inode, struct file *file)
+{
+ int ret;
+
+ ret = seq_open(file, &ext4_es_seq_shrinker_info_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = PDE_DATA(inode);
+ }
+
return ret;
}
-void ext4_es_register_shrinker(struct super_block *sb)
+static int
+ext4_es_seq_shrinker_info_release(struct inode *inode, struct file *file)
{
- struct ext4_sb_info *sbi;
+ return seq_release(inode, file);
+}
- sbi = EXT4_SB(sb);
+static const struct file_operations ext4_es_seq_shrinker_info_fops = {
+ .owner = THIS_MODULE,
+ .open = ext4_es_seq_shrinker_info_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = ext4_es_seq_shrinker_info_release,
+};
+
+int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
+{
+ int err;
+
INIT_LIST_HEAD(&sbi->s_es_lru);
spin_lock_init(&sbi->s_es_lru_lock);
+ sbi->s_es_stats.es_stats_last_sorted = 0;
+ sbi->s_es_stats.es_stats_shrunk = 0;
+ sbi->s_es_stats.es_stats_cache_hits = 0;
+ sbi->s_es_stats.es_stats_cache_misses = 0;
+ sbi->s_es_stats.es_stats_scan_time = 0;
+ sbi->s_es_stats.es_stats_max_scan_time = 0;
+ err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0);
+ if (err)
+ return err;
+ err = percpu_counter_init(&sbi->s_es_stats.es_stats_lru_cnt, 0);
+ if (err)
+ goto err1;
+
sbi->s_es_shrinker.shrink = ext4_es_shrink;
sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&sbi->s_es_shrinker);
+
+ if (sbi->s_proc)
+ proc_create_data("es_shrinker_info", S_IRUGO, sbi->s_proc,
+ &ext4_es_seq_shrinker_info_fops, sbi);
+
+ return 0;
+
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
+err1:
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
+ return err;
}
-void ext4_es_unregister_shrinker(struct super_block *sb)
+void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
{
- unregister_shrinker(&EXT4_SB(sb)->s_es_shrinker);
+ if (sbi->s_proc)
+ remove_proc_entry("es_shrinker_info", sbi->s_proc);
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
+ unregister_shrinker(&sbi->s_es_shrinker);
}
void ext4_es_lru_add(struct inode *inode)
@@ -955,11 +1234,14 @@
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ei->i_touch_when = jiffies;
+
+ if (!list_empty(&ei->i_es_lru))
+ return;
+
spin_lock(&sbi->s_es_lru_lock);
if (list_empty(&ei->i_es_lru))
list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
- else
- list_move_tail(&ei->i_es_lru, &sbi->s_es_lru);
spin_unlock(&sbi->s_es_lru_lock);
}
@@ -981,11 +1263,17 @@
struct ext4_es_tree *tree = &ei->i_es_tree;
struct rb_node *node;
struct extent_status *es;
- int nr_shrunk = 0;
+ unsigned long nr_shrunk = 0;
+ static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
if (ei->i_es_lru_nr == 0)
return 0;
+ if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
+ __ratelimit(&_rs))
+ ext4_warning(inode->i_sb, "forced shrink of precached extents");
+
node = rb_first(&tree->root);
while (node != NULL) {
es = rb_entry(node, struct extent_status, rb_node);
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index f740eb03..efd5f97 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -29,16 +29,27 @@
/*
* These flags live in the high bits of extent_status.es_pblk
*/
-#define EXTENT_STATUS_WRITTEN (1ULL << 63)
-#define EXTENT_STATUS_UNWRITTEN (1ULL << 62)
-#define EXTENT_STATUS_DELAYED (1ULL << 61)
-#define EXTENT_STATUS_HOLE (1ULL << 60)
+#define ES_SHIFT 60
+
+#define EXTENT_STATUS_WRITTEN (1 << 3)
+#define EXTENT_STATUS_UNWRITTEN (1 << 2)
+#define EXTENT_STATUS_DELAYED (1 << 1)
+#define EXTENT_STATUS_HOLE (1 << 0)
#define EXTENT_STATUS_FLAGS (EXTENT_STATUS_WRITTEN | \
EXTENT_STATUS_UNWRITTEN | \
EXTENT_STATUS_DELAYED | \
EXTENT_STATUS_HOLE)
+#define ES_WRITTEN (1ULL << 63)
+#define ES_UNWRITTEN (1ULL << 62)
+#define ES_DELAYED (1ULL << 61)
+#define ES_HOLE (1ULL << 60)
+
+#define ES_MASK (ES_WRITTEN | ES_UNWRITTEN | \
+ ES_DELAYED | ES_HOLE)
+
+struct ext4_sb_info;
struct ext4_extent;
struct extent_status {
@@ -53,13 +64,27 @@
struct extent_status *cache_es; /* recently accessed extent */
};
+struct ext4_es_stats {
+ unsigned long es_stats_last_sorted;
+ unsigned long es_stats_shrunk;
+ unsigned long es_stats_cache_hits;
+ unsigned long es_stats_cache_misses;
+ u64 es_stats_scan_time;
+ u64 es_stats_max_scan_time;
+ struct percpu_counter es_stats_all_cnt;
+ struct percpu_counter es_stats_lru_cnt;
+};
+
extern int __init ext4_init_es(void);
extern void ext4_exit_es(void);
extern void ext4_es_init_tree(struct ext4_es_tree *tree);
extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned long long status);
+ unsigned int status);
+extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status);
extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len);
extern void ext4_es_find_delayed_extent_range(struct inode *inode,
@@ -67,36 +92,35 @@
struct extent_status *es);
extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
struct extent_status *es);
-extern int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex);
static inline int ext4_es_is_written(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_WRITTEN) != 0;
+ return (es->es_pblk & ES_WRITTEN) != 0;
}
static inline int ext4_es_is_unwritten(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_UNWRITTEN) != 0;
+ return (es->es_pblk & ES_UNWRITTEN) != 0;
}
static inline int ext4_es_is_delayed(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_DELAYED) != 0;
+ return (es->es_pblk & ES_DELAYED) != 0;
}
static inline int ext4_es_is_hole(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_HOLE) != 0;
+ return (es->es_pblk & ES_HOLE) != 0;
}
-static inline ext4_fsblk_t ext4_es_status(struct extent_status *es)
+static inline unsigned int ext4_es_status(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_FLAGS);
+ return es->es_pblk >> ES_SHIFT;
}
static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
{
- return (es->es_pblk & ~EXTENT_STATUS_FLAGS);
+ return es->es_pblk & ~ES_MASK;
}
static inline void ext4_es_store_pblock(struct extent_status *es,
@@ -104,23 +128,29 @@
{
ext4_fsblk_t block;
- block = (pb & ~EXTENT_STATUS_FLAGS) |
- (es->es_pblk & EXTENT_STATUS_FLAGS);
+ block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK);
es->es_pblk = block;
}
static inline void ext4_es_store_status(struct extent_status *es,
- unsigned long long status)
+ unsigned int status)
{
- ext4_fsblk_t block;
-
- block = (status & EXTENT_STATUS_FLAGS) |
- (es->es_pblk & ~EXTENT_STATUS_FLAGS);
- es->es_pblk = block;
+ es->es_pblk = (((ext4_fsblk_t)
+ (status & EXTENT_STATUS_FLAGS) << ES_SHIFT) |
+ (es->es_pblk & ~ES_MASK));
}
-extern void ext4_es_register_shrinker(struct super_block *sb);
-extern void ext4_es_unregister_shrinker(struct super_block *sb);
+static inline void ext4_es_store_pblock_status(struct extent_status *es,
+ ext4_fsblk_t pb,
+ unsigned int status)
+{
+ es->es_pblk = (((ext4_fsblk_t)
+ (status & EXTENT_STATUS_FLAGS) << ES_SHIFT) |
+ (pb & ~ES_MASK));
+}
+
+extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
+extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
extern void ext4_es_lru_add(struct inode *inode);
extern void ext4_es_lru_del(struct inode *inode);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ec9770f..da43705 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,13 +57,142 @@
return 0;
}
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
}
+#if 0
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete. Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block. If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
+{
+ struct super_block *sb = inode->i_sb;
+ int blockmask = sb->s_blocksize - 1;
+
+ if (pos >= i_size_read(inode))
+ return 0;
+
+ if ((pos | iov_iter_alignment(from)) & blockmask)
+ return 1;
+
+ return 0;
+}
+
+static ssize_t
+ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct mutex *aio_mutex = NULL;
+ struct blk_plug plug;
+ int o_direct = file->f_flags & O_DIRECT;
+ int overwrite = 0;
+ size_t length = iov_iter_count(from);
+ ssize_t ret;
+ loff_t pos = iocb->ki_pos;
+
+ /*
+ * Unaligned direct AIO must be serialized; see comment above
+ * In the case of O_APPEND, assume that we must always serialize
+ */
+ if (o_direct &&
+ ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ !is_sync_kiocb(iocb) &&
+ (file->f_flags & O_APPEND ||
+ ext4_unaligned_aio(inode, from, pos))) {
+ aio_mutex = ext4_aio_mutex(inode);
+ mutex_lock(aio_mutex);
+ ext4_unwritten_wait(inode);
+ }
+
+ mutex_lock(&inode->i_mutex);
+ if (file->f_flags & O_APPEND)
+ iocb->ki_pos = pos = i_size_read(inode);
+
+ /*
+ * If we have encountered a bitmap-format file, the size limit
+ * is smaller than s_maxbytes, which is for extent-mapped files.
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if ((pos > sbi->s_bitmap_maxbytes) ||
+ (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+ mutex_unlock(&inode->i_mutex);
+ ret = -EFBIG;
+ goto errout;
+ }
+
+ if (pos + length > sbi->s_bitmap_maxbytes)
+ iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
+ }
+
+ iocb->private = &overwrite;
+ if (o_direct) {
+ blk_start_plug(&plug);
+
+
+ /* check whether we do a DIO overwrite or not */
+ if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+ !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ struct ext4_map_blocks map;
+ unsigned int blkbits = inode->i_blkbits;
+ int err, len;
+
+ map.m_lblk = pos >> blkbits;
+ map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+ - map.m_lblk;
+ len = map.m_len;
+
+ err = ext4_map_blocks(NULL, inode, &map, 0);
+ /*
+ * 'err==len' means that all of blocks has
+ * been preallocated no matter they are
+ * initialized or not. For excluding
+ * unwritten extents, we need to check
+ * m_flags. There are two conditions that
+ * indicate for initialized extents. 1) If we
+ * hit extent cache, EXT4_MAP_MAPPED flag is
+ * returned; 2) If we do a real lookup,
+ * non-flags are returned. So we should check
+ * these two conditions.
+ */
+ if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+ overwrite = 1;
+ }
+ }
+
+ ret = __generic_file_write_iter(iocb, from);
+ mutex_unlock(&inode->i_mutex);
+
+ if (ret > 0) {
+ ssize_t err;
+
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+ if (err < 0)
+ ret = err;
+ }
+ if (o_direct)
+ blk_finish_plug(&plug);
+
+errout:
+ if (aio_mutex)
+ mutex_unlock(aio_mutex);
+ return ret;
+}
+#endif
+
/*
* This tests whether the IO in question is block-aligned or not.
* Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
@@ -100,7 +229,7 @@
struct blk_plug plug;
int unaligned_aio = 0;
ssize_t ret;
- int *overwrite = iocb->private;
+ int overwrite = 0;
size_t length = iov_length(iov, nr_segs);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
@@ -118,6 +247,8 @@
mutex_lock(&inode->i_mutex);
blk_start_plug(&plug);
+ iocb->private = &overwrite;
+
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
@@ -141,7 +272,7 @@
* So we should check these two conditions.
*/
if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
- *overwrite = 1;
+ overwrite = 1;
}
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
@@ -168,7 +299,6 @@
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
- int overwrite = 0;
/*
* If we have encountered a bitmap-format file, the size limit
@@ -189,7 +319,6 @@
}
}
- iocb->private = &overwrite;
if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
else
@@ -200,16 +329,24 @@
static const struct vm_operations_struct ext4_file_vm_ops = {
.fault = filemap_fault,
+#if 0
+ .map_pages = filemap_map_pages,
+#endif
.page_mkwrite = ext4_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct address_space *mapping = file->f_mapping;
+ struct inode *inode = file->f_mapping->host;
- if (!mapping->a_ops->readpage)
- return -ENOEXEC;
+ if (ext4_encrypted_inode(inode)) {
+ int err = ext4_get_encryption_info(inode);
+ if (err)
+ return 0;
+ if (ext4_encryption_info(inode) == NULL)
+ return -ENOKEY;
+ }
file_accessed(file);
vma->vm_ops = &ext4_file_vm_ops;
return 0;
@@ -219,10 +356,10 @@
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
+ int ret;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
@@ -244,6 +381,7 @@
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
@@ -255,26 +393,21 @@
ext4_journal_stop(handle);
}
}
+ if (ext4_encrypted_inode(inode)) {
+ ret = ext4_get_encryption_info(inode);
+ if (ret)
+ return -EACCES;
+ if (ext4_encryption_info(inode) == NULL)
+ return -ENOKEY;
+ }
/*
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
- if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
- struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
-
- spin_lock(&inode->i_lock);
- if (!ei->jinode) {
- if (!jinode) {
- spin_unlock(&inode->i_lock);
- return -ENOMEM;
- }
- ei->jinode = jinode;
- jbd2_journal_init_jbd_inode(ei->jinode, inode);
- jinode = NULL;
- }
- spin_unlock(&inode->i_lock);
- if (unlikely(jinode != NULL))
- jbd2_free_inode(jinode);
+ if (filp->f_mode & FMODE_WRITE) {
+ ret = ext4_inode_attach_jinode(inode);
+ if (ret < 0)
+ return ret;
}
return dquot_file_open(inode, filp);
}
@@ -424,6 +557,37 @@
return found;
}
+static inline int unsigned_offsets(struct file *file)
+{
+ return file->f_mode & FMODE_UNSIGNED_OFFSET;
+}
+
+/**
+ * vfs_setpos - update the file offset for lseek
+ * @file: file structure in question
+ * @offset: file offset to seek to
+ * @maxsize: maximum file size
+ *
+ * This is a low-level filesystem helper for updating the file offset to
+ * the value specified by @offset if the given offset is valid and it is
+ * not equal to the current file offset.
+ *
+ * Return the specified offset on success and -EINVAL on invalid offset.
+ */
+static loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
+{
+ if (offset < 0 && !unsigned_offsets(file))
+ return -EINVAL;
+ if (offset > maxsize)
+ return -EINVAL;
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+ return offset;
+}
+
/*
* ext4_seek_data() retrieves the offset for SEEK_DATA.
*/
@@ -494,17 +658,7 @@
if (dataoff > isize)
return -ENXIO;
- if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
- return -EINVAL;
- if (dataoff > maxsize)
- return -EINVAL;
-
- if (dataoff != file->f_pos) {
- file->f_pos = dataoff;
- file->f_version = 0;
- }
-
- return dataoff;
+ return vfs_setpos(file, dataoff, maxsize);
}
/*
@@ -580,17 +734,7 @@
if (holeoff > isize)
holeoff = isize;
- if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
- return -EINVAL;
- if (holeoff > maxsize)
- return -EINVAL;
-
- if (holeoff != file->f_pos) {
- file->f_pos = holeoff;
- file->f_version = 0;
- }
-
- return holeoff;
+ return vfs_setpos(file, holeoff, maxsize);
}
/*
@@ -650,6 +794,9 @@
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
+#if 0
+ .set_acl = ext4_set_acl,
+#endif
.fiemap = ext4_fiemap,
};
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index e0ba8a4..a8bc47f 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -73,32 +73,6 @@
return ret;
}
-/**
- * __sync_file - generic_file_fsync without the locking and filemap_write
- * @inode: inode to sync
- * @datasync: only sync essential metadata if true
- *
- * This is just generic_file_fsync without the locking. This is needed for
- * nojournal mode to make sure this inodes data/metadata makes it to disk
- * properly. The i_mutex should be held already.
- */
-static int __sync_inode(struct inode *inode, int datasync)
-{
- int err;
- int ret;
-
- ret = sync_mapping_buffers(inode->i_mapping);
- if (!(inode->i_state & I_DIRTY))
- return ret;
- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
- return ret;
-
- err = sync_inode_metadata(inode, 1);
- if (ret == 0)
- ret = err;
- return ret;
-}
-
/*
* akpm: A new design for ext4_sync_file().
*
@@ -116,7 +90,7 @@
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- int ret, err;
+ int ret = 0, err;
tid_t commit_tid;
bool needs_barrier = false;
@@ -124,25 +98,24 @@
trace_ext4_sync_file_enter(file, datasync);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (ret)
- return ret;
- mutex_lock(&inode->i_mutex);
-
- if (inode->i_sb->s_flags & MS_RDONLY)
+ if (inode->i_sb->s_flags & MS_RDONLY) {
+ /* Make sure that we read updated s_mount_flags value */
+ smp_rmb();
+ if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ ret = -EROFS;
goto out;
-
- ret = ext4_flush_unwritten_io(inode);
- if (ret < 0)
- goto out;
+ }
if (!journal) {
- ret = __sync_inode(inode, datasync);
+ ret = generic_file_fsync(file, start, end, datasync);
if (!ret && !hlist_empty(&inode->i_dentry))
ret = ext4_sync_parent(inode);
goto out;
}
+ ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ if (ret)
+ return ret;
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
@@ -172,8 +145,7 @@
if (!ret)
ret = err;
}
- out:
- mutex_unlock(&inode->i_mutex);
+out:
trace_ext4_sync_file_exit(inode, ret);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 00cbc64..8b2980a 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -70,18 +70,26 @@
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
+ struct ext4_group_info *grp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_group_clusters_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
- EXT4_INODES_PER_GROUP(sb) / 8);
+ grp = ext4_get_group_info(sb, block_group);
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ int count;
+ count = ext4_free_inodes_count(sb, gdp);
+ percpu_counter_sub(&sbi->s_freeinodes_counter,
+ count);
+ }
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
return 0;
}
@@ -117,6 +125,8 @@
struct ext4_group_desc *desc;
struct buffer_head *bh = NULL;
ext4_fsblk_t bitmap_blk;
+ struct ext4_group_info *grp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
@@ -185,6 +195,14 @@
put_bh(bh);
ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
"inode_bitmap = %llu", block_group, bitmap_blk);
+ grp = ext4_get_group_info(sb, block_group);
+ if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ int count;
+ count = ext4_free_inodes_count(sb, desc);
+ percpu_counter_sub(&sbi->s_freeinodes_counter,
+ count);
+ }
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
return NULL;
}
ext4_unlock_group(sb, block_group);
@@ -221,6 +239,7 @@
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
int fatal = 0, err, count, cleared;
+ struct ext4_group_info *grp;
if (!sb) {
printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
@@ -266,7 +285,9 @@
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
- if (!bitmap_bh)
+ /* Don't bother if the inode bitmap is corrupt. */
+ grp = ext4_get_group_info(sb, block_group);
+ if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || !bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
@@ -315,8 +336,16 @@
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
- } else
+ } else {
ext4_error(sb, "bit already cleared for inode %lu", ino);
+ if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ int count;
+ count = ext4_free_inodes_count(sb, gdp);
+ percpu_counter_sub(&sbi->s_freeinodes_counter,
+ count);
+ }
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ }
error_return:
brelse(bitmap_bh);
@@ -426,7 +455,7 @@
ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
grp = hinfo.hash;
} else
- get_random_bytes(&grp, sizeof(grp));
+ grp = prandom_u32();
parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
g = (parent_group + i) % ngroups;
@@ -625,6 +654,51 @@
}
/*
+ * In no journal mode, if an inode has recently been deleted, we want
+ * to avoid reusing it until we're reasonably sure the inode table
+ * block has been written back to disk. (Yes, these values are
+ * somewhat arbitrary...)
+ */
+#define RECENTCY_MIN 5
+#define RECENTCY_DIRTY 30
+
+static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
+{
+ struct ext4_group_desc *gdp;
+ struct ext4_inode *raw_inode;
+ struct buffer_head *bh;
+ unsigned long dtime, now;
+ int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+ int offset, ret = 0, recentcy = RECENTCY_MIN;
+
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (unlikely(!gdp))
+ return 0;
+
+ bh = sb_getblk(sb, ext4_inode_table(sb, gdp) +
+ (ino / inodes_per_block));
+ if (unlikely(!bh) || !buffer_uptodate(bh))
+ /*
+ * If the block is not in the buffer cache, then it
+ * must have been written out.
+ */
+ goto out;
+
+ offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb);
+ raw_inode = (struct ext4_inode *) (bh->b_data + offset);
+ dtime = le32_to_cpu(raw_inode->i_dtime);
+ now = get_seconds();
+ if (buffer_dirty(bh))
+ recentcy += RECENTCY_DIRTY;
+
+ if (dtime && (dtime < now) && (now < dtime + recentcy))
+ ret = 1;
+out:
+ brelse(bh);
+ return ret;
+}
+
+/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
@@ -652,11 +726,26 @@
struct inode *ret;
ext4_group_t i;
ext4_group_t flex_group;
+ struct ext4_group_info *grp;
+ int encrypt = 0;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
+ if ((ext4_encrypted_inode(dir) ||
+ DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+ err = ext4_get_encryption_info(dir);
+ if (err)
+ return ERR_PTR(err);
+ if (ext4_encryption_info(dir) == NULL)
+ return ERR_PTR(-EPERM);
+ if (!handle)
+ nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
+ encrypt = 1;
+ }
+
sb = dir->i_sb;
ngroups = ext4_get_groups_count(sb);
trace_ext4_request_inode(dir, mode);
@@ -725,10 +814,22 @@
continue;
}
+ grp = ext4_get_group_info(sb, group);
+ /* Skip groups with already-known suspicious inode tables */
+ if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ if (++group == ngroups)
+ group = 0;
+ continue;
+ }
+
brelse(inode_bitmap_bh);
inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
- if (!inode_bitmap_bh)
- goto out;
+ /* Skip groups with suspicious inode tables */
+ if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || !inode_bitmap_bh) {
+ if (++group == ngroups)
+ group = 0;
+ continue;
+ }
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
@@ -741,10 +842,16 @@
"inode=%lu", ino + 1);
continue;
}
+ if ((EXT4_SB(sb)->s_journal == NULL) &&
+ recently_deleted(sb, group, ino)) {
+ ino++;
+ goto next_inode;
+ }
if (!handle) {
BUG_ON(nblocks <= 0);
handle = __ext4_journal_start_sb(dir->i_sb, line_no,
- handle_type, nblocks);
+ handle_type, nblocks,
+ 0);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
ext4_std_error(sb, err);
@@ -763,6 +870,7 @@
ino++; /* the inode bitmap is zero-based */
if (!ret2)
goto got; /* we grabbed the inode! */
+next_inode:
if (ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
next_group:
@@ -921,8 +1029,7 @@
spin_unlock(&sbi->s_next_gen_lock);
/* Precompute checksum seed for inode metadata */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ if (ext4_has_metadata_csum(sb)) {
__u32 csum;
__le32 inum = cpu_to_le32(inode->i_ino);
__le32 gen = cpu_to_le32(inode->i_generation);
@@ -936,11 +1043,9 @@
ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
-
ei->i_inline_off = 0;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA))
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
-
ret = inode;
err = dquot_alloc_inode(inode);
if (err)
@@ -967,6 +1072,12 @@
ei->i_datasync_tid = handle->h_transaction->t_tid;
}
+ if (encrypt) {
+ err = ext4_inherit_context(dir, inode);
+ if (err)
+ goto fail_free_drop;
+ }
+
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b07a221..8968ebd 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -23,7 +23,6 @@
#include <linux/aio.h>
#include "ext4_jbd2.h"
#include "truncate.h"
-#include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */
#include <trace/events/ext4.h>
@@ -319,34 +318,24 @@
* ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
* as described above and return 0.
*/
-static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, int indirect_blks,
- int *blks, ext4_fsblk_t goal,
- ext4_lblk_t *offsets, Indirect *branch)
+static int ext4_alloc_branch(handle_t *handle,
+ struct ext4_allocation_request *ar,
+ int indirect_blks, ext4_lblk_t *offsets,
+ Indirect *branch)
{
- struct ext4_allocation_request ar;
struct buffer_head * bh;
ext4_fsblk_t b, new_blocks[4];
__le32 *p;
int i, j, err, len = 1;
- /*
- * Set up for the direct block allocation
- */
- memset(&ar, 0, sizeof(ar));
- ar.inode = inode;
- ar.len = *blks;
- ar.logical = iblock;
- if (S_ISREG(inode->i_mode))
- ar.flags = EXT4_MB_HINT_DATA;
-
for (i = 0; i <= indirect_blks; i++) {
if (i == indirect_blks) {
- ar.goal = goal;
- new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err);
+ new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err);
} else
- goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode,
- goal, 0, NULL, &err);
+ ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle,
+ ar->inode, ar->goal,
+ ar->flags & EXT4_MB_DELALLOC_RESERVED,
+ NULL, &err);
if (err) {
i--;
goto failed;
@@ -355,7 +344,7 @@
if (i == 0)
continue;
- bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]);
+ bh = branch[i].bh = sb_getblk(ar->inode->i_sb, new_blocks[i-1]);
if (unlikely(!bh)) {
err = -ENOMEM;
goto failed;
@@ -373,7 +362,7 @@
b = new_blocks[i];
if (i == indirect_blks)
- len = ar.len;
+ len = ar->len;
for (j = 0; j < len; j++)
*p++ = cpu_to_le32(b++);
@@ -382,11 +371,10 @@
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, bh);
+ err = ext4_handle_dirty_metadata(handle, ar->inode, bh);
if (err)
goto failed;
}
- *blks = ar.len;
return 0;
failed:
for (; i >= 0; i--) {
@@ -397,10 +385,10 @@
* existing before ext4_alloc_branch() was called.
*/
if (i > 0 && i != indirect_blks && branch[i].bh)
- ext4_forget(handle, 1, inode, branch[i].bh,
+ ext4_forget(handle, 1, ar->inode, branch[i].bh,
branch[i].bh->b_blocknr);
- ext4_free_blocks(handle, inode, NULL, new_blocks[i],
- (i == indirect_blks) ? ar.len : 1, 0);
+ ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i],
+ (i == indirect_blks) ? ar->len : 1, 0);
}
return err;
}
@@ -420,9 +408,9 @@
* inode (->i_blocks, etc.). In case of success we end up with the full
* chain to new block and return 0.
*/
-static int ext4_splice_branch(handle_t *handle, struct inode *inode,
- ext4_lblk_t block, Indirect *where, int num,
- int blks)
+static int ext4_splice_branch(handle_t *handle,
+ struct ext4_allocation_request *ar,
+ Indirect *where, int num)
{
int i;
int err = 0;
@@ -447,9 +435,9 @@
* Update the host buffer_head or inode to point to more just allocated
* direct blocks blocks
*/
- if (num == 0 && blks > 1) {
+ if (num == 0 && ar->len > 1) {
current_block = le32_to_cpu(where->key) + 1;
- for (i = 1; i < blks; i++)
+ for (i = 1; i < ar->len; i++)
*(where->p + i) = cpu_to_le32(current_block++);
}
@@ -466,14 +454,14 @@
*/
jbd_debug(5, "splicing indirect only\n");
BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, where->bh);
+ err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh);
if (err)
goto err_out;
} else {
/*
* OK, we spliced it into the inode itself on a direct block.
*/
- ext4_mark_inode_dirty(handle, inode);
+ ext4_mark_inode_dirty(handle, ar->inode);
jbd_debug(5, "splicing direct\n");
}
return err;
@@ -485,11 +473,11 @@
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
- ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+ ext4_free_blocks(handle, ar->inode, where[i].bh, 0, 1,
EXT4_FREE_BLOCKS_FORGET);
}
- ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
- blks, 0);
+ ext4_free_blocks(handle, ar->inode, NULL, le32_to_cpu(where[num].key),
+ ar->len, 0);
return err;
}
@@ -526,11 +514,11 @@
struct ext4_map_blocks *map,
int flags)
{
+ struct ext4_allocation_request ar;
int err = -EIO;
ext4_lblk_t offsets[4];
Indirect chain[4];
Indirect *partial;
- ext4_fsblk_t goal;
int indirect_blks;
int blocks_to_boundary = 0;
int depth;
@@ -577,10 +565,19 @@
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
"non-extent mapped inodes with bigalloc");
- return -EUCLEAN;
+ return -ENOSPC;
}
- goal = ext4_find_goal(inode, map->m_lblk, partial);
+ /* Set up for the direct block allocation */
+ memset(&ar, 0, sizeof(ar));
+ ar.inode = inode;
+ ar.logical = map->m_lblk;
+ if (S_ISREG(inode->i_mode))
+ ar.flags = EXT4_MB_HINT_DATA;
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ar.flags |= EXT4_MB_DELALLOC_RESERVED;
+
+ ar.goal = ext4_find_goal(inode, map->m_lblk, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) - partial - 1;
@@ -589,13 +586,13 @@
* Next look up the indirect map to count the totoal number of
* direct blocks to allocate for this branch.
*/
- count = ext4_blks_to_allocate(partial, indirect_blks,
- map->m_len, blocks_to_boundary);
+ ar.len = ext4_blks_to_allocate(partial, indirect_blks,
+ map->m_len, blocks_to_boundary);
+
/*
* Block out ext4_truncate while we alter the tree
*/
- err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
- &count, goal,
+ err = ext4_alloc_branch(handle, &ar, indirect_blks,
offsets + (partial - chain), partial);
/*
@@ -606,14 +603,14 @@
* may need to return -EAGAIN upwards in the worst case. --sct
*/
if (!err)
- err = ext4_splice_branch(handle, inode, map->m_lblk,
- partial, indirect_blks, count);
+ err = ext4_splice_branch(handle, &ar, partial, indirect_blks);
if (err)
goto cleanup;
map->m_flags |= EXT4_MAP_NEW;
ext4_update_inode_fsync_trans(handle, inode, 1);
+ count = ar.len;
got_it:
map->m_flags |= EXT4_MAP_MAPPED;
map->m_pblk = le32_to_cpu(chain[depth-1].key);
@@ -630,7 +627,7 @@
partial--;
}
out:
- trace_ext4_ind_map_blocks_exit(inode, map, err);
+ trace_ext4_ind_map_blocks_exit(inode, flags, map, err);
return err;
}
@@ -681,11 +678,6 @@
retry:
if (rw == READ && ext4_should_dioread_nolock(inode)) {
- if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) {
- mutex_lock(&inode->i_mutex);
- ext4_flush_unwritten_io(inode);
- mutex_unlock(&inode->i_mutex);
- }
/*
* Nolock dioread optimization may be dynamically disabled
* via ext4_inode_block_unlocked_dio(). Check inode's state
@@ -700,7 +692,7 @@
}
ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
- offset, nr_segs,
+ offset, nr_segs,
ext4_get_block, NULL, NULL, 0);
inode_dio_done(inode);
} else {
@@ -710,7 +702,7 @@
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;
if (end > isize)
ext4_truncate_failed_write(inode);
@@ -785,27 +777,18 @@
return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}
-int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+/*
+ * Calculate number of indirect blocks touched by mapping @nrblocks logically
+ * contiguous blocks
+ */
+int ext4_ind_trans_blocks(struct inode *inode, int nrblocks)
{
- int indirects;
-
- /* if nrblocks are contiguous */
- if (chunk) {
- /*
- * With N contiguous data blocks, we need at most
- * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
- * 2 dindirect blocks, and 1 tindirect block
- */
- return DIV_ROUND_UP(nrblocks,
- EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
- }
/*
- * if nrblocks are not contiguous, worse case, each block touch
- * a indirect block, and each indirect block touch a double indirect
- * block, plus a triple indirect block
+ * With N contiguous data blocks, we need at most
+ * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+ * 2 dindirect blocks, and 1 tindirect block
*/
- indirects = nrblocks * 2 + 1;
- return indirects;
+ return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
}
/*
@@ -946,11 +929,13 @@
__le32 *last)
{
__le32 *p;
- int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
+ int flags = EXT4_FREE_BLOCKS_VALIDATED;
int err;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
+ flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA;
+ else if (ext4_should_journal_data(inode))
+ flags |= EXT4_FREE_BLOCKS_FORGET;
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
count)) {
@@ -1310,97 +1295,220 @@
}
}
-static int free_hole_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *parent_bh, __le32 *i_data,
- int level, ext4_lblk_t first,
- ext4_lblk_t count, int max)
+/**
+ * ext4_ind_remove_space - remove space from the range
+ * @handle: JBD handle for this transaction
+ * @inode: inode we are dealing with
+ * @start: First block to remove
+ * @end: One block after the last block to remove (exclusive)
+ *
+ * Free the blocks in the defined range (end is exclusive endpoint of
+ * range). This is used by ext4_punch_hole().
+ */
+int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+ ext4_lblk_t start, ext4_lblk_t end)
{
- struct buffer_head *bh = NULL;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *i_data = ei->i_data;
int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ret = 0;
- int i, inc;
- ext4_lblk_t offset;
- __le32 blk;
+ ext4_lblk_t offsets[4], offsets2[4];
+ Indirect chain[4], chain2[4];
+ Indirect *partial, *partial2;
+ ext4_lblk_t max_block;
+ __le32 nr = 0, nr2 = 0;
+ int n = 0, n2 = 0;
+ unsigned blocksize = inode->i_sb->s_blocksize;
- inc = 1 << ((EXT4_BLOCK_SIZE_BITS(inode->i_sb) - 2) * level);
- for (i = 0, offset = 0; i < max; i++, i_data++, offset += inc) {
- if (offset >= count + first)
- break;
- if (*i_data == 0 || (offset + inc) <= first)
- continue;
- blk = *i_data;
- if (level > 0) {
- ext4_lblk_t first2;
- ext4_lblk_t count2;
+ max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+ if (end >= max_block)
+ end = max_block;
+ if ((start >= end) || (start > max_block))
+ return 0;
- bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
- if (!bh) {
- EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
- "Read failure");
- return -EIO;
- }
- if (first > offset) {
- first2 = first - offset;
- count2 = count;
+ n = ext4_block_to_path(inode, start, offsets, NULL);
+ n2 = ext4_block_to_path(inode, end, offsets2, NULL);
+
+ BUG_ON(n > n2);
+
+ if ((n == 1) && (n == n2)) {
+ /* We're punching only within direct block range */
+ ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+ i_data + offsets2[0]);
+ return 0;
+ } else if (n2 > n) {
+ /*
+ * Start and end are on a different levels so we're going to
+ * free partial block at start, and partial block at end of
+ * the range. If there are some levels in between then
+ * do_indirects label will take care of that.
+ */
+
+ if (n == 1) {
+ /*
+ * Start is at the direct block level, free
+ * everything to the end of the level.
+ */
+ ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+ i_data + EXT4_NDIR_BLOCKS);
+ goto end_range;
+ }
+
+
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ if (nr) {
+ if (partial == chain) {
+ /* Shared branch grows from the inode */
+ ext4_free_branches(handle, inode, NULL,
+ &nr, &nr+1, (chain+n-1) - partial);
+ *partial->p = 0;
} else {
- first2 = 0;
- count2 = count - (offset - first);
- }
- ret = free_hole_blocks(handle, inode, bh,
- (__le32 *)bh->b_data, level - 1,
- first2, count2,
- inode->i_sb->s_blocksize >> 2);
- if (ret) {
- brelse(bh);
- goto err;
+ /* Shared branch grows from an indirect block */
+ BUFFER_TRACE(partial->bh, "get_write_access");
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p,
+ partial->p+1, (chain+n-1) - partial);
}
}
- if (level == 0 ||
- (bh && all_zeroes((__le32 *)bh->b_data,
- (__le32 *)bh->b_data + addr_per_block))) {
- ext4_free_data(handle, inode, parent_bh, &blk, &blk+1);
- *i_data = 0;
+
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the start of the range
+ */
+ while (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ (__le32 *)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
}
- brelse(bh);
- bh = NULL;
- }
-err:
- return ret;
-}
-
-int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t first, ext4_lblk_t stop)
-{
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int level, ret = 0;
- int num = EXT4_NDIR_BLOCKS;
- ext4_lblk_t count, max = EXT4_NDIR_BLOCKS;
- __le32 *i_data = EXT4_I(inode)->i_data;
-
- count = stop - first;
- for (level = 0; level < 4; level++, max *= addr_per_block) {
- if (first < max) {
- ret = free_hole_blocks(handle, inode, NULL, i_data,
- level, first, count, num);
- if (ret)
- goto err;
- if (count > max - first)
- count -= max - first;
- else
- break;
- first = 0;
+end_range:
+ partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+ if (nr2) {
+ if (partial2 == chain2) {
+ /*
+ * Remember, end is exclusive so here we're at
+ * the start of the next level we're not going
+ * to free. Everything was covered by the start
+ * of the range.
+ */
+ return 0;
+ } else {
+ /* Shared branch grows from an indirect block */
+ partial2--;
+ }
} else {
- first -= max;
+ /*
+ * ext4_find_shared returns Indirect structure which
+ * points to the last element which should not be
+ * removed by truncate. But this is end of the range
+ * in punch_hole so we need to point to the next element
+ */
+ partial2->p++;
}
- i_data += num;
- if (level == 0) {
- num = 1;
- max = 1;
+
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the end of the range
+ */
+ while (partial2 > chain2) {
+ ext4_free_branches(handle, inode, partial2->bh,
+ (__le32 *)partial2->bh->b_data,
+ partial2->p,
+ (chain2+n2-1) - partial2);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ partial2--;
+ }
+ goto do_indirects;
+ }
+
+ /* Punch happened within the same level (n == n2) */
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+ /*
+ * ext4_find_shared returns Indirect structure which
+ * points to the last element which should not be
+ * removed by truncate. But this is end of the range
+ * in punch_hole so we need to point to the next element
+ */
+ partial2->p++;
+ while ((partial > chain) || (partial2 > chain2)) {
+ /* We're at the same block, so we're almost finished */
+ if ((partial->bh && partial2->bh) &&
+ (partial->bh->b_blocknr == partial2->bh->b_blocknr)) {
+ if ((partial > chain) && (partial2 > chain2)) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ partial2->p,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ }
+ return 0;
+ }
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the start of the range
+ */
+ if (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p + 1,
+ (__le32 *)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+ /*
+ * Clear the ends of indirect blocks on the shared branch
+ * at the end of the range
+ */
+ if (partial2 > chain2) {
+ ext4_free_branches(handle, inode, partial2->bh,
+ (__le32 *)partial2->bh->b_data,
+ partial2->p,
+ (chain2+n-1) - partial2);
+ BUFFER_TRACE(partial2->bh, "call brelse");
+ brelse(partial2->bh);
+ partial2--;
}
}
-err:
- return ret;
+do_indirects:
+ /* Kill the remaining (whole) subtrees */
+ switch (offsets[0]) {
+ default:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_IND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+ i_data[EXT4_IND_BLOCK] = 0;
+ }
+ case EXT4_IND_BLOCK:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_DIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+ i_data[EXT4_DIND_BLOCK] = 0;
+ }
+ case EXT4_DIND_BLOCK:
+ if (++n >= n2)
+ return 0;
+ nr = i_data[EXT4_TIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+ i_data[EXT4_TIND_BLOCK] = 0;
+ }
+ case EXT4_TIND_BLOCK:
+ ;
+ }
+ return 0;
}
-
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index e350be6..6990a6f 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -11,18 +11,20 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
+
+#include <linux/fiemap.h>
+
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
#include "truncate.h"
-#include <linux/fiemap.h>
#define EXT4_XATTR_SYSTEM_DATA "data"
#define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS))
#define EXT4_INLINE_DOTDOT_OFFSET 2
#define EXT4_INLINE_DOTDOT_SIZE 4
-int ext4_get_inline_size(struct inode *inode)
+static int ext4_get_inline_size(struct inode *inode)
{
if (EXT4_I(inode)->i_inline_off)
return EXT4_I(inode)->i_inline_size;
@@ -72,7 +74,7 @@
entry = (struct ext4_xattr_entry *)
((void *)raw_inode + EXT4_I(inode)->i_inline_off);
- free += le32_to_cpu(entry->e_value_size);
+ free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size));
goto out;
}
@@ -120,12 +122,6 @@
return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE;
}
-int ext4_has_inline_data(struct inode *inode)
-{
- return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
- EXT4_I(inode)->i_inline_off;
-}
-
/*
* this function does not take xattr_sem, which is OK because it is
* currently only used in a code path coming form ext4_iget, before
@@ -211,8 +207,8 @@
* value since it is already handled by ext4_xattr_ibody_inline_set.
* That saves us one memcpy.
*/
-void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
- void *buffer, loff_t pos, unsigned int len)
+static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
+ void *buffer, loff_t pos, unsigned int len)
{
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
@@ -264,6 +260,7 @@
if (error)
return error;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -347,6 +344,7 @@
if (error == -ENODATA)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -373,8 +371,8 @@
return error;
}
-int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len)
+static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len)
{
int ret, size;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -424,6 +422,7 @@
if (error)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -597,6 +596,7 @@
if (ret) {
unlock_page(page);
page_cache_release(page);
+ page = NULL;
ext4_orphan_add(handle, inode);
up_write(&EXT4_I(inode)->xattr_sem);
sem_held = 0;
@@ -616,7 +616,8 @@
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
- block_commit_write(page, from, to);
+ if (page)
+ block_commit_write(page, from, to);
out:
if (page) {
unlock_page(page);
@@ -849,15 +850,16 @@
handle_t *handle;
struct page *page;
struct ext4_iloc iloc;
+ int retries;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
+retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- handle = NULL;
goto out;
}
@@ -867,7 +869,7 @@
if (inline_size >= pos + len) {
ret = ext4_prepare_inline_data(handle, inode, pos + len);
if (ret && ret != -ENOSPC)
- goto out;
+ goto out_journal;
}
if (ret == -ENOSPC) {
@@ -875,6 +877,10 @@
inode,
flags,
fsdata);
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_journal;
goto out;
}
@@ -887,7 +893,7 @@
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
- goto out;
+ goto out_journal;
}
down_read(&EXT4_I(inode)->xattr_sem);
@@ -904,16 +910,15 @@
up_read(&EXT4_I(inode)->xattr_sem);
*pagep = page;
- handle = NULL;
brelse(iloc.bh);
return 1;
out_release_page:
up_read(&EXT4_I(inode)->xattr_sem);
unlock_page(page);
page_cache_release(page);
+out_journal:
+ ext4_journal_stop(handle);
out:
- if (handle)
- ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
}
@@ -986,29 +991,26 @@
* and -EEXIST if directory entry already exists.
*/
static int ext4_add_dirent_to_inline(handle_t *handle,
+ struct ext4_filename *fname,
struct dentry *dentry,
struct inode *inode,
struct ext4_iloc *iloc,
void *inline_start, int inline_size)
{
struct inode *dir = dentry->d_parent->d_inode;
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
- unsigned short reclen;
int err;
struct ext4_dir_entry_2 *de;
- reclen = EXT4_DIR_REC_LEN(namelen);
- err = ext4_find_dest_de(dir, inode, iloc->bh,
- inline_start, inline_size,
- name, namelen, &de);
+ err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start,
+ inline_size, fname, &de);
if (err)
return err;
+ BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
- ext4_insert_dentry(inode, de, inline_size, name, namelen);
+ ext4_insert_dentry(dir, inode, de, inline_size, fname);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
@@ -1126,8 +1128,7 @@
memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
inline_size - EXT4_INLINE_DOTDOT_SIZE);
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
inode->i_size = inode->i_sb->s_blocksize;
@@ -1172,6 +1173,18 @@
if (error < 0)
goto out;
+ /*
+ * Make sure the inline directory entries pass checks before we try to
+ * convert them, so that we avoid touching stuff that needs fsck.
+ */
+ if (S_ISDIR(inode->i_mode)) {
+ error = ext4_check_all_de(inode, iloc->bh,
+ buf + EXT4_INLINE_DOTDOT_SIZE,
+ inline_size - EXT4_INLINE_DOTDOT_SIZE);
+ if (error)
+ goto out;
+ }
+
error = ext4_destroy_inline_data_nolock(handle, inode);
if (error)
goto out;
@@ -1228,8 +1241,8 @@
* If succeeds, return 0. If not, extended the inline dir and copied data to
* the new created block.
*/
-int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
- struct inode *inode)
+int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
+ struct dentry *dentry, struct inode *inode)
{
int ret, inline_size;
void *inline_start;
@@ -1248,7 +1261,7 @@
EXT4_INLINE_DOTDOT_SIZE;
inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
- ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc,
+ ret = ext4_add_dirent_to_inline(handle, fname, dentry, inode, &iloc,
inline_start, inline_size);
if (ret != -ENOSPC)
goto out;
@@ -1269,8 +1282,9 @@
if (inline_size) {
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
- ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc,
- inline_start, inline_size);
+ ret = ext4_add_dirent_to_inline(handle, fname, dentry,
+ inode, &iloc, inline_start,
+ inline_size);
if (ret != -ENOSPC)
goto out;
@@ -1310,6 +1324,7 @@
struct ext4_iloc iloc;
void *dir_buf = NULL;
struct ext4_dir_entry_2 fake;
+ struct ext4_str tmp_str;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
@@ -1381,8 +1396,10 @@
continue;
if (de->inode == 0)
continue;
- err = ext4_htree_store_dirent(dir_file,
- hinfo->hash, hinfo->minor_hash, de);
+ tmp_str.name = de->name;
+ tmp_str.len = de->name_len;
+ err = ext4_htree_store_dirent(dir_file, hinfo->hash,
+ hinfo->minor_hash, de, &tmp_str);
if (err) {
count = err;
goto out;
@@ -1404,16 +1421,15 @@
* offset as if '.' and '..' really take place.
*
*/
-int ext4_read_inline_dir(struct file *filp,
- void *dirent, filldir_t filldir,
+int ext4_read_inline_dir(struct file *file,
+ struct dir_context *ctx,
int *has_inline_data)
{
- int error = 0;
unsigned int offset, parent_ino;
- int i, stored;
+ int i;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = file_inode(file);
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
@@ -1443,10 +1459,10 @@
if (ret < 0)
goto out;
+ ret = 0;
sb = inode->i_sb;
- stored = 0;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
- offset = filp->f_pos;
+ offset = ctx->pos;
/*
* dotdot_offset and dotdot_size is the real offset and
@@ -1460,104 +1476,74 @@
extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
extra_size = extra_offset + inline_size;
- while (!error && !stored && filp->f_pos < extra_size) {
-revalidate:
- /*
- * If the version has changed since the last call to
- * readdir(2), then we might be pointing to an invalid
- * dirent right now. Scan from the start of the inline
- * dir to make sure.
- */
- if (filp->f_version != inode->i_version) {
- for (i = 0; i < extra_size && i < offset;) {
- /*
- * "." is with offset 0 and
- * ".." is dotdot_offset.
- */
- if (!i) {
- i = dotdot_offset;
- continue;
- } else if (i == dotdot_offset) {
- i = dotdot_size;
- continue;
- }
- /* for other entry, the real offset in
- * the buf has to be tuned accordingly.
- */
- de = (struct ext4_dir_entry_2 *)
- (dir_buf + i - extra_offset);
- /* It's too expensive to do a full
- * dirent test each time round this
- * loop, but we do have to test at
- * least that it is non-zero. A
- * failure will be detected in the
- * dirent test below. */
- if (ext4_rec_len_from_disk(de->rec_len,
- extra_size) < EXT4_DIR_REC_LEN(1))
- break;
- i += ext4_rec_len_from_disk(de->rec_len,
- extra_size);
- }
- offset = i;
- filp->f_pos = offset;
- filp->f_version = inode->i_version;
- }
-
- while (!error && filp->f_pos < extra_size) {
- if (filp->f_pos == 0) {
- error = filldir(dirent, ".", 1, 0, inode->i_ino,
- DT_DIR);
- if (error)
- break;
- stored++;
- filp->f_pos = dotdot_offset;
+ /*
+ * If the version has changed since the last call to
+ * readdir(2), then we might be pointing to an invalid
+ * dirent right now. Scan from the start of the inline
+ * dir to make sure.
+ */
+ if (file->f_version != inode->i_version) {
+ for (i = 0; i < extra_size && i < offset;) {
+ /*
+ * "." is with offset 0 and
+ * ".." is dotdot_offset.
+ */
+ if (!i) {
+ i = dotdot_offset;
+ continue;
+ } else if (i == dotdot_offset) {
+ i = dotdot_size;
continue;
}
-
- if (filp->f_pos == dotdot_offset) {
- error = filldir(dirent, "..", 2,
- dotdot_offset,
- parent_ino, DT_DIR);
- if (error)
- break;
- stored++;
-
- filp->f_pos = dotdot_size;
- continue;
- }
-
+ /* for other entry, the real offset in
+ * the buf has to be tuned accordingly.
+ */
de = (struct ext4_dir_entry_2 *)
- (dir_buf + filp->f_pos - extra_offset);
- if (ext4_check_dir_entry(inode, filp, de,
- iloc.bh, dir_buf,
- extra_size, filp->f_pos)) {
- ret = stored;
- goto out;
- }
- if (le32_to_cpu(de->inode)) {
- /* We might block in the next section
- * if the data destination is
- * currently swapped out. So, use a
- * version stamp to detect whether or
- * not the directory has been modified
- * during the copy operation.
- */
- u64 version = filp->f_version;
-
- error = filldir(dirent, de->name,
- de->name_len,
- filp->f_pos,
- le32_to_cpu(de->inode),
- get_dtype(sb, de->file_type));
- if (error)
- break;
- if (version != filp->f_version)
- goto revalidate;
- stored++;
- }
- filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
- extra_size);
+ (dir_buf + i - extra_offset);
+ /* It's too expensive to do a full
+ * dirent test each time round this
+ * loop, but we do have to test at
+ * least that it is non-zero. A
+ * failure will be detected in the
+ * dirent test below. */
+ if (ext4_rec_len_from_disk(de->rec_len, extra_size)
+ < EXT4_DIR_REC_LEN(1))
+ break;
+ i += ext4_rec_len_from_disk(de->rec_len,
+ extra_size);
}
+ offset = i;
+ ctx->pos = offset;
+ file->f_version = inode->i_version;
+ }
+
+ while (ctx->pos < extra_size) {
+ if (ctx->pos == 0) {
+ if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR))
+ goto out;
+ ctx->pos = dotdot_offset;
+ continue;
+ }
+
+ if (ctx->pos == dotdot_offset) {
+ if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR))
+ goto out;
+ ctx->pos = dotdot_size;
+ continue;
+ }
+
+ de = (struct ext4_dir_entry_2 *)
+ (dir_buf + ctx->pos - extra_offset);
+ if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf,
+ extra_size, ctx->pos))
+ goto out;
+ if (le32_to_cpu(de->inode)) {
+ if (!dir_emit(ctx, de->name, de->name_len,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type)))
+ goto out;
+ }
+ ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size);
}
out:
kfree(dir_buf);
@@ -1619,6 +1605,7 @@
}
struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+ struct ext4_filename *fname,
const struct qstr *d_name,
struct ext4_dir_entry_2 **res_dir,
int *has_inline_data)
@@ -1640,8 +1627,8 @@
inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
EXT4_INLINE_DOTDOT_SIZE;
inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
- ret = search_dir(iloc.bh, inline_start, inline_size,
- dir, d_name, 0, res_dir);
+ ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
+ dir, fname, d_name, 0, res_dir);
if (ret == 1)
goto out_find;
if (ret < 0)
@@ -1653,8 +1640,8 @@
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
- ret = search_dir(iloc.bh, inline_start, inline_size,
- dir, d_name, 0, res_dir);
+ ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
+ dir, fname, d_name, 0, res_dir);
if (ret == 1)
goto out_find;
@@ -1698,6 +1685,7 @@
EXT4_MIN_INLINE_DATA_SIZE;
}
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto out;
@@ -1870,7 +1858,6 @@
{
int error;
struct ext4_xattr_entry *entry;
- struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
@@ -1879,7 +1866,6 @@
return error;
raw_inode = ext4_raw_inode(&iloc);
- header = IHDR(inode, raw_inode);
entry = (struct ext4_xattr_entry *)((void *)raw_inode +
EXT4_I(inode)->i_inline_off);
if (EXT4_XATTR_LEN(entry->e_name_len) +
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 221b582..271c336 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -83,8 +83,7 @@
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
- !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ !ext4_has_metadata_csum(inode->i_sb))
return 1;
provided = le16_to_cpu(raw->i_checksum_lo);
@@ -105,8 +104,7 @@
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
- !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ !ext4_has_metadata_csum(inode->i_sb))
return;
csum = ext4_inode_csum(inode, raw, ei);
@@ -133,20 +131,23 @@
new_size);
}
-static void ext4_invalidatepage(struct page *page, unsigned long offset);
+static void ext4_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
-static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
- struct inode *inode, struct page *page, loff_t from,
- loff_t length, int flags);
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+ int pextents);
/*
* Test whether an inode is a fast symlink.
*/
-static int ext4_inode_is_fast_symlink(struct inode *inode)
+int ext4_inode_is_fast_symlink(struct inode *inode)
{
- int ea_blocks = EXT4_I(inode)->i_file_acl ?
- (inode->i_sb->s_blocksize >> 9) : 0;
+ int ea_blocks = EXT4_I(inode)->i_file_acl ?
+ EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
+
+ if (ext4_has_inline_data(inode))
+ return 0;
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
@@ -215,21 +216,21 @@
jbd2_complete_transaction(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
- truncate_inode_pages(&inode->i_data, 0);
- ext4_ioend_shutdown(inode);
+ truncate_inode_pages_final(&inode->i_data);
+
+ WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
goto no_delete;
}
- if (!is_bad_inode(inode))
- dquot_initialize(inode);
+ if (is_bad_inode(inode))
+ goto no_delete;
+ dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
- truncate_inode_pages(&inode->i_data, 0);
- ext4_ioend_shutdown(inode);
+ truncate_inode_pages_final(&inode->i_data);
- if (is_bad_inode(inode))
- goto no_delete;
+ WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
/*
* Protect us against freezing - iput() caller didn't have to have any
@@ -321,18 +322,6 @@
#endif
/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate a block located at @lblock
- */
-static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
-{
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- return ext4_ext_calc_metadata_amount(inode, lblock);
-
- return ext4_ind_calc_metadata_amount(inode, lblock);
-}
-
-/*
* Called with i_data_sem down, which is important since we can call
* ext4_discard_preallocations() from here.
*/
@@ -353,35 +342,10 @@
used = ei->i_reserved_data_blocks;
}
- if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
- ext4_warning(inode->i_sb, "ino %lu, allocated %d "
- "with only %d reserved metadata blocks "
- "(releasing %d blocks with reserved %d data blocks)",
- inode->i_ino, ei->i_allocated_meta_blocks,
- ei->i_reserved_meta_blocks, used,
- ei->i_reserved_data_blocks);
- WARN_ON(1);
- ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
- }
-
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
- ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- percpu_counter_sub(&sbi->s_dirtyclusters_counter,
- used + ei->i_allocated_meta_blocks);
- ei->i_allocated_meta_blocks = 0;
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
- if (ei->i_reserved_data_blocks == 0) {
- /*
- * We can release all of the reserved metadata blocks
- * only when we have written all of the delayed
- * allocation blocks.
- */
- percpu_counter_sub(&sbi->s_dirtyclusters_counter,
- ei->i_reserved_meta_blocks);
- ei->i_reserved_meta_blocks = 0;
- ei->i_da_metadata_calc_len = 0;
- }
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
@@ -424,66 +388,6 @@
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
-/*
- * Return the number of contiguous dirty pages in a given inode
- * starting at page frame idx.
- */
-static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
- unsigned int max_pages)
-{
- struct address_space *mapping = inode->i_mapping;
- pgoff_t index;
- struct pagevec pvec;
- pgoff_t num = 0;
- int i, nr_pages, done = 0;
-
- if (max_pages == 0)
- return 0;
- pagevec_init(&pvec, 0);
- while (!done) {
- index = idx;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- (pgoff_t)PAGEVEC_SIZE);
- if (nr_pages == 0)
- break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
- struct buffer_head *bh, *head;
-
- lock_page(page);
- if (unlikely(page->mapping != mapping) ||
- !PageDirty(page) ||
- PageWriteback(page) ||
- page->index != idx) {
- done = 1;
- unlock_page(page);
- break;
- }
- if (page_has_buffers(page)) {
- bh = head = page_buffers(page);
- do {
- if (!buffer_delay(bh) &&
- !buffer_unwritten(bh))
- done = 1;
- bh = bh->b_this_page;
- } while (!done && (bh != head));
- }
- unlock_page(page);
- if (done)
- break;
- idx++;
- num++;
- if (num >= max_pages) {
- done = 1;
- break;
- }
- }
- pagevec_release(&pvec);
- }
- return num;
-}
-
#ifdef ES_AGGRESSIVE_TEST
static void ext4_map_blocks_es_recheck(handle_t *handle,
struct inode *inode,
@@ -502,7 +406,7 @@
* could be converted.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -525,7 +429,7 @@
if (es_map->m_lblk != map->m_lblk ||
es_map->m_flags != map->m_flags ||
es_map->m_pblk != map->m_pblk) {
- printk("ES cache assertation failed for inode: %lu "
+ printk("ES cache assertion failed for inode: %lu "
"es_cached ex [%d/%d/%llu/%x] != "
"found ex [%d/%d/%llu/%x] retval %d flags %x\n",
inode->i_ino, es_map->m_lblk, es_map->m_len,
@@ -548,8 +452,8 @@
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
- * On success, it returns the number of blocks being mapped or allocate.
- * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * On success, it returns the number of blocks being mapped or allocated.
+ * if create==0 and the blocks are pre-allocated and unwritten block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
@@ -563,6 +467,7 @@
{
struct extent_status es;
int retval;
+ int ret = 0;
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
@@ -574,8 +479,19 @@
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
+ /*
+ * ext4_map_blocks returns an int, and m_len is an unsigned int
+ */
+ if (unlikely(map->m_len > INT_MAX))
+ map->m_len = INT_MAX;
+
+ /* We can handle the block number less than EXT_MAX_BLOCKS */
+ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
+ return -EIO;
+
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ ext4_es_lru_add(inode);
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
@@ -602,7 +518,7 @@
* file system block.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -611,22 +527,19 @@
EXT4_GET_BLOCKS_KEEP_SIZE);
}
if (retval > 0) {
- int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
- !(status & EXTENT_STATUS_WRITTEN) &&
ext4_find_delalloc_range(inode, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
@@ -640,7 +553,7 @@
found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret = check_block_validity(inode, map);
+ ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
@@ -657,7 +570,13 @@
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
- return retval;
+ /*
+ * If we need to convert extent to unwritten
+ * we continue and do the actual work in
+ * ext4_ext_map_blocks()
+ */
+ if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
+ return retval;
/*
* Here we clear m_flags because after allocating an new extent,
@@ -666,22 +585,14 @@
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
- * New blocks allocate and/or writing to uninitialized extent
+ * New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
- * the write lock of i_data_sem, and call get_blocks()
+ * the write lock of i_data_sem, and call get_block()
* with create == 1 flag.
*/
- down_write((&EXT4_I(inode)->i_data_sem));
+ down_write(&EXT4_I(inode)->i_data_sem);
/*
- * if the caller is from delayed allocation writeout path
- * we have already reserved fs blocks for allocation
- * let the underlying get_block() function know to
- * avoid double accounting
- */
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
- /*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
@@ -709,21 +620,17 @@
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
if (retval > 0) {
- int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (allocation)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
/*
* If the extent has been zeroed out, we don't need to update
@@ -737,7 +644,6 @@
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
- !(status & EXTENT_STATUS_WRITTEN) &&
ext4_find_delalloc_range(inode, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
@@ -750,7 +656,7 @@
has_zeroout:
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret = check_block_validity(inode, map);
+ ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
@@ -790,8 +696,12 @@
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret > 0) {
+ ext4_io_end_t *io_end = ext4_inode_aio(inode);
+
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+ if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
+ set_buffer_defer_completion(bh);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
}
@@ -811,11 +721,11 @@
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
- ext4_lblk_t block, int create, int *errp)
+ ext4_lblk_t block, int create)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
- int fatal = 0, err;
+ int err;
J_ASSERT(handle != NULL || create == 0);
@@ -824,21 +734,14 @@
err = ext4_map_blocks(handle, inode, &map,
create ? EXT4_GET_BLOCKS_CREATE : 0);
- /* ensure we send some value back into *errp */
- *errp = 0;
-
- if (create && err == 0)
- err = -ENOSPC; /* should never happen */
+ if (err == 0)
+ return create ? ERR_PTR(-ENOSPC) : NULL;
if (err < 0)
- *errp = err;
- if (err <= 0)
- return NULL;
+ return ERR_PTR(err);
bh = sb_getblk(inode->i_sb, map.m_pblk);
- if (unlikely(!bh)) {
- *errp = -ENOMEM;
- return NULL;
- }
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
J_ASSERT(create != 0);
J_ASSERT(handle != NULL);
@@ -852,44 +755,44 @@
*/
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
- fatal = ext4_journal_get_create_access(handle, bh);
- if (!fatal && !buffer_uptodate(bh)) {
+ err = ext4_journal_get_create_access(handle, bh);
+ if (unlikely(err)) {
+ unlock_buffer(bh);
+ goto errout;
+ }
+ if (!buffer_uptodate(bh)) {
memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (!fatal)
- fatal = err;
- } else {
+ if (unlikely(err))
+ goto errout;
+ } else
BUFFER_TRACE(bh, "not a new buffer");
- }
- if (fatal) {
- *errp = fatal;
- brelse(bh);
- bh = NULL;
- }
return bh;
+errout:
+ brelse(bh);
+ return ERR_PTR(err);
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
- ext4_lblk_t block, int create, int *err)
+ ext4_lblk_t block, int create)
{
struct buffer_head *bh;
- bh = ext4_getblk(handle, inode, block, create, err);
- if (!bh)
+ bh = ext4_getblk(handle, inode, block, create);
+ if (IS_ERR(bh))
return bh;
- if (buffer_uptodate(bh))
+ if (!bh || buffer_uptodate(bh))
return bh;
ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
put_bh(bh);
- *err = -EIO;
- return NULL;
+ return ERR_PTR(-EIO);
}
int ext4_walk_page_buffers(handle_t *handle,
@@ -965,6 +868,7 @@
*/
if (dirty)
clear_buffer_dirty(bh);
+ BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -973,6 +877,95 @@
static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
+ get_block_t *get_block)
+{
+ unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+ unsigned to = from + len;
+ struct inode *inode = page->mapping->host;
+ unsigned block_start, block_end;
+ sector_t block;
+ int err = 0;
+ unsigned blocksize = inode->i_sb->s_blocksize;
+ unsigned bbits;
+ struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
+ bool decrypt = false;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(from > PAGE_CACHE_SIZE);
+ BUG_ON(to > PAGE_CACHE_SIZE);
+ BUG_ON(from > to);
+
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, blocksize, 0);
+ head = page_buffers(page);
+ bbits = ilog2(blocksize);
+ block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+
+ for (bh = head, block_start = 0; bh != head || !block_start;
+ block++, block_start = block_end, bh = bh->b_this_page) {
+ block_end = block_start + blocksize;
+ if (block_end <= from || block_start >= to) {
+ if (PageUptodate(page)) {
+ if (!buffer_uptodate(bh))
+ set_buffer_uptodate(bh);
+ }
+ continue;
+ }
+ if (buffer_new(bh))
+ clear_buffer_new(bh);
+ if (!buffer_mapped(bh)) {
+ WARN_ON(bh->b_size != blocksize);
+ err = get_block(inode, block, bh, 1);
+ if (err)
+ break;
+ if (buffer_new(bh)) {
+ unmap_underlying_metadata(bh->b_bdev,
+ bh->b_blocknr);
+ if (PageUptodate(page)) {
+ clear_buffer_new(bh);
+ set_buffer_uptodate(bh);
+ mark_buffer_dirty(bh);
+ continue;
+ }
+ if (block_end > to || block_start < from)
+ zero_user_segments(page, to, block_end,
+ block_start, from);
+ continue;
+ }
+ }
+ if (PageUptodate(page)) {
+ if (!buffer_uptodate(bh))
+ set_buffer_uptodate(bh);
+ continue;
+ }
+ if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
+ !buffer_unwritten(bh) &&
+ (block_start < from || block_end > to)) {
+ ll_rw_block(READ, 1, &bh);
+ *wait_bh++ = bh;
+ decrypt = ext4_encrypted_inode(inode) &&
+ S_ISREG(inode->i_mode);
+ }
+ }
+ /*
+ * If we issued read requests, let them complete.
+ */
+ while (wait_bh > wait) {
+ wait_on_buffer(*--wait_bh);
+ if (!buffer_uptodate(*wait_bh))
+ err = -EIO;
+ }
+ if (unlikely(err))
+ page_zero_new_buffers(page, from, to);
+ else if (decrypt)
+ err = ext4_decrypt_one(inode, page);
+ return err;
+}
+#endif
+
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1035,11 +1028,19 @@
/* In case writeback began while the page was unlocked */
wait_for_stable_page(page);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (ext4_should_dioread_nolock(inode))
+ ret = ext4_block_write_begin(page, pos, len,
+ ext4_get_block_write);
+ else
+ ret = ext4_block_write_begin(page, pos, len,
+ ext4_get_block);
+#else
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
else
ret = __block_write_begin(page, pos, len, ext4_get_block);
-
+#endif
if (!ret && ext4_should_journal_data(inode)) {
ret = ext4_walk_page_buffers(handle, page_buffers(page),
from, to, NULL,
@@ -1131,27 +1132,11 @@
} else
copied = block_write_end(file, mapping, pos,
len, copied, page, fsdata);
-
/*
- * No need to use i_size_read() here, the i_size
- * cannot change under us because we hole i_mutex.
- *
- * But it's important to update i_size while still holding page lock:
+ * it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
- if (pos + copied > inode->i_size) {
- i_size_write(inode, pos + copied);
- i_size_changed = 1;
- }
-
- if (pos + copied > EXT4_I(inode)->i_disksize) {
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * but greater than i_disksize. (hint delalloc)
- */
- ext4_update_i_disksize(inode, (pos + copied));
- i_size_changed = 1;
- }
+ i_size_changed = ext4_update_inode_size(inode, pos + copied);
unlock_page(page);
page_cache_release(page);
@@ -1164,8 +1149,6 @@
if (i_size_changed)
ext4_mark_inode_dirty(handle, inode);
- if (copied < 0)
- ret = copied;
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
@@ -1201,7 +1184,7 @@
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
- loff_t new_i_size;
+ int size_changed = 0;
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1224,20 +1207,18 @@
if (!partial)
SetPageUptodate(page);
}
- new_i_size = pos + copied;
- if (new_i_size > inode->i_size)
- i_size_write(inode, pos+copied);
+ size_changed = ext4_update_inode_size(inode, pos + copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, new_i_size);
+ unlock_page(page);
+ page_cache_release(page);
+
+ if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
- unlock_page(page);
- page_cache_release(page);
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
@@ -1263,49 +1244,6 @@
}
/*
- * Reserve a metadata for a single block located at lblock
- */
-static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
-{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- struct ext4_inode_info *ei = EXT4_I(inode);
- unsigned int md_needed;
- ext4_lblk_t save_last_lblock;
- int save_len;
-
- /*
- * recalculate the amount of metadata blocks to reserve
- * in order to allocate nrblocks
- * worse case is one extent per block
- */
- spin_lock(&ei->i_block_reservation_lock);
- /*
- * ext4_calc_metadata_amount() has side effects, which we have
- * to be prepared undo if we fail to claim space.
- */
- save_len = ei->i_da_metadata_calc_len;
- save_last_lblock = ei->i_da_metadata_calc_last_lblock;
- md_needed = EXT4_NUM_B2C(sbi,
- ext4_calc_metadata_amount(inode, lblock));
- trace_ext4_da_reserve_space(inode, md_needed);
-
- /*
- * We do still charge estimated metadata to the sb though;
- * we cannot afford to run out of free blocks.
- */
- if (ext4_claim_free_clusters(sbi, md_needed, 0)) {
- ei->i_da_metadata_calc_len = save_len;
- ei->i_da_metadata_calc_last_lblock = save_last_lblock;
- spin_unlock(&ei->i_block_reservation_lock);
- return -ENOSPC;
- }
- ei->i_reserved_meta_blocks += md_needed;
- spin_unlock(&ei->i_block_reservation_lock);
-
- return 0; /* success */
-}
-
-/*
* Reserve a single cluster located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
@@ -1314,8 +1252,6 @@
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
int ret;
- ext4_lblk_t save_last_lblock;
- int save_len;
/*
* We will charge metadata quota at writeout time; this saves
@@ -1336,25 +1272,15 @@
* ext4_calc_metadata_amount() has side effects, which we have
* to be prepared undo if we fail to claim space.
*/
- save_len = ei->i_da_metadata_calc_len;
- save_last_lblock = ei->i_da_metadata_calc_last_lblock;
- md_needed = EXT4_NUM_B2C(sbi,
- ext4_calc_metadata_amount(inode, lblock));
- trace_ext4_da_reserve_space(inode, md_needed);
+ md_needed = 0;
+ trace_ext4_da_reserve_space(inode, 0);
- /*
- * We do still charge estimated metadata to the sb though;
- * we cannot afford to run out of free blocks.
- */
- if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
- ei->i_da_metadata_calc_len = save_len;
- ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+ if (ext4_claim_free_clusters(sbi, 1, 0)) {
spin_unlock(&ei->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
ei->i_reserved_data_blocks++;
- ei->i_reserved_meta_blocks += md_needed;
spin_unlock(&ei->i_block_reservation_lock);
return 0; /* success */
@@ -1387,20 +1313,6 @@
}
ei->i_reserved_data_blocks -= to_free;
- if (ei->i_reserved_data_blocks == 0) {
- /*
- * We can release all of the reserved metadata blocks
- * only when we have written all of the delayed
- * allocation blocks.
- * Note that in case of bigalloc, i_reserved_meta_blocks,
- * i_reserved_data_blocks, etc. refer to number of clusters.
- */
- percpu_counter_sub(&sbi->s_dirtyclusters_counter,
- ei->i_reserved_meta_blocks);
- ei->i_reserved_meta_blocks = 0;
- ei->i_da_metadata_calc_len = 0;
- }
-
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
@@ -1410,40 +1322,38 @@
}
static void ext4_da_page_release_reservation(struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
- int to_release = 0, contiguous_blks = 0;
+ int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
struct inode *inode = page->mapping->host;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned int stop = offset + length;
int num_clusters;
ext4_fsblk_t lblk;
+ BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+
head = page_buffers(page);
bh = head;
do {
unsigned int next_off = curr_off + bh->b_size;
+ if (next_off > stop)
+ break;
+
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
- contiguous_blks++;
clear_buffer_delay(bh);
- } else if (contiguous_blks) {
- lblk = page->index <<
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
- lblk += (curr_off >> inode->i_blkbits) -
- contiguous_blks;
- ext4_es_remove_extent(inode, lblk, contiguous_blks);
- contiguous_blks = 0;
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- if (contiguous_blks) {
+ if (to_release) {
lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
- ext4_es_remove_extent(inode, lblk, contiguous_blks);
+ ext4_es_remove_extent(inode, lblk, to_release);
}
/* If we have released all the blocks belonging to a cluster, then we
@@ -1464,140 +1374,43 @@
* Delayed allocation stuff
*/
-/*
- * mpage_da_submit_io - walks through extent of pages and try to write
- * them with writepage() call back
- *
- * @mpd->inode: inode
- * @mpd->first_page: first page of the extent
- * @mpd->next_page: page after the last page of the extent
- *
- * By the time mpage_da_submit_io() is called we expect all blocks
- * to be allocated. this may be wrong if allocation failed.
- *
- * As pages are already locked by write_cache_pages(), we can't use it
- */
-static int mpage_da_submit_io(struct mpage_da_data *mpd,
- struct ext4_map_blocks *map)
-{
- struct pagevec pvec;
- unsigned long index, end;
- int ret = 0, err, nr_pages, i;
- struct inode *inode = mpd->inode;
- struct address_space *mapping = inode->i_mapping;
- loff_t size = i_size_read(inode);
- unsigned int len, block_start;
- struct buffer_head *bh, *page_bufs = NULL;
- sector_t pblock = 0, cur_logical = 0;
- struct ext4_io_submit io_submit;
+struct mpage_da_data {
+ struct inode *inode;
+ struct writeback_control *wbc;
- BUG_ON(mpd->next_page <= mpd->first_page);
- memset(&io_submit, 0, sizeof(io_submit));
+ pgoff_t first_page; /* The first page to write */
+ pgoff_t next_page; /* Current page to examine */
+ pgoff_t last_page; /* Last page to examine */
/*
- * We need to start from the first_page to the next_page - 1
- * to make sure we also write the mapped dirty buffer_heads.
- * If we look at mpd->b_blocknr we would only be looking
- * at the currently mapped buffer_heads.
+ * Extent to map - this can be after first_page because that can be
+ * fully mapped. We somewhat abuse m_flags to store whether the extent
+ * is delalloc or unwritten.
*/
- index = mpd->first_page;
- end = mpd->next_page - 1;
+ struct ext4_map_blocks map;
+ struct ext4_io_submit io_submit; /* IO submission data */
+};
- pagevec_init(&pvec, 0);
- while (index <= end) {
- nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
- if (nr_pages == 0)
- break;
- for (i = 0; i < nr_pages; i++) {
- int skip_page = 0;
- struct page *page = pvec.pages[i];
-
- index = page->index;
- if (index > end)
- break;
-
- if (index == size >> PAGE_CACHE_SHIFT)
- len = size & ~PAGE_CACHE_MASK;
- else
- len = PAGE_CACHE_SIZE;
- if (map) {
- cur_logical = index << (PAGE_CACHE_SHIFT -
- inode->i_blkbits);
- pblock = map->m_pblk + (cur_logical -
- map->m_lblk);
- }
- index++;
-
- BUG_ON(!PageLocked(page));
- BUG_ON(PageWriteback(page));
-
- bh = page_bufs = page_buffers(page);
- block_start = 0;
- do {
- if (map && (cur_logical >= map->m_lblk) &&
- (cur_logical <= (map->m_lblk +
- (map->m_len - 1)))) {
- if (buffer_delay(bh)) {
- clear_buffer_delay(bh);
- bh->b_blocknr = pblock;
- }
- if (buffer_unwritten(bh) ||
- buffer_mapped(bh))
- BUG_ON(bh->b_blocknr != pblock);
- if (map->m_flags & EXT4_MAP_UNINIT)
- set_buffer_uninit(bh);
- clear_buffer_unwritten(bh);
- }
-
- /*
- * skip page if block allocation undone and
- * block is dirty
- */
- if (ext4_bh_delay_or_unwritten(NULL, bh))
- skip_page = 1;
- bh = bh->b_this_page;
- block_start += bh->b_size;
- cur_logical++;
- pblock++;
- } while (bh != page_bufs);
-
- if (skip_page) {
- unlock_page(page);
- continue;
- }
-
- clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&io_submit, page, len,
- mpd->wbc);
- if (!err)
- mpd->pages_written++;
- /*
- * In error case, we have to continue because
- * remaining pages are still locked
- */
- if (ret == 0)
- ret = err;
- }
- pagevec_release(&pvec);
- }
- ext4_io_submit(&io_submit);
- return ret;
-}
-
-static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
+static void mpage_release_unused_pages(struct mpage_da_data *mpd,
+ bool invalidate)
{
int nr_pages, i;
pgoff_t index, end;
struct pagevec pvec;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
- ext4_lblk_t start, last;
+
+ /* This is necessary when next_page == 0. */
+ if (mpd->first_page >= mpd->next_page)
+ return;
index = mpd->first_page;
end = mpd->next_page - 1;
-
- start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- ext4_es_remove_extent(inode, start, last - start + 1);
+ if (invalidate) {
+ ext4_lblk_t start, last;
+ start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ ext4_es_remove_extent(inode, start, last - start + 1);
+ }
pagevec_init(&pvec, 0);
while (index <= end) {
@@ -1610,14 +1423,15 @@
break;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- block_invalidatepage(page, 0);
- ClearPageUptodate(page);
+ if (invalidate) {
+ block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+ ClearPageUptodate(page);
+ }
unlock_page(page);
}
index = pvec.pages[nr_pages - 1]->index + 1;
pagevec_release(&pvec);
}
- return;
}
static void ext4_print_free_blocks(struct inode *inode)
@@ -1639,219 +1453,6 @@
ext4_msg(sb, KERN_CRIT, "Block reservation details");
ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
ei->i_reserved_data_blocks);
- ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u",
- ei->i_reserved_meta_blocks);
- ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u",
- ei->i_allocated_meta_blocks);
- return;
-}
-
-/*
- * mpage_da_map_and_submit - go through given space, map them
- * if necessary, and then submit them for I/O
- *
- * @mpd - bh describing space
- *
- * The function skips space we know is already mapped to disk blocks.
- *
- */
-static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
-{
- int err, blks, get_blocks_flags;
- struct ext4_map_blocks map, *mapp = NULL;
- sector_t next = mpd->b_blocknr;
- unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
- loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
- handle_t *handle = NULL;
-
- /*
- * If the blocks are mapped already, or we couldn't accumulate
- * any blocks, then proceed immediately to the submission stage.
- */
- if ((mpd->b_size == 0) ||
- ((mpd->b_state & (1 << BH_Mapped)) &&
- !(mpd->b_state & (1 << BH_Delay)) &&
- !(mpd->b_state & (1 << BH_Unwritten))))
- goto submit_io;
-
- handle = ext4_journal_current_handle();
- BUG_ON(!handle);
-
- /*
- * Call ext4_map_blocks() to allocate any delayed allocation
- * blocks, or to convert an uninitialized extent to be
- * initialized (in the case where we have written into
- * one or more preallocated blocks).
- *
- * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
- * indicate that we are on the delayed allocation path. This
- * affects functions in many different parts of the allocation
- * call path. This flag exists primarily because we don't
- * want to change *many* call functions, so ext4_map_blocks()
- * will set the EXT4_STATE_DELALLOC_RESERVED flag once the
- * inode's allocation semaphore is taken.
- *
- * If the blocks in questions were delalloc blocks, set
- * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
- * variables are updated after the blocks have been allocated.
- */
- map.m_lblk = next;
- map.m_len = max_blocks;
- /*
- * We're in delalloc path and it is possible that we're going to
- * need more metadata blocks than previously reserved. However
- * we must not fail because we're in writeback and there is
- * nothing we can do about it so it might result in data loss.
- * So use reserved blocks to allocate metadata if possible.
- */
- get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
- EXT4_GET_BLOCKS_METADATA_NOFAIL;
- if (ext4_should_dioread_nolock(mpd->inode))
- get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
- if (mpd->b_state & (1 << BH_Delay))
- get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
-
-
- blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
- if (blks < 0) {
- struct super_block *sb = mpd->inode->i_sb;
-
- err = blks;
- /*
- * If get block returns EAGAIN or ENOSPC and there
- * appears to be free blocks we will just let
- * mpage_da_submit_io() unlock all of the pages.
- */
- if (err == -EAGAIN)
- goto submit_io;
-
- if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
- mpd->retval = err;
- goto submit_io;
- }
-
- /*
- * get block failure will cause us to loop in
- * writepages, because a_ops->writepage won't be able
- * to make progress. The page will be redirtied by
- * writepage and writepages will again try to write
- * the same.
- */
- if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) {
- ext4_msg(sb, KERN_CRIT,
- "delayed block allocation failed for inode %lu "
- "at logical offset %llu with max blocks %zd "
- "with error %d", mpd->inode->i_ino,
- (unsigned long long) next,
- mpd->b_size >> mpd->inode->i_blkbits, err);
- ext4_msg(sb, KERN_CRIT,
- "This should not happen!! Data will be lost");
- if (err == -ENOSPC)
- ext4_print_free_blocks(mpd->inode);
- }
- /* invalidate all the pages */
- ext4_da_block_invalidatepages(mpd);
-
- /* Mark this page range as having been completed */
- mpd->io_done = 1;
- return;
- }
- BUG_ON(blks == 0);
-
- mapp = ↦
- if (map.m_flags & EXT4_MAP_NEW) {
- struct block_device *bdev = mpd->inode->i_sb->s_bdev;
- int i;
-
- for (i = 0; i < map.m_len; i++)
- unmap_underlying_metadata(bdev, map.m_pblk + i);
- }
-
- /*
- * Update on-disk size along with block allocation.
- */
- disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
- if (disksize > i_size_read(mpd->inode))
- disksize = i_size_read(mpd->inode);
- if (disksize > EXT4_I(mpd->inode)->i_disksize) {
- ext4_update_i_disksize(mpd->inode, disksize);
- err = ext4_mark_inode_dirty(handle, mpd->inode);
- if (err)
- ext4_error(mpd->inode->i_sb,
- "Failed to mark inode %lu dirty",
- mpd->inode->i_ino);
- }
-
-submit_io:
- mpage_da_submit_io(mpd, mapp);
- mpd->io_done = 1;
-}
-
-#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
- (1 << BH_Delay) | (1 << BH_Unwritten))
-
-/*
- * mpage_add_bh_to_extent - try to add one more block to extent of blocks
- *
- * @mpd->lbh - extent of blocks
- * @logical - logical number of the block in the file
- * @b_state - b_state of the buffer head added
- *
- * the function is used to collect contig. blocks in same state
- */
-static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t logical,
- unsigned long b_state)
-{
- sector_t next;
- int blkbits = mpd->inode->i_blkbits;
- int nrblocks = mpd->b_size >> blkbits;
-
- /*
- * XXX Don't go larger than mballoc is willing to allocate
- * This is a stopgap solution. We eventually need to fold
- * mpage_da_submit_io() into this function and then call
- * ext4_map_blocks() multiple times in a loop
- */
- if (nrblocks >= (8*1024*1024 >> blkbits))
- goto flush_it;
-
- /* check if the reserved journal credits might overflow */
- if (!ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS)) {
- if (nrblocks >= EXT4_MAX_TRANS_DATA) {
- /*
- * With non-extent format we are limited by the journal
- * credit available. Total credit needed to insert
- * nrblocks contiguous blocks is dependent on the
- * nrblocks. So limit nrblocks.
- */
- goto flush_it;
- }
- }
- /*
- * First block in the extent
- */
- if (mpd->b_size == 0) {
- mpd->b_blocknr = logical;
- mpd->b_size = 1 << blkbits;
- mpd->b_state = b_state & BH_FLAGS;
- return;
- }
-
- next = mpd->b_blocknr + nrblocks;
- /*
- * Can we merge the block to our big extent?
- */
- if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
- mpd->b_size += 1 << blkbits;
- return;
- }
-
-flush_it:
- /*
- * We couldn't merge the block to our extent, so we
- * need to flush current extent and start new one
- */
- mpage_da_map_and_submit(mpd);
return;
}
@@ -1889,10 +1490,10 @@
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, &es)) {
-
+ ext4_es_lru_add(inode);
if (ext4_es_is_hole(&es)) {
retval = 0;
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
@@ -1929,7 +1530,7 @@
* Try to see if we can get the block without requesting a new
* file system block.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode)) {
/*
* We will soon create blocks for this page, and let
@@ -1968,13 +1569,6 @@
retval = ret;
goto out_unlock;
}
- } else {
- ret = ext4_da_reserve_metadata(inode, iblock);
- if (ret) {
- /* not enough space to reserve */
- retval = ret;
- goto out_unlock;
- }
}
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
@@ -1994,16 +1588,15 @@
set_buffer_delay(bh);
} else if (retval > 0) {
int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -2020,7 +1613,7 @@
}
/*
- * This is a special get_blocks_t callback which is used by
+ * This is a special get_block_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
*
@@ -2108,33 +1701,21 @@
ext4_walk_page_buffers(handle, page_bufs, 0, len,
NULL, bget_one);
}
- /*
- * We need to release the page lock before we start the
- * journal, so grab a reference so the page won't disappear
- * out from under us.
- */
- get_page(page);
+ /* As soon as we unlock the page, it can go away, but we have
+ * references to buffers so we are safe */
unlock_page(page);
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- put_page(page);
- goto out_no_pagelock;
- }
- BUG_ON(!ext4_handle_valid(handle));
-
- lock_page(page);
- put_page(page);
- if (page->mapping != mapping) {
- /* The page got truncated from under us */
- ext4_journal_stop(handle);
- ret = 0;
goto out;
}
+ BUG_ON(!ext4_handle_valid(handle));
+
if (inline_data) {
+ BUFFER_TRACE(inode_bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode_bh);
err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
@@ -2154,12 +1735,10 @@
ret = err;
if (!ext4_has_inline_data(inode))
- ext4_walk_page_buffers(handle, page_bufs, 0, len,
+ ext4_walk_page_buffers(NULL, page_bufs, 0, len,
NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
- unlock_page(page);
-out_no_pagelock:
brelse(inode_bh);
return ret;
}
@@ -2175,7 +1754,7 @@
* lock so we have to do some magic.
*
* This function can get called via...
- * - ext4_da_writepages after taking page lock (have journal handle)
+ * - ext4_writepages after taking page lock (have journal handle)
* - journal_submit_inode_data_buffers (no journal handle)
* - shrink_page_list via the kswapd/direct reclaim (no journal handle)
* - grab_page_cache when doing write_begin (have journal handle)
@@ -2214,6 +1793,7 @@
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
+ bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
@@ -2244,6 +1824,7 @@
unlock_page(page);
return 0;
}
+ keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -2253,76 +1834,460 @@
*/
return __ext4_journalled_writepage(page, len);
- memset(&io_submit, 0, sizeof(io_submit));
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ext4_io_submit_init(&io_submit, wbc);
+ io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_submit.io_end) {
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return -ENOMEM;
+ }
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
+ /* Drop io_end reference we got from init */
+ ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
-/*
- * This is called via ext4_da_writepages() to
- * calculate the total number of credits to reserve to fit
- * a single extent allocation into a single transaction,
- * ext4_da_writpeages() will loop calling this before
- * the block allocation.
- */
-
-static int ext4_da_writepages_trans_blocks(struct inode *inode)
+static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
{
- int max_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+ int len;
+ loff_t size = i_size_read(mpd->inode);
+ int err;
- /*
- * With non-extent format the journal credit needed to
- * insert nrblocks contiguous block is dependent on
- * number of contiguous block. So we will limit
- * number of contiguous block to a sane value
- */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
- (max_blocks > EXT4_MAX_TRANS_DATA))
- max_blocks = EXT4_MAX_TRANS_DATA;
+ BUG_ON(page->index != mpd->first_page);
+ if (page->index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+ clear_page_dirty_for_io(page);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
+ if (!err)
+ mpd->wbc->nr_to_write--;
+ mpd->first_page++;
- return ext4_chunk_trans_blocks(inode, max_blocks);
+ return err;
+}
+
+#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
+
+/*
+ * mballoc gives us at most this number of blocks...
+ * XXX: That seems to be only a limitation of ext4_mb_normalize_request().
+ * The rest of mballoc seems to handle chunks up to full group size.
+ */
+#define MAX_WRITEPAGES_EXTENT_LEN 2048
+
+/*
+ * mpage_add_bh_to_extent - try to add bh to extent of blocks to map
+ *
+ * @mpd - extent of blocks
+ * @lblk - logical number of the block in the file
+ * @bh - buffer head we want to add to the extent
+ *
+ * The function is used to collect contig. blocks in the same state. If the
+ * buffer doesn't require mapping for writeback and we haven't started the
+ * extent of buffers to map yet, the function returns 'true' immediately - the
+ * caller can write the buffer right away. Otherwise the function returns true
+ * if the block has been added to the extent, false if the block couldn't be
+ * added.
+ */
+static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
+ struct buffer_head *bh)
+{
+ struct ext4_map_blocks *map = &mpd->map;
+
+ /* Buffer that doesn't need mapping for writeback? */
+ if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
+ (!buffer_delay(bh) && !buffer_unwritten(bh))) {
+ /* So far no extent to map => we write the buffer right away */
+ if (map->m_len == 0)
+ return true;
+ return false;
+ }
+
+ /* First block in the extent? */
+ if (map->m_len == 0) {
+ map->m_lblk = lblk;
+ map->m_len = 1;
+ map->m_flags = bh->b_state & BH_FLAGS;
+ return true;
+ }
+
+ /* Don't go larger than mballoc is willing to allocate */
+ if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
+ return false;
+
+ /* Can we merge the block to our big extent? */
+ if (lblk == map->m_lblk + map->m_len &&
+ (bh->b_state & BH_FLAGS) == map->m_flags) {
+ map->m_len++;
+ return true;
+ }
+ return false;
}
/*
- * write_cache_pages_da - walk the list of dirty pages of the given
- * address space and accumulate pages that need writing, and call
- * mpage_da_map_and_submit to map a single contiguous memory region
- * and then write them.
+ * mpage_process_page_bufs - submit page buffers for IO or add them to extent
+ *
+ * @mpd - extent of blocks for mapping
+ * @head - the first buffer in the page
+ * @bh - buffer we should start processing from
+ * @lblk - logical number of the block in the file corresponding to @bh
+ *
+ * Walk through page buffers from @bh upto @head (exclusive) and either submit
+ * the page for IO if all buffers in this page were mapped and there's no
+ * accumulated extent of buffers to map or add buffers in the page to the
+ * extent of buffers to map. The function returns 1 if the caller can continue
+ * by processing the next page, 0 if it should stop adding buffers to the
+ * extent to map because we cannot extend it anymore. It can also return value
+ * < 0 in case of error during IO submission.
*/
-static int write_cache_pages_da(handle_t *handle,
- struct address_space *mapping,
- struct writeback_control *wbc,
- struct mpage_da_data *mpd,
- pgoff_t *done_index)
+static int mpage_process_page_bufs(struct mpage_da_data *mpd,
+ struct buffer_head *head,
+ struct buffer_head *bh,
+ ext4_lblk_t lblk)
{
- struct buffer_head *bh, *head;
- struct inode *inode = mapping->host;
- struct pagevec pvec;
- unsigned int nr_pages;
- sector_t logical;
- pgoff_t index, end;
- long nr_to_write = wbc->nr_to_write;
- int i, tag, ret = 0;
+ struct inode *inode = mpd->inode;
+ int err;
+ ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+ >> inode->i_blkbits;
- memset(mpd, 0, sizeof(struct mpage_da_data));
- mpd->wbc = wbc;
- mpd->inode = inode;
+ do {
+ BUG_ON(buffer_locked(bh));
+
+ if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) {
+ /* Found extent to map? */
+ if (mpd->map.m_len)
+ return 0;
+ /* Everything mapped so far and we hit EOF */
+ break;
+ }
+ } while (lblk++, (bh = bh->b_this_page) != head);
+ /* So far everything mapped? Submit the page for IO. */
+ if (mpd->map.m_len == 0) {
+ err = mpage_submit_page(mpd, head->b_page);
+ if (err < 0)
+ return err;
+ }
+ return lblk < blocks;
+}
+
+/*
+ * mpage_map_buffers - update buffers corresponding to changed extent and
+ * submit fully mapped pages for IO
+ *
+ * @mpd - description of extent to map, on return next extent to map
+ *
+ * Scan buffers corresponding to changed extent (we expect corresponding pages
+ * to be already locked) and update buffer state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits,
+ * and mark buffers as uninit when we perform writes to unwritten extents
+ * and do extent conversion after IO is finished. If the last page is not fully
+ * mapped, we update @map to the next extent in the last page that needs
+ * mapping. Otherwise we submit the page for IO.
+ */
+static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
+{
+ struct pagevec pvec;
+ int nr_pages, i;
+ struct inode *inode = mpd->inode;
+ struct buffer_head *head, *bh;
+ int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits;
+ pgoff_t start, end;
+ ext4_lblk_t lblk;
+ sector_t pblock;
+ int err;
+
+ start = mpd->map.m_lblk >> bpp_bits;
+ end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
+ lblk = start << bpp_bits;
+ pblock = mpd->map.m_pblk;
+
pagevec_init(&pvec, 0);
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ while (start <= end) {
+ nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start,
+ PAGEVEC_SIZE);
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
- if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ if (page->index > end)
+ break;
+ /* Up to 'end' pages must be contiguous */
+ BUG_ON(page->index != start);
+ bh = head = page_buffers(page);
+ do {
+ if (lblk < mpd->map.m_lblk)
+ continue;
+ if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+ /*
+ * Buffer after end of mapped extent.
+ * Find next buffer in the page to map.
+ */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ /*
+ * FIXME: If dioread_nolock supports
+ * blocksize < pagesize, we need to make
+ * sure we add size mapped so far to
+ * io_end->size as the following call
+ * can submit the page for IO.
+ */
+ err = mpage_process_page_bufs(mpd, head,
+ bh, lblk);
+ pagevec_release(&pvec);
+ if (err > 0)
+ err = 0;
+ return err;
+ }
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock++;
+ }
+ clear_buffer_unwritten(bh);
+ } while (lblk++, (bh = bh->b_this_page) != head);
+
+ /*
+ * FIXME: This is going to break if dioread_nolock
+ * supports blocksize < pagesize as we will try to
+ * convert potentially unmapped parts of inode.
+ */
+ mpd->io_submit.io_end->size += PAGE_CACHE_SIZE;
+ /* Page fully mapped - let IO run! */
+ err = mpage_submit_page(mpd, page);
+ if (err < 0) {
+ pagevec_release(&pvec);
+ return err;
+ }
+ start++;
+ }
+ pagevec_release(&pvec);
+ }
+ /* Extent fully mapped and matches with page boundary. We are done. */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ return 0;
+}
+
+static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
+{
+ struct inode *inode = mpd->inode;
+ struct ext4_map_blocks *map = &mpd->map;
+ int get_blocks_flags;
+ int err, dioread_nolock;
+
+ trace_ext4_da_write_pages_extent(inode, map);
+ /*
+ * Call ext4_map_blocks() to allocate any delayed allocation blocks, or
+ * to convert an unwritten extent to be initialized (in the case
+ * where we have written into one or more preallocated blocks). It is
+ * possible that we're going to need more metadata blocks than
+ * previously reserved. However we must not fail because we're in
+ * writeback and there is nothing we can do about it so it might result
+ * in data loss. So use reserved blocks to allocate metadata if
+ * possible.
+ *
+ * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if
+ * the blocks in question are delalloc blocks. This indicates
+ * that the blocks and quotas has already been checked when
+ * the data was copied into the page cache.
+ */
+ get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
+ EXT4_GET_BLOCKS_METADATA_NOFAIL;
+ dioread_nolock = ext4_should_dioread_nolock(inode);
+ if (dioread_nolock)
+ get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
+ if (map->m_flags & (1 << BH_Delay))
+ get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
+ err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
+ if (err < 0)
+ return err;
+ if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
+ if (!mpd->io_submit.io_end->handle &&
+ ext4_handle_valid(handle)) {
+ mpd->io_submit.io_end->handle = handle->h_rsv_handle;
+ handle->h_rsv_handle = NULL;
+ }
+ ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end);
+ }
+
+ BUG_ON(map->m_len == 0);
+ if (map->m_flags & EXT4_MAP_NEW) {
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ int i;
+
+ for (i = 0; i < map->m_len; i++)
+ unmap_underlying_metadata(bdev, map->m_pblk + i);
+ }
+ return 0;
+}
+
+/*
+ * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
+ * mpd->len and submit pages underlying it for IO
+ *
+ * @handle - handle for journal operations
+ * @mpd - extent to map
+ * @give_up_on_write - we set this to true iff there is a fatal error and there
+ * is no hope of writing the data. The caller should discard
+ * dirty pages to avoid infinite loops.
+ *
+ * The function maps extent starting at mpd->lblk of length mpd->len. If it is
+ * delayed, blocks are allocated, if it is unwritten, we may need to convert
+ * them to initialized or split the described range from larger unwritten
+ * extent. Note that we need not map all the described range since allocation
+ * can return less blocks or the range is covered by more unwritten extents. We
+ * cannot map more because we are limited by reserved transaction credits. On
+ * the other hand we always make sure that the last touched page is fully
+ * mapped so that it can be written out (and thus forward progress is
+ * guaranteed). After mapping we submit all mapped pages for IO.
+ */
+static int mpage_map_and_submit_extent(handle_t *handle,
+ struct mpage_da_data *mpd,
+ bool *give_up_on_write)
+{
+ struct inode *inode = mpd->inode;
+ struct ext4_map_blocks *map = &mpd->map;
+ int err;
+ loff_t disksize;
+ int progress = 0;
+
+ mpd->io_submit.io_end->offset =
+ ((loff_t)map->m_lblk) << inode->i_blkbits;
+ do {
+ err = mpage_map_one_extent(handle, mpd);
+ if (err < 0) {
+ struct super_block *sb = inode->i_sb;
+
+ if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ goto invalidate_dirty_pages;
+ /*
+ * Let the uper layers retry transient errors.
+ * In the case of ENOSPC, if ext4_count_free_blocks()
+ * is non-zero, a commit should free up blocks.
+ */
+ if ((err == -ENOMEM) ||
+ (err == -ENOSPC && ext4_count_free_clusters(sb))) {
+ if (progress)
+ goto update_disksize;
+ return err;
+ }
+ ext4_msg(sb, KERN_CRIT,
+ "Delayed block allocation failed for "
+ "inode %lu at logical offset %llu with"
+ " max blocks %u with error %d",
+ inode->i_ino,
+ (unsigned long long)map->m_lblk,
+ (unsigned)map->m_len, -err);
+ ext4_msg(sb, KERN_CRIT,
+ "This should not happen!! Data will "
+ "be lost\n");
+ if (err == -ENOSPC)
+ ext4_print_free_blocks(inode);
+ invalidate_dirty_pages:
+ *give_up_on_write = true;
+ return err;
+ }
+ progress = 1;
+ /*
+ * Update buffer state, submit mapped pages, and get us new
+ * extent to map
+ */
+ err = mpage_map_and_submit_buffers(mpd);
+ if (err < 0)
+ goto update_disksize;
+ } while (map->m_len);
+
+update_disksize:
+ /*
+ * Update on-disk size after IO is submitted. Races with
+ * truncate are avoided by checking i_size under i_data_sem.
+ */
+ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
+ if (disksize > EXT4_I(inode)->i_disksize) {
+ int err2;
+ loff_t i_size;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ i_size = i_size_read(inode);
+ if (disksize > i_size)
+ disksize = i_size;
+ if (disksize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = disksize;
+ err2 = ext4_mark_inode_dirty(handle, inode);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (err2)
+ ext4_error(inode->i_sb,
+ "Failed to mark inode %lu dirty",
+ inode->i_ino);
+ if (!err)
+ err = err2;
+ }
+ return err;
+}
+
+/*
+ * Calculate the total number of credits to reserve for one writepages
+ * iteration. This is called from ext4_writepages(). We map an extent of
+ * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
+ * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
+ * bpp - 1 blocks in bpp different extents.
+ */
+static int ext4_da_writepages_trans_blocks(struct inode *inode)
+{
+ int bpp = ext4_journal_blocks_per_page(inode);
+
+ return ext4_meta_trans_blocks(inode,
+ MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
+}
+
+/*
+ * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages
+ * and underlying extent to map
+ *
+ * @mpd - where to look for pages
+ *
+ * Walk dirty pages in the mapping. If they are fully mapped, submit them for
+ * IO immediately. When we find a page which isn't mapped we start accumulating
+ * extent of buffers underlying these pages that needs mapping (formed by
+ * either delayed or unwritten buffers). We also lock the pages containing
+ * these buffers. The extent found is returned in @mpd structure (starting at
+ * mpd->lblk with length mpd->len blocks).
+ *
+ * Note that this function can attach bios to one io_end structure which are
+ * neither logically nor physically contiguous. Although it may seem as an
+ * unnecessary complication, it is actually inevitable in blocksize < pagesize
+ * case as we need to track IO to all buffers underlying a page in one io_end.
+ */
+static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
+{
+ struct address_space *mapping = mpd->inode->i_mapping;
+ struct pagevec pvec;
+ unsigned int nr_pages;
+ long left = mpd->wbc->nr_to_write;
+ pgoff_t index = mpd->first_page;
+ pgoff_t end = mpd->last_page;
+ int tag;
+ int i, err = 0;
+ int blkbits = mpd->inode->i_blkbits;
+ ext4_lblk_t lblk;
+ struct buffer_head *head;
+
+ if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
- *done_index = index;
+ pagevec_init(&pvec, 0);
+ mpd->map.m_len = 0;
+ mpd->next_page = index;
while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
- return 0;
+ goto out;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@@ -2337,31 +2302,32 @@
if (page->index > end)
goto out;
- *done_index = page->index + 1;
-
/*
- * If we can't merge this page, and we have
- * accumulated an contiguous region, write it
+ * Accumulated enough dirty pages? This doesn't apply
+ * to WB_SYNC_ALL mode. For integrity sync we have to
+ * keep going because someone may be concurrently
+ * dirtying pages, and we might have synced a lot of
+ * newly appeared dirty pages, but have not synced all
+ * of the old dirty pages.
*/
- if ((mpd->next_page != page->index) &&
- (mpd->next_page != mpd->first_page)) {
- mpage_da_map_and_submit(mpd);
- goto ret_extent_tail;
- }
+ if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0)
+ goto out;
+
+ /* If we can't merge this page, we are done. */
+ if (mpd->map.m_len > 0 && mpd->next_page != page->index)
+ goto out;
lock_page(page);
-
/*
- * If the page is no longer dirty, or its
- * mapping no longer corresponds to inode we
- * are writing (which means it has been
- * truncated or invalidated), or the page is
- * already under writeback and we are not
- * doing a data integrity writeback, skip the page
+ * If the page is no longer dirty, or its mapping no
+ * longer corresponds to inode we are writing (which
+ * means it has been truncated or invalidated), or the
+ * page is already under writeback and we are not doing
+ * a data integrity writeback, skip the page
*/
if (!PageDirty(page) ||
(PageWriteback(page) &&
- (wbc->sync_mode == WB_SYNC_NONE)) ||
+ (mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
@@ -2370,106 +2336,54 @@
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
- /*
- * If we have inline data and arrive here, it means that
- * we will soon create the block for the 1st page, so
- * we'd better clear the inline data here.
- */
- if (ext4_has_inline_data(inode)) {
- BUG_ON(ext4_test_inode_state(inode,
- EXT4_STATE_MAY_INLINE_DATA));
- ext4_destroy_inline_data(handle, inode);
- }
-
- if (mpd->next_page != page->index)
+ if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
- logical = (sector_t) page->index <<
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
/* Add all dirty buffers to mpd */
+ lblk = ((ext4_lblk_t)page->index) <<
+ (PAGE_CACHE_SHIFT - blkbits);
head = page_buffers(page);
- bh = head;
- do {
- BUG_ON(buffer_locked(bh));
- /*
- * We need to try to allocate unmapped blocks
- * in the same page. Otherwise we won't make
- * progress with the page in ext4_writepage
- */
- if (ext4_bh_delay_or_unwritten(NULL, bh)) {
- mpage_add_bh_to_extent(mpd, logical,
- bh->b_state);
- if (mpd->io_done)
- goto ret_extent_tail;
- } else if (buffer_dirty(bh) &&
- buffer_mapped(bh)) {
- /*
- * mapped dirty buffer. We need to
- * update the b_state because we look
- * at b_state in mpage_da_map_blocks.
- * We don't update b_size because if we
- * find an unmapped buffer_head later
- * we need to use the b_state flag of
- * that buffer_head.
- */
- if (mpd->b_size == 0)
- mpd->b_state =
- bh->b_state & BH_FLAGS;
- }
- logical++;
- } while ((bh = bh->b_this_page) != head);
-
- if (nr_to_write > 0) {
- nr_to_write--;
- if (nr_to_write == 0 &&
- wbc->sync_mode == WB_SYNC_NONE)
- /*
- * We stop writing back only if we are
- * not doing integrity sync. In case of
- * integrity sync we have to keep going
- * because someone may be concurrently
- * dirtying pages, and we might have
- * synced a lot of newly appeared dirty
- * pages, but have not synced all of the
- * old dirty pages.
- */
- goto out;
- }
+ err = mpage_process_page_bufs(mpd, head, head, lblk);
+ if (err <= 0)
+ goto out;
+ err = 0;
+ left--;
}
pagevec_release(&pvec);
cond_resched();
}
return 0;
-ret_extent_tail:
- ret = MPAGE_DA_EXTENT_TAIL;
out:
pagevec_release(&pvec);
- cond_resched();
+ return err;
+}
+
+static int __writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
+{
+ struct address_space *mapping = data;
+ int ret = ext4_writepage(page, wbc);
+ mapping_set_error(mapping, ret);
return ret;
}
-
-static int ext4_da_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
+static int ext4_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
{
- pgoff_t index;
+ pgoff_t writeback_index = 0;
+ long nr_to_write = wbc->nr_to_write;
int range_whole = 0;
+ int cycled = 1;
handle_t *handle = NULL;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
- int pages_written = 0;
- unsigned int max_pages;
- int range_cyclic, cycled = 1, io_done = 0;
- int needed_blocks, ret = 0;
- long desired_nr_to_write, nr_to_writebump = 0;
- loff_t range_start = wbc->range_start;
+ int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
- pgoff_t done_index = 0;
- pgoff_t end;
+ bool done;
struct blk_plug plug;
+ bool give_up_on_write = false;
- trace_ext4_da_writepages(inode, wbc);
+ trace_ext4_writepages(inode, wbc);
/*
* No pages to write? This is mainly a kludge to avoid starting
@@ -2477,7 +2391,16 @@
* because that could violate lock ordering on umount
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
- return 0;
+ goto out_writepages;
+
+ if (ext4_should_journal_data(inode)) {
+ struct blk_plug plug;
+
+ blk_start_plug(&plug);
+ ret = write_cache_pages(mapping, wbc, __writepage, mapping);
+ blk_finish_plug(&plug);
+ goto out_writepages;
+ }
/*
* If the filesystem has aborted, it is read-only, so return
@@ -2485,158 +2408,151 @@
* will obscure the real source of the problem. We test
* EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
* the latter could be true if the filesystem is mounted
- * read-only, and in that case, ext4_da_writepages should
+ * read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
- if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
- return -EROFS;
+ if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ret = -EROFS;
+ goto out_writepages;
+ }
+
+ if (ext4_should_dioread_nolock(inode)) {
+ /*
+ * We may need to convert up to one extent per block in
+ * the page and we may dirty the inode.
+ */
+ rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits);
+ }
+
+ /*
+ * If we have inline data and arrive here, it means that
+ * we will soon create the block for the 1st page, so
+ * we'd better clear the inline data here.
+ */
+ if (ext4_has_inline_data(inode)) {
+ /* Just inode will be modified... */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_writepages;
+ }
+ BUG_ON(ext4_test_inode_state(inode,
+ EXT4_STATE_MAY_INLINE_DATA));
+ ext4_destroy_inline_data(handle, inode);
+ ext4_journal_stop(handle);
+ }
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
- range_cyclic = wbc->range_cyclic;
if (wbc->range_cyclic) {
- index = mapping->writeback_index;
- if (index)
+ writeback_index = mapping->writeback_index;
+ if (writeback_index)
cycled = 0;
- wbc->range_start = index << PAGE_CACHE_SHIFT;
- wbc->range_end = LLONG_MAX;
- wbc->range_cyclic = 0;
- end = -1;
+ mpd.first_page = writeback_index;
+ mpd.last_page = -1;
} else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT;
+ mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT;
}
- /*
- * This works around two forms of stupidity. The first is in
- * the writeback code, which caps the maximum number of pages
- * written to be 1024 pages. This is wrong on multiple
- * levels; different architectues have a different page size,
- * which changes the maximum amount of data which gets
- * written. Secondly, 4 megabytes is way too small. XFS
- * forces this value to be 16 megabytes by multiplying
- * nr_to_write parameter by four, and then relies on its
- * allocator to allocate larger extents to make them
- * contiguous. Unfortunately this brings us to the second
- * stupidity, which is that ext4's mballoc code only allocates
- * at most 2048 blocks. So we force contiguous writes up to
- * the number of dirty blocks in the inode, or
- * sbi->max_writeback_mb_bump whichever is smaller.
- */
- max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
- if (!range_cyclic && range_whole) {
- if (wbc->nr_to_write == LONG_MAX)
- desired_nr_to_write = wbc->nr_to_write;
- else
- desired_nr_to_write = wbc->nr_to_write * 8;
- } else
- desired_nr_to_write = ext4_num_dirty_pages(inode, index,
- max_pages);
- if (desired_nr_to_write > max_pages)
- desired_nr_to_write = max_pages;
-
- if (wbc->nr_to_write < desired_nr_to_write) {
- nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
- wbc->nr_to_write = desired_nr_to_write;
- }
-
+ mpd.inode = inode;
+ mpd.wbc = wbc;
+ ext4_io_submit_init(&mpd.io_submit, wbc);
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
- tag_pages_for_writeback(mapping, index, end);
-
+ tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
+ done = false;
blk_start_plug(&plug);
- while (!ret && wbc->nr_to_write > 0) {
+ while (!done && mpd.first_page <= mpd.last_page) {
+ /* For each extent of pages we use new io_end */
+ mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
+ if (!mpd.io_submit.io_end) {
+ ret = -ENOMEM;
+ break;
+ }
/*
- * we insert one extent at a time. So we need
- * credit needed for single extent allocation.
- * journalled mode is currently not supported
- * by delalloc
+ * We have two constraints: We find one extent to map and we
+ * must always write out whole page (makes a difference when
+ * blocksize < pagesize) so that we don't block on IO when we
+ * try to write out the rest of the page. Journalled mode is
+ * not supported by delalloc.
*/
BUG_ON(ext4_should_journal_data(inode));
needed_blocks = ext4_da_writepages_trans_blocks(inode);
- /* start a new transaction*/
- handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
- needed_blocks);
+ /* start a new transaction */
+ handle = ext4_journal_start_with_reserve(inode,
+ EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
- blk_finish_plug(&plug);
- goto out_writepages;
+ /* Release allocated io_end */
+ ext4_put_io_end(mpd.io_submit.io_end);
+ break;
}
- /*
- * Now call write_cache_pages_da() to find the next
- * contiguous region of logical blocks that need
- * blocks to be allocated by ext4 and submit them.
- */
- ret = write_cache_pages_da(handle, mapping,
- wbc, &mpd, &done_index);
- /*
- * If we have a contiguous extent of pages and we
- * haven't done the I/O yet, map the blocks and submit
- * them for I/O.
- */
- if (!mpd.io_done && mpd.next_page != mpd.first_page) {
- mpage_da_map_and_submit(&mpd);
- ret = MPAGE_DA_EXTENT_TAIL;
+ trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
+ ret = mpage_prepare_extent_to_map(&mpd);
+ if (!ret) {
+ if (mpd.map.m_len)
+ ret = mpage_map_and_submit_extent(handle, &mpd,
+ &give_up_on_write);
+ else {
+ /*
+ * We scanned the whole range (or exhausted
+ * nr_to_write), submitted what was mapped and
+ * didn't find anything needing mapping. We are
+ * done.
+ */
+ done = true;
+ }
}
- trace_ext4_da_write_pages(inode, &mpd);
- wbc->nr_to_write -= mpd.pages_written;
-
ext4_journal_stop(handle);
+ /* Submit prepared bio */
+ ext4_io_submit(&mpd.io_submit);
+ /* Unlock pages we didn't use */
+ mpage_release_unused_pages(&mpd, give_up_on_write);
+ /* Drop our io_end reference we got from init */
+ ext4_put_io_end(mpd.io_submit.io_end);
- if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
- /* commit the transaction which would
+ if (ret == -ENOSPC && sbi->s_journal) {
+ /*
+ * Commit the transaction which would
* free blocks released in the transaction
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
ret = 0;
- } else if (ret == MPAGE_DA_EXTENT_TAIL) {
- /*
- * Got one extent now try with rest of the pages.
- * If mpd.retval is set -EIO, journal is aborted.
- * So we don't need to write any more.
- */
- pages_written += mpd.pages_written;
- ret = mpd.retval;
- io_done = 1;
- } else if (wbc->nr_to_write)
- /*
- * There is no more writeout needed
- * or we requested for a noblocking writeout
- * and we found the device congested
- */
+ continue;
+ }
+ /* Fatal error - ENOMEM, EIO... */
+ if (ret)
break;
}
blk_finish_plug(&plug);
- if (!io_done && !cycled) {
+ if (!ret && !cycled && wbc->nr_to_write > 0) {
cycled = 1;
- index = 0;
- wbc->range_start = index << PAGE_CACHE_SHIFT;
- wbc->range_end = mapping->writeback_index - 1;
+ mpd.last_page = writeback_index - 1;
+ mpd.first_page = 0;
goto retry;
}
/* Update index */
- wbc->range_cyclic = range_cyclic;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
- * set the writeback_index so that range_cyclic
+ * Set the writeback_index so that range_cyclic
* mode will write it back later
*/
- mapping->writeback_index = done_index;
+ mapping->writeback_index = mpd.first_page;
out_writepages:
- wbc->nr_to_write -= nr_to_writebump;
- wbc->range_start = range_start;
- trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
+ trace_ext4_writepages_result(inode, wbc, ret,
+ nr_to_write - wbc->nr_to_write);
return ret;
}
@@ -2756,7 +2672,12 @@
/* In case writeback began while the page was unlocked */
wait_for_stable_page(page);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ ret = ext4_block_write_begin(page, pos, len,
+ ext4_da_get_block_prep);
+#else
ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
+#endif
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
@@ -2832,10 +2753,7 @@
if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
if (ext4_has_inline_data(inode) ||
ext4_da_should_update_i_disksize(page, end)) {
- down_write(&EXT4_I(inode)->i_data_sem);
- if (new_i_size > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = new_i_size;
- up_write(&EXT4_I(inode)->i_data_sem);
+ ext4_update_i_disksize(inode, new_i_size);
/* We need to mark inode dirty even if
* new_i_size is less that inode->i_size
* bu greater than i_disksize.(hint delalloc)
@@ -2863,7 +2781,8 @@
return ret ? ret : copied;
}
-static void ext4_da_invalidatepage(struct page *page, unsigned long offset)
+static void ext4_da_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
/*
* Drop reserved blocks
@@ -2872,10 +2791,10 @@
if (!page_has_buffers(page))
goto out;
- ext4_da_page_release_reservation(page, offset);
+ ext4_da_page_release_reservation(page, offset, length);
out:
- ext4_invalidatepage(page, offset);
+ ext4_invalidatepage(page, offset, length);
return;
}
@@ -2887,8 +2806,7 @@
{
trace_ext4_alloc_da_blocks(inode);
- if (!EXT4_I(inode)->i_reserved_data_blocks &&
- !EXT4_I(inode)->i_reserved_meta_blocks)
+ if (!EXT4_I(inode)->i_reserved_data_blocks)
return 0;
/*
@@ -2898,7 +2816,7 @@
* laptop_mode, not even desirable). However, to do otherwise
* would require replicating code paths in:
*
- * ext4_da_writepages() ->
+ * ext4_writepages() ->
* write_cache_pages() ---> (via passed in callback function)
* __mpage_da_writepage() -->
* mpage_add_bh_to_extent()
@@ -3005,7 +2923,7 @@
ret = ext4_readpage_inline(inode, page);
if (ret == -EAGAIN)
- return mpage_readpage(page, ext4_get_block);
+ return ext4_mpage_readpages(page->mapping, NULL, page, 1);
return ret;
}
@@ -3020,40 +2938,43 @@
if (ext4_has_inline_data(inode))
return 0;
- return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
+ return ext4_mpage_readpages(mapping, pages, NULL, nr_pages);
}
-static void ext4_invalidatepage(struct page *page, unsigned long offset)
+static void ext4_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
- trace_ext4_invalidatepage(page, offset);
+ trace_ext4_invalidatepage(page, offset, length);
/* No journalling happens on data buffers when this function is used */
WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
- block_invalidatepage(page, offset);
+ block_invalidatepage(page, offset, length);
}
static int __ext4_journalled_invalidatepage(struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
- trace_ext4_journalled_invalidatepage(page, offset);
+ trace_ext4_journalled_invalidatepage(page, offset, length);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
- if (offset == 0)
+ if (offset == 0 && length == PAGE_CACHE_SIZE)
ClearPageChecked(page);
- return jbd2_journal_invalidatepage(journal, page, offset);
+ return jbd2_journal_invalidatepage(journal, page, offset, length);
}
/* Wrapper for aops... */
static void ext4_journalled_invalidatepage(struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
- WARN_ON(__ext4_journalled_invalidatepage(page, offset) < 0);
+ WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -3095,15 +3016,13 @@
}
static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
- ssize_t size, void *private, int ret,
- bool is_async)
+ ssize_t size, void *private)
{
- struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
- /* if not async direct IO or dio with 0 bytes write, just return */
- if (!io_end || !size)
- goto out;
+ /* if not async direct IO just return */
+ if (!io_end)
+ return;
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3111,25 +3030,9 @@
size);
iocb->private = NULL;
-
- /* if not aio dio with unwritten extents, just free io and return */
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- ext4_free_io_end(io_end);
-out:
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
- return;
- }
-
io_end->offset = offset;
io_end->size = size;
- if (is_async) {
- io_end->iocb = iocb;
- io_end->result = ret;
- }
-
- ext4_add_complete_io(io_end);
+ ext4_put_io_end(io_end);
}
/*
@@ -3137,9 +3040,9 @@
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
- * For holes, we fallocate those blocks, mark them as uninitialized
+ * For holes, we fallocate those blocks, mark them as unwritten
* If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as uninitialized.
+ * still keep the range to write as unwritten.
*
* The unwritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
@@ -3163,6 +3066,7 @@
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
+ ext4_io_end_t *io_end = NULL;
/* Use the old path for reads and writes beyond i_size. */
if (rw != WRITE || final_size > inode->i_size)
@@ -3170,11 +3074,18 @@
BUG_ON(iocb->private == NULL);
+ /*
+ * Make all waiters for direct IO properly wait also for extent
+ * conversion. This also disallows race between truncate() and
+ * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
+ */
+ if (rw == WRITE)
+ atomic_inc(&inode->i_dio_count);
+
/* If we do a overwrite dio, i_mutex locking can be released */
overwrite = *((int *)iocb->private);
if (overwrite) {
- atomic_inc(&inode->i_dio_count);
down_read(&EXT4_I(inode)->i_data_sem);
mutex_unlock(&inode->i_mutex);
}
@@ -3183,12 +3094,12 @@
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as
- * uninitialized to prevent parallel buffered read to expose
+ * unwritten to prevent parallel buffered read to expose
* the stale data before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block will
* just simply mark the buffer mapped but still keep the
- * extents uninitialized.
+ * extents unwritten.
*
* For non AIO case, we will convert those unwritten extents
* to written after return back from blockdev_direct_IO.
@@ -3201,13 +3112,15 @@
iocb->private = NULL;
ext4_inode_aio_set(inode, NULL);
if (!is_sync_kiocb(iocb)) {
- ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
+ io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end) {
ret = -ENOMEM;
goto retake_lock;
}
- io_end->flag |= EXT4_IO_END_DIRECT;
- iocb->private = io_end;
+ /*
+ * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
+ */
+ iocb->private = ext4_get_io_end(io_end);
/*
* we save the io structure for current async direct
* IO, so that later ext4_map_blocks() could flag the
@@ -3223,6 +3136,9 @@
get_block_func = ext4_get_block_write;
dio_flags = DIO_LOCKING;
}
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
+#endif
ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
@@ -3231,33 +3147,35 @@
NULL,
dio_flags);
- if (iocb->private)
- ext4_inode_aio_set(inode, NULL);
/*
- * The io_end structure takes a reference to the inode, that
- * structure needs to be destroyed and the reference to the
- * inode need to be dropped, when IO is complete, even with 0
- * byte write, or failed.
- *
- * In the successful AIO DIO case, the io_end structure will
- * be destroyed and the reference to the inode will be dropped
- * after the end_io call back function is called.
- *
- * In the case there is 0 byte write, or error case, since VFS
- * direct IO won't invoke the end_io call back function, we
- * need to free the end_io structure here.
+ * Put our reference to io_end. This can free the io_end structure e.g.
+ * in sync IO case or in case of error. It can even perform extent
+ * conversion if all bios we submitted finished before we got here.
+ * Note that in that case iocb->private can be already set to NULL
+ * here.
*/
- if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
- ext4_free_io_end(iocb->private);
- iocb->private = NULL;
- } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+ if (io_end) {
+ ext4_inode_aio_set(inode, NULL);
+ ext4_put_io_end(io_end);
+ /*
+ * When no IO was submitted ext4_end_io_dio() was not
+ * called so we have to put iocb's reference.
+ */
+ if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
+ WARN_ON(iocb->private != io_end);
+ WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+ ext4_put_io_end(io_end);
+ iocb->private = NULL;
+ }
+ }
+ if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
* for non AIO case, since the IO is already
* completed, we could do the conversion right here
*/
- err = ext4_convert_unwritten_extents(inode,
+ err = ext4_convert_unwritten_extents(NULL, inode,
offset, ret);
if (err < 0)
ret = err;
@@ -3265,9 +3183,10 @@
}
retake_lock:
+ if (rw == WRITE)
+ inode_dio_done(inode);
/* take i_mutex locking again if we do a ovewrite dio */
if (overwrite) {
- inode_dio_done(inode);
up_read(&EXT4_I(inode)->i_data_sem);
mutex_lock(&inode->i_mutex);
}
@@ -3281,8 +3200,14 @@
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ size_t count = iov_length(iov, nr_segs);
ssize_t ret;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ return 0;
+#endif
+
/*
* If we are doing data journalling we don't support O_DIRECT
*/
@@ -3293,13 +3218,12 @@
if (ext4_has_inline_data(inode))
return 0;
- trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext4_direct_IO_enter(inode, offset, count, rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
else
ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
- trace_ext4_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ trace_ext4_direct_IO_exit(inode, offset, count, rw, ret);
return ret;
}
@@ -3326,6 +3250,7 @@
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
+ .writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_write_end,
.bmap = ext4_bmap,
@@ -3341,6 +3266,7 @@
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
+ .writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
@@ -3356,7 +3282,7 @@
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .writepages = ext4_da_writepages,
+ .writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.bmap = ext4_bmap,
@@ -3389,20 +3315,22 @@
inode->i_mapping->a_ops = &ext4_aops;
}
-
/*
- * ext4_discard_partial_page_buffers()
- * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
- * This function finds and locks the page containing the offset
- * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
- * Calling functions that already have the page locked should call
- * ext4_discard_partial_page_buffers_no_lock directly.
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'. The range to be zero'd must
+ * be contained with in one block. If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
*/
-int ext4_discard_partial_page_buffers(handle_t *handle,
- struct address_space *mapping, loff_t from,
- loff_t length, int flags)
+static int ext4_block_zero_page_range(handle_t *handle,
+ struct address_space *mapping, loff_t from, loff_t length)
{
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned blocksize, max, pos;
+ ext4_lblk_t iblock;
struct inode *inode = mapping->host;
+ struct buffer_head *bh;
struct page *page;
int err = 0;
@@ -3411,67 +3339,12 @@
if (!page)
return -ENOMEM;
- err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
- from, length, flags);
-
- unlock_page(page);
- page_cache_release(page);
- return err;
-}
-
-/*
- * ext4_discard_partial_page_buffers_no_lock()
- * Zeros a page range of length 'length' starting from offset 'from'.
- * Buffer heads that correspond to the block aligned regions of the
- * zeroed range will be unmapped. Unblock aligned regions
- * will have the corresponding buffer head mapped if needed so that
- * that region of the page can be updated with the partial zero out.
- *
- * This function assumes that the page has already been locked. The
- * The range to be discarded must be contained with in the given page.
- * If the specified range exceeds the end of the page it will be shortened
- * to the end of the page that corresponds to 'from'. This function is
- * appropriate for updating a page and it buffer heads to be unmapped and
- * zeroed for blocks that have been either released, or are going to be
- * released.
- *
- * handle: The journal handle
- * inode: The files inode
- * page: A locked page that contains the offset "from"
- * from: The starting byte offset (from the beginning of the file)
- * to begin discarding
- * len: The length of bytes to discard
- * flags: Optional flags that may be used:
- *
- * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
- * Only zero the regions of the page whose buffer heads
- * have already been unmapped. This flag is appropriate
- * for updating the contents of a page whose blocks may
- * have already been released, and we only want to zero
- * out the regions that correspond to those released blocks.
- *
- * Returns zero on success or negative on failure.
- */
-static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
- struct inode *inode, struct page *page, loff_t from,
- loff_t length, int flags)
-{
- ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
- unsigned int offset = from & (PAGE_CACHE_SIZE-1);
- unsigned int blocksize, max, pos;
- ext4_lblk_t iblock;
- struct buffer_head *bh;
- int err = 0;
-
blocksize = inode->i_sb->s_blocksize;
- max = PAGE_CACHE_SIZE - offset;
-
- if (index != page->index)
- return -EINVAL;
+ max = blocksize - (offset & (blocksize - 1));
/*
* correct length if it does not fall between
- * 'from' and the end of the page
+ * 'from' and the end of the block
*/
if (length > max || length < 0)
length = max;
@@ -3489,106 +3362,118 @@
iblock++;
pos += blocksize;
}
-
- pos = offset;
- while (pos < offset + length) {
- unsigned int end_of_block, range_to_discard;
-
- err = 0;
-
- /* The length of space left to zero and unmap */
- range_to_discard = offset + length - pos;
-
- /* The length of space until the end of the block */
- end_of_block = blocksize - (pos & (blocksize-1));
-
- /*
- * Do not unmap or zero past end of block
- * for this buffer head
- */
- if (range_to_discard > end_of_block)
- range_to_discard = end_of_block;
-
-
- /*
- * Skip this buffer head if we are only zeroing unampped
- * regions of the page
- */
- if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
- buffer_mapped(bh))
- goto next;
-
- /* If the range is block aligned, unmap */
- if (range_to_discard == blocksize) {
- clear_buffer_dirty(bh);
- bh->b_bdev = NULL;
- clear_buffer_mapped(bh);
- clear_buffer_req(bh);
- clear_buffer_new(bh);
- clear_buffer_delay(bh);
- clear_buffer_unwritten(bh);
- clear_buffer_uptodate(bh);
- zero_user(page, pos, range_to_discard);
- BUFFER_TRACE(bh, "Buffer discarded");
- goto next;
- }
-
- /*
- * If this block is not completely contained in the range
- * to be discarded, then it is not going to be released. Because
- * we need to keep this block, we need to make sure this part
- * of the page is uptodate before we modify it by writeing
- * partial zeros on it.
- */
+ if (buffer_freed(bh)) {
+ BUFFER_TRACE(bh, "freed: skip");
+ goto unlock;
+ }
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh)) {
- /*
- * Buffer head must be mapped before we can read
- * from the block
- */
- BUFFER_TRACE(bh, "unmapped");
- ext4_get_block(inode, iblock, bh, 0);
- /* unmapped? It's a hole - nothing to do */
- if (!buffer_mapped(bh)) {
- BUFFER_TRACE(bh, "still unmapped");
- goto next;
- }
+ BUFFER_TRACE(bh, "still unmapped");
+ goto unlock;
}
-
- /* Ok, it's mapped. Make sure it's up-to-date */
- if (PageUptodate(page))
- set_buffer_uptodate(bh);
-
- if (!buffer_uptodate(bh)) {
- err = -EIO;
- ll_rw_block(READ, 1, &bh);
- wait_on_buffer(bh);
- /* Uhhuh. Read error. Complain and punt.*/
- if (!buffer_uptodate(bh))
- goto next;
- }
-
- if (ext4_should_journal_data(inode)) {
- BUFFER_TRACE(bh, "get write access");
- err = ext4_journal_get_write_access(handle, bh);
- if (err)
- goto next;
- }
-
- zero_user(page, pos, range_to_discard);
-
- err = 0;
- if (ext4_should_journal_data(inode)) {
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else
- mark_buffer_dirty(bh);
-
- BUFFER_TRACE(bh, "Partial buffer zeroed");
-next:
- bh = bh->b_this_page;
- iblock++;
- pos += range_to_discard;
}
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt. */
+ if (!buffer_uptodate(bh))
+ goto unlock;
+ if (S_ISREG(inode->i_mode) &&
+ ext4_encrypted_inode(inode)) {
+ /* We expect the key to be set. */
+ BUG_ON(!ext4_has_encryption_key(inode));
+ BUG_ON(blocksize != PAGE_CACHE_SIZE);
+ WARN_ON_ONCE(ext4_decrypt_one(inode, page));
+ }
+ }
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto unlock;
+ }
+ zero_user(page, offset, length);
+ BUFFER_TRACE(bh, "zeroed end of block");
+
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ } else {
+ err = 0;
+ mark_buffer_dirty(bh);
+ if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE))
+ err = ext4_jbd2_file_inode(handle, inode);
+ }
+
+unlock:
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+}
+
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+static int ext4_block_truncate_page(handle_t *handle,
+ struct address_space *mapping, loff_t from)
+{
+ unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned length;
+ unsigned blocksize;
+ struct inode *inode = mapping->host;
+
+ blocksize = inode->i_sb->s_blocksize;
+ length = blocksize - (offset & (blocksize - 1));
+
+ return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
+ loff_t lstart, loff_t length)
+{
+ struct super_block *sb = inode->i_sb;
+ struct address_space *mapping = inode->i_mapping;
+ unsigned partial_start, partial_end;
+ ext4_fsblk_t start, end;
+ loff_t byte_end = (lstart + length - 1);
+ int err = 0;
+
+ partial_start = lstart & (sb->s_blocksize - 1);
+ partial_end = byte_end & (sb->s_blocksize - 1);
+
+ start = lstart >> sb->s_blocksize_bits;
+ end = byte_end >> sb->s_blocksize_bits;
+
+ /* Handle partial zero within the single block */
+ if (start == end &&
+ (partial_start || (partial_end != sb->s_blocksize - 1))) {
+ err = ext4_block_zero_page_range(handle, mapping,
+ lstart, length);
+ return err;
+ }
+ /* Handle partial zero out on the start of the range */
+ if (partial_start) {
+ err = ext4_block_zero_page_range(handle, mapping,
+ lstart, sb->s_blocksize);
+ if (err)
+ return err;
+ }
+ /* Handle partial zero out on the end of the range */
+ if (partial_end != sb->s_blocksize - 1)
+ err = ext4_block_zero_page_range(handle, mapping,
+ byte_end - partial_end,
+ partial_end + 1);
return err;
}
@@ -3614,14 +3499,12 @@
* Returns: 0 on success or negative on failure
*/
-int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
+int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
{
- struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
- loff_t first_page, last_page, page_len;
- loff_t first_page_offset, last_page_offset;
+ loff_t first_block_offset, last_block_offset;
handle_t *handle;
unsigned int credits;
int ret = 0;
@@ -3629,12 +3512,7 @@
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
- if (EXT4_SB(sb)->s_cluster_ratio > 1) {
- /* TODO: Add support for bigalloc file systems */
- return -EOPNOTSUPP;
- }
-
- trace_ext4_punch_hole(inode, offset, length);
+ trace_ext4_punch_hole(inode, offset, length, 0);
/*
* Write out all dirty pages to avoid race conditions
@@ -3648,15 +3526,6 @@
}
mutex_lock(&inode->i_mutex);
- /* It's not possible punch hole on append only file */
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
- ret = -EPERM;
- goto out_mutex;
- }
- if (IS_SWAPFILE(inode)) {
- ret = -ETXTBSY;
- goto out_mutex;
- }
/* No need to punch hole beyond i_size */
if (offset >= inode->i_size)
@@ -3672,23 +3541,28 @@
offset;
}
- first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- last_page = (offset + length) >> PAGE_CACHE_SHIFT;
+ if (offset & (sb->s_blocksize - 1) ||
+ (offset + length) & (sb->s_blocksize - 1)) {
+ /*
+ * Attach jinode to inode for jbd2 if we do any zeroing of
+ * partial block
+ */
+ ret = ext4_inode_attach_jinode(inode);
+ if (ret < 0)
+ goto out_mutex;
- first_page_offset = first_page << PAGE_CACHE_SHIFT;
- last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
- /* Now release the pages */
- if (last_page_offset > first_page_offset) {
- truncate_pagecache_range(inode, first_page_offset,
- last_page_offset - 1);
}
+ first_block_offset = round_up(offset, sb->s_blocksize);
+ last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
+
+ /* Now release the pages and zero block aligned part of pages*/
+ if (last_block_offset > first_block_offset)
+ truncate_pagecache_range(inode, first_block_offset,
+ last_block_offset);
+
/* Wait all existing dio workers, newcomers will block on i_mutex */
ext4_inode_block_unlocked_dio(inode);
- ret = ext4_flush_unwritten_io(inode);
- if (ret)
- goto out_dio;
inode_dio_wait(inode);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
@@ -3702,66 +3576,10 @@
goto out_dio;
}
- /*
- * Now we need to zero out the non-page-aligned data in the
- * pages at the start and tail of the hole, and unmap the
- * buffer heads for the block aligned regions of the page that
- * were completely zeroed.
- */
- if (first_page > last_page) {
- /*
- * If the file space being truncated is contained
- * within a page just zero out and unmap the middle of
- * that page
- */
- ret = ext4_discard_partial_page_buffers(handle,
- mapping, offset, length, 0);
-
- if (ret)
- goto out_stop;
- } else {
- /*
- * zero out and unmap the partial page that contains
- * the start of the hole
- */
- page_len = first_page_offset - offset;
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers(handle, mapping,
- offset, page_len, 0);
- if (ret)
- goto out_stop;
- }
-
- /*
- * zero out and unmap the partial page that contains
- * the end of the hole
- */
- page_len = offset + length - last_page_offset;
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers(handle, mapping,
- last_page_offset, page_len, 0);
- if (ret)
- goto out_stop;
- }
- }
-
- /*
- * If i_size is contained in the last page, we need to
- * unmap and zero the partial page after i_size
- */
- if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
- inode->i_size % PAGE_CACHE_SIZE != 0) {
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
-
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0);
-
- if (ret)
- goto out_stop;
- }
- }
+ ret = ext4_zero_partial_blocks(handle, inode, offset,
+ length);
+ if (ret)
+ goto out_stop;
first_block = (offset + sb->s_blocksize - 1) >>
EXT4_BLOCK_SIZE_BITS(sb);
@@ -3785,13 +3603,18 @@
ret = ext4_ext_remove_space(inode, first_block,
stop_block - 1);
else
- ret = ext4_free_hole_blocks(handle, inode, first_block,
+ ret = ext4_ind_remove_space(handle, inode, first_block,
stop_block);
- ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
+
+ /* Now release the pages again to reduce race window */
+ if (last_block_offset > first_block_offset)
+ truncate_pagecache_range(inode, first_block_offset,
+ last_block_offset);
+
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
out_stop:
@@ -3803,6 +3626,31 @@
return ret;
}
+int ext4_inode_attach_jinode(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct jbd2_inode *jinode;
+
+ if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
+ return 0;
+
+ jinode = jbd2_alloc_inode(GFP_KERNEL);
+ spin_lock(&inode->i_lock);
+ if (!ei->jinode) {
+ if (!jinode) {
+ spin_unlock(&inode->i_lock);
+ return -ENOMEM;
+ }
+ ei->jinode = jinode;
+ jbd2_journal_init_jbd_inode(ei->jinode, inode);
+ jinode = NULL;
+ }
+ spin_unlock(&inode->i_lock);
+ if (unlikely(jinode != NULL))
+ jbd2_free_inode(jinode);
+ return 0;
+}
+
/*
* ext4_truncate()
*
@@ -3837,11 +3685,10 @@
unsigned int credits;
handle_t *handle;
struct address_space *mapping = inode->i_mapping;
- loff_t page_len;
/*
* There is a possibility that we're either freeing the inode
- * or it completely new indode. In those cases we might not
+ * or it's a completely new inode. In those cases we might not
* have i_mutex locked because it's not necessary.
*/
if (!(inode->i_state & (I_NEW|I_FREEING)))
@@ -3864,11 +3711,11 @@
return;
}
- /*
- * finish any pending end_io work so we won't run the risk of
- * converting any truncated blocks to initialized later
- */
- ext4_flush_unwritten_io(inode);
+ /* If we zero-out tail of the page, we have to create jinode for jbd2 */
+ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
+ if (ext4_inode_attach_jinode(inode) < 0)
+ return;
+ }
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
@@ -3881,14 +3728,8 @@
return;
}
- if (inode->i_size % PAGE_CACHE_SIZE != 0) {
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
-
- if (ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0))
- goto out_stop;
- }
+ if (inode->i_size & (inode->i_sb->s_blocksize - 1))
+ ext4_block_truncate_page(handle, mapping, inode->i_size);
/*
* We add the inode to the orphan list, so that if this
@@ -4099,8 +3940,8 @@
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
- set_mask_bits(&inode->i_flags,
- S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
+ inode_set_flags(inode, new_fl,
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4204,8 +4045,7 @@
ei->i_extra_isize = 0;
/* Precompute checksum seed for inode metadata */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ if (ext4_has_metadata_csum(sb)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le32 inum = cpu_to_le32(inode->i_ino);
@@ -4319,11 +4159,13 @@
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
- inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
- if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
- if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
- inode->i_version |=
- (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+ if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+ inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+ if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+ if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+ inode->i_version |=
+ (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+ }
}
ret = 0;
@@ -4358,7 +4200,8 @@
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext4_inode_is_fast_symlink(inode)) {
+ if (ext4_inode_is_fast_symlink(inode) &&
+ !ext4_encrypted_inode(inode)) {
inode->i_op = &ext4_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
@@ -4453,12 +4296,15 @@
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
+ struct super_block *sb = inode->i_sb;
int err = 0, rc, block;
- int need_datasync = 0;
+ int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
- /* For fields not not tracking in the in-memory inode,
+ spin_lock(&ei->i_raw_lock);
+
+ /* For fields not tracked in the in-memory inode,
* initialise them to zero for new inodes. */
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
@@ -4496,12 +4342,14 @@
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
- if (ext4_inode_blocks_set(handle, raw_inode, ei))
+ err = ext4_inode_blocks_set(handle, raw_inode, ei);
+ if (err) {
+ spin_unlock(&ei->i_raw_lock);
goto out_brelse;
+ }
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
- if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
- cpu_to_le32(EXT4_OS_HURD))
+ if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
@@ -4510,24 +4358,11 @@
need_datasync = 1;
}
if (ei->i_disksize > 0x7fffffffULL) {
- struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
- cpu_to_le32(EXT4_GOOD_OLD_REV)) {
- /* If this is the first large file
- * created, add a flag to the superblock.
- */
- err = ext4_journal_get_write_access(handle,
- EXT4_SB(sb)->s_sbh);
- if (err)
- goto out_brelse;
- ext4_update_dynamic_rev(sb);
- EXT4_SET_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
- ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
- }
+ cpu_to_le32(EXT4_GOOD_OLD_REV))
+ set_large_file = 1;
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -4546,22 +4381,37 @@
raw_inode->i_block[block] = ei->i_data[block];
}
- raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
- if (ei->i_extra_isize) {
- if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
- raw_inode->i_version_hi =
- cpu_to_le32(inode->i_version >> 32);
- raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+ if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+ raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+ if (ei->i_extra_isize) {
+ if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+ raw_inode->i_version_hi =
+ cpu_to_le32(inode->i_version >> 32);
+ raw_inode->i_extra_isize =
+ cpu_to_le16(ei->i_extra_isize);
+ }
}
ext4_inode_csum_set(inode, raw_inode, ei);
+ spin_unlock(&ei->i_raw_lock);
+
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
-
+ if (set_large_file) {
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_brelse;
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_super(handle, sb);
+ }
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
@@ -4574,21 +4424,20 @@
*
* We are called from a few places:
*
- * - Within generic_file_write() for O_SYNC files.
+ * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
* transaction to commit.
*
- * - Within sys_sync(), kupdate and such.
- * We wait on commit, if tol to.
+ * - Within flush work (sys_sync(), kupdate and such).
+ * We wait on commit, if told to.
*
- * - Within prune_icache() (PF_MEMALLOC == true)
- * Here we simply return. We can't afford to block kswapd on the
- * journal commit.
+ * - Within iput_final() -> write_inode_now()
+ * We wait on commit, if told to.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
- * ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for
- * knfsd.
+ * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL
+ * writeback.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
@@ -4600,15 +4449,15 @@
* stuff();
* inode->i_size = expr;
*
- * is in error because a kswapd-driven write_inode() could occur while
- * `stuff()' is running, and the new i_size will be lost. Plus the inode
- * will no longer be on the superblock's dirty inode list.
+ * is in error because write_inode() could occur while `stuff()' is running,
+ * and the new i_size will be lost. Plus the inode will no longer be on the
+ * superblock's dirty inode list.
*/
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
- if (current->flags & PF_MEMALLOC)
+ if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
return 0;
if (EXT4_SB(inode->i_sb)->s_journal) {
@@ -4618,7 +4467,12 @@
return -EIO;
}
- if (wbc->sync_mode != WB_SYNC_ALL)
+ /*
+ * No need to force transaction in WB_SYNC_NONE mode. Also
+ * ext4_sync_fs() will force the commit after everything is
+ * written.
+ */
+ if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
return 0;
err = ext4_force_commit(inode->i_sb);
@@ -4628,7 +4482,11 @@
err = __ext4_get_inode_loc(inode, &iloc, 0);
if (err)
return err;
- if (wbc->sync_mode == WB_SYNC_ALL)
+ /*
+ * sync(2) will flush the whole buffer cache. No need to do
+ * it here separately for each inode.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
@@ -4666,7 +4524,8 @@
inode->i_size >> PAGE_CACHE_SHIFT);
if (!page)
return;
- ret = __ext4_journalled_invalidatepage(page, offset);
+ ret = __ext4_journalled_invalidatepage(page, offset,
+ PAGE_CACHE_SIZE - offset);
unlock_page(page);
page_cache_release(page);
if (ret != -EBUSY)
@@ -4748,7 +4607,7 @@
if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
handle_t *handle;
- loff_t oldsize = inode->i_size;
+ loff_t oldsize = i_size_read(inode);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -4777,18 +4636,31 @@
error = ext4_orphan_add(handle, inode);
orphan = 1;
}
+ down_write(&EXT4_I(inode)->i_data_sem);
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
error = rc;
+ /*
+ * We have to update i_size under i_data_sem together
+ * with i_disksize to avoid races with writeback code
+ * running ext4_wb_update_i_disksize().
+ */
+ if (!error)
+ i_size_write(inode, attr->ia_size);
+ up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
if (error) {
ext4_orphan_del(NULL, inode);
goto err_out;
}
+ } else {
+ loff_t oldsize = inode->i_size;
+
+ i_size_write(inode, attr->ia_size);
+ pagecache_isize_extended(inode, oldsize, inode->i_size);
}
- i_size_write(inode, attr->ia_size);
/*
* Blocks are going to be removed from the inode. Wait
* for dio in flight. Temporarily disable
@@ -4806,7 +4678,7 @@
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
- truncate_pagecache(inode, oldsize, inode->i_size);
+ truncate_pagecache(inode, oldsize, inode->i_size);
}
/*
* We want to call ext4_truncate() even if attr->ia_size ==
@@ -4827,8 +4699,11 @@
if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+#error POSIX_ACL not supported in 3.18 backport
if (!rc && (ia_valid & ATTR_MODE))
- rc = ext4_acl_chmod(inode);
+ rc = posix_acl_chmod(inode, inode->i_mode);
+#endif
err_out:
ext4_std_error(inode->i_sb, error);
@@ -4847,6 +4722,15 @@
generic_fillattr(inode, stat);
/*
+ * If there is inline data in the inode, the inode will normally not
+ * have data blocks allocated (it may have an external xattr block).
+ * Report at least one sector for such files, so tools like tar, rsync,
+ * others doen't incorrectly think the file is completely sparse.
+ */
+ if (unlikely(ext4_has_inline_data(inode)))
+ stat->blocks += (stat->size + 511) >> 9;
+
+ /*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
* allocation is done, we will have i_blocks inconsistent with
@@ -4857,17 +4741,17 @@
* blocks for this file.
*/
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
- EXT4_I(inode)->i_reserved_data_blocks);
-
- stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
+ EXT4_I(inode)->i_reserved_data_blocks);
+ stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9);
return 0;
}
-static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+static int ext4_index_trans_blocks(struct inode *inode, int lblocks,
+ int pextents)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return ext4_ind_trans_blocks(inode, nrblocks, chunk);
- return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
+ return ext4_ind_trans_blocks(inode, lblocks);
+ return ext4_ext_index_trans_blocks(inode, pextents);
}
/*
@@ -4881,7 +4765,8 @@
*
* Also account for superblock, inode, quota and xattr blocks
*/
-static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+ int pextents)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
@@ -4889,14 +4774,10 @@
int ret = 0;
/*
- * How many index blocks need to touch to modify nrblocks?
- * The "Chunk" flag indicating whether the nrblocks is
- * physically contiguous on disk
- *
- * For Direct IO and fallocate, they calls get_block to allocate
- * one single extent at a time, so they could set the "Chunk" flag
+ * How many index blocks need to touch to map @lblocks logical blocks
+ * to @pextents physical extents?
*/
- idxblocks = ext4_index_trans_blocks(inode, nrblocks, chunk);
+ idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents);
ret = idxblocks;
@@ -4904,12 +4785,7 @@
* Now let's see how many group bitmaps and group descriptors need
* to account
*/
- groups = idxblocks;
- if (chunk)
- groups += 1;
- else
- groups += nrblocks;
-
+ groups = idxblocks + pextents;
gdpblocks = groups;
if (groups > ngroups)
groups = ngroups;
@@ -4940,7 +4816,7 @@
int bpp = ext4_journal_blocks_per_page(inode);
int ret;
- ret = ext4_meta_trans_blocks(inode, bpp, 0);
+ ret = ext4_meta_trans_blocks(inode, bpp, bpp);
/* Account for data blocks for journalled mode */
if (ext4_should_journal_data(inode))
@@ -5207,7 +5083,12 @@
if (val)
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else {
- jbd2_journal_flush(journal);
+ err = jbd2_journal_flush(journal);
+ if (err < 0) {
+ jbd2_journal_unlock_updates(journal);
+ ext4_inode_resume_unlocked_dio(inode);
+ return err;
+ }
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
}
ext4_set_aops(inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d4fd81c..21d077c 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -14,10 +14,10 @@
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/file.h>
+#include <linux/random.h>
#include <asm/uaccess.h>
#include "ext4_jbd2.h"
#include "ext4.h"
-#include "ext4_extents.h"
#define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
@@ -102,28 +102,18 @@
handle_t *handle;
int err;
struct inode *inode_bl;
- struct ext4_inode_info *ei;
struct ext4_inode_info *ei_bl;
- struct ext4_sb_info *sbi;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
- err = -EINVAL;
- goto swap_boot_out;
- }
+ if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
+ return -EINVAL;
- if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
- err = -EPERM;
- goto swap_boot_out;
- }
-
- sbi = EXT4_SB(sb);
- ei = EXT4_I(inode);
+ if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
+ return -EPERM;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
- if (IS_ERR(inode_bl)) {
- err = PTR_ERR(inode_bl);
- goto swap_boot_out;
- }
+ if (IS_ERR(inode_bl))
+ return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
filemap_flush(inode->i_mapping);
@@ -131,7 +121,7 @@
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
- ext4_inode_double_lock(inode, inode_bl);
+ lock_two_nondirectories(inode, inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
@@ -198,23 +188,27 @@
ext4_mark_inode_dirty(handle, inode);
}
}
-
ext4_journal_stop(handle);
-
ext4_double_up_write_data_sem(inode, inode_bl);
journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
-
- ext4_inode_double_unlock(inode, inode_bl);
-
+ unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
-
-swap_boot_out:
return err;
}
+static int uuid_is_zero(__u8 u[16])
+{
+ int i;
+
+ for (i = 0; i < 16; i++)
+ if (u[i])
+ return 0;
+ return 1;
+}
+
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -348,8 +342,7 @@
if (!inode_owner_or_capable(inode))
return -EPERM;
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
@@ -605,11 +598,13 @@
return err;
}
+ case FIDTRIM:
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
+ int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -617,13 +612,15 @@
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
+ if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q))
+ return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
- ret = ext4_trim_fs(sb, &range);
+ ret = ext4_trim_fs(sb, &range, flags);
if (ret < 0)
return ret;
@@ -633,7 +630,80 @@
return 0;
}
+ case EXT4_IOC_PRECACHE_EXTENTS:
+ return ext4_ext_precache(inode);
+ case EXT4_IOC_SET_ENCRYPTION_POLICY: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ struct ext4_encryption_policy policy;
+ int err = 0;
+ if (copy_from_user(&policy,
+ (struct ext4_encryption_policy __user *)arg,
+ sizeof(policy))) {
+ err = -EFAULT;
+ goto encryption_policy_out;
+ }
+
+ err = ext4_process_policy(&policy, inode);
+encryption_policy_out:
+ return err;
+#else
+ return -EOPNOTSUPP;
+#endif
+ }
+ case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+ int err, err2;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ handle_t *handle;
+
+ if (!ext4_sb_has_crypto(sb))
+ return -EOPNOTSUPP;
+ if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto pwsalt_err_exit;
+ }
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+ if (err)
+ goto pwsalt_err_journal;
+ generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+ err = ext4_handle_dirty_metadata(handle, NULL,
+ sbi->s_sbh);
+ pwsalt_err_journal:
+ err2 = ext4_journal_stop(handle);
+ if (err2 && !err)
+ err = err2;
+ pwsalt_err_exit:
+ mnt_drop_write_file(filp);
+ if (err)
+ return err;
+ }
+ if (copy_to_user((void *) arg, sbi->s_es->s_encrypt_pw_salt,
+ 16))
+ return -EFAULT;
+ return 0;
+ }
+ case EXT4_IOC_GET_ENCRYPTION_POLICY: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ struct ext4_encryption_policy policy;
+ int err = 0;
+
+ if (!ext4_encrypted_inode(inode))
+ return -ENOENT;
+ err = ext4_get_policy(inode, &policy);
+ if (err)
+ return err;
+ if (copy_to_user((void *)arg, &policy, sizeof(policy)))
+ return -EFAULT;
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+ }
default:
return -ENOTTY;
}
@@ -697,6 +767,10 @@
case EXT4_IOC_MOVE_EXT:
case FITRIM:
case EXT4_IOC_RESIZE_FS:
+ case EXT4_IOC_PRECACHE_EXTENTS:
+ case EXT4_IOC_SET_ENCRYPTION_POLICY:
+ case EXT4_IOC_GET_ENCRYPTION_PWSALT:
+ case EXT4_IOC_GET_ENCRYPTION_POLICY:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 08b4495..8921932 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -722,6 +722,7 @@
void *buddy, void *bitmap, ext4_group_t group)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_grpblk_t i = 0;
ext4_grpblk_t first;
@@ -751,13 +752,18 @@
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u clusters in bitmap, %u in gd",
+ "block bitmap and bg descriptor "
+ "inconsistent: %u vs %u free clusters",
free, grp->bb_free);
/*
- * If we intent to continue, we consider group descritor
+ * If we intend to continue, we consider group descriptor
* corrupt and update bb_free using bitmap value
*/
grp->bb_free = free;
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
}
mb_set_largest_free_order(sb, grp);
@@ -987,7 +993,7 @@
poff = block % blocks_per_page;
page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
if (!page)
- return -EIO;
+ return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
e4b->bd_bitmap_page = page;
e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
@@ -1001,7 +1007,7 @@
pnum = block / blocks_per_page;
page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
if (!page)
- return -EIO;
+ return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
e4b->bd_buddy_page = page;
return 0;
@@ -1042,6 +1048,8 @@
* allocating. If we are looking at the buddy cache we would
* have taken a reference using ext4_mb_load_buddy and that
* would have pinned buddy page to page cache.
+ * The call to ext4_mb_get_buddy_page_lock will mark the
+ * page accessed.
*/
ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
@@ -1060,7 +1068,6 @@
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
if (e4b.bd_buddy_page == NULL) {
/*
@@ -1080,7 +1087,6 @@
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
err:
ext4_mb_put_buddy_page_lock(&e4b);
return ret;
@@ -1139,7 +1145,7 @@
/* we could use find_or_create_page(), but it locks page
* what we'd like to avoid in fast path ... */
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
/*
@@ -1166,19 +1172,24 @@
unlock_page(page);
}
}
- if (page == NULL || !PageUptodate(page)) {
+ if (page == NULL) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ if (!PageUptodate(page)) {
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_bitmap_page = page;
e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
block++;
pnum = block / blocks_per_page;
poff = block % blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
page_cache_release(page);
@@ -1195,13 +1206,18 @@
unlock_page(page);
}
}
- if (page == NULL || !PageUptodate(page)) {
+ if (page == NULL) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ if (!PageUptodate(page)) {
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_buddy_page = page;
e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
@@ -1402,6 +1418,10 @@
return;
BUG_ON(last >= (sb->s_blocksize << 3));
assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
+ /* Don't bother if the block group is corrupt. */
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ return;
+
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
@@ -1419,6 +1439,7 @@
right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap);
if (unlikely(block != -1)) {
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1427,7 +1448,14 @@
inode ? inode->i_ino : 0,
blocknr,
"freeing already freed block "
- "(bit %u)", block);
+ "(bit %u); block bitmap corrupt.",
+ block);
+ if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ e4b->bd_info->bb_free);
+ /* Mark the block group as corrupt. */
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+ &e4b->bd_info->bb_state);
mb_regenerate_buddy(e4b);
goto done;
}
@@ -1794,9 +1822,15 @@
if (err)
return err;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
+ ext4_mb_unload_buddy(e4b);
+ return 0;
+ }
+
ext4_lock_group(ac->ac_sb, group);
max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
+ ex.fe_logical = 0xDEADFA11; /* debug value */
if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
ext4_fsblk_t start;
@@ -1925,7 +1959,7 @@
*/
break;
}
-
+ ex.fe_logical = 0xDEADC0DE; /* debug value */
ext4_mb_measure_extent(ac, &ex, e4b);
i += ex.fe_len;
@@ -1966,6 +2000,7 @@
max = mb_find_extent(e4b, i, sbi->s_stripe, &ex);
if (max >= sbi->s_stripe) {
ac->ac_found++;
+ ex.fe_logical = 0xDEADF00D; /* debug value */
ac->ac_b_ex = ex;
ext4_mb_use_best_found(ac, e4b);
break;
@@ -1991,6 +2026,9 @@
if (cr <= 2 && free < ac->ac_g_ex.fe_len)
return 0;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+ return 0;
+
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
int ret = ext4_mb_init_group(ac->ac_sb, group);
@@ -2109,6 +2147,7 @@
group = ac->ac_g_ex.fe_group;
for (i = 0; i < ngroups; group++, i++) {
+ cond_resched();
/*
* Artificially restricted ngroups for non-extent
* files makes group > ngroups possible on first loop.
@@ -2594,7 +2633,7 @@
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
ret = -ENOMEM;
- goto out_free_groupinfo_slab;
+ goto out;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2619,8 +2658,6 @@
out_free_locality_groups:
free_percpu(sbi->s_locality_groups);
sbi->s_locality_groups = NULL;
-out_free_groupinfo_slab:
- ext4_groupinfo_destroy_slabs();
out:
kfree(sbi->s_mb_offsets);
sbi->s_mb_offsets = NULL;
@@ -2711,7 +2748,8 @@
}
static inline int ext4_issue_discard(struct super_block *sb,
- ext4_group_t block_group, ext4_grpblk_t cluster, int count)
+ ext4_group_t block_group, ext4_grpblk_t cluster, int count,
+ unsigned long flags)
{
ext4_fsblk_t discard_block;
@@ -2720,7 +2758,7 @@
count = EXT4_C2B(EXT4_SB(sb), count);
trace_ext4_discard_blocks(sb,
(unsigned long long) discard_block, count);
- return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+ return sb_issue_discard(sb, discard_block, count, GFP_NOFS, flags);
}
/*
@@ -2742,7 +2780,7 @@
if (test_opt(sb, DISCARD)) {
err = ext4_issue_discard(sb, entry->efd_group,
entry->efd_start_cluster,
- entry->efd_count);
+ entry->efd_count, 0);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
" group:%d block:%d count:%d failed"
@@ -2853,6 +2891,7 @@
if (!bitmap_bh)
goto out_err;
+ BUFFER_TRACE(bitmap_bh, "getting write access");
err = ext4_journal_get_write_access(handle, bitmap_bh);
if (err)
goto out_err;
@@ -2865,6 +2904,7 @@
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
ext4_free_group_clusters(sb, gdp));
+ BUFFER_TRACE(gdp_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdp_bh);
if (err)
goto out_err;
@@ -3042,8 +3082,9 @@
(23 - bsbits)) << 23;
size = 8 * 1024 * 1024;
} else {
- start_off = (loff_t)ac->ac_o_ex.fe_logical << bsbits;
- size = ac->ac_o_ex.fe_len << bsbits;
+ start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits;
+ size = (loff_t) EXT4_C2B(EXT4_SB(ac->ac_sb),
+ ac->ac_o_ex.fe_len) << bsbits;
}
size = size >> bsbits;
start = start_off >> bsbits;
@@ -3119,9 +3160,8 @@
"start %lu, size %lu, fe_logical %lu",
(unsigned long) start, (unsigned long) size,
(unsigned long) ac->ac_o_ex.fe_logical);
+ BUG();
}
- BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
- start > ac->ac_o_ex.fe_logical);
BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
@@ -4015,8 +4055,7 @@
(unsigned long)ac->ac_b_ex.fe_len,
(unsigned long)ac->ac_b_ex.fe_logical,
(int)ac->ac_criteria);
- ext4_msg(ac->ac_sb, KERN_ERR, "%lu scanned, %d found",
- ac->ac_ex_scanned, ac->ac_found);
+ ext4_msg(ac->ac_sb, KERN_ERR, "%d found", ac->ac_found);
ext4_msg(ac->ac_sb, KERN_ERR, "groups: ");
ngroups = ext4_get_groups_count(sb);
for (i = 0; i < ngroups; i++) {
@@ -4099,7 +4138,7 @@
* per cpu locality group is to reduce the contention between block
* request from multiple CPUs.
*/
- ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
+ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups);
/* we're going to use group allocation */
ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
@@ -4375,14 +4414,7 @@
if (IS_NOQUOTA(ar->inode))
ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
- /*
- * For delayed allocation, we could skip the ENOSPC and
- * EDQUOT check, as blocks and quotas have been already
- * reserved when data being copied into pagecache.
- */
- if (ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED))
- ar->flags |= EXT4_MB_DELALLOC_RESERVED;
- else {
+ if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) {
/* Without delayed allocation we need to verify
* there is enough free blocks to do block allocation
* and verify allocation doesn't exceed the quota limits.
@@ -4438,17 +4470,20 @@
repeat:
/* allocate space in core */
*errp = ext4_mb_regular_allocator(ac);
+ if (*errp)
+ goto discard_and_exit;
+
+ /* as we've just preallocated more space than
+ * user requested originally, we store allocated
+ * space in a special descriptor */
+ if (ac->ac_status == AC_STATUS_FOUND &&
+ ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
+ *errp = ext4_mb_new_preallocation(ac);
if (*errp) {
+ discard_and_exit:
ext4_discard_allocated_blocks(ac);
goto errout;
}
-
- /* as we've just preallocated more space than
- * user requested orinally, we store allocated
- * space in a special descriptor */
- if (ac->ac_status == AC_STATUS_FOUND &&
- ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
- ext4_mb_new_preallocation(ac);
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
@@ -4479,8 +4514,7 @@
if (inquota && ar->len < inquota)
dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
if (!ar->len) {
- if (!ext4_test_inode_state(ar->inode,
- EXT4_STATE_DELALLOC_RESERVED))
+ if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0)
/* release all the reserved blocks if non delalloc */
percpu_counter_sub(&sbi->s_dirtyclusters_counter,
reserv_clstrs);
@@ -4603,7 +4637,6 @@
struct buffer_head *gd_bh;
ext4_group_t block_group;
struct ext4_sb_info *sbi;
- struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_buddy e4b;
unsigned int count_clusters;
int err = 0;
@@ -4635,10 +4668,11 @@
BUG_ON(bh && (count > 1));
for (i = 0; i < count; i++) {
+ cond_resched();
if (!bh)
tbh = sb_find_get_block(inode->i_sb,
block + i);
- if (unlikely(!tbh))
+ if (!tbh)
continue;
ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
inode, tbh, block + i);
@@ -4691,6 +4725,10 @@
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(
+ ext4_get_group_info(sb, block_group))))
+ return;
+
/*
* Check to see if we are freeing blocks across a group
* boundary.
@@ -4757,12 +4795,18 @@
/*
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
- *
- * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
- * to fail.
*/
- new_entry = kmem_cache_alloc(ext4_free_data_cachep,
- GFP_NOFS|__GFP_NOFAIL);
+ retry:
+ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
+ if (!new_entry) {
+ /*
+ * We use a retry loop because
+ * ext4_free_blocks() is not allowed to fail.
+ */
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
new_entry->efd_count = count_clusters;
@@ -4777,7 +4821,8 @@
* them with group lock_held
*/
if (test_opt(sb, DISCARD)) {
- err = ext4_issue_discard(sb, block_group, bit, count);
+ err = ext4_issue_discard(sb, block_group, bit, count,
+ 0);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
" group:%d block:%d count:%lu failed"
@@ -4803,19 +4848,7 @@
&sbi->s_flex_groups[flex_group].free_clusters);
}
- if (flags & EXT4_FREE_BLOCKS_RESERVE && ei->i_reserved_data_blocks) {
- percpu_counter_add(&sbi->s_dirtyclusters_counter,
- count_clusters);
- spin_lock(&ei->i_block_reservation_lock);
- if (flags & EXT4_FREE_BLOCKS_METADATA)
- ei->i_reserved_meta_blocks += count_clusters;
- else
- ei->i_reserved_data_blocks += count_clusters;
- spin_unlock(&ei->i_block_reservation_lock);
- if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
- dquot_reclaim_block(inode,
- EXT4_C2B(sbi, count_clusters));
- } else if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
@@ -4984,13 +5017,17 @@
* @count: number of blocks to TRIM
* @group: alloc. group we are working with
* @e4b: ext4 buddy for the group
+ * @blkdev_flags: flags for the block device
*
* Trim "count" blocks starting at "start" in the "group". To assure that no
* one will allocate those blocks, mark it as used in buddy bitmap. This must
* be called with under the group lock.
*/
static int ext4_trim_extent(struct super_block *sb, int start, int count,
- ext4_group_t group, struct ext4_buddy *e4b)
+ ext4_group_t group, struct ext4_buddy *e4b,
+ unsigned long blkdev_flags)
+__releases(bitlock)
+__acquires(bitlock)
{
struct ext4_free_extent ex;
int ret = 0;
@@ -5009,7 +5046,7 @@
*/
mb_mark_used(e4b, &ex);
ext4_unlock_group(sb, group);
- ret = ext4_issue_discard(sb, group, start, count);
+ ret = ext4_issue_discard(sb, group, start, count, blkdev_flags);
ext4_lock_group(sb, group);
mb_free_blocks(NULL, e4b, start, ex.fe_len);
return ret;
@@ -5022,6 +5059,7 @@
* @start: first group block to examine
* @max: last group block to examine
* @minblocks: minimum extent block count
+ * @blkdev_flags: flags for the block device
*
* ext4_trim_all_free walks through group's buddy bitmap searching for free
* extents. When the free block is found, ext4_trim_extent is called to TRIM
@@ -5036,7 +5074,7 @@
static ext4_grpblk_t
ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t start, ext4_grpblk_t max,
- ext4_grpblk_t minblocks)
+ ext4_grpblk_t minblocks, unsigned long blkdev_flags)
{
void *bitmap;
ext4_grpblk_t next, count = 0, free_count = 0;
@@ -5069,7 +5107,8 @@
if ((next - start) >= minblocks) {
ret = ext4_trim_extent(sb, start,
- next - start, group, &e4b);
+ next - start, group, &e4b,
+ blkdev_flags);
if (ret && ret != -EOPNOTSUPP)
break;
ret = 0;
@@ -5111,6 +5150,7 @@
* ext4_trim_fs() -- trim ioctl handle function
* @sb: superblock for filesystem
* @range: fstrim_range structure
+ * @blkdev_flags: flags for the block device
*
* start: First Byte to trim
* len: number of Bytes to trim from start
@@ -5119,7 +5159,8 @@
* start to start+len. For each such a group ext4_trim_all_free function
* is invoked to trim all free space.
*/
-int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range,
+ unsigned long blkdev_flags)
{
struct ext4_group_info *grp;
ext4_group_t group, first_group, last_group;
@@ -5175,7 +5216,7 @@
if (grp->bb_free >= minlen) {
cnt = ext4_trim_all_free(sb, group, first_cluster,
- end, minlen);
+ end, minlen, blkdev_flags);
if (cnt < 0) {
ret = cnt;
break;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 08481ee..d634e18 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -48,7 +48,7 @@
} \
} while (0)
#else
-#define mb_debug(n, fmt, a...)
+#define mb_debug(n, fmt, a...) no_printk(fmt, ## a)
#endif
#define EXT4_MB_HISTORY_ALLOC 1 /* allocation */
@@ -175,8 +175,6 @@
/* copy of the best found extent taken before preallocation efforts */
struct ext4_free_extent ac_f_ex;
- /* number of iterations done. we have to track to limit searching */
- unsigned long ac_ex_scanned;
__u16 ac_groups_scanned;
__u16 ac_found;
__u16 ac_tail;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index d19efab..a432634 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -39,8 +39,9 @@
newext.ee_block = cpu_to_le32(lb->first_block);
newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1);
ext4_ext_store_pblock(&newext, lb->first_pblock);
- path = ext4_ext_find_extent(inode, lb->first_block, NULL);
-
+ /* Locking only for convinience since we are operating on temp inode */
+ down_write(&EXT4_I(inode)->i_data_sem);
+ path = ext4_find_extent(inode, lb->first_block, NULL, 0);
if (IS_ERR(path)) {
retval = PTR_ERR(path);
path = NULL;
@@ -61,7 +62,9 @@
*/
if (needed && ext4_handle_has_enough_credits(handle,
EXT4_RESERVE_TRANS_BLOCKS)) {
+ up_write((&EXT4_I(inode)->i_data_sem));
retval = ext4_journal_restart(handle, needed);
+ down_write((&EXT4_I(inode)->i_data_sem));
if (retval)
goto err_out;
} else if (needed) {
@@ -70,17 +73,18 @@
/*
* IF not able to extend the journal restart the journal
*/
+ up_write((&EXT4_I(inode)->i_data_sem));
retval = ext4_journal_restart(handle, needed);
+ down_write((&EXT4_I(inode)->i_data_sem));
if (retval)
goto err_out;
}
}
- retval = ext4_ext_insert_extent(handle, inode, path, &newext, 0);
+ retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0);
err_out:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
+ up_write((&EXT4_I(inode)->i_data_sem));
+ ext4_ext_drop_refs(path);
+ kfree(path);
lb->first_pblock = 0;
return retval;
}
@@ -494,7 +498,7 @@
* superblock modification.
*
* For the tmp_inode we already have committed the
- * trascation that created the inode. Later as and
+ * transaction that created the inode. Later as and
* when we add extents we extent the journal
*/
/*
@@ -505,7 +509,7 @@
* with i_data_sem held to prevent racing with block
* allocation.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
@@ -616,7 +620,6 @@
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
- ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
@@ -630,14 +633,6 @@
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
- /*
- * In order to get correct extent info, force all delayed allocation
- * blocks to be allocated, otherwise delayed allocation blocks may not
- * be reflected and bypass the checks on extent header.
- */
- if (test_opt(inode->i_sb, DELALLOC))
- ext4_alloc_da_blocks(inode);
-
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -655,13 +650,11 @@
goto errout;
}
if (eh->eh_entries == 0)
- blk = len = start = end = 0;
+ blk = len = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
- start = le32_to_cpu(ex->ee_block);
- end = start + len - 1;
- if (end >= EXT4_NDIR_BLOCKS) {
+ if (len > EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
@@ -669,7 +662,7 @@
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
- for (i = start; i <= end; i++)
+ for (i=0; i < len; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 214461e..8313ca3 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -18,19 +18,17 @@
return cpu_to_le32(csum);
}
-int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return 1;
return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
}
-void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return;
mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);
@@ -259,7 +257,7 @@
u32 new_seq;
do {
- get_random_bytes(&new_seq, sizeof(u32));
+ new_seq = prandom_u32();
} while (new_seq > EXT4_MMP_SEQ_MAX);
return new_seq;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index ad52ace..023314c 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -27,120 +27,26 @@
* @lblock: logical block number to find an extent path
* @path: pointer to an extent path pointer (for output)
*
- * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
+ * ext4_find_extent wrapper. Return 0 on success, or a negative error value
* on failure.
*/
static inline int
get_ext_path(struct inode *inode, ext4_lblk_t lblock,
- struct ext4_ext_path **orig_path)
+ struct ext4_ext_path **ppath)
{
- int ret = 0;
struct ext4_ext_path *path;
- path = ext4_ext_find_extent(inode, lblock, *orig_path);
+ path = ext4_find_extent(inode, lblock, ppath, EXT4_EX_NOCACHE);
if (IS_ERR(path))
- ret = PTR_ERR(path);
- else if (path[ext_depth(inode)].p_ext == NULL)
- ret = -ENODATA;
- else
- *orig_path = path;
-
- return ret;
-}
-
-/**
- * copy_extent_status - Copy the extent's initialization status
- *
- * @src: an extent for getting initialize status
- * @dest: an extent to be set the status
- */
-static void
-copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
-{
- if (ext4_ext_is_uninitialized(src))
- ext4_ext_mark_uninitialized(dest);
- else
- dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
-}
-
-/**
- * mext_next_extent - Search for the next extent and set it to "extent"
- *
- * @inode: inode which is searched
- * @path: this will obtain data for the next extent
- * @extent: pointer to the next extent we have just gotten
- *
- * Search the next extent in the array of ext4_ext_path structure (@path)
- * and set it to ext4_extent structure (@extent). In addition, the member of
- * @path (->p_ext) also points the next extent. Return 0 on success, 1 if
- * ext4_ext_path structure refers to the last extent, or a negative error
- * value on failure.
- */
-static int
-mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
- struct ext4_extent **extent)
-{
- struct ext4_extent_header *eh;
- int ppos, leaf_ppos = path->p_depth;
-
- ppos = leaf_ppos;
- if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
- /* leaf block */
- *extent = ++path[ppos].p_ext;
- path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
- return 0;
+ return PTR_ERR(path);
+ if (path[ext_depth(inode)].p_ext == NULL) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ *ppath = NULL;
+ return -ENODATA;
}
-
- while (--ppos >= 0) {
- if (EXT_LAST_INDEX(path[ppos].p_hdr) >
- path[ppos].p_idx) {
- int cur_ppos = ppos;
-
- /* index block */
- path[ppos].p_idx++;
- path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
- if (path[ppos+1].p_bh)
- brelse(path[ppos+1].p_bh);
- path[ppos+1].p_bh =
- sb_bread(inode->i_sb, path[ppos].p_block);
- if (!path[ppos+1].p_bh)
- return -EIO;
- path[ppos+1].p_hdr =
- ext_block_hdr(path[ppos+1].p_bh);
-
- /* Halfway index block */
- while (++cur_ppos < leaf_ppos) {
- path[cur_ppos].p_idx =
- EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
- path[cur_ppos].p_block =
- ext4_idx_pblock(path[cur_ppos].p_idx);
- if (path[cur_ppos+1].p_bh)
- brelse(path[cur_ppos+1].p_bh);
- path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
- path[cur_ppos].p_block);
- if (!path[cur_ppos+1].p_bh)
- return -EIO;
- path[cur_ppos+1].p_hdr =
- ext_block_hdr(path[cur_ppos+1].p_bh);
- }
-
- path[leaf_ppos].p_ext = *extent = NULL;
-
- eh = path[leaf_ppos].p_hdr;
- if (le16_to_cpu(eh->eh_entries) == 0)
- /* empty leaf is found */
- return -ENODATA;
-
- /* leaf block */
- path[leaf_ppos].p_ext = *extent =
- EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
- path[leaf_ppos].p_block =
- ext4_ext_pblock(path[leaf_ppos].p_ext);
- return 0;
- }
- }
- /* We found the last extent */
- return 1;
+ *ppath = path;
+ return 0;
}
/**
@@ -178,429 +84,19 @@
}
/**
- * mext_insert_across_blocks - Insert extents across leaf block
- *
- * @handle: journal handle
- * @orig_inode: original inode
- * @o_start: first original extent to be changed
- * @o_end: last original extent to be changed
- * @start_ext: first new extent to be inserted
- * @new_ext: middle of new extent to be inserted
- * @end_ext: last new extent to be inserted
- *
- * Allocate a new leaf block and insert extents into it. Return 0 on success,
- * or a negative error value on failure.
- */
-static int
-mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
- struct ext4_extent *o_start, struct ext4_extent *o_end,
- struct ext4_extent *start_ext, struct ext4_extent *new_ext,
- struct ext4_extent *end_ext)
-{
- struct ext4_ext_path *orig_path = NULL;
- ext4_lblk_t eblock = 0;
- int new_flag = 0;
- int end_flag = 0;
- int err = 0;
-
- if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) {
- if (o_start == o_end) {
-
- /* start_ext new_ext end_ext
- * donor |---------|-----------|--------|
- * orig |------------------------------|
- */
- end_flag = 1;
- } else {
-
- /* start_ext new_ext end_ext
- * donor |---------|----------|---------|
- * orig |---------------|--------------|
- */
- o_end->ee_block = end_ext->ee_block;
- o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
- }
-
- o_start->ee_len = start_ext->ee_len;
- eblock = le32_to_cpu(start_ext->ee_block);
- new_flag = 1;
-
- } else if (start_ext->ee_len && new_ext->ee_len &&
- !end_ext->ee_len && o_start == o_end) {
-
- /* start_ext new_ext
- * donor |--------------|---------------|
- * orig |------------------------------|
- */
- o_start->ee_len = start_ext->ee_len;
- eblock = le32_to_cpu(start_ext->ee_block);
- new_flag = 1;
-
- } else if (!start_ext->ee_len && new_ext->ee_len &&
- end_ext->ee_len && o_start == o_end) {
-
- /* new_ext end_ext
- * donor |--------------|---------------|
- * orig |------------------------------|
- */
- o_end->ee_block = end_ext->ee_block;
- o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
-
- /*
- * Set 0 to the extent block if new_ext was
- * the first block.
- */
- if (new_ext->ee_block)
- eblock = le32_to_cpu(new_ext->ee_block);
-
- new_flag = 1;
- } else {
- ext4_debug("ext4 move extent: Unexpected insert case\n");
- return -EIO;
- }
-
- if (new_flag) {
- err = get_ext_path(orig_inode, eblock, &orig_path);
- if (err)
- goto out;
-
- if (ext4_ext_insert_extent(handle, orig_inode,
- orig_path, new_ext, 0))
- goto out;
- }
-
- if (end_flag) {
- err = get_ext_path(orig_inode,
- le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
- if (err)
- goto out;
-
- if (ext4_ext_insert_extent(handle, orig_inode,
- orig_path, end_ext, 0))
- goto out;
- }
-out:
- if (orig_path) {
- ext4_ext_drop_refs(orig_path);
- kfree(orig_path);
- }
-
- return err;
-
-}
-
-/**
- * mext_insert_inside_block - Insert new extent to the extent block
- *
- * @o_start: first original extent to be moved
- * @o_end: last original extent to be moved
- * @start_ext: first new extent to be inserted
- * @new_ext: middle of new extent to be inserted
- * @end_ext: last new extent to be inserted
- * @eh: extent header of target leaf block
- * @range_to_move: used to decide how to insert extent
- *
- * Insert extents into the leaf block. The extent (@o_start) is overwritten
- * by inserted extents.
- */
-static void
-mext_insert_inside_block(struct ext4_extent *o_start,
- struct ext4_extent *o_end,
- struct ext4_extent *start_ext,
- struct ext4_extent *new_ext,
- struct ext4_extent *end_ext,
- struct ext4_extent_header *eh,
- int range_to_move)
-{
- int i = 0;
- unsigned long len;
-
- /* Move the existing extents */
- if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) {
- len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) -
- (unsigned long)(o_end + 1);
- memmove(o_end + 1 + range_to_move, o_end + 1, len);
- }
-
- /* Insert start entry */
- if (start_ext->ee_len)
- o_start[i++].ee_len = start_ext->ee_len;
-
- /* Insert new entry */
- if (new_ext->ee_len) {
- o_start[i] = *new_ext;
- ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
- }
-
- /* Insert end entry */
- if (end_ext->ee_len)
- o_start[i] = *end_ext;
-
- /* Increment the total entries counter on the extent block */
- le16_add_cpu(&eh->eh_entries, range_to_move);
-}
-
-/**
- * mext_insert_extents - Insert new extent
- *
- * @handle: journal handle
- * @orig_inode: original inode
- * @orig_path: path indicates first extent to be changed
- * @o_start: first original extent to be changed
- * @o_end: last original extent to be changed
- * @start_ext: first new extent to be inserted
- * @new_ext: middle of new extent to be inserted
- * @end_ext: last new extent to be inserted
- *
- * Call the function to insert extents. If we cannot add more extents into
- * the leaf block, we call mext_insert_across_blocks() to create a
- * new leaf block. Otherwise call mext_insert_inside_block(). Return 0
- * on success, or a negative error value on failure.
- */
-static int
-mext_insert_extents(handle_t *handle, struct inode *orig_inode,
- struct ext4_ext_path *orig_path,
- struct ext4_extent *o_start,
- struct ext4_extent *o_end,
- struct ext4_extent *start_ext,
- struct ext4_extent *new_ext,
- struct ext4_extent *end_ext)
-{
- struct ext4_extent_header *eh;
- unsigned long need_slots, slots_range;
- int range_to_move, depth, ret;
-
- /*
- * The extents need to be inserted
- * start_extent + new_extent + end_extent.
- */
- need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) +
- (new_ext->ee_len ? 1 : 0);
-
- /* The number of slots between start and end */
- slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1)
- / sizeof(struct ext4_extent);
-
- /* Range to move the end of extent */
- range_to_move = need_slots - slots_range;
- depth = orig_path->p_depth;
- orig_path += depth;
- eh = orig_path->p_hdr;
-
- if (depth) {
- /* Register to journal */
- ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
- if (ret)
- return ret;
- }
-
- /* Expansion */
- if (range_to_move > 0 &&
- (range_to_move > le16_to_cpu(eh->eh_max)
- - le16_to_cpu(eh->eh_entries))) {
-
- ret = mext_insert_across_blocks(handle, orig_inode, o_start,
- o_end, start_ext, new_ext, end_ext);
- if (ret < 0)
- return ret;
- } else
- mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
- end_ext, eh, range_to_move);
-
- return ext4_ext_dirty(handle, orig_inode, orig_path);
-}
-
-/**
- * mext_leaf_block - Move one leaf extent block into the inode.
- *
- * @handle: journal handle
- * @orig_inode: original inode
- * @orig_path: path indicates first extent to be changed
- * @dext: donor extent
- * @from: start offset on the target file
- *
- * In order to insert extents into the leaf block, we must divide the extent
- * in the leaf block into three extents. The one is located to be inserted
- * extents, and the others are located around it.
- *
- * Therefore, this function creates structures to save extents of the leaf
- * block, and inserts extents by calling mext_insert_extents() with
- * created extents. Return 0 on success, or a negative error value on failure.
- */
-static int
-mext_leaf_block(handle_t *handle, struct inode *orig_inode,
- struct ext4_ext_path *orig_path, struct ext4_extent *dext,
- ext4_lblk_t *from)
-{
- struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
- struct ext4_extent new_ext, start_ext, end_ext;
- ext4_lblk_t new_ext_end;
- int oext_alen, new_ext_alen, end_ext_alen;
- int depth = ext_depth(orig_inode);
- int ret;
-
- start_ext.ee_block = end_ext.ee_block = 0;
- o_start = o_end = oext = orig_path[depth].p_ext;
- oext_alen = ext4_ext_get_actual_len(oext);
- start_ext.ee_len = end_ext.ee_len = 0;
-
- new_ext.ee_block = cpu_to_le32(*from);
- ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
- new_ext.ee_len = dext->ee_len;
- new_ext_alen = ext4_ext_get_actual_len(&new_ext);
- new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
-
- /*
- * Case: original extent is first
- * oext |--------|
- * new_ext |--|
- * start_ext |--|
- */
- if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) &&
- le32_to_cpu(new_ext.ee_block) <
- le32_to_cpu(oext->ee_block) + oext_alen) {
- start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
- le32_to_cpu(oext->ee_block));
- start_ext.ee_block = oext->ee_block;
- copy_extent_status(oext, &start_ext);
- } else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
- prev_ext = oext - 1;
- /*
- * We can merge new_ext into previous extent,
- * if these are contiguous and same extent type.
- */
- if (ext4_can_extents_be_merged(orig_inode, prev_ext,
- &new_ext)) {
- o_start = prev_ext;
- start_ext.ee_len = cpu_to_le16(
- ext4_ext_get_actual_len(prev_ext) +
- new_ext_alen);
- start_ext.ee_block = oext->ee_block;
- copy_extent_status(prev_ext, &start_ext);
- new_ext.ee_len = 0;
- }
- }
-
- /*
- * Case: new_ext_end must be less than oext
- * oext |-----------|
- * new_ext |-------|
- */
- if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
- EXT4_ERROR_INODE(orig_inode,
- "new_ext_end(%u) should be less than or equal to "
- "oext->ee_block(%u) + oext_alen(%d) - 1",
- new_ext_end, le32_to_cpu(oext->ee_block),
- oext_alen);
- ret = -EIO;
- goto out;
- }
-
- /*
- * Case: new_ext is smaller than original extent
- * oext |---------------|
- * new_ext |-----------|
- * end_ext |---|
- */
- if (le32_to_cpu(oext->ee_block) <= new_ext_end &&
- new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) {
- end_ext.ee_len =
- cpu_to_le16(le32_to_cpu(oext->ee_block) +
- oext_alen - 1 - new_ext_end);
- copy_extent_status(oext, &end_ext);
- end_ext_alen = ext4_ext_get_actual_len(&end_ext);
- ext4_ext_store_pblock(&end_ext,
- (ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
- end_ext.ee_block =
- cpu_to_le32(le32_to_cpu(o_end->ee_block) +
- oext_alen - end_ext_alen);
- }
-
- ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
- o_end, &start_ext, &new_ext, &end_ext);
-out:
- return ret;
-}
-
-/**
- * mext_calc_swap_extents - Calculate extents for extent swapping.
- *
- * @tmp_dext: the extent that will belong to the original inode
- * @tmp_oext: the extent that will belong to the donor inode
- * @orig_off: block offset of original inode
- * @donor_off: block offset of donor inode
- * @max_count: the maximum length of extents
- *
- * Return 0 on success, or a negative error value on failure.
- */
-static int
-mext_calc_swap_extents(struct ext4_extent *tmp_dext,
- struct ext4_extent *tmp_oext,
- ext4_lblk_t orig_off, ext4_lblk_t donor_off,
- ext4_lblk_t max_count)
-{
- ext4_lblk_t diff, orig_diff;
- struct ext4_extent dext_old, oext_old;
-
- BUG_ON(orig_off != donor_off);
-
- /* original and donor extents have to cover the same block offset */
- if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
- le32_to_cpu(tmp_oext->ee_block) +
- ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
- return -ENODATA;
-
- if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
- le32_to_cpu(tmp_dext->ee_block) +
- ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
- return -ENODATA;
-
- dext_old = *tmp_dext;
- oext_old = *tmp_oext;
-
- /* When tmp_dext is too large, pick up the target range. */
- diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
-
- ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
- le32_add_cpu(&tmp_dext->ee_block, diff);
- le16_add_cpu(&tmp_dext->ee_len, -diff);
-
- if (max_count < ext4_ext_get_actual_len(tmp_dext))
- tmp_dext->ee_len = cpu_to_le16(max_count);
-
- orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
- ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
-
- /* Adjust extent length if donor extent is larger than orig */
- if (ext4_ext_get_actual_len(tmp_dext) >
- ext4_ext_get_actual_len(tmp_oext) - orig_diff)
- tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) -
- orig_diff);
-
- tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext));
-
- copy_extent_status(&oext_old, tmp_dext);
- copy_extent_status(&dext_old, tmp_oext);
-
- return 0;
-}
-
-/**
* mext_check_coverage - Check that all extents in range has the same type
*
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
- * @uninit: extents expected to be uninitialized
+ * @unwritten: extents expected to be unwritten
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
- int uninit, int *err)
+ int unwritten, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
@@ -611,178 +107,32 @@
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
- if (uninit != ext4_ext_is_uninitialized(ext))
+ if (unwritten != ext4_ext_is_unwritten(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
}
ret = 1;
out:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
+ ext4_ext_drop_refs(path);
+ kfree(path);
return ret;
}
/**
- * mext_replace_branches - Replace original extents with new extents
- *
- * @handle: journal handle
- * @orig_inode: original inode
- * @donor_inode: donor inode
- * @from: block offset of orig_inode
- * @count: block count to be replaced
- * @err: pointer to save return value
- *
- * Replace original inode extents and donor inode extents page by page.
- * We implement this replacement in the following three steps:
- * 1. Save the block information of original and donor inodes into
- * dummy extents.
- * 2. Change the block information of original inode to point at the
- * donor inode blocks.
- * 3. Change the block information of donor inode to point at the saved
- * original inode blocks in the dummy extents.
- *
- * Return replaced block count.
- */
-static int
-mext_replace_branches(handle_t *handle, struct inode *orig_inode,
- struct inode *donor_inode, ext4_lblk_t from,
- ext4_lblk_t count, int *err)
-{
- struct ext4_ext_path *orig_path = NULL;
- struct ext4_ext_path *donor_path = NULL;
- struct ext4_extent *oext, *dext;
- struct ext4_extent tmp_dext, tmp_oext;
- ext4_lblk_t orig_off = from, donor_off = from;
- int depth;
- int replaced_count = 0;
- int dext_alen;
-
- *err = ext4_es_remove_extent(orig_inode, from, count);
- if (*err)
- goto out;
-
- *err = ext4_es_remove_extent(donor_inode, from, count);
- if (*err)
- goto out;
-
- /* Get the original extent for the block "orig_off" */
- *err = get_ext_path(orig_inode, orig_off, &orig_path);
- if (*err)
- goto out;
-
- /* Get the donor extent for the head */
- *err = get_ext_path(donor_inode, donor_off, &donor_path);
- if (*err)
- goto out;
- depth = ext_depth(orig_inode);
- oext = orig_path[depth].p_ext;
- tmp_oext = *oext;
-
- depth = ext_depth(donor_inode);
- dext = donor_path[depth].p_ext;
- if (unlikely(!dext))
- goto missing_donor_extent;
- tmp_dext = *dext;
-
- *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
- donor_off, count);
- if (*err)
- goto out;
-
- /* Loop for the donor extents */
- while (1) {
- /* The extent for donor must be found. */
- if (unlikely(!dext)) {
- missing_donor_extent:
- EXT4_ERROR_INODE(donor_inode,
- "The extent for donor must be found");
- *err = -EIO;
- goto out;
- } else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
- EXT4_ERROR_INODE(donor_inode,
- "Donor offset(%u) and the first block of donor "
- "extent(%u) should be equal",
- donor_off,
- le32_to_cpu(tmp_dext.ee_block));
- *err = -EIO;
- goto out;
- }
-
- /* Set donor extent to orig extent */
- *err = mext_leaf_block(handle, orig_inode,
- orig_path, &tmp_dext, &orig_off);
- if (*err)
- goto out;
-
- /* Set orig extent to donor extent */
- *err = mext_leaf_block(handle, donor_inode,
- donor_path, &tmp_oext, &donor_off);
- if (*err)
- goto out;
-
- dext_alen = ext4_ext_get_actual_len(&tmp_dext);
- replaced_count += dext_alen;
- donor_off += dext_alen;
- orig_off += dext_alen;
-
- BUG_ON(replaced_count > count);
- /* Already moved the expected blocks */
- if (replaced_count >= count)
- break;
-
- if (orig_path)
- ext4_ext_drop_refs(orig_path);
- *err = get_ext_path(orig_inode, orig_off, &orig_path);
- if (*err)
- goto out;
- depth = ext_depth(orig_inode);
- oext = orig_path[depth].p_ext;
- tmp_oext = *oext;
-
- if (donor_path)
- ext4_ext_drop_refs(donor_path);
- *err = get_ext_path(donor_inode, donor_off, &donor_path);
- if (*err)
- goto out;
- depth = ext_depth(donor_inode);
- dext = donor_path[depth].p_ext;
- tmp_dext = *dext;
-
- *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
- donor_off, count - replaced_count);
- if (*err)
- goto out;
- }
-
-out:
- if (orig_path) {
- ext4_ext_drop_refs(orig_path);
- kfree(orig_path);
- }
- if (donor_path) {
- ext4_ext_drop_refs(donor_path);
- kfree(donor_path);
- }
-
- return replaced_count;
-}
-
-/**
* mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2
*
* @inode1: the inode structure
* @inode2: the inode structure
- * @index: page index
+ * @index1: page index
+ * @index2: page index
* @page: result page vector
*
* Grab two locked pages for inode's by inode order
*/
static int
mext_page_double_lock(struct inode *inode1, struct inode *inode2,
- pgoff_t index, struct page *page[2])
+ pgoff_t index1, pgoff_t index2, struct page *page[2])
{
struct address_space *mapping[2];
unsigned fl = AOP_FLAG_NOFS;
@@ -792,15 +142,18 @@
mapping[0] = inode1->i_mapping;
mapping[1] = inode2->i_mapping;
} else {
+ pgoff_t tmp = index1;
+ index1 = index2;
+ index2 = tmp;
mapping[0] = inode2->i_mapping;
mapping[1] = inode1->i_mapping;
}
- page[0] = grab_cache_page_write_begin(mapping[0], index, fl);
+ page[0] = grab_cache_page_write_begin(mapping[0], index1, fl);
if (!page[0])
return -ENOMEM;
- page[1] = grab_cache_page_write_begin(mapping[1], index, fl);
+ page[1] = grab_cache_page_write_begin(mapping[1], index2, fl);
if (!page[1]) {
unlock_page(page[0]);
page_cache_release(page[0]);
@@ -861,8 +214,7 @@
}
if (!buffer_mapped(bh)) {
zero_user(page, block_start, blocksize);
- if (!err)
- set_buffer_uptodate(bh);
+ set_buffer_uptodate(bh);
continue;
}
}
@@ -893,26 +245,27 @@
* @o_filp: file structure of original file
* @donor_inode: donor inode
* @orig_page_offset: page index on original file
+ * @donor_page_offset: page index on donor file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
- * @uninit: orig extent is uninitialized or not
+ * @unwritten: orig extent is unwritten or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
- * with donor inode extents by calling mext_replace_branches().
+ * with donor inode extents by calling ext4_swap_extents().
* Finally, write out the saved data in new original inode blocks. Return
* replaced block count.
*/
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
- pgoff_t orig_page_offset, int data_offset_in_page,
- int block_len_in_page, int uninit, int *err)
+ pgoff_t orig_page_offset, pgoff_t donor_page_offset,
+ int data_offset_in_page,
+ int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
handle_t *handle;
- ext4_lblk_t orig_blk_offset;
- long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
+ ext4_lblk_t orig_blk_offset, donor_blk_offset;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
unsigned int w_flags = 0;
unsigned int tmp_data_size, data_size, replaced_size;
@@ -940,7 +293,8 @@
orig_blk_offset = orig_page_offset * blocks_per_page +
data_offset_in_page;
- offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
+ donor_blk_offset = donor_page_offset * blocks_per_page +
+ data_offset_in_page;
/* Calculate data_size */
if ((orig_blk_offset + block_len_in_page - 1) ==
@@ -962,31 +316,31 @@
replaced_size = data_size;
*err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
- pagep);
+ donor_page_offset, pagep);
if (unlikely(*err < 0))
goto stop_journal;
/*
- * If orig extent was uninitialized it can become initialized
+ * If orig extent was unwritten it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
- if (uninit) {
+ if (unwritten) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
- uninit = mext_check_coverage(orig_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten &= mext_check_coverage(donor_inode, donor_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- if (!uninit) {
+ if (!unwritten) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
@@ -997,9 +351,10 @@
*err = -EBUSY;
goto drop_data_sem;
}
- replaced_count = mext_replace_branches(handle, orig_inode,
- donor_inode, orig_blk_offset,
- block_len_in_page, err);
+ replaced_count = ext4_swap_extents(handle, orig_inode,
+ donor_inode, orig_blk_offset,
+ donor_blk_offset,
+ block_len_in_page, 1, err);
drop_data_sem:
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto unlock_pages;
@@ -1016,10 +371,11 @@
*err = -EBUSY;
goto unlock_pages;
}
-
- replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
- orig_blk_offset,
- block_len_in_page, err);
+ ext4_double_down_write_data_sem(orig_inode, donor_inode);
+ replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode,
+ orig_blk_offset, donor_blk_offset,
+ block_len_in_page, 1, err);
+ ext4_double_up_write_data_sem(orig_inode, donor_inode);
if (*err) {
if (replaced_count) {
block_len_in_page = replaced_count;
@@ -1063,9 +419,9 @@
* Try to swap extents to it's original places
*/
ext4_double_down_write_data_sem(orig_inode, donor_inode);
- replaced_count = mext_replace_branches(handle, donor_inode, orig_inode,
- orig_blk_offset,
- block_len_in_page, &err2);
+ replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode,
+ orig_blk_offset, donor_blk_offset,
+ block_len_in_page, 0, &err2);
ext4_double_up_write_data_sem(orig_inode, donor_inode);
if (replaced_count != block_len_in_page) {
EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset),
@@ -1095,10 +451,14 @@
struct inode *donor_inode, __u64 orig_start,
__u64 donor_start, __u64 *len)
{
- ext4_lblk_t orig_blocks, donor_blocks;
+ __u64 orig_eof, donor_eof;
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;
+ orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits;
+ donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits;
+
+
if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
ext4_debug("ext4 move extent: suid or sgid is set"
" to donor file [ino:orig %lu, donor %lu]\n",
@@ -1114,7 +474,7 @@
ext4_debug("ext4 move extent: The argument files should "
"not be swapfile [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
- return -EINVAL;
+ return -EBUSY;
}
if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
@@ -1141,67 +501,28 @@
}
/* Start offset should be same */
- if (orig_start != donor_start) {
+ if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
+ (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
ext4_debug("ext4 move extent: orig and donor's start "
- "offset are not same [ino:orig %lu, donor %lu]\n",
+ "offset are not alligned [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if ((orig_start >= EXT_MAX_BLOCKS) ||
+ (donor_start >= EXT_MAX_BLOCKS) ||
(*len > EXT_MAX_BLOCKS) ||
+ (donor_start + *len >= EXT_MAX_BLOCKS) ||
(orig_start + *len >= EXT_MAX_BLOCKS)) {
ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
-
- if (orig_inode->i_size > donor_inode->i_size) {
- donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits;
- /* TODO: eliminate this artificial restriction */
- if (orig_start >= donor_blocks) {
- ext4_debug("ext4 move extent: orig start offset "
- "[%llu] should be less than donor file blocks "
- "[%u] [ino:orig %lu, donor %lu]\n",
- orig_start, donor_blocks,
- orig_inode->i_ino, donor_inode->i_ino);
- return -EINVAL;
- }
-
- /* TODO: eliminate this artificial restriction */
- if (orig_start + *len > donor_blocks) {
- ext4_debug("ext4 move extent: End offset [%llu] should "
- "be less than donor file blocks [%u]."
- "So adjust length from %llu to %llu "
- "[ino:orig %lu, donor %lu]\n",
- orig_start + *len, donor_blocks,
- *len, donor_blocks - orig_start,
- orig_inode->i_ino, donor_inode->i_ino);
- *len = donor_blocks - orig_start;
- }
- } else {
- orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits;
- if (orig_start >= orig_blocks) {
- ext4_debug("ext4 move extent: start offset [%llu] "
- "should be less than original file blocks "
- "[%u] [ino:orig %lu, donor %lu]\n",
- orig_start, orig_blocks,
- orig_inode->i_ino, donor_inode->i_ino);
- return -EINVAL;
- }
-
- if (orig_start + *len > orig_blocks) {
- ext4_debug("ext4 move extent: Adjust length "
- "from %llu to %llu. Because it should be "
- "less than original file blocks "
- "[ino:orig %lu, donor %lu]\n",
- *len, orig_blocks - orig_start,
- orig_inode->i_ino, donor_inode->i_ino);
- *len = orig_blocks - orig_start;
- }
- }
-
+ if (orig_eof < orig_start + *len - 1)
+ *len = orig_eof - orig_start;
+ if (donor_eof < donor_start + *len - 1)
+ *len = donor_eof - donor_start;
if (!*len) {
ext4_debug("ext4 move extent: len should not be 0 "
"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
@@ -1213,100 +534,30 @@
}
/**
- * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
- *
- * @inode1: the inode structure
- * @inode2: the inode structure
- *
- * Lock two inodes' i_mutex
- */
-void
-ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
- BUG_ON(inode1 == inode2);
- if (inode1 < inode2) {
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
- } else {
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
- }
-}
-
-/**
- * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
- *
- * @inode1: the inode that is released first
- * @inode2: the inode that is released second
- *
- */
-
-void
-ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
- mutex_unlock(&inode1->i_mutex);
- mutex_unlock(&inode2->i_mutex);
-}
-
-/**
* ext4_move_extents - Exchange the specified range of a file
*
* @o_filp: file structure of the original file
* @d_filp: file structure of the donor file
- * @orig_start: start offset in block for orig
- * @donor_start: start offset in block for donor
+ * @orig_blk: start offset in block for orig
+ * @donor_blk: start offset in block for donor
* @len: the number of blocks to be moved
* @moved_len: moved block length
*
* This function returns 0 and moved block length is set in moved_len
* if succeed, otherwise returns error value.
*
- * Note: ext4_move_extents() proceeds the following order.
- * 1:ext4_move_extents() calculates the last block number of moving extent
- * function by the start block number (orig_start) and the number of blocks
- * to be moved (len) specified as arguments.
- * If the {orig, donor}_start points a hole, the extent's start offset
- * pointed by ext_cur (current extent), holecheck_path, orig_path are set
- * after hole behind.
- * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent
- * or the ext_cur exceeds the block_end which is last logical block number.
- * 3:To get the length of continues area, call mext_next_extent()
- * specified with the ext_cur (initial value is holecheck_path) re-cursive,
- * until find un-continuous extent, the start logical block number exceeds
- * the block_end or the extent points to the last extent.
- * 4:Exchange the original inode data with donor inode data
- * from orig_page_offset to seq_end_page.
- * The start indexes of data are specified as arguments.
- * That of the original inode is orig_page_offset,
- * and the donor inode is also orig_page_offset
- * (To easily handle blocksize != pagesize case, the offset for the
- * donor inode is block unit).
- * 5:Update holecheck_path and orig_path to points a next proceeding extent,
- * then returns to step 2.
- * 6:Release holecheck_path, orig_path and set the len to moved_len
- * which shows the number of moved blocks.
- * The moved_len is useful for the command to calculate the file offset
- * for starting next move extent ioctl.
- * 7:Return 0 on success, or a negative error value on failure.
*/
int
-ext4_move_extents(struct file *o_filp, struct file *d_filp,
- __u64 orig_start, __u64 donor_start, __u64 len,
- __u64 *moved_len)
+ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
+ __u64 donor_blk, __u64 len, __u64 *moved_len)
{
struct inode *orig_inode = file_inode(o_filp);
struct inode *donor_inode = file_inode(d_filp);
- struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL;
- struct ext4_extent *ext_prev, *ext_cur, *ext_dummy;
- ext4_lblk_t block_start = orig_start;
- ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0;
- ext4_lblk_t rest_blocks;
- pgoff_t orig_page_offset = 0, seq_end_page;
- int ret, depth, last_extent = 0;
+ struct ext4_ext_path *path = NULL;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
- int data_offset_in_page;
- int block_len_in_page;
- int uninit;
+ ext4_lblk_t o_end, o_start = orig_blk;
+ ext4_lblk_t d_start = donor_blk;
+ int ret;
if (orig_inode->i_sb != donor_inode->i_sb) {
ext4_debug("ext4 move extent: The argument files "
@@ -1337,7 +588,7 @@
return -EINVAL;
}
/* Protect orig and donor inodes against a truncate */
- ext4_inode_double_lock(orig_inode, donor_inode);
+ lock_two_nondirectories(orig_inode, donor_inode);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(orig_inode);
@@ -1348,121 +599,58 @@
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
- ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
- donor_start, &len);
+ ret = mext_check_arguments(orig_inode, donor_inode, orig_blk,
+ donor_blk, &len);
if (ret)
goto out;
+ o_end = o_start + len;
- file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits;
- block_end = block_start + len - 1;
- if (file_end < block_end)
- len -= block_end - file_end;
+ while (o_start < o_end) {
+ struct ext4_extent *ex;
+ ext4_lblk_t cur_blk, next_blk;
+ pgoff_t orig_page_index, donor_page_index;
+ int offset_in_page;
+ int unwritten, cur_len;
- ret = get_ext_path(orig_inode, block_start, &orig_path);
- if (ret)
- goto out;
-
- /* Get path structure to check the hole */
- ret = get_ext_path(orig_inode, block_start, &holecheck_path);
- if (ret)
- goto out;
-
- depth = ext_depth(orig_inode);
- ext_cur = holecheck_path[depth].p_ext;
-
- /*
- * Get proper starting location of block replacement if block_start was
- * within the hole.
- */
- if (le32_to_cpu(ext_cur->ee_block) +
- ext4_ext_get_actual_len(ext_cur) - 1 < block_start) {
- /*
- * The hole exists between extents or the tail of
- * original file.
- */
- last_extent = mext_next_extent(orig_inode,
- holecheck_path, &ext_cur);
- if (last_extent < 0) {
- ret = last_extent;
+ ret = get_ext_path(orig_inode, o_start, &path);
+ if (ret)
goto out;
- }
- last_extent = mext_next_extent(orig_inode, orig_path,
- &ext_dummy);
- if (last_extent < 0) {
- ret = last_extent;
- goto out;
- }
- seq_start = le32_to_cpu(ext_cur->ee_block);
- } else if (le32_to_cpu(ext_cur->ee_block) > block_start)
- /* The hole exists at the beginning of original file. */
- seq_start = le32_to_cpu(ext_cur->ee_block);
- else
- seq_start = block_start;
-
- /* No blocks within the specified range. */
- if (le32_to_cpu(ext_cur->ee_block) > block_end) {
- ext4_debug("ext4 move extent: The specified range of file "
- "may be the hole\n");
- ret = -EINVAL;
- goto out;
- }
-
- /* Adjust start blocks */
- add_blocks = min(le32_to_cpu(ext_cur->ee_block) +
- ext4_ext_get_actual_len(ext_cur), block_end + 1) -
- max(le32_to_cpu(ext_cur->ee_block), block_start);
-
- while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) {
- seq_blocks += add_blocks;
-
- /* Adjust tail blocks */
- if (seq_start + seq_blocks - 1 > block_end)
- seq_blocks = block_end - seq_start + 1;
-
- ext_prev = ext_cur;
- last_extent = mext_next_extent(orig_inode, holecheck_path,
- &ext_cur);
- if (last_extent < 0) {
- ret = last_extent;
- break;
- }
- add_blocks = ext4_ext_get_actual_len(ext_cur);
-
- /*
- * Extend the length of contiguous block (seq_blocks)
- * if extents are contiguous.
- */
- if (ext4_can_extents_be_merged(orig_inode,
- ext_prev, ext_cur) &&
- block_end >= le32_to_cpu(ext_cur->ee_block) &&
- !last_extent)
+ ex = path[path->p_depth].p_ext;
+ next_blk = ext4_ext_next_allocated_block(path);
+ cur_blk = le32_to_cpu(ex->ee_block);
+ cur_len = ext4_ext_get_actual_len(ex);
+ /* Check hole before the start pos */
+ if (cur_blk + cur_len - 1 < o_start) {
+ if (next_blk == EXT_MAX_BLOCKS) {
+ o_start = o_end;
+ ret = -ENODATA;
+ goto out;
+ }
+ d_start += next_blk - o_start;
+ o_start = next_blk;
continue;
-
- /* Is original extent is uninitialized */
- uninit = ext4_ext_is_uninitialized(ext_prev);
-
- data_offset_in_page = seq_start % blocks_per_page;
-
- /*
- * Calculate data blocks count that should be swapped
- * at the first page.
- */
- if (data_offset_in_page + seq_blocks > blocks_per_page) {
- /* Swapped blocks are across pages */
- block_len_in_page =
- blocks_per_page - data_offset_in_page;
- } else {
- /* Swapped blocks are in a page */
- block_len_in_page = seq_blocks;
+ /* Check hole after the start pos */
+ } else if (cur_blk > o_start) {
+ /* Skip hole */
+ d_start += cur_blk - o_start;
+ o_start = cur_blk;
+ /* Extent inside requested range ?*/
+ if (cur_blk >= o_end)
+ goto out;
+ } else { /* in_range(o_start, o_blk, o_len) */
+ cur_len += cur_blk - o_start;
}
+ unwritten = ext4_ext_is_unwritten(ex);
+ if (o_end - o_start < cur_len)
+ cur_len = o_end - o_start;
- orig_page_offset = seq_start >>
- (PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
- seq_end_page = (seq_start + seq_blocks - 1) >>
- (PAGE_CACHE_SHIFT - orig_inode->i_blkbits);
- seq_start = le32_to_cpu(ext_cur->ee_block);
- rest_blocks = seq_blocks;
-
+ orig_page_index = o_start >> (PAGE_CACHE_SHIFT -
+ orig_inode->i_blkbits);
+ donor_page_index = d_start >> (PAGE_CACHE_SHIFT -
+ donor_inode->i_blkbits);
+ offset_in_page = o_start % blocks_per_page;
+ if (cur_len > blocks_per_page- offset_in_page)
+ cur_len = blocks_per_page - offset_in_page;
/*
* Up semaphore to avoid following problems:
* a. transaction deadlock among ext4_journal_start,
@@ -1471,81 +659,33 @@
* in move_extent_per_page
*/
ext4_double_up_write_data_sem(orig_inode, donor_inode);
-
- while (orig_page_offset <= seq_end_page) {
-
- /* Swap original branches with new branches */
- block_len_in_page = move_extent_per_page(
- o_filp, donor_inode,
- orig_page_offset,
- data_offset_in_page,
- block_len_in_page, uninit,
- &ret);
-
- /* Count how many blocks we have exchanged */
- *moved_len += block_len_in_page;
- if (ret < 0)
- break;
- if (*moved_len > len) {
- EXT4_ERROR_INODE(orig_inode,
- "We replaced blocks too much! "
- "sum of replaced: %llu requested: %llu",
- *moved_len, len);
- ret = -EIO;
- break;
- }
-
- orig_page_offset++;
- data_offset_in_page = 0;
- rest_blocks -= block_len_in_page;
- if (rest_blocks > blocks_per_page)
- block_len_in_page = blocks_per_page;
- else
- block_len_in_page = rest_blocks;
- }
-
+ /* Swap original branches with new branches */
+ move_extent_per_page(o_filp, donor_inode,
+ orig_page_index, donor_page_index,
+ offset_in_page, cur_len,
+ unwritten, &ret);
ext4_double_down_write_data_sem(orig_inode, donor_inode);
if (ret < 0)
break;
-
- /* Decrease buffer counter */
- if (holecheck_path)
- ext4_ext_drop_refs(holecheck_path);
- ret = get_ext_path(orig_inode, seq_start, &holecheck_path);
- if (ret)
- break;
- depth = holecheck_path->p_depth;
-
- /* Decrease buffer counter */
- if (orig_path)
- ext4_ext_drop_refs(orig_path);
- ret = get_ext_path(orig_inode, seq_start, &orig_path);
- if (ret)
- break;
-
- ext_cur = holecheck_path[depth].p_ext;
- add_blocks = ext4_ext_get_actual_len(ext_cur);
- seq_blocks = 0;
-
+ o_start += cur_len;
+ d_start += cur_len;
}
+ *moved_len = o_start - orig_blk;
+ if (*moved_len > len)
+ *moved_len = len;
+
out:
if (*moved_len) {
ext4_discard_preallocations(orig_inode);
ext4_discard_preallocations(donor_inode);
}
- if (orig_path) {
- ext4_ext_drop_refs(orig_path);
- kfree(orig_path);
- }
- if (holecheck_path) {
- ext4_ext_drop_refs(holecheck_path);
- kfree(holecheck_path);
- }
+ ext4_ext_drop_refs(path);
+ kfree(path);
ext4_double_up_write_data_sem(orig_inode, donor_inode);
ext4_inode_resume_unlocked_dio(orig_inode);
ext4_inode_resume_unlocked_dio(donor_inode);
- ext4_inode_double_unlock(orig_inode, donor_inode);
+ unlock_two_nondirectories(orig_inode, donor_inode);
return ret;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index facf8590..a57ef7d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -53,7 +53,7 @@
ext4_lblk_t *block)
{
struct buffer_head *bh;
- int err = 0;
+ int err;
if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb &&
((inode->i_size >> 10) >=
@@ -62,11 +62,12 @@
*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
- bh = ext4_bread(handle, inode, *block, 1, &err);
- if (!bh)
- return ERR_PTR(err);
+ bh = ext4_bread(handle, inode, *block, 1);
+ if (IS_ERR(bh))
+ return bh;
inode->i_size += inode->i_sb->s_blocksize;
EXT4_I(inode)->i_disksize = inode->i_size;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
@@ -93,20 +94,20 @@
{
struct buffer_head *bh;
struct ext4_dir_entry *dirent;
- int err = 0, is_dx_block = 0;
+ int is_dx_block = 0;
- bh = ext4_bread(NULL, inode, block, 0, &err);
- if (!bh) {
- if (err == 0) {
- ext4_error_inode(inode, __func__, line, block,
- "Directory hole found");
- return ERR_PTR(-EIO);
- }
+ bh = ext4_bread(NULL, inode, block, 0);
+ if (IS_ERR(bh)) {
__ext4_warning(inode->i_sb, __func__, line,
- "error reading directory block "
- "(ino %lu, block %lu)", inode->i_ino,
+ "error %ld reading directory block "
+ "(ino %lu, block %lu)", PTR_ERR(bh), inode->i_ino,
(unsigned long) block);
- return ERR_PTR(err);
+
+ return bh;
+ }
+ if (!bh) {
+ ext4_error_inode(inode, __func__, line, block, "Directory hole found");
+ return ERR_PTR(-EIO);
}
dirent = (struct ext4_dir_entry *) bh->b_data;
/* Determine whether or not we have an index block */
@@ -123,8 +124,7 @@
"directory leaf block found instead of index block");
return ERR_PTR(-EIO);
}
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) ||
+ if (!ext4_has_metadata_csum(inode->i_sb) ||
buffer_verified(bh))
return bh;
@@ -249,14 +249,14 @@
static void dx_set_limit(struct dx_entry *entries, unsigned value);
static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
static unsigned dx_node_limit(struct inode *dir);
-static struct dx_frame *dx_probe(const struct qstr *d_name,
+static struct dx_frame *dx_probe(struct ext4_filename *fname,
struct inode *dir,
struct dx_hash_info *hinfo,
- struct dx_frame *frame,
- int *err);
+ struct dx_frame *frame);
static void dx_release(struct dx_frame *frames);
-static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
- struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
+ unsigned blocksize, struct dx_hash_info *hinfo,
+ struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
struct dx_map_entry *offsets, int count, unsigned blocksize);
@@ -268,11 +268,10 @@
struct dx_frame *frames,
__u32 *start_hash);
static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
- const struct qstr *d_name,
- struct ext4_dir_entry_2 **res_dir,
- int *err);
-static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
- struct inode *inode);
+ struct ext4_filename *fname,
+ struct ext4_dir_entry_2 **res_dir);
+static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
+ struct dentry *dentry, struct inode *inode);
/* checksumming functions */
void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
@@ -339,8 +338,7 @@
{
struct ext4_dir_entry_tail *t;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return 1;
t = get_dirent_tail(inode, dirent);
@@ -361,8 +359,7 @@
{
struct ext4_dir_entry_tail *t;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return;
t = get_dirent_tail(inode, dirent);
@@ -437,8 +434,7 @@
struct dx_tail *t;
int count_offset, limit, count;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return 1;
c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -467,8 +463,7 @@
struct dx_tail *t;
int count_offset, limit, count;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return;
c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -556,8 +551,7 @@
unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
EXT4_DIR_REC_LEN(2) - infosize;
- if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
return entry_space / sizeof(struct dx_entry);
}
@@ -566,8 +560,7 @@
{
unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
- if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
return entry_space / sizeof(struct dx_entry);
}
@@ -594,8 +587,10 @@
unsigned bcount;
};
-static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de,
- int size, int show_names)
+static struct stats dx_show_leaf(struct inode *dir,
+ struct dx_hash_info *hinfo,
+ struct ext4_dir_entry_2 *de,
+ int size, int show_names)
{
unsigned names = 0, space = 0;
char *base = (char *) de;
@@ -608,12 +603,69 @@
{
if (show_names)
{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ int len;
+ char *name;
+ struct ext4_str fname_crypto_str
+ = {.name = NULL, .len = 0};
+ int res = 0;
+
+ name = de->name;
+ len = de->name_len;
+ if (ext4_encrypted_inode(inode))
+ res = ext4_get_encryption_info(dir);
+ if (res) {
+ printk(KERN_WARNING "Error setting up"
+ " fname crypto: %d\n", res);
+ }
+ if (ctx == NULL) {
+ /* Directory is not encrypted */
+ ext4fs_dirhash(de->name,
+ de->name_len, &h);
+ printk("%*.s:(U)%x.%u ", len,
+ name, h.hash,
+ (unsigned) ((char *) de
+ - base));
+ } else {
+ /* Directory is encrypted */
+ res = ext4_fname_crypto_alloc_buffer(
+ ctx, de->name_len,
+ &fname_crypto_str);
+ if (res < 0) {
+ printk(KERN_WARNING "Error "
+ "allocating crypto "
+ "buffer--skipping "
+ "crypto\n");
+ ctx = NULL;
+ }
+ res = ext4_fname_disk_to_usr(ctx, NULL, de,
+ &fname_crypto_str);
+ if (res < 0) {
+ printk(KERN_WARNING "Error "
+ "converting filename "
+ "from disk to usr"
+ "\n");
+ name = "??";
+ len = 2;
+ } else {
+ name = fname_crypto_str.name;
+ len = fname_crypto_str.len;
+ }
+ ext4fs_dirhash(de->name, de->name_len,
+ &h);
+ printk("%*.s:(E)%x.%u ", len, name,
+ h.hash, (unsigned) ((char *) de
+ - base));
+ ext4_fname_crypto_free_buffer(
+ &fname_crypto_str);
+ }
+#else
int len = de->name_len;
char *name = de->name;
- while (len--) printk("%c", *name++);
ext4fs_dirhash(de->name, de->name_len, &h);
- printk(":%x.%u ", h.hash,
+ printk("%*.s:%x.%u ", len, name, h.hash,
(unsigned) ((char *) de - base));
+#endif
}
space += EXT4_DIR_REC_LEN(de->name_len);
names++;
@@ -631,7 +683,6 @@
unsigned count = dx_get_count(entries), names = 0, space = 0, i;
unsigned bcount = 0;
struct buffer_head *bh;
- int err;
printk("%i indexed blocks...\n", count);
for (i = 0; i < count; i++, entries++)
{
@@ -640,10 +691,13 @@
u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
struct stats stats;
printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range);
- if (!(bh = ext4_bread (NULL,dir, block, 0,&err))) continue;
+ bh = ext4_bread(NULL,dir, block, 0);
+ if (!bh || IS_ERR(bh))
+ continue;
stats = levels?
dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
- dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0);
+ dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *)
+ bh->b_data, blocksize, 0);
names += stats.names;
space += stats.space;
bcount += stats.bcount;
@@ -667,53 +721,47 @@
* back to userspace.
*/
static struct dx_frame *
-dx_probe(const struct qstr *d_name, struct inode *dir,
- struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
+dx_probe(struct ext4_filename *fname, struct inode *dir,
+ struct dx_hash_info *hinfo, struct dx_frame *frame_in)
{
unsigned count, indirect;
struct dx_entry *at, *entries, *p, *q, *m;
struct dx_root *root;
- struct buffer_head *bh;
struct dx_frame *frame = frame_in;
+ struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
u32 hash;
- frame->bh = NULL;
- bh = ext4_read_dirblock(dir, 0, INDEX);
- if (IS_ERR(bh)) {
- *err = PTR_ERR(bh);
- goto fail;
- }
- root = (struct dx_root *) bh->b_data;
+ frame->bh = ext4_read_dirblock(dir, 0, INDEX);
+ if (IS_ERR(frame->bh))
+ return (struct dx_frame *) frame->bh;
+
+ root = (struct dx_root *) frame->bh->b_data;
if (root->info.hash_version != DX_HASH_TEA &&
root->info.hash_version != DX_HASH_HALF_MD4 &&
root->info.hash_version != DX_HASH_LEGACY) {
ext4_warning(dir->i_sb, "Unrecognised inode hash code %d",
root->info.hash_version);
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
goto fail;
}
+ if (fname)
+ hinfo = &fname->hinfo;
hinfo->hash_version = root->info.hash_version;
if (hinfo->hash_version <= DX_HASH_TEA)
hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
- if (d_name)
- ext4fs_dirhash(d_name->name, d_name->len, hinfo);
+ if (fname && fname_name(fname))
+ ext4fs_dirhash(fname_name(fname), fname_len(fname), hinfo);
hash = hinfo->hash;
if (root->info.unused_flags & 1) {
ext4_warning(dir->i_sb, "Unimplemented inode hash flags: %#06x",
root->info.unused_flags);
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
goto fail;
}
if ((indirect = root->info.indirect_levels) > 1) {
ext4_warning(dir->i_sb, "Unimplemented inode hash depth: %#06x",
root->info.indirect_levels);
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
goto fail;
}
@@ -723,27 +771,21 @@
if (dx_get_limit(entries) != dx_root_limit(dir,
root->info.info_length)) {
ext4_warning(dir->i_sb, "dx entry: limit != root limit");
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
goto fail;
}
dxtrace(printk("Look up %x", hash));
- while (1)
- {
+ while (1) {
count = dx_get_count(entries);
if (!count || count > dx_get_limit(entries)) {
ext4_warning(dir->i_sb,
"dx entry: no count or count > limit");
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
- goto fail2;
+ goto fail;
}
p = entries + 1;
q = entries + count - 1;
- while (p <= q)
- {
+ while (p <= q) {
m = p + (q - p)/2;
dxtrace(printk("."));
if (dx_get_hash(m) > hash)
@@ -752,8 +794,7 @@
p = m + 1;
}
- if (0) // linear search cross check
- {
+ if (0) { // linear search cross check
unsigned n = count - 1;
at = entries;
while (n--)
@@ -770,38 +811,36 @@
at = p - 1;
dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at)));
- frame->bh = bh;
frame->entries = entries;
frame->at = at;
- if (!indirect--) return frame;
- bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
- if (IS_ERR(bh)) {
- *err = PTR_ERR(bh);
- goto fail2;
+ if (!indirect--)
+ return frame;
+ frame++;
+ frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
+ if (IS_ERR(frame->bh)) {
+ ret_err = (struct dx_frame *) frame->bh;
+ frame->bh = NULL;
+ goto fail;
}
- entries = ((struct dx_node *) bh->b_data)->entries;
+ entries = ((struct dx_node *) frame->bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit (dir)) {
ext4_warning(dir->i_sb,
"dx entry: limit != node limit");
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
- goto fail2;
+ goto fail;
}
- frame++;
- frame->bh = NULL;
}
-fail2:
+fail:
while (frame >= frame_in) {
brelse(frame->bh);
frame--;
}
-fail:
- if (*err == ERR_BAD_DX_DIR)
+
+ if (ret_err == ERR_PTR(ERR_BAD_DX_DIR))
ext4_warning(dir->i_sb,
"Corrupt dir inode %lu, running e2fsck is "
"recommended.", dir->i_ino);
- return NULL;
+ return ret_err;
}
static void dx_release (struct dx_frame *frames)
@@ -902,6 +941,7 @@
struct buffer_head *bh;
struct ext4_dir_entry_2 *de, *top;
int err = 0, count = 0;
+ struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}, tmp_str;
dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
(unsigned long)block));
@@ -913,6 +953,22 @@
top = (struct ext4_dir_entry_2 *) ((char *) de +
dir->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(0));
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ /* Check if the directory is encrypted */
+ if (ext4_encrypted_inode(dir)) {
+ err = ext4_get_encryption_info(dir);
+ if (err < 0) {
+ brelse(bh);
+ return err;
+ }
+ err = ext4_fname_crypto_alloc_buffer(dir, EXT4_NAME_LEN,
+ &fname_crypto_str);
+ if (err < 0) {
+ brelse(bh);
+ return err;
+ }
+ }
+#endif
for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
bh->b_data, bh->b_size,
@@ -928,14 +984,38 @@
continue;
if (de->inode == 0)
continue;
- if ((err = ext4_htree_store_dirent(dir_file,
- hinfo->hash, hinfo->minor_hash, de)) != 0) {
- brelse(bh);
- return err;
+ if (!ext4_encrypted_inode(dir)) {
+ tmp_str.name = de->name;
+ tmp_str.len = de->name_len;
+ err = ext4_htree_store_dirent(dir_file,
+ hinfo->hash, hinfo->minor_hash, de,
+ &tmp_str);
+ } else {
+ int save_len = fname_crypto_str.len;
+
+ /* Directory is encrypted */
+ err = ext4_fname_disk_to_usr(dir, hinfo, de,
+ &fname_crypto_str);
+ if (err < 0) {
+ count = err;
+ goto errout;
+ }
+ err = ext4_htree_store_dirent(dir_file,
+ hinfo->hash, hinfo->minor_hash, de,
+ &fname_crypto_str);
+ fname_crypto_str.len = save_len;
+ }
+ if (err != 0) {
+ count = err;
+ goto errout;
}
count++;
}
+errout:
brelse(bh);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ ext4_fname_crypto_free_buffer(&fname_crypto_str);
+#endif
return count;
}
@@ -959,6 +1039,7 @@
int count = 0;
int ret, err;
__u32 hashval;
+ struct ext4_str tmp_str;
dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
start_hash, start_minor_hash));
@@ -987,21 +1068,29 @@
}
hinfo.hash = start_hash;
hinfo.minor_hash = 0;
- frame = dx_probe(NULL, dir, &hinfo, frames, &err);
- if (!frame)
- return err;
+ frame = dx_probe(NULL, dir, &hinfo, frames);
+ if (IS_ERR(frame))
+ return PTR_ERR(frame);
/* Add '.' and '..' from the htree header */
if (!start_hash && !start_minor_hash) {
de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
- if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0)
+ tmp_str.name = de->name;
+ tmp_str.len = de->name_len;
+ err = ext4_htree_store_dirent(dir_file, 0, 0,
+ de, &tmp_str);
+ if (err != 0)
goto errout;
count++;
}
if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
de = ext4_next_entry(de, dir->i_sb->s_blocksize);
- if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0)
+ tmp_str.name = de->name;
+ tmp_str.len = de->name_len;
+ err = ext4_htree_store_dirent(dir_file, 2, 0,
+ de, &tmp_str);
+ if (err != 0)
goto errout;
count++;
}
@@ -1043,12 +1132,13 @@
static inline int search_dirblock(struct buffer_head *bh,
struct inode *dir,
+ struct ext4_filename *fname,
const struct qstr *d_name,
unsigned int offset,
struct ext4_dir_entry_2 **res_dir)
{
- return search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
- d_name, offset, res_dir);
+ return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
+ fname, d_name, offset, res_dir);
}
/*
@@ -1059,8 +1149,8 @@
* Create map of hash values, offsets, and sizes, stored at end of block.
* Returns number of entries mapped.
*/
-static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
- struct dx_hash_info *hinfo,
+static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
+ unsigned blocksize, struct dx_hash_info *hinfo,
struct dx_map_entry *map_tail)
{
int count = 0;
@@ -1130,57 +1220,87 @@
* `len <= EXT4_NAME_LEN' is guaranteed by caller.
* `de != NULL' is guaranteed by caller.
*/
-static inline int ext4_match (int len, const char * const name,
- struct ext4_dir_entry_2 * de)
+static inline int ext4_match(struct ext4_filename *fname,
+ struct ext4_dir_entry_2 *de)
{
- if (len != de->name_len)
- return 0;
+ const void *name = fname_name(fname);
+ u32 len = fname_len(fname);
+
if (!de->inode)
return 0;
- return !memcmp(name, de->name, len);
+
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (unlikely(!name)) {
+ if (fname->usr_fname->name[0] == '_') {
+ int ret;
+ if (de->name_len < 16)
+ return 0;
+ ret = memcmp(de->name + de->name_len - 16,
+ fname->crypto_buf.name + 8, 16);
+ return (ret == 0) ? 1 : 0;
+ }
+ name = fname->crypto_buf.name;
+ len = fname->crypto_buf.len;
+ }
+#endif
+ if (de->name_len != len)
+ return 0;
+ return (memcmp(de->name, name, len) == 0) ? 1 : 0;
}
/*
* Returns 0 if not found, -1 on failure, and 1 on success
*/
-int search_dir(struct buffer_head *bh,
- char *search_buf,
- int buf_size,
- struct inode *dir,
- const struct qstr *d_name,
- unsigned int offset,
- struct ext4_dir_entry_2 **res_dir)
+int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
+ struct inode *dir, struct ext4_filename *fname,
+ const struct qstr *d_name,
+ unsigned int offset, struct ext4_dir_entry_2 **res_dir)
{
struct ext4_dir_entry_2 * de;
char * dlimit;
int de_len;
- const char *name = d_name->name;
- int namelen = d_name->len;
+ int res;
de = (struct ext4_dir_entry_2 *)search_buf;
dlimit = search_buf + buf_size;
while ((char *) de < dlimit) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
+ if ((char *) de + de->name_len <= dlimit) {
+ res = ext4_match(fname, de);
+ if (res < 0) {
+ res = -1;
+ goto return_result;
+ }
+ if (res > 0) {
+ /* found a match - just to be sure, do
+ * a full check */
+ if (ext4_check_dir_entry(dir, NULL, de, bh,
+ bh->b_data,
+ bh->b_size, offset)) {
+ res = -1;
+ goto return_result;
+ }
+ *res_dir = de;
+ res = 1;
+ goto return_result;
+ }
- if ((char *) de + namelen <= dlimit &&
- ext4_match (namelen, name, de)) {
- /* found a match - just to be sure, do a full check */
- if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
- bh->b_size, offset))
- return -1;
- *res_dir = de;
- return 1;
}
/* prevent looping on a bad block */
de_len = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
- if (de_len <= 0)
- return -1;
+ if (de_len <= 0) {
+ res = -1;
+ goto return_result;
+ }
offset += de_len;
de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
}
- return 0;
+
+ res = 0;
+return_result:
+ return res;
}
static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block,
@@ -1226,8 +1346,8 @@
buffer */
int num = 0;
ext4_lblk_t nblocks;
- int i, err;
- int namelen;
+ int i, namelen, retval;
+ struct ext4_filename fname;
*res_dir = NULL;
sb = dir->i_sb;
@@ -1235,14 +1355,18 @@
if (namelen > EXT4_NAME_LEN)
return NULL;
+ retval = ext4_fname_setup_filename(dir, d_name, 1, &fname);
+ if (retval)
+ return ERR_PTR(retval);
+
if (ext4_has_inline_data(dir)) {
int has_inline_data = 1;
- ret = ext4_find_inline_entry(dir, d_name, res_dir,
+ ret = ext4_find_inline_entry(dir, &fname, d_name, res_dir,
&has_inline_data);
if (has_inline_data) {
if (inlined)
*inlined = 1;
- return ret;
+ goto cleanup_and_exit;
}
}
@@ -1257,14 +1381,14 @@
goto restart;
}
if (is_dx(dir)) {
- bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
+ ret = ext4_dx_find_entry(dir, &fname, res_dir);
/*
* On success, or if the error was file not found,
* return. Otherwise, fall back to doing a search the
* old fashioned way.
*/
- if (bh || (err != ERR_BAD_DX_DIR))
- return bh;
+ if (!IS_ERR(ret) || PTR_ERR(ret) != ERR_BAD_DX_DIR)
+ goto cleanup_and_exit;
dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
"falling back\n"));
}
@@ -1293,7 +1417,14 @@
break;
}
num++;
- bh = ext4_getblk(NULL, dir, b++, 0, &err);
+ bh = ext4_getblk(NULL, dir, b++, 0);
+ if (unlikely(IS_ERR(bh))) {
+ if (ra_max == 0) {
+ ret = bh;
+ goto cleanup_and_exit;
+ }
+ break;
+ }
bh_use[ra_max] = bh;
if (bh)
ll_rw_block(READ | REQ_META | REQ_PRIO,
@@ -1321,7 +1452,7 @@
goto next;
}
set_buffer_verified(bh);
- i = search_dirblock(bh, dir, d_name,
+ i = search_dirblock(bh, dir, &fname, d_name,
block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
if (i == 1) {
EXT4_I(dir)->i_dir_start_lookup = block;
@@ -1352,58 +1483,62 @@
/* Clean up the read-ahead blocks */
for (; ra_ptr < ra_max; ra_ptr++)
brelse(bh_use[ra_ptr]);
+ ext4_fname_free_filename(&fname);
return ret;
}
-static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
- struct ext4_dir_entry_2 **res_dir, int *err)
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
+ struct ext4_filename *fname,
+ struct ext4_dir_entry_2 **res_dir)
{
struct super_block * sb = dir->i_sb;
- struct dx_hash_info hinfo;
struct dx_frame frames[2], *frame;
+ const struct qstr *d_name = fname->usr_fname;
struct buffer_head *bh;
ext4_lblk_t block;
int retval;
- if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
- return NULL;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ *res_dir = NULL;
+#endif
+ frame = dx_probe(fname, dir, NULL, frames);
+ if (IS_ERR(frame))
+ return (struct buffer_head *) frame;
do {
block = dx_get_block(frame->at);
bh = ext4_read_dirblock(dir, block, DIRENT);
- if (IS_ERR(bh)) {
- *err = PTR_ERR(bh);
+ if (IS_ERR(bh))
goto errout;
- }
- retval = search_dirblock(bh, dir, d_name,
+
+ retval = search_dirblock(bh, dir, fname, d_name,
block << EXT4_BLOCK_SIZE_BITS(sb),
res_dir);
- if (retval == 1) { /* Success! */
- dx_release(frames);
- return bh;
- }
+ if (retval == 1)
+ goto success;
brelse(bh);
if (retval == -1) {
- *err = ERR_BAD_DX_DIR;
+ bh = ERR_PTR(ERR_BAD_DX_DIR);
goto errout;
}
/* Check to see if we should continue to search */
- retval = ext4_htree_next_block(dir, hinfo.hash, frame,
+ retval = ext4_htree_next_block(dir, fname->hinfo.hash, frame,
frames, NULL);
if (retval < 0) {
ext4_warning(sb,
- "error reading index page in directory #%lu",
- dir->i_ino);
- *err = retval;
+ "error %d reading index page in directory #%lu",
+ retval, dir->i_ino);
+ bh = ERR_PTR(retval);
goto errout;
}
} while (retval == 1);
- *err = -ENOENT;
+ bh = NULL;
errout:
dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
- dx_release (frames);
- return NULL;
+success:
+ dx_release(frames);
+ return bh;
}
static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
@@ -1416,6 +1551,8 @@
return ERR_PTR(-ENAMETOOLONG);
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+ if (IS_ERR(bh))
+ return (struct dentry *) bh;
inode = NULL;
if (bh) {
__u32 ino = le32_to_cpu(de->inode);
@@ -1425,9 +1562,8 @@
return ERR_PTR(-EIO);
}
if (unlikely(ino == dir->i_ino)) {
- EXT4_ERROR_INODE(dir, "'%.*s' linked to parent dir",
- dentry->d_name.len,
- dentry->d_name.name);
+ EXT4_ERROR_INODE(dir, "'%pd' linked to parent dir",
+ dentry);
return ERR_PTR(-EIO);
}
inode = ext4_iget_normal(dir->i_sb, ino);
@@ -1437,6 +1573,18 @@
ino);
return ERR_PTR(-EIO);
}
+ if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)) &&
+ !ext4_is_child_context_consistent_with_parent(dir,
+ inode)) {
+ iput(inode);
+ ext4_warning(inode->i_sb,
+ "Inconsistent encryption contexts: %lu/%lu\n",
+ (unsigned long) dir->i_ino,
+ (unsigned long) inode->i_ino);
+ return ERR_PTR(-EPERM);
+ }
}
return d_splice_alias(inode, dentry);
}
@@ -1450,6 +1598,8 @@
struct buffer_head *bh;
bh = ext4_find_entry(child->d_inode, &dotdot, &de, NULL);
+ if (IS_ERR(bh))
+ return (struct dentry *) bh;
if (!bh)
return ERR_PTR(-ENOENT);
ino = le32_to_cpu(de->inode);
@@ -1520,7 +1670,7 @@
*/
static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
struct buffer_head **bh,struct dx_frame *frame,
- struct dx_hash_info *hinfo, int *error)
+ struct dx_hash_info *hinfo)
{
unsigned blocksize = dir->i_sb->s_blocksize;
unsigned count, continued;
@@ -1535,16 +1685,14 @@
int csum_size = 0;
int err = 0, i;
- if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(dir->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
bh2 = ext4_append(handle, dir, &newblock);
if (IS_ERR(bh2)) {
brelse(*bh);
*bh = NULL;
- *error = PTR_ERR(bh2);
- return NULL;
+ return (struct ext4_dir_entry_2 *) bh2;
}
BUFFER_TRACE(*bh, "get_write_access");
@@ -1561,7 +1709,7 @@
/* create map in the end of data2 block */
map = (struct dx_map_entry *) (data2 + blocksize);
- count = dx_make_map((struct ext4_dir_entry_2 *) data1,
+ count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1,
blocksize, hinfo, map);
map -= count;
dx_sort_map(map, count);
@@ -1584,7 +1732,8 @@
hash2, split, count-split));
/* Fancy dance to stay within two buffers */
- de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize);
+ de2 = dx_move_dirents(data1, data2, map + split, count - split,
+ blocksize);
de = dx_pack_dirents(data1, blocksize);
de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) -
(char *) de,
@@ -1600,12 +1749,13 @@
initialize_dirent_tail(t, blocksize);
}
- dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
- dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
+ dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1,
+ blocksize, 1));
+ dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data2,
+ blocksize, 1));
/* Which block gets the new entry? */
- if (hinfo->hash >= hash2)
- {
+ if (hinfo->hash >= hash2) {
swap(*bh, bh2);
de = de2;
}
@@ -1625,30 +1775,38 @@
brelse(bh2);
*bh = NULL;
ext4_std_error(dir->i_sb, err);
- *error = err;
- return NULL;
+ return ERR_PTR(err);
}
int ext4_find_dest_de(struct inode *dir, struct inode *inode,
struct buffer_head *bh,
void *buf, int buf_size,
- const char *name, int namelen,
+ struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de)
{
struct ext4_dir_entry_2 *de;
- unsigned short reclen = EXT4_DIR_REC_LEN(namelen);
+ unsigned short reclen = EXT4_DIR_REC_LEN(fname_len(fname));
int nlen, rlen;
unsigned int offset = 0;
char *top;
+ int res;
de = (struct ext4_dir_entry_2 *)buf;
top = buf + buf_size - reclen;
while ((char *) de <= top) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
- buf, buf_size, offset))
- return -EIO;
- if (ext4_match(namelen, name, de))
- return -EEXIST;
+ buf, buf_size, offset)) {
+ res = -EIO;
+ goto return_result;
+ }
+ /* Provide crypto context and crypto buffer to ext4 match */
+ res = ext4_match(fname, de);
+ if (res < 0)
+ goto return_result;
+ if (res > 0) {
+ res = -EEXIST;
+ goto return_result;
+ }
nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
if ((de->inode ? rlen - nlen : rlen) >= reclen)
@@ -1656,17 +1814,22 @@
de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
offset += rlen;
}
- if ((char *) de > top)
- return -ENOSPC;
- *dest_de = de;
- return 0;
+ if ((char *) de > top)
+ res = -ENOSPC;
+ else {
+ *dest_de = de;
+ res = 0;
+ }
+return_result:
+ return res;
}
-void ext4_insert_dentry(struct inode *inode,
- struct ext4_dir_entry_2 *de,
- int buf_size,
- const char *name, int namelen)
+int ext4_insert_dentry(struct inode *dir,
+ struct inode *inode,
+ struct ext4_dir_entry_2 *de,
+ int buf_size,
+ struct ext4_filename *fname)
{
int nlen, rlen;
@@ -1675,7 +1838,7 @@
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
if (de->inode) {
struct ext4_dir_entry_2 *de1 =
- (struct ext4_dir_entry_2 *)((char *)de + nlen);
+ (struct ext4_dir_entry_2 *)((char *)de + nlen);
de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, buf_size);
de->rec_len = ext4_rec_len_to_disk(nlen, buf_size);
de = de1;
@@ -1683,9 +1846,11 @@
de->file_type = EXT4_FT_UNKNOWN;
de->inode = cpu_to_le32(inode->i_ino);
ext4_set_de_type(inode->i_sb, de, inode->i_mode);
- de->name_len = namelen;
- memcpy(de->name, name, namelen);
+ de->name_len = fname_len(fname);
+ memcpy(de->name, fname_name(fname), fname_len(fname));
+ return 0;
}
+
/*
* Add a new entry into a directory (leaf) block. If de is non-NULL,
* it points to a directory entry which is guaranteed to be large
@@ -1694,25 +1859,21 @@
* space. It will return -ENOSPC if no space is available, and -EIO
* and -EEXIST if directory entry already exists.
*/
-static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
+static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
+ struct inode *dir,
struct inode *inode, struct ext4_dir_entry_2 *de,
struct buffer_head *bh)
{
- struct inode *dir = dentry->d_parent->d_inode;
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
unsigned int blocksize = dir->i_sb->s_blocksize;
int csum_size = 0;
int err;
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
if (!de) {
- err = ext4_find_dest_de(dir, inode,
- bh, bh->b_data, blocksize - csum_size,
- name, namelen, &de);
+ err = ext4_find_dest_de(dir, inode, bh, bh->b_data,
+ blocksize - csum_size, fname, &de);
if (err)
return err;
}
@@ -1723,8 +1884,11 @@
return err;
}
- /* By now the buffer is marked for journaling */
- ext4_insert_dentry(inode, de, blocksize, name, namelen);
+ /* By now the buffer is marked for journaling. Due to crypto operations,
+ * the following function call may fail */
+ err = ext4_insert_dentry(dir, inode, de, blocksize, fname);
+ if (err < 0)
+ return err;
/*
* XXX shouldn't update any times until successful
@@ -1752,12 +1916,11 @@
* This converts a one block unindexed directory to a 3 block indexed
* directory, and adds the dentry to the indexed directory.
*/
-static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
+static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
+ struct dentry *dentry,
struct inode *inode, struct buffer_head *bh)
{
struct inode *dir = dentry->d_parent->d_inode;
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
struct buffer_head *bh2;
struct dx_root *root;
struct dx_frame frames[2], *frame;
@@ -1768,17 +1931,16 @@
unsigned len;
int retval;
unsigned blocksize;
- struct dx_hash_info hinfo;
ext4_lblk_t block;
struct fake_dirent *fde;
- int csum_size = 0;
+ int csum_size = 0;
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
blocksize = dir->i_sb->s_blocksize;
dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
+ BUFFER_TRACE(bh, "get_write_access");
retval = ext4_journal_get_write_access(handle, bh);
if (retval) {
ext4_std_error(dir->i_sb, retval);
@@ -1834,36 +1996,45 @@
dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));
/* Initialize as for dx_probe */
- hinfo.hash_version = root->info.hash_version;
- if (hinfo.hash_version <= DX_HASH_TEA)
- hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
- hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
- ext4fs_dirhash(name, namelen, &hinfo);
+ fname->hinfo.hash_version = root->info.hash_version;
+ if (fname->hinfo.hash_version <= DX_HASH_TEA)
+ fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
+ fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+ ext4fs_dirhash(fname_name(fname), fname_len(fname), &fname->hinfo);
+
+ memset(frames, 0, sizeof(frames));
frame = frames;
frame->entries = entries;
frame->at = entries;
frame->bh = bh;
bh = bh2;
- ext4_handle_dirty_dx_node(handle, dir, frame->bh);
- ext4_handle_dirty_dirent_node(handle, dir, bh);
+ retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
+ if (retval)
+ goto out_frames;
+ retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+ if (retval)
+ goto out_frames;
- de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
- if (!de) {
- /*
- * Even if the block split failed, we have to properly write
- * out all the changes we did so far. Otherwise we can end up
- * with corrupted filesystem.
- */
- ext4_mark_inode_dirty(handle, dir);
- dx_release(frames);
- return retval;
+ de = do_split(handle,dir, &bh, frame, &fname->hinfo);
+ if (IS_ERR(de)) {
+ retval = PTR_ERR(de);
+ goto out_frames;
}
dx_release(frames);
- retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
brelse(bh);
return retval;
+out_frames:
+ /*
+ * Even if the block split failed, we have to properly write
+ * out all the changes we did so far. Otherwise we can end up
+ * with corrupted filesystem.
+ */
+ ext4_mark_inode_dirty(handle, dir);
+ dx_release(frames);
+ return retval;
}
/*
@@ -1884,14 +2055,14 @@
struct ext4_dir_entry_2 *de;
struct ext4_dir_entry_tail *t;
struct super_block *sb;
+ struct ext4_filename fname;
int retval;
int dx_fallback=0;
unsigned blocksize;
ext4_lblk_t block, blocks;
int csum_size = 0;
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
sb = dir->i_sb;
@@ -1899,10 +2070,15 @@
if (!dentry->d_name.len)
return -EINVAL;
+ retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
+ if (retval)
+ return retval;
+
if (ext4_has_inline_data(dir)) {
- retval = ext4_try_add_inline_entry(handle, dentry, inode);
+ retval = ext4_try_add_inline_entry(handle, &fname,
+ dentry, inode);
if (retval < 0)
- return retval;
+ goto out;
if (retval == 1) {
retval = 0;
goto out;
@@ -1910,7 +2086,7 @@
}
if (is_dx(dir)) {
- retval = ext4_dx_add_entry(handle, dentry, inode);
+ retval = ext4_dx_add_entry(handle, &fname, dentry, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
goto out;
ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
@@ -1920,24 +2096,31 @@
blocks = dir->i_size >> sb->s_blocksize_bits;
for (block = 0; block < blocks; block++) {
bh = ext4_read_dirblock(dir, block, DIRENT);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
-
- retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+ if (IS_ERR(bh)) {
+ retval = PTR_ERR(bh);
+ bh = NULL;
+ goto out;
+ }
+ retval = add_dirent_to_buf(handle, &fname, dir, inode,
+ NULL, bh);
if (retval != -ENOSPC)
goto out;
if (blocks == 1 && !dx_fallback &&
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
- retval = make_indexed_dir(handle, dentry, inode, bh);
+ retval = make_indexed_dir(handle, &fname, dentry,
+ inode, bh);
bh = NULL; /* make_indexed_dir releases bh */
goto out;
}
brelse(bh);
}
bh = ext4_append(handle, dir, &block);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
+ if (IS_ERR(bh)) {
+ retval = PTR_ERR(bh);
+ bh = NULL;
+ goto out;
+ }
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize);
@@ -1947,8 +2130,9 @@
initialize_dirent_tail(t, blocksize);
}
- retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ retval = add_dirent_to_buf(handle, &fname, dir, inode, de, bh);
out:
+ ext4_fname_free_filename(&fname);
brelse(bh);
if (retval == 0)
ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
@@ -1958,21 +2142,20 @@
/*
* Returns 0 for success, or a negative error value
*/
-static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
- struct inode *inode)
+static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
+ struct dentry *dentry, struct inode *inode)
{
struct dx_frame frames[2], *frame;
struct dx_entry *entries, *at;
- struct dx_hash_info hinfo;
struct buffer_head *bh;
struct inode *dir = dentry->d_parent->d_inode;
struct super_block *sb = dir->i_sb;
struct ext4_dir_entry_2 *de;
int err;
- frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
- if (!frame)
- return err;
+ frame = dx_probe(fname, dir, NULL, frames);
+ if (IS_ERR(frame))
+ return PTR_ERR(frame);
entries = frame->entries;
at = frame->at;
bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT);
@@ -1987,7 +2170,7 @@
if (err)
goto journal_error;
- err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+ err = add_dirent_to_buf(handle, fname, dir, inode, NULL, bh);
if (err != -ENOSPC)
goto cleanup;
@@ -2083,10 +2266,12 @@
goto cleanup;
}
}
- de = do_split(handle, dir, &bh, frame, &hinfo, &err);
- if (!de)
+ de = do_split(handle, dir, &bh, frame, &fname->hinfo);
+ if (IS_ERR(de)) {
+ err = PTR_ERR(de);
goto cleanup;
- err = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ }
+ err = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
goto cleanup;
journal_error:
@@ -2155,8 +2340,7 @@
return err;
}
- if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(dir->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
BUFFER_TRACE(bh, "get_write_access");
@@ -2298,6 +2482,46 @@
return err;
}
+#if 0
+static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ handle_t *handle;
+ struct inode *inode;
+ int err, retries = 0;
+
+ dquot_initialize(dir);
+
+retry:
+ inode = ext4_new_inode_start_handle(dir, mode,
+ NULL, 0, NULL,
+ EXT4_HT_DIR,
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ 4 + EXT4_XATTR_TRANS_BLOCKS);
+ handle = ext4_journal_current_handle();
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ inode->i_op = &ext4_file_inode_operations;
+ inode->i_fop = &ext4_file_operations;
+ ext4_set_aops(inode);
+ d_tmpfile(dentry, inode);
+ err = ext4_orphan_add(handle, inode);
+ if (err)
+ goto err_unlock_inode;
+ mark_inode_dirty(inode);
+ unlock_new_inode(inode);
+ }
+ if (handle)
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+err_unlock_inode:
+ ext4_journal_stop(handle);
+ unlock_new_inode(inode);
+ return err;
+}
+#endif
+
struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
struct ext4_dir_entry_2 *de,
int blocksize, int csum_size,
@@ -2337,8 +2561,7 @@
int csum_size = 0;
int err;
- if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(dir->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -2353,10 +2576,6 @@
dir_block = ext4_append(handle, inode, &block);
if (IS_ERR(dir_block))
return PTR_ERR(dir_block);
- BUFFER_TRACE(dir_block, "get_write_access");
- err = ext4_journal_get_write_access(handle, dir_block);
- if (err)
- goto out;
de = (struct ext4_dir_entry_2 *)dir_block->b_data;
ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0);
set_nlink(inode, 2);
@@ -2434,7 +2653,7 @@
/*
* routine to check that the specified directory is empty (for rmdir)
*/
-static int empty_dir(struct inode *inode)
+int ext4_empty_dir(struct inode *inode)
{
unsigned int offset;
struct buffer_head *bh;
@@ -2475,8 +2694,7 @@
ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
de = ext4_next_entry(de1, sb->s_blocksize);
while (offset < inode->i_size) {
- if (!bh ||
- (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+ if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
unsigned int lblock;
err = 0;
brelse(bh);
@@ -2504,26 +2722,37 @@
return 1;
}
-/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+/*
+ * ext4_orphan_add() links an unlinked or truncated inode into a list of
* such inodes, starting at the superblock, in case we crash before the
* file is closed/deleted, or in case the inode truncate spans multiple
* transactions and the last transaction is not recovered after a crash.
*
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
+ *
+ * Orphan list manipulation functions must be called under i_mutex unless
+ * we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_iloc iloc;
int err = 0, rc;
+ bool dirty = false;
- if (!EXT4_SB(sb)->s_journal)
+ if (!sbi->s_journal || is_bad_inode(inode))
return 0;
- mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /*
+ * Exit early if inode already is on orphan list. This is a big speedup
+ * since we don't have to contend on the global s_orphan_lock.
+ */
if (!list_empty(&EXT4_I(inode)->i_orphan))
- goto out_unlock;
+ return 0;
/*
* Orphan handling is only valid for files with data blocks
@@ -2534,48 +2763,51 @@
J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
- BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
- err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
- goto out_unlock;
+ goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
- goto out_unlock;
+ goto out;
+
+ mutex_lock(&sbi->s_orphan_lock);
/*
* Due to previous errors inode may be already a part of on-disk
* orphan list. If so skip on-disk list modification.
*/
- if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
- goto mem_insert;
+ if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
+ (le32_to_cpu(sbi->s_es->s_inodes_count))) {
+ /* Insert this inode at the head of the on-disk orphan list */
+ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ dirty = true;
+ }
+ list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
- /* Insert this inode at the head of the on-disk orphan list... */
- NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
- EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_handle_dirty_super(handle, sb);
- rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
- if (!err)
- err = rc;
-
- /* Only add to the head of the in-memory list if all the
- * previous operations succeeded. If the orphan_add is going to
- * fail (possibly taking the journal offline), we can't risk
- * leaving the inode on the orphan list: stray orphan-list
- * entries can cause panics at unmount time.
- *
- * This is safe: on error we're going to ignore the orphan list
- * anyway on the next recovery. */
-mem_insert:
- if (!err)
- list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
-
+ if (dirty) {
+ err = ext4_handle_dirty_super(handle, sb);
+ rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (!err)
+ err = rc;
+ if (err) {
+ /*
+ * We have to remove inode from in-memory list if
+ * addition to on disk orphan list failed. Stray orphan
+ * list entries can cause panics at unmount time.
+ */
+ mutex_lock(&sbi->s_orphan_lock);
+ list_del(&EXT4_I(inode)->i_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
+ }
+ }
jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
jbd_debug(4, "orphan inode %lu will point to %d\n",
inode->i_ino, NEXT_ORPHAN(inode));
-out_unlock:
- mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
- ext4_std_error(inode->i_sb, err);
+out:
+ ext4_std_error(sb, err);
return err;
}
@@ -2587,45 +2819,51 @@
{
struct list_head *prev;
struct ext4_inode_info *ei = EXT4_I(inode);
- struct ext4_sb_info *sbi;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 ino_next;
struct ext4_iloc iloc;
int err = 0;
- if ((!EXT4_SB(inode->i_sb)->s_journal) &&
- !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS))
+ if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
return 0;
- mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /* Do this quick check before taking global s_orphan_lock. */
if (list_empty(&ei->i_orphan))
- goto out;
+ return 0;
- ino_next = NEXT_ORPHAN(inode);
- prev = ei->i_orphan.prev;
- sbi = EXT4_SB(inode->i_sb);
+ if (handle) {
+ /* Grab inode buffer early before taking global s_orphan_lock */
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ }
+ mutex_lock(&sbi->s_orphan_lock);
jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
+ prev = ei->i_orphan.prev;
list_del_init(&ei->i_orphan);
/* If we're on an error path, we may not have a valid
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
- goto out;
-
- err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (err)
+ if (!handle || err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_err;
+ }
+ ino_next = NEXT_ORPHAN(inode);
if (prev == &sbi->s_orphan) {
jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ mutex_unlock(&sbi->s_orphan_lock);
err = ext4_handle_dirty_super(handle, inode->i_sb);
} else {
struct ext4_iloc iloc2;
@@ -2635,20 +2873,20 @@
jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
NEXT_ORPHAN(i_prev) = ino_next;
err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+ mutex_unlock(&sbi->s_orphan_lock);
}
if (err)
goto out_brelse;
NEXT_ORPHAN(inode) = 0;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-
out_err:
ext4_std_error(inode->i_sb, err);
-out:
- mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
return err;
out_brelse:
@@ -2671,6 +2909,8 @@
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
if (!bh)
goto end_rmdir;
@@ -2681,7 +2921,7 @@
goto end_rmdir;
retval = -ENOTEMPTY;
- if (!empty_dir(inode))
+ if (!ext4_empty_dir(inode))
goto end_rmdir;
handle = ext4_journal_start(dir, EXT4_HT_DIR,
@@ -2738,6 +2978,8 @@
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
if (!bh)
goto end_unlink;
@@ -2790,16 +3032,38 @@
{
handle_t *handle;
struct inode *inode;
- int l, err, retries = 0;
+ int err, len = strlen(symname);
int credits;
+ bool encryption_required;
+ struct ext4_str disk_link;
+ struct ext4_encrypted_symlink_data *sd = NULL;
- l = strlen(symname)+1;
- if (l > dir->i_sb->s_blocksize)
- return -ENAMETOOLONG;
+ disk_link.len = len + 1;
+ disk_link.name = (char *) symname;
+
+ encryption_required = (ext4_encrypted_inode(dir) ||
+ DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb)));
+ if (encryption_required) {
+ err = ext4_get_encryption_info(dir);
+ if (err)
+ return err;
+ if (ext4_encryption_info(dir) == NULL)
+ return -EPERM;
+ disk_link.len = (ext4_fname_encrypted_size(dir, len) +
+ sizeof(struct ext4_encrypted_symlink_data));
+ sd = kzalloc(disk_link.len, GFP_KERNEL);
+ if (!sd)
+ return -ENOMEM;
+ }
+
+ if (disk_link.len > dir->i_sb->s_blocksize) {
+ err = -ENAMETOOLONG;
+ goto err_free_sd;
+ }
dquot_initialize(dir);
- if (l > EXT4_N_BLOCKS * 4) {
+ if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
/*
* For non-fast symlinks, we just allocate inode and put it on
* orphan list in the first transaction => we need bitmap,
@@ -2818,16 +3082,34 @@
credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
}
-retry:
+
inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO,
&dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
- err = PTR_ERR(inode);
- if (IS_ERR(inode))
- goto out_stop;
+ if (IS_ERR(inode)) {
+ if (handle)
+ ext4_journal_stop(handle);
+ err = PTR_ERR(inode);
+ goto err_free_sd;
+ }
- if (l > EXT4_N_BLOCKS * 4) {
+ if (encryption_required) {
+ struct qstr istr;
+ struct ext4_str ostr;
+
+ istr.name = (const unsigned char *) symname;
+ istr.len = len;
+ ostr.name = sd->encrypted_path;
+ ostr.len = disk_link.len;
+ err = ext4_fname_usr_to_disk(inode, &istr, &ostr);
+ if (err < 0)
+ goto err_drop_inode;
+ sd->len = cpu_to_le16(ostr.len);
+ disk_link.name = (char *) sd;
+ }
+
+ if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
/*
@@ -2843,9 +3125,10 @@
drop_nlink(inode);
err = ext4_orphan_add(handle, inode);
ext4_journal_stop(handle);
+ handle = NULL;
if (err)
goto err_drop_inode;
- err = __page_symlink(inode, symname, l, 1);
+ err = __page_symlink(inode, disk_link.name, disk_link.len, 1);
if (err)
goto err_drop_inode;
/*
@@ -2857,36 +3140,40 @@
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
+ handle = NULL;
goto err_drop_inode;
}
set_nlink(inode, 1);
err = ext4_orphan_del(handle, inode);
- if (err) {
- ext4_journal_stop(handle);
- clear_nlink(inode);
+ if (err)
goto err_drop_inode;
- }
} else {
/* clear the extent format for fast symlink */
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
- inode->i_op = &ext4_fast_symlink_inode_operations;
- memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
- inode->i_size = l-1;
+ inode->i_op = encryption_required ?
+ &ext4_symlink_inode_operations :
+ &ext4_fast_symlink_inode_operations;
+ memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name,
+ disk_link.len);
+ inode->i_size = disk_link.len - 1;
}
EXT4_I(inode)->i_disksize = inode->i_size;
err = ext4_add_nondir(handle, dentry, inode);
if (!err && IS_DIRSYNC(dir))
ext4_handle_sync(handle);
-out_stop:
if (handle)
ext4_journal_stop(handle);
- if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
- goto retry;
+ kfree(sd);
return err;
err_drop_inode:
+ if (handle)
+ ext4_journal_stop(handle);
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
+err_free_sd:
+ kfree(sd);
return err;
}
@@ -2899,13 +3186,15 @@
if (inode->i_nlink >= EXT4_LINK_MAX)
return -EMLINK;
-
+ if (ext4_encrypted_inode(dir) &&
+ !ext4_is_child_context_consistent_with_parent(dir, inode))
+ return -EPERM;
dquot_initialize(dir);
retry:
handle = ext4_journal_start(dir, EXT4_HT_DIR,
(EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS));
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS) + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2919,6 +3208,11 @@
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
+ /* this can happen only for tmpfile being
+ * linked the first time
+ */
+ if (inode->i_nlink == 1)
+ ext4_orphan_del(handle, inode);
d_instantiate(dentry, inode);
} else {
drop_nlink(inode);
@@ -2960,205 +3254,536 @@
return ext4_get_first_inline_block(inode, parent_de, retval);
}
+struct ext4_renament {
+ struct inode *dir;
+ struct dentry *dentry;
+ struct inode *inode;
+ bool is_dir;
+ int dir_nlink_delta;
+
+ /* entry for "dentry" */
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de;
+ int inlined;
+
+ /* entry for ".." in inode if it's a directory */
+ struct buffer_head *dir_bh;
+ struct ext4_dir_entry_2 *parent_de;
+ int dir_inlined;
+};
+
+static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
+{
+ int retval;
+
+ ent->dir_bh = ext4_get_first_dir_block(handle, ent->inode,
+ &retval, &ent->parent_de,
+ &ent->dir_inlined);
+ if (!ent->dir_bh)
+ return retval;
+ if (le32_to_cpu(ent->parent_de->inode) != ent->dir->i_ino)
+ return -EIO;
+ BUFFER_TRACE(ent->dir_bh, "get_write_access");
+ return ext4_journal_get_write_access(handle, ent->dir_bh);
+}
+
+static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
+ unsigned dir_ino)
+{
+ int retval;
+
+ ent->parent_de->inode = cpu_to_le32(dir_ino);
+ BUFFER_TRACE(ent->dir_bh, "call ext4_handle_dirty_metadata");
+ if (!ent->dir_inlined) {
+ if (is_dx(ent->inode)) {
+ retval = ext4_handle_dirty_dx_node(handle,
+ ent->inode,
+ ent->dir_bh);
+ } else {
+ retval = ext4_handle_dirty_dirent_node(handle,
+ ent->inode,
+ ent->dir_bh);
+ }
+ } else {
+ retval = ext4_mark_inode_dirty(handle, ent->inode);
+ }
+ if (retval) {
+ ext4_std_error(ent->dir->i_sb, retval);
+ return retval;
+ }
+ return 0;
+}
+
+static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
+ unsigned ino, unsigned file_type)
+{
+ int retval;
+
+ BUFFER_TRACE(ent->bh, "get write access");
+ retval = ext4_journal_get_write_access(handle, ent->bh);
+ if (retval)
+ return retval;
+ ent->de->inode = cpu_to_le32(ino);
+ if (EXT4_HAS_INCOMPAT_FEATURE(ent->dir->i_sb,
+ EXT4_FEATURE_INCOMPAT_FILETYPE))
+ ent->de->file_type = file_type;
+ ent->dir->i_version++;
+ ent->dir->i_ctime = ent->dir->i_mtime =
+ ext4_current_time(ent->dir);
+ ext4_mark_inode_dirty(handle, ent->dir);
+ BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
+ if (!ent->inlined) {
+ retval = ext4_handle_dirty_dirent_node(handle,
+ ent->dir, ent->bh);
+ if (unlikely(retval)) {
+ ext4_std_error(ent->dir->i_sb, retval);
+ return retval;
+ }
+ }
+ brelse(ent->bh);
+ ent->bh = NULL;
+
+ return 0;
+}
+
+static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
+ const struct qstr *d_name)
+{
+ int retval = -ENOENT;
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de;
+
+ bh = ext4_find_entry(dir, d_name, &de, NULL);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
+ if (bh) {
+ retval = ext4_delete_entry(handle, dir, de, bh);
+ brelse(bh);
+ }
+ return retval;
+}
+
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent,
+ int force_reread)
+{
+ int retval;
+ /*
+ * ent->de could have moved from under us during htree split, so make
+ * sure that we are deleting the right entry. We might also be pointing
+ * to a stale entry in the unused part of ent->bh so just checking inum
+ * and the name isn't enough.
+ */
+ if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
+ ent->de->name_len != ent->dentry->d_name.len ||
+ strncmp(ent->de->name, ent->dentry->d_name.name,
+ ent->de->name_len) ||
+ force_reread) {
+ retval = ext4_find_delete_entry(handle, ent->dir,
+ &ent->dentry->d_name);
+ } else {
+ retval = ext4_delete_entry(handle, ent->dir, ent->de, ent->bh);
+ if (retval == -ENOENT) {
+ retval = ext4_find_delete_entry(handle, ent->dir,
+ &ent->dentry->d_name);
+ }
+ }
+
+ if (retval) {
+ ext4_warning(ent->dir->i_sb,
+ "Deleting old file (%lu), %d, error=%d",
+ ent->dir->i_ino, ent->dir->i_nlink, retval);
+ }
+}
+
+#if 0
+static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
+{
+ if (ent->dir_nlink_delta) {
+ if (ent->dir_nlink_delta == -1)
+ ext4_dec_count(handle, ent->dir);
+ else
+ ext4_inc_count(handle, ent->dir);
+ ext4_mark_inode_dirty(handle, ent->dir);
+ }
+}
+
+static struct inode *ext4_whiteout_for_rename(struct ext4_renament *ent,
+ int credits, handle_t **h)
+{
+ struct inode *wh;
+ handle_t *handle;
+ int retries = 0;
+
+ /*
+ * for inode block, sb block, group summaries,
+ * and inode bitmap
+ */
+ credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
+ EXT4_XATTR_TRANS_BLOCKS + 4);
+retry:
+ wh = ext4_new_inode_start_handle(ent->dir, S_IFCHR | WHITEOUT_MODE,
+ &ent->dentry->d_name, 0, NULL,
+ EXT4_HT_DIR, credits);
+
+ handle = ext4_journal_current_handle();
+ if (IS_ERR(wh)) {
+ if (handle)
+ ext4_journal_stop(handle);
+ if (PTR_ERR(wh) == -ENOSPC &&
+ ext4_should_retry_alloc(ent->dir->i_sb, &retries))
+ goto retry;
+ } else {
+ *h = handle;
+ init_special_inode(wh, wh->i_mode, WHITEOUT_DEV);
+ wh->i_op = &ext4_special_inode_operations;
+ }
+ return wh;
+}
+#endif
+
/*
* Anybody can rename anything with this: the permission checks are left to the
* higher-level routines.
+ *
+ * n.b. old_{dentry,inode) refers to the source dentry/inode
+ * while new_{dentry,inode) refers to the destination dentry/inode
+ * This comes from rename(const char *oldpath, const char *newpath)
*/
static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
- handle_t *handle;
- struct inode *old_inode, *new_inode;
- struct buffer_head *old_bh, *new_bh, *dir_bh;
- struct ext4_dir_entry_2 *old_de, *new_de;
- int retval, force_da_alloc = 0;
- int inlined = 0, new_inlined = 0;
- struct ext4_dir_entry_2 *parent_de;
+ handle_t *handle = NULL;
+ struct ext4_renament old = {
+ .dir = old_dir,
+ .dentry = old_dentry,
+ .inode = old_dentry->d_inode,
+ };
+ struct ext4_renament new = {
+ .dir = new_dir,
+ .dentry = new_dentry,
+ .inode = new_dentry->d_inode,
+ };
+ int force_reread;
+ int retval;
+ struct inode *whiteout = NULL;
+ int credits;
+ u8 old_file_type;
- dquot_initialize(old_dir);
- dquot_initialize(new_dir);
-
- old_bh = new_bh = dir_bh = NULL;
+ dquot_initialize(old.dir);
+ dquot_initialize(new.dir);
/* Initialize quotas before so that eventual writes go
* in separate transaction */
- if (new_dentry->d_inode)
- dquot_initialize(new_dentry->d_inode);
- handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
- (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ if (new.inode)
+ dquot_initialize(new.inode);
- if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
- ext4_handle_sync(handle);
-
- old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL);
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ if (IS_ERR(old.bh))
+ return PTR_ERR(old.bh);
/*
* Check for inode number is _not_ due to possible IO errors.
* We might rmdir the source, keep it as pwd of some process
* and merrily kill the link to whatever was created under the
* same name. Goodbye sticky bit ;-<
*/
- old_inode = old_dentry->d_inode;
retval = -ENOENT;
- if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
+ if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
goto end_rename;
- new_inode = new_dentry->d_inode;
- new_bh = ext4_find_entry(new_dir, &new_dentry->d_name,
- &new_de, &new_inlined);
- if (new_bh) {
- if (!new_inode) {
- brelse(new_bh);
- new_bh = NULL;
+ if ((old.dir != new.dir) &&
+ ext4_encrypted_inode(new.dir) &&
+ !ext4_is_child_context_consistent_with_parent(new.dir,
+ old.inode)) {
+ retval = -EPERM;
+ goto end_rename;
+ }
+
+ new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+ &new.de, &new.inlined);
+ if (IS_ERR(new.bh)) {
+ retval = PTR_ERR(new.bh);
+ new.bh = NULL;
+ goto end_rename;
+ }
+ if (new.bh) {
+ if (!new.inode) {
+ brelse(new.bh);
+ new.bh = NULL;
}
}
- if (S_ISDIR(old_inode->i_mode)) {
- if (new_inode) {
+ if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC))
+ ext4_alloc_da_blocks(old.inode);
+
+ credits = (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
+#if 0
+ if (!(flags & RENAME_WHITEOUT)) {
+#endif
+ handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+#if 0
+ } else {
+ whiteout = ext4_whiteout_for_rename(&old, credits, &handle);
+ if (IS_ERR(whiteout))
+ return PTR_ERR(whiteout);
+ }
+#endif
+
+ if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
+ ext4_handle_sync(handle);
+
+ if (S_ISDIR(old.inode->i_mode)) {
+ if (new.inode) {
retval = -ENOTEMPTY;
- if (!empty_dir(new_inode))
+ if (!ext4_empty_dir(new.inode))
+ goto end_rename;
+ } else {
+ retval = -EMLINK;
+ if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
goto end_rename;
}
- retval = -EIO;
- dir_bh = ext4_get_first_dir_block(handle, old_inode,
- &retval, &parent_de,
- &inlined);
- if (!dir_bh)
- goto end_rename;
- if (le32_to_cpu(parent_de->inode) != old_dir->i_ino)
- goto end_rename;
- retval = -EMLINK;
- if (!new_inode && new_dir != old_dir &&
- EXT4_DIR_LINK_MAX(new_dir))
- goto end_rename;
- BUFFER_TRACE(dir_bh, "get_write_access");
- retval = ext4_journal_get_write_access(handle, dir_bh);
+ retval = ext4_rename_dir_prepare(handle, &old);
if (retval)
goto end_rename;
}
- if (!new_bh) {
- retval = ext4_add_entry(handle, new_dentry, old_inode);
+ /*
+ * If we're renaming a file within an inline_data dir and adding or
+ * setting the new dirent causes a conversion from inline_data to
+ * extents/blockmap, we need to force the dirent delete code to
+ * re-read the directory, or else we end up trying to delete a dirent
+ * from what is now the extent tree root (or a block map).
+ */
+ force_reread = (new.dir->i_ino == old.dir->i_ino &&
+ ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
+
+ old_file_type = old.de->file_type;
+ if (whiteout) {
+ /*
+ * Do this before adding a new entry, so the old entry is sure
+ * to be still pointing to the valid old entry.
+ */
+ retval = ext4_setent(handle, &old, whiteout->i_ino,
+ EXT4_FT_CHRDEV);
+ if (retval)
+ goto end_rename;
+ ext4_mark_inode_dirty(handle, whiteout);
+ }
+ if (!new.bh) {
+ retval = ext4_add_entry(handle, new.dentry, old.inode);
if (retval)
goto end_rename;
} else {
- BUFFER_TRACE(new_bh, "get write access");
- retval = ext4_journal_get_write_access(handle, new_bh);
+ retval = ext4_setent(handle, &new,
+ old.inode->i_ino, old_file_type);
if (retval)
goto end_rename;
- new_de->inode = cpu_to_le32(old_inode->i_ino);
- if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
- EXT4_FEATURE_INCOMPAT_FILETYPE))
- new_de->file_type = old_de->file_type;
- new_dir->i_version++;
- new_dir->i_ctime = new_dir->i_mtime =
- ext4_current_time(new_dir);
- ext4_mark_inode_dirty(handle, new_dir);
- BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
- if (!new_inlined) {
- retval = ext4_handle_dirty_dirent_node(handle,
- new_dir, new_bh);
- if (unlikely(retval)) {
- ext4_std_error(new_dir->i_sb, retval);
- goto end_rename;
- }
- }
- brelse(new_bh);
- new_bh = NULL;
}
+ if (force_reread)
+ force_reread = !ext4_test_inode_flag(new.dir,
+ EXT4_INODE_INLINE_DATA);
/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- old_inode->i_ctime = ext4_current_time(old_inode);
- ext4_mark_inode_dirty(handle, old_inode);
+ old.inode->i_ctime = ext4_current_time(old.inode);
+ ext4_mark_inode_dirty(handle, old.inode);
- /*
- * ok, that's it
- */
- if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
- old_de->name_len != old_dentry->d_name.len ||
- strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
- (retval = ext4_delete_entry(handle, old_dir,
- old_de, old_bh)) == -ENOENT) {
- /* old_de could have moved from under us during htree split, so
- * make sure that we are deleting the right entry. We might
- * also be pointing to a stale entry in the unused part of
- * old_bh so just checking inum and the name isn't enough. */
- struct buffer_head *old_bh2;
- struct ext4_dir_entry_2 *old_de2;
-
- old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name,
- &old_de2, NULL);
- if (old_bh2) {
- retval = ext4_delete_entry(handle, old_dir,
- old_de2, old_bh2);
- brelse(old_bh2);
- }
- }
- if (retval) {
- ext4_warning(old_dir->i_sb,
- "Deleting old file (%lu), %d, error=%d",
- old_dir->i_ino, old_dir->i_nlink, retval);
+ if (!whiteout) {
+ /*
+ * ok, that's it
+ */
+ ext4_rename_delete(handle, &old, force_reread);
}
- if (new_inode) {
- ext4_dec_count(handle, new_inode);
- new_inode->i_ctime = ext4_current_time(new_inode);
+ if (new.inode) {
+ ext4_dec_count(handle, new.inode);
+ new.inode->i_ctime = ext4_current_time(new.inode);
}
- old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
- ext4_update_dx_flag(old_dir);
- if (dir_bh) {
- parent_de->inode = cpu_to_le32(new_dir->i_ino);
- BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
- if (!inlined) {
- if (is_dx(old_inode)) {
- retval = ext4_handle_dirty_dx_node(handle,
- old_inode,
- dir_bh);
- } else {
- retval = ext4_handle_dirty_dirent_node(handle,
- old_inode, dir_bh);
- }
- } else {
- retval = ext4_mark_inode_dirty(handle, old_inode);
- }
- if (retval) {
- ext4_std_error(old_dir->i_sb, retval);
+ old.dir->i_ctime = old.dir->i_mtime = ext4_current_time(old.dir);
+ ext4_update_dx_flag(old.dir);
+ if (old.dir_bh) {
+ retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+ if (retval)
goto end_rename;
- }
- ext4_dec_count(handle, old_dir);
- if (new_inode) {
- /* checked empty_dir above, can't have another parent,
- * ext4_dec_count() won't work for many-linked dirs */
- clear_nlink(new_inode);
+
+ ext4_dec_count(handle, old.dir);
+ if (new.inode) {
+ /* checked ext4_empty_dir above, can't have another
+ * parent, ext4_dec_count() won't work for many-linked
+ * dirs */
+ clear_nlink(new.inode);
} else {
- ext4_inc_count(handle, new_dir);
- ext4_update_dx_flag(new_dir);
- ext4_mark_inode_dirty(handle, new_dir);
+ ext4_inc_count(handle, new.dir);
+ ext4_update_dx_flag(new.dir);
+ ext4_mark_inode_dirty(handle, new.dir);
}
}
- ext4_mark_inode_dirty(handle, old_dir);
- if (new_inode) {
- ext4_mark_inode_dirty(handle, new_inode);
- if (!new_inode->i_nlink)
- ext4_orphan_add(handle, new_inode);
- if (!test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
- force_da_alloc = 1;
+ ext4_mark_inode_dirty(handle, old.dir);
+ if (new.inode) {
+ ext4_mark_inode_dirty(handle, new.inode);
+ if (!new.inode->i_nlink)
+ ext4_orphan_add(handle, new.inode);
}
retval = 0;
end_rename:
- brelse(dir_bh);
- brelse(old_bh);
- brelse(new_bh);
- ext4_journal_stop(handle);
- if (retval == 0 && force_da_alloc)
- ext4_alloc_da_blocks(old_inode);
+ brelse(old.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
+ if (whiteout) {
+ if (retval)
+ drop_nlink(whiteout);
+ unlock_new_inode(whiteout);
+ iput(whiteout);
+ }
+ if (handle)
+ ext4_journal_stop(handle);
return retval;
}
+#if 0
+static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ handle_t *handle = NULL;
+ struct ext4_renament old = {
+ .dir = old_dir,
+ .dentry = old_dentry,
+ .inode = old_dentry->d_inode,
+ };
+ struct ext4_renament new = {
+ .dir = new_dir,
+ .dentry = new_dentry,
+ .inode = new_dentry->d_inode,
+ };
+ u8 new_file_type;
+ int retval;
+
+ if ((ext4_encrypted_inode(old_dir) ||
+ ext4_encrypted_inode(new_dir)) &&
+ (old_dir != new_dir) &&
+ (!ext4_is_child_context_consistent_with_parent(new_dir,
+ old.inode) ||
+ !ext4_is_child_context_consistent_with_parent(old_dir,
+ new.inode)))
+ return -EPERM;
+
+ dquot_initialize(old.dir);
+ dquot_initialize(new.dir);
+
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name,
+ &old.de, &old.inlined);
+ if (IS_ERR(old.bh))
+ return PTR_ERR(old.bh);
+ /*
+ * Check for inode number is _not_ due to possible IO errors.
+ * We might rmdir the source, keep it as pwd of some process
+ * and merrily kill the link to whatever was created under the
+ * same name. Goodbye sticky bit ;-<
+ */
+ retval = -ENOENT;
+ if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
+ goto end_rename;
+
+ new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+ &new.de, &new.inlined);
+ if (IS_ERR(new.bh)) {
+ retval = PTR_ERR(new.bh);
+ new.bh = NULL;
+ goto end_rename;
+ }
+
+ /* RENAME_EXCHANGE case: old *and* new must both exist */
+ if (!new.bh || le32_to_cpu(new.de->inode) != new.inode->i_ino)
+ goto end_rename;
+
+ handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
+ (2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
+ 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
+ ext4_handle_sync(handle);
+
+ if (S_ISDIR(old.inode->i_mode)) {
+ old.is_dir = true;
+ retval = ext4_rename_dir_prepare(handle, &old);
+ if (retval)
+ goto end_rename;
+ }
+ if (S_ISDIR(new.inode->i_mode)) {
+ new.is_dir = true;
+ retval = ext4_rename_dir_prepare(handle, &new);
+ if (retval)
+ goto end_rename;
+ }
+
+ /*
+ * Other than the special case of overwriting a directory, parents'
+ * nlink only needs to be modified if this is a cross directory rename.
+ */
+ if (old.dir != new.dir && old.is_dir != new.is_dir) {
+ old.dir_nlink_delta = old.is_dir ? -1 : 1;
+ new.dir_nlink_delta = -old.dir_nlink_delta;
+ retval = -EMLINK;
+ if ((old.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(old.dir)) ||
+ (new.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(new.dir)))
+ goto end_rename;
+ }
+
+ new_file_type = new.de->file_type;
+ retval = ext4_setent(handle, &new, old.inode->i_ino, old.de->file_type);
+ if (retval)
+ goto end_rename;
+
+ retval = ext4_setent(handle, &old, new.inode->i_ino, new_file_type);
+ if (retval)
+ goto end_rename;
+
+ /*
+ * Like most other Unix systems, set the ctime for inodes on a
+ * rename.
+ */
+ old.inode->i_ctime = ext4_current_time(old.inode);
+ new.inode->i_ctime = ext4_current_time(new.inode);
+ ext4_mark_inode_dirty(handle, old.inode);
+ ext4_mark_inode_dirty(handle, new.inode);
+
+ if (old.dir_bh) {
+ retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+ if (retval)
+ goto end_rename;
+ }
+ if (new.dir_bh) {
+ retval = ext4_rename_dir_finish(handle, &new, old.dir->i_ino);
+ if (retval)
+ goto end_rename;
+ }
+ ext4_update_dir_count(handle, &old);
+ ext4_update_dir_count(handle, &new);
+ retval = 0;
+
+end_rename:
+ brelse(old.dir_bh);
+ brelse(new.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
+ if (handle)
+ ext4_journal_stop(handle);
+ return retval;
+}
+#endif
+
+static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ return ext4_rename(old_dir, old_dentry, new_dir, new_dentry, 0);
+}
+
/*
* directories can handle most operations...
*/
@@ -3171,13 +3796,19 @@
.mkdir = ext4_mkdir,
.rmdir = ext4_rmdir,
.mknod = ext4_mknod,
- .rename = ext4_rename,
+#if 0
+ .tmpfile = ext4_tmpfile,
+#endif
+ .rename = ext4_rename2,
.setattr = ext4_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
+#if 0
+ .set_acl = ext4_set_acl,
+#endif
.fiemap = ext4_fiemap,
};
@@ -3188,4 +3819,7 @@
.listxattr = ext4_listxattr,
.removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
+#if 0
+ .set_acl = ext4_set_acl,
+#endif
};
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index b12a442..f55384c 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -25,6 +25,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
+#include <linux/ratelimit.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -46,165 +47,6 @@
}
/*
- * This function is called by ext4_evict_inode() to make sure there is
- * no more pending I/O completion work left to do.
- */
-void ext4_ioend_shutdown(struct inode *inode)
-{
- wait_queue_head_t *wq = ext4_ioend_wq(inode);
-
- wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
- /*
- * We need to make sure the work structure is finished being
- * used before we let the inode get destroyed.
- */
- if (work_pending(&EXT4_I(inode)->i_unwritten_work))
- cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
-}
-
-void ext4_free_io_end(ext4_io_end_t *io)
-{
- BUG_ON(!io);
- BUG_ON(!list_empty(&io->list));
- BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
-
- if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
- wake_up_all(ext4_ioend_wq(io->inode));
- kmem_cache_free(io_end_cachep, io);
-}
-
-/* check a range of space and convert unwritten extents to written. */
-static int ext4_end_io(ext4_io_end_t *io)
-{
- struct inode *inode = io->inode;
- loff_t offset = io->offset;
- ssize_t size = io->size;
- int ret = 0;
-
- ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
- "list->prev 0x%p\n",
- io, inode->i_ino, io->list.next, io->list.prev);
-
- ret = ext4_convert_unwritten_extents(inode, offset, size);
- if (ret < 0) {
- ext4_msg(inode->i_sb, KERN_EMERG,
- "failed to convert unwritten extents to written "
- "extents -- potential data loss! "
- "(inode %lu, offset %llu, size %zd, error %d)",
- inode->i_ino, offset, size, ret);
- }
- /* Wake up anyone waiting on unwritten extent conversion */
- if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
- wake_up_all(ext4_ioend_wq(inode));
- if (io->flag & EXT4_IO_END_DIRECT)
- inode_dio_done(inode);
- if (io->iocb)
- aio_complete(io->iocb, io->result, 0);
- return ret;
-}
-
-static void dump_completed_IO(struct inode *inode)
-{
-#ifdef EXT4FS_DEBUG
- struct list_head *cur, *before, *after;
- ext4_io_end_t *io, *io0, *io1;
-
- if (list_empty(&EXT4_I(inode)->i_completed_io_list)) {
- ext4_debug("inode %lu completed_io list is empty\n",
- inode->i_ino);
- return;
- }
-
- ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino);
- list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) {
- cur = &io->list;
- before = cur->prev;
- io0 = container_of(before, ext4_io_end_t, list);
- after = cur->next;
- io1 = container_of(after, ext4_io_end_t, list);
-
- ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
- io, inode->i_ino, io0, io1);
- }
-#endif
-}
-
-/* Add the io_end to per-inode completed end_io list. */
-void ext4_add_complete_io(ext4_io_end_t *io_end)
-{
- struct ext4_inode_info *ei = EXT4_I(io_end->inode);
- struct workqueue_struct *wq;
- unsigned long flags;
-
- BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
- wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
-
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- if (list_empty(&ei->i_completed_io_list))
- queue_work(wq, &ei->i_unwritten_work);
- list_add_tail(&io_end->list, &ei->i_completed_io_list);
- spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-}
-
-static int ext4_do_flush_completed_IO(struct inode *inode)
-{
- ext4_io_end_t *io;
- struct list_head unwritten;
- unsigned long flags;
- struct ext4_inode_info *ei = EXT4_I(inode);
- int err, ret = 0;
-
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- dump_completed_IO(inode);
- list_replace_init(&ei->i_completed_io_list, &unwritten);
- spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-
- while (!list_empty(&unwritten)) {
- io = list_entry(unwritten.next, ext4_io_end_t, list);
- BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
- list_del_init(&io->list);
-
- err = ext4_end_io(io);
- if (unlikely(!ret && err))
- ret = err;
- io->flag &= ~EXT4_IO_END_UNWRITTEN;
- ext4_free_io_end(io);
- }
- return ret;
-}
-
-/*
- * work on completed aio dio IO, to convert unwritten extents to extents
- */
-void ext4_end_io_work(struct work_struct *work)
-{
- struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
- i_unwritten_work);
- ext4_do_flush_completed_IO(&ei->vfs_inode);
-}
-
-int ext4_flush_unwritten_io(struct inode *inode)
-{
- int ret;
- WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
- !(inode->i_state & I_FREEING));
- ret = ext4_do_flush_completed_IO(inode);
- ext4_unwritten_wait(inode);
- return ret;
-}
-
-ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
-{
- ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
- if (io) {
- atomic_inc(&EXT4_I(inode)->i_ioend_count);
- io->inode = inode;
- INIT_LIST_HEAD(&io->list);
- }
- return io;
-}
-
-/*
* Print an buffer I/O error compatible with the fs/buffer.c. This
* provides compatibility with dmesg scrapers that look for a specific
* buffer I/O error message. We really need a unified error reporting
@@ -214,29 +56,23 @@
static void buffer_io_error(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
- printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+ printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
bdevname(bh->b_bdev, b),
(unsigned long long)bh->b_blocknr);
}
-static void ext4_end_bio(struct bio *bio, int error)
+static void ext4_finish_bio(struct bio *bio)
{
- ext4_io_end_t *io_end = bio->bi_private;
- struct inode *inode;
int i;
- int blocksize;
- sector_t bi_sector = bio->bi_sector;
+ int error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
+ struct bio_vec *bvec;
- BUG_ON(!io_end);
- inode = io_end->inode;
- blocksize = 1 << inode->i_blkbits;
- bio->bi_private = NULL;
- bio->bi_end_io = NULL;
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = 0;
- for (i = 0; i < bio->bi_vcnt; i++) {
- struct bio_vec *bvec = &bio->bi_io_vec[i];
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ struct page *data_page = NULL;
+ struct ext4_crypto_ctx *ctx = NULL;
+#endif
struct buffer_head *bh, *head;
unsigned bio_start = bvec->bv_offset;
unsigned bio_end = bio_start + bvec->bv_len;
@@ -246,6 +82,15 @@
if (!page)
continue;
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (!page->mapping) {
+ /* The bounce data pages are unmapped. */
+ data_page = page;
+ ctx = (struct ext4_crypto_ctx *)page_private(data_page);
+ page = ctx->w.control_page;
+ }
+#endif
+
if (error) {
SetPageError(page);
set_bit(AS_EIO, &page->mapping->flags);
@@ -259,7 +104,7 @@
bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
do {
if (bh_offset(bh) < bio_start ||
- bh_offset(bh) + blocksize > bio_end) {
+ bh_offset(bh) + bh->b_size > bio_end) {
if (buffer_async_write(bh))
under_io++;
continue;
@@ -270,28 +115,244 @@
} while ((bh = bh->b_this_page) != head);
bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
local_irq_restore(flags);
- if (!under_io)
+ if (!under_io) {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (ctx)
+ ext4_restore_control_page(data_page);
+#endif
end_page_writeback(page);
+ }
}
- bio_put(bio);
+}
+
+static void ext4_release_io_end(ext4_io_end_t *io_end)
+{
+ struct bio *bio, *next_bio;
+
+ BUG_ON(!list_empty(&io_end->list));
+ BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+ WARN_ON(io_end->handle);
+
+ if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
+ wake_up_all(ext4_ioend_wq(io_end->inode));
+
+ for (bio = io_end->bio; bio; bio = next_bio) {
+ next_bio = bio->bi_private;
+ ext4_finish_bio(bio);
+ bio_put(bio);
+ }
+ kmem_cache_free(io_end_cachep, io_end);
+}
+
+static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
+{
+ struct inode *inode = io_end->inode;
+
+ io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
+ /* Wake up anyone waiting on unwritten extent conversion */
+ if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+ wake_up_all(ext4_ioend_wq(inode));
+}
+
+/*
+ * Check a range of space and convert unwritten extents to written. Note that
+ * we are protected from truncate touching same part of extent tree by the
+ * fact that truncate code waits for all DIO to finish (thus exclusion from
+ * direct IO is achieved) and also waits for PageWriteback bits. Thus we
+ * cannot get to ext4_ext_truncate() before all IOs overlapping that range are
+ * completed (happens from ext4_free_ioend()).
+ */
+static int ext4_end_io(ext4_io_end_t *io)
+{
+ struct inode *inode = io->inode;
+ loff_t offset = io->offset;
+ ssize_t size = io->size;
+ handle_t *handle = io->handle;
+ int ret = 0;
+
+ ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
+ "list->prev 0x%p\n",
+ io, inode->i_ino, io->list.next, io->list.prev);
+
+ io->handle = NULL; /* Following call will use up the handle */
+ ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
+ if (ret < 0) {
+ ext4_msg(inode->i_sb, KERN_EMERG,
+ "failed to convert unwritten extents to written "
+ "extents -- potential data loss! "
+ "(inode %lu, offset %llu, size %zd, error %d)",
+ inode->i_ino, offset, size, ret);
+ }
+ ext4_clear_io_unwritten_flag(io);
+ ext4_release_io_end(io);
+ return ret;
+}
+
+static void dump_completed_IO(struct inode *inode, struct list_head *head)
+{
+#ifdef EXT4FS_DEBUG
+ struct list_head *cur, *before, *after;
+ ext4_io_end_t *io, *io0, *io1;
+
+ if (list_empty(head))
+ return;
+
+ ext4_debug("Dump inode %lu completed io list\n", inode->i_ino);
+ list_for_each_entry(io, head, list) {
+ cur = &io->list;
+ before = cur->prev;
+ io0 = container_of(before, ext4_io_end_t, list);
+ after = cur->next;
+ io1 = container_of(after, ext4_io_end_t, list);
+
+ ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+ io, inode->i_ino, io0, io1);
+ }
+#endif
+}
+
+/* Add the io_end to per-inode completed end_io list. */
+static void ext4_add_complete_io(ext4_io_end_t *io_end)
+{
+ struct ext4_inode_info *ei = EXT4_I(io_end->inode);
+ struct ext4_sb_info *sbi = EXT4_SB(io_end->inode->i_sb);
+ struct workqueue_struct *wq;
+ unsigned long flags;
+
+ /* Only reserved conversions from writeback should enter here */
+ WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+ WARN_ON(!io_end->handle && sbi->s_journal);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ wq = sbi->rsv_conversion_wq;
+ if (list_empty(&ei->i_rsv_conversion_list))
+ queue_work(wq, &ei->i_rsv_conversion_work);
+ list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+}
+
+static int ext4_do_flush_completed_IO(struct inode *inode,
+ struct list_head *head)
+{
+ ext4_io_end_t *io;
+ struct list_head unwritten;
+ unsigned long flags;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int err, ret = 0;
+
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ dump_completed_IO(inode, head);
+ list_replace_init(head, &unwritten);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+ while (!list_empty(&unwritten)) {
+ io = list_entry(unwritten.next, ext4_io_end_t, list);
+ BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
+ list_del_init(&io->list);
+
+ err = ext4_end_io(io);
+ if (unlikely(!ret && err))
+ ret = err;
+ }
+ return ret;
+}
+
+/*
+ * work on completed IO, to convert unwritten extents to extents
+ */
+void ext4_end_io_rsv_work(struct work_struct *work)
+{
+ struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+ i_rsv_conversion_work);
+ ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
+}
+
+ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
+{
+ ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
+ if (io) {
+ atomic_inc(&EXT4_I(inode)->i_ioend_count);
+ io->inode = inode;
+ INIT_LIST_HEAD(&io->list);
+ atomic_set(&io->count, 1);
+ }
+ return io;
+}
+
+void ext4_put_io_end_defer(ext4_io_end_t *io_end)
+{
+ if (atomic_dec_and_test(&io_end->count)) {
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
+ ext4_release_io_end(io_end);
+ return;
+ }
+ ext4_add_complete_io(io_end);
+ }
+}
+
+int ext4_put_io_end(ext4_io_end_t *io_end)
+{
+ int err = 0;
+
+ if (atomic_dec_and_test(&io_end->count)) {
+ if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+ err = ext4_convert_unwritten_extents(io_end->handle,
+ io_end->inode, io_end->offset,
+ io_end->size);
+ io_end->handle = NULL;
+ ext4_clear_io_unwritten_flag(io_end);
+ }
+ ext4_release_io_end(io_end);
+ }
+ return err;
+}
+
+ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
+{
+ atomic_inc(&io_end->count);
+ return io_end;
+}
+
+/* BIO completion function for page writeback */
+static void ext4_end_bio(struct bio *bio, int error)
+{
+ ext4_io_end_t *io_end = bio->bi_private;
+ sector_t bi_sector = bio->bi_sector;
+
+ BUG_ON(!io_end);
+ bio->bi_end_io = NULL;
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = 0;
if (error) {
- io_end->flag |= EXT4_IO_END_ERROR;
- ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+ struct inode *inode = io_end->inode;
+
+ ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
"(offset %llu size %ld starting block %llu)",
- inode->i_ino,
+ error, inode->i_ino,
(unsigned long long) io_end->offset,
(long) io_end->size,
(unsigned long long)
bi_sector >> (inode->i_blkbits - 9));
+ mapping_set_error(inode->i_mapping, error);
}
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- ext4_free_io_end(io_end);
- return;
+ if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+ /*
+ * Link bio into list hanging from io_end. We have to do it
+ * atomically as bio completions can be racing against each
+ * other.
+ */
+ bio->bi_private = xchg(&io_end->bio, bio);
+ ext4_put_io_end_defer(io_end);
+ } else {
+ /*
+ * Drop io_end reference early. Inode can get freed once
+ * we finish the bio.
+ */
+ ext4_put_io_end_defer(io_end);
+ ext4_finish_bio(bio);
+ bio_put(bio);
}
-
- ext4_add_complete_io(io_end);
}
void ext4_io_submit(struct ext4_io_submit *io)
@@ -305,43 +366,39 @@
bio_put(io->io_bio);
}
io->io_bio = NULL;
- io->io_op = 0;
+}
+
+void ext4_io_submit_init(struct ext4_io_submit *io,
+ struct writeback_control *wbc)
+{
+ io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+ io->io_bio = NULL;
io->io_end = NULL;
}
-static int io_submit_init(struct ext4_io_submit *io,
- struct inode *inode,
- struct writeback_control *wbc,
- struct buffer_head *bh)
+static int io_submit_init_bio(struct ext4_io_submit *io,
+ struct buffer_head *bh)
{
- ext4_io_end_t *io_end;
- struct page *page = bh->b_page;
int nvecs = bio_get_nr_vecs(bh->b_bdev);
struct bio *bio;
- io_end = ext4_init_io_end(inode, GFP_NOFS);
- if (!io_end)
- return -ENOMEM;
bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
+ if (!bio)
+ return -ENOMEM;
bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
- bio->bi_private = io->io_end = io_end;
bio->bi_end_io = ext4_end_bio;
-
- io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
-
+ bio->bi_private = ext4_get_io_end(io->io_end);
io->io_bio = bio;
- io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
io->io_next_block = bh->b_blocknr;
return 0;
}
static int io_submit_add_bh(struct ext4_io_submit *io,
struct inode *inode,
- struct writeback_control *wbc,
+ struct page *page,
struct buffer_head *bh)
{
- ext4_io_end_t *io_end;
int ret;
if (io->io_bio && bh->b_blocknr != io->io_next_block) {
@@ -349,26 +406,24 @@
ext4_io_submit(io);
}
if (io->io_bio == NULL) {
- ret = io_submit_init(io, inode, wbc, bh);
+ ret = io_submit_init_bio(io, bh);
if (ret)
return ret;
}
- io_end = io->io_end;
- if (test_clear_buffer_uninit(bh))
- ext4_set_io_unwritten_flag(inode, io_end);
- io->io_end->size += bh->b_size;
- io->io_next_block++;
- ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+ ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
+ io->io_next_block++;
return 0;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ bool keep_towrite)
{
+ struct page *data_page = NULL;
struct inode *inode = page->mapping->host;
unsigned block_start, blocksize;
struct buffer_head *bh, *head;
@@ -380,11 +435,14 @@
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- set_page_writeback(page);
+ if (keep_towrite)
+ set_page_writeback_keepwrite(page);
+ else
+ set_page_writeback(page);
ClearPageError(page);
/*
- * Comments copied from block_write_full_page_endio:
+ * Comments copied from block_write_full_page:
*
* The page straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
@@ -425,19 +483,29 @@
set_buffer_async_write(bh);
} while ((bh = bh->b_this_page) != head);
- /* Now submit buffers to write */
bh = head = page_buffers(page);
+
+ if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ data_page = ext4_encrypt(inode, page);
+ if (IS_ERR(data_page)) {
+ ret = PTR_ERR(data_page);
+ data_page = NULL;
+ goto out;
+ }
+ }
+
+ /* Now submit buffers to write */
do {
if (!buffer_async_write(bh))
continue;
- ret = io_submit_add_bh(io, inode, wbc, bh);
+ ret = io_submit_add_bh(io, inode,
+ data_page ? data_page : page, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
- redirty_page_for_writepage(wbc, page);
break;
}
nr_submitted++;
@@ -446,6 +514,11 @@
/* Error stopped previous loop? Clean up buffers... */
if (ret) {
+ out:
+ if (data_page)
+ ext4_restore_control_page(data_page);
+ printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
+ redirty_page_for_writepage(wbc, page);
do {
clear_buffer_async_write(bh);
bh = bh->b_this_page;
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
new file mode 100644
index 0000000..4cd252b
--- /dev/null
+++ b/fs/ext4/readpage.c
@@ -0,0 +1,328 @@
+/*
+ * linux/fs/ext4/readpage.c
+ *
+ * Copyright (C) 2002, Linus Torvalds.
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This was originally taken from fs/mpage.c
+ *
+ * The intent is the ext4_mpage_readpages() function here is intended
+ * to replace mpage_readpages() in the general case, not just for
+ * encrypted files. It has some limitations (see below), where it
+ * will fall back to read_block_full_page(), but these limitations
+ * should only be hit when page_size != block_size.
+ *
+ * This will allow us to attach a callback function to support ext4
+ * encryption.
+ *
+ * If anything unusual happens, such as:
+ *
+ * - encountering a page which has buffers
+ * - encountering a page which has a non-hole after a hole
+ * - encountering a page with non-contiguous blocks
+ *
+ * then this code just gives up and calls the buffer_head-based read function.
+ * It does handle a page which has holes at the end - that is a common case:
+ * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/kdev_t.h>
+#include <linux/gfp.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/highmem.h>
+#include <linux/prefetch.h>
+#include <linux/mpage.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/cleancache.h>
+
+#include "ext4.h"
+
+/*
+ * Call ext4_decrypt on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ struct ext4_crypto_ctx *ctx =
+ container_of(work, struct ext4_crypto_ctx, r.work);
+ struct bio *bio = ctx->r.bio;
+ struct bio_vec *bv;
+ int i;
+
+ bio_for_each_segment_all(bv, bio, i) {
+ struct page *page = bv->bv_page;
+
+ int ret = ext4_decrypt(ctx, page);
+ if (ret) {
+ WARN_ON_ONCE(1);
+ SetPageError(page);
+ } else
+ SetPageUptodate(page);
+ unlock_page(page);
+ }
+ ext4_release_crypto_ctx(ctx);
+ bio_put(bio);
+#else
+ BUG();
+#endif
+}
+
+static inline bool ext4_bio_encrypted(struct bio *bio)
+{
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ return unlikely(bio->bi_private != NULL);
+#else
+ return false;
+#endif
+}
+
+/*
+ * I/O completion handler for multipage BIOs.
+ *
+ * The mpage code never puts partial pages into a BIO (except for end-of-file).
+ * If a page does not map to a contiguous run of blocks then it simply falls
+ * back to block_read_full_page().
+ *
+ * Why is this? If a page's completion depends on a number of different BIOs
+ * which can complete in any order (or at the same time) then determining the
+ * status of that page is hard. See end_buffer_async_read() for the details.
+ * There is no point in duplicating all that complexity.
+ */
+static void mpage_end_io(struct bio *bio, int err)
+{
+ struct bio_vec *bv;
+ int i;
+
+ if (ext4_bio_encrypted(bio)) {
+ struct ext4_crypto_ctx *ctx = bio->bi_private;
+
+ if (err) {
+ ext4_release_crypto_ctx(ctx);
+ } else {
+ INIT_WORK(&ctx->r.work, completion_pages);
+ ctx->r.bio = bio;
+ queue_work(ext4_read_workqueue, &ctx->r.work);
+ return;
+ }
+ }
+ bio_for_each_segment_all(bv, bio, i) {
+ struct page *page = bv->bv_page;
+
+ if (!err) {
+ SetPageUptodate(page);
+ } else {
+ ClearPageUptodate(page);
+ SetPageError(page);
+ }
+ unlock_page(page);
+ }
+
+ bio_put(bio);
+}
+
+int ext4_mpage_readpages(struct address_space *mapping,
+ struct list_head *pages, struct page *page,
+ unsigned nr_pages)
+{
+ struct bio *bio = NULL;
+ unsigned page_idx;
+ sector_t last_block_in_bio = 0;
+
+ struct inode *inode = mapping->host;
+ const unsigned blkbits = inode->i_blkbits;
+ const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+ const unsigned blocksize = 1 << blkbits;
+ sector_t block_in_file;
+ sector_t last_block;
+ sector_t last_block_in_file;
+ sector_t blocks[MAX_BUF_PER_PAGE];
+ unsigned page_block;
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ int length;
+ unsigned relative_block = 0;
+ struct ext4_map_blocks map;
+
+ map.m_pblk = 0;
+ map.m_lblk = 0;
+ map.m_len = 0;
+ map.m_flags = 0;
+
+ for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+ int fully_mapped = 1;
+ unsigned first_hole = blocks_per_page;
+
+ prefetchw(&page->flags);
+ if (pages) {
+ page = list_entry(pages->prev, struct page, lru);
+ list_del(&page->lru);
+ if (add_to_page_cache_lru(page, mapping,
+ page->index, GFP_KERNEL))
+ goto next_page;
+ }
+
+ if (page_has_buffers(page))
+ goto confused;
+
+ block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+ last_block = block_in_file + nr_pages * blocks_per_page;
+ last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+ if (last_block > last_block_in_file)
+ last_block = last_block_in_file;
+ page_block = 0;
+
+ /*
+ * Map blocks using the previous result first.
+ */
+ if ((map.m_flags & EXT4_MAP_MAPPED) &&
+ block_in_file > map.m_lblk &&
+ block_in_file < (map.m_lblk + map.m_len)) {
+ unsigned map_offset = block_in_file - map.m_lblk;
+ unsigned last = map.m_len - map_offset;
+
+ for (relative_block = 0; ; relative_block++) {
+ if (relative_block == last) {
+ /* needed? */
+ map.m_flags &= ~EXT4_MAP_MAPPED;
+ break;
+ }
+ if (page_block == blocks_per_page)
+ break;
+ blocks[page_block] = map.m_pblk + map_offset +
+ relative_block;
+ page_block++;
+ block_in_file++;
+ }
+ }
+
+ /*
+ * Then do more ext4_map_blocks() calls until we are
+ * done with this page.
+ */
+ while (page_block < blocks_per_page) {
+ if (block_in_file < last_block) {
+ map.m_lblk = block_in_file;
+ map.m_len = last_block - block_in_file;
+
+ if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
+ set_error_page:
+ SetPageError(page);
+ zero_user_segment(page, 0,
+ PAGE_CACHE_SIZE);
+ unlock_page(page);
+ goto next_page;
+ }
+ }
+ if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
+ fully_mapped = 0;
+ if (first_hole == blocks_per_page)
+ first_hole = page_block;
+ page_block++;
+ block_in_file++;
+ continue;
+ }
+ if (first_hole != blocks_per_page)
+ goto confused; /* hole -> non-hole */
+
+ /* Contiguous blocks? */
+ if (page_block && blocks[page_block-1] != map.m_pblk-1)
+ goto confused;
+ for (relative_block = 0; ; relative_block++) {
+ if (relative_block == map.m_len) {
+ /* needed? */
+ map.m_flags &= ~EXT4_MAP_MAPPED;
+ break;
+ } else if (page_block == blocks_per_page)
+ break;
+ blocks[page_block] = map.m_pblk+relative_block;
+ page_block++;
+ block_in_file++;
+ }
+ }
+ if (first_hole != blocks_per_page) {
+ zero_user_segment(page, first_hole << blkbits,
+ PAGE_CACHE_SIZE);
+ if (first_hole == 0) {
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto next_page;
+ }
+ } else if (fully_mapped) {
+ SetPageMappedToDisk(page);
+ }
+ if (fully_mapped && blocks_per_page == 1 &&
+ !PageUptodate(page) && cleancache_get_page(page) == 0) {
+ SetPageUptodate(page);
+ goto confused;
+ }
+
+ /*
+ * This page will go to BIO. Do we need to send this
+ * BIO off first?
+ */
+ if (bio && (last_block_in_bio != blocks[0] - 1)) {
+ submit_and_realloc:
+ submit_bio(READ, bio);
+ bio = NULL;
+ }
+ if (bio == NULL) {
+ struct ext4_crypto_ctx *ctx = NULL;
+
+ if (ext4_encrypted_inode(inode) &&
+ S_ISREG(inode->i_mode)) {
+ ctx = ext4_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ goto set_error_page;
+ }
+ bio = bio_alloc(GFP_KERNEL,
+ min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+ if (!bio) {
+ if (ctx)
+ ext4_release_crypto_ctx(ctx);
+ goto set_error_page;
+ }
+ bio->bi_bdev = bdev;
+ bio->bi_sector = blocks[0] << (blkbits - 9);
+ bio->bi_end_io = mpage_end_io;
+ bio->bi_private = ctx;
+ }
+
+ length = first_hole << blkbits;
+ if (bio_add_page(bio, page, length, 0) < length)
+ goto submit_and_realloc;
+
+ if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
+ (relative_block == map.m_len)) ||
+ (first_hole != blocks_per_page)) {
+ submit_bio(READ, bio);
+ bio = NULL;
+ } else
+ last_block_in_bio = blocks[blocks_per_page - 1];
+ goto next_page;
+ confused:
+ if (bio) {
+ submit_bio(READ, bio);
+ bio = NULL;
+ }
+ if (!PageUptodate(page))
+ block_read_full_page(page, ext4_get_block);
+ else
+ unlock_page(page);
+ next_page:
+ if (pages)
+ page_cache_release(page);
+ }
+ BUG_ON(pages && !list_empty(pages));
+ if (bio)
+ submit_bio(READ, bio);
+ return 0;
+}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index cf0a704..d534e58 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -42,7 +42,7 @@
void ext4_resize_end(struct super_block *sb)
{
clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
@@ -79,12 +79,20 @@
ext4_fsblk_t end = start + input->blocks_count;
ext4_group_t group = input->group;
ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
- unsigned overhead = ext4_group_overhead_blocks(sb, group);
- ext4_fsblk_t metaend = start + overhead;
+ unsigned overhead;
+ ext4_fsblk_t metaend;
struct buffer_head *bh = NULL;
ext4_grpblk_t free_blocks_count, offset;
int err = -EINVAL;
+ if (group != sbi->s_groups_count) {
+ ext4_warning(sb, "Cannot add at group %u (only %u groups)",
+ input->group, sbi->s_groups_count);
+ return -EINVAL;
+ }
+
+ overhead = ext4_group_overhead_blocks(sb, group);
+ metaend = start + overhead;
input->free_blocks_count = free_blocks_count =
input->blocks_count - 2 - overhead - sbi->s_itb_per_group;
@@ -96,10 +104,7 @@
free_blocks_count, input->reserved_blocks);
ext4_get_group_no_and_offset(sb, start, NULL, &offset);
- if (group != sbi->s_groups_count)
- ext4_warning(sb, "Cannot add at group %u (only %u groups)",
- input->group, sbi->s_groups_count);
- else if (offset != 0)
+ if (offset != 0)
ext4_warning(sb, "Last group not full");
else if (input->reserved_blocks > input->blocks_count / 5)
ext4_warning(sb, "Reserved blocks too high (%u)",
@@ -343,6 +348,7 @@
bh = sb_getblk(sb, blk);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -421,6 +427,7 @@
if (unlikely(!bh))
return -ENOMEM;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
return err;
@@ -513,6 +520,7 @@
goto out;
}
+ BUFFER_TRACE(gdb, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb);
if (err) {
brelse(gdb);
@@ -567,6 +575,7 @@
bh = bclean(handle, sb, block);
if (IS_ERR(bh)) {
err = PTR_ERR(bh);
+ bh = NULL;
goto out;
}
overhead = ext4_group_overhead_blocks(sb, group);
@@ -595,6 +604,7 @@
bh = bclean(handle, sb, block);
if (IS_ERR(bh)) {
err = PTR_ERR(bh);
+ bh = NULL;
goto out;
}
@@ -785,14 +795,17 @@
goto exit_dind;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(dind, "get_write_access");
err = ext4_journal_get_write_access(handle, dind);
if (unlikely(err))
ext4_std_error(sb, err);
@@ -897,6 +910,7 @@
EXT4_SB(sb)->s_group_desc = n_group_desc;
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree(o_group_desc);
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
brelse(gdb_bh);
@@ -972,6 +986,7 @@
}
for (i = 0; i < reserved_gdb; i++) {
+ BUFFER_TRACE(primary[i], "get_write_access");
if ((err = ext4_journal_get_write_access(handle, primary[i])))
goto exit_bh;
}
@@ -1079,6 +1094,7 @@
ext4_debug("update metadata backup %llu(+%llu)\n",
backup_block, backup_block -
ext4_group_first_block_no(sb, group));
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh)))
break;
lock_buffer(bh);
@@ -1158,6 +1174,7 @@
*/
if (gdb_off) {
gdb_bh = sbi->s_group_desc[gdb_num];
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
@@ -1195,8 +1212,7 @@
{
struct buffer_head *bh;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return 0;
bh = ext4_get_bitmap(sb, group_data->inode_bitmap);
@@ -1428,6 +1444,7 @@
goto exit;
}
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto exit_journal;
@@ -1559,11 +1576,10 @@
int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
struct inode *inode = NULL;
- int gdb_off, gdb_num;
+ int gdb_off;
int err;
__u16 bg_flags = 0;
- gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
@@ -1641,6 +1657,7 @@
return err;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) {
ext4_warning(sb, "error %d on journal write access", err);
@@ -1800,6 +1817,7 @@
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 15a8189..43deaf0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -59,6 +59,7 @@
static struct ext4_lazy_init *ext4_li_info;
static struct mutex ext4_li_mtx;
static struct ext4_features *ext4_feat;
+static int ext4_mballoc_ready;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
@@ -136,11 +137,10 @@
return cpu_to_le32(csum);
}
-int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es)
+static int ext4_superblock_csum_verify(struct super_block *sb,
+ struct ext4_super_block *es)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return 1;
return es->s_checksum == ext4_superblock_csum(sb, es);
@@ -150,8 +150,7 @@
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(sb))
return;
es->s_checksum = ext4_superblock_csum(sb, es);
@@ -161,7 +160,7 @@
{
void *ret;
- ret = kmalloc(size, flags);
+ ret = kmalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags, PAGE_KERNEL);
return ret;
@@ -171,7 +170,7 @@
{
void *ret;
- ret = kzalloc(size, flags);
+ ret = kzalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
return ret;
@@ -305,6 +304,8 @@
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (bdev_read_only(sb->s_bdev))
+ return;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
es->s_last_error_time = cpu_to_le32(get_seconds());
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
@@ -398,37 +399,44 @@
}
if (test_opt(sb, ERRORS_RO)) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+ /*
+ * Make sure updated value of ->s_mount_flags will be visible
+ * before ->s_flags update
+ */
+ smp_wmb();
sb->s_flags |= MS_RDONLY;
}
- if (test_opt(sb, ERRORS_PANIC)) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
+ if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
- }
}
+#define ext4_error_ratelimit(sb) \
+ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \
+ "EXT4-fs error")
+
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
- sb->s_id, function, line, current->comm, &vaf);
- va_end(args);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
+ sb->s_id, function, line, current->comm, &vaf);
+ va_end(args);
+ }
save_error_info(sb, function, line);
-
ext4_handle_error(sb);
}
-void ext4_error_inode(struct inode *inode, const char *function,
- unsigned int line, ext4_fsblk_t block,
- const char *fmt, ...)
+void __ext4_error_inode(struct inode *inode, const char *function,
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
struct va_format vaf;
@@ -436,28 +444,29 @@
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: block %llu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, &vaf);
+ else
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: block %llu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, &vaf);
- else
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
-void ext4_error_file(struct file *file, const char *function,
- unsigned int line, ext4_fsblk_t block,
- const char *fmt, ...)
+void __ext4_error_file(struct file *file, const char *function,
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
struct va_format vaf;
@@ -467,27 +476,28 @@
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (IS_ERR(path))
+ path = "(unknown)";
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "block %llu: comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, path, &vaf);
+ else
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, path, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- path = d_path(&(file->f_path), pathname, sizeof(pathname));
- if (IS_ERR(path))
- path = "(unknown)";
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "block %llu: comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, path, &vaf);
- else
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, path, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
@@ -541,11 +551,13 @@
(sb->s_flags & MS_RDONLY))
return;
- errstr = ext4_decode_error(sb, errno, nbuf);
- printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
- sb->s_id, function, line, errstr);
- save_error_info(sb, function, line);
+ if (ext4_error_ratelimit(sb)) {
+ errstr = ext4_decode_error(sb, errno, nbuf);
+ printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
+ sb->s_id, function, line, errstr);
+ }
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
@@ -574,25 +586,30 @@
if ((sb->s_flags & MS_RDONLY) == 0) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ /*
+ * Make sure updated value of ->s_mount_flags will be visible
+ * before ->s_flags update
+ */
+ smp_wmb();
+ sb->s_flags |= MS_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
}
- if (test_opt(sb, ERRORS_PANIC)) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
+ if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs panic from previous error\n");
- }
}
-void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+void __ext4_msg(struct super_block *sb,
+ const char *prefix, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
@@ -606,6 +623,10 @@
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+ "EXT4-fs warning"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
@@ -629,18 +650,20 @@
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
- sb->s_id, function, line, grp);
- if (ino)
- printk(KERN_CONT "inode %lu: ", ino);
- if (block)
- printk(KERN_CONT "block %llu:", (unsigned long long) block);
- printk(KERN_CONT "%pV\n", &vaf);
- va_end(args);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
+ sb->s_id, function, line, grp);
+ if (ino)
+ printk(KERN_CONT "inode %lu: ", ino);
+ if (block)
+ printk(KERN_CONT "block %llu:",
+ (unsigned long long) block);
+ printk(KERN_CONT "%pV\n", &vaf);
+ va_end(args);
+ }
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
@@ -758,8 +781,8 @@
ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
- flush_workqueue(sbi->dio_unwritten_wq);
- destroy_workqueue(sbi->dio_unwritten_wq);
+ flush_workqueue(sbi->rsv_conversion_wq);
+ destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
@@ -768,8 +791,8 @@
ext4_abort(sb, "Couldn't clean up the journal");
}
- ext4_es_unregister_shrinker(sb);
- del_timer(&sbi->s_err_report);
+ ext4_es_unregister_shrinker(sbi);
+ del_timer_sync(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
@@ -796,10 +819,9 @@
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
- percpu_counter_destroy(&sbi->s_extent_cache_cnt);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
- for (i = 0; i < MAXQUOTAS; i++)
+ for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
@@ -811,7 +833,6 @@
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
- sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
@@ -823,6 +844,10 @@
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
+ if (sbi->s_mb_cache) {
+ ext4_xattr_destroy_cache(sbi->s_mb_cache);
+ sbi->s_mb_cache = NULL;
+ }
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
sb->s_fs_info = NULL;
@@ -852,12 +877,15 @@
return NULL;
ei->vfs_inode.i_version = 1;
+ spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
rwlock_init(&ei->i_es_lock);
INIT_LIST_HEAD(&ei->i_es_lru);
+ ei->i_es_all_nr = 0;
ei->i_es_lru_nr = 0;
+ ei->i_touch_when = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
@@ -868,14 +896,16 @@
ei->i_reserved_quota = 0;
#endif
ei->jinode = NULL;
- INIT_LIST_HEAD(&ei->i_completed_io_list);
+ INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
atomic_set(&ei->i_unwritten, 0);
- INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work);
-
+ INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ ei->i_crypt_info = NULL;
+#endif
return &ei->vfs_inode;
}
@@ -917,7 +947,7 @@
inode_init_once(&ei->vfs_inode);
}
-static int init_inodecache(void)
+static int __init init_inodecache(void)
{
ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
sizeof(struct ext4_inode_info),
@@ -953,6 +983,10 @@
jbd2_free_inode(EXT4_I(inode)->jinode);
EXT4_I(inode)->jinode = NULL;
}
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ if (EXT4_I(inode)->i_crypt_info)
+ ext4_free_encryption_info(inode, EXT4_I(inode)->i_crypt_info);
+#endif
}
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
@@ -1095,24 +1129,6 @@
.bdev_try_to_free_page = bdev_try_to_free_page,
};
-static const struct super_operations ext4_nojournal_sops = {
- .alloc_inode = ext4_alloc_inode,
- .destroy_inode = ext4_destroy_inode,
- .write_inode = ext4_write_inode,
- .dirty_inode = ext4_dirty_inode,
- .drop_inode = ext4_drop_inode,
- .evict_inode = ext4_evict_inode,
- .put_super = ext4_put_super,
- .statfs = ext4_statfs,
- .remount_fs = ext4_remount,
- .show_options = ext4_show_options,
-#ifdef CONFIG_QUOTA
- .quota_read = ext4_quota_read,
- .quota_write = ext4_quota_write,
-#endif
- .bdev_try_to_free_page = bdev_try_to_free_page,
-};
-
static const struct export_operations ext4_export_ops = {
.fh_to_dentry = ext4_fh_to_dentry,
.fh_to_parent = ext4_fh_to_parent,
@@ -1125,10 +1141,10 @@
Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
- Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
- Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
+ Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
+ Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
- Opt_data_err_abort, Opt_data_err_ignore,
+ Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
@@ -1170,6 +1186,7 @@
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_dev, "journal_dev=%u"},
+ {Opt_journal_path, "journal_path=%s"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
@@ -1213,6 +1230,7 @@
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
+ {Opt_test_dummy_encryption, "test_dummy_encryption"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
@@ -1329,6 +1347,7 @@
#define MOPT_NO_EXT2 0x0100
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
+#define MOPT_STRING 0x0400
static const struct mount_opts {
int token;
@@ -1378,6 +1397,7 @@
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
{Opt_journal_dev, 0, MOPT_GTE0},
+ {Opt_journal_path, 0, MOPT_STRING},
{Opt_journal_ioprio, 0, MOPT_GTE0},
{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
@@ -1409,6 +1429,7 @@
{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
+ {Opt_test_dummy_encryption, 0, MOPT_GTE0},
{Opt_err, 0, 0}
};
@@ -1471,7 +1492,7 @@
return -1;
}
- if (args->from && match_int(args, &arg))
+ if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
@@ -1533,6 +1554,44 @@
return -1;
}
*journal_devnum = arg;
+ } else if (token == Opt_journal_path) {
+ char *journal_path;
+ struct inode *journal_inode;
+ struct path path;
+ int error;
+
+ if (is_remount) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
+ return -1;
+ }
+ journal_path = match_strdup(&args[0]);
+ if (!journal_path) {
+ ext4_msg(sb, KERN_ERR, "error: could not dup "
+ "journal device string");
+ return -1;
+ }
+
+ error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+ if (error) {
+ ext4_msg(sb, KERN_ERR, "error: could not find "
+ "journal device path: error %d", error);
+ kfree(journal_path);
+ return -1;
+ }
+
+ journal_inode = path.dentry->d_inode;
+ if (!S_ISBLK(journal_inode->i_mode)) {
+ ext4_msg(sb, KERN_ERR, "error: journal path %s "
+ "is not a block device", journal_path);
+ path_put(&path);
+ kfree(journal_path);
+ return -1;
+ }
+
+ *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+ path_put(&path);
+ kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
if (arg > 7) {
ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
@@ -1541,6 +1600,15 @@
}
*journal_ioprio =
IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
+ } else if (token == Opt_test_dummy_encryption) {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION;
+ ext4_msg(sb, KERN_WARNING,
+ "Test dummy encryption mode enabled");
+#else
+ ext4_msg(sb, KERN_WARNING,
+ "Test dummy encryption mount option ignored");
+#endif
} else if (m->flags & MOPT_DATAJ) {
if (is_remount) {
if (!sbi->s_journal)
@@ -1824,7 +1892,7 @@
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
- else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+ else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
@@ -1902,7 +1970,6 @@
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
ext4_group_t flex_group;
- unsigned int groups_per_flex = 0;
int i, err;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
@@ -1910,7 +1977,6 @@
sbi->s_log_groups_per_flex = 0;
return 1;
}
- groups_per_flex = 1U << sbi->s_log_groups_per_flex;
err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
if (err)
@@ -1940,8 +2006,7 @@
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
- if ((sbi->s_es->s_feature_ro_compat &
- cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) {
+ if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
__le16 save_csum;
__u32 csum32;
@@ -2070,10 +2135,6 @@
}
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
-
- ext4_free_blocks_count_set(sbi->s_es,
- EXT4_C2B(sbi, ext4_count_free_clusters(sb)));
- sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
return 1;
}
@@ -2123,7 +2184,7 @@
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
/* don't clear list on RO mount w/ errors */
if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
- jbd_debug(1, "Errors on filesystem, "
+ ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
"clearing orphan list.\n");
es->s_last_orphan = 0;
}
@@ -2139,7 +2200,7 @@
/* Needed for iput() to work correctly and not trash data */
sb->s_flags |= MS_ACTIVE;
/* Turn on quotas so that they are updated correctly */
- for (i = 0; i < MAXQUOTAS; i++) {
+ for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (EXT4_SB(sb)->s_qf_names[i]) {
int ret = ext4_quota_on_mount(sb, i);
if (ret < 0)
@@ -2172,19 +2233,22 @@
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
dquot_initialize(inode);
if (inode->i_nlink) {
- ext4_msg(sb, KERN_DEBUG,
- "%s: truncating inode %lu to %lld bytes",
- __func__, inode->i_ino, inode->i_size);
+ if (test_opt(sb, DEBUG))
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: truncating inode %lu to %lld bytes",
+ __func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
mutex_lock(&inode->i_mutex);
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
mutex_unlock(&inode->i_mutex);
nr_truncates++;
} else {
- ext4_msg(sb, KERN_DEBUG,
- "%s: deleting unreferenced inode %lu",
- __func__, inode->i_ino);
+ if (test_opt(sb, DEBUG))
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: deleting unreferenced inode %lu",
+ __func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
@@ -2202,7 +2266,7 @@
PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
/* Turn quotas off */
- for (i = 0; i < MAXQUOTAS; i++) {
+ for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
dquot_quota_off(sb, i);
}
@@ -2338,6 +2402,16 @@
if (ext4_bg_has_super(sb, bg))
has_super = 1;
+ /*
+ * If we have a meta_bg fs with 1k blocks, group 0's GDT is at
+ * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
+ * on modern mke2fs or blksize > 1k on older mke2fs) then we must
+ * compensate.
+ */
+ if (sb->s_blocksize == 1024 && nr == 0 &&
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+ has_super++;
+
return (has_super + ext4_group_first_block_no(sb, bg));
}
@@ -2385,7 +2459,10 @@
ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
const char *, size_t);
- int offset;
+ union {
+ int offset;
+ int deprecated_val;
+ } u;
};
static int parse_strtoull(const char *buf,
@@ -2454,7 +2531,7 @@
static ssize_t sbi_ui_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+ unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}
@@ -2463,7 +2540,7 @@
struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+ unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
unsigned long t;
int ret;
@@ -2474,6 +2551,16 @@
return count;
}
+static ssize_t es_ui_show(struct ext4_attr *a,
+ struct ext4_sb_info *sbi, char *buf)
+{
+
+ unsigned int *ui = (unsigned int *) (((char *) sbi->s_es) +
+ a->u.offset);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
static ssize_t reserved_clusters_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
@@ -2512,22 +2599,53 @@
return count;
}
+static ssize_t sbi_deprecated_show(struct ext4_attr *a,
+ struct ext4_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val);
+}
+
#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.show = _show, \
.store = _store, \
- .offset = offsetof(struct ext4_sb_info, _elname), \
+ .u = { \
+ .offset = offsetof(struct ext4_sb_info, _elname),\
+ }, \
}
+
+#define EXT4_ATTR_OFFSET_ES(_name,_mode,_show,_store,_elname) \
+static struct ext4_attr ext4_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = _mode }, \
+ .show = _show, \
+ .store = _store, \
+ .u = { \
+ .offset = offsetof(struct ext4_super_block, _elname), \
+ }, \
+}
+
#define EXT4_ATTR(name, mode, show, store) \
static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
+
+#define EXT4_RO_ATTR_ES_UI(name, elname) \
+ EXT4_ATTR_OFFSET_ES(name, 0444, es_ui_show, NULL, elname)
#define EXT4_RW_ATTR_SBI_UI(name, elname) \
EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
+
#define ATTR_LIST(name) &ext4_attr_##name.attr
+#define EXT4_DEPRECATED_ATTR(_name, _val) \
+static struct ext4_attr ext4_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0444 }, \
+ .show = sbi_deprecated_show, \
+ .u = { \
+ .deprecated_val = _val, \
+ }, \
+}
EXT4_RO_ATTR(delayed_allocation_blocks);
EXT4_RO_ATTR(session_write_kbytes);
@@ -2542,9 +2660,18 @@
EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
-EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
+EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
+EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
+EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
@@ -2562,6 +2689,15 @@
ATTR_LIST(max_writeback_mb_bump),
ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
+ ATTR_LIST(err_ratelimit_interval_ms),
+ ATTR_LIST(err_ratelimit_burst),
+ ATTR_LIST(warning_ratelimit_interval_ms),
+ ATTR_LIST(warning_ratelimit_burst),
+ ATTR_LIST(msg_ratelimit_interval_ms),
+ ATTR_LIST(msg_ratelimit_burst),
+ ATTR_LIST(errors_count),
+ ATTR_LIST(first_error_time),
+ ATTR_LIST(last_error_time),
NULL,
};
@@ -2569,11 +2705,13 @@
EXT4_INFO_ATTR(lazy_itable_init);
EXT4_INFO_ATTR(batched_discard);
EXT4_INFO_ATTR(meta_bg_resize);
+EXT4_INFO_ATTR(encryption);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(batched_discard),
ATTR_LIST(meta_bg_resize),
+ ATTR_LIST(encryption),
NULL,
};
@@ -2621,9 +2759,25 @@
complete(&ext4_feat->f_kobj_unregister);
}
+static ssize_t ext4_feat_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "supported\n");
+}
+
+/*
+ * We can not use ext4_attr_show/store because it relies on the kobject
+ * being embedded in the ext4_sb_info structure which is definitely not
+ * true in this case.
+ */
+static const struct sysfs_ops ext4_feat_ops = {
+ .show = ext4_feat_show,
+ .store = NULL,
+};
+
static struct kobj_type ext4_feat_ktype = {
.default_attrs = ext4_feat_attrs,
- .sysfs_ops = &ext4_attr_ops,
+ .sysfs_ops = &ext4_feat_ops,
.release = ext4_feat_release,
};
@@ -2977,7 +3131,6 @@
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr;
- unsigned long rnd;
elr = kzalloc(sizeof(*elr), GFP_KERNEL);
if (!elr)
@@ -2992,10 +3145,8 @@
* spread the inode table initialization requests
* better.
*/
- get_random_bytes(&rnd, sizeof(rnd));
- elr->lr_next_sched = jiffies + (unsigned long)rnd %
- (EXT4_DEF_LI_MAX_START_DELAY * HZ);
-
+ elr->lr_next_sched = jiffies + (prandom_u32() %
+ (EXT4_DEF_LI_MAX_START_DELAY * HZ));
return elr;
}
@@ -3080,17 +3231,20 @@
int compat, incompat;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
- /* journal checksum v2 */
+ if (ext4_has_metadata_csum(sb)) {
+ /* journal checksum v3 */
compat = 0;
- incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+ incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
} else {
/* journal checksum v1 */
compat = JBD2_FEATURE_COMPAT_CHECKSUM;
incompat = 0;
}
+ jbd2_journal_clear_features(sbi->s_journal,
+ JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+ JBD2_FEATURE_INCOMPAT_CSUM_V3 |
+ JBD2_FEATURE_INCOMPAT_CSUM_V2);
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ret = jbd2_journal_set_features(sbi->s_journal,
compat, 0,
@@ -3103,10 +3257,8 @@
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else {
- jbd2_journal_clear_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
- JBD2_FEATURE_INCOMPAT_CSUM_V2);
+ jbd2_journal_clear_features(sbi->s_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
}
return ret;
@@ -3244,7 +3396,7 @@
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
- * uninitialized extents in delalloc path. In most cases such
+ * unwritten extents in delalloc path. In most cases such
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
@@ -3336,7 +3488,7 @@
logical_sb_block = sb_block;
}
- if (!(bh = sb_bread(sb, logical_sb_block))) {
+ if (!(bh = sb_bread_unmovable(sb, logical_sb_block))) {
ext4_msg(sb, KERN_ERR, "unable to read superblock");
goto out_fail;
}
@@ -3387,8 +3539,7 @@
}
/* Precompute checksum seed for all metadata */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (ext4_has_metadata_csum(sb))
sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
sizeof(es->s_uuid));
@@ -3406,6 +3557,10 @@
#ifdef CONFIG_EXT4_FS_POSIX_ACL
set_opt(sb, POSIX_ACL);
#endif
+ /* don't forget to enable journal_csum when metadata_csum is enabled. */
+ if (ext4_has_metadata_csum(sb))
+ set_opt(sb, JOURNAL_CHECKSUM);
+
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
@@ -3419,8 +3574,8 @@
set_opt(sb, ERRORS_CONT);
else
set_opt(sb, ERRORS_RO);
- if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
- set_opt(sb, BLOCK_VALIDITY);
+ /* block_validity enabled by default; disable with noblock_validity */
+ set_opt(sb, BLOCK_VALIDITY);
if (def_mount_opts & EXT4_DEFM_DISCARD)
set_opt(sb, DISCARD);
@@ -3487,6 +3642,16 @@
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
+ if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
+ set_opt2(sb, HURD_COMPAT);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_64BIT)) {
+ ext4_msg(sb, KERN_ERR,
+ "The Hurd can't support 64-bit file systems");
+ goto failed_mount;
+ }
+ }
+
if (IS_EXT2_SB(sb)) {
if (ext2_feature_set_ok(sb))
ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
@@ -3525,6 +3690,13 @@
goto failed_mount;
}
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) &&
+ es->s_encryption_level) {
+ ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
+ es->s_encryption_level);
+ goto failed_mount;
+ }
+
if (sb->s_blocksize != blocksize) {
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
@@ -3536,7 +3708,7 @@
brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
- bh = sb_bread(sb, logical_sb_block);
+ bh = sb_bread_unmovable(sb, logical_sb_block);
if (!bh) {
ext4_msg(sb, KERN_ERR,
"Can't read superblock on 2nd try");
@@ -3758,7 +3930,7 @@
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logical_sb_block, i);
- sbi->s_group_desc[i] = sb_bread(sb, block);
+ sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
if (!sbi->s_group_desc[i]) {
ext4_msg(sb, KERN_ERR,
"can't read group descriptor %d", i);
@@ -3770,13 +3942,6 @@
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
goto failed_mount2;
}
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
- if (!ext4_fill_flex_info(sb)) {
- ext4_msg(sb, KERN_ERR,
- "unable to initialize "
- "flex_bg meta info!");
- goto failed_mount2;
- }
sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
@@ -3787,41 +3952,16 @@
sbi->s_err_report.data = (unsigned long) sb;
/* Register extent status tree shrinker */
- ext4_es_register_shrinker(sb);
-
- err = percpu_counter_init(&sbi->s_freeclusters_counter,
- ext4_count_free_clusters(sb));
- if (!err) {
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0);
- }
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
+ if (ext4_es_register_shrinker(sbi))
goto failed_mount3;
- }
sbi->s_stripe = ext4_get_stripe_size(sbi);
- sbi->s_max_writeback_mb_bump = 128;
sbi->s_extent_max_zeroout_kb = 32;
/*
* set up enough so that it can read an inode
*/
- if (!test_opt(sb, NOLOAD) &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
- sb->s_op = &ext4_sops;
- else
- sb->s_op = &ext4_nojournal_sops;
+ sb->s_op = &ext4_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
@@ -3845,7 +3985,7 @@
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
!(sb->s_flags & MS_RDONLY))
if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
- goto failed_mount3;
+ goto failed_mount3a;
/*
* The first inode we look at is the journal inode. Don't try
@@ -3854,7 +3994,7 @@
if (!test_opt(sb, NOLOAD) &&
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
if (ext4_load_journal(sb, es, journal_devnum))
- goto failed_mount3;
+ goto failed_mount3a;
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
@@ -3910,19 +4050,22 @@
sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
- /*
- * The journal may have updated the bg summary counts, so we
- * need to update the global counters.
- */
- percpu_counter_set(&sbi->s_freeclusters_counter,
- ext4_count_free_clusters(sb));
- percpu_counter_set(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- percpu_counter_set(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
-
no_journal:
+ if (ext4_mballoc_ready) {
+ sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
+ if (!sbi->s_mb_cache) {
+ ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+ goto failed_mount_wq;
+ }
+ }
+
+ if (unlikely(sbi->s_mount_flags & EXT4_MF_TEST_DUMMY_ENCRYPTION) &&
+ !(sb->s_flags & MS_RDONLY) &&
+ !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) {
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT);
+ ext4_commit_super(sb, 1);
+ }
+
/*
* Get the # of file system overhead blocks from the
* superblock if present.
@@ -3939,12 +4082,12 @@
* The maximum number of concurrent works can be high and
* concurrency isn't really necessary. Limit it to 1.
*/
- EXT4_SB(sb)->dio_unwritten_wq =
- alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
- if (!EXT4_SB(sb)->dio_unwritten_wq) {
- printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+ EXT4_SB(sb)->rsv_conversion_wq =
+ alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+ if (!EXT4_SB(sb)->rsv_conversion_wq) {
+ printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
ret = -ENOMEM;
- goto failed_mount_wq;
+ goto failed_mount4;
}
/*
@@ -4021,6 +4164,33 @@
goto failed_mount5;
}
+ block = ext4_count_free_clusters(sb);
+ ext4_free_blocks_count_set(sbi->s_es,
+ EXT4_C2B(sbi, block));
+ err = percpu_counter_init(&sbi->s_freeclusters_counter, block);
+ if (!err) {
+ unsigned long freei = ext4_count_free_inodes(sb);
+ sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
+ err = percpu_counter_init(&sbi->s_freeinodes_counter, freei);
+ }
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount6;
+ }
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ if (!ext4_fill_flex_info(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "unable to initialize "
+ "flex_bg meta info!");
+ goto failed_mount6;
+ }
+
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
goto failed_mount6;
@@ -4074,6 +4244,11 @@
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
+ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */
+ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+
kfree(orig_data);
return 0;
@@ -4090,6 +4265,12 @@
ext4_unregister_li_request(sb);
failed_mount6:
ext4_mb_release(sb);
+ if (sbi->s_flex_groups)
+ ext4_kvfree(sbi->s_flex_groups);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
failed_mount5:
ext4_ext_release(sb);
ext4_release_system_zone(sb);
@@ -4098,22 +4279,17 @@
sb->s_root = NULL;
failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
- destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+ if (EXT4_SB(sb)->rsv_conversion_wq)
+ destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
failed_mount_wq:
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
+failed_mount3a:
+ ext4_es_unregister_shrinker(sbi);
failed_mount3:
- ext4_es_unregister_shrinker(sb);
- del_timer(&sbi->s_err_report);
- if (sbi->s_flex_groups)
- ext4_kvfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeclusters_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
- percpu_counter_destroy(&sbi->s_extent_cache_cnt);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
@@ -4128,7 +4304,7 @@
remove_proc_entry(sb->s_id, ext4_proc_root);
}
#ifdef CONFIG_QUOTA
- for (i = 0; i < MAXQUOTAS; i++)
+ for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
ext4_blkdev_remove(sbi);
@@ -4256,6 +4432,15 @@
goto out_bdev;
}
+ if ((le32_to_cpu(es->s_feature_ro_compat) &
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+ es->s_checksum != ext4_superblock_csum(sb, es)) {
+ ext4_msg(sb, KERN_ERR, "external journal has "
+ "corrupt superblock");
+ brelse(bh);
+ goto out_bdev;
+ }
+
if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
ext4_msg(sb, KERN_ERR, "journal UUID does not match");
brelse(bh);
@@ -4430,11 +4615,13 @@
else
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
- ext4_free_blocks_count_set(es,
+ if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+ ext4_free_blocks_count_set(es,
EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeclusters_counter)));
- es->s_free_inodes_count =
- cpu_to_le32(percpu_counter_sum_positive(
+ if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+ es->s_free_inodes_count =
+ cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
@@ -4541,19 +4728,41 @@
{
int ret = 0;
tid_t target;
+ bool needs_barrier = false;
struct ext4_sb_info *sbi = EXT4_SB(sb);
trace_ext4_sync_fs(sb, wait);
- flush_workqueue(sbi->dio_unwritten_wq);
+ flush_workqueue(sbi->rsv_conversion_wq);
/*
* Writeback quota in non-journalled quota case - journalled quota has
* no dirty dquots
*/
dquot_writeback_dquots(sb, -1);
- if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
- if (wait)
- jbd2_log_wait_commit(sbi->s_journal, target);
+ /*
+ * Data writeback is possible w/o journal transaction, so barrier must
+ * being sent at the end of the function. But we can skip it if
+ * transaction_commit will do it for us.
+ */
+ if (sbi->s_journal) {
+ target = jbd2_get_latest_transaction(sbi->s_journal);
+ if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
+ !jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
+ needs_barrier = true;
+
+ if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
+ if (wait)
+ ret = jbd2_log_wait_commit(sbi->s_journal,
+ target);
+ }
+ } else if (wait && test_opt(sb, BARRIER))
+ needs_barrier = true;
+ if (needs_barrier) {
+ int err;
+ err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+ if (!ret)
+ ret = err;
}
+
return ret;
}
@@ -4575,23 +4784,26 @@
journal = EXT4_SB(sb)->s_journal;
- /* Now we set up the journal barrier. */
- jbd2_journal_lock_updates(journal);
+ if (journal) {
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
- /*
- * Don't clear the needs_recovery flag if we failed to flush
- * the journal.
- */
- error = jbd2_journal_flush(journal);
- if (error < 0)
- goto out;
+ /*
+ * Don't clear the needs_recovery flag if we failed to
+ * flush the journal.
+ */
+ error = jbd2_journal_flush(journal);
+ if (error < 0)
+ goto out;
+ }
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
out:
- /* we rely on upper layer to stop further updates */
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ if (journal)
+ /* we rely on upper layer to stop further updates */
+ jbd2_journal_unlock_updates(journal);
return error;
}
@@ -4622,7 +4834,7 @@
u32 s_min_batch_time, s_max_batch_time;
#ifdef CONFIG_QUOTA
int s_jquota_fmt;
- char *s_qf_names[MAXQUOTAS];
+ char *s_qf_names[EXT4_MAXQUOTAS];
#endif
};
@@ -4652,7 +4864,7 @@
old_opts.s_max_batch_time = sbi->s_max_batch_time;
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
- for (i = 0; i < MAXQUOTAS; i++)
+ for (i = 0; i < EXT4_MAXQUOTAS; i++)
if (sbi->s_qf_names[i]) {
old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
GFP_KERNEL);
@@ -4676,6 +4888,14 @@
goto restore_opts;
}
+ if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
+ test_opt(sb, JOURNAL_CHECKSUM)) {
+ ext4_msg(sb, KERN_ERR, "changing journal_checksum "
+ "during remount not supported");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
@@ -4711,6 +4931,9 @@
}
if (*flags & MS_RDONLY) {
+ err = sync_filesystem(sb);
+ if (err < 0)
+ goto restore_opts;
err = dquot_suspend(sb, -1);
if (err < 0)
goto restore_opts;
@@ -4810,7 +5033,7 @@
#ifdef CONFIG_QUOTA
/* Release old quota file names */
- for (i = 0; i < MAXQUOTAS; i++)
+ for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(old_opts.s_qf_names[i]);
if (enable_quota) {
if (sb_any_quota_suspended(sb))
@@ -4839,7 +5062,7 @@
sbi->s_max_batch_time = old_opts.s_max_batch_time;
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
- for (i = 0; i < MAXQUOTAS; i++) {
+ for (i = 0; i < EXT4_MAXQUOTAS; i++) {
kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
@@ -5060,7 +5283,7 @@
{
int err;
struct inode *qf_inode;
- unsigned long qf_inums[MAXQUOTAS] = {
+ unsigned long qf_inums[EXT4_MAXQUOTAS] = {
le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
};
@@ -5091,13 +5314,13 @@
static int ext4_enable_quotas(struct super_block *sb)
{
int type, err = 0;
- unsigned long qf_inums[MAXQUOTAS] = {
+ unsigned long qf_inums[EXT4_MAXQUOTAS] = {
le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
};
sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
- for (type = 0; type < MAXQUOTAS; type++) {
+ for (type = 0; type < EXT4_MAXQUOTAS; type++) {
if (qf_inums[type]) {
err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
DQUOT_USAGE_ENABLED);
@@ -5175,7 +5398,6 @@
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
- int err = 0;
int offset = off & (sb->s_blocksize - 1);
int tocopy;
size_t toread;
@@ -5190,9 +5412,9 @@
while (toread > 0) {
tocopy = sb->s_blocksize - offset < toread ?
sb->s_blocksize - offset : toread;
- bh = ext4_bread(NULL, inode, blk, 0, &err);
- if (err)
- return err;
+ bh = ext4_bread(NULL, inode, blk, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
if (!bh) /* A hole? */
memset(data, 0, tocopy);
else
@@ -5213,8 +5435,7 @@
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
- int err = 0;
- int offset = off & (sb->s_blocksize - 1);
+ int err, offset = off & (sb->s_blocksize - 1);
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
@@ -5235,13 +5456,16 @@
return -EIO;
}
- bh = ext4_bread(handle, inode, blk, 1, &err);
+ bh = ext4_bread(handle, inode, blk, 1);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
if (!bh)
goto out;
+ BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
- goto out;
+ return err;
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, len);
@@ -5250,8 +5474,6 @@
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
out:
- if (err)
- return err;
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
@@ -5413,11 +5635,9 @@
err = ext4_init_mballoc();
if (err)
- goto out3;
-
- err = ext4_init_xattr();
- if (err)
goto out2;
+ else
+ ext4_mballoc_ready = 1;
err = init_inodecache();
if (err)
goto out1;
@@ -5433,10 +5653,9 @@
unregister_as_ext3();
destroy_inodecache();
out1:
- ext4_exit_xattr();
-out2:
+ ext4_mballoc_ready = 0;
ext4_exit_mballoc();
-out3:
+out2:
ext4_exit_feat_adverts();
out4:
if (ext4_proc_root)
@@ -5454,12 +5673,12 @@
static void __exit ext4_exit_fs(void)
{
+ ext4_exit_crypto();
ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
- ext4_exit_xattr();
ext4_exit_mballoc();
ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index ff37119..4f68e83 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -23,8 +23,93 @@
#include "ext4.h"
#include "xattr.h"
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
{
+ struct page *cpage = NULL;
+ char *caddr, *paddr = NULL;
+ struct ext4_str cstr, pstr;
+ struct inode *inode = dentry->d_inode;
+ struct ext4_encrypted_symlink_data *sd;
+ loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
+ int res;
+ u32 plen, max_size = inode->i_sb->s_blocksize;
+
+ if (!ext4_encrypted_inode(inode))
+ return page_follow_link_light(dentry, nd);
+
+ res = ext4_get_encryption_info(inode);
+ if (res)
+ return ERR_PTR(res);
+
+ if (ext4_inode_is_fast_symlink(inode)) {
+ caddr = (char *) EXT4_I(dentry->d_inode)->i_data;
+ max_size = sizeof(EXT4_I(dentry->d_inode)->i_data);
+ } else {
+ cpage = read_mapping_page(inode->i_mapping, 0, NULL);
+ if (IS_ERR(cpage))
+ return cpage;
+ caddr = kmap(cpage);
+ caddr[size] = 0;
+ }
+
+ /* Symlink is encrypted */
+ sd = (struct ext4_encrypted_symlink_data *)caddr;
+ cstr.name = sd->encrypted_path;
+ cstr.len = le32_to_cpu(sd->len);
+ if ((cstr.len +
+ sizeof(struct ext4_encrypted_symlink_data) - 1) >
+ max_size) {
+ /* Symlink data on the disk is corrupted */
+ res = -EIO;
+ goto errout;
+ }
+ plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ?
+ EXT4_FNAME_CRYPTO_DIGEST_SIZE*2 : cstr.len;
+ paddr = kmalloc(plen + 1, GFP_NOFS);
+ if (!paddr) {
+ res = -ENOMEM;
+ goto errout;
+ }
+ pstr.name = paddr;
+ pstr.len = plen;
+ res = _ext4_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+ if (res < 0)
+ goto errout;
+ /* Null-terminate the name */
+ if (res <= plen)
+ paddr[res] = '\0';
+ nd_set_link(nd, paddr);
+ if (cpage) {
+ kunmap(cpage);
+ page_cache_release(cpage);
+ }
+ return NULL;
+errout:
+ if (cpage) {
+ kunmap(cpage);
+ page_cache_release(cpage);
+ }
+ kfree(paddr);
+ return ERR_PTR(res);
+}
+
+static void ext4_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ struct page *page = cookie;
+
+ if (!page) {
+ kfree(nd_get_link(nd));
+ } else {
+ kunmap(page);
+ page_cache_release(page);
+ }
+}
+#endif
+
+static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd)
+{
struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
nd_set_link(nd, (char *) ei->i_data);
return NULL;
@@ -32,8 +117,13 @@
const struct inode_operations ext4_symlink_inode_operations = {
.readlink = generic_readlink,
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+ .follow_link = ext4_follow_link,
+ .put_link = ext4_put_link,
+#else
.follow_link = page_follow_link_light,
.put_link = page_put_link,
+#endif
.setattr = ext4_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
@@ -43,7 +133,7 @@
const struct inode_operations ext4_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ext4_follow_link,
+ .follow_link = ext4_follow_fast_link,
.setattr = ext4_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index a20816e..1e09fc7 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -81,7 +81,7 @@
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
-static void ext4_xattr_cache_insert(struct buffer_head *);
+static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct ext4_xattr_header *,
struct mb_cache_entry **);
@@ -90,13 +90,11 @@
static int ext4_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
-static struct mb_cache *ext4_xattr_cache;
-
static const struct xattr_handler *ext4_xattr_handler_map[] = {
[EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
- [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &ext4_xattr_acl_access_handler,
- [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
+ [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
+ [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
[EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_SECURITY
@@ -108,8 +106,8 @@
&ext4_xattr_user_handler,
&ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
- &ext4_xattr_acl_access_handler,
- &ext4_xattr_acl_default_handler,
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_EXT4_FS_SECURITY
&ext4_xattr_security_handler,
@@ -117,6 +115,9 @@
NULL
};
+#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \
+ inode->i_sb->s_fs_info)->s_mb_cache)
+
static __le32 ext4_xattr_block_csum(struct inode *inode,
sector_t block_nr,
struct ext4_xattr_header *hdr)
@@ -141,8 +142,7 @@
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+ if (ext4_has_metadata_csum(inode->i_sb) &&
(hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
return 0;
return 1;
@@ -152,8 +152,7 @@
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return;
hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
@@ -280,6 +279,7 @@
struct ext4_xattr_entry *entry;
size_t size;
int error;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
@@ -301,7 +301,7 @@
error = -EIO;
goto cleanup;
}
- ext4_xattr_cache_insert(bh);
+ ext4_xattr_cache_insert(ext4_mb_cache, bh);
entry = BFIRST(bh);
error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
if (error == -EIO)
@@ -382,6 +382,9 @@
{
int error;
+ if (strlen(name) > 255)
+ return -ERANGE;
+
down_read(&EXT4_I(inode)->xattr_sem);
error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
buffer_size);
@@ -424,6 +427,7 @@
struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
int error;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
@@ -445,7 +449,7 @@
error = -EIO;
goto cleanup;
}
- ext4_xattr_cache_insert(bh);
+ ext4_xattr_cache_insert(ext4_mb_cache, bh);
error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
@@ -525,6 +529,7 @@
if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
return;
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
ext4_handle_dirty_super(handle, sb);
@@ -541,8 +546,10 @@
{
struct mb_cache_entry *ce = NULL;
int error = 0;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
- ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
+ ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
+ BUFFER_TRACE(bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bh);
if (error)
goto out;
@@ -597,12 +604,13 @@
size_t *min_offs, void *base, int *total)
{
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
- *total += EXT4_XATTR_LEN(last->e_name_len);
if (!last->e_value_block && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < *min_offs)
*min_offs = offs;
}
+ if (total)
+ *total += EXT4_XATTR_LEN(last->e_name_len);
}
return (*min_offs - ((void *)last - base) - sizeof(__u32));
}
@@ -775,14 +783,16 @@
struct ext4_xattr_search *s = &bs->s;
struct mb_cache_entry *ce = NULL;
int error = 0;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
#define header(x) ((struct ext4_xattr_header *)(x))
if (i->value && i->value_len > sb->s_blocksize)
return -ENOSPC;
if (s->base) {
- ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev,
+ ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
bs->bh->b_blocknr);
+ BUFFER_TRACE(bs->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
goto cleanup;
@@ -799,7 +809,8 @@
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base),
s->here);
- ext4_xattr_cache_insert(bs->bh);
+ ext4_xattr_cache_insert(ext4_mb_cache,
+ bs->bh);
}
unlock_buffer(bs->bh);
if (error == -EIO)
@@ -867,6 +878,7 @@
EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
+ BUFFER_TRACE(new_bh, "get_write_access");
error = ext4_journal_get_write_access(handle,
new_bh);
if (error)
@@ -900,14 +912,8 @@
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
- /*
- * take i_data_sem because we will test
- * i_delalloc_reserved_flag in ext4_mb_new_blocks
- */
- down_read((&EXT4_I(inode)->i_data_sem));
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
- up_read((&EXT4_I(inode)->i_data_sem));
if (error)
goto cleanup;
@@ -935,7 +941,7 @@
memcpy(new_bh->b_data, s->base, new_bh->b_size);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
- ext4_xattr_cache_insert(new_bh);
+ ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
error = ext4_handle_dirty_xattr_block(handle,
inode, new_bh);
if (error)
@@ -1259,7 +1265,7 @@
struct ext4_xattr_block_find *bs = NULL;
char *buffer = NULL, *b_entry_name = NULL;
size_t min_offs, free;
- int total_ino, total_blk;
+ int total_ino;
void *base, *start, *end;
int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
@@ -1317,8 +1323,7 @@
first = BFIRST(bh);
end = bh->b_data + bh->b_size;
min_offs = end - base;
- free = ext4_xattr_free_space(first, &min_offs, base,
- &total_blk);
+ free = ext4_xattr_free_space(first, &min_offs, base, NULL);
if (free < new_extra_isize) {
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
@@ -1526,13 +1531,13 @@
* Returns 0, or a negative error number on failure.
*/
static void
-ext4_xattr_cache_insert(struct buffer_head *bh)
+ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
{
__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
struct mb_cache_entry *ce;
int error;
- ce = mb_cache_entry_alloc(ext4_xattr_cache, GFP_NOFS);
+ ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
if (!ce) {
ea_bdebug(bh, "out of memory");
return;
@@ -1604,12 +1609,13 @@
{
__u32 hash = le32_to_cpu(header->h_hash);
struct mb_cache_entry *ce;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
again:
- ce = mb_cache_entry_find_first(ext4_xattr_cache, inode->i_sb->s_bdev,
+ ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
hash);
while (ce) {
struct buffer_head *bh;
@@ -1707,19 +1713,17 @@
#undef BLOCK_HASH_SHIFT
-int __init
-ext4_init_xattr(void)
+#define HASH_BUCKET_BITS 10
+
+struct mb_cache *
+ext4_xattr_create_cache(char *name)
{
- ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
- if (!ext4_xattr_cache)
- return -ENOMEM;
- return 0;
+ return mb_cache_create(name, HASH_BUCKET_BITS);
}
-void
-ext4_exit_xattr(void)
+void ext4_xattr_destroy_cache(struct mb_cache *cache)
{
- if (ext4_xattr_cache)
- mb_cache_destroy(ext4_xattr_cache);
- ext4_xattr_cache = NULL;
+ if (cache)
+ mb_cache_destroy(cache);
}
+
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index c767dbd..ddc0957 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -23,6 +23,7 @@
#define EXT4_XATTR_INDEX_SECURITY 6
#define EXT4_XATTR_INDEX_SYSTEM 7
#define EXT4_XATTR_INDEX_RICHACL 8
+#define EXT4_XATTR_INDEX_ENCRYPTION 9
struct ext4_xattr_header {
__le32 h_magic; /* magic number for identification */
@@ -96,10 +97,10 @@
extern const struct xattr_handler ext4_xattr_user_handler;
extern const struct xattr_handler ext4_xattr_trusted_handler;
-extern const struct xattr_handler ext4_xattr_acl_access_handler;
-extern const struct xattr_handler ext4_xattr_acl_default_handler;
extern const struct xattr_handler ext4_xattr_security_handler;
+#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
+
extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
@@ -112,9 +113,6 @@
extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
struct ext4_inode *raw_inode, handle_t *handle);
-extern int __init ext4_init_xattr(void);
-extern void ext4_exit_xattr(void);
-
extern const struct xattr_handler *ext4_xattr_handlers[];
extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
@@ -126,6 +124,9 @@
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is);
+extern struct mb_cache *ext4_xattr_create_cache(char *name);
+extern void ext4_xattr_destroy_cache(struct mb_cache *);
+
#ifdef CONFIG_EXT4_FS_SECURITY
extern int ext4_init_security(handle_t *handle, struct inode *inode,
struct inode *dir, const struct qstr *qstr);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 91ff93b..6a03029 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -445,6 +445,15 @@
return 0;
}
+static int get_data_block_bmap(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ /* Block number less than F2FS MAX BLOCKS */
+ if (unlikely(iblock >= max_file_size(0)))
+ return -EFBIG;
+ return get_data_block_ro(inode, iblock, bh_result, create);
+}
+
static int f2fs_read_data_page(struct file *file, struct page *page)
{
return mpage_readpage(page, get_data_block_ro);
@@ -698,7 +707,8 @@
get_data_block_ro);
}
-static void f2fs_invalidate_data_page(struct page *page, unsigned long offset)
+static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -731,7 +741,7 @@
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
- return generic_block_bmap(mapping, block, get_data_block_ro);
+ return generic_block_bmap(mapping, block, get_data_block_bmap);
}
const struct address_space_operations f2fs_dblock_aops = {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 20aab02..8aeea5d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -928,6 +928,7 @@
/*
* super.c
*/
+loff_t max_file_size(unsigned bits);
int f2fs_sync_fs(struct super_block *, int);
extern __printf(3, 4)
void f2fs_msg(struct super_block *, const char *, const char *, ...);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 3df43b4..74f3c7b 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1205,7 +1205,8 @@
return 0;
}
-static void f2fs_invalidate_node_page(struct page *page, unsigned long offset)
+static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8555f7d..9f3bbc5 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -239,7 +239,6 @@
if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
seq_puts(seq, ",disable_ext_identify");
- seq_printf(seq, ",active_logs=%u", sbi->active_logs);
return 0;
}
@@ -376,7 +375,7 @@
return 0;
}
-static loff_t max_file_size(unsigned bits)
+loff_t max_file_size(unsigned bits)
{
loff_t result = ADDRS_PER_INODE;
loff_t leaf_count = ADDRS_PER_BLOCK;
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 7a6f02c..4b775e6 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -776,6 +776,13 @@
return ret;
}
+static int fat_ioctl_volume_id(struct inode *dir)
+{
+ struct super_block *sb = dir->i_sb;
+ struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ return sbi->vol_id;
+}
+
static long fat_dir_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
@@ -792,6 +799,8 @@
short_only = 0;
both = 1;
break;
+ case VFAT_IOCTL_GET_VOLUME_ID:
+ return fat_ioctl_volume_id(inode);
default:
return fat_generic_ioctl(filp, cmd, arg);
}
@@ -832,6 +841,8 @@
short_only = 0;
both = 1;
break;
+ case VFAT_IOCTL_GET_VOLUME_ID:
+ return fat_ioctl_volume_id(inode);
default:
return fat_generic_ioctl(filp, cmd, (unsigned long)arg);
}
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 21664fc..8180ece 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -86,6 +86,7 @@
const void *dir_ops; /* Opaque; default directory operations */
int dir_per_block; /* dir entries per block */
int dir_per_block_bits; /* log2(dir_per_block) */
+ unsigned long vol_id; /* volume ID */
int fatent_shift;
struct fatent_operations *fatent_ops;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 5d4513c..ebdc665 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -632,6 +632,8 @@
struct msdos_sb_info *sbi = MSDOS_SB(sb);
*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
+ sync_filesystem(sb);
+
/* make sure we update state on remount. */
new_rdonly = *flags & MS_RDONLY;
if (new_rdonly != (sb->s_flags & MS_RDONLY)) {
@@ -1252,6 +1254,7 @@
struct inode *fsinfo_inode = NULL;
struct buffer_head *bh;
struct fat_boot_sector *b;
+ struct fat_boot_bsx *bsx;
struct msdos_sb_info *sbi;
u16 logical_sector_size;
u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors;
@@ -1398,6 +1401,8 @@
goto out_fail;
}
+ bsx = (struct fat_boot_bsx *)(bh->b_data + FAT32_BSX_OFFSET);
+
fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data;
if (!IS_FSINFO(fsinfo)) {
fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: "
@@ -1413,8 +1418,14 @@
}
brelse(fsinfo_bh);
+ } else {
+ bsx = (struct fat_boot_bsx *)(bh->b_data + FAT16_BSX_OFFSET);
}
+ /* interpret volume ID as a little endian 32 bit integer */
+ sbi->vol_id = (((u32)bsx->vol_id[0]) | ((u32)bsx->vol_id[1] << 8) |
+ ((u32)bsx->vol_id[2] << 16) | ((u32)bsx->vol_id[3] << 24));
+
sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
diff --git a/fs/file_table.c b/fs/file_table.c
index 28f02a7..cd4ef34 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -36,6 +36,8 @@
.max_files = NR_FILE
};
+DEFINE_STATIC_LGLOCK(files_lglock);
+
/* SLAB cache for file structures */
static struct kmem_cache *filp_cachep __read_mostly;
@@ -132,6 +134,7 @@
return ERR_PTR(error);
}
+ INIT_LIST_HEAD(&f->f_u.fu_list);
atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
spin_lock_init(&f->f_lock);
@@ -301,6 +304,7 @@
if (atomic_long_dec_and_test(&file->f_count)) {
struct task_struct *task = current;
+ file_sb_list_del(file);
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
init_task_work(&file->f_u.fu_rcuhead, ____fput);
if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
@@ -324,6 +328,7 @@
{
if (atomic_long_dec_and_test(&file->f_count)) {
struct task_struct *task = current;
+ file_sb_list_del(file);
BUG_ON(!(task->flags & PF_KTHREAD));
__fput(file);
}
@@ -335,10 +340,127 @@
{
if (atomic_long_dec_and_test(&file->f_count)) {
security_file_free(file);
+ file_sb_list_del(file);
file_free(file);
}
}
+static inline int file_list_cpu(struct file *file)
+{
+#ifdef CONFIG_SMP
+ return file->f_sb_list_cpu;
+#else
+ return smp_processor_id();
+#endif
+}
+
+/* helper for file_sb_list_add to reduce ifdefs */
+static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
+{
+ struct list_head *list;
+#ifdef CONFIG_SMP
+ int cpu;
+ cpu = smp_processor_id();
+ file->f_sb_list_cpu = cpu;
+ list = per_cpu_ptr(sb->s_files, cpu);
+#else
+ list = &sb->s_files;
+#endif
+ list_add(&file->f_u.fu_list, list);
+}
+
+/**
+ * file_sb_list_add - add a file to the sb's file list
+ * @file: file to add
+ * @sb: sb to add it to
+ *
+ * Use this function to associate a file with the superblock of the inode it
+ * refers to.
+ */
+void file_sb_list_add(struct file *file, struct super_block *sb)
+{
+ lg_local_lock(&files_lglock);
+ __file_sb_list_add(file, sb);
+ lg_local_unlock(&files_lglock);
+}
+
+/**
+ * file_sb_list_del - remove a file from the sb's file list
+ * @file: file to remove
+ * @sb: sb to remove it from
+ *
+ * Use this function to remove a file from its superblock.
+ */
+void file_sb_list_del(struct file *file)
+{
+ if (!list_empty(&file->f_u.fu_list)) {
+ lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
+ list_del_init(&file->f_u.fu_list);
+ lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
+ }
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * These macros iterate all files on all CPUs for a given superblock.
+ * files_lglock must be held globally.
+ */
+#define do_file_list_for_each_entry(__sb, __file) \
+{ \
+ int i; \
+ for_each_possible_cpu(i) { \
+ struct list_head *list; \
+ list = per_cpu_ptr((__sb)->s_files, i); \
+ list_for_each_entry((__file), list, f_u.fu_list)
+
+#define while_file_list_for_each_entry \
+ } \
+}
+
+#else
+
+#define do_file_list_for_each_entry(__sb, __file) \
+{ \
+ struct list_head *list; \
+ list = &(sb)->s_files; \
+ list_for_each_entry((__file), list, f_u.fu_list)
+
+#define while_file_list_for_each_entry \
+}
+
+#endif
+
+/**
+ * mark_files_ro - mark all files read-only
+ * @sb: superblock in question
+ *
+ * All files are marked read-only. We don't care about pending
+ * delete files so this should be used in 'force' mode only.
+ */
+void mark_files_ro(struct super_block *sb)
+{
+ struct file *f;
+
+ lg_global_lock(&files_lglock);
+ do_file_list_for_each_entry(sb, f) {
+ if (!S_ISREG(file_inode(f)->i_mode))
+ continue;
+ if (!file_count(f))
+ continue;
+ if (!(f->f_mode & FMODE_WRITE))
+ continue;
+ spin_lock(&f->f_lock);
+ f->f_mode &= ~FMODE_WRITE;
+ spin_unlock(&f->f_lock);
+ if (file_check_writeable(f) != 0)
+ continue;
+ __mnt_drop_write(f->f_path.mnt);
+ file_release_write(f);
+ } while_file_list_for_each_entry;
+ lg_global_unlock(&files_lglock);
+}
+
void __init files_init(unsigned long mempages)
{
unsigned long n;
@@ -354,5 +476,6 @@
n = (mempages * (PAGE_SIZE / 1024)) / 10;
files_stat.max_files = max_t(unsigned long, n, NR_FILE);
files_defer_init();
+ lg_lock_init(&files_lglock, "files_lglock");
percpu_counter_init(&nr_files, 0);
}
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index e37eb27..7ca8c75 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -124,6 +124,7 @@
static int vxfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index b443063..8d6005c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -45,6 +45,7 @@
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
+ unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
@@ -456,9 +457,11 @@
/*
* Make sure to wait on the data before writing out the metadata.
* This is important for filesystems that modify metadata on data
- * I/O completion.
+ * I/O completion. We don't do it for sync(2) writeback because it has a
+ * separate, external IO completion path and ->sync_fs for guaranteeing
+ * inode metadata is written back correctly.
*/
- if (wbc->sync_mode == WB_SYNC_ALL) {
+ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
@@ -610,6 +613,7 @@
.tagged_writepages = work->tagged_writepages,
.for_kupdate = work->for_kupdate,
.for_background = work->for_background,
+ .for_sync = work->for_sync,
.range_cyclic = work->range_cyclic,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -1170,7 +1174,7 @@
if ((inode->i_state & flags) == flags)
return;
- if (unlikely(block_dump))
+ if (unlikely(block_dump > 1))
block_dump___mark_inode_dirty(inode);
spin_lock(&inode->i_lock);
@@ -1393,6 +1397,7 @@
.range_cyclic = 0,
.done = &done,
.reason = WB_REASON_SYNC,
+ .for_sync = 1,
};
/* Nothing to do? */
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index b535008..69eee30 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -13,6 +13,7 @@
#include <linux/poll.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
+#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>
@@ -20,6 +21,7 @@
#include <linux/swap.h>
#include <linux/splice.h>
#include <linux/aio.h>
+#include <linux/freezer.h>
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
@@ -464,7 +466,10 @@
* Wait it out.
*/
spin_unlock(&fc->lock);
- wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+
+ while (req->state != FUSE_REQ_FINISHED)
+ wait_event_freezable(req->waitq,
+ req->state == FUSE_REQ_FINISHED);
spin_lock(&fc->lock);
if (!req->aborted)
@@ -1870,6 +1875,10 @@
spin_unlock(&fc->lock);
err = copy_out_args(cs, &req->out, nbytes);
+ if (req->in.h.opcode == FUSE_CANONICAL_PATH) {
+ req->out.h.error = kern_path((char *)req->out.args[0].value, 0,
+ req->canonical_path);
+ }
fuse_copy_finish(cs);
spin_lock(&fc->lock);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index e67b13d..7668bbc 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -252,6 +252,50 @@
return 1;
}
+/*
+ * Get the canonical path. Since we must translate to a path, this must be done
+ * in the context of the userspace daemon, however, the userspace daemon cannot
+ * look up paths on its own. Instead, we handle the lookup as a special case
+ * inside of the write request.
+ */
+static void fuse_dentry_canonical_path(const struct path *path, struct path *canonical_path) {
+ struct inode *inode = path->dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_req *req;
+ int err;
+ char *path_name;
+
+ req = fuse_get_req(fc, 1);
+ err = PTR_ERR(req);
+ if (IS_ERR(req))
+ goto default_path;
+
+ path_name = (char*)__get_free_page(GFP_KERNEL);
+ if (!path_name) {
+ fuse_put_request(fc, req);
+ goto default_path;
+ }
+
+ req->in.h.opcode = FUSE_CANONICAL_PATH;
+ req->in.h.nodeid = get_node_id(inode);
+ req->in.numargs = 0;
+ req->out.numargs = 1;
+ req->out.args[0].size = PATH_MAX;
+ req->out.args[0].value = path_name;
+ req->canonical_path = canonical_path;
+ req->out.argvar = 1;
+ fuse_request_send(fc, req);
+ err = req->out.h.error;
+ fuse_put_request(fc, req);
+ free_page((unsigned long)path_name);
+ if (!err)
+ return;
+default_path:
+ canonical_path->dentry = path->dentry;
+ canonical_path->mnt = path->mnt;
+ path_get(canonical_path);
+}
+
static int invalid_nodeid(u64 nodeid)
{
return !nodeid || nodeid == FUSE_ROOT_ID;
@@ -259,6 +303,7 @@
const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
+ .d_canonical_path = fuse_dentry_canonical_path,
};
int fuse_valid_type(int m)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 5ced199..93f861a 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -348,6 +348,9 @@
/** Inode used in the request or NULL */
struct inode *inode;
+ /** Path used for completing d_canonical_path */
+ struct path *canonical_path;
+
/** AIO control block */
struct fuse_io_priv *io;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index efe802e..0526f12e 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -135,6 +135,7 @@
static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
if (*flags & MS_MANDLOCK)
return -EINVAL;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 7625160..e8de950 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -110,7 +110,7 @@
/* Is the page fully outside i_size? (truncate in progress) */
offset = i_size & (PAGE_CACHE_SIZE-1);
if (page->index > end_index || (page->index == end_index && !offset)) {
- page->mapping->a_ops->invalidatepage(page, 0);
+ page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
goto out;
}
return 1;
@@ -299,7 +299,8 @@
/* Is the page fully outside i_size? (truncate in progress) */
if (page->index > end_index || (page->index == end_index && !offset)) {
- page->mapping->a_ops->invalidatepage(page, 0);
+ page->mapping->a_ops->invalidatepage(page, 0,
+ PAGE_CACHE_SIZE);
unlock_page(page);
continue;
}
@@ -943,7 +944,8 @@
unlock_buffer(bh);
}
-static void gfs2_invalidatepage(struct page *page, unsigned long offset)
+static void gfs2_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
struct buffer_head *bh, *head;
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9973df4..7102c7a 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -88,7 +88,10 @@
struct inode *dir = parent->d_inode;
struct inode *inode = child->d_inode;
struct gfs2_inode *dip, *ip;
- struct get_name_filldir gnfd;
+ struct get_name_filldir gnfd = {
+ .ctx.actor = get_name_filldir,
+ .name = name
+ };
struct gfs2_holder gh;
u64 offset = 0;
int error;
@@ -106,7 +109,6 @@
*name = 0;
gnfd.inum.no_addr = ip->i_no_addr;
gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
- gnfd.name = name;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
if (error)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index e5639de..db7fff5 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1142,6 +1142,8 @@
struct gfs2_tune *gt = &sdp->sd_tune;
int error;
+ sync_filesystem(sb);
+
spin_lock(>->gt_spin);
args.ar_commit = gt->gt_logd_secs;
args.ar_quota_quantum = gt->gt_quota_quantum;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 2d2039e..eee7206 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -112,6 +112,7 @@
static int hfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_NODIRATIME;
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
return 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 4c4d142..1b9414f 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -323,6 +323,7 @@
static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
return 0;
if (!(*flags & MS_RDONLY)) {
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 2c1ce19..0d4b1f6 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -398,6 +398,8 @@
struct hpfs_sb_info *sbi = hpfs_sb(s);
char *new_opts = kstrdup(data, GFP_KERNEL);
+ sync_filesystem(s);
+
*flags |= MS_NOATIME;
hpfs_lock(s);
diff --git a/fs/inode.c b/fs/inode.c
index 17f95b4..dd1d22d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -980,6 +980,41 @@
EXPORT_SYMBOL(unlock_new_inode);
/**
+ * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ *
+ * Lock any non-NULL argument that is not a directory.
+ * Zero, one or two objects may be locked by this function.
+ *
+ * @inode1: first inode to lock
+ * @inode2: second inode to lock
+ */
+void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+ if (inode1 > inode2)
+ swap(inode1, inode2);
+
+ if (inode1 && !S_ISDIR(inode1->i_mode))
+ mutex_lock(&inode1->i_mutex);
+ if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
+}
+EXPORT_SYMBOL(lock_two_nondirectories);
+
+/**
+ * unlock_two_nondirectories - release locks from lock_two_nondirectories()
+ * @inode1: first inode to unlock
+ * @inode2: second inode to unlock
+ */
+void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+ if (inode1 && !S_ISDIR(inode1->i_mode))
+ mutex_unlock(&inode1->i_mutex);
+ if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
+ mutex_unlock(&inode2->i_mutex);
+}
+EXPORT_SYMBOL(unlock_two_nondirectories);
+
+/**
* iget5_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @hashval: hash value (usually inode number) to get
@@ -1900,3 +1935,34 @@
wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
EXPORT_SYMBOL(inode_dio_done);
+
+/*
+ * inode_set_flags - atomically set some inode flags
+ *
+ * Note: the caller should be holding i_mutex, or else be sure that
+ * they have exclusive access to the inode structure (i.e., while the
+ * inode is being instantiated). The reason for the cmpxchg() loop
+ * --- which wouldn't be necessary if all code paths which modify
+ * i_flags actually followed this rule, is that there is at least one
+ * code path which doesn't today --- for example,
+ * __generic_file_aio_write() calls file_remove_suid() without holding
+ * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ *
+ * In the long run, i_mutex is overkill, and we should probably look
+ * at using the i_lock spinlock to protect i_flags, and then make sure
+ * it is so documented in include/linux/fs.h and that all code follows
+ * the locking convention!!
+ */
+void inode_set_flags(struct inode *inode, unsigned int flags,
+ unsigned int mask)
+{
+ unsigned int old_flags, new_flags;
+
+ WARN_ON_ONCE(flags & ~mask);
+ do {
+ old_flags = ACCESS_ONCE(inode->i_flags);
+ new_flags = (old_flags & ~mask) | flags;
+ } while (unlikely(cmpxchg(&inode->i_flags, old_flags,
+ new_flags) != old_flags));
+}
+EXPORT_SYMBOL(inode_set_flags);
diff --git a/fs/internal.h b/fs/internal.h
index 2ffa65a..6812158 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -74,6 +74,9 @@
/*
* file_table.c
*/
+extern void file_sb_list_add(struct file *f, struct super_block *sb);
+extern void file_sb_list_del(struct file *f);
+extern void mark_files_ro(struct super_block *);
extern struct file *get_empty_filp(void);
/*
diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig
index 69a48c2..5a9f553 100644
--- a/fs/jbd2/Kconfig
+++ b/fs/jbd2/Kconfig
@@ -20,7 +20,7 @@
config JBD2_DEBUG
bool "JBD2 (ext4) debugging support"
- depends on JBD2 && DEBUG_FS
+ depends on JBD2
help
If you are using the ext4 journaled file system (or
potentially any other filesystem/device using JBD2), this option
@@ -29,7 +29,7 @@
By default, the debugging output will be turned off.
If you select Y here, then you will be able to turn on debugging
- with "echo N > /sys/kernel/debug/jbd2/jbd2-debug", where N is a
+ with "echo N > /sys/module/jbd2/parameters/jbd2_debug", where N is a
number between 1 and 5. The higher the number, the more debugging
output is generated. To turn debugging off again, do
- "echo 0 > /sys/kernel/debug/jbd2/jbd2-debug".
+ "echo 0 > /sys/module/jbd2/parameters/jbd2_debug".
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 6bb5285..4227dc4 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -96,15 +96,8 @@
if (jh->b_transaction == NULL && !buffer_locked(bh) &&
!buffer_dirty(bh) && !buffer_write_io_error(bh)) {
- /*
- * Get our reference so that bh cannot be freed before
- * we unlock it
- */
- get_bh(bh);
JBUFFER_TRACE(jh, "remove from checkpoint list");
ret = __jbd2_journal_remove_checkpoint(jh) + 1;
- BUFFER_TRACE(bh, "release");
- __brelse(bh);
}
return ret;
}
@@ -120,10 +113,8 @@
int nblocks, space_left;
/* assert_spin_locked(&journal->j_state_lock); */
- nblocks = jbd_space_needed(journal);
- while (__jbd2_log_space_left(journal) < nblocks) {
- if (journal->j_flags & JBD2_ABORT)
- return;
+ nblocks = jbd2_space_needed(journal);
+ while (jbd2_log_space_left(journal) < nblocks) {
write_unlock(&journal->j_state_lock);
mutex_lock(&journal->j_checkpoint_mutex);
@@ -139,9 +130,13 @@
* trace for forensic evidence.
*/
write_lock(&journal->j_state_lock);
+ if (journal->j_flags & JBD2_ABORT) {
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ return;
+ }
spin_lock(&journal->j_list_lock);
- nblocks = jbd_space_needed(journal);
- space_left = __jbd2_log_space_left(journal);
+ nblocks = jbd2_space_needed(journal);
+ space_left = jbd2_log_space_left(journal);
if (space_left < nblocks) {
int chkpt = journal->j_checkpoint_transactions != NULL;
tid_t tid = 0;
@@ -156,7 +151,15 @@
/* We were able to recover space; yay! */
;
} else if (tid) {
+ /*
+ * jbd2_journal_commit_transaction() may want
+ * to take the checkpoint_mutex if JBD2_FLUSHED
+ * is set. So we need to temporarily drop it.
+ */
+ mutex_unlock(&journal->j_checkpoint_mutex);
jbd2_log_wait_commit(journal, tid);
+ write_lock(&journal->j_state_lock);
+ continue;
} else {
printk(KERN_ERR "%s: needed %d blocks and "
"only had %d space available\n",
@@ -175,58 +178,6 @@
}
}
-/*
- * Clean up transaction's list of buffers submitted for io.
- * We wait for any pending IO to complete and remove any clean
- * buffers. Note that we take the buffers in the opposite ordering
- * from the one in which they were submitted for IO.
- *
- * Return 0 on success, and return <0 if some buffers have failed
- * to be written out.
- *
- * Called with j_list_lock held.
- */
-static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
-{
- struct journal_head *jh;
- struct buffer_head *bh;
- tid_t this_tid;
- int released = 0;
- int ret = 0;
-
- this_tid = transaction->t_tid;
-restart:
- /* Did somebody clean up the transaction in the meanwhile? */
- if (journal->j_checkpoint_transactions != transaction ||
- transaction->t_tid != this_tid)
- return ret;
- while (!released && transaction->t_checkpoint_io_list) {
- jh = transaction->t_checkpoint_io_list;
- bh = jh2bh(jh);
- get_bh(bh);
- if (buffer_locked(bh)) {
- spin_unlock(&journal->j_list_lock);
- wait_on_buffer(bh);
- /* the journal_head may have gone by now */
- BUFFER_TRACE(bh, "brelse");
- __brelse(bh);
- spin_lock(&journal->j_list_lock);
- goto restart;
- }
- if (unlikely(buffer_write_io_error(bh)))
- ret = -EIO;
-
- /*
- * Now in whatever state the buffer currently is, we know that
- * it has been written out and so we can drop it from the list
- */
- released = __jbd2_journal_remove_checkpoint(jh);
- __brelse(bh);
- }
-
- return ret;
-}
-
static void
__flush_batch(journal_t *journal, int *batch_count)
{
@@ -247,81 +198,6 @@
}
/*
- * Try to flush one buffer from the checkpoint list to disk.
- *
- * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list. Return <0 if the buffer has failed to
- * be written out.
- *
- * Called with j_list_lock held and drops it if 1 is returned
- */
-static int __process_buffer(journal_t *journal, struct journal_head *jh,
- int *batch_count, transaction_t *transaction)
-{
- struct buffer_head *bh = jh2bh(jh);
- int ret = 0;
-
- if (buffer_locked(bh)) {
- get_bh(bh);
- spin_unlock(&journal->j_list_lock);
- wait_on_buffer(bh);
- /* the journal_head may have gone by now */
- BUFFER_TRACE(bh, "brelse");
- __brelse(bh);
- ret = 1;
- } else if (jh->b_transaction != NULL) {
- transaction_t *t = jh->b_transaction;
- tid_t tid = t->t_tid;
-
- transaction->t_chp_stats.cs_forced_to_close++;
- spin_unlock(&journal->j_list_lock);
- if (unlikely(journal->j_flags & JBD2_UNMOUNT))
- /*
- * The journal thread is dead; so starting and
- * waiting for a commit to finish will cause
- * us to wait for a _very_ long time.
- */
- printk(KERN_ERR "JBD2: %s: "
- "Waiting for Godot: block %llu\n",
- journal->j_devname,
- (unsigned long long) bh->b_blocknr);
- jbd2_log_start_commit(journal, tid);
- jbd2_log_wait_commit(journal, tid);
- ret = 1;
- } else if (!buffer_dirty(bh)) {
- ret = 1;
- if (unlikely(buffer_write_io_error(bh)))
- ret = -EIO;
- get_bh(bh);
- BUFFER_TRACE(bh, "remove from checkpoint");
- __jbd2_journal_remove_checkpoint(jh);
- spin_unlock(&journal->j_list_lock);
- __brelse(bh);
- } else {
- /*
- * Important: we are about to write the buffer, and
- * possibly block, while still holding the journal lock.
- * We cannot afford to let the transaction logic start
- * messing around with this buffer before we write it to
- * disk, as that would break recoverability.
- */
- BUFFER_TRACE(bh, "queue");
- get_bh(bh);
- J_ASSERT_BH(bh, !buffer_jwrite(bh));
- journal->j_chkpt_bhs[*batch_count] = bh;
- __buffer_relink_io(jh);
- transaction->t_chp_stats.cs_written++;
- (*batch_count)++;
- if (*batch_count == JBD2_NR_BATCH) {
- spin_unlock(&journal->j_list_lock);
- __flush_batch(journal, batch_count);
- ret = 1;
- }
- }
- return ret;
-}
-
-/*
* Perform an actual checkpoint. We take the first transaction on the
* list of transactions to be checkpointed and send all its buffers
* to disk. We submit larger chunks of data at once.
@@ -331,9 +207,11 @@
*/
int jbd2_log_do_checkpoint(journal_t *journal)
{
- transaction_t *transaction;
- tid_t this_tid;
- int result;
+ struct journal_head *jh;
+ struct buffer_head *bh;
+ transaction_t *transaction;
+ tid_t this_tid;
+ int result, batch_count = 0;
jbd_debug(1, "Start checkpoint\n");
@@ -366,45 +244,117 @@
* done (maybe it's a new transaction, but it fell at the same
* address).
*/
- if (journal->j_checkpoint_transactions == transaction &&
- transaction->t_tid == this_tid) {
- int batch_count = 0;
- struct journal_head *jh;
- int retry = 0, err;
+ if (journal->j_checkpoint_transactions != transaction ||
+ transaction->t_tid != this_tid)
+ goto out;
- while (!retry && transaction->t_checkpoint_list) {
- jh = transaction->t_checkpoint_list;
- retry = __process_buffer(journal, jh, &batch_count,
- transaction);
- if (retry < 0 && !result)
- result = retry;
- if (!retry && (need_resched() ||
- spin_needbreak(&journal->j_list_lock))) {
- spin_unlock(&journal->j_list_lock);
- retry = 1;
- break;
- }
+ /* checkpoint all of the transaction's buffers */
+ while (transaction->t_checkpoint_list) {
+ jh = transaction->t_checkpoint_list;
+ bh = jh2bh(jh);
+
+ if (buffer_locked(bh)) {
+ spin_unlock(&journal->j_list_lock);
+ get_bh(bh);
+ wait_on_buffer(bh);
+ /* the journal_head may have gone by now */
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ goto retry;
}
+ if (jh->b_transaction != NULL) {
+ transaction_t *t = jh->b_transaction;
+ tid_t tid = t->t_tid;
- if (batch_count) {
- if (!retry) {
- spin_unlock(&journal->j_list_lock);
- retry = 1;
- }
- __flush_batch(journal, &batch_count);
+ transaction->t_chp_stats.cs_forced_to_close++;
+ spin_unlock(&journal->j_list_lock);
+ if (unlikely(journal->j_flags & JBD2_UNMOUNT))
+ /*
+ * The journal thread is dead; so
+ * starting and waiting for a commit
+ * to finish will cause us to wait for
+ * a _very_ long time.
+ */
+ printk(KERN_ERR
+ "JBD2: %s: Waiting for Godot: block %llu\n",
+ journal->j_devname, (unsigned long long) bh->b_blocknr);
+
+ jbd2_log_start_commit(journal, tid);
+ jbd2_log_wait_commit(journal, tid);
+ goto retry;
}
-
- if (retry) {
- spin_lock(&journal->j_list_lock);
- goto restart;
+ if (!buffer_dirty(bh)) {
+ if (unlikely(buffer_write_io_error(bh)) && !result)
+ result = -EIO;
+ BUFFER_TRACE(bh, "remove from checkpoint");
+ if (__jbd2_journal_remove_checkpoint(jh))
+ /* The transaction was released; we're done */
+ goto out;
+ continue;
}
/*
- * Now we have cleaned up the first transaction's checkpoint
- * list. Let's clean up the second one
+ * Important: we are about to write the buffer, and
+ * possibly block, while still holding the journal
+ * lock. We cannot afford to let the transaction
+ * logic start messing around with this buffer before
+ * we write it to disk, as that would break
+ * recoverability.
*/
- err = __wait_cp_io(journal, transaction);
- if (!result)
- result = err;
+ BUFFER_TRACE(bh, "queue");
+ get_bh(bh);
+ J_ASSERT_BH(bh, !buffer_jwrite(bh));
+ journal->j_chkpt_bhs[batch_count++] = bh;
+ __buffer_relink_io(jh);
+ transaction->t_chp_stats.cs_written++;
+ if ((batch_count == JBD2_NR_BATCH) ||
+ need_resched() ||
+ spin_needbreak(&journal->j_list_lock))
+ goto unlock_and_flush;
+ }
+
+ if (batch_count) {
+ unlock_and_flush:
+ spin_unlock(&journal->j_list_lock);
+ retry:
+ if (batch_count)
+ __flush_batch(journal, &batch_count);
+ spin_lock(&journal->j_list_lock);
+ goto restart;
+ }
+
+ /*
+ * Now we issued all of the transaction's buffers, let's deal
+ * with the buffers that are out for I/O.
+ */
+restart2:
+ /* Did somebody clean up the transaction in the meanwhile? */
+ if (journal->j_checkpoint_transactions != transaction ||
+ transaction->t_tid != this_tid)
+ goto out;
+
+ while (transaction->t_checkpoint_io_list) {
+ jh = transaction->t_checkpoint_io_list;
+ bh = jh2bh(jh);
+ if (buffer_locked(bh)) {
+ spin_unlock(&journal->j_list_lock);
+ get_bh(bh);
+ wait_on_buffer(bh);
+ /* the journal_head may have gone by now */
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ spin_lock(&journal->j_list_lock);
+ goto restart2;
+ }
+ if (unlikely(buffer_write_io_error(bh)) && !result)
+ result = -EIO;
+
+ /*
+ * Now in whatever state the buffer currently is, we
+ * know that it has been written out and so we can
+ * drop it from the list
+ */
+ if (__jbd2_journal_remove_checkpoint(jh))
+ break;
}
out:
spin_unlock(&journal->j_list_lock);
@@ -469,18 +419,16 @@
* Find all the written-back checkpoint buffers in the given list and
* release them.
*
- * Called with the journal locked.
* Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
+ * Returns 1 if we freed the transaction, 0 otherwise.
*/
-
-static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
+static int journal_clean_one_cp_list(struct journal_head *jh)
{
struct journal_head *last_jh;
struct journal_head *next_jh = jh;
- int ret, freed = 0;
+ int ret;
+ int freed = 0;
- *released = 0;
if (!jh)
return 0;
@@ -489,13 +437,11 @@
jh = next_jh;
next_jh = jh->b_cpnext;
ret = __try_to_free_cp_buf(jh);
- if (ret) {
- freed++;
- if (ret == 2) {
- *released = 1;
- return freed;
- }
- }
+ if (!ret)
+ return freed;
+ if (ret == 2)
+ return 1;
+ freed = 1;
/*
* This function only frees up some memory
* if possible so we dont have an obligation
@@ -514,49 +460,49 @@
*
* Find all the written-back checkpoint buffers in the journal and release them.
*
- * Called with the journal locked.
* Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
*/
-
-int __jbd2_journal_clean_checkpoint_list(journal_t *journal)
+void __jbd2_journal_clean_checkpoint_list(journal_t *journal)
{
transaction_t *transaction, *last_transaction, *next_transaction;
- int ret = 0;
- int released;
+ int ret;
transaction = journal->j_checkpoint_transactions;
if (!transaction)
- goto out;
+ return;
last_transaction = transaction->t_cpprev;
next_transaction = transaction;
do {
transaction = next_transaction;
next_transaction = transaction->t_cpnext;
- ret += journal_clean_one_cp_list(transaction->
- t_checkpoint_list, &released);
+ ret = journal_clean_one_cp_list(transaction->t_checkpoint_list);
/*
* This function only frees up some memory if possible so we
* dont have an obligation to finish processing. Bail out if
* preemption requested:
*/
if (need_resched())
- goto out;
- if (released)
+ return;
+ if (ret)
continue;
/*
* It is essential that we are as careful as in the case of
* t_checkpoint_list with removing the buffer from the list as
* we can possibly see not yet submitted buffers on io_list
*/
- ret += journal_clean_one_cp_list(transaction->
- t_checkpoint_io_list, &released);
+ ret = journal_clean_one_cp_list(transaction->
+ t_checkpoint_io_list);
if (need_resched())
- goto out;
+ return;
+ /*
+ * Stop scanning if we couldn't free the transaction. This
+ * avoids pointless scanning of transactions which still
+ * weren't checkpointed.
+ */
+ if (!ret)
+ return;
} while (transaction != last_transaction);
-out:
- return ret;
}
/*
@@ -624,10 +570,6 @@
__jbd2_journal_drop_transaction(journal, transaction);
jbd2_journal_free_transaction(transaction);
-
- /* Just in case anybody was waiting for more transactions to be
- checkpointed... */
- wake_up(&journal->j_wait_logspace);
ret = 1;
out:
return ret;
@@ -689,9 +631,7 @@
J_ASSERT(transaction->t_state == T_FINISHED);
J_ASSERT(transaction->t_buffers == NULL);
J_ASSERT(transaction->t_forget == NULL);
- J_ASSERT(transaction->t_iobuf_list == NULL);
J_ASSERT(transaction->t_shadow_list == NULL);
- J_ASSERT(transaction->t_log_list == NULL);
J_ASSERT(transaction->t_checkpoint_list == NULL);
J_ASSERT(transaction->t_checkpoint_io_list == NULL);
J_ASSERT(atomic_read(&transaction->t_updates) == 0);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 0f53946..b73e021 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -30,15 +30,22 @@
#include <trace/events/jbd2.h>
/*
- * Default IO end handler for temporary BJ_IO buffer_heads.
+ * IO end handler for temporary buffer_heads handling writes to the journal.
*/
static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
{
+ struct buffer_head *orig_bh = bh->b_private;
+
BUFFER_TRACE(bh, "");
if (uptodate)
set_buffer_uptodate(bh);
else
clear_buffer_uptodate(bh);
+ if (orig_bh) {
+ clear_bit_unlock(BH_Shadow, &orig_bh->b_state);
+ smp_mb__after_atomic();
+ wake_up_bit(&orig_bh->b_state, BH_Shadow);
+ }
unlock_buffer(bh);
}
@@ -85,21 +92,19 @@
__brelse(bh);
}
-static void jbd2_commit_block_csum_set(journal_t *j,
- struct journal_head *descriptor)
+static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
{
struct commit_header *h;
__u32 csum;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return;
- h = (struct commit_header *)(jh2bh(descriptor)->b_data);
+ h = (struct commit_header *)(bh->b_data);
h->h_chksum_type = 0;
h->h_chksum_size = 0;
h->h_chksum[0] = 0;
- csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data,
- j->j_blocksize);
+ csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
h->h_chksum[0] = cpu_to_be32(csum);
}
@@ -116,7 +121,6 @@
struct buffer_head **cbh,
__u32 crc32_sum)
{
- struct journal_head *descriptor;
struct commit_header *tmp;
struct buffer_head *bh;
int ret;
@@ -127,12 +131,10 @@
if (is_journal_aborted(journal))
return 0;
- descriptor = jbd2_journal_get_descriptor_buffer(journal);
- if (!descriptor)
+ bh = jbd2_journal_get_descriptor_buffer(journal);
+ if (!bh)
return 1;
- bh = jh2bh(descriptor);
-
tmp = (struct commit_header *)bh->b_data;
tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
@@ -146,9 +148,9 @@
tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE;
tmp->h_chksum[0] = cpu_to_be32(crc32_sum);
}
- jbd2_commit_block_csum_set(journal, descriptor);
+ jbd2_commit_block_csum_set(journal, bh);
- JBUFFER_TRACE(descriptor, "submit commit block");
+ BUFFER_TRACE(bh, "submit commit block");
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
@@ -180,7 +182,6 @@
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
put_bh(bh); /* One for getblk() */
- jbd2_journal_put_journal_head(bh2jh(bh));
return ret;
}
@@ -238,7 +239,7 @@
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
spin_unlock(&journal->j_list_lock);
@@ -276,7 +277,7 @@
}
spin_lock(&journal->j_list_lock);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
@@ -312,51 +313,53 @@
return checksum;
}
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
unsigned long long block)
{
tag->t_blocknr = cpu_to_be32(block & (u32)~0);
- if (tag_bytes > JBD2_TAG_SIZE32)
+ if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
}
static void jbd2_descr_block_csum_set(journal_t *j,
- struct journal_head *descriptor)
+ struct buffer_head *bh)
{
struct jbd2_journal_block_tail *tail;
__u32 csum;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return;
- tail = (struct jbd2_journal_block_tail *)
- (jh2bh(descriptor)->b_data + j->j_blocksize -
+ tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
sizeof(struct jbd2_journal_block_tail));
tail->t_checksum = 0;
- csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data,
- j->j_blocksize);
+ csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
tail->t_checksum = cpu_to_be32(csum);
}
static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
struct buffer_head *bh, __u32 sequence)
{
+ journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
struct page *page = bh->b_page;
__u8 *addr;
- __u32 csum;
+ __u32 csum32;
+ __be32 seq;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return;
- sequence = cpu_to_be32(sequence);
+ seq = cpu_to_be32(sequence);
addr = kmap_atomic(page);
- csum = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
- sizeof(sequence));
- csum = jbd2_chksum(j, csum, addr + offset_in_page(bh->b_data),
- bh->b_size);
+ csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
+ csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data),
+ bh->b_size);
kunmap_atomic(addr);
- tag->t_checksum = cpu_to_be32(csum);
+ if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+ tag3->t_checksum = cpu_to_be32(csum32);
+ else
+ tag->t_checksum = cpu_to_be16(csum32);
}
/*
* jbd2_journal_commit_transaction
@@ -368,7 +371,8 @@
{
struct transaction_stats_s stats;
transaction_t *commit_transaction;
- struct journal_head *jh, *new_jh, *descriptor;
+ struct journal_head *jh;
+ struct buffer_head *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
int flags;
@@ -392,8 +396,10 @@
tid_t first_tid;
int update_tail;
int csum_size = 0;
+ LIST_HEAD(io_bufs);
+ LIST_HEAD(log_bufs);
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
csum_size = sizeof(struct jbd2_journal_block_tail);
/*
@@ -424,13 +430,13 @@
J_ASSERT(journal->j_committing_transaction == NULL);
commit_transaction = journal->j_running_transaction;
- J_ASSERT(commit_transaction->t_state == T_RUNNING);
trace_jbd2_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD2: starting commit of transaction %d\n",
commit_transaction->t_tid);
write_lock(&journal->j_state_lock);
+ J_ASSERT(commit_transaction->t_state == T_RUNNING);
commit_transaction->t_state = T_LOCKED;
trace_jbd2_commit_locking(journal, commit_transaction);
@@ -520,6 +526,12 @@
*/
jbd2_journal_switch_revoke_table(journal);
+ /*
+ * Reserved credits cannot be claimed anymore, free them
+ */
+ atomic_sub(atomic_read(&journal->j_reserved_credits),
+ &commit_transaction->t_outstanding_credits);
+
trace_jbd2_commit_flushing(journal, commit_transaction);
stats.run.rs_flushing = jiffies;
stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,
@@ -533,7 +545,7 @@
wake_up(&journal->j_wait_transaction_locked);
write_unlock(&journal->j_state_lock);
- jbd_debug(3, "JBD2: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2a\n");
/*
* Now start flushing things to disk, in the order they appear
@@ -545,10 +557,9 @@
blk_start_plug(&plug);
jbd2_journal_write_revoke_records(journal, commit_transaction,
- WRITE_SYNC);
- blk_finish_plug(&plug);
+ &log_bufs, WRITE_SYNC);
- jbd_debug(3, "JBD2: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2b\n");
/*
* Way to go: we have now written out all of the data for a
@@ -571,9 +582,8 @@
atomic_read(&commit_transaction->t_outstanding_credits));
err = 0;
- descriptor = NULL;
bufs = 0;
- blk_start_plug(&plug);
+ descriptor = NULL;
while (commit_transaction->t_buffers) {
/* Find the next buffer to be journaled... */
@@ -604,8 +614,6 @@
record the metadata buffer. */
if (!descriptor) {
- struct buffer_head *bh;
-
J_ASSERT (bufs == 0);
jbd_debug(4, "JBD2: get descriptor\n");
@@ -616,26 +624,26 @@
continue;
}
- bh = jh2bh(descriptor);
jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
- (unsigned long long)bh->b_blocknr, bh->b_data);
- header = (journal_header_t *)&bh->b_data[0];
+ (unsigned long long)descriptor->b_blocknr,
+ descriptor->b_data);
+ header = (journal_header_t *)descriptor->b_data;
header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
- tagp = &bh->b_data[sizeof(journal_header_t)];
- space_left = bh->b_size - sizeof(journal_header_t);
+ tagp = &descriptor->b_data[sizeof(journal_header_t)];
+ space_left = descriptor->b_size -
+ sizeof(journal_header_t);
first_tag = 1;
- set_buffer_jwrite(bh);
- set_buffer_dirty(bh);
- wbuf[bufs++] = bh;
+ set_buffer_jwrite(descriptor);
+ set_buffer_dirty(descriptor);
+ wbuf[bufs++] = descriptor;
/* Record it so that we can wait for IO
completion later */
- BUFFER_TRACE(bh, "ph3: file as descriptor");
- jbd2_journal_file_buffer(descriptor, commit_transaction,
- BJ_LogCtl);
+ BUFFER_TRACE(descriptor, "ph3: file as descriptor");
+ jbd2_file_log_bh(&log_bufs, descriptor);
}
/* Where is the buffer to be written? */
@@ -658,29 +666,22 @@
/* Bump b_count to prevent truncate from stumbling over
the shadowed buffer! @@@ This can go if we ever get
- rid of the BJ_IO/BJ_Shadow pairing of buffers. */
+ rid of the shadow pairing of buffers. */
atomic_inc(&jh2bh(jh)->b_count);
- /* Make a temporary IO buffer with which to write it out
- (this will requeue both the metadata buffer and the
- temporary IO buffer). new_bh goes on BJ_IO*/
-
- set_bit(BH_JWrite, &jh2bh(jh)->b_state);
/*
- * akpm: jbd2_journal_write_metadata_buffer() sets
- * new_bh->b_transaction to commit_transaction.
- * We need to clean this up before we release new_bh
- * (which is of type BJ_IO)
+ * Make a temporary IO buffer with which to write it out
+ * (this will requeue the metadata buffer to BJ_Shadow).
*/
+ set_bit(BH_JWrite, &jh2bh(jh)->b_state);
JBUFFER_TRACE(jh, "ph3: write metadata");
flags = jbd2_journal_write_metadata_buffer(commit_transaction,
- jh, &new_jh, blocknr);
+ jh, &wbuf[bufs], blocknr);
if (flags < 0) {
jbd2_journal_abort(journal, flags);
continue;
}
- set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
- wbuf[bufs++] = jh2bh(new_jh);
+ jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
/* Record the new block's tag in the current descriptor
buffer */
@@ -692,12 +693,13 @@
tag_flag |= JBD2_FLAG_SAME_UUID;
tag = (journal_block_tag_t *) tagp;
- write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+ write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
tag->t_flags = cpu_to_be16(tag_flag);
- jbd2_block_tag_csum_set(journal, tag, jh2bh(new_jh),
+ jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
commit_transaction->t_tid);
tagp += tag_bytes;
space_left -= tag_bytes;
+ bufs++;
if (first_tag) {
memcpy (tagp, journal->j_uuid, 16);
@@ -809,7 +811,7 @@
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
transaction's t_log_list queue, and metadata buffers are on
- the t_iobuf_list queue.
+ the io_bufs list.
Wait for the buffers in reverse order. That way we are
less likely to be woken up until all IOs have completed, and
@@ -818,47 +820,33 @@
jbd_debug(3, "JBD2: commit phase 3\n");
- /*
- * akpm: these are BJ_IO, and j_list_lock is not needed.
- * See __journal_try_to_free_buffer.
- */
-wait_for_iobuf:
- while (commit_transaction->t_iobuf_list != NULL) {
- struct buffer_head *bh;
+ while (!list_empty(&io_bufs)) {
+ struct buffer_head *bh = list_entry(io_bufs.prev,
+ struct buffer_head,
+ b_assoc_buffers);
- jh = commit_transaction->t_iobuf_list->b_tprev;
- bh = jh2bh(jh);
- if (buffer_locked(bh)) {
- wait_on_buffer(bh);
- goto wait_for_iobuf;
- }
- if (cond_resched())
- goto wait_for_iobuf;
+ wait_on_buffer(bh);
+ cond_resched();
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
-
- clear_buffer_jwrite(bh);
-
- JBUFFER_TRACE(jh, "ph4: unfile after journal write");
- jbd2_journal_unfile_buffer(journal, jh);
+ jbd2_unfile_log_bh(bh);
/*
- * ->t_iobuf_list should contain only dummy buffer_heads
- * which were created by jbd2_journal_write_metadata_buffer().
+ * The list contains temporary buffer heads created by
+ * jbd2_journal_write_metadata_buffer().
*/
BUFFER_TRACE(bh, "dumping temporary bh");
- jbd2_journal_put_journal_head(jh);
__brelse(bh);
J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
free_buffer_head(bh);
- /* We also have to unlock and free the corresponding
- shadowed buffer */
+ /* We also have to refile the corresponding shadowed buffer */
jh = commit_transaction->t_shadow_list->b_tprev;
bh = jh2bh(jh);
- clear_bit(BH_JWrite, &bh->b_state);
+ clear_buffer_jwrite(bh);
J_ASSERT_BH(bh, buffer_jbddirty(bh));
+ J_ASSERT_BH(bh, !buffer_shadow(bh));
/* The metadata is now released for reuse, but we need
to remember it against this transaction so that when
@@ -866,14 +854,6 @@
required. */
JBUFFER_TRACE(jh, "file as BJ_Forget");
jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
- /*
- * Wake up any transactions which were waiting for this IO to
- * complete. The barrier must be here so that changes by
- * jbd2_journal_file_buffer() take effect before wake_up_bit()
- * does the waitqueue check.
- */
- smp_mb();
- wake_up_bit(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "brelse shadowed buffer");
__brelse(bh);
}
@@ -883,26 +863,19 @@
jbd_debug(3, "JBD2: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
- wait_for_ctlbuf:
- while (commit_transaction->t_log_list != NULL) {
+ while (!list_empty(&log_bufs)) {
struct buffer_head *bh;
- jh = commit_transaction->t_log_list->b_tprev;
- bh = jh2bh(jh);
- if (buffer_locked(bh)) {
- wait_on_buffer(bh);
- goto wait_for_ctlbuf;
- }
- if (cond_resched())
- goto wait_for_ctlbuf;
+ bh = list_entry(log_bufs.prev, struct buffer_head, b_assoc_buffers);
+ wait_on_buffer(bh);
+ cond_resched();
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
- jbd2_journal_unfile_buffer(journal, jh);
- jbd2_journal_put_journal_head(jh);
+ jbd2_unfile_log_bh(bh);
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
@@ -952,9 +925,7 @@
J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
- J_ASSERT(commit_transaction->t_iobuf_list == NULL);
J_ASSERT(commit_transaction->t_shadow_list == NULL);
- J_ASSERT(commit_transaction->t_log_list == NULL);
restart_loop:
/*
@@ -1097,6 +1068,25 @@
goto restart_loop;
}
+ /* Add the transaction to the checkpoint list
+ * __journal_remove_checkpoint() can not destroy transaction
+ * under us because it is not marked as T_FINISHED yet */
+ if (journal->j_checkpoint_transactions == NULL) {
+ journal->j_checkpoint_transactions = commit_transaction;
+ commit_transaction->t_cpnext = commit_transaction;
+ commit_transaction->t_cpprev = commit_transaction;
+ } else {
+ commit_transaction->t_cpnext =
+ journal->j_checkpoint_transactions;
+ commit_transaction->t_cpprev =
+ commit_transaction->t_cpnext->t_cpprev;
+ commit_transaction->t_cpnext->t_cpprev =
+ commit_transaction;
+ commit_transaction->t_cpprev->t_cpnext =
+ commit_transaction;
+ }
+ spin_unlock(&journal->j_list_lock);
+
/* Done with this transaction! */
jbd_debug(3, "JBD2: commit phase 7\n");
@@ -1115,24 +1105,7 @@
atomic_read(&commit_transaction->t_handle_count);
trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
commit_transaction->t_tid, &stats.run);
-
- /*
- * Calculate overall stats
- */
- spin_lock(&journal->j_history_lock);
- journal->j_stats.ts_tid++;
- if (commit_transaction->t_requested)
- journal->j_stats.ts_requested++;
- journal->j_stats.run.rs_wait += stats.run.rs_wait;
- journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
- journal->j_stats.run.rs_running += stats.run.rs_running;
- journal->j_stats.run.rs_locked += stats.run.rs_locked;
- journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
- journal->j_stats.run.rs_logging += stats.run.rs_logging;
- journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
- journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
- journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
- spin_unlock(&journal->j_history_lock);
+ stats.ts_requested = (commit_transaction->t_requested) ? 1 : 0;
commit_transaction->t_state = T_COMMIT_CALLBACK;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
@@ -1152,24 +1125,6 @@
write_unlock(&journal->j_state_lock);
- if (journal->j_checkpoint_transactions == NULL) {
- journal->j_checkpoint_transactions = commit_transaction;
- commit_transaction->t_cpnext = commit_transaction;
- commit_transaction->t_cpprev = commit_transaction;
- } else {
- commit_transaction->t_cpnext =
- journal->j_checkpoint_transactions;
- commit_transaction->t_cpprev =
- commit_transaction->t_cpnext->t_cpprev;
- commit_transaction->t_cpnext->t_cpprev =
- commit_transaction;
- commit_transaction->t_cpprev->t_cpnext =
- commit_transaction;
- }
- spin_unlock(&journal->j_list_lock);
- /* Drop all spin_locks because commit_callback may be block.
- * __journal_remove_checkpoint() can not destroy transaction
- * under us because it is not marked as T_FINISHED yet */
if (journal->j_commit_callback)
journal->j_commit_callback(journal, commit_transaction);
@@ -1180,7 +1135,7 @@
write_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
commit_transaction->t_state = T_FINISHED;
- /* Recheck checkpoint lists after j_list_lock was dropped */
+ /* Check if the transaction can be dropped now that we are finished */
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__jbd2_journal_drop_transaction(journal, commit_transaction);
@@ -1189,4 +1144,21 @@
spin_unlock(&journal->j_list_lock);
write_unlock(&journal->j_state_lock);
wake_up(&journal->j_wait_done_commit);
+
+ /*
+ * Calculate overall stats
+ */
+ spin_lock(&journal->j_history_lock);
+ journal->j_stats.ts_tid++;
+ journal->j_stats.ts_requested += stats.ts_requested;
+ journal->j_stats.run.rs_wait += stats.run.rs_wait;
+ journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
+ journal->j_stats.run.rs_running += stats.run.rs_running;
+ journal->j_stats.run.rs_locked += stats.run.rs_locked;
+ journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+ journal->j_stats.run.rs_logging += stats.run.rs_logging;
+ journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+ journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+ journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
+ spin_unlock(&journal->j_history_lock);
}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 85733dd..0524ae6 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -103,18 +103,37 @@
static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);
-/* Checksumming functions */
-int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
+#ifdef CONFIG_JBD2_DEBUG
+void __jbd2_debug(int level, const char *file, const char *func,
+ unsigned int line, const char *fmt, ...)
{
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ struct va_format vaf;
+ va_list args;
+
+ if (level > jbd2_journal_enable_debug)
+ return;
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf);
+ va_end(args);
+}
+EXPORT_SYMBOL(__jbd2_debug);
+#endif
+
+/* Checksumming functions */
+static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
+{
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
}
-static __u32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
+static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
{
- __u32 csum, old_csum;
+ __u32 csum;
+ __be32 old_csum;
old_csum = sb->s_checksum;
sb->s_checksum = 0;
@@ -124,17 +143,17 @@
return cpu_to_be32(csum);
}
-int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
+static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
{
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
return sb->s_checksum == jbd2_superblock_csum(j, sb);
}
-void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
+static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
{
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return;
sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -283,8 +302,8 @@
journal->j_flags |= JBD2_UNMOUNT;
while (journal->j_task) {
- wake_up(&journal->j_wait_commit);
write_unlock(&journal->j_state_lock);
+ wake_up(&journal->j_wait_commit);
wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
write_lock(&journal->j_state_lock);
}
@@ -310,14 +329,12 @@
*
* If the source buffer has already been modified by a new transaction
* since we took the last commit snapshot, we use the frozen copy of
- * that data for IO. If we end up using the existing buffer_head's data
- * for the write, then we *have* to lock the buffer to prevent anyone
- * else from using and possibly modifying it while the IO is in
- * progress.
+ * that data for IO. If we end up using the existing buffer_head's data
+ * for the write, then we have to make sure nobody modifies it while the
+ * IO is in progress. do_get_write_access() handles this.
*
- * The function returns a pointer to the buffer_heads to be used for IO.
- *
- * We assume that the journal has already been locked in this function.
+ * The function returns a pointer to the buffer_head to be used for IO.
+ *
*
* Return value:
* <0: Error
@@ -330,15 +347,14 @@
int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
struct journal_head *jh_in,
- struct journal_head **jh_out,
- unsigned long long blocknr)
+ struct buffer_head **bh_out,
+ sector_t blocknr)
{
int need_copy_out = 0;
int done_copy_out = 0;
int do_escape = 0;
char *mapped_data;
struct buffer_head *new_bh;
- struct journal_head *new_jh;
struct page *new_page;
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
@@ -368,14 +384,13 @@
/* keep subsequent assertions sane */
atomic_set(&new_bh->b_count, 1);
- new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
+ jbd_lock_bh_state(bh_in);
+repeat:
/*
* If a new transaction has already done a buffer copy-out, then
* we use that version of the data for the commit.
*/
- jbd_lock_bh_state(bh_in);
-repeat:
if (jh_in->b_frozen_data) {
done_copy_out = 1;
new_page = virt_to_page(jh_in->b_frozen_data);
@@ -415,7 +430,7 @@
jbd_unlock_bh_state(bh_in);
tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
if (!tmp) {
- jbd2_journal_put_journal_head(new_jh);
+ brelse(new_bh);
return -ENOMEM;
}
jbd_lock_bh_state(bh_in);
@@ -426,7 +441,7 @@
jh_in->b_frozen_data = tmp;
mapped_data = kmap_atomic(new_page);
- memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
+ memcpy(tmp, mapped_data + new_offset, bh_in->b_size);
kunmap_atomic(mapped_data);
new_page = virt_to_page(tmp);
@@ -452,14 +467,14 @@
}
set_bh_page(new_bh, new_page, new_offset);
- new_jh->b_transaction = NULL;
- new_bh->b_size = jh2bh(jh_in)->b_size;
- new_bh->b_bdev = transaction->t_journal->j_dev;
+ new_bh->b_size = bh_in->b_size;
+ new_bh->b_bdev = journal->j_dev;
new_bh->b_blocknr = blocknr;
+ new_bh->b_private = bh_in;
set_buffer_mapped(new_bh);
set_buffer_dirty(new_bh);
- *jh_out = new_jh;
+ *bh_out = new_bh;
/*
* The to-be-written buffer needs to get moved to the io queue,
@@ -470,11 +485,9 @@
spin_lock(&journal->j_list_lock);
__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
spin_unlock(&journal->j_list_lock);
+ set_buffer_shadow(bh_in);
jbd_unlock_bh_state(bh_in);
- JBUFFER_TRACE(new_jh, "file as BJ_IO");
- jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
-
return do_escape | (done_copy_out << 1);
}
@@ -484,35 +497,6 @@
*/
/*
- * __jbd2_log_space_left: Return the number of free blocks left in the journal.
- *
- * Called with the journal already locked.
- *
- * Called under j_state_lock
- */
-
-int __jbd2_log_space_left(journal_t *journal)
-{
- int left = journal->j_free;
-
- /* assert_spin_locked(&journal->j_state_lock); */
-
- /*
- * Be pessimistic here about the number of those free blocks which
- * might be required for log descriptor control blocks.
- */
-
-#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */
-
- left -= MIN_LOG_RESERVED_BLOCKS;
-
- if (left <= 0)
- return 0;
- left -= (left >> 3);
- return left;
-}
-
-/*
* Called with j_state_lock locked for writing.
* Returns true if a transaction commit was started.
*/
@@ -564,20 +548,17 @@
}
/*
- * Force and wait upon a commit if the calling process is not within
- * transaction. This is used for forcing out undo-protected data which contains
- * bitmaps, when the fs is running out of space.
- *
- * We can only force the running transaction if we don't have an active handle;
- * otherwise, we will deadlock.
- *
- * Returns true if a transaction was started.
+ * Force and wait any uncommitted transactions. We can only force the running
+ * transaction if we don't have an active handle, otherwise, we will deadlock.
+ * Returns: <0 in case of error,
+ * 0 if nothing to commit,
+ * 1 if transaction was successfully committed.
*/
-int jbd2_journal_force_commit_nested(journal_t *journal)
+static int __jbd2_journal_force_commit(journal_t *journal)
{
transaction_t *transaction = NULL;
tid_t tid;
- int need_to_start = 0;
+ int need_to_start = 0, ret = 0;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction && !current->journal_info) {
@@ -588,16 +569,53 @@
transaction = journal->j_committing_transaction;
if (!transaction) {
+ /* Nothing to commit */
read_unlock(&journal->j_state_lock);
- return 0; /* Nothing to retry */
+ return 0;
}
-
tid = transaction->t_tid;
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
- jbd2_log_wait_commit(journal, tid);
- return 1;
+ ret = jbd2_log_wait_commit(journal, tid);
+ if (!ret)
+ ret = 1;
+
+ return ret;
+}
+
+/**
+ * Force and wait upon a commit if the calling process is not within
+ * transaction. This is used for forcing out undo-protected data which contains
+ * bitmaps, when the fs is running out of space.
+ *
+ * @journal: journal to force
+ * Returns true if progress was made.
+ */
+int jbd2_journal_force_commit_nested(journal_t *journal)
+{
+ int ret;
+
+ ret = __jbd2_journal_force_commit(journal);
+ return ret > 0;
+}
+
+/**
+ * int journal_force_commit() - force any uncommitted transactions
+ * @journal: journal to force
+ *
+ * Caller want unconditional commit. We can only force the running transaction
+ * if we don't have an active handle, otherwise, we will deadlock.
+ */
+int jbd2_journal_force_commit(journal_t *journal)
+{
+ int ret;
+
+ J_ASSERT(!current->journal_info);
+ ret = __jbd2_journal_force_commit(journal);
+ if (ret > 0)
+ ret = 0;
+ return ret;
}
/*
@@ -684,7 +702,7 @@
read_lock(&journal->j_state_lock);
#ifdef CONFIG_JBD2_DEBUG
if (!tid_geq(journal->j_commit_request, tid)) {
- printk(KERN_EMERG
+ printk(KERN_ERR
"%s: error: j_commit_request=%d, tid=%d\n",
__func__, journal->j_commit_request, tid);
}
@@ -692,18 +710,16 @@
while (tid_gt(tid, journal->j_commit_sequence)) {
jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
tid, journal->j_commit_sequence);
- wake_up(&journal->j_wait_commit);
read_unlock(&journal->j_state_lock);
+ wake_up(&journal->j_wait_commit);
wait_event(journal->j_wait_done_commit,
!tid_gt(tid, journal->j_commit_sequence));
read_lock(&journal->j_state_lock);
}
read_unlock(&journal->j_state_lock);
- if (unlikely(is_journal_aborted(journal))) {
- printk(KERN_EMERG "journal commit I/O error\n");
+ if (unlikely(is_journal_aborted(journal)))
err = -EIO;
- }
return err;
}
@@ -798,7 +814,7 @@
* But we don't bother doing that, so there will be coherency problems with
* mmaps of blockdevs which hold live JBD-controlled filesystems.
*/
-struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
+struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
{
struct buffer_head *bh;
unsigned long long blocknr;
@@ -817,7 +833,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
BUFFER_TRACE(bh, "return this buffer");
- return jbd2_journal_add_journal_head(bh);
+ return bh;
}
/*
@@ -1069,11 +1085,10 @@
return NULL;
init_waitqueue_head(&journal->j_wait_transaction_locked);
- init_waitqueue_head(&journal->j_wait_logspace);
init_waitqueue_head(&journal->j_wait_done_commit);
- init_waitqueue_head(&journal->j_wait_checkpoint);
init_waitqueue_head(&journal->j_wait_commit);
init_waitqueue_head(&journal->j_wait_updates);
+ init_waitqueue_head(&journal->j_wait_reserved);
mutex_init(&journal->j_barrier);
mutex_init(&journal->j_checkpoint_mutex);
spin_lock_init(&journal->j_revoke_lock);
@@ -1083,6 +1098,7 @@
journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
journal->j_min_batch_time = 0;
journal->j_max_batch_time = 15000; /* 15ms */
+ atomic_set(&journal->j_reserved_credits, 0);
/* The journal is marked for error until we succeed with recovery! */
journal->j_flags = JBD2_ABORT;
@@ -1228,7 +1244,7 @@
goto out_err;
}
- bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ bh = getblk_unmovable(journal->j_dev, blocknr, journal->j_blocksize);
if (!bh) {
printk(KERN_ERR
"%s: Cannot get buffer for journal superblock\n",
@@ -1523,24 +1539,32 @@
goto out;
}
- if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
- JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+ JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+ /* Can't have checksum v2 and v3 at the same time! */
+ printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+ "at the same time!\n");
+ goto out;
+ }
+
+ if (jbd2_journal_has_csum_v2or3(journal) &&
+ JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
/* Can't have checksum v1 and v2 on at the same time! */
- printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 "
+ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 "
"at the same time!\n");
goto out;
}
if (!jbd2_verify_csum_type(journal, sb)) {
- printk(KERN_ERR "JBD: Unknown checksum type\n");
+ printk(KERN_ERR "JBD2: Unknown checksum type\n");
goto out;
}
/* Load the checksum driver */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+ if (jbd2_journal_has_csum_v2or3(journal)) {
journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
if (IS_ERR(journal->j_chksum_driver)) {
- printk(KERN_ERR "JBD: Cannot load crc32c driver.\n");
+ printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
err = PTR_ERR(journal->j_chksum_driver);
journal->j_chksum_driver = NULL;
goto out;
@@ -1549,12 +1573,12 @@
/* Check superblock checksum */
if (!jbd2_superblock_csum_verify(journal, sb)) {
- printk(KERN_ERR "JBD: journal checksum error\n");
+ printk(KERN_ERR "JBD2: journal checksum error\n");
goto out;
}
/* Precompute checksum seed for all metadata */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
sizeof(sb->s_uuid));
@@ -1820,8 +1844,14 @@
if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
return 0;
- /* Asking for checksumming v2 and v1? Only give them v2. */
- if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+ /* If enabling v2 checksums, turn on v3 instead */
+ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+ incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+ incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+ }
+
+ /* Asking for checksumming v3 and v1? Only give them v3. */
+ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
compat & JBD2_FEATURE_COMPAT_CHECKSUM)
compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -1830,8 +1860,8 @@
sb = journal->j_superblock;
- /* If enabling v2 checksums, update superblock */
- if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+ /* If enabling v3 checksums, update superblock */
+ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
sb->s_feature_compat &=
~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1841,25 +1871,24 @@
journal->j_chksum_driver = crypto_alloc_shash("crc32c",
0, 0);
if (IS_ERR(journal->j_chksum_driver)) {
- printk(KERN_ERR "JBD: Cannot load crc32c "
+ printk(KERN_ERR "JBD2: Cannot load crc32c "
"driver.\n");
journal->j_chksum_driver = NULL;
return 0;
}
- }
- /* Precompute checksum seed for all metadata */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ /* Precompute checksum seed for all metadata */
journal->j_csum_seed = jbd2_chksum(journal, ~0,
sb->s_uuid,
sizeof(sb->s_uuid));
+ }
}
/* If enabling v1 checksums, downgrade superblock */
if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
sb->s_feature_incompat &=
- ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+ JBD2_FEATURE_INCOMPAT_CSUM_V3);
sb->s_feature_compat |= cpu_to_be32(compat);
sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2184,16 +2213,20 @@
*/
size_t journal_tag_bytes(journal_t *journal)
{
- journal_block_tag_t tag;
- size_t x = 0;
+ size_t sz;
+
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+ return sizeof(journal_block_tag3_t);
+
+ sz = sizeof(journal_block_tag_t);
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
- x += sizeof(tag.t_checksum);
+ sz += sizeof(__u16);
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
- return x + JBD2_TAG_SIZE64;
+ return sz;
else
- return x + JBD2_TAG_SIZE32;
+ return sz - sizeof(__u32);
}
/*
@@ -2361,13 +2394,13 @@
#ifdef CONFIG_JBD2_DEBUG
atomic_inc(&nr_journal_heads);
#endif
- ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+ ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS);
if (!ret) {
jbd_debug(1, "out of memory for journal_head\n");
pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__);
while (!ret) {
yield();
- ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+ ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS);
}
}
return ret;
@@ -2429,10 +2462,8 @@
struct journal_head *new_jh = NULL;
repeat:
- if (!buffer_jbd(bh)) {
+ if (!buffer_jbd(bh))
new_jh = journal_alloc_journal_head();
- memset(new_jh, 0, sizeof(*new_jh));
- }
jbd_lock_bh_journal_head(bh);
if (buffer_jbd(bh)) {
@@ -2664,7 +2695,7 @@
#ifdef CONFIG_JBD2_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
- printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
+ printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n);
#endif
jbd2_remove_jbd_stats_proc_entry();
jbd2_journal_destroy_caches();
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 6e2fb5c..bcbef08 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -178,9 +178,10 @@
void *buf)
{
struct jbd2_journal_block_tail *tail;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -190,8 +191,7 @@
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
tail->t_checksum = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
/*
@@ -205,7 +205,7 @@
int nr = 0, size = journal->j_blocksize;
int tag_bytes = journal_tag_bytes(journal);
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
size -= sizeof(struct jbd2_journal_block_tail);
tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@
return err;
}
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+ journal_block_tag_t *tag)
{
unsigned long long block = be32_to_cpu(tag->t_blocknr);
- if (tag_bytes > JBD2_TAG_SIZE32)
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
return block;
}
@@ -381,9 +382,10 @@
static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
{
struct commit_header *h;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
h = buf;
@@ -392,25 +394,27 @@
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
h->h_chksum[0] = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
void *buf, __u32 sequence)
{
- __u32 provided, calculated;
+ journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
+ __u32 csum32;
+ __be32 seq;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
- sequence = cpu_to_be32(sequence);
- calculated = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
- sizeof(sequence));
- calculated = jbd2_chksum(j, calculated, buf, j->j_blocksize);
- provided = be32_to_cpu(tag->t_checksum);
+ seq = cpu_to_be32(sequence);
+ csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
+ csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
- return provided == cpu_to_be32(calculated);
+ if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+ return tag3->t_checksum == cpu_to_be32(csum32);
+ else
+ return tag->t_checksum == cpu_to_be16(csum32);
}
static int do_one_pass(journal_t *journal,
@@ -514,8 +518,7 @@
switch(blocktype) {
case JBD2_DESCRIPTOR_BLOCK:
/* Verify checksum first */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
descr_csum_size =
sizeof(struct jbd2_journal_block_tail);
if (descr_csum_size > 0 &&
@@ -577,7 +580,7 @@
unsigned long long blocknr;
J_ASSERT(obh != NULL);
- blocknr = read_tag_block(tag_bytes,
+ blocknr = read_tag_block(journal,
tag);
/* If the block has been
@@ -597,7 +600,7 @@
be32_to_cpu(tmp->h_sequence))) {
brelse(obh);
success = -EIO;
- printk(KERN_ERR "JBD: Invalid "
+ printk(KERN_ERR "JBD2: Invalid "
"checksum recovering "
"block %llu in log\n",
blocknr);
@@ -813,9 +816,10 @@
void *buf)
{
struct jbd2_journal_revoke_tail *tail;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return 1;
tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
@@ -825,8 +829,7 @@
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
tail->r_checksum = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
/* Scan a revoke record, marking all blocks mentioned as revoked. */
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index f30b80b..c6cbaef 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,9 @@
#include <linux/list.h>
#include <linux/init.h>
#include <linux/bio.h>
-#endif
#include <linux/log2.h>
+#include <linux/hash.h>
+#endif
static struct kmem_cache *jbd2_revoke_record_cache;
static struct kmem_cache *jbd2_revoke_table_cache;
@@ -122,23 +123,17 @@
#ifdef __KERNEL__
static void write_one_revoke_record(journal_t *, transaction_t *,
- struct journal_head **, int *,
+ struct list_head *,
+ struct buffer_head **, int *,
struct jbd2_revoke_record_s *, int);
-static void flush_descriptor(journal_t *, struct journal_head *, int, int);
+static void flush_descriptor(journal_t *, struct buffer_head *, int, int);
#endif
/* Utility functions to maintain the revoke table */
-/* Borrowed from buffer.c: this is a tried and tested block hash function */
static inline int hash(journal_t *journal, unsigned long long block)
{
- struct jbd2_revoke_table_s *table = journal->j_revoke;
- int hash_shift = table->hash_shift;
- int hash = (int)block ^ (int)((block >> 31) >> 1);
-
- return ((hash << (hash_shift - 6)) ^
- (hash >> 13) ^
- (hash << (hash_shift - 12))) & (table->hash_size - 1);
+ return hash_64(block, journal->j_revoke->hash_shift);
}
static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr,
@@ -531,9 +526,10 @@
*/
void jbd2_journal_write_revoke_records(journal_t *journal,
transaction_t *transaction,
+ struct list_head *log_bufs,
int write_op)
{
- struct journal_head *descriptor;
+ struct buffer_head *descriptor;
struct jbd2_revoke_record_s *record;
struct jbd2_revoke_table_s *revoke;
struct list_head *hash_list;
@@ -553,7 +549,7 @@
while (!list_empty(hash_list)) {
record = (struct jbd2_revoke_record_s *)
hash_list->next;
- write_one_revoke_record(journal, transaction,
+ write_one_revoke_record(journal, transaction, log_bufs,
&descriptor, &offset,
record, write_op);
count++;
@@ -573,13 +569,14 @@
static void write_one_revoke_record(journal_t *journal,
transaction_t *transaction,
- struct journal_head **descriptorp,
+ struct list_head *log_bufs,
+ struct buffer_head **descriptorp,
int *offsetp,
struct jbd2_revoke_record_s *record,
int write_op)
{
int csum_size = 0;
- struct journal_head *descriptor;
+ struct buffer_head *descriptor;
int offset;
journal_header_t *header;
@@ -594,7 +591,7 @@
offset = *offsetp;
/* Do we need to leave space at the end for a checksum? */
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (jbd2_journal_has_csum_v2or3(journal))
csum_size = sizeof(struct jbd2_journal_revoke_tail);
/* Make sure we have a descriptor with space left for the record */
@@ -609,26 +606,26 @@
descriptor = jbd2_journal_get_descriptor_buffer(journal);
if (!descriptor)
return;
- header = (journal_header_t *) &jh2bh(descriptor)->b_data[0];
+ header = (journal_header_t *)descriptor->b_data;
header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK);
header->h_sequence = cpu_to_be32(transaction->t_tid);
/* Record it so that we can wait for IO completion later */
- JBUFFER_TRACE(descriptor, "file as BJ_LogCtl");
- jbd2_journal_file_buffer(descriptor, transaction, BJ_LogCtl);
+ BUFFER_TRACE(descriptor, "file in log_bufs");
+ jbd2_file_log_bh(log_bufs, descriptor);
offset = sizeof(jbd2_journal_revoke_header_t);
*descriptorp = descriptor;
}
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) {
- * ((__be64 *)(&jh2bh(descriptor)->b_data[offset])) =
+ * ((__be64 *)(&descriptor->b_data[offset])) =
cpu_to_be64(record->blocknr);
offset += 8;
} else {
- * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) =
+ * ((__be32 *)(&descriptor->b_data[offset])) =
cpu_to_be32(record->blocknr);
offset += 4;
}
@@ -636,21 +633,18 @@
*offsetp = offset;
}
-static void jbd2_revoke_csum_set(journal_t *j,
- struct journal_head *descriptor)
+static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
{
struct jbd2_journal_revoke_tail *tail;
__u32 csum;
- if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+ if (!jbd2_journal_has_csum_v2or3(j))
return;
- tail = (struct jbd2_journal_revoke_tail *)
- (jh2bh(descriptor)->b_data + j->j_blocksize -
+ tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
sizeof(struct jbd2_journal_revoke_tail));
tail->r_checksum = 0;
- csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data,
- j->j_blocksize);
+ csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
tail->r_checksum = cpu_to_be32(csum);
}
@@ -662,25 +656,24 @@
*/
static void flush_descriptor(journal_t *journal,
- struct journal_head *descriptor,
+ struct buffer_head *descriptor,
int offset, int write_op)
{
jbd2_journal_revoke_header_t *header;
- struct buffer_head *bh = jh2bh(descriptor);
if (is_journal_aborted(journal)) {
- put_bh(bh);
+ put_bh(descriptor);
return;
}
- header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data;
+ header = (jbd2_journal_revoke_header_t *)descriptor->b_data;
header->r_count = cpu_to_be32(offset);
jbd2_revoke_csum_set(journal, descriptor);
- set_buffer_jwrite(bh);
- BUFFER_TRACE(bh, "write");
- set_buffer_dirty(bh);
- write_dirty_buffer(bh, write_op);
+ set_buffer_jwrite(descriptor);
+ BUFFER_TRACE(descriptor, "write");
+ set_buffer_dirty(descriptor);
+ write_dirty_buffer(descriptor, write_op);
}
#endif
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 21b828c..c6aa583 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -89,7 +89,8 @@
transaction->t_expires = jiffies + journal->j_commit_interval;
spin_lock_init(&transaction->t_handle_lock);
atomic_set(&transaction->t_updates, 0);
- atomic_set(&transaction->t_outstanding_credits, 0);
+ atomic_set(&transaction->t_outstanding_credits,
+ atomic_read(&journal->j_reserved_credits));
atomic_set(&transaction->t_handle_count, 0);
INIT_LIST_HEAD(&transaction->t_inode_list);
INIT_LIST_HEAD(&transaction->t_private_list);
@@ -141,6 +142,112 @@
}
/*
+ * Wait until running transaction passes T_LOCKED state. Also starts the commit
+ * if needed. The function expects running transaction to exist and releases
+ * j_state_lock.
+ */
+static void wait_transaction_locked(journal_t *journal)
+ __releases(journal->j_state_lock)
+{
+ DEFINE_WAIT(wait);
+ int need_to_start;
+ tid_t tid = journal->j_running_transaction->t_tid;
+
+ prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
+ TASK_UNINTERRUPTIBLE);
+ need_to_start = !tid_geq(journal->j_commit_request, tid);
+ read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
+ schedule();
+ finish_wait(&journal->j_wait_transaction_locked, &wait);
+}
+
+static void sub_reserved_credits(journal_t *journal, int blocks)
+{
+ atomic_sub(blocks, &journal->j_reserved_credits);
+ wake_up(&journal->j_wait_reserved);
+}
+
+/*
+ * Wait until we can add credits for handle to the running transaction. Called
+ * with j_state_lock held for reading. Returns 0 if handle joined the running
+ * transaction. Returns 1 if we had to wait, j_state_lock is dropped, and
+ * caller must retry.
+ */
+static int add_transaction_credits(journal_t *journal, int blocks,
+ int rsv_blocks)
+{
+ transaction_t *t = journal->j_running_transaction;
+ int needed;
+ int total = blocks + rsv_blocks;
+
+ /*
+ * If the current transaction is locked down for commit, wait
+ * for the lock to be released.
+ */
+ if (t->t_state == T_LOCKED) {
+ wait_transaction_locked(journal);
+ return 1;
+ }
+
+ /*
+ * If there is not enough space left in the log to write all
+ * potential buffers requested by this operation, we need to
+ * stall pending a log checkpoint to free some more log space.
+ */
+ needed = atomic_add_return(total, &t->t_outstanding_credits);
+ if (needed > journal->j_max_transaction_buffers) {
+ /*
+ * If the current transaction is already too large,
+ * then start to commit it: we can then go back and
+ * attach this handle to a new transaction.
+ */
+ atomic_sub(total, &t->t_outstanding_credits);
+ wait_transaction_locked(journal);
+ return 1;
+ }
+
+ /*
+ * The commit code assumes that it can get enough log space
+ * without forcing a checkpoint. This is *critical* for
+ * correctness: a checkpoint of a buffer which is also
+ * associated with a committing transaction creates a deadlock,
+ * so commit simply cannot force through checkpoints.
+ *
+ * We must therefore ensure the necessary space in the journal
+ * *before* starting to dirty potentially checkpointed buffers
+ * in the new transaction.
+ */
+ if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) {
+ atomic_sub(total, &t->t_outstanding_credits);
+ read_unlock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
+ if (jbd2_log_space_left(journal) < jbd2_space_needed(journal))
+ __jbd2_log_wait_for_space(journal);
+ write_unlock(&journal->j_state_lock);
+ return 1;
+ }
+
+ /* No reservation? We are done... */
+ if (!rsv_blocks)
+ return 0;
+
+ needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits);
+ /* We allow at most half of a transaction to be reserved */
+ if (needed > journal->j_max_transaction_buffers / 2) {
+ sub_reserved_credits(journal, rsv_blocks);
+ atomic_sub(total, &t->t_outstanding_credits);
+ read_unlock(&journal->j_state_lock);
+ wait_event(journal->j_wait_reserved,
+ atomic_read(&journal->j_reserved_credits) + rsv_blocks
+ <= journal->j_max_transaction_buffers / 2);
+ return 1;
+ }
+ return 0;
+}
+
+/*
* start_this_handle: Given a handle, deal with any locking or stalling
* needed to make sure that there is enough journal space for the handle
* to begin. Attach the handle to a transaction and set up the
@@ -151,18 +258,24 @@
gfp_t gfp_mask)
{
transaction_t *transaction, *new_transaction = NULL;
- tid_t tid;
- int needed, need_to_start;
- int nblocks = handle->h_buffer_credits;
+ int blocks = handle->h_buffer_credits;
+ int rsv_blocks = 0;
unsigned long ts = jiffies;
- if (nblocks > journal->j_max_transaction_buffers) {
+ /*
+ * 1/2 of transaction can be reserved so we can practically handle
+ * only 1/2 of maximum transaction size per operation
+ */
+ if (WARN_ON(blocks > journal->j_max_transaction_buffers / 2)) {
printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n",
- current->comm, nblocks,
- journal->j_max_transaction_buffers);
+ current->comm, blocks,
+ journal->j_max_transaction_buffers / 2);
return -ENOSPC;
}
+ if (handle->h_rsv_handle)
+ rsv_blocks = handle->h_rsv_handle->h_buffer_credits;
+
alloc_transaction:
if (!journal->j_running_transaction) {
new_transaction = kmem_cache_zalloc(transaction_cache,
@@ -199,8 +312,12 @@
return -EROFS;
}
- /* Wait on the journal's transaction barrier if necessary */
- if (journal->j_barrier_count) {
+ /*
+ * Wait on the journal's transaction barrier if necessary. Specifically
+ * we allow reserved handles to proceed because otherwise commit could
+ * deadlock on page writeback not being able to complete.
+ */
+ if (!handle->h_reserved && journal->j_barrier_count) {
read_unlock(&journal->j_state_lock);
wait_event(journal->j_wait_transaction_locked,
journal->j_barrier_count == 0);
@@ -213,7 +330,7 @@
goto alloc_transaction;
write_lock(&journal->j_state_lock);
if (!journal->j_running_transaction &&
- !journal->j_barrier_count) {
+ (handle->h_reserved || !journal->j_barrier_count)) {
jbd2_get_transaction(journal, new_transaction);
new_transaction = NULL;
}
@@ -223,85 +340,18 @@
transaction = journal->j_running_transaction;
- /*
- * If the current transaction is locked down for commit, wait for the
- * lock to be released.
- */
- if (transaction->t_state == T_LOCKED) {
- DEFINE_WAIT(wait);
-
- prepare_to_wait(&journal->j_wait_transaction_locked,
- &wait, TASK_UNINTERRUPTIBLE);
- read_unlock(&journal->j_state_lock);
- schedule();
- finish_wait(&journal->j_wait_transaction_locked, &wait);
- goto repeat;
- }
-
- /*
- * If there is not enough space left in the log to write all potential
- * buffers requested by this operation, we need to stall pending a log
- * checkpoint to free some more log space.
- */
- needed = atomic_add_return(nblocks,
- &transaction->t_outstanding_credits);
-
- if (needed > journal->j_max_transaction_buffers) {
+ if (!handle->h_reserved) {
+ /* We may have dropped j_state_lock - restart in that case */
+ if (add_transaction_credits(journal, blocks, rsv_blocks))
+ goto repeat;
+ } else {
/*
- * If the current transaction is already too large, then start
- * to commit it: we can then go back and attach this handle to
- * a new transaction.
+ * We have handle reserved so we are allowed to join T_LOCKED
+ * transaction and we don't have to check for transaction size
+ * and journal space.
*/
- DEFINE_WAIT(wait);
-
- jbd_debug(2, "Handle %p starting new commit...\n", handle);
- atomic_sub(nblocks, &transaction->t_outstanding_credits);
- prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
- TASK_UNINTERRUPTIBLE);
- tid = transaction->t_tid;
- need_to_start = !tid_geq(journal->j_commit_request, tid);
- read_unlock(&journal->j_state_lock);
- if (need_to_start)
- jbd2_log_start_commit(journal, tid);
- schedule();
- finish_wait(&journal->j_wait_transaction_locked, &wait);
- goto repeat;
- }
-
- /*
- * The commit code assumes that it can get enough log space
- * without forcing a checkpoint. This is *critical* for
- * correctness: a checkpoint of a buffer which is also
- * associated with a committing transaction creates a deadlock,
- * so commit simply cannot force through checkpoints.
- *
- * We must therefore ensure the necessary space in the journal
- * *before* starting to dirty potentially checkpointed buffers
- * in the new transaction.
- *
- * The worst part is, any transaction currently committing can
- * reduce the free space arbitrarily. Be careful to account for
- * those buffers when checkpointing.
- */
-
- /*
- * @@@ AKPM: This seems rather over-defensive. We're giving commit
- * a _lot_ of headroom: 1/4 of the journal plus the size of
- * the committing transaction. Really, we only need to give it
- * committing_transaction->t_outstanding_credits plus "enough" for
- * the log control blocks.
- * Also, this test is inconsistent with the matching one in
- * jbd2_journal_extend().
- */
- if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
- jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
- atomic_sub(nblocks, &transaction->t_outstanding_credits);
- read_unlock(&journal->j_state_lock);
- write_lock(&journal->j_state_lock);
- if (__jbd2_log_space_left(journal) < jbd_space_needed(journal))
- __jbd2_log_wait_for_space(journal);
- write_unlock(&journal->j_state_lock);
- goto repeat;
+ sub_reserved_credits(journal, blocks);
+ handle->h_reserved = 0;
}
/* OK, account for the buffers that this operation expects to
@@ -309,15 +359,16 @@
*/
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
- handle->h_requested_credits = nblocks;
+ handle->h_requested_credits = blocks;
handle->h_start_jiffies = jiffies;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
- jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
- handle, nblocks,
+ jbd_debug(4, "Handle %p given %d credits (total %d, free %lu)\n",
+ handle, blocks,
atomic_read(&transaction->t_outstanding_credits),
- __jbd2_log_space_left(journal));
+ jbd2_log_space_left(journal));
read_unlock(&journal->j_state_lock);
+ current->journal_info = handle;
lock_map_acquire(&handle->h_lockdep_map);
jbd2_journal_free_transaction(new_transaction);
@@ -348,16 +399,21 @@
*
* We make sure that the transaction can guarantee at least nblocks of
* modified buffers in the log. We block until the log can guarantee
- * that much space.
- *
- * This function is visible to journal users (like ext3fs), so is not
- * called with the journal already locked.
+ * that much space. Additionally, if rsv_blocks > 0, we also create another
+ * handle with rsv_blocks reserved blocks in the journal. This handle is
+ * is stored in h_rsv_handle. It is not attached to any particular transaction
+ * and thus doesn't block transaction commit. If the caller uses this reserved
+ * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop()
+ * on the parent handle will dispose the reserved one. Reserved handle has to
+ * be converted to a normal handle using jbd2_journal_start_reserved() before
+ * it can be used.
*
* Return a pointer to a newly allocated handle, or an ERR_PTR() value
* on failure.
*/
-handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask,
- unsigned int type, unsigned int line_no)
+handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
+ gfp_t gfp_mask, unsigned int type,
+ unsigned int line_no)
{
handle_t *handle = journal_current_handle();
int err;
@@ -374,13 +430,24 @@
handle = new_handle(nblocks);
if (!handle)
return ERR_PTR(-ENOMEM);
+ if (rsv_blocks) {
+ handle_t *rsv_handle;
- current->journal_info = handle;
+ rsv_handle = new_handle(rsv_blocks);
+ if (!rsv_handle) {
+ jbd2_free_handle(handle);
+ return ERR_PTR(-ENOMEM);
+ }
+ rsv_handle->h_reserved = 1;
+ rsv_handle->h_journal = journal;
+ handle->h_rsv_handle = rsv_handle;
+ }
err = start_this_handle(journal, handle, gfp_mask);
if (err < 0) {
+ if (handle->h_rsv_handle)
+ jbd2_free_handle(handle->h_rsv_handle);
jbd2_free_handle(handle);
- current->journal_info = NULL;
return ERR_PTR(err);
}
handle->h_type = type;
@@ -395,10 +462,67 @@
handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
{
- return jbd2__journal_start(journal, nblocks, GFP_NOFS, 0, 0);
+ return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0);
}
EXPORT_SYMBOL(jbd2_journal_start);
+void jbd2_journal_free_reserved(handle_t *handle)
+{
+ journal_t *journal = handle->h_journal;
+
+ WARN_ON(!handle->h_reserved);
+ sub_reserved_credits(journal, handle->h_buffer_credits);
+ jbd2_free_handle(handle);
+}
+EXPORT_SYMBOL(jbd2_journal_free_reserved);
+
+/**
+ * int jbd2_journal_start_reserved(handle_t *handle) - start reserved handle
+ * @handle: handle to start
+ *
+ * Start handle that has been previously reserved with jbd2_journal_reserve().
+ * This attaches @handle to the running transaction (or creates one if there's
+ * not transaction running). Unlike jbd2_journal_start() this function cannot
+ * block on journal commit, checkpointing, or similar stuff. It can block on
+ * memory allocation or frozen journal though.
+ *
+ * Return 0 on success, non-zero on error - handle is freed in that case.
+ */
+int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
+ unsigned int line_no)
+{
+ journal_t *journal = handle->h_journal;
+ int ret = -EIO;
+
+ if (WARN_ON(!handle->h_reserved)) {
+ /* Someone passed in normal handle? Just stop it. */
+ jbd2_journal_stop(handle);
+ return ret;
+ }
+ /*
+ * Usefulness of mixing of reserved and unreserved handles is
+ * questionable. So far nobody seems to need it so just error out.
+ */
+ if (WARN_ON(current->journal_info)) {
+ jbd2_journal_free_reserved(handle);
+ return ret;
+ }
+
+ handle->h_journal = NULL;
+ /*
+ * GFP_NOFS is here because callers are likely from writeback or
+ * similarly constrained call sites
+ */
+ ret = start_this_handle(journal, handle, GFP_NOFS);
+ if (ret < 0) {
+ jbd2_journal_free_reserved(handle);
+ return ret;
+ }
+ handle->h_type = type;
+ handle->h_line_no = line_no;
+ return 0;
+}
+EXPORT_SYMBOL(jbd2_journal_start_reserved);
/**
* int jbd2_journal_extend() - extend buffer credits.
@@ -423,49 +547,53 @@
int jbd2_journal_extend(handle_t *handle, int nblocks)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
int result;
int wanted;
- result = -EIO;
+ WARN_ON(!transaction);
if (is_handle_aborted(handle))
- goto out;
+ return -EROFS;
+ journal = transaction->t_journal;
result = 1;
read_lock(&journal->j_state_lock);
/* Don't extend a locked-down transaction! */
- if (handle->h_transaction->t_state != T_RUNNING) {
+ if (transaction->t_state != T_RUNNING) {
jbd_debug(3, "denied handle %p %d blocks: "
"transaction not running\n", handle, nblocks);
goto error_out;
}
spin_lock(&transaction->t_handle_lock);
- wanted = atomic_read(&transaction->t_outstanding_credits) + nblocks;
+ wanted = atomic_add_return(nblocks,
+ &transaction->t_outstanding_credits);
if (wanted > journal->j_max_transaction_buffers) {
jbd_debug(3, "denied handle %p %d blocks: "
"transaction too large\n", handle, nblocks);
+ atomic_sub(nblocks, &transaction->t_outstanding_credits);
goto unlock;
}
- if (wanted > __jbd2_log_space_left(journal)) {
+ if (wanted + (wanted >> JBD2_CONTROL_BLOCKS_SHIFT) >
+ jbd2_log_space_left(journal)) {
jbd_debug(3, "denied handle %p %d blocks: "
"insufficient log space\n", handle, nblocks);
+ atomic_sub(nblocks, &transaction->t_outstanding_credits);
goto unlock;
}
trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
- handle->h_transaction->t_tid,
+ transaction->t_tid,
handle->h_type, handle->h_line_no,
handle->h_buffer_credits,
nblocks);
handle->h_buffer_credits += nblocks;
handle->h_requested_credits += nblocks;
- atomic_add(nblocks, &transaction->t_outstanding_credits);
result = 0;
jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
@@ -473,7 +601,6 @@
spin_unlock(&transaction->t_handle_lock);
error_out:
read_unlock(&journal->j_state_lock);
-out:
return result;
}
@@ -490,19 +617,22 @@
* to a running handle, a call to jbd2_journal_restart will commit the
* handle's transaction so far and reattach the handle to a new
* transaction capabable of guaranteeing the requested number of
- * credits.
+ * credits. We preserve reserved handle if there's any attached to the
+ * passed in handle.
*/
int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
tid_t tid;
int need_to_start, ret;
+ WARN_ON(!transaction);
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
if (is_handle_aborted(handle))
return 0;
+ journal = transaction->t_journal;
/*
* First unlink the handle from its current transaction, and start the
@@ -515,10 +645,16 @@
spin_lock(&transaction->t_handle_lock);
atomic_sub(handle->h_buffer_credits,
&transaction->t_outstanding_credits);
+ if (handle->h_rsv_handle) {
+ sub_reserved_credits(journal,
+ handle->h_rsv_handle->h_buffer_credits);
+ }
if (atomic_dec_and_test(&transaction->t_updates))
wake_up(&journal->j_wait_updates);
tid = transaction->t_tid;
spin_unlock(&transaction->t_handle_lock);
+ handle->h_transaction = NULL;
+ current->journal_info = NULL;
jbd_debug(2, "restarting handle %p\n", handle);
need_to_start = !tid_geq(journal->j_commit_request, tid);
@@ -557,6 +693,14 @@
write_lock(&journal->j_state_lock);
++journal->j_barrier_count;
+ /* Wait until there are no reserved handles */
+ if (atomic_read(&journal->j_reserved_credits)) {
+ write_unlock(&journal->j_state_lock);
+ wait_event(journal->j_wait_reserved,
+ atomic_read(&journal->j_reserved_credits) == 0);
+ write_lock(&journal->j_state_lock);
+ }
+
/* Wait until there are no running updates */
while (1) {
transaction_t *transaction = journal->j_running_transaction;
@@ -634,17 +778,16 @@
int force_copy)
{
struct buffer_head *bh;
- transaction_t *transaction;
+ transaction_t *transaction = handle->h_transaction;
journal_t *journal;
int error;
char *frozen_buffer = NULL;
int need_copy = 0;
unsigned long start_lock, time_lock;
+ WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
-
- transaction = handle->h_transaction;
journal = transaction->t_journal;
jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
@@ -754,41 +897,29 @@
* journaled. If the primary copy is already going to
* disk then we cannot do copy-out here. */
- if (jh->b_jlist == BJ_Shadow) {
- DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow);
- wait_queue_head_t *wqh;
-
- wqh = bit_waitqueue(&bh->b_state, BH_Unshadow);
-
+ if (buffer_shadow(bh)) {
JBUFFER_TRACE(jh, "on shadow: sleep");
jbd_unlock_bh_state(bh);
- /* commit wakes up all shadow buffers after IO */
- for ( ; ; ) {
- prepare_to_wait(wqh, &wait.wait,
- TASK_UNINTERRUPTIBLE);
- if (jh->b_jlist != BJ_Shadow)
- break;
- schedule();
- }
- finish_wait(wqh, &wait.wait);
+ wait_on_bit_io(&bh->b_state, BH_Shadow,
+ TASK_UNINTERRUPTIBLE);
goto repeat;
}
- /* Only do the copy if the currently-owning transaction
- * still needs it. If it is on the Forget list, the
- * committing transaction is past that stage. The
- * buffer had better remain locked during the kmalloc,
- * but that should be true --- we hold the journal lock
- * still and the buffer is already on the BUF_JOURNAL
- * list so won't be flushed.
+ /*
+ * Only do the copy if the currently-owning transaction still
+ * needs it. If buffer isn't on BJ_Metadata list, the
+ * committing transaction is past that stage (here we use the
+ * fact that BH_Shadow is set under bh_state lock together with
+ * refiling to BJ_Shadow list and at this point we know the
+ * buffer doesn't have BH_Shadow set).
*
* Subtle point, though: if this is a get_undo_access,
* then we will be relying on the frozen_data to contain
* the new value of the committed_data record after the
* transaction, so we HAVE to force the frozen_data copy
- * in that case. */
-
- if (jh->b_jlist != BJ_Forget || force_copy) {
+ * in that case.
+ */
+ if (jh->b_jlist == BJ_Metadata || force_copy) {
JBUFFER_TRACE(jh, "generate frozen data");
if (!frozen_buffer) {
JBUFFER_TRACE(jh, "allocate memory for buffer");
@@ -797,7 +928,7 @@
jbd2_alloc(jh2bh(jh)->b_size,
GFP_NOFS);
if (!frozen_buffer) {
- printk(KERN_EMERG
+ printk(KERN_ERR
"%s: OOM for frozen_buffer\n",
__func__);
JBUFFER_TRACE(jh, "oom!");
@@ -915,14 +1046,16 @@
int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
struct journal_head *jh = jbd2_journal_add_journal_head(bh);
int err;
jbd_debug(5, "journal_head %p\n", jh);
+ WARN_ON(!transaction);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
+ journal = transaction->t_journal;
err = 0;
JBUFFER_TRACE(jh, "entry");
@@ -934,7 +1067,6 @@
* reused here.
*/
jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
jh->b_transaction == NULL ||
(jh->b_transaction == journal->j_committing_transaction &&
@@ -957,12 +1089,14 @@
jh->b_modified = 0;
JBUFFER_TRACE(jh, "file as BJ_Reserved");
+ spin_lock(&journal->j_list_lock);
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
} else if (jh->b_transaction == journal->j_committing_transaction) {
/* first access by this transaction */
jh->b_modified = 0;
JBUFFER_TRACE(jh, "set next transaction");
+ spin_lock(&journal->j_list_lock);
jh->b_next_transaction = transaction;
}
spin_unlock(&journal->j_list_lock);
@@ -1029,7 +1163,7 @@
if (!jh->b_committed_data) {
committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
if (!committed_data) {
- printk(KERN_EMERG "%s: No memory for committed data\n",
+ printk(KERN_ERR "%s: No memory for committed data\n",
__func__);
err = -ENOMEM;
goto out;
@@ -1128,12 +1262,14 @@
int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
struct journal_head *jh;
int ret = 0;
+ WARN_ON(!transaction);
if (is_handle_aborted(handle))
- goto out;
+ return -EROFS;
+ journal = transaction->t_journal;
jh = jbd2_journal_grab_journal_head(bh);
if (!jh) {
ret = -EUCLEAN;
@@ -1169,9 +1305,9 @@
JBUFFER_TRACE(jh, "fastpath");
if (unlikely(jh->b_transaction !=
journal->j_running_transaction)) {
- printk(KERN_EMERG "JBD: %s: "
+ printk(KERN_ERR "JBD2: %s: "
"jh->b_transaction (%llu, %p, %u) != "
- "journal->j_running_transaction (%p, %u)",
+ "journal->j_running_transaction (%p, %u)\n",
journal->j_devname,
(unsigned long long) bh->b_blocknr,
jh->b_transaction,
@@ -1194,30 +1330,25 @@
*/
if (jh->b_transaction != transaction) {
JBUFFER_TRACE(jh, "already on other transaction");
- if (unlikely(jh->b_transaction !=
- journal->j_committing_transaction)) {
- printk(KERN_EMERG "JBD: %s: "
- "jh->b_transaction (%llu, %p, %u) != "
- "journal->j_committing_transaction (%p, %u)",
+ if (unlikely(((jh->b_transaction !=
+ journal->j_committing_transaction)) ||
+ (jh->b_next_transaction != transaction))) {
+ printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: "
+ "bad jh for block %llu: "
+ "transaction (%p, %u), "
+ "jh->b_transaction (%p, %u), "
+ "jh->b_next_transaction (%p, %u), jlist %u\n",
journal->j_devname,
(unsigned long long) bh->b_blocknr,
+ transaction, transaction->t_tid,
jh->b_transaction,
- jh->b_transaction ? jh->b_transaction->t_tid : 0,
- journal->j_committing_transaction,
- journal->j_committing_transaction ?
- journal->j_committing_transaction->t_tid : 0);
- ret = -EINVAL;
- }
- if (unlikely(jh->b_next_transaction != transaction)) {
- printk(KERN_EMERG "JBD: %s: "
- "jh->b_next_transaction (%llu, %p, %u) != "
- "transaction (%p, %u)",
- journal->j_devname,
- (unsigned long long) bh->b_blocknr,
+ jh->b_transaction ?
+ jh->b_transaction->t_tid : 0,
jh->b_next_transaction,
jh->b_next_transaction ?
jh->b_next_transaction->t_tid : 0,
- transaction, transaction->t_tid);
+ jh->b_jlist);
+ WARN_ON(1);
ret = -EINVAL;
}
/* And this case is illegal: we can't reuse another
@@ -1230,7 +1361,7 @@
JBUFFER_TRACE(jh, "file as BJ_Metadata");
spin_lock(&journal->j_list_lock);
- __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_Metadata);
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata);
spin_unlock(&journal->j_list_lock);
out_unlock_bh:
jbd_unlock_bh_state(bh);
@@ -1260,16 +1391,20 @@
int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
struct journal_head *jh;
int drop_reserve = 0;
int err = 0;
int was_modified = 0;
+ WARN_ON(!transaction);
+ if (is_handle_aborted(handle))
+ return -EROFS;
+ journal = transaction->t_journal;
+
BUFFER_TRACE(bh, "entry");
jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
if (!buffer_jbd(bh))
goto not_jbd;
@@ -1292,7 +1427,7 @@
*/
jh->b_modified = 0;
- if (jh->b_transaction == handle->h_transaction) {
+ if (jh->b_transaction == transaction) {
J_ASSERT_JH(jh, !jh->b_frozen_data);
/* If we are forgetting a buffer which is already part
@@ -1322,6 +1457,7 @@
* we know to remove the checkpoint after we commit.
*/
+ spin_lock(&journal->j_list_lock);
if (jh->b_cp_transaction) {
__jbd2_journal_temp_unlink_buffer(jh);
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
@@ -1334,6 +1470,7 @@
goto drop;
}
}
+ spin_unlock(&journal->j_list_lock);
} else if (jh->b_transaction) {
J_ASSERT_JH(jh, (jh->b_transaction ==
journal->j_committing_transaction));
@@ -1345,7 +1482,9 @@
if (jh->b_next_transaction) {
J_ASSERT(jh->b_next_transaction == transaction);
+ spin_lock(&journal->j_list_lock);
jh->b_next_transaction = NULL;
+ spin_unlock(&journal->j_list_lock);
/*
* only drop a reference if this transaction modified
@@ -1357,7 +1496,6 @@
}
not_jbd:
- spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
__brelse(bh);
drop:
@@ -1387,19 +1525,21 @@
int jbd2_journal_stop(handle_t *handle)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
- int err, wait_for_commit = 0;
+ journal_t *journal;
+ int err = 0, wait_for_commit = 0;
tid_t tid;
pid_t pid;
+ if (!transaction)
+ goto free_and_exit;
+ journal = transaction->t_journal;
+
J_ASSERT(journal_current_handle() == handle);
if (is_handle_aborted(handle))
err = -EIO;
- else {
+ else
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
- err = 0;
- }
if (--handle->h_ref > 0) {
jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
@@ -1409,7 +1549,7 @@
jbd_debug(4, "Handle %p going down\n", handle);
trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev,
- handle->h_transaction->t_tid,
+ transaction->t_tid,
handle->h_type, handle->h_line_no,
jiffies - handle->h_start_jiffies,
handle->h_sync, handle->h_requested_credits,
@@ -1523,33 +1663,13 @@
lock_map_release(&handle->h_lockdep_map);
+ if (handle->h_rsv_handle)
+ jbd2_journal_free_reserved(handle->h_rsv_handle);
+free_and_exit:
jbd2_free_handle(handle);
return err;
}
-/**
- * int jbd2_journal_force_commit() - force any uncommitted transactions
- * @journal: journal to force
- *
- * For synchronous operations: force any uncommitted transactions
- * to disk. May seem kludgy, but it reuses all the handle batching
- * code in a very simple manner.
- */
-int jbd2_journal_force_commit(journal_t *journal)
-{
- handle_t *handle;
- int ret;
-
- handle = jbd2_journal_start(journal, 1);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- } else {
- handle->h_sync = 1;
- ret = jbd2_journal_stop(handle);
- }
- return ret;
-}
-
/*
*
* List management code snippets: various functions for manipulating the
@@ -1606,10 +1726,10 @@
* Remove a buffer from the appropriate transaction list.
*
* Note that this function can *change* the value of
- * bh->b_transaction->t_buffers, t_forget, t_iobuf_list, t_shadow_list,
- * t_log_list or t_reserved_list. If the caller is holding onto a copy of one
- * of these pointers, it could go bad. Generally the caller needs to re-read
- * the pointer from the transaction_t.
+ * bh->b_transaction->t_buffers, t_forget, t_shadow_list, t_log_list or
+ * t_reserved_list. If the caller is holding onto a copy of one of these
+ * pointers, it could go bad. Generally the caller needs to re-read the
+ * pointer from the transaction_t.
*
* Called under j_list_lock.
*/
@@ -1639,15 +1759,9 @@
case BJ_Forget:
list = &transaction->t_forget;
break;
- case BJ_IO:
- list = &transaction->t_iobuf_list;
- break;
case BJ_Shadow:
list = &transaction->t_shadow_list;
break;
- case BJ_LogCtl:
- list = &transaction->t_log_list;
- break;
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
@@ -1702,11 +1816,11 @@
if (buffer_locked(bh) || buffer_dirty(bh))
goto out;
- if (jh->b_next_transaction != NULL)
+ if (jh->b_next_transaction != NULL || jh->b_transaction != NULL)
goto out;
spin_lock(&journal->j_list_lock);
- if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
+ if (jh->b_cp_transaction != NULL) {
/* written-back checkpointed metadata buffer */
JBUFFER_TRACE(jh, "remove from checkpoint list");
__jbd2_journal_remove_checkpoint(jh);
@@ -2041,18 +2155,23 @@
* void jbd2_journal_invalidatepage()
* @journal: journal to use for flush...
* @page: page to flush
- * @offset: length of page to invalidate.
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
*
- * Reap page buffers containing data after offset in page. Can return -EBUSY
- * if buffers are part of the committing transaction and the page is straddling
- * i_size. Caller then has to wait for current commit and try again.
+ * Reap page buffers containing data after in the specified range in page.
+ * Can return -EBUSY if buffers are part of the committing transaction and
+ * the page is straddling i_size. Caller then has to wait for current commit
+ * and try again.
*/
int jbd2_journal_invalidatepage(journal_t *journal,
struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
struct buffer_head *head, *bh, *next;
+ unsigned int stop = offset + length;
unsigned int curr_off = 0;
+ int partial_page = (offset || length < PAGE_CACHE_SIZE);
int may_free = 1;
int ret = 0;
@@ -2061,6 +2180,8 @@
if (!page_has_buffers(page))
return 0;
+ BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+
/* We will potentially be playing with lists other than just the
* data lists (especially for journaled data mode), so be
* cautious in our locking. */
@@ -2070,10 +2191,13 @@
unsigned int next_off = curr_off + bh->b_size;
next = bh->b_this_page;
+ if (next_off > stop)
+ return 0;
+
if (offset <= curr_off) {
/* This block is wholly outside the truncation point */
lock_buffer(bh);
- ret = journal_unmap_buffer(journal, bh, offset > 0);
+ ret = journal_unmap_buffer(journal, bh, partial_page);
unlock_buffer(bh);
if (ret < 0)
return ret;
@@ -2084,7 +2208,7 @@
} while (bh != head);
- if (!offset) {
+ if (!partial_page) {
if (may_free && try_to_free_buffers(page))
J_ASSERT(!page_has_buffers(page));
}
@@ -2145,15 +2269,9 @@
case BJ_Forget:
list = &transaction->t_forget;
break;
- case BJ_IO:
- list = &transaction->t_iobuf_list;
- break;
case BJ_Shadow:
list = &transaction->t_shadow_list;
break;
- case BJ_LogCtl:
- list = &transaction->t_log_list;
- break;
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
@@ -2255,10 +2373,12 @@
int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
{
transaction_t *transaction = handle->h_transaction;
- journal_t *journal = transaction->t_journal;
+ journal_t *journal;
+ WARN_ON(!transaction);
if (is_handle_aborted(handle))
- return -EIO;
+ return -EROFS;
+ journal = transaction->t_journal;
jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino,
transaction->t_tid);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 0defb1c..0918f0e 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -243,6 +243,7 @@
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
int err;
+ sync_filesystem(sb);
err = jffs2_parse_options(c, data);
if (err)
return -EINVAL;
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 6740d34..9e3aaff 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -571,9 +571,10 @@
return ret;
}
-static void metapage_invalidatepage(struct page *page, unsigned long offset)
+static void metapage_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
- BUG_ON(offset);
+ BUG_ON(offset || length < PAGE_CACHE_SIZE);
BUG_ON(PageWriteback(page));
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 788e0a9..b7486da 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -413,6 +413,7 @@
int flag = JFS_SBI(sb)->flag;
int ret;
+ sync_filesystem(sb);
if (!parse_options(data, sb, &newLVSize, &flag)) {
return -EINVAL;
}
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index c2219a6..57914fc 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -159,7 +159,8 @@
return __logfs_writepage(page);
}
-static void logfs_invalidatepage(struct page *page, unsigned long offset)
+static void logfs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct logfs_block *block = logfs_block(page);
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 038da09..d448a77 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -884,7 +884,8 @@
return area;
}
-static void map_invalidatepage(struct page *page, unsigned long l)
+static void map_invalidatepage(struct page *page, unsigned int o,
+ unsigned int l)
{
return;
}
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index df12249..a54d088 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -123,6 +123,7 @@
struct minix_sb_info * sbi = minix_sb(sb);
struct minix_super_block * ms;
+ sync_filesystem(sb);
ms = sbi->s_ms;
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
return 0;
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 26910c8..3f54348 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -99,6 +99,7 @@
static int ncp_remount(struct super_block *sb, int *flags, char* data)
{
+ sync_filesystem(sb);
*flags |= MS_NODIRATIME;
return 0;
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a87a44f..6b4a79f 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -451,11 +451,13 @@
* - Called if either PG_private or PG_fscache is set on the page
* - Caller holds page lock
*/
-static void nfs_invalidate_page(struct page *page, unsigned long offset)
+static void nfs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
- dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);
+ dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n",
+ page, offset, length);
- if (offset != 0)
+ if (offset != 0 || length < PAGE_CACHE_SIZE)
return;
/* Cancel any unstarted writes on this page */
nfs_wb_page_cancel(page_file_mapping(page)->host, page);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 02c6ead..9de3976 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -79,7 +79,7 @@
{
if (fatal_signal_pending(current))
return -ERESTARTSYS;
- freezable_schedule();
+ freezable_schedule_unsafe();
return 0;
}
EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 43ea96c..ce90eb4 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -33,7 +33,7 @@
res = rpc_call_sync(clnt, msg, flags);
if (res != -EJUKEBOX)
break;
- freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
+ freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME);
res = -ERESTARTSYS;
} while (!fatal_signal_pending(current));
return res;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c2b89a1..6b4689b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -268,7 +268,7 @@
*timeout = NFS4_POLL_RETRY_MIN;
if (*timeout > NFS4_POLL_RETRY_MAX)
*timeout = NFS4_POLL_RETRY_MAX;
- freezable_schedule_timeout_killable(*timeout);
+ freezable_schedule_timeout_killable_unsafe(*timeout);
if (fatal_signal_pending(current))
res = -ERESTARTSYS;
*timeout <<= 1;
@@ -4557,7 +4557,7 @@
static unsigned long
nfs4_set_lock_task_retry(unsigned long timeout)
{
- freezable_schedule_timeout_killable(timeout);
+ freezable_schedule_timeout_killable_unsafe(timeout);
timeout <<= 1;
if (timeout > NFS4_LOCK_MAXTIMEOUT)
return NFS4_LOCK_MAXTIMEOUT;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2d7525f..d85c1b8 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2133,6 +2133,8 @@
struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
u32 nfsvers = nfss->nfs_client->rpc_ops->version;
+ sync_filesystem(sb);
+
/*
* Userspace mount programs that send binary options generally send
* them populated with default values. We have no way to know which
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 4e9a21d..105a3b0 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -240,11 +240,16 @@
struct list_head list;
};
+struct nfs4_dir_ctx {
+ struct dir_context ctx;
+ struct list_head names;
+};
+
static int
nfsd4_build_namelist(void *arg, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
- struct list_head *names = arg;
+ struct nfs4_dir_ctx *ctx = arg;
struct name_list *entry;
if (namlen != HEXDIR_LEN - 1)
@@ -254,7 +259,7 @@
return -ENOMEM;
memcpy(entry->name, name, HEXDIR_LEN - 1);
entry->name[HEXDIR_LEN - 1] = '\0';
- list_add(&entry->list, names);
+ list_add(&entry->list, &ctx->names);
return 0;
}
@@ -263,7 +268,10 @@
{
const struct cred *original_cred;
struct dentry *dir = nn->rec_file->f_path.dentry;
- LIST_HEAD(names);
+ struct nfs4_dir_ctx ctx = {
+ .ctx.actor = nfsd4_build_namelist,
+ .names = LIST_HEAD_INIT(ctx.names)
+ };
int status;
status = nfs4_save_creds(&original_cred);
@@ -276,11 +284,11 @@
return status;
}
- status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names);
+ status = iterate_dir(nn->rec_file, &ctx.ctx);
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
- while (!list_empty(&names)) {
+ while (!list_empty(&ctx.names)) {
struct name_list *entry;
- entry = list_entry(names.next, struct name_list, list);
+ entry = list_entry(ctx.names.next, struct name_list, list);
if (!status) {
struct dentry *dentry;
dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 81325ba..11224fa 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1950,6 +1950,7 @@
};
struct readdir_data {
+ struct dir_context ctx;
char *dirent;
size_t used;
int full;
@@ -1981,13 +1982,15 @@
static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
struct readdir_cd *cdp, loff_t *offsetp)
{
- struct readdir_data buf;
struct buffered_dirent *de;
int host_err;
int size;
loff_t offset;
+ struct readdir_data buf = {
+ .ctx.actor = nfsd_buffered_filldir,
+ .dirent = (void *)__get_free_page(GFP_KERNEL)
+ };
- buf.dirent = (void *)__get_free_page(GFP_KERNEL);
if (!buf.dirent)
return nfserrno(-ENOMEM);
@@ -2001,7 +2004,7 @@
buf.used = 0;
buf.full = 0;
- host_err = vfs_readdir(file, nfsd_buffered_filldir, &buf);
+ host_err = iterate_dir(file, &buf.ctx);
if (buf.full)
host_err = 0;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index c7d1f9f..4b0a8d4 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1114,6 +1114,7 @@
unsigned long old_mount_opt;
int err;
+ sync_filesystem(sb);
old_sb_flags = sb->s_flags;
old_mount_opt = nilfs->ns_mount_opt;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 959815c..fce2b85 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -738,6 +738,8 @@
struct fsnotify_group *group;
struct inode *inode;
struct path path;
+ struct path alteredpath;
+ struct path *canonical_path = &path;
struct fd f;
int ret;
unsigned flags = 0;
@@ -765,13 +767,22 @@
if (ret)
goto fput_and_out;
+ /* support stacked filesystems */
+ if(path.dentry && path.dentry->d_op) {
+ if (path.dentry->d_op->d_canonical_path) {
+ path.dentry->d_op->d_canonical_path(&path, &alteredpath);
+ canonical_path = &alteredpath;
+ path_put(&path);
+ }
+ }
+
/* inode held in place by reference to path; group by fget on fd */
- inode = path.dentry->d_inode;
+ inode = canonical_path->dentry->d_inode;
group = f.file->private_data;
/* create/update an inode mark */
ret = inotify_update_watch(group, inode, mask);
- path_put(&path);
+ path_put(canonical_path);
fput_and_out:
fdput(f);
return ret;
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index fa9c05f..d267ea6 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1372,7 +1372,7 @@
* The page may have dirty, unmapped buffers. Make them
* freeable here, so the page does not leak.
*/
- block_invalidatepage(page, 0);
+ block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
unlock_page(page);
ntfs_debug("Write outside i_size - truncated?");
return 0;
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 82650d5..bd5610d 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -468,6 +468,8 @@
ntfs_debug("Entering with remount options string: %s", opt);
+ sync_filesystem(sb);
+
#ifndef NTFS_RW
/* For read-only compiled driver, enforce read-only flag. */
*flags |= MS_RDONLY;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index f998c60..b259907 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -565,9 +565,7 @@
static void ocfs2_dio_end_io(struct kiocb *iocb,
loff_t offset,
ssize_t bytes,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct inode *inode = file_inode(iocb->ki_filp);
int level;
@@ -592,10 +590,6 @@
level = ocfs2_iocb_rw_locked_level(iocb);
ocfs2_rw_unlock(inode, level);
-
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
}
/*
@@ -603,7 +597,8 @@
* from ext3. PageChecked() bits have been removed as OCFS2 does not
* do journalled data.
*/
-static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
+static void ocfs2_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 01b8516..616bde6 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -632,6 +632,8 @@
struct ocfs2_super *osb = OCFS2_SB(sb);
u32 tmp;
+ sync_filesystem(sb);
+
if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
!ocfs2_check_set_options(sb, &parsed_options)) {
ret = -EINVAL;
diff --git a/fs/open.c b/fs/open.c
index 5f129683..86092bd 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -674,6 +674,7 @@
}
f->f_mapping = inode->i_mapping;
+ file_sb_list_add(f, inode->i_sb);
if (unlikely(f->f_mode & FMODE_PATH)) {
f->f_op = &empty_fops;
@@ -708,6 +709,7 @@
cleanup_all:
fops_put(f->f_op);
+ file_sb_list_del(f);
if (f->f_mode & FMODE_WRITE) {
if (!special_file(inode->i_mode)) {
/*
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 75885ff..f4026ab 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -375,6 +375,7 @@
static int openprom_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_NOATIME;
return 0;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index e5160b7..0b66e12 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2750,8 +2750,8 @@
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
- REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+ REG("oom_adj", S_IRUSR, proc_oom_adj_operations),
+ REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
@@ -3046,6 +3046,44 @@
}
/*
+ * proc_tid_comm_permission is a special permission function exclusively
+ * used for the node /proc/<pid>/task/<tid>/comm.
+ * It bypasses generic permission checks in the case where a task of the same
+ * task group attempts to access the node.
+ * The rational behind this is that glibc and bionic access this node for
+ * cross thread naming (pthread_set/getname_np(!self)). However, if
+ * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0,
+ * which locks out the cross thread naming implementation.
+ * This function makes sure that the node is always accessible for members of
+ * same thread group.
+ */
+static int proc_tid_comm_permission(struct inode *inode, int mask)
+{
+ bool is_same_tgroup;
+ struct task_struct *task;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
+ is_same_tgroup = same_thread_group(current, task);
+ put_task_struct(task);
+
+ if (likely(is_same_tgroup && !(mask & MAY_EXEC))) {
+ /* This file (/proc/<pid>/task/<tid>/comm) can always be
+ * read or written by the members of the corresponding
+ * thread group.
+ */
+ return 0;
+ }
+
+ return generic_permission(inode, mask);
+}
+
+static const struct inode_operations proc_tid_comm_inode_operations = {
+ .permission = proc_tid_comm_permission,
+};
+
+/*
* Tasks
*/
static const struct pid_entry tid_base_stuff[] = {
@@ -3060,7 +3098,9 @@
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
- REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+ NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
+ &proc_tid_comm_inode_operations,
+ &proc_pid_set_comm_operations, {}),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
INF("syscall", S_IRUGO, proc_pid_syscall),
#endif
@@ -3107,8 +3147,8 @@
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
- REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
- REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+ REG("oom_adj", S_IRUSR, proc_oom_adj_operations),
+ REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index d7a4a28..d8eda97 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -302,11 +302,19 @@
*/
int proc_fd_permission(struct inode *inode, int mask)
{
- int rv = generic_permission(inode, mask);
+ struct task_struct *p;
+ int rv;
+
+ rv = generic_permission(inode, mask);
if (rv == 0)
- return 0;
- if (task_pid(current) == proc_pid(inode))
+ return rv;
+
+ rcu_read_lock();
+ p = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (p && same_thread_group(p, current))
rv = 0;
+ rcu_read_unlock();
+
return rv;
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 04ec276..3df19e6e 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -92,6 +92,8 @@
int proc_remount(struct super_block *sb, int *flags, char *data)
{
struct pid_namespace *pid = sb->s_fs_info;
+
+ sync_filesystem(sb);
return !proc_parse_options(data, pid);
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b86db12..91cc282 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -134,6 +134,56 @@
}
#endif
+static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
+{
+ const char __user *name = vma_get_anon_name(vma);
+ struct mm_struct *mm = vma->vm_mm;
+
+ unsigned long page_start_vaddr;
+ unsigned long page_offset;
+ unsigned long num_pages;
+ unsigned long max_len = NAME_MAX;
+ int i;
+
+ page_start_vaddr = (unsigned long)name & PAGE_MASK;
+ page_offset = (unsigned long)name - page_start_vaddr;
+ num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE);
+
+ seq_puts(m, "[anon:");
+
+ for (i = 0; i < num_pages; i++) {
+ int len;
+ int write_len;
+ const char *kaddr;
+ long pages_pinned;
+ struct page *page;
+
+ pages_pinned = get_user_pages(current, mm, page_start_vaddr,
+ 1, 0, 0, &page, NULL);
+ if (pages_pinned < 1) {
+ seq_puts(m, "<fault>]");
+ return;
+ }
+
+ kaddr = (const char *)kmap(page);
+ len = min(max_len, PAGE_SIZE - page_offset);
+ write_len = strnlen(kaddr + page_offset, len);
+ seq_write(m, kaddr + page_offset, write_len);
+ kunmap(page);
+ put_page(page);
+
+ /* if strnlen hit a null terminator then we're done */
+ if (write_len != len)
+ break;
+
+ max_len -= len;
+ page_offset = 0;
+ page_start_vaddr += PAGE_SIZE;
+ }
+
+ seq_putc(m, ']');
+}
+
static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
if (vma && vma != priv->tail_vma) {
@@ -335,6 +385,12 @@
pad_len_spaces(m, len);
seq_printf(m, "[stack:%d]", tid);
}
+ goto done;
+ }
+
+ if (vma_get_anon_name(vma)) {
+ pad_len_spaces(m, len);
+ seq_print_vma_name(m, vma);
}
}
@@ -441,6 +497,7 @@
unsigned long swap;
unsigned long nonlinear;
u64 pss;
+ u64 swap_pss;
};
@@ -458,9 +515,20 @@
} else if (is_swap_pte(ptent)) {
swp_entry_t swpent = pte_to_swp_entry(ptent);
- if (!non_swap_entry(swpent))
- mss->swap += ptent_size;
- else if (is_migration_entry(swpent))
+ if (!non_swap_entry(swpent)) {
+ int mapcount;
+
+ mss->swap += PAGE_SIZE;
+ mapcount = swp_swapcount(swpent);
+ if (mapcount >= 2) {
+ u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT;
+
+ do_div(pss_delta, mapcount);
+ mss->swap_pss += pss_delta;
+ } else {
+ mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
+ }
+ } else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
} else if (pte_file(ptent)) {
if (pte_to_pgoff(ptent) != pgoff)
@@ -609,6 +677,7 @@
"Anonymous: %8lu kB\n"
"AnonHugePages: %8lu kB\n"
"Swap: %8lu kB\n"
+ "SwapPss: %8lu kB\n"
"KernelPageSize: %8lu kB\n"
"MMUPageSize: %8lu kB\n"
"Locked: %8lu kB\n",
@@ -623,6 +692,7 @@
mss.anonymous >> 10,
mss.anonymous_thp >> 10,
mss.swap >> 10,
+ (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
vma_kernel_pagesize(vma) >> 10,
vma_mmu_pagesize(vma) >> 10,
(vma->vm_flags & VM_LOCKED) ?
@@ -634,6 +704,12 @@
show_smap_vma_flags(m, vma);
+ if (vma_get_anon_name(vma)) {
+ seq_puts(m, "Name: ");
+ seq_print_vma_name(m, vma);
+ seq_putc(m, '\n');
+ }
+
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task->mm))
? vma->vm_start : 0;
@@ -722,6 +798,7 @@
#define CLEAR_REFS_ALL 1
#define CLEAR_REFS_ANON 2
#define CLEAR_REFS_MAPPED 3
+#define CLEAR_REFS_MM_HIWATER_RSS 5
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
@@ -741,7 +818,8 @@
rv = kstrtoint(strstrip(buffer), 10, &type);
if (rv < 0)
return rv;
- if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+ if ((type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) &&
+ type != CLEAR_REFS_MM_HIWATER_RSS)
return -EINVAL;
task = get_proc_task(file_inode(file));
if (!task)
@@ -752,6 +830,18 @@
.pmd_entry = clear_refs_pte_range,
.mm = mm,
};
+
+ if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+ /*
+ * Writing 5 to /proc/pid/clear_refs resets the peak
+ * resident set size to this mm's current rss value.
+ */
+ down_write(&mm->mmap_sem);
+ reset_mm_hiwater_rss(mm);
+ up_write(&mm->mmap_sem);
+ goto out_mm;
+ }
+
down_read(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
clear_refs_walk.private = vma;
@@ -775,6 +865,7 @@
}
flush_tlb_mm(mm);
up_read(&mm->mmap_sem);
+out_mm:
mmput(mm);
}
put_task_struct(task);
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index ca71db6..da12fd4 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -19,6 +19,16 @@
When the option is enabled, pstore will log all kernel
messages, even if no oops or panic happened.
+config PSTORE_PMSG
+ bool "Log user space messages"
+ depends on PSTORE
+ help
+ When the option is enabled, pstore will export a character
+ interface /dev/pmsg0 to log user space messages. On reboot
+ data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID].
+
+ If unsure, say N.
+
config PSTORE_FTRACE
bool "Persistent function tracer"
depends on PSTORE
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
index 4c9095c..e647d8e 100644
--- a/fs/pstore/Makefile
+++ b/fs/pstore/Makefile
@@ -7,5 +7,7 @@
pstore-objs += inode.o platform.o
obj-$(CONFIG_PSTORE_FTRACE) += ftrace.o
+obj-$(CONFIG_PSTORE_PMSG) += pmsg.o
+
ramoops-objs += ram.o ram_core.o
obj-$(CONFIG_PSTORE_RAM) += ramoops.o
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 66c8c2f..5474993 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -249,6 +249,7 @@
static int pstore_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
parse_options(data);
return 0;
@@ -315,22 +316,27 @@
switch (type) {
case PSTORE_TYPE_DMESG:
- sprintf(name, "dmesg-%s-%lld", psname, id);
+ scnprintf(name, sizeof(name), "dmesg-%s-%lld",
+ psname, id);
break;
case PSTORE_TYPE_CONSOLE:
- sprintf(name, "console-%s-%lld", psname, id);
+ scnprintf(name, sizeof(name), "console-%s-%lld", psname, id);
break;
case PSTORE_TYPE_FTRACE:
- sprintf(name, "ftrace-%s-%lld", psname, id);
+ scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id);
break;
case PSTORE_TYPE_MCE:
- sprintf(name, "mce-%s-%lld", psname, id);
+ scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id);
+ break;
+ case PSTORE_TYPE_PMSG:
+ scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
break;
case PSTORE_TYPE_UNKNOWN:
- sprintf(name, "unknown-%s-%lld", psname, id);
+ scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
break;
default:
- sprintf(name, "type%d-%s-%lld", type, psname, id);
+ scnprintf(name, sizeof(name), "type%d-%s-%lld",
+ type, psname, id);
break;
}
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 937d820..fd8d248 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -45,6 +45,12 @@
static inline void pstore_register_ftrace(void) {}
#endif
+#ifdef CONFIG_PSTORE_PMSG
+extern void pstore_register_pmsg(void);
+#else
+static inline void pstore_register_pmsg(void) {}
+#endif
+
extern struct pstore_info *psinfo;
extern void pstore_set_kmsg_bytes(int);
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 86d1038..4f11f23 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -267,6 +267,7 @@
kmsg_dump_register(&pstore_dumper);
pstore_register_console();
pstore_register_ftrace();
+ pstore_register_pmsg();
if (pstore_update_ms >= 0) {
pstore_timer.expires = jiffies +
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
new file mode 100644
index 0000000..82a86aa
--- /dev/null
+++ b/fs/pstore/pmsg.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include "internal.h"
+
+static DEFINE_MUTEX(pmsg_lock);
+#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE)
+
+static ssize_t write_pmsg(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ size_t i, buffer_size;
+ char *buffer;
+
+ if (!count)
+ return 0;
+
+ if (!access_ok(VERIFY_READ, buf, count))
+ return -EFAULT;
+
+ buffer_size = count;
+ if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE)
+ buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE;
+ buffer = vmalloc(buffer_size);
+ if (!buffer)
+ return -ENOMEM;
+
+ mutex_lock(&pmsg_lock);
+ for (i = 0; i < count; ) {
+ size_t c = min(count - i, buffer_size);
+ u64 id;
+ long ret;
+
+ ret = __copy_from_user(buffer, buf + i, c);
+ if (unlikely(ret != 0)) {
+ mutex_unlock(&pmsg_lock);
+ vfree(buffer);
+ return -EFAULT;
+ }
+ psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, c,
+ psinfo);
+
+ i += c;
+ }
+
+ mutex_unlock(&pmsg_lock);
+ vfree(buffer);
+ return count;
+}
+
+static const struct file_operations pmsg_fops = {
+ .owner = THIS_MODULE,
+ .llseek = noop_llseek,
+ .write = write_pmsg,
+};
+
+static struct class *pmsg_class;
+static int pmsg_major;
+#define PMSG_NAME "pmsg"
+#undef pr_fmt
+#define pr_fmt(fmt) PMSG_NAME ": " fmt
+
+static char *pmsg_devnode(struct device *dev, umode_t *mode)
+{
+ if (mode)
+ *mode = 0220;
+ return NULL;
+}
+
+void pstore_register_pmsg(void)
+{
+ struct device *pmsg_device;
+
+ pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops);
+ if (pmsg_major < 0) {
+ pr_err("register_chrdev failed\n");
+ goto err;
+ }
+
+ pmsg_class = class_create(THIS_MODULE, PMSG_NAME);
+ if (IS_ERR(pmsg_class)) {
+ pr_err("device class file already in use\n");
+ goto err_class;
+ }
+ pmsg_class->devnode = pmsg_devnode;
+
+ pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0),
+ NULL, "%s%d", PMSG_NAME, 0);
+ if (IS_ERR(pmsg_device)) {
+ pr_err("failed to create device\n");
+ goto err_device;
+ }
+ return;
+
+err_device:
+ class_destroy(pmsg_class);
+err_class:
+ unregister_chrdev(pmsg_major, PMSG_NAME);
+err:
+ return;
+}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index d3d3714..f721e47 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -51,6 +51,10 @@
module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400);
MODULE_PARM_DESC(ftrace_size, "size of ftrace log");
+static ulong ramoops_pmsg_size = MIN_MEM_SIZE;
+module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
+MODULE_PARM_DESC(pmsg_size, "size of user space message log");
+
static ulong mem_address;
module_param(mem_address, ulong, 0400);
MODULE_PARM_DESC(mem_address,
@@ -82,12 +86,14 @@
struct persistent_ram_zone **przs;
struct persistent_ram_zone *cprz;
struct persistent_ram_zone *fprz;
+ struct persistent_ram_zone *mprz;
phys_addr_t phys_addr;
unsigned long size;
unsigned int memtype;
size_t record_size;
size_t console_size;
size_t ftrace_size;
+ size_t pmsg_size;
int dump_oops;
struct persistent_ram_ecc_info ecc_info;
unsigned int max_dump_cnt;
@@ -96,6 +102,7 @@
unsigned int dump_read_cnt;
unsigned int console_read_cnt;
unsigned int ftrace_read_cnt;
+ unsigned int pmsg_read_cnt;
struct pstore_info pstore;
};
@@ -109,6 +116,7 @@
cxt->dump_read_cnt = 0;
cxt->console_read_cnt = 0;
cxt->ftrace_read_cnt = 0;
+ cxt->pmsg_read_cnt = 0;
return 0;
}
@@ -141,6 +149,12 @@
return prz;
}
+static bool prz_ok(struct persistent_ram_zone *prz)
+{
+ return !!prz && !!(persistent_ram_old_size(prz) +
+ persistent_ram_ecc_string(prz, NULL, 0));
+}
+
static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
int *count, struct timespec *time,
char **buf, struct pstore_info *psi)
@@ -153,13 +167,16 @@
prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt,
cxt->max_dump_cnt, id, type,
PSTORE_TYPE_DMESG, 1);
- if (!prz)
+ if (!prz_ok(prz))
prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt,
1, id, type, PSTORE_TYPE_CONSOLE, 0);
- if (!prz)
+ if (!prz_ok(prz))
prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt,
1, id, type, PSTORE_TYPE_FTRACE, 0);
- if (!prz)
+ if (!prz_ok(prz))
+ prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
+ 1, id, type, PSTORE_TYPE_PMSG, 0);
+ if (!prz_ok(prz))
return 0;
/* TODO(kees): Bogus time for the moment. */
@@ -222,6 +239,11 @@
return -ENOMEM;
persistent_ram_write(cxt->fprz, buf, size);
return 0;
+ } else if (type == PSTORE_TYPE_PMSG) {
+ if (!cxt->mprz)
+ return -ENOMEM;
+ persistent_ram_write(cxt->mprz, buf, size);
+ return 0;
}
if (type != PSTORE_TYPE_DMESG)
@@ -279,6 +301,9 @@
case PSTORE_TYPE_FTRACE:
prz = cxt->fprz;
break;
+ case PSTORE_TYPE_PMSG:
+ prz = cxt->mprz;
+ break;
default:
return -EINVAL;
}
@@ -388,6 +413,12 @@
return 0;
}
+void notrace ramoops_console_write_buf(const char *buf, size_t size)
+{
+ struct ramoops_context *cxt = &oops_cxt;
+ persistent_ram_write(cxt->cprz, buf, size);
+}
+
static int ramoops_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -404,7 +435,7 @@
goto fail_out;
if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size &&
- !pdata->ftrace_size)) {
+ !pdata->ftrace_size && !pdata->pmsg_size)) {
pr_err("The memory size and the record/console size must be "
"non-zero\n");
goto fail_out;
@@ -418,6 +449,8 @@
pdata->console_size = rounddown_pow_of_two(pdata->console_size);
if (!is_power_of_2(pdata->ftrace_size))
pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
+ if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size))
+ pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size);
cxt->size = pdata->mem_size;
cxt->phys_addr = pdata->mem_address;
@@ -425,12 +458,14 @@
cxt->record_size = pdata->record_size;
cxt->console_size = pdata->console_size;
cxt->ftrace_size = pdata->ftrace_size;
+ cxt->pmsg_size = pdata->pmsg_size;
cxt->dump_oops = pdata->dump_oops;
cxt->ecc_info = pdata->ecc_info;
paddr = cxt->phys_addr;
- dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size;
+ dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size
+ - cxt->pmsg_size;
err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz);
if (err)
goto fail_out;
@@ -445,13 +480,9 @@
if (err)
goto fail_init_fprz;
- if (!cxt->przs && !cxt->cprz && !cxt->fprz) {
- pr_err("memory size too small, minimum is %zu\n",
- cxt->console_size + cxt->record_size +
- cxt->ftrace_size);
- err = -EINVAL;
- goto fail_cnt;
- }
+ err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0);
+ if (err)
+ goto fail_init_mprz;
cxt->pstore.data = cxt;
/*
@@ -497,7 +528,8 @@
fail_clear:
cxt->pstore.bufsize = 0;
cxt->max_dump_cnt = 0;
-fail_cnt:
+ kfree(cxt->mprz);
+fail_init_mprz:
kfree(cxt->fprz);
fail_init_fprz:
kfree(cxt->cprz);
@@ -556,6 +588,7 @@
dummy_data->record_size = record_size;
dummy_data->console_size = ramoops_console_size;
dummy_data->ftrace_size = ramoops_ftrace_size;
+ dummy_data->pmsg_size = ramoops_pmsg_size;
dummy_data->dump_oops = dump_oops;
/*
* For backwards compatibility ramoops.ecc=1 means 16 bytes ECC
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 2e8caa6..3410e9f 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -46,6 +46,7 @@
{
struct qnx4_sb_info *qs;
+ sync_filesystem(sb);
qs = qnx4_sb(sb);
qs->Version = QNX4_VERSION;
*flags |= MS_RDONLY;
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 8d941ed..65cdaab 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -55,6 +55,7 @@
static int qnx6_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
diff --git a/fs/readdir.c b/fs/readdir.c
index fee38e0..d46eca8 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -20,11 +20,11 @@
#include <asm/uaccess.h>
-int vfs_readdir(struct file *file, filldir_t filler, void *buf)
+int iterate_dir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
int res = -ENOTDIR;
- if (!file->f_op || !file->f_op->readdir)
+ if (!file->f_op || (!file->f_op->readdir && !file->f_op->iterate))
goto out;
res = security_file_permission(file, MAY_READ);
@@ -37,15 +37,21 @@
res = -ENOENT;
if (!IS_DEADDIR(inode)) {
- res = file->f_op->readdir(file, buf, filler);
+ if (file->f_op->iterate) {
+ ctx->pos = file->f_pos;
+ res = file->f_op->iterate(file, ctx);
+ file->f_pos = ctx->pos;
+ } else {
+ res = file->f_op->readdir(file, ctx, ctx->actor);
+ ctx->pos = file->f_pos;
+ }
file_accessed(file);
}
mutex_unlock(&inode->i_mutex);
out:
return res;
}
-
-EXPORT_SYMBOL(vfs_readdir);
+EXPORT_SYMBOL(iterate_dir);
/*
* Traditional linux readdir() handling..
@@ -66,6 +72,7 @@
};
struct readdir_callback {
+ struct dir_context ctx;
struct old_linux_dirent __user * dirent;
int result;
};
@@ -73,7 +80,7 @@
static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset,
u64 ino, unsigned int d_type)
{
- struct readdir_callback * buf = (struct readdir_callback *) __buf;
+ struct readdir_callback *buf = (struct readdir_callback *) __buf;
struct old_linux_dirent __user * dirent;
unsigned long d_ino;
@@ -107,15 +114,15 @@
{
int error;
struct fd f = fdget(fd);
- struct readdir_callback buf;
+ struct readdir_callback buf = {
+ .ctx.actor = fillonedir,
+ .dirent = dirent
+ };
if (!f.file)
return -EBADF;
- buf.result = 0;
- buf.dirent = dirent;
-
- error = vfs_readdir(f.file, fillonedir, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (buf.result)
error = buf.result;
@@ -137,6 +144,7 @@
};
struct getdents_callback {
+ struct dir_context ctx;
struct linux_dirent __user * current_dir;
struct linux_dirent __user * previous;
int count;
@@ -191,7 +199,11 @@
{
struct fd f;
struct linux_dirent __user * lastdirent;
- struct getdents_callback buf;
+ struct getdents_callback buf = {
+ .ctx.actor = filldir,
+ .count = count,
+ .current_dir = dirent
+ };
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
@@ -201,17 +213,12 @@
if (!f.file)
return -EBADF;
- buf.current_dir = dirent;
- buf.previous = NULL;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(f.file, filldir, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
- if (put_user(f.file->f_pos, &lastdirent->d_off))
+ if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
@@ -221,6 +228,7 @@
}
struct getdents_callback64 {
+ struct dir_context ctx;
struct linux_dirent64 __user * current_dir;
struct linux_dirent64 __user * previous;
int count;
@@ -271,7 +279,11 @@
{
struct fd f;
struct linux_dirent64 __user * lastdirent;
- struct getdents_callback64 buf;
+ struct getdents_callback64 buf = {
+ .ctx.actor = filldir64,
+ .count = count,
+ .current_dir = dirent
+ };
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
@@ -281,17 +293,12 @@
if (!f.file)
return -EBADF;
- buf.current_dir = dirent;
- buf.previous = NULL;
- buf.count = count;
- buf.error = 0;
-
- error = vfs_readdir(f.file, filldir64, &buf);
+ error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
- typeof(lastdirent->d_off) d_off = f.file->f_pos;
+ typeof(lastdirent->d_off) d_off = buf.ctx.pos;
if (__put_user(d_off, &lastdirent->d_off))
error = -EFAULT;
else
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 3616644..dd76473 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2975,7 +2975,8 @@
}
/* clm -- taken from fs/buffer.c:block_invalidate_page */
-static void reiserfs_invalidatepage(struct page *page, unsigned long offset)
+static void reiserfs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct buffer_head *head, *bh, *next;
struct inode *inode = page->mapping->host;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index e2e202a..460f762 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1317,6 +1317,7 @@
int i;
#endif
+ sync_filesystem(s);
reiserfs_write_lock(s);
#ifdef CONFIG_QUOTA
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 15cbc41e..ae83948 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -435,6 +435,7 @@
*/
static int romfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
diff --git a/fs/sdcardfs/Kconfig b/fs/sdcardfs/Kconfig
new file mode 100755
index 0000000..a1c1033
--- /dev/null
+++ b/fs/sdcardfs/Kconfig
@@ -0,0 +1,13 @@
+config SDCARD_FS
+ tristate "sdcard file system"
+ depends on CONFIGFS_FS
+ default n
+ help
+ Sdcardfs is based on Wrapfs file system.
+
+config SDCARD_FS_FADV_NOACTIVE
+ bool "sdcardfs fadvise noactive support"
+ depends on FADV_NOACTIVE
+ default y
+ help
+ Sdcardfs supports fadvise noactive mode.
diff --git a/fs/sdcardfs/Makefile b/fs/sdcardfs/Makefile
new file mode 100755
index 0000000..b84fbb2
--- /dev/null
+++ b/fs/sdcardfs/Makefile
@@ -0,0 +1,7 @@
+SDCARDFS_VERSION="0.1"
+
+EXTRA_CFLAGS += -DSDCARDFS_VERSION=\"$(SDCARDFS_VERSION)\"
+
+obj-$(CONFIG_SDCARD_FS) += sdcardfs.o
+
+sdcardfs-y := dentry.o file.o inode.o main.o super.o lookup.o mmap.o packagelist.o derived_perm.o
diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c
new file mode 100755
index 0000000..b2fa36f
--- /dev/null
+++ b/fs/sdcardfs/dentry.c
@@ -0,0 +1,187 @@
+/*
+ * fs/sdcardfs/dentry.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include "linux/ctype.h"
+
+/*
+ * returns: -ERRNO if error (returned to user)
+ * 0: tell VFS to invalidate dentry
+ * 1: dentry is valid
+ */
+static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ int err = 1;
+ struct path parent_lower_path, lower_path;
+ struct dentry *parent_dentry = NULL;
+ struct dentry *parent_lower_dentry = NULL;
+ struct dentry *lower_cur_parent_dentry = NULL;
+ struct dentry *lower_dentry = NULL;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ spin_lock(&dentry->d_lock);
+ if (IS_ROOT(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ return 1;
+ }
+ spin_unlock(&dentry->d_lock);
+
+ /* check uninitialized obb_dentry and
+ * whether the base obbpath has been changed or not */
+ if (is_obbpath_invalid(dentry)) {
+ d_drop(dentry);
+ return 0;
+ }
+
+ parent_dentry = dget_parent(dentry);
+ sdcardfs_get_lower_path(parent_dentry, &parent_lower_path);
+ sdcardfs_get_real_lower(dentry, &lower_path);
+ parent_lower_dentry = parent_lower_path.dentry;
+ lower_dentry = lower_path.dentry;
+ lower_cur_parent_dentry = dget_parent(lower_dentry);
+
+ spin_lock(&lower_dentry->d_lock);
+ if (d_unhashed(lower_dentry)) {
+ spin_unlock(&lower_dentry->d_lock);
+ d_drop(dentry);
+ err = 0;
+ goto out;
+ }
+ spin_unlock(&lower_dentry->d_lock);
+
+ if (parent_lower_dentry != lower_cur_parent_dentry) {
+ d_drop(dentry);
+ err = 0;
+ goto out;
+ }
+
+ if (dentry < lower_dentry) {
+ spin_lock(&dentry->d_lock);
+ spin_lock(&lower_dentry->d_lock);
+ } else {
+ spin_lock(&lower_dentry->d_lock);
+ spin_lock(&dentry->d_lock);
+ }
+
+ if (dentry->d_name.len != lower_dentry->d_name.len) {
+ __d_drop(dentry);
+ err = 0;
+ } else if (strncasecmp(dentry->d_name.name, lower_dentry->d_name.name,
+ dentry->d_name.len) != 0) {
+ __d_drop(dentry);
+ err = 0;
+ }
+
+ if (dentry < lower_dentry) {
+ spin_unlock(&lower_dentry->d_lock);
+ spin_unlock(&dentry->d_lock);
+ } else {
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&lower_dentry->d_lock);
+ }
+
+out:
+ dput(parent_dentry);
+ dput(lower_cur_parent_dentry);
+ sdcardfs_put_lower_path(parent_dentry, &parent_lower_path);
+ sdcardfs_put_real_lower(dentry, &lower_path);
+ return err;
+}
+
+static void sdcardfs_d_release(struct dentry *dentry)
+{
+ /* release and reset the lower paths */
+ if(has_graft_path(dentry)) {
+ sdcardfs_put_reset_orig_path(dentry);
+ }
+ sdcardfs_put_reset_lower_path(dentry);
+ free_dentry_private_data(dentry);
+ return;
+}
+
+static int sdcardfs_hash_ci(const struct dentry *dentry,
+ const struct inode *inode, struct qstr *qstr)
+{
+ /*
+ * This function is copy of vfat_hashi.
+ * FIXME Should we support national language?
+ * Refer to vfat_hashi()
+ * struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
+ */
+ const unsigned char *name;
+ unsigned int len;
+ unsigned long hash;
+
+ name = qstr->name;
+ //len = vfat_striptail_len(qstr);
+ len = qstr->len;
+
+ hash = init_name_hash();
+ while (len--)
+ //hash = partial_name_hash(nls_tolower(t, *name++), hash);
+ hash = partial_name_hash(tolower(*name++), hash);
+ qstr->hash = end_name_hash(hash);
+
+ return 0;
+}
+
+/*
+ * Case insensitive compare of two vfat names.
+ */
+static int sdcardfs_cmp_ci(const struct dentry *parent,
+ const struct inode *pinode,
+ const struct dentry *dentry, const struct inode *inode,
+ unsigned int len, const char *str, const struct qstr *name)
+{
+ /* This function is copy of vfat_cmpi */
+ // FIXME Should we support national language?
+ //struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io;
+ //unsigned int alen, blen;
+
+ /* A filename cannot end in '.' or we treat it like it has none */
+ /*
+ alen = vfat_striptail_len(name);
+ blen = __vfat_striptail_len(len, str);
+ if (alen == blen) {
+ if (nls_strnicmp(t, name->name, str, alen) == 0)
+ return 0;
+ }
+ */
+ if (name->len == len) {
+ if (strncasecmp(name->name, str, len) == 0)
+ return 0;
+ }
+ return 1;
+}
+
+static void sdcardfs_canonical_path(const struct path *path, struct path *actual_path) {
+ sdcardfs_get_real_lower(path->dentry, actual_path);
+}
+
+const struct dentry_operations sdcardfs_ci_dops = {
+ .d_revalidate = sdcardfs_d_revalidate,
+ .d_release = sdcardfs_d_release,
+ .d_hash = sdcardfs_hash_ci,
+ .d_compare = sdcardfs_cmp_ci,
+ .d_canonical_path = sdcardfs_canonical_path,
+};
+
diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c
new file mode 100755
index 0000000..41e0e11
--- /dev/null
+++ b/fs/sdcardfs/derived_perm.c
@@ -0,0 +1,265 @@
+/*
+ * fs/sdcardfs/derived_perm.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+/* copy derived state from parent inode */
+static void inherit_derived_state(struct inode *parent, struct inode *child)
+{
+ struct sdcardfs_inode_info *pi = SDCARDFS_I(parent);
+ struct sdcardfs_inode_info *ci = SDCARDFS_I(child);
+
+ ci->perm = PERM_INHERIT;
+ ci->userid = pi->userid;
+ ci->d_uid = pi->d_uid;
+ ci->under_android = pi->under_android;
+}
+
+/* helper function for derived state */
+void setup_derived_state(struct inode *inode, perm_t perm,
+ userid_t userid, uid_t uid, bool under_android)
+{
+ struct sdcardfs_inode_info *info = SDCARDFS_I(inode);
+
+ info->perm = perm;
+ info->userid = userid;
+ info->d_uid = uid;
+ info->under_android = under_android;
+}
+
+/* While renaming, there is a point where we want the path from dentry, but the name from newdentry */
+void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry)
+{
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ struct sdcardfs_inode_info *info = SDCARDFS_I(dentry->d_inode);
+ struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode);
+ appid_t appid;
+
+ /* By default, each inode inherits from its parent.
+ * the properties are maintained on its private fields
+ * because the inode attributes will be modified with that of
+ * its lower inode.
+ * The derived state will be updated on the last
+ * stage of each system call by fix_derived_permission(inode).
+ */
+
+ inherit_derived_state(parent->d_inode, dentry->d_inode);
+
+ /* Derive custom permissions based on parent and current node */
+ switch (parent_info->perm) {
+ case PERM_INHERIT:
+ /* Already inherited above */
+ break;
+ case PERM_PRE_ROOT:
+ /* Legacy internal layout places users at top level */
+ info->perm = PERM_ROOT;
+ info->userid = simple_strtoul(newdentry->d_name.name, NULL, 10);
+ break;
+ case PERM_ROOT:
+ /* Assume masked off by default. */
+ if (!strcasecmp(newdentry->d_name.name, "Android")) {
+ /* App-specific directories inside; let anyone traverse */
+ info->perm = PERM_ANDROID;
+ info->under_android = true;
+ }
+ break;
+ case PERM_ANDROID:
+ if (!strcasecmp(newdentry->d_name.name, "data")) {
+ /* App-specific directories inside; let anyone traverse */
+ info->perm = PERM_ANDROID_DATA;
+ } else if (!strcasecmp(newdentry->d_name.name, "obb")) {
+ /* App-specific directories inside; let anyone traverse */
+ info->perm = PERM_ANDROID_OBB;
+ /* Single OBB directory is always shared */
+ } else if (!strcasecmp(newdentry->d_name.name, "media")) {
+ /* App-specific directories inside; let anyone traverse */
+ info->perm = PERM_ANDROID_MEDIA;
+ }
+ break;
+ case PERM_ANDROID_DATA:
+ case PERM_ANDROID_OBB:
+ case PERM_ANDROID_MEDIA:
+ appid = get_appid(sbi->pkgl_id, newdentry->d_name.name);
+ if (appid != 0) {
+ info->d_uid = multiuser_get_uid(parent_info->userid, appid);
+ }
+ break;
+ }
+}
+
+void get_derived_permission(struct dentry *parent, struct dentry *dentry)
+{
+ get_derived_permission_new(parent, dentry, dentry);
+}
+
+void get_derive_permissions_recursive(struct dentry *parent) {
+ struct dentry *dentry;
+ list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
+ if (dentry->d_inode) {
+ mutex_lock(&dentry->d_inode->i_mutex);
+ get_derived_permission(parent, dentry);
+ fix_derived_permission(dentry->d_inode);
+ get_derive_permissions_recursive(dentry);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ }
+ }
+}
+
+/* main function for updating derived permission */
+inline void update_derived_permission_lock(struct dentry *dentry)
+{
+ struct dentry *parent;
+
+ if(!dentry || !dentry->d_inode) {
+ printk(KERN_ERR "sdcardfs: %s: invalid dentry\n", __func__);
+ return;
+ }
+ /* FIXME:
+ * 1. need to check whether the dentry is updated or not
+ * 2. remove the root dentry update
+ */
+ mutex_lock(&dentry->d_inode->i_mutex);
+ if(IS_ROOT(dentry)) {
+ //setup_default_pre_root_state(dentry->d_inode);
+ } else {
+ parent = dget_parent(dentry);
+ if(parent) {
+ get_derived_permission(parent, dentry);
+ dput(parent);
+ }
+ }
+ fix_derived_permission(dentry->d_inode);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+}
+
+int need_graft_path(struct dentry *dentry)
+{
+ int ret = 0;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ if(parent_info->perm == PERM_ANDROID &&
+ !strcasecmp(dentry->d_name.name, "obb")) {
+
+ /* /Android/obb is the base obbpath of DERIVED_UNIFIED */
+ if(!(sbi->options.multiuser == false
+ && parent_info->userid == 0)) {
+ ret = 1;
+ }
+ }
+ dput(parent);
+ return ret;
+}
+
+int is_obbpath_invalid(struct dentry *dent)
+{
+ int ret = 0;
+ struct sdcardfs_dentry_info *di = SDCARDFS_D(dent);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb);
+ char *path_buf, *obbpath_s;
+
+ /* check the base obbpath has been changed.
+ * this routine can check an uninitialized obb dentry as well.
+ * regarding the uninitialized obb, refer to the sdcardfs_mkdir() */
+ spin_lock(&di->lock);
+ if(di->orig_path.dentry) {
+ if(!di->lower_path.dentry) {
+ ret = 1;
+ } else {
+ path_get(&di->lower_path);
+ //lower_parent = lock_parent(lower_path->dentry);
+
+ path_buf = kmalloc(PATH_MAX, GFP_ATOMIC);
+ if(!path_buf) {
+ ret = 1;
+ printk(KERN_ERR "sdcardfs: fail to allocate path_buf in %s.\n", __func__);
+ } else {
+ obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX);
+ if (d_unhashed(di->lower_path.dentry) ||
+ strcasecmp(sbi->obbpath_s, obbpath_s)) {
+ ret = 1;
+ }
+ kfree(path_buf);
+ }
+
+ //unlock_dir(lower_parent);
+ path_put(&di->lower_path);
+ }
+ }
+ spin_unlock(&di->lock);
+ return ret;
+}
+
+int is_base_obbpath(struct dentry *dentry)
+{
+ int ret = 0;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ spin_lock(&SDCARDFS_D(dentry)->lock);
+ if (sbi->options.multiuser) {
+ if(parent_info->perm == PERM_PRE_ROOT &&
+ !strcasecmp(dentry->d_name.name, "obb")) {
+ ret = 1;
+ }
+ } else if (parent_info->perm == PERM_ANDROID &&
+ !strcasecmp(dentry->d_name.name, "obb")) {
+ ret = 1;
+ }
+ spin_unlock(&SDCARDFS_D(dentry)->lock);
+ return ret;
+}
+
+/* The lower_path will be stored to the dentry's orig_path
+ * and the base obbpath will be copyed to the lower_path variable.
+ * if an error returned, there's no change in the lower_path
+ * returns: -ERRNO if error (0: no error) */
+int setup_obb_dentry(struct dentry *dentry, struct path *lower_path)
+{
+ int err = 0;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ struct path obbpath;
+
+ /* A local obb dentry must have its own orig_path to support rmdir
+ * and mkdir of itself. Usually, we expect that the sbi->obbpath
+ * is avaiable on this stage. */
+ sdcardfs_set_orig_path(dentry, lower_path);
+
+ err = kern_path(sbi->obbpath_s,
+ LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath);
+
+ if(!err) {
+ /* the obbpath base has been found */
+ printk(KERN_INFO "sdcardfs: the sbi->obbpath is found\n");
+ pathcpy(lower_path, &obbpath);
+ } else {
+ /* if the sbi->obbpath is not available, we can optionally
+ * setup the lower_path with its orig_path.
+ * but, the current implementation just returns an error
+ * because the sdcard daemon also regards this case as
+ * a lookup fail. */
+ printk(KERN_INFO "sdcardfs: the sbi->obbpath is not available\n");
+ }
+ return err;
+}
+
+
diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c
new file mode 100755
index 0000000..369051e
--- /dev/null
+++ b/fs/sdcardfs/file.c
@@ -0,0 +1,354 @@
+/*
+ * fs/sdcardfs/file.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+#include <linux/backing-dev.h>
+#endif
+
+static ssize_t sdcardfs_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err;
+ struct file *lower_file;
+ struct dentry *dentry = file->f_path.dentry;
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+ struct backing_dev_info *bdi;
+#endif
+
+ lower_file = sdcardfs_lower_file(file);
+
+#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE
+ if (file->f_mode & FMODE_NOACTIVE) {
+ if (!(lower_file->f_mode & FMODE_NOACTIVE)) {
+ bdi = lower_file->f_mapping->backing_dev_info;
+ lower_file->f_ra.ra_pages = bdi->ra_pages * 2;
+ spin_lock(&lower_file->f_lock);
+ lower_file->f_mode |= FMODE_NOACTIVE;
+ spin_unlock(&lower_file->f_lock);
+ }
+ }
+#endif
+
+ err = vfs_read(lower_file, buf, count, ppos);
+ /* update our inode atime upon a successful lower read */
+ if (err >= 0)
+ fsstack_copy_attr_atime(dentry->d_inode,
+ lower_file->f_path.dentry->d_inode);
+
+ return err;
+}
+
+static ssize_t sdcardfs_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err = 0;
+ struct file *lower_file;
+ struct dentry *dentry = file->f_path.dentry;
+
+ /* check disk space */
+ if (!check_min_free_space(dentry, count, 0)) {
+ printk(KERN_INFO "No minimum free space.\n");
+ return -ENOSPC;
+ }
+
+ lower_file = sdcardfs_lower_file(file);
+ err = vfs_write(lower_file, buf, count, ppos);
+ /* update our inode times+sizes upon a successful lower write */
+ if (err >= 0) {
+ fsstack_copy_inode_size(dentry->d_inode,
+ lower_file->f_path.dentry->d_inode);
+ fsstack_copy_attr_times(dentry->d_inode,
+ lower_file->f_path.dentry->d_inode);
+ }
+
+ return err;
+}
+
+static int sdcardfs_readdir(struct file *file, struct dir_context *ctx)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+
+ lower_file = sdcardfs_lower_file(file);
+
+ lower_file->f_pos = file->f_pos;
+ err = iterate_dir(lower_file, ctx);
+ file->f_pos = lower_file->f_pos;
+ if (err >= 0) /* copy the atime */
+ fsstack_copy_attr_atime(dentry->d_inode,
+ lower_file->f_path.dentry->d_inode);
+ return err;
+}
+
+static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ long err = -ENOTTY;
+ struct file *lower_file;
+
+ lower_file = sdcardfs_lower_file(file);
+
+ /* XXX: use vfs_ioctl if/when VFS exports it */
+ if (!lower_file || !lower_file->f_op)
+ goto out;
+ if (lower_file->f_op->unlocked_ioctl)
+ err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
+
+out:
+ return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long sdcardfs_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ long err = -ENOTTY;
+ struct file *lower_file;
+
+ lower_file = sdcardfs_lower_file(file);
+
+ /* XXX: use vfs_ioctl if/when VFS exports it */
+ if (!lower_file || !lower_file->f_op)
+ goto out;
+ if (lower_file->f_op->compat_ioctl)
+ err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
+
+out:
+ return err;
+}
+#endif
+
+static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int err = 0;
+ bool willwrite;
+ struct file *lower_file;
+ const struct vm_operations_struct *saved_vm_ops = NULL;
+
+ /* this might be deferred to mmap's writepage */
+ willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags);
+
+ /*
+ * File systems which do not implement ->writepage may use
+ * generic_file_readonly_mmap as their ->mmap op. If you call
+ * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL.
+ * But we cannot call the lower ->mmap op, so we can't tell that
+ * writeable mappings won't work. Therefore, our only choice is to
+ * check if the lower file system supports the ->writepage, and if
+ * not, return EINVAL (the same error that
+ * generic_file_readonly_mmap returns in that case).
+ */
+ lower_file = sdcardfs_lower_file(file);
+ if (willwrite && !lower_file->f_mapping->a_ops->writepage) {
+ err = -EINVAL;
+ printk(KERN_ERR "sdcardfs: lower file system does not "
+ "support writeable mmap\n");
+ goto out;
+ }
+
+ /*
+ * find and save lower vm_ops.
+ *
+ * XXX: the VFS should have a cleaner way of finding the lower vm_ops
+ */
+ if (!SDCARDFS_F(file)->lower_vm_ops) {
+ err = lower_file->f_op->mmap(lower_file, vma);
+ if (err) {
+ printk(KERN_ERR "sdcardfs: lower mmap failed %d\n", err);
+ goto out;
+ }
+ saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */
+ err = do_munmap(current->mm, vma->vm_start,
+ vma->vm_end - vma->vm_start);
+ if (err) {
+ printk(KERN_ERR "sdcardfs: do_munmap failed %d\n", err);
+ goto out;
+ }
+ }
+
+ /*
+ * Next 3 lines are all I need from generic_file_mmap. I definitely
+ * don't want its test for ->readpage which returns -ENOEXEC.
+ */
+ file_accessed(file);
+ vma->vm_ops = &sdcardfs_vm_ops;
+
+ file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */
+ if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */
+ SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops;
+
+out:
+ return err;
+}
+
+static int sdcardfs_open(struct inode *inode, struct file *file)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct path lower_path;
+ struct dentry *dentry = file->f_path.dentry;
+ struct dentry *parent = dget_parent(dentry);
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ const struct cred *saved_cred = NULL;
+
+ /* don't open unhashed/deleted files */
+ if (d_unhashed(dentry)) {
+ err = -ENOENT;
+ goto out_err;
+ }
+
+ if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_err;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(sbi, saved_cred);
+
+ file->private_data =
+ kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL);
+ if (!SDCARDFS_F(file)) {
+ err = -ENOMEM;
+ goto out_revert_cred;
+ }
+
+ /* open lower object and link sdcardfs's file struct to lower's */
+ sdcardfs_get_lower_path(file->f_path.dentry, &lower_path);
+ lower_file = dentry_open(&lower_path, file->f_flags, current_cred());
+ path_put(&lower_path);
+ if (IS_ERR(lower_file)) {
+ err = PTR_ERR(lower_file);
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file) {
+ sdcardfs_set_lower_file(file, NULL);
+ fput(lower_file); /* fput calls dput for lower_dentry */
+ }
+ } else {
+ sdcardfs_set_lower_file(file, lower_file);
+ }
+
+ if (err)
+ kfree(SDCARDFS_F(file));
+ else {
+ sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode));
+ }
+
+out_revert_cred:
+ REVERT_CRED(saved_cred);
+out_err:
+ dput(parent);
+ return err;
+}
+
+static int sdcardfs_flush(struct file *file, fl_owner_t id)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file && lower_file->f_op && lower_file->f_op->flush)
+ err = lower_file->f_op->flush(lower_file, id);
+
+ return err;
+}
+
+/* release all lower object references & free the file info structure */
+static int sdcardfs_file_release(struct inode *inode, struct file *file)
+{
+ struct file *lower_file;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file) {
+ sdcardfs_set_lower_file(file, NULL);
+ fput(lower_file);
+ }
+
+ kfree(SDCARDFS_F(file));
+ return 0;
+}
+
+static int sdcardfs_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ int err;
+ struct file *lower_file;
+ struct path lower_path;
+ struct dentry *dentry = file->f_path.dentry;
+
+ err = generic_file_fsync(file, start, end, datasync);
+ if (err)
+ goto out;
+
+ lower_file = sdcardfs_lower_file(file);
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_fsync_range(lower_file, start, end, datasync);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out:
+ return err;
+}
+
+static int sdcardfs_fasync(int fd, struct file *file, int flag)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+
+ lower_file = sdcardfs_lower_file(file);
+ if (lower_file->f_op && lower_file->f_op->fasync)
+ err = lower_file->f_op->fasync(fd, lower_file, flag);
+
+ return err;
+}
+
+const struct file_operations sdcardfs_main_fops = {
+ .llseek = generic_file_llseek,
+ .read = sdcardfs_read,
+ .write = sdcardfs_write,
+ .unlocked_ioctl = sdcardfs_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = sdcardfs_compat_ioctl,
+#endif
+ .mmap = sdcardfs_mmap,
+ .open = sdcardfs_open,
+ .flush = sdcardfs_flush,
+ .release = sdcardfs_file_release,
+ .fsync = sdcardfs_fsync,
+ .fasync = sdcardfs_fasync,
+};
+
+/* trimmed directory options */
+const struct file_operations sdcardfs_dir_fops = {
+ .llseek = generic_file_llseek,
+ .read = generic_read_dir,
+ .iterate = sdcardfs_readdir,
+ .unlocked_ioctl = sdcardfs_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = sdcardfs_compat_ioctl,
+#endif
+ .open = sdcardfs_open,
+ .release = sdcardfs_file_release,
+ .flush = sdcardfs_flush,
+ .fsync = sdcardfs_fsync,
+ .fasync = sdcardfs_fasync,
+};
diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c
new file mode 100755
index 0000000..0f4aa17
--- /dev/null
+++ b/fs/sdcardfs/inode.c
@@ -0,0 +1,813 @@
+/*
+ * fs/sdcardfs/inode.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+/* Do not directly use this function. Use OVERRIDE_CRED() instead. */
+const struct cred * override_fsids(struct sdcardfs_sb_info* sbi)
+{
+ struct cred * cred;
+ const struct cred * old_cred;
+
+ cred = prepare_creds();
+ if (!cred)
+ return NULL;
+
+ cred->fsuid = sbi->options.fs_low_uid;
+ cred->fsgid = sbi->options.fs_low_gid;
+
+ old_cred = override_creds(cred);
+
+ return old_cred;
+}
+
+/* Do not directly use this function, use REVERT_CRED() instead. */
+void revert_fsids(const struct cred * old_cred)
+{
+ const struct cred * cur_cred;
+
+ cur_cred = current->cred;
+ revert_creds(old_cred);
+ put_cred(cur_cred);
+}
+
+static int sdcardfs_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool want_excl)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+
+ if(!check_caller_access_to_name(dir, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred);
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ /* set last 16bytes of mode field to 0664 */
+ mode = (mode & S_IFMT) | 00664;
+ err = vfs_create(lower_parent_dentry->d_inode, lower_dentry, mode, want_excl);
+ if (err)
+ goto out;
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, SDCARDFS_I(dir)->userid);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, lower_parent_dentry->d_inode);
+
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *new_dentry)
+{
+ struct dentry *lower_old_dentry;
+ struct dentry *lower_new_dentry;
+ struct dentry *lower_dir_dentry;
+ u64 file_size_save;
+ int err;
+ struct path lower_old_path, lower_new_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ file_size_save = i_size_read(old_dentry->d_inode);
+ sdcardfs_get_lower_path(old_dentry, &lower_old_path);
+ sdcardfs_get_lower_path(new_dentry, &lower_new_path);
+ lower_old_dentry = lower_old_path.dentry;
+ lower_new_dentry = lower_new_path.dentry;
+ lower_dir_dentry = lock_parent(lower_new_dentry);
+
+ err = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
+ lower_new_dentry);
+ if (err || !lower_new_dentry->d_inode)
+ goto out;
+
+ err = sdcardfs_interpose(new_dentry, dir->i_sb, &lower_new_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, lower_new_dentry->d_inode);
+ fsstack_copy_inode_size(dir, lower_new_dentry->d_inode);
+ set_nlink(old_dentry->d_inode,
+ sdcardfs_lower_inode(old_dentry->d_inode)->i_nlink);
+ i_size_write(new_dentry->d_inode, file_size_save);
+out:
+ unlock_dir(lower_dir_dentry);
+ sdcardfs_put_lower_path(old_dentry, &lower_old_path);
+ sdcardfs_put_lower_path(new_dentry, &lower_new_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct inode *lower_dir_inode = sdcardfs_lower_inode(dir);
+ struct dentry *lower_dir_dentry;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+
+ if(!check_caller_access_to_name(dir, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred);
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ dget(lower_dentry);
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ err = vfs_unlink(lower_dir_inode, lower_dentry);
+
+ /*
+ * Note: unlinking on top of NFS can cause silly-renamed files.
+ * Trying to delete such files results in EBUSY from NFS
+ * below. Silly-renamed files will get deleted by NFS later on, so
+ * we just need to detect them here and treat such EBUSY errors as
+ * if the upper file was successfully deleted.
+ */
+ if (err == -EBUSY && lower_dentry->d_flags & DCACHE_NFSFS_RENAMED)
+ err = 0;
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, lower_dir_inode);
+ fsstack_copy_inode_size(dir, lower_dir_inode);
+ set_nlink(dentry->d_inode,
+ sdcardfs_lower_inode(dentry->d_inode)->i_nlink);
+ dentry->d_inode->i_ctime = dir->i_ctime;
+ d_drop(dentry); /* this is needed, else LTP fails (VFS won't do it) */
+out:
+ unlock_dir(lower_dir_dentry);
+ dput(lower_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_symlink(struct inode *dir, struct dentry *dentry,
+ const char *symname)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ err = vfs_symlink(lower_parent_dentry->d_inode, lower_dentry, symname);
+ if (err)
+ goto out;
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, lower_parent_dentry->d_inode);
+
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+static int touch(char *abs_path, mode_t mode) {
+ struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode);
+ if (IS_ERR(filp)) {
+ if (PTR_ERR(filp) == -EEXIST) {
+ return 0;
+ }
+ else {
+ printk(KERN_ERR "sdcardfs: failed to open(%s): %ld\n",
+ abs_path, PTR_ERR(filp));
+ return PTR_ERR(filp);
+ }
+ }
+ filp_close(filp, current->files);
+ return 0;
+}
+
+static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ int err = 0;
+ int make_nomedia_in_obb = 0;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+ const struct cred *saved_cred = NULL;
+ struct sdcardfs_inode_info *pi = SDCARDFS_I(dir);
+ char *page_buf;
+ char *nomedia_dir_name;
+ char *nomedia_fullpath;
+ int fullpath_namelen;
+ int touch_err = 0;
+
+ if(!check_caller_access_to_name(dir, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred);
+
+ /* check disk space */
+ if (!check_min_free_space(dentry, 0, 1)) {
+ printk(KERN_INFO "sdcardfs: No minimum free space.\n");
+ err = -ENOSPC;
+ goto out_revert;
+ }
+
+ /* the lower_dentry is negative here */
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ /* set last 16bytes of mode field to 0775 */
+ mode = (mode & S_IFMT) | 00775;
+ err = vfs_mkdir(lower_parent_dentry->d_inode, lower_dentry, mode);
+
+ if (err)
+ goto out;
+
+ /* if it is a local obb dentry, setup it with the base obbpath */
+ if(need_graft_path(dentry)) {
+
+ err = setup_obb_dentry(dentry, &lower_path);
+ if(err) {
+ /* if the sbi->obbpath is not available, the lower_path won't be
+ * changed by setup_obb_dentry() but the lower path is saved to
+ * its orig_path. this dentry will be revalidated later.
+ * but now, the lower_path should be NULL */
+ sdcardfs_put_reset_lower_path(dentry);
+
+ /* the newly created lower path which saved to its orig_path or
+ * the lower_path is the base obbpath.
+ * therefore, an additional path_get is required */
+ path_get(&lower_path);
+ } else
+ make_nomedia_in_obb = 1;
+ }
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pi->userid);
+ if (err)
+ goto out;
+
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, lower_parent_dentry->d_inode);
+ /* update number of links on parent directory */
+ set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink);
+
+ if ((!sbi->options.multiuser) && (!strcasecmp(dentry->d_name.name, "obb"))
+ && (pi->perm == PERM_ANDROID) && (pi->userid == 0))
+ make_nomedia_in_obb = 1;
+
+ /* When creating /Android/data and /Android/obb, mark them as .nomedia */
+ if (make_nomedia_in_obb ||
+ ((pi->perm == PERM_ANDROID) && (!strcasecmp(dentry->d_name.name, "data")))) {
+
+ page_buf = (char *)__get_free_page(GFP_KERNEL);
+ if (!page_buf) {
+ printk(KERN_ERR "sdcardfs: failed to allocate page buf\n");
+ goto out;
+ }
+
+ nomedia_dir_name = d_absolute_path(&lower_path, page_buf, PAGE_SIZE);
+ if (IS_ERR(nomedia_dir_name)) {
+ free_page((unsigned long)page_buf);
+ printk(KERN_ERR "sdcardfs: failed to get .nomedia dir name\n");
+ goto out;
+ }
+
+ fullpath_namelen = page_buf + PAGE_SIZE - nomedia_dir_name - 1;
+ fullpath_namelen += strlen("/.nomedia");
+ nomedia_fullpath = kzalloc(fullpath_namelen + 1, GFP_KERNEL);
+ if (!nomedia_fullpath) {
+ free_page((unsigned long)page_buf);
+ printk(KERN_ERR "sdcardfs: failed to allocate .nomedia fullpath buf\n");
+ goto out;
+ }
+
+ strcpy(nomedia_fullpath, nomedia_dir_name);
+ free_page((unsigned long)page_buf);
+ strcat(nomedia_fullpath, "/.nomedia");
+ touch_err = touch(nomedia_fullpath, 0664);
+ if (touch_err) {
+ printk(KERN_ERR "sdcardfs: failed to touch(%s): %d\n",
+ nomedia_fullpath, touch_err);
+ kfree(nomedia_fullpath);
+ goto out;
+ }
+ kfree(nomedia_fullpath);
+ }
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out_revert:
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ struct dentry *lower_dentry;
+ struct dentry *lower_dir_dentry;
+ int err;
+ struct path lower_path;
+ const struct cred *saved_cred = NULL;
+
+ if(!check_caller_access_to_name(dir, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred);
+
+ /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry
+ * the dentry on the original path should be deleted. */
+ sdcardfs_get_real_lower(dentry, &lower_path);
+
+ lower_dentry = lower_path.dentry;
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ err = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry);
+ if (err)
+ goto out;
+
+ d_drop(dentry); /* drop our dentry on success (why not VFS's job?) */
+ if (dentry->d_inode)
+ clear_nlink(dentry->d_inode);
+ fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+ fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
+ set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
+
+out:
+ unlock_dir(lower_dir_dentry);
+ sdcardfs_put_real_lower(dentry, &lower_path);
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+ dev_t dev)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct path lower_path;
+
+ OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb));
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev);
+ if (err)
+ goto out;
+
+ err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path);
+ if (err)
+ goto out;
+ fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir));
+ fsstack_copy_inode_size(dir, lower_parent_dentry->d_inode);
+
+out:
+ unlock_dir(lower_parent_dentry);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ REVERT_CRED();
+ return err;
+}
+#endif
+
+/*
+ * The locking rules in sdcardfs_rename are complex. We could use a simpler
+ * superblock-level name-space lock for renames and copy-ups.
+ */
+static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ int err = 0;
+ struct dentry *lower_old_dentry = NULL;
+ struct dentry *lower_new_dentry = NULL;
+ struct dentry *lower_old_dir_dentry = NULL;
+ struct dentry *lower_new_dir_dentry = NULL;
+ struct dentry *trap = NULL;
+ struct dentry *new_parent = NULL;
+ struct path lower_old_path, lower_new_path;
+ const struct cred *saved_cred = NULL;
+
+ if(!check_caller_access_to_name(old_dir, old_dentry->d_name.name) ||
+ !check_caller_access_to_name(new_dir, new_dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " new_dentry: %s, task:%s\n",
+ __func__, new_dentry->d_name.name, current->comm);
+ err = -EACCES;
+ goto out_eacces;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred);
+
+ sdcardfs_get_real_lower(old_dentry, &lower_old_path);
+ sdcardfs_get_lower_path(new_dentry, &lower_new_path);
+ lower_old_dentry = lower_old_path.dentry;
+ lower_new_dentry = lower_new_path.dentry;
+ lower_old_dir_dentry = dget_parent(lower_old_dentry);
+ lower_new_dir_dentry = dget_parent(lower_new_dentry);
+
+ trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+ /* source should not be ancestor of target */
+ if (trap == lower_old_dentry) {
+ err = -EINVAL;
+ goto out;
+ }
+ /* target should not be ancestor of source */
+ if (trap == lower_new_dentry) {
+ err = -ENOTEMPTY;
+ goto out;
+ }
+
+ err = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
+ lower_new_dir_dentry->d_inode, lower_new_dentry);
+ if (err)
+ goto out;
+
+ /* Copy attrs from lower dir, but i_uid/i_gid */
+ sdcardfs_copy_and_fix_attrs(new_dir, lower_new_dir_dentry->d_inode);
+ fsstack_copy_inode_size(new_dir, lower_new_dir_dentry->d_inode);
+
+ if (new_dir != old_dir) {
+ sdcardfs_copy_and_fix_attrs(old_dir, lower_old_dir_dentry->d_inode);
+ fsstack_copy_inode_size(old_dir, lower_old_dir_dentry->d_inode);
+
+ /* update the derived permission of the old_dentry
+ * with its new parent
+ */
+ new_parent = dget_parent(new_dentry);
+ if(new_parent) {
+ if(old_dentry->d_inode) {
+ update_derived_permission_lock(old_dentry);
+ }
+ dput(new_parent);
+ }
+ }
+ /* At this point, not all dentry information has been moved, so
+ * we pass along new_dentry for the name.*/
+ mutex_lock(&old_dentry->d_inode->i_mutex);
+ get_derived_permission_new(new_dentry->d_parent, old_dentry, new_dentry);
+ fix_derived_permission(old_dentry->d_inode);
+ get_derive_permissions_recursive(old_dentry);
+ mutex_unlock(&old_dentry->d_inode->i_mutex);
+out:
+ unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+ dput(lower_old_dir_dentry);
+ dput(lower_new_dir_dentry);
+ sdcardfs_put_real_lower(old_dentry, &lower_old_path);
+ sdcardfs_put_lower_path(new_dentry, &lower_new_path);
+ REVERT_CRED(saved_cred);
+out_eacces:
+ return err;
+}
+
+#if 0
+static int sdcardfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct path lower_path;
+ /* XXX readlink does not requires overriding credential */
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ if (!lower_dentry->d_inode->i_op ||
+ !lower_dentry->d_inode->i_op->readlink) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = lower_dentry->d_inode->i_op->readlink(lower_dentry,
+ buf, bufsiz);
+ if (err < 0)
+ goto out;
+ fsstack_copy_attr_atime(dentry->d_inode, lower_dentry->d_inode);
+
+out:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ return err;
+}
+#endif
+
+#if 0
+static void *sdcardfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ char *buf;
+ int len = PAGE_SIZE, err;
+ mm_segment_t old_fs;
+
+ /* This is freed by the put_link method assuming a successful call. */
+ buf = kmalloc(len, GFP_KERNEL);
+ if (!buf) {
+ buf = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ /* read the symlink, and then we will follow it */
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = sdcardfs_readlink(dentry, buf, len);
+ set_fs(old_fs);
+ if (err < 0) {
+ kfree(buf);
+ buf = ERR_PTR(err);
+ } else {
+ buf[err] = '\0';
+ }
+out:
+ nd_set_link(nd, buf);
+ return NULL;
+}
+#endif
+
+#if 0
+/* this @nd *IS* still used */
+static void sdcardfs_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ char *buf = nd_get_link(nd);
+ if (!IS_ERR(buf)) /* free the char* */
+ kfree(buf);
+}
+#endif
+
+static int sdcardfs_permission(struct inode *inode, int mask)
+{
+ int err;
+
+ /*
+ * Permission check on sdcardfs inode.
+ * Calling process should have AID_SDCARD_RW permission
+ */
+ err = generic_permission(inode, mask);
+
+ /* XXX
+ * Original sdcardfs code calls inode_permission(lower_inode,.. )
+ * for checking inode permission. But doing such things here seems
+ * duplicated work, because the functions called after this func,
+ * such as vfs_create, vfs_unlink, vfs_rename, and etc,
+ * does exactly same thing, i.e., they calls inode_permission().
+ * So we just let they do the things.
+ * If there are any security hole, just uncomment following if block.
+ */
+#if 0
+ if (!err) {
+ /*
+ * Permission check on lower_inode(=EXT4).
+ * we check it with AID_MEDIA_RW permission
+ */
+ struct inode *lower_inode;
+ OVERRIDE_CRED(SDCARDFS_SB(inode->sb));
+
+ lower_inode = sdcardfs_lower_inode(inode);
+ err = inode_permission(lower_inode, mask);
+
+ REVERT_CRED();
+ }
+#endif
+ return err;
+
+}
+
+static int sdcardfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct dentry *lower_dentry;
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct path lower_path;
+ struct dentry *parent;
+
+ parent = dget_parent(dentry);
+ if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ dput(parent);
+ return -EACCES;
+ }
+ dput(parent);
+
+ inode = dentry->d_inode;
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_inode = sdcardfs_lower_inode(inode);
+
+
+ sdcardfs_copy_and_fix_attrs(inode, lower_inode);
+ fsstack_copy_inode_size(inode, lower_inode);
+
+
+ generic_fillattr(inode, stat);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+ return 0;
+}
+
+static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct path lower_path;
+ struct iattr lower_ia;
+ struct dentry *parent;
+
+ inode = dentry->d_inode;
+
+ /*
+ * Check if user has permission to change inode. We don't check if
+ * this user can change the lower inode: that should happen when
+ * calling notify_change on the lower inode.
+ */
+ err = inode_change_ok(inode, ia);
+
+ /* no vfs_XXX operations required, cred overriding will be skipped. wj*/
+ if (!err) {
+ /* check the Android group ID */
+ parent = dget_parent(dentry);
+ if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) {
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ err = -EACCES;
+ }
+ dput(parent);
+ }
+
+ if (err)
+ goto out_err;
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ lower_dentry = lower_path.dentry;
+ lower_inode = sdcardfs_lower_inode(inode);
+
+ /* prepare our own lower struct iattr (with the lower file) */
+ memcpy(&lower_ia, ia, sizeof(lower_ia));
+ if (ia->ia_valid & ATTR_FILE)
+ lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file);
+
+ lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE);
+
+ /*
+ * If shrinking, first truncate upper level to cancel writing dirty
+ * pages beyond the new eof; and also if its' maxbytes is more
+ * limiting (fail with -EFBIG before making any change to the lower
+ * level). There is no need to vmtruncate the upper level
+ * afterwards in the other cases: we fsstack_copy_inode_size from
+ * the lower level.
+ */
+ if (current->mm)
+ down_write(¤t->mm->mmap_sem);
+ if (ia->ia_valid & ATTR_SIZE) {
+ err = inode_newsize_ok(inode, ia->ia_size);
+ if (err) {
+ if (current->mm)
+ up_write(¤t->mm->mmap_sem);
+ goto out;
+ }
+ truncate_setsize(inode, ia->ia_size);
+ }
+
+ /*
+ * mode change is for clearing setuid/setgid bits. Allow lower fs
+ * to interpret this in its own way.
+ */
+ if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
+ lower_ia.ia_valid &= ~ATTR_MODE;
+
+ /* notify the (possibly copied-up) lower inode */
+ /*
+ * Note: we use lower_dentry->d_inode, because lower_inode may be
+ * unlinked (no inode->i_sb and i_ino==0. This happens if someone
+ * tries to open(), unlink(), then ftruncate() a file.
+ */
+ mutex_lock(&lower_dentry->d_inode->i_mutex);
+ err = notify_change(lower_dentry, &lower_ia); /* note: lower_ia */
+ mutex_unlock(&lower_dentry->d_inode->i_mutex);
+ if (current->mm)
+ up_write(¤t->mm->mmap_sem);
+ if (err)
+ goto out;
+
+ /* get attributes from the lower inode and update derived permissions */
+ sdcardfs_copy_and_fix_attrs(inode, lower_inode);
+
+ /*
+ * Not running fsstack_copy_inode_size(inode, lower_inode), because
+ * VFS should update our inode size, and notify_change on
+ * lower_inode should update its size.
+ */
+
+out:
+ sdcardfs_put_lower_path(dentry, &lower_path);
+out_err:
+ return err;
+}
+
+const struct inode_operations sdcardfs_symlink_iops = {
+ .permission = sdcardfs_permission,
+ .setattr = sdcardfs_setattr,
+ /* XXX Following operations are implemented,
+ * but FUSE(sdcard) or FAT does not support them
+ * These methods are *NOT* perfectly tested.
+ .readlink = sdcardfs_readlink,
+ .follow_link = sdcardfs_follow_link,
+ .put_link = sdcardfs_put_link,
+ */
+};
+
+const struct inode_operations sdcardfs_dir_iops = {
+ .create = sdcardfs_create,
+ .lookup = sdcardfs_lookup,
+#if 0
+ .permission = sdcardfs_permission,
+#endif
+ .unlink = sdcardfs_unlink,
+ .mkdir = sdcardfs_mkdir,
+ .rmdir = sdcardfs_rmdir,
+ .rename = sdcardfs_rename,
+ .setattr = sdcardfs_setattr,
+ .getattr = sdcardfs_getattr,
+ /* XXX Following operations are implemented,
+ * but FUSE(sdcard) or FAT does not support them
+ * These methods are *NOT* perfectly tested.
+ .symlink = sdcardfs_symlink,
+ .link = sdcardfs_link,
+ .mknod = sdcardfs_mknod,
+ */
+};
+
+const struct inode_operations sdcardfs_main_iops = {
+ .permission = sdcardfs_permission,
+ .setattr = sdcardfs_setattr,
+ .getattr = sdcardfs_getattr,
+};
diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c
new file mode 100755
index 0000000..a01b06a
--- /dev/null
+++ b/fs/sdcardfs/lookup.c
@@ -0,0 +1,384 @@
+/*
+ * fs/sdcardfs/lookup.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include "linux/delay.h"
+
+/* The dentry cache is just so we have properly sized dentries */
+static struct kmem_cache *sdcardfs_dentry_cachep;
+
+int sdcardfs_init_dentry_cache(void)
+{
+ sdcardfs_dentry_cachep =
+ kmem_cache_create("sdcardfs_dentry",
+ sizeof(struct sdcardfs_dentry_info),
+ 0, SLAB_RECLAIM_ACCOUNT, NULL);
+
+ return sdcardfs_dentry_cachep ? 0 : -ENOMEM;
+}
+
+void sdcardfs_destroy_dentry_cache(void)
+{
+ if (sdcardfs_dentry_cachep)
+ kmem_cache_destroy(sdcardfs_dentry_cachep);
+}
+
+void free_dentry_private_data(struct dentry *dentry)
+{
+ if (!dentry || !dentry->d_fsdata)
+ return;
+ kmem_cache_free(sdcardfs_dentry_cachep, dentry->d_fsdata);
+ dentry->d_fsdata = NULL;
+}
+
+/* allocate new dentry private data */
+int new_dentry_private_data(struct dentry *dentry)
+{
+ struct sdcardfs_dentry_info *info = SDCARDFS_D(dentry);
+
+ /* use zalloc to init dentry_info.lower_path */
+ info = kmem_cache_zalloc(sdcardfs_dentry_cachep, GFP_ATOMIC);
+ if (!info)
+ return -ENOMEM;
+
+ spin_lock_init(&info->lock);
+ dentry->d_fsdata = info;
+
+ return 0;
+}
+
+struct inode_data {
+ struct inode *lower_inode;
+ userid_t id;
+};
+
+static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void *candidate_lower_inode*/)
+{
+ struct inode *current_lower_inode = sdcardfs_lower_inode(inode);
+ userid_t current_userid = SDCARDFS_I(inode)->userid;
+ if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode &&
+ current_userid == ((struct inode_data *)candidate_data)->id)
+ return 1; /* found a match */
+ else
+ return 0; /* no match */
+}
+
+static int sdcardfs_inode_set(struct inode *inode, void *lower_inode)
+{
+ /* we do actual inode initialization in sdcardfs_iget */
+ return 0;
+}
+
+struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, userid_t id)
+{
+ struct sdcardfs_inode_info *info;
+ struct inode_data data;
+ struct inode *inode; /* the new inode to return */
+ int err;
+
+ data.id = id;
+ data.lower_inode = lower_inode;
+ inode = iget5_locked(sb, /* our superblock */
+ /*
+ * hashval: we use inode number, but we can
+ * also use "(unsigned long)lower_inode"
+ * instead.
+ */
+ lower_inode->i_ino, /* hashval */
+ sdcardfs_inode_test, /* inode comparison function */
+ sdcardfs_inode_set, /* inode init function */
+ &data); /* data passed to test+set fxns */
+ if (!inode) {
+ err = -EACCES;
+ iput(lower_inode);
+ return ERR_PTR(err);
+ }
+ /* if found a cached inode, then just return it */
+ if (!(inode->i_state & I_NEW))
+ return inode;
+
+ /* initialize new inode */
+ info = SDCARDFS_I(inode);
+
+ inode->i_ino = lower_inode->i_ino;
+ if (!igrab(lower_inode)) {
+ err = -ESTALE;
+ return ERR_PTR(err);
+ }
+ sdcardfs_set_lower_inode(inode, lower_inode);
+
+ inode->i_version++;
+
+ /* use different set of inode ops for symlinks & directories */
+ if (S_ISDIR(lower_inode->i_mode))
+ inode->i_op = &sdcardfs_dir_iops;
+ else if (S_ISLNK(lower_inode->i_mode))
+ inode->i_op = &sdcardfs_symlink_iops;
+ else
+ inode->i_op = &sdcardfs_main_iops;
+
+ /* use different set of file ops for directories */
+ if (S_ISDIR(lower_inode->i_mode))
+ inode->i_fop = &sdcardfs_dir_fops;
+ else
+ inode->i_fop = &sdcardfs_main_fops;
+
+ inode->i_mapping->a_ops = &sdcardfs_aops;
+
+ inode->i_atime.tv_sec = 0;
+ inode->i_atime.tv_nsec = 0;
+ inode->i_mtime.tv_sec = 0;
+ inode->i_mtime.tv_nsec = 0;
+ inode->i_ctime.tv_sec = 0;
+ inode->i_ctime.tv_nsec = 0;
+
+ /* properly initialize special inodes */
+ if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) ||
+ S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode))
+ init_special_inode(inode, lower_inode->i_mode,
+ lower_inode->i_rdev);
+
+ /* all well, copy inode attributes */
+ sdcardfs_copy_and_fix_attrs(inode, lower_inode);
+ fsstack_copy_inode_size(inode, lower_inode);
+
+ unlock_new_inode(inode);
+ return inode;
+}
+
+/*
+ * Connect a sdcardfs inode dentry/inode with several lower ones. This is
+ * the classic stackable file system "vnode interposition" action.
+ *
+ * @dentry: sdcardfs's dentry which interposes on lower one
+ * @sb: sdcardfs's super_block
+ * @lower_path: the lower path (caller does path_get/put)
+ */
+int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb,
+ struct path *lower_path, userid_t id)
+{
+ int err = 0;
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct super_block *lower_sb;
+
+ lower_inode = lower_path->dentry->d_inode;
+ lower_sb = sdcardfs_lower_super(sb);
+
+ /* check that the lower file system didn't cross a mount point */
+ if (lower_inode->i_sb != lower_sb) {
+ err = -EXDEV;
+ goto out;
+ }
+
+ /*
+ * We allocate our new inode below by calling sdcardfs_iget,
+ * which will initialize some of the new inode's fields
+ */
+
+ /* inherit lower inode number for sdcardfs's inode */
+ inode = sdcardfs_iget(sb, lower_inode, id);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto out;
+ }
+
+ d_add(dentry, inode);
+ update_derived_permission_lock(dentry);
+out:
+ return err;
+}
+
+/*
+ * Main driver function for sdcardfs's lookup.
+ *
+ * Returns: NULL (ok), ERR_PTR if an error occurred.
+ * Fills in lower_parent_path with <dentry,mnt> on success.
+ */
+static struct dentry *__sdcardfs_lookup(struct dentry *dentry,
+ unsigned int flags, struct path *lower_parent_path, userid_t id)
+{
+ int err = 0;
+ struct vfsmount *lower_dir_mnt;
+ struct dentry *lower_dir_dentry = NULL;
+ struct dentry *lower_dentry;
+ const char *name;
+ struct path lower_path;
+ struct qstr this;
+ struct sdcardfs_sb_info *sbi;
+
+ sbi = SDCARDFS_SB(dentry->d_sb);
+ /* must initialize dentry operations */
+ d_set_d_op(dentry, &sdcardfs_ci_dops);
+
+ if (IS_ROOT(dentry))
+ goto out;
+
+ name = dentry->d_name.name;
+
+ /* now start the actual lookup procedure */
+ lower_dir_dentry = lower_parent_path->dentry;
+ lower_dir_mnt = lower_parent_path->mnt;
+
+ /* Use vfs_path_lookup to check if the dentry exists or not */
+ err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name, 0,
+ &lower_path);
+
+ /* no error: handle positive dentries */
+ if (!err) {
+ /* check if the dentry is an obb dentry
+ * if true, the lower_inode must be replaced with
+ * the inode of the graft path */
+
+ if(need_graft_path(dentry)) {
+
+ /* setup_obb_dentry()
+ * The lower_path will be stored to the dentry's orig_path
+ * and the base obbpath will be copyed to the lower_path variable.
+ * if an error returned, there's no change in the lower_path
+ * returns: -ERRNO if error (0: no error) */
+ err = setup_obb_dentry(dentry, &lower_path);
+
+ if(err) {
+ /* if the sbi->obbpath is not available, we can optionally
+ * setup the lower_path with its orig_path.
+ * but, the current implementation just returns an error
+ * because the sdcard daemon also regards this case as
+ * a lookup fail. */
+ printk(KERN_INFO "sdcardfs: base obbpath is not available\n");
+ sdcardfs_put_reset_orig_path(dentry);
+ goto out;
+ }
+ }
+
+ sdcardfs_set_lower_path(dentry, &lower_path);
+ err = sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id);
+ if (err) /* path_put underlying path on error */
+ sdcardfs_put_reset_lower_path(dentry);
+ goto out;
+ }
+
+ /*
+ * We don't consider ENOENT an error, and we want to return a
+ * negative dentry.
+ */
+ if (err && err != -ENOENT)
+ goto out;
+
+ /* instatiate a new negative dentry */
+ this.name = name;
+ this.len = strlen(name);
+ this.hash = full_name_hash(this.name, this.len);
+ lower_dentry = d_lookup(lower_dir_dentry, &this);
+ if (lower_dentry)
+ goto setup_lower;
+
+ lower_dentry = d_alloc(lower_dir_dentry, &this);
+ if (!lower_dentry) {
+ err = -ENOMEM;
+ goto out;
+ }
+ d_add(lower_dentry, NULL); /* instantiate and hash */
+
+setup_lower:
+ lower_path.dentry = lower_dentry;
+ lower_path.mnt = mntget(lower_dir_mnt);
+ sdcardfs_set_lower_path(dentry, &lower_path);
+
+ /*
+ * If the intent is to create a file, then don't return an error, so
+ * the VFS will continue the process of making this negative dentry
+ * into a positive one.
+ */
+ if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET))
+ err = 0;
+
+out:
+ return ERR_PTR(err);
+}
+
+/*
+ * On success:
+ * fills dentry object appropriate values and returns NULL.
+ * On fail (== error)
+ * returns error ptr
+ *
+ * @dir : Parent inode. It is locked (dir->i_mutex)
+ * @dentry : Target dentry to lookup. we should set each of fields.
+ * (dentry->d_name is initialized already)
+ * @nd : nameidata of parent inode
+ */
+struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct dentry *ret = NULL, *parent;
+ struct path lower_parent_path;
+ int err = 0;
+ const struct cred *saved_cred = NULL;
+
+ parent = dget_parent(dentry);
+
+ if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) {
+ ret = ERR_PTR(-EACCES);
+ printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n"
+ " dentry: %s, task:%s\n",
+ __func__, dentry->d_name.name, current->comm);
+ goto out_err;
+ }
+
+ /* save current_cred and override it */
+ OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred);
+
+ sdcardfs_get_lower_path(parent, &lower_parent_path);
+
+ /* allocate dentry private data. We free it in ->d_release */
+ err = new_dentry_private_data(dentry);
+ if (err) {
+ ret = ERR_PTR(err);
+ goto out;
+ }
+
+ ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path, SDCARDFS_I(dir)->userid);
+ if (IS_ERR(ret))
+ {
+ goto out;
+ }
+ if (ret)
+ dentry = ret;
+ if (dentry->d_inode) {
+ fsstack_copy_attr_times(dentry->d_inode,
+ sdcardfs_lower_inode(dentry->d_inode));
+ /* get drived permission */
+ mutex_lock(&dentry->d_inode->i_mutex);
+ get_derived_permission(parent, dentry);
+ fix_derived_permission(dentry->d_inode);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ }
+ /* update parent directory's atime */
+ fsstack_copy_attr_atime(parent->d_inode,
+ sdcardfs_lower_inode(parent->d_inode));
+
+out:
+ sdcardfs_put_lower_path(parent, &lower_parent_path);
+ REVERT_CRED(saved_cred);
+out_err:
+ dput(parent);
+ return ret;
+}
diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c
new file mode 100755
index 0000000..a652228
--- /dev/null
+++ b/fs/sdcardfs/main.c
@@ -0,0 +1,402 @@
+/*
+ * fs/sdcardfs/main.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/parser.h>
+
+enum {
+ Opt_fsuid,
+ Opt_fsgid,
+ Opt_gid,
+ Opt_debug,
+ Opt_lower_fs,
+ Opt_mask,
+ Opt_multiuser, // May need?
+ Opt_userid,
+ Opt_reserved_mb,
+ Opt_err,
+};
+
+static const match_table_t sdcardfs_tokens = {
+ {Opt_fsuid, "fsuid=%u"},
+ {Opt_fsgid, "fsgid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_debug, "debug"},
+ {Opt_mask, "mask=%u"},
+ {Opt_userid, "userid=%d"},
+ {Opt_multiuser, "multiuser"},
+ {Opt_reserved_mb, "reserved_mb=%u"},
+ {Opt_err, NULL}
+};
+
+static int parse_options(struct super_block *sb, char *options, int silent,
+ int *debug, struct sdcardfs_mount_options *opts)
+{
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+
+ /* by default, we use AID_MEDIA_RW as uid, gid */
+ opts->fs_low_uid = AID_MEDIA_RW;
+ opts->fs_low_gid = AID_MEDIA_RW;
+ opts->mask = 0;
+ opts->multiuser = false;
+ opts->fs_user_id = 0;
+ opts->gid = 0;
+ /* by default, 0MB is reserved */
+ opts->reserved_mb = 0;
+
+ *debug = 0;
+
+ if (!options)
+ return 0;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ token = match_token(p, sdcardfs_tokens, args);
+
+ switch (token) {
+ case Opt_debug:
+ *debug = 1;
+ break;
+ case Opt_fsuid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_low_uid = option;
+ break;
+ case Opt_fsgid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_low_gid = option;
+ break;
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->gid = option;
+ break;
+ case Opt_userid:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->fs_user_id = option;
+ break;
+ case Opt_mask:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->mask = option;
+ break;
+ case Opt_multiuser:
+ opts->multiuser = true;
+ break;
+ case Opt_reserved_mb:
+ if (match_int(&args[0], &option))
+ return 0;
+ opts->reserved_mb = option;
+ break;
+ /* unknown option */
+ default:
+ if (!silent) {
+ printk( KERN_ERR "Unrecognized mount option \"%s\" "
+ "or missing value", p);
+ }
+ return -EINVAL;
+ }
+ }
+
+ if (*debug) {
+ printk( KERN_INFO "sdcardfs : options - debug:%d\n", *debug);
+ printk( KERN_INFO "sdcardfs : options - uid:%d\n",
+ opts->fs_low_uid);
+ printk( KERN_INFO "sdcardfs : options - gid:%d\n",
+ opts->fs_low_gid);
+ }
+
+ return 0;
+}
+
+#if 0
+/*
+ * our custom d_alloc_root work-alike
+ *
+ * we can't use d_alloc_root if we want to use our own interpose function
+ * unchanged, so we simply call our own "fake" d_alloc_root
+ */
+static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb)
+{
+ struct dentry *ret = NULL;
+
+ if (sb) {
+ static const struct qstr name = {
+ .name = "/",
+ .len = 1
+ };
+
+ ret = d_alloc(NULL, &name);
+ if (ret) {
+ d_set_d_op(ret, &sdcardfs_ci_dops);
+ ret->d_sb = sb;
+ ret->d_parent = ret;
+ }
+ }
+ return ret;
+}
+#endif
+
+DEFINE_MUTEX(sdcardfs_super_list_lock);
+LIST_HEAD(sdcardfs_super_list);
+EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock);
+EXPORT_SYMBOL_GPL(sdcardfs_super_list);
+
+/*
+ * There is no need to lock the sdcardfs_super_info's rwsem as there is no
+ * way anyone can have a reference to the superblock at this point in time.
+ */
+static int sdcardfs_read_super(struct super_block *sb, const char *dev_name,
+ void *raw_data, int silent)
+{
+ int err = 0;
+ int debug;
+ struct super_block *lower_sb;
+ struct path lower_path;
+ struct sdcardfs_sb_info *sb_info;
+ struct inode *inode;
+
+ printk(KERN_INFO "sdcardfs version 2.0\n");
+
+ if (!dev_name) {
+ printk(KERN_ERR
+ "sdcardfs: read_super: missing dev_name argument\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ printk(KERN_INFO "sdcardfs: dev_name -> %s\n", dev_name);
+ printk(KERN_INFO "sdcardfs: options -> %s\n", (char *)raw_data);
+
+ /* parse lower path */
+ err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
+ &lower_path);
+ if (err) {
+ printk(KERN_ERR "sdcardfs: error accessing lower directory '%s'\n", dev_name);
+ goto out;
+ }
+
+ /* allocate superblock private data */
+ sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL);
+ if (!SDCARDFS_SB(sb)) {
+ printk(KERN_CRIT "sdcardfs: read_super: out of memory\n");
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ sb_info = sb->s_fs_info;
+ /* parse options */
+ err = parse_options(sb, raw_data, silent, &debug, &sb_info->options);
+ if (err) {
+ printk(KERN_ERR "sdcardfs: invalid options\n");
+ goto out_freesbi;
+ }
+
+ /* set the lower superblock field of upper superblock */
+ lower_sb = lower_path.dentry->d_sb;
+ atomic_inc(&lower_sb->s_active);
+ sdcardfs_set_lower_super(sb, lower_sb);
+
+ /* inherit maxbytes from lower file system */
+ sb->s_maxbytes = lower_sb->s_maxbytes;
+
+ /*
+ * Our c/m/atime granularity is 1 ns because we may stack on file
+ * systems whose granularity is as good.
+ */
+ sb->s_time_gran = 1;
+
+ sb->s_magic = SDCARDFS_SUPER_MAGIC;
+ sb->s_op = &sdcardfs_sops;
+
+ /* get a new inode and allocate our root dentry */
+ inode = sdcardfs_iget(sb, lower_path.dentry->d_inode, 0);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto out_sput;
+ }
+ sb->s_root = d_make_root(inode);
+ if (!sb->s_root) {
+ err = -ENOMEM;
+ goto out_iput;
+ }
+ d_set_d_op(sb->s_root, &sdcardfs_ci_dops);
+
+ /* link the upper and lower dentries */
+ sb->s_root->d_fsdata = NULL;
+ err = new_dentry_private_data(sb->s_root);
+ if (err)
+ goto out_freeroot;
+
+ /* set the lower dentries for s_root */
+ sdcardfs_set_lower_path(sb->s_root, &lower_path);
+
+ /*
+ * No need to call interpose because we already have a positive
+ * dentry, which was instantiated by d_make_root. Just need to
+ * d_rehash it.
+ */
+ d_rehash(sb->s_root);
+
+ /* setup permission policy */
+ sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL);
+ mutex_lock(&sdcardfs_super_list_lock);
+ if(sb_info->options.multiuser) {
+ setup_derived_state(sb->s_root->d_inode, PERM_PRE_ROOT, sb_info->options.fs_user_id, AID_ROOT, false);
+ snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name);
+ /*err = prepare_dir(sb_info->obbpath_s,
+ sb_info->options.fs_low_uid,
+ sb_info->options.fs_low_gid, 00755);*/
+ } else {
+ setup_derived_state(sb->s_root->d_inode, PERM_ROOT, sb_info->options.fs_low_uid, AID_ROOT, false);
+ snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name);
+ }
+ fix_derived_permission(sb->s_root->d_inode);
+ sb_info->sb = sb;
+ list_add(&sb_info->list, &sdcardfs_super_list);
+ mutex_unlock(&sdcardfs_super_list_lock);
+
+ if (!silent)
+ printk(KERN_INFO "sdcardfs: mounted on top of %s type %s\n",
+ dev_name, lower_sb->s_type->name);
+ goto out; /* all is well */
+
+ /* no longer needed: free_dentry_private_data(sb->s_root); */
+out_freeroot:
+ dput(sb->s_root);
+out_iput:
+ iput(inode);
+out_sput:
+ /* drop refs we took earlier */
+ atomic_dec(&lower_sb->s_active);
+out_freesbi:
+ kfree(SDCARDFS_SB(sb));
+ sb->s_fs_info = NULL;
+out_free:
+ path_put(&lower_path);
+
+out:
+ return err;
+}
+
+/* A feature which supports mount_nodev() with options */
+static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data,
+ int (*fill_super)(struct super_block *, const char *, void *, int))
+
+{
+ int error;
+ struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL);
+
+ if (IS_ERR(s))
+ return ERR_CAST(s);
+
+ s->s_flags = flags;
+
+ error = fill_super(s, dev_name, data, flags & MS_SILENT ? 1 : 0);
+ if (error) {
+ deactivate_locked_super(s);
+ return ERR_PTR(error);
+ }
+ s->s_flags |= MS_ACTIVE;
+ return dget(s->s_root);
+}
+
+struct dentry *sdcardfs_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *raw_data)
+{
+ /*
+ * dev_name is a lower_path_name,
+ * raw_data is a option string.
+ */
+ return mount_nodev_with_options(fs_type, flags, dev_name,
+ raw_data, sdcardfs_read_super);
+}
+
+void sdcardfs_kill_sb(struct super_block *sb) {
+ struct sdcardfs_sb_info *sbi;
+ if (sb->s_magic == SDCARDFS_SUPER_MAGIC) {
+ sbi = SDCARDFS_SB(sb);
+ mutex_lock(&sdcardfs_super_list_lock);
+ list_del(&sbi->list);
+ mutex_unlock(&sdcardfs_super_list_lock);
+ }
+ generic_shutdown_super(sb);
+}
+
+static struct file_system_type sdcardfs_fs_type = {
+ .owner = THIS_MODULE,
+ .name = SDCARDFS_NAME,
+ .mount = sdcardfs_mount,
+ .kill_sb = sdcardfs_kill_sb,
+ .fs_flags = 0,
+};
+
+static int __init init_sdcardfs_fs(void)
+{
+ int err;
+
+ pr_info("Registering sdcardfs " SDCARDFS_VERSION "\n");
+
+ err = sdcardfs_init_inode_cache();
+ if (err)
+ goto out;
+ err = sdcardfs_init_dentry_cache();
+ if (err)
+ goto out;
+ err = packagelist_init();
+ if (err)
+ goto out;
+ err = register_filesystem(&sdcardfs_fs_type);
+out:
+ if (err) {
+ sdcardfs_destroy_inode_cache();
+ sdcardfs_destroy_dentry_cache();
+ packagelist_exit();
+ }
+ return err;
+}
+
+static void __exit exit_sdcardfs_fs(void)
+{
+ sdcardfs_destroy_inode_cache();
+ sdcardfs_destroy_dentry_cache();
+ packagelist_exit();
+ unregister_filesystem(&sdcardfs_fs_type);
+ pr_info("Completed sdcardfs module unload\n");
+}
+
+MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University"
+ " (http://www.fsl.cs.sunysb.edu/)");
+MODULE_DESCRIPTION("Wrapfs " SDCARDFS_VERSION
+ " (http://wrapfs.filesystems.org/)");
+MODULE_LICENSE("GPL");
+
+module_init(init_sdcardfs_fs);
+module_exit(exit_sdcardfs_fs);
diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c
new file mode 100755
index 0000000..c807d7f
--- /dev/null
+++ b/fs/sdcardfs/mmap.c
@@ -0,0 +1,82 @@
+/*
+ * fs/sdcardfs/mmap.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ int err;
+ struct file *file, *lower_file;
+ const struct vm_operations_struct *lower_vm_ops;
+ struct vm_area_struct lower_vma;
+
+ memcpy(&lower_vma, vma, sizeof(struct vm_area_struct));
+ file = lower_vma.vm_file;
+ lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops;
+ BUG_ON(!lower_vm_ops);
+
+ lower_file = sdcardfs_lower_file(file);
+ /*
+ * XXX: vm_ops->fault may be called in parallel. Because we have to
+ * resort to temporarily changing the vma->vm_file to point to the
+ * lower file, a concurrent invocation of sdcardfs_fault could see a
+ * different value. In this workaround, we keep a different copy of
+ * the vma structure in our stack, so we never expose a different
+ * value of the vma->vm_file called to us, even temporarily. A
+ * better fix would be to change the calling semantics of ->fault to
+ * take an explicit file pointer.
+ */
+ lower_vma.vm_file = lower_file;
+ err = lower_vm_ops->fault(&lower_vma, vmf);
+ return err;
+}
+
+static ssize_t sdcardfs_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ /*
+ * This function returns zero on purpose in order to support direct IO.
+ * __dentry_open checks a_ops->direct_IO and returns EINVAL if it is null.
+ *
+ * However, this function won't be called by certain file operations
+ * including generic fs functions. * reads and writes are delivered to
+ * the lower file systems and the direct IOs will be handled by them.
+ *
+ * NOTE: exceptionally, on the recent kernels (since Linux 3.8.x),
+ * swap_writepage invokes this function directly.
+ */
+ printk(KERN_INFO "%s, operation is not supported\n", __func__);
+ return 0;
+}
+
+/*
+ * XXX: the default address_space_ops for sdcardfs is empty. We cannot set
+ * our inode->i_mapping->a_ops to NULL because too many code paths expect
+ * the a_ops vector to be non-NULL.
+ */
+const struct address_space_operations sdcardfs_aops = {
+ /* empty on purpose */
+ .direct_IO = sdcardfs_direct_IO,
+};
+
+const struct vm_operations_struct sdcardfs_vm_ops = {
+ .fault = sdcardfs_fault,
+};
diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h
new file mode 100755
index 0000000..923ba10
--- /dev/null
+++ b/fs/sdcardfs/multiuser.h
@@ -0,0 +1,37 @@
+/*
+ * fs/sdcardfs/multiuser.h
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#define MULTIUSER_APP_PER_USER_RANGE 100000
+
+typedef uid_t userid_t;
+typedef uid_t appid_t;
+
+static inline userid_t multiuser_get_user_id(uid_t uid) {
+ return uid / MULTIUSER_APP_PER_USER_RANGE;
+}
+
+static inline appid_t multiuser_get_app_id(uid_t uid) {
+ return uid % MULTIUSER_APP_PER_USER_RANGE;
+}
+
+static inline uid_t multiuser_get_uid(userid_t userId, appid_t appId) {
+ return userId * MULTIUSER_APP_PER_USER_RANGE + (appId % MULTIUSER_APP_PER_USER_RANGE);
+}
+
diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c
new file mode 100755
index 0000000..0cf9c34
--- /dev/null
+++ b/fs/sdcardfs/packagelist.c
@@ -0,0 +1,447 @@
+/*
+ * fs/sdcardfs/packagelist.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+#include <linux/hashtable.h>
+#include <linux/delay.h>
+
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+#define STRING_BUF_SIZE (512)
+
+struct hashtable_entry {
+ struct hlist_node hlist;
+ void *key;
+ unsigned int value;
+};
+
+struct sb_list {
+ struct super_block *sb;
+ struct list_head list;
+};
+
+struct packagelist_data {
+ DECLARE_HASHTABLE(package_to_appid,8);
+ struct mutex hashtable_lock;
+
+};
+
+static struct packagelist_data *pkgl_data_all;
+
+static struct kmem_cache *hashtable_entry_cachep;
+
+static unsigned int str_hash(const char *key) {
+ int i;
+ unsigned int h = strlen(key);
+ char *data = (char *)key;
+
+ for (i = 0; i < strlen(key); i++) {
+ h = h * 31 + *data;
+ data++;
+ }
+ return h;
+}
+
+appid_t get_appid(void *pkgl_id, const char *app_name)
+{
+ struct packagelist_data *pkgl_dat = pkgl_data_all;
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = str_hash(app_name);
+ appid_t ret_id;
+
+ mutex_lock(&pkgl_dat->hashtable_lock);
+ hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) {
+ if (!strcasecmp(app_name, hash_cur->key)) {
+ ret_id = (appid_t)hash_cur->value;
+ mutex_unlock(&pkgl_dat->hashtable_lock);
+ return ret_id;
+ }
+ }
+ mutex_unlock(&pkgl_dat->hashtable_lock);
+ return 0;
+}
+
+/* Kernel has already enforced everything we returned through
+ * derive_permissions_locked(), so this is used to lock down access
+ * even further, such as enforcing that apps hold sdcard_rw. */
+int check_caller_access_to_name(struct inode *parent_node, const char* name) {
+
+ /* Always block security-sensitive files at root */
+ if (parent_node && SDCARDFS_I(parent_node)->perm == PERM_ROOT) {
+ if (!strcasecmp(name, "autorun.inf")
+ || !strcasecmp(name, ".android_secure")
+ || !strcasecmp(name, "android_secure")) {
+ return 0;
+ }
+ }
+
+ /* Root always has access; access for any other UIDs should always
+ * be controlled through packages.list. */
+ if (current_fsuid() == 0) {
+ return 1;
+ }
+
+ /* No extra permissions to enforce */
+ return 1;
+}
+
+/* This function is used when file opening. The open flags must be
+ * checked before calling check_caller_access_to_name() */
+int open_flags_to_access_mode(int open_flags) {
+ if((open_flags & O_ACCMODE) == O_RDONLY) {
+ return 0; /* R_OK */
+ } else if ((open_flags & O_ACCMODE) == O_WRONLY) {
+ return 1; /* W_OK */
+ } else {
+ /* Probably O_RDRW, but treat as default to be safe */
+ return 1; /* R_OK | W_OK */
+ }
+}
+
+static int insert_str_to_int_lock(struct packagelist_data *pkgl_dat, char *key,
+ unsigned int value)
+{
+ struct hashtable_entry *hash_cur;
+ struct hashtable_entry *new_entry;
+ unsigned int hash = str_hash(key);
+
+ hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) {
+ if (!strcasecmp(key, hash_cur->key)) {
+ hash_cur->value = value;
+ return 0;
+ }
+ }
+ new_entry = kmem_cache_alloc(hashtable_entry_cachep, GFP_KERNEL);
+ if (!new_entry)
+ return -ENOMEM;
+ new_entry->key = kstrdup(key, GFP_KERNEL);
+ new_entry->value = value;
+ hash_add(pkgl_dat->package_to_appid, &new_entry->hlist, hash);
+ return 0;
+}
+
+static void fixup_perms(struct super_block *sb) {
+ if (sb && sb->s_magic == SDCARDFS_SUPER_MAGIC) {
+ mutex_lock(&sb->s_root->d_inode->i_mutex);
+ get_derive_permissions_recursive(sb->s_root);
+ mutex_unlock(&sb->s_root->d_inode->i_mutex);
+ }
+}
+
+static int insert_str_to_int(struct packagelist_data *pkgl_dat, char *key,
+ unsigned int value) {
+ int ret;
+ struct sdcardfs_sb_info *sbinfo;
+ mutex_lock(&sdcardfs_super_list_lock);
+ mutex_lock(&pkgl_dat->hashtable_lock);
+ ret = insert_str_to_int_lock(pkgl_dat, key, value);
+ mutex_unlock(&pkgl_dat->hashtable_lock);
+
+ list_for_each_entry(sbinfo, &sdcardfs_super_list, list) {
+ if (sbinfo) {
+ fixup_perms(sbinfo->sb);
+ }
+ }
+ mutex_unlock(&sdcardfs_super_list_lock);
+ return ret;
+}
+
+static void remove_str_to_int_lock(struct hashtable_entry *h_entry) {
+ kfree(h_entry->key);
+ hash_del(&h_entry->hlist);
+ kmem_cache_free(hashtable_entry_cachep, h_entry);
+}
+
+static void remove_str_to_int(struct packagelist_data *pkgl_dat, const char *key)
+{
+ struct sdcardfs_sb_info *sbinfo;
+ struct hashtable_entry *hash_cur;
+ unsigned int hash = str_hash(key);
+ mutex_lock(&sdcardfs_super_list_lock);
+ mutex_lock(&pkgl_dat->hashtable_lock);
+ hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) {
+ if (!strcasecmp(key, hash_cur->key)) {
+ remove_str_to_int_lock(hash_cur);
+ break;
+ }
+ }
+ mutex_unlock(&pkgl_dat->hashtable_lock);
+ list_for_each_entry(sbinfo, &sdcardfs_super_list, list) {
+ if (sbinfo) {
+ fixup_perms(sbinfo->sb);
+ }
+ }
+ mutex_unlock(&sdcardfs_super_list_lock);
+ return;
+}
+
+static void remove_all_hashentrys(struct packagelist_data *pkgl_dat)
+{
+ struct hashtable_entry *hash_cur;
+ struct hlist_node *h_t;
+ int i;
+ mutex_lock(&pkgl_dat->hashtable_lock);
+ hash_for_each_safe(pkgl_dat->package_to_appid, i, h_t, hash_cur, hlist)
+ remove_str_to_int_lock(hash_cur);
+ mutex_unlock(&pkgl_dat->hashtable_lock);
+ hash_init(pkgl_dat->package_to_appid);
+}
+
+static struct packagelist_data * packagelist_create(void)
+{
+ struct packagelist_data *pkgl_dat;
+
+ pkgl_dat = kmalloc(sizeof(*pkgl_dat), GFP_KERNEL | __GFP_ZERO);
+ if (!pkgl_dat) {
+ printk(KERN_ERR "sdcardfs: Failed to create hash\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ mutex_init(&pkgl_dat->hashtable_lock);
+ hash_init(pkgl_dat->package_to_appid);
+
+ return pkgl_dat;
+}
+
+static void packagelist_destroy(struct packagelist_data *pkgl_dat)
+{
+ remove_all_hashentrys(pkgl_dat);
+ printk(KERN_INFO "sdcardfs: destroyed packagelist pkgld\n");
+ kfree(pkgl_dat);
+}
+
+struct package_appid {
+ struct config_item item;
+ int add_pid;
+};
+
+static inline struct package_appid *to_package_appid(struct config_item *item)
+{
+ return item ? container_of(item, struct package_appid, item) : NULL;
+}
+
+static struct configfs_attribute package_appid_attr_add_pid = {
+ .ca_owner = THIS_MODULE,
+ .ca_name = "appid",
+ .ca_mode = S_IRUGO | S_IWUGO,
+};
+
+static struct configfs_attribute *package_appid_attrs[] = {
+ &package_appid_attr_add_pid,
+ NULL,
+};
+
+static ssize_t package_appid_attr_show(struct config_item *item,
+ struct configfs_attribute *attr,
+ char *page)
+{
+ ssize_t count;
+ count = sprintf(page, "%d\n", get_appid(pkgl_data_all, item->ci_name));
+ return count;
+}
+
+static ssize_t package_appid_attr_store(struct config_item *item,
+ struct configfs_attribute *attr,
+ const char *page, size_t count)
+{
+ struct package_appid *package_appid = to_package_appid(item);
+ unsigned long tmp;
+ char *p = (char *) page;
+ int ret;
+
+ tmp = simple_strtoul(p, &p, 10);
+ if (!p || (*p && (*p != '\n')))
+ return -EINVAL;
+
+ if (tmp > INT_MAX)
+ return -ERANGE;
+ ret = insert_str_to_int(pkgl_data_all, item->ci_name, (unsigned int)tmp);
+ package_appid->add_pid = tmp;
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static void package_appid_release(struct config_item *item)
+{
+ printk(KERN_INFO "sdcardfs: removing %s\n", item->ci_dentry->d_name.name);
+ /* item->ci_name is freed already, so we rely on the dentry */
+ remove_str_to_int(pkgl_data_all, item->ci_dentry->d_name.name);
+ kfree(to_package_appid(item));
+}
+
+static struct configfs_item_operations package_appid_item_ops = {
+ .release = package_appid_release,
+ .show_attribute = package_appid_attr_show,
+ .store_attribute = package_appid_attr_store,
+};
+
+static struct config_item_type package_appid_type = {
+ .ct_item_ops = &package_appid_item_ops,
+ .ct_attrs = package_appid_attrs,
+ .ct_owner = THIS_MODULE,
+};
+
+
+struct sdcardfs_packages {
+ struct config_group group;
+};
+
+static inline struct sdcardfs_packages *to_sdcardfs_packages(struct config_item *item)
+{
+ return item ? container_of(to_config_group(item), struct sdcardfs_packages, group) : NULL;
+}
+
+static struct config_item *sdcardfs_packages_make_item(struct config_group *group, const char *name)
+{
+ struct package_appid *package_appid;
+
+ package_appid = kzalloc(sizeof(struct package_appid), GFP_KERNEL);
+ if (!package_appid)
+ return ERR_PTR(-ENOMEM);
+
+ config_item_init_type_name(&package_appid->item, name,
+ &package_appid_type);
+
+ package_appid->add_pid = 0;
+
+ return &package_appid->item;
+}
+
+static struct configfs_attribute sdcardfs_packages_attr_description = {
+ .ca_owner = THIS_MODULE,
+ .ca_name = "packages_gid.list",
+ .ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *sdcardfs_packages_attrs[] = {
+ &sdcardfs_packages_attr_description,
+ NULL,
+};
+
+static ssize_t packages_attr_show(struct config_item *item,
+ struct configfs_attribute *attr,
+ char *page)
+{
+ struct hashtable_entry *hash_cur;
+ struct hlist_node *h_t;
+ int i;
+ int count = 0, written = 0;
+ char errormsg[] = "<truncated>\n";
+
+ mutex_lock(&pkgl_data_all->hashtable_lock);
+ hash_for_each_safe(pkgl_data_all->package_to_appid, i, h_t, hash_cur, hlist) {
+ written = scnprintf(page + count, PAGE_SIZE - sizeof(errormsg) - count, "%s %d\n", (char *)hash_cur->key, hash_cur->value);
+ if (count + written == PAGE_SIZE - sizeof(errormsg)) {
+ count += scnprintf(page + count, PAGE_SIZE - count, errormsg);
+ break;
+ }
+ count += written;
+ }
+ mutex_unlock(&pkgl_data_all->hashtable_lock);
+
+ return count;
+}
+
+static void sdcardfs_packages_release(struct config_item *item)
+{
+
+ printk(KERN_INFO "sdcardfs: destroyed something?\n");
+ kfree(to_sdcardfs_packages(item));
+}
+
+static struct configfs_item_operations sdcardfs_packages_item_ops = {
+ .release = sdcardfs_packages_release,
+ .show_attribute = packages_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations sdcardfs_packages_group_ops = {
+ .make_item = sdcardfs_packages_make_item,
+};
+
+static struct config_item_type sdcardfs_packages_type = {
+ .ct_item_ops = &sdcardfs_packages_item_ops,
+ .ct_group_ops = &sdcardfs_packages_group_ops,
+ .ct_attrs = sdcardfs_packages_attrs,
+ .ct_owner = THIS_MODULE,
+};
+
+static struct configfs_subsystem sdcardfs_packages_subsys = {
+ .su_group = {
+ .cg_item = {
+ .ci_namebuf = "sdcardfs",
+ .ci_type = &sdcardfs_packages_type,
+ },
+ },
+};
+
+static int configfs_sdcardfs_init(void)
+{
+ int ret;
+ struct configfs_subsystem *subsys = &sdcardfs_packages_subsys;
+
+ config_group_init(&subsys->su_group);
+ mutex_init(&subsys->su_mutex);
+ ret = configfs_register_subsystem(subsys);
+ if (ret) {
+ printk(KERN_ERR "Error %d while registering subsystem %s\n",
+ ret,
+ subsys->su_group.cg_item.ci_namebuf);
+ }
+ return ret;
+}
+
+static void configfs_sdcardfs_exit(void)
+{
+ configfs_unregister_subsystem(&sdcardfs_packages_subsys);
+}
+
+int packagelist_init(void)
+{
+ hashtable_entry_cachep =
+ kmem_cache_create("packagelist_hashtable_entry",
+ sizeof(struct hashtable_entry), 0, 0, NULL);
+ if (!hashtable_entry_cachep) {
+ printk(KERN_ERR "sdcardfs: failed creating pkgl_hashtable entry slab cache\n");
+ return -ENOMEM;
+ }
+
+ pkgl_data_all = packagelist_create();
+ configfs_sdcardfs_init();
+ return 0;
+}
+
+void packagelist_exit(void)
+{
+ configfs_sdcardfs_exit();
+ packagelist_destroy(pkgl_data_all);
+ if (hashtable_entry_cachep)
+ kmem_cache_destroy(hashtable_entry_cachep);
+}
diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h
new file mode 100755
index 0000000..7f3dee3
--- /dev/null
+++ b/fs/sdcardfs/sdcardfs.h
@@ -0,0 +1,530 @@
+/*
+ * fs/sdcardfs/sdcardfs.h
+ *
+ * The sdcardfs v2.0
+ * This file system replaces the sdcard daemon on Android
+ * On version 2.0, some of the daemon functions have been ported
+ * to support the multi-user concepts of Android 4.4
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#ifndef _SDCARDFS_H_
+#define _SDCARDFS_H_
+
+#include <linux/dcache.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include <linux/fs_stack.h>
+#include <linux/magic.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/security.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include "multiuser.h"
+
+/* the file system name */
+#define SDCARDFS_NAME "sdcardfs"
+
+/* sdcardfs root inode number */
+#define SDCARDFS_ROOT_INO 1
+
+/* useful for tracking code reachability */
+#define UDBG printk(KERN_DEFAULT "DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__)
+
+#define SDCARDFS_DIRENT_SIZE 256
+
+/* temporary static uid settings for development */
+#define AID_ROOT 0 /* uid for accessing /mnt/sdcard & extSdcard */
+#define AID_MEDIA_RW 1023 /* internal media storage write access */
+
+#define AID_SDCARD_RW 1015 /* external storage write access */
+#define AID_SDCARD_R 1028 /* external storage read access */
+#define AID_SDCARD_PICS 1033 /* external storage photos access */
+#define AID_SDCARD_AV 1034 /* external storage audio/video access */
+#define AID_SDCARD_ALL 1035 /* access all users external storage */
+
+#define AID_PACKAGE_INFO 1027
+
+#define fix_derived_permission(x) \
+ do { \
+ (x)->i_uid = SDCARDFS_I(x)->d_uid; \
+ (x)->i_gid = get_gid(SDCARDFS_I(x)); \
+ (x)->i_mode = ((x)->i_mode & S_IFMT) | get_mode(SDCARDFS_I(x));\
+ } while (0)
+
+
+/* OVERRIDE_CRED() and REVERT_CRED()
+ * OVERRID_CRED()
+ * backup original task->cred
+ * and modifies task->cred->fsuid/fsgid to specified value.
+ * REVERT_CRED()
+ * restore original task->cred->fsuid/fsgid.
+ * These two macro should be used in pair, and OVERRIDE_CRED() should be
+ * placed at the beginning of a function, right after variable declaration.
+ */
+#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred) \
+ saved_cred = override_fsids(sdcardfs_sbi); \
+ if (!saved_cred) { return -ENOMEM; }
+
+#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred) \
+ saved_cred = override_fsids(sdcardfs_sbi); \
+ if (!saved_cred) { return ERR_PTR(-ENOMEM); }
+
+#define REVERT_CRED(saved_cred) revert_fsids(saved_cred)
+
+#define DEBUG_CRED() \
+ printk("KAKJAGI: %s:%d fsuid %d fsgid %d\n", \
+ __FUNCTION__, __LINE__, \
+ (int)current->cred->fsuid, \
+ (int)current->cred->fsgid);
+
+/* Android 5.0 support */
+
+/* Permission mode for a specific node. Controls how file permissions
+ * are derived for children nodes. */
+typedef enum {
+ /* Nothing special; this node should just inherit from its parent. */
+ PERM_INHERIT,
+ /* This node is one level above a normal root; used for legacy layouts
+ * which use the first level to represent user_id. */
+ PERM_PRE_ROOT,
+ /* This node is "/" */
+ PERM_ROOT,
+ /* This node is "/Android" */
+ PERM_ANDROID,
+ /* This node is "/Android/data" */
+ PERM_ANDROID_DATA,
+ /* This node is "/Android/obb" */
+ PERM_ANDROID_OBB,
+ /* This node is "/Android/media" */
+ PERM_ANDROID_MEDIA,
+} perm_t;
+
+struct sdcardfs_sb_info;
+struct sdcardfs_mount_options;
+
+/* Do not directly use this function. Use OVERRIDE_CRED() instead. */
+const struct cred * override_fsids(struct sdcardfs_sb_info* sbi);
+/* Do not directly use this function, use REVERT_CRED() instead. */
+void revert_fsids(const struct cred * old_cred);
+
+/* operations vectors defined in specific files */
+extern const struct file_operations sdcardfs_main_fops;
+extern const struct file_operations sdcardfs_dir_fops;
+extern const struct inode_operations sdcardfs_main_iops;
+extern const struct inode_operations sdcardfs_dir_iops;
+extern const struct inode_operations sdcardfs_symlink_iops;
+extern const struct super_operations sdcardfs_sops;
+extern const struct dentry_operations sdcardfs_ci_dops;
+extern const struct address_space_operations sdcardfs_aops, sdcardfs_dummy_aops;
+extern const struct vm_operations_struct sdcardfs_vm_ops;
+
+extern int sdcardfs_init_inode_cache(void);
+extern void sdcardfs_destroy_inode_cache(void);
+extern int sdcardfs_init_dentry_cache(void);
+extern void sdcardfs_destroy_dentry_cache(void);
+extern int new_dentry_private_data(struct dentry *dentry);
+extern void free_dentry_private_data(struct dentry *dentry);
+extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags);
+extern struct inode *sdcardfs_iget(struct super_block *sb,
+ struct inode *lower_inode, userid_t id);
+extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb,
+ struct path *lower_path, userid_t id);
+
+/* file private data */
+struct sdcardfs_file_info {
+ struct file *lower_file;
+ const struct vm_operations_struct *lower_vm_ops;
+};
+
+/* sdcardfs inode data in memory */
+struct sdcardfs_inode_info {
+ struct inode *lower_inode;
+ /* state derived based on current position in hierachy */
+ perm_t perm;
+ userid_t userid;
+ uid_t d_uid;
+ bool under_android;
+
+ struct inode vfs_inode;
+};
+
+
+/* sdcardfs dentry data in memory */
+struct sdcardfs_dentry_info {
+ spinlock_t lock; /* protects lower_path */
+ struct path lower_path;
+ struct path orig_path;
+};
+
+struct sdcardfs_mount_options {
+ uid_t fs_low_uid;
+ gid_t fs_low_gid;
+ userid_t fs_user_id;
+ gid_t gid;
+ mode_t mask;
+ bool multiuser;
+ unsigned int reserved_mb;
+};
+
+/* sdcardfs super-block data in memory */
+struct sdcardfs_sb_info {
+ struct super_block *sb;
+ struct super_block *lower_sb;
+ /* derived perm policy : some of options have been added
+ * to sdcardfs_mount_options (Android 4.4 support) */
+ struct sdcardfs_mount_options options;
+ spinlock_t lock; /* protects obbpath */
+ char *obbpath_s;
+ struct path obbpath;
+ void *pkgl_id;
+ struct list_head list;
+};
+
+/*
+ * inode to private data
+ *
+ * Since we use containers and the struct inode is _inside_ the
+ * sdcardfs_inode_info structure, SDCARDFS_I will always (given a non-NULL
+ * inode pointer), return a valid non-NULL pointer.
+ */
+static inline struct sdcardfs_inode_info *SDCARDFS_I(const struct inode *inode)
+{
+ return container_of(inode, struct sdcardfs_inode_info, vfs_inode);
+}
+
+/* dentry to private data */
+#define SDCARDFS_D(dent) ((struct sdcardfs_dentry_info *)(dent)->d_fsdata)
+
+/* superblock to private data */
+#define SDCARDFS_SB(super) ((struct sdcardfs_sb_info *)(super)->s_fs_info)
+
+/* file to private Data */
+#define SDCARDFS_F(file) ((struct sdcardfs_file_info *)((file)->private_data))
+
+/* file to lower file */
+static inline struct file *sdcardfs_lower_file(const struct file *f)
+{
+ return SDCARDFS_F(f)->lower_file;
+}
+
+static inline void sdcardfs_set_lower_file(struct file *f, struct file *val)
+{
+ SDCARDFS_F(f)->lower_file = val;
+}
+
+/* inode to lower inode. */
+static inline struct inode *sdcardfs_lower_inode(const struct inode *i)
+{
+ return SDCARDFS_I(i)->lower_inode;
+}
+
+static inline void sdcardfs_set_lower_inode(struct inode *i, struct inode *val)
+{
+ SDCARDFS_I(i)->lower_inode = val;
+}
+
+/* superblock to lower superblock */
+static inline struct super_block *sdcardfs_lower_super(
+ const struct super_block *sb)
+{
+ return SDCARDFS_SB(sb)->lower_sb;
+}
+
+static inline void sdcardfs_set_lower_super(struct super_block *sb,
+ struct super_block *val)
+{
+ SDCARDFS_SB(sb)->lower_sb = val;
+}
+
+/* path based (dentry/mnt) macros */
+static inline void pathcpy(struct path *dst, const struct path *src)
+{
+ dst->dentry = src->dentry;
+ dst->mnt = src->mnt;
+}
+
+/* sdcardfs_get_pname functions calls path_get()
+ * therefore, the caller must call "proper" path_put functions
+ */
+#define SDCARDFS_DENT_FUNC(pname) \
+static inline void sdcardfs_get_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ pathcpy(pname, &SDCARDFS_D(dent)->pname); \
+ path_get(pname); \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_put_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ path_put(pname); \
+ return; \
+} \
+static inline void sdcardfs_set_##pname(const struct dentry *dent, \
+ struct path *pname) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ pathcpy(&SDCARDFS_D(dent)->pname, pname); \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_reset_##pname(const struct dentry *dent) \
+{ \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ SDCARDFS_D(dent)->pname.dentry = NULL; \
+ SDCARDFS_D(dent)->pname.mnt = NULL; \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+} \
+static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \
+{ \
+ struct path pname; \
+ spin_lock(&SDCARDFS_D(dent)->lock); \
+ if(SDCARDFS_D(dent)->pname.dentry) { \
+ pathcpy(&pname, &SDCARDFS_D(dent)->pname); \
+ SDCARDFS_D(dent)->pname.dentry = NULL; \
+ SDCARDFS_D(dent)->pname.mnt = NULL; \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ path_put(&pname); \
+ } else \
+ spin_unlock(&SDCARDFS_D(dent)->lock); \
+ return; \
+}
+
+SDCARDFS_DENT_FUNC(lower_path)
+SDCARDFS_DENT_FUNC(orig_path)
+
+static inline int get_gid(struct sdcardfs_inode_info *info) {
+ struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb);
+ if (sb_info->options.gid == AID_SDCARD_RW) {
+ /* As an optimization, certain trusted system components only run
+ * as owner but operate across all users. Since we're now handing
+ * out the sdcard_rw GID only to trusted apps, we're okay relaxing
+ * the user boundary enforcement for the default view. The UIDs
+ * assigned to app directories are still multiuser aware. */
+ return AID_SDCARD_RW;
+ } else {
+ return multiuser_get_uid(info->userid, sb_info->options.gid);
+ }
+}
+static inline int get_mode(struct sdcardfs_inode_info *info) {
+ int owner_mode;
+ int filtered_mode;
+ struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb);
+ int visible_mode = 0775 & ~sb_info->options.mask;
+
+ if (info->perm == PERM_PRE_ROOT) {
+ /* Top of multi-user view should always be visible to ensure
+ * secondary users can traverse inside. */
+ visible_mode = 0711;
+ } else if (info->under_android) {
+ /* Block "other" access to Android directories, since only apps
+ * belonging to a specific user should be in there; we still
+ * leave +x open for the default view. */
+ if (sb_info->options.gid == AID_SDCARD_RW) {
+ visible_mode = visible_mode & ~0006;
+ } else {
+ visible_mode = visible_mode & ~0007;
+ }
+ }
+ owner_mode = info->lower_inode->i_mode & 0700;
+ filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6));
+ return filtered_mode;
+}
+
+static inline int has_graft_path(const struct dentry *dent)
+{
+ int ret = 0;
+
+ spin_lock(&SDCARDFS_D(dent)->lock);
+ if (SDCARDFS_D(dent)->orig_path.dentry != NULL)
+ ret = 1;
+ spin_unlock(&SDCARDFS_D(dent)->lock);
+
+ return ret;
+}
+
+static inline void sdcardfs_get_real_lower(const struct dentry *dent,
+ struct path *real_lower)
+{
+ /* in case of a local obb dentry
+ * the orig_path should be returned
+ */
+ if(has_graft_path(dent))
+ sdcardfs_get_orig_path(dent, real_lower);
+ else
+ sdcardfs_get_lower_path(dent, real_lower);
+}
+
+static inline void sdcardfs_put_real_lower(const struct dentry *dent,
+ struct path *real_lower)
+{
+ if(has_graft_path(dent))
+ sdcardfs_put_orig_path(dent, real_lower);
+ else
+ sdcardfs_put_lower_path(dent, real_lower);
+}
+
+extern struct mutex sdcardfs_super_list_lock;
+extern struct list_head sdcardfs_super_list;
+
+/* for packagelist.c */
+extern appid_t get_appid(void *pkgl_id, const char *app_name);
+extern int check_caller_access_to_name(struct inode *parent_node, const char* name);
+extern int open_flags_to_access_mode(int open_flags);
+extern int packagelist_init(void);
+extern void packagelist_exit(void);
+
+/* for derived_perm.c */
+extern void setup_derived_state(struct inode *inode, perm_t perm,
+ userid_t userid, uid_t uid, bool under_android);
+extern void get_derived_permission(struct dentry *parent, struct dentry *dentry);
+extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry);
+extern void get_derive_permissions_recursive(struct dentry *parent);
+
+extern void update_derived_permission_lock(struct dentry *dentry);
+extern int need_graft_path(struct dentry *dentry);
+extern int is_base_obbpath(struct dentry *dentry);
+extern int is_obbpath_invalid(struct dentry *dentry);
+extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path);
+
+/* locking helpers */
+static inline struct dentry *lock_parent(struct dentry *dentry)
+{
+ struct dentry *dir = dget_parent(dentry);
+ mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
+ return dir;
+}
+
+static inline void unlock_dir(struct dentry *dir)
+{
+ mutex_unlock(&dir->d_inode->i_mutex);
+ dput(dir);
+}
+
+static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t mode)
+{
+ int err;
+ struct dentry *dent;
+ struct iattr attrs;
+ struct path parent;
+
+ dent = kern_path_locked(path_s, &parent);
+ if (IS_ERR(dent)) {
+ err = PTR_ERR(dent);
+ if (err == -EEXIST)
+ err = 0;
+ goto out_unlock;
+ }
+
+ err = vfs_mkdir(parent.dentry->d_inode, dent, mode);
+ if (err) {
+ if (err == -EEXIST)
+ err = 0;
+ goto out_dput;
+ }
+
+ attrs.ia_uid = uid;
+ attrs.ia_gid = gid;
+ attrs.ia_valid = ATTR_UID | ATTR_GID;
+ mutex_lock(&dent->d_inode->i_mutex);
+ notify_change(dent, &attrs);
+ mutex_unlock(&dent->d_inode->i_mutex);
+
+out_dput:
+ dput(dent);
+
+out_unlock:
+ /* parent dentry locked by lookup_create */
+ mutex_unlock(&parent.dentry->d_inode->i_mutex);
+ path_put(&parent);
+ return err;
+}
+
+/*
+ * Return 1, if a disk has enough free space, otherwise 0.
+ * We assume that any files can not be overwritten.
+ */
+static inline int check_min_free_space(struct dentry *dentry, size_t size, int dir)
+{
+ int err;
+ struct path lower_path;
+ struct kstatfs statfs;
+ u64 avail;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ if (sbi->options.reserved_mb) {
+ /* Get fs stat of lower filesystem. */
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_statfs(&lower_path, &statfs);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+
+ if (unlikely(err))
+ return 0;
+
+ /* Invalid statfs informations. */
+ if (unlikely(statfs.f_bsize == 0))
+ return 0;
+
+ /* if you are checking directory, set size to f_bsize. */
+ if (unlikely(dir))
+ size = statfs.f_bsize;
+
+ /* available size */
+ avail = statfs.f_bavail * statfs.f_bsize;
+
+ /* not enough space */
+ if ((u64)size > avail)
+ return 0;
+
+ /* enough space */
+ if ((avail - size) > (sbi->options.reserved_mb * 1024 * 1024))
+ return 1;
+
+ return 0;
+ } else
+ return 1;
+}
+
+/* Copies attrs and maintains sdcardfs managed attrs */
+static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src)
+{
+ dest->i_mode = (src->i_mode & S_IFMT) | get_mode(SDCARDFS_I(dest));
+ dest->i_uid = SDCARDFS_I(dest)->d_uid;
+ dest->i_gid = get_gid(SDCARDFS_I(dest));
+ dest->i_rdev = src->i_rdev;
+ dest->i_atime = src->i_atime;
+ dest->i_mtime = src->i_mtime;
+ dest->i_ctime = src->i_ctime;
+ dest->i_blkbits = src->i_blkbits;
+ dest->i_flags = src->i_flags;
+ set_nlink(dest, src->i_nlink);
+}
+#endif /* not _SDCARDFS_H_ */
diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c
new file mode 100755
index 0000000..1d64901
--- /dev/null
+++ b/fs/sdcardfs/super.c
@@ -0,0 +1,222 @@
+/*
+ * fs/sdcardfs/super.c
+ *
+ * Copyright (c) 2013 Samsung Electronics Co. Ltd
+ * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun,
+ * Sunghwan Yun, Sungjong Seo
+ *
+ * This program has been developed as a stackable file system based on
+ * the WrapFS which written by
+ *
+ * Copyright (c) 1998-2011 Erez Zadok
+ * Copyright (c) 2009 Shrikar Archak
+ * Copyright (c) 2003-2011 Stony Brook University
+ * Copyright (c) 2003-2011 The Research Foundation of SUNY
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#include "sdcardfs.h"
+
+/*
+ * The inode cache is used with alloc_inode for both our inode info and the
+ * vfs inode.
+ */
+static struct kmem_cache *sdcardfs_inode_cachep;
+
+/* final actions when unmounting a file system */
+static void sdcardfs_put_super(struct super_block *sb)
+{
+ struct sdcardfs_sb_info *spd;
+ struct super_block *s;
+
+ spd = SDCARDFS_SB(sb);
+ if (!spd)
+ return;
+
+ if(spd->obbpath_s) {
+ kfree(spd->obbpath_s);
+ path_put(&spd->obbpath);
+ }
+
+ /* decrement lower super references */
+ s = sdcardfs_lower_super(sb);
+ sdcardfs_set_lower_super(sb, NULL);
+ atomic_dec(&s->s_active);
+
+ kfree(spd);
+ sb->s_fs_info = NULL;
+}
+
+static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ int err;
+ struct path lower_path;
+ u32 min_blocks;
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb);
+
+ sdcardfs_get_lower_path(dentry, &lower_path);
+ err = vfs_statfs(&lower_path, buf);
+ sdcardfs_put_lower_path(dentry, &lower_path);
+
+ if (sbi->options.reserved_mb) {
+ /* Invalid statfs informations. */
+ if (buf->f_bsize == 0) {
+ printk(KERN_ERR "Returned block size is zero.\n");
+ return -EINVAL;
+ }
+
+ min_blocks = ((sbi->options.reserved_mb * 1024 * 1024)/buf->f_bsize);
+ buf->f_blocks -= min_blocks;
+
+ if (buf->f_bavail > min_blocks)
+ buf->f_bavail -= min_blocks;
+ else
+ buf->f_bavail = 0;
+
+ /* Make reserved blocks invisiable to media storage */
+ buf->f_bfree = buf->f_bavail;
+ }
+
+ /* set return buf to our f/s to avoid confusing user-level utils */
+ buf->f_type = SDCARDFS_SUPER_MAGIC;
+
+ return err;
+}
+
+/*
+ * @flags: numeric mount options
+ * @options: mount options string
+ */
+static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options)
+{
+ int err = 0;
+
+ /*
+ * The VFS will take care of "ro" and "rw" flags among others. We
+ * can safely accept a few flags (RDONLY, MANDLOCK), and honor
+ * SILENT, but anything else left over is an error.
+ */
+ if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) {
+ printk(KERN_ERR
+ "sdcardfs: remount flags 0x%x unsupported\n", *flags);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+/*
+ * Called by iput() when the inode reference count reached zero
+ * and the inode is not hashed anywhere. Used to clear anything
+ * that needs to be, before the inode is completely destroyed and put
+ * on the inode free list.
+ */
+static void sdcardfs_evict_inode(struct inode *inode)
+{
+ struct inode *lower_inode;
+
+ truncate_inode_pages(&inode->i_data, 0);
+ clear_inode(inode);
+ /*
+ * Decrement a reference to a lower_inode, which was incremented
+ * by our read_inode when it was created initially.
+ */
+ lower_inode = sdcardfs_lower_inode(inode);
+ sdcardfs_set_lower_inode(inode, NULL);
+ iput(lower_inode);
+}
+
+static struct inode *sdcardfs_alloc_inode(struct super_block *sb)
+{
+ struct sdcardfs_inode_info *i;
+
+ i = kmem_cache_alloc(sdcardfs_inode_cachep, GFP_KERNEL);
+ if (!i)
+ return NULL;
+
+ /* memset everything up to the inode to 0 */
+ memset(i, 0, offsetof(struct sdcardfs_inode_info, vfs_inode));
+
+ i->vfs_inode.i_version = 1;
+ return &i->vfs_inode;
+}
+
+static void sdcardfs_destroy_inode(struct inode *inode)
+{
+ kmem_cache_free(sdcardfs_inode_cachep, SDCARDFS_I(inode));
+}
+
+/* sdcardfs inode cache constructor */
+static void init_once(void *obj)
+{
+ struct sdcardfs_inode_info *i = obj;
+
+ inode_init_once(&i->vfs_inode);
+}
+
+int sdcardfs_init_inode_cache(void)
+{
+ int err = 0;
+
+ sdcardfs_inode_cachep =
+ kmem_cache_create("sdcardfs_inode_cache",
+ sizeof(struct sdcardfs_inode_info), 0,
+ SLAB_RECLAIM_ACCOUNT, init_once);
+ if (!sdcardfs_inode_cachep)
+ err = -ENOMEM;
+ return err;
+}
+
+/* sdcardfs inode cache destructor */
+void sdcardfs_destroy_inode_cache(void)
+{
+ if (sdcardfs_inode_cachep)
+ kmem_cache_destroy(sdcardfs_inode_cachep);
+}
+
+/*
+ * Used only in nfs, to kill any pending RPC tasks, so that subsequent
+ * code can actually succeed and won't leave tasks that need handling.
+ */
+static void sdcardfs_umount_begin(struct super_block *sb)
+{
+ struct super_block *lower_sb;
+
+ lower_sb = sdcardfs_lower_super(sb);
+ if (lower_sb && lower_sb->s_op && lower_sb->s_op->umount_begin)
+ lower_sb->s_op->umount_begin(lower_sb);
+}
+
+static int sdcardfs_show_options(struct seq_file *m, struct dentry *root)
+{
+ struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb);
+ struct sdcardfs_mount_options *opts = &sbi->options;
+
+ if (opts->fs_low_uid != 0)
+ seq_printf(m, ",uid=%u", opts->fs_low_uid);
+ if (opts->fs_low_gid != 0)
+ seq_printf(m, ",gid=%u", opts->fs_low_gid);
+
+ if (opts->multiuser)
+ seq_printf(m, ",multiuser");
+
+ if (opts->reserved_mb != 0)
+ seq_printf(m, ",reserved=%uMB", opts->reserved_mb);
+
+ return 0;
+};
+
+const struct super_operations sdcardfs_sops = {
+ .put_super = sdcardfs_put_super,
+ .statfs = sdcardfs_statfs,
+ .remount_fs = sdcardfs_remount_fs,
+ .evict_inode = sdcardfs_evict_inode,
+ .umount_begin = sdcardfs_umount_begin,
+ .show_options = sdcardfs_show_options,
+ .alloc_inode = sdcardfs_alloc_inode,
+ .destroy_inode = sdcardfs_destroy_inode,
+ .drop_inode = generic_delete_inode,
+};
diff --git a/fs/select.c b/fs/select.c
index 8c1c96c..6b14dc7 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -27,6 +27,7 @@
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
#include <linux/sched/rt.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
@@ -236,7 +237,8 @@
set_current_state(state);
if (!pwq->triggered)
- rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
+ rc = freezable_schedule_hrtimeout_range(expires, slack,
+ HRTIMER_MODE_ABS);
__set_current_state(TASK_RUNNING);
/*
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 3dd44db..d84ca59 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -8,8 +8,10 @@
#include <linux/fs.h>
#include <linux/export.h>
#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/cred.h>
+#include <linux/mm.h>
#include <asm/uaccess.h>
#include <asm/page.h>
@@ -30,6 +32,16 @@
m->count = m->size;
}
+static void *seq_buf_alloc(unsigned long size)
+{
+ void *buf;
+
+ buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+ if (!buf && size > PAGE_SIZE)
+ buf = vmalloc(size);
+ return buf;
+}
+
/**
* seq_open - initialize sequential file
* @file: file we initialize
@@ -96,7 +108,7 @@
return 0;
}
if (!m->buf) {
- m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+ m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
if (!m->buf)
return -ENOMEM;
}
@@ -135,8 +147,8 @@
Eoverflow:
m->op->stop(m, p);
- kfree(m->buf);
- m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+ kvfree(m->buf);
+ m->buf = seq_buf_alloc(m->size <<= 1);
return !m->buf ? -ENOMEM : -EAGAIN;
}
@@ -191,7 +203,7 @@
/* grab buffer if we didn't have one */
if (!m->buf) {
- m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+ m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
if (!m->buf)
goto Enomem;
}
@@ -231,8 +243,8 @@
if (m->count < m->size)
goto Fill;
m->op->stop(m, p);
- kfree(m->buf);
- m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+ kvfree(m->buf);
+ m->buf = seq_buf_alloc(m->size <<= 1);
if (!m->buf)
goto Enomem;
m->count = 0;
@@ -349,7 +361,7 @@
int seq_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
- kfree(m->buf);
+ kvfree(m->buf);
kfree(m);
return 0;
}
@@ -604,13 +616,13 @@
int single_open_size(struct file *file, int (*show)(struct seq_file *, void *),
void *data, size_t size)
{
- char *buf = kmalloc(size, GFP_KERNEL);
+ char *buf = seq_buf_alloc(size);
int ret;
if (!buf)
return -ENOMEM;
ret = single_open(file, show, data);
if (ret) {
- kfree(buf);
+ kvfree(buf);
return ret;
}
((struct seq_file *)file->private_data)->buf = buf;
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index c70111e..ffb093e 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -25,6 +25,78 @@
If unsure, say N.
+choice
+ prompt "File decompression options"
+ depends on SQUASHFS
+ help
+ Squashfs now supports two options for decompressing file
+ data. Traditionally Squashfs has decompressed into an
+ intermediate buffer and then memcopied it into the page cache.
+ Squashfs now supports the ability to decompress directly into
+ the page cache.
+
+ If unsure, select "Decompress file data into an intermediate buffer"
+
+config SQUASHFS_FILE_CACHE
+ bool "Decompress file data into an intermediate buffer"
+ help
+ Decompress file data into an intermediate buffer and then
+ memcopy it into the page cache.
+
+config SQUASHFS_FILE_DIRECT
+ bool "Decompress files directly into the page cache"
+ help
+ Directly decompress file data into the page cache.
+ Doing so can significantly improve performance because
+ it eliminates a memcpy and it also removes the lock contention
+ on the single buffer.
+
+endchoice
+
+choice
+ prompt "Decompressor parallelisation options"
+ depends on SQUASHFS
+ help
+ Squashfs now supports three parallelisation options for
+ decompression. Each one exhibits various trade-offs between
+ decompression performance and CPU and memory usage.
+
+ If in doubt, select "Single threaded compression"
+
+config SQUASHFS_DECOMP_SINGLE
+ bool "Single threaded compression"
+ help
+ Traditionally Squashfs has used single-threaded decompression.
+ Only one block (data or metadata) can be decompressed at any
+ one time. This limits CPU and memory usage to a minimum.
+
+config SQUASHFS_DECOMP_MULTI
+ bool "Use multiple decompressors for parallel I/O"
+ help
+ By default Squashfs uses a single decompressor but it gives
+ poor performance on parallel I/O workloads when using multiple CPU
+ machines due to waiting on decompressor availability.
+
+ If you have a parallel I/O workload and your system has enough memory,
+ using this option may improve overall I/O performance.
+
+ This decompressor implementation uses up to two parallel
+ decompressors per core. It dynamically allocates decompressors
+ on a demand basis.
+
+config SQUASHFS_DECOMP_MULTI_PERCPU
+ bool "Use percpu multiple decompressors for parallel I/O"
+ help
+ By default Squashfs uses a single decompressor but it gives
+ poor performance on parallel I/O workloads when using multiple CPU
+ machines due to waiting on decompressor availability.
+
+ This decompressor implementation uses a maximum of one
+ decompressor per core. It uses percpu variables to ensure
+ decompression is load-balanced across the cores.
+
+endchoice
+
config SQUASHFS_XATTR
bool "Squashfs XATTR support"
depends on SQUASHFS
@@ -48,6 +120,21 @@
If unsure, say Y.
+config SQUASHFS_LZ4
+ bool "Include support for LZ4 compressed file systems"
+ depends on SQUASHFS
+ select LZ4_DECOMPRESS
+ help
+ Saying Y here includes support for reading Squashfs file systems
+ compressed with LZ4 compression. LZ4 compression is mainly
+ aimed at embedded systems with slower CPUs where the overheads
+ of zlib are too high.
+
+ LZ4 is not the standard compression used in Squashfs and so most
+ file systems will be readable without selecting this option.
+
+ If unsure, say N.
+
config SQUASHFS_LZO
bool "Include support for LZO compressed file systems"
depends on SQUASHFS
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 110b047..246a6f3 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -5,7 +5,13 @@
obj-$(CONFIG_SQUASHFS) += squashfs.o
squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
squashfs-y += namei.o super.o symlink.o decompressor.o
+squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
+squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o
+squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o
squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o
squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index fb50652..0cea9b9 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -36,6 +36,7 @@
#include "squashfs_fs_sb.h"
#include "squashfs.h"
#include "decompressor.h"
+#include "page_actor.h"
/*
* Read the metadata block length, this is stored in the first two
@@ -86,16 +87,16 @@
* generated a larger block - this does occasionally happen with compression
* algorithms).
*/
-int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
- int length, u64 *next_index, int srclength, int pages)
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+ u64 *next_index, struct squashfs_page_actor *output)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
struct buffer_head **bh;
int offset = index & ((1 << msblk->devblksize_log2) - 1);
u64 cur_index = index >> msblk->devblksize_log2;
- int bytes, compressed, b = 0, k = 0, page = 0, avail;
+ int bytes, compressed, b = 0, k = 0, avail, i;
- bh = kcalloc(((srclength + msblk->devblksize - 1)
+ bh = kcalloc(((output->length + msblk->devblksize - 1)
>> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
if (bh == NULL)
return -ENOMEM;
@@ -111,9 +112,9 @@
*next_index = index + length;
TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
- index, compressed ? "" : "un", length, srclength);
+ index, compressed ? "" : "un", length, output->length);
- if (length < 0 || length > srclength ||
+ if (length < 0 || length > output->length ||
(index + length) > msblk->bytes_used)
goto read_failure;
@@ -145,7 +146,7 @@
TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
compressed ? "" : "un", length);
- if (length < 0 || length > srclength ||
+ if (length < 0 || length > output->length ||
(index + length) > msblk->bytes_used)
goto block_release;
@@ -158,35 +159,36 @@
ll_rw_block(READ, b - 1, bh + 1);
}
+ for (i = 0; i < b; i++) {
+ wait_on_buffer(bh[i]);
+ if (!buffer_uptodate(bh[i]))
+ goto block_release;
+ }
+
if (compressed) {
- length = squashfs_decompress(msblk, buffer, bh, b, offset,
- length, srclength, pages);
+ length = squashfs_decompress(msblk, bh, b, offset, length,
+ output);
if (length < 0)
goto read_failure;
} else {
/*
* Block is uncompressed.
*/
- int i, in, pg_offset = 0;
-
- for (i = 0; i < b; i++) {
- wait_on_buffer(bh[i]);
- if (!buffer_uptodate(bh[i]))
- goto block_release;
- }
+ int in, pg_offset = 0;
+ void *data = squashfs_first_page(output);
for (bytes = length; k < b; k++) {
in = min(bytes, msblk->devblksize - offset);
bytes -= in;
while (in) {
if (pg_offset == PAGE_CACHE_SIZE) {
- page++;
+ data = squashfs_next_page(output);
pg_offset = 0;
}
avail = min_t(int, in, PAGE_CACHE_SIZE -
pg_offset);
- memcpy(buffer[page] + pg_offset,
- bh[k]->b_data + offset, avail);
+ memcpy(data + pg_offset, bh[k]->b_data + offset,
+ avail);
in -= avail;
pg_offset += avail;
offset += avail;
@@ -194,6 +196,7 @@
offset = 0;
put_bh(bh[k]);
}
+ squashfs_finish_page(output);
}
kfree(bh);
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index af0b738..1cb70a0 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -56,6 +56,7 @@
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
#include "squashfs.h"
+#include "page_actor.h"
/*
* Look-up block in cache, and increment usage count. If not in cache, read
@@ -119,9 +120,8 @@
entry->error = 0;
spin_unlock(&cache->lock);
- entry->length = squashfs_read_data(sb, entry->data,
- block, length, &entry->next_index,
- cache->block_size, cache->pages);
+ entry->length = squashfs_read_data(sb, block, length,
+ &entry->next_index, entry->actor);
spin_lock(&cache->lock);
@@ -220,6 +220,7 @@
kfree(cache->entry[i].data[j]);
kfree(cache->entry[i].data);
}
+ kfree(cache->entry[i].actor);
}
kfree(cache->entry);
@@ -280,6 +281,13 @@
goto cleanup;
}
}
+
+ entry->actor = squashfs_page_actor_init(entry->data,
+ cache->pages, 0);
+ if (entry->actor == NULL) {
+ ERROR("Failed to allocate %s cache entry\n", name);
+ goto cleanup;
+ }
}
return cache;
@@ -410,6 +418,7 @@
int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
int i, res;
void *table, *buffer, **data;
+ struct squashfs_page_actor *actor;
table = buffer = kmalloc(length, GFP_KERNEL);
if (table == NULL)
@@ -421,19 +430,28 @@
goto failed;
}
+ actor = squashfs_page_actor_init(data, pages, length);
+ if (actor == NULL) {
+ res = -ENOMEM;
+ goto failed2;
+ }
+
for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
data[i] = buffer;
- res = squashfs_read_data(sb, data, block, length |
- SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages);
+ res = squashfs_read_data(sb, block, length |
+ SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor);
kfree(data);
+ kfree(actor);
if (res < 0)
goto failed;
return table;
+failed2:
+ kfree(data);
failed:
kfree(table);
return ERR_PTR(res);
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index 3f6271d..e9034bf 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -30,6 +30,7 @@
#include "squashfs_fs_sb.h"
#include "decompressor.h"
#include "squashfs.h"
+#include "page_actor.h"
/*
* This file (and decompressor.h) implements a decompressor framework for
@@ -37,33 +38,40 @@
*/
static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
- NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
+ NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
};
+#ifndef CONFIG_SQUASHFS_LZ4
+static const struct squashfs_decompressor squashfs_lz4_comp_ops = {
+ NULL, NULL, NULL, NULL, LZ4_COMPRESSION, "lz4", 0
+};
+#endif
+
#ifndef CONFIG_SQUASHFS_LZO
static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
- NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
+ NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
};
#endif
#ifndef CONFIG_SQUASHFS_XZ
static const struct squashfs_decompressor squashfs_xz_comp_ops = {
- NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+ NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
};
#endif
#ifndef CONFIG_SQUASHFS_ZLIB
static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
- NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
+ NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
};
#endif
static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
- NULL, NULL, NULL, 0, "unknown", 0
+ NULL, NULL, NULL, NULL, 0, "unknown", 0
};
static const struct squashfs_decompressor *decompressor[] = {
&squashfs_zlib_comp_ops,
+ &squashfs_lz4_comp_ops,
&squashfs_lzo_comp_ops,
&squashfs_xz_comp_ops,
&squashfs_lzma_unsupported_comp_ops,
@@ -83,10 +91,11 @@
}
-void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags)
+static void *get_comp_opts(struct super_block *sb, unsigned short flags)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- void *strm, *buffer = NULL;
+ void *buffer = NULL, *comp_opts;
+ struct squashfs_page_actor *actor = NULL;
int length = 0;
/*
@@ -94,23 +103,46 @@
*/
if (SQUASHFS_COMP_OPTS(flags)) {
buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
- if (buffer == NULL)
- return ERR_PTR(-ENOMEM);
+ if (buffer == NULL) {
+ comp_opts = ERR_PTR(-ENOMEM);
+ goto out;
+ }
- length = squashfs_read_data(sb, &buffer,
- sizeof(struct squashfs_super_block), 0, NULL,
- PAGE_CACHE_SIZE, 1);
+ actor = squashfs_page_actor_init(&buffer, 1, 0);
+ if (actor == NULL) {
+ comp_opts = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ length = squashfs_read_data(sb,
+ sizeof(struct squashfs_super_block), 0, NULL, actor);
if (length < 0) {
- strm = ERR_PTR(length);
- goto finished;
+ comp_opts = ERR_PTR(length);
+ goto out;
}
}
- strm = msblk->decompressor->init(msblk, buffer, length);
+ comp_opts = squashfs_comp_opts(msblk, buffer, length);
-finished:
+out:
+ kfree(actor);
kfree(buffer);
+ return comp_opts;
+}
- return strm;
+
+void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags)
+{
+ struct squashfs_sb_info *msblk = sb->s_fs_info;
+ void *stream, *comp_opts = get_comp_opts(sb, flags);
+
+ if (IS_ERR(comp_opts))
+ return comp_opts;
+
+ stream = squashfs_decompressor_create(msblk, comp_opts);
+ if (IS_ERR(stream))
+ kfree(comp_opts);
+
+ return stream;
}
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index 330073e..a25713c 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -24,34 +24,32 @@
*/
struct squashfs_decompressor {
- void *(*init)(struct squashfs_sb_info *, void *, int);
+ void *(*init)(struct squashfs_sb_info *, void *);
+ void *(*comp_opts)(struct squashfs_sb_info *, void *, int);
void (*free)(void *);
- int (*decompress)(struct squashfs_sb_info *, void **,
- struct buffer_head **, int, int, int, int, int);
+ int (*decompress)(struct squashfs_sb_info *, void *,
+ struct buffer_head **, int, int, int,
+ struct squashfs_page_actor *);
int id;
char *name;
int supported;
};
-static inline void squashfs_decompressor_free(struct squashfs_sb_info *msblk,
- void *s)
+static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk,
+ void *buff, int length)
{
- if (msblk->decompressor)
- msblk->decompressor->free(s);
-}
-
-static inline int squashfs_decompress(struct squashfs_sb_info *msblk,
- void **buffer, struct buffer_head **bh, int b, int offset, int length,
- int srclength, int pages)
-{
- return msblk->decompressor->decompress(msblk, buffer, bh, b, offset,
- length, srclength, pages);
+ return msblk->decompressor->comp_opts ?
+ msblk->decompressor->comp_opts(msblk, buff, length) : NULL;
}
#ifdef CONFIG_SQUASHFS_XZ
extern const struct squashfs_decompressor squashfs_xz_comp_ops;
#endif
+#ifdef CONFIG_SQUASHFS_LZ4
+extern const struct squashfs_decompressor squashfs_lz4_comp_ops;
+#endif
+
#ifdef CONFIG_SQUASHFS_LZO
extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
#endif
diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c
new file mode 100644
index 0000000..d6008a6
--- /dev/null
+++ b/fs/squashfs/decompressor_multi.c
@@ -0,0 +1,198 @@
+/*
+ * Copyright (c) 2013
+ * Minchan Kim <minchan@kernel.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/buffer_head.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/cpumask.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements multi-threaded decompression in the
+ * decompressor framework
+ */
+
+
+/*
+ * The reason that multiply two is that a CPU can request new I/O
+ * while it is waiting previous request.
+ */
+#define MAX_DECOMPRESSOR (num_online_cpus() * 2)
+
+
+int squashfs_max_decompressors(void)
+{
+ return MAX_DECOMPRESSOR;
+}
+
+
+struct squashfs_stream {
+ void *comp_opts;
+ struct list_head strm_list;
+ struct mutex mutex;
+ int avail_decomp;
+ wait_queue_head_t wait;
+};
+
+
+struct decomp_stream {
+ void *stream;
+ struct list_head list;
+};
+
+
+static void put_decomp_stream(struct decomp_stream *decomp_strm,
+ struct squashfs_stream *stream)
+{
+ mutex_lock(&stream->mutex);
+ list_add(&decomp_strm->list, &stream->strm_list);
+ mutex_unlock(&stream->mutex);
+ wake_up(&stream->wait);
+}
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+ void *comp_opts)
+{
+ struct squashfs_stream *stream;
+ struct decomp_stream *decomp_strm = NULL;
+ int err = -ENOMEM;
+
+ stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+ if (!stream)
+ goto out;
+
+ stream->comp_opts = comp_opts;
+ mutex_init(&stream->mutex);
+ INIT_LIST_HEAD(&stream->strm_list);
+ init_waitqueue_head(&stream->wait);
+
+ /*
+ * We should have a decompressor at least as default
+ * so if we fail to allocate new decompressor dynamically,
+ * we could always fall back to default decompressor and
+ * file system works.
+ */
+ decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL);
+ if (!decomp_strm)
+ goto out;
+
+ decomp_strm->stream = msblk->decompressor->init(msblk,
+ stream->comp_opts);
+ if (IS_ERR(decomp_strm->stream)) {
+ err = PTR_ERR(decomp_strm->stream);
+ goto out;
+ }
+
+ list_add(&decomp_strm->list, &stream->strm_list);
+ stream->avail_decomp = 1;
+ return stream;
+
+out:
+ kfree(decomp_strm);
+ kfree(stream);
+ return ERR_PTR(err);
+}
+
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+ struct squashfs_stream *stream = msblk->stream;
+ if (stream) {
+ struct decomp_stream *decomp_strm;
+
+ while (!list_empty(&stream->strm_list)) {
+ decomp_strm = list_entry(stream->strm_list.prev,
+ struct decomp_stream, list);
+ list_del(&decomp_strm->list);
+ msblk->decompressor->free(decomp_strm->stream);
+ kfree(decomp_strm);
+ stream->avail_decomp--;
+ }
+ WARN_ON(stream->avail_decomp);
+ kfree(stream->comp_opts);
+ kfree(stream);
+ }
+}
+
+
+static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk,
+ struct squashfs_stream *stream)
+{
+ struct decomp_stream *decomp_strm;
+
+ while (1) {
+ mutex_lock(&stream->mutex);
+
+ /* There is available decomp_stream */
+ if (!list_empty(&stream->strm_list)) {
+ decomp_strm = list_entry(stream->strm_list.prev,
+ struct decomp_stream, list);
+ list_del(&decomp_strm->list);
+ mutex_unlock(&stream->mutex);
+ break;
+ }
+
+ /*
+ * If there is no available decomp and already full,
+ * let's wait for releasing decomp from other users.
+ */
+ if (stream->avail_decomp >= MAX_DECOMPRESSOR)
+ goto wait;
+
+ /* Let's allocate new decomp */
+ decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL);
+ if (!decomp_strm)
+ goto wait;
+
+ decomp_strm->stream = msblk->decompressor->init(msblk,
+ stream->comp_opts);
+ if (IS_ERR(decomp_strm->stream)) {
+ kfree(decomp_strm);
+ goto wait;
+ }
+
+ stream->avail_decomp++;
+ WARN_ON(stream->avail_decomp > MAX_DECOMPRESSOR);
+
+ mutex_unlock(&stream->mutex);
+ break;
+wait:
+ /*
+ * If system memory is tough, let's for other's
+ * releasing instead of hurting VM because it could
+ * make page cache thrashing.
+ */
+ mutex_unlock(&stream->mutex);
+ wait_event(stream->wait,
+ !list_empty(&stream->strm_list));
+ }
+
+ return decomp_strm;
+}
+
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+ int b, int offset, int length, struct squashfs_page_actor *output)
+{
+ int res;
+ struct squashfs_stream *stream = msblk->stream;
+ struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream);
+ res = msblk->decompressor->decompress(msblk, decomp_stream->stream,
+ bh, b, offset, length, output);
+ put_decomp_stream(decomp_stream, stream);
+ if (res < 0)
+ ERROR("%s decompression failed, data probably corrupt\n",
+ msblk->decompressor->name);
+ return res;
+}
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
new file mode 100644
index 0000000..23a9c28
--- /dev/null
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+#include <linux/buffer_head.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements multi-threaded decompression using percpu
+ * variables, one thread per cpu core.
+ */
+
+struct squashfs_stream {
+ void *stream;
+};
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+ void *comp_opts)
+{
+ struct squashfs_stream *stream;
+ struct squashfs_stream __percpu *percpu;
+ int err, cpu;
+
+ percpu = alloc_percpu(struct squashfs_stream);
+ if (percpu == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ for_each_possible_cpu(cpu) {
+ stream = per_cpu_ptr(percpu, cpu);
+ stream->stream = msblk->decompressor->init(msblk, comp_opts);
+ if (IS_ERR(stream->stream)) {
+ err = PTR_ERR(stream->stream);
+ goto out;
+ }
+ }
+
+ kfree(comp_opts);
+ return (__force void *) percpu;
+
+out:
+ for_each_possible_cpu(cpu) {
+ stream = per_cpu_ptr(percpu, cpu);
+ if (!IS_ERR_OR_NULL(stream->stream))
+ msblk->decompressor->free(stream->stream);
+ }
+ free_percpu(percpu);
+ return ERR_PTR(err);
+}
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+ struct squashfs_stream __percpu *percpu =
+ (struct squashfs_stream __percpu *) msblk->stream;
+ struct squashfs_stream *stream;
+ int cpu;
+
+ if (msblk->stream) {
+ for_each_possible_cpu(cpu) {
+ stream = per_cpu_ptr(percpu, cpu);
+ msblk->decompressor->free(stream->stream);
+ }
+ free_percpu(percpu);
+ }
+}
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+ int b, int offset, int length, struct squashfs_page_actor *output)
+{
+ struct squashfs_stream __percpu *percpu =
+ (struct squashfs_stream __percpu *) msblk->stream;
+ struct squashfs_stream *stream = get_cpu_ptr(percpu);
+ int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+ offset, length, output);
+ put_cpu_ptr(stream);
+
+ if (res < 0)
+ ERROR("%s decompression failed, data probably corrupt\n",
+ msblk->decompressor->name);
+
+ return res;
+}
+
+int squashfs_max_decompressors(void)
+{
+ return num_possible_cpus();
+}
diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c
new file mode 100644
index 0000000..a6c7592
--- /dev/null
+++ b/fs/squashfs/decompressor_single.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/buffer_head.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements single-threaded decompression in the
+ * decompressor framework
+ */
+
+struct squashfs_stream {
+ void *stream;
+ struct mutex mutex;
+};
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+ void *comp_opts)
+{
+ struct squashfs_stream *stream;
+ int err = -ENOMEM;
+
+ stream = kmalloc(sizeof(*stream), GFP_KERNEL);
+ if (stream == NULL)
+ goto out;
+
+ stream->stream = msblk->decompressor->init(msblk, comp_opts);
+ if (IS_ERR(stream->stream)) {
+ err = PTR_ERR(stream->stream);
+ goto out;
+ }
+
+ kfree(comp_opts);
+ mutex_init(&stream->mutex);
+ return stream;
+
+out:
+ kfree(stream);
+ return ERR_PTR(err);
+}
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+ struct squashfs_stream *stream = msblk->stream;
+
+ if (stream) {
+ msblk->decompressor->free(stream->stream);
+ kfree(stream);
+ }
+}
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+ int b, int offset, int length, struct squashfs_page_actor *output)
+{
+ int res;
+ struct squashfs_stream *stream = msblk->stream;
+
+ mutex_lock(&stream->mutex);
+ res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+ offset, length, output);
+ mutex_unlock(&stream->mutex);
+
+ if (res < 0)
+ ERROR("%s decompression failed, data probably corrupt\n",
+ msblk->decompressor->name);
+
+ return res;
+}
+
+int squashfs_max_decompressors(void)
+{
+ return 1;
+}
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index 57dc70e..d8c2d74 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -54,6 +54,7 @@
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
int err, i, index, length = 0;
+ unsigned int size;
struct squashfs_dir_index dir_index;
TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n",
@@ -81,8 +82,14 @@
*/
break;
+ size = le32_to_cpu(dir_index.size) + 1;
+
+ /* size should never be larger than SQUASHFS_NAME_LEN */
+ if (size > SQUASHFS_NAME_LEN)
+ break;
+
err = squashfs_read_metadata(sb, NULL, &index_start,
- &index_offset, le32_to_cpu(dir_index.size) + 1);
+ &index_offset, size);
if (err < 0)
break;
@@ -100,14 +107,13 @@
}
-static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
+static int squashfs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
u64 block = squashfs_i(inode)->start + msblk->directory_table;
- int offset = squashfs_i(inode)->offset, length, dir_count, size,
- type, err;
- unsigned int inode_number;
+ int offset = squashfs_i(inode)->offset, length, err;
+ unsigned int inode_number, dir_count, size, type;
struct squashfs_dir_header dirh;
struct squashfs_dir_entry *dire;
@@ -127,11 +133,11 @@
* It also means that the external f_pos is offset by 3 from the
* on-disk directory f_pos.
*/
- while (file->f_pos < 3) {
+ while (ctx->pos < 3) {
char *name;
int i_ino;
- if (file->f_pos == 0) {
+ if (ctx->pos == 0) {
name = ".";
size = 1;
i_ino = inode->i_ino;
@@ -141,24 +147,18 @@
i_ino = squashfs_i(inode)->parent;
}
- TRACE("Calling filldir(%p, %s, %d, %lld, %d, %d)\n",
- dirent, name, size, file->f_pos, i_ino,
- squashfs_filetype_table[1]);
-
- if (filldir(dirent, name, size, file->f_pos, i_ino,
- squashfs_filetype_table[1]) < 0) {
- TRACE("Filldir returned less than 0\n");
+ if (!dir_emit(ctx, name, size, i_ino,
+ squashfs_filetype_table[1]))
goto finish;
- }
- file->f_pos += size;
+ ctx->pos += size;
}
length = get_dir_index_using_offset(inode->i_sb, &block, &offset,
squashfs_i(inode)->dir_idx_start,
squashfs_i(inode)->dir_idx_offset,
squashfs_i(inode)->dir_idx_cnt,
- file->f_pos);
+ ctx->pos);
while (length < i_size_read(inode)) {
/*
@@ -198,7 +198,7 @@
length += sizeof(*dire) + size;
- if (file->f_pos >= length)
+ if (ctx->pos >= length)
continue;
dire->name[size] = '\0';
@@ -206,22 +206,15 @@
((short) le16_to_cpu(dire->inode_number));
type = le16_to_cpu(dire->type);
- TRACE("Calling filldir(%p, %s, %d, %lld, %x:%x, %d, %d)"
- "\n", dirent, dire->name, size,
- file->f_pos,
- le32_to_cpu(dirh.start_block),
- le16_to_cpu(dire->offset),
- inode_number,
- squashfs_filetype_table[type]);
+ if (type > SQUASHFS_MAX_DIR_TYPE)
+ goto failed_read;
- if (filldir(dirent, dire->name, size, file->f_pos,
+ if (!dir_emit(ctx, dire->name, size,
inode_number,
- squashfs_filetype_table[type]) < 0) {
- TRACE("Filldir returned less than 0\n");
+ squashfs_filetype_table[type]))
goto finish;
- }
- file->f_pos = length;
+ ctx->pos = length;
}
}
@@ -238,6 +231,6 @@
const struct file_operations squashfs_dir_ops = {
.read = generic_read_dir,
- .readdir = squashfs_readdir,
+ .iterate = squashfs_readdir,
.llseek = default_llseek,
};
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 8ca62c2..e5c9689 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -370,77 +370,15 @@
return le32_to_cpu(size);
}
-
-static int squashfs_readpage(struct file *file, struct page *page)
+/* Copy data into page cache */
+void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
+ int bytes, int offset)
{
struct inode *inode = page->mapping->host;
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
- int bytes, i, offset = 0, sparse = 0;
- struct squashfs_cache_entry *buffer = NULL;
void *pageaddr;
-
- int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
- int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
- int start_index = page->index & ~mask;
- int end_index = start_index | mask;
- int file_end = i_size_read(inode) >> msblk->block_log;
-
- TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
- page->index, squashfs_i(inode)->start);
-
- if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT))
- goto out;
-
- if (index < file_end || squashfs_i(inode)->fragment_block ==
- SQUASHFS_INVALID_BLK) {
- /*
- * Reading a datablock from disk. Need to read block list
- * to get location and block size.
- */
- u64 block = 0;
- int bsize = read_blocklist(inode, index, &block);
- if (bsize < 0)
- goto error_out;
-
- if (bsize == 0) { /* hole */
- bytes = index == file_end ?
- (i_size_read(inode) & (msblk->block_size - 1)) :
- msblk->block_size;
- sparse = 1;
- } else {
- /*
- * Read and decompress datablock.
- */
- buffer = squashfs_get_datablock(inode->i_sb,
- block, bsize);
- if (buffer->error) {
- ERROR("Unable to read page, block %llx, size %x"
- "\n", block, bsize);
- squashfs_cache_put(buffer);
- goto error_out;
- }
- bytes = buffer->length;
- }
- } else {
- /*
- * Datablock is stored inside a fragment (tail-end packed
- * block).
- */
- buffer = squashfs_get_fragment(inode->i_sb,
- squashfs_i(inode)->fragment_block,
- squashfs_i(inode)->fragment_size);
-
- if (buffer->error) {
- ERROR("Unable to read page, block %llx, size %x\n",
- squashfs_i(inode)->fragment_block,
- squashfs_i(inode)->fragment_size);
- squashfs_cache_put(buffer);
- goto error_out;
- }
- bytes = i_size_read(inode) & (msblk->block_size - 1);
- offset = squashfs_i(inode)->fragment_offset;
- }
+ int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+ int start_index = page->index & ~mask, end_index = start_index | mask;
/*
* Loop copying datablock into pages. As the datablock likely covers
@@ -451,7 +389,7 @@
for (i = start_index; i <= end_index && bytes > 0; i++,
bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
struct page *push_page;
- int avail = sparse ? 0 : min_t(int, bytes, PAGE_CACHE_SIZE);
+ int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0;
TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail);
@@ -475,11 +413,75 @@
if (i != page->index)
page_cache_release(push_page);
}
+}
- if (!sparse)
- squashfs_cache_put(buffer);
+/* Read datablock stored packed inside a fragment (tail-end packed block) */
+static int squashfs_readpage_fragment(struct page *page)
+{
+ struct inode *inode = page->mapping->host;
+ struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+ struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb,
+ squashfs_i(inode)->fragment_block,
+ squashfs_i(inode)->fragment_size);
+ int res = buffer->error;
+ if (res)
+ ERROR("Unable to read page, block %llx, size %x\n",
+ squashfs_i(inode)->fragment_block,
+ squashfs_i(inode)->fragment_size);
+ else
+ squashfs_copy_cache(page, buffer, i_size_read(inode) &
+ (msblk->block_size - 1),
+ squashfs_i(inode)->fragment_offset);
+
+ squashfs_cache_put(buffer);
+ return res;
+}
+
+static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
+{
+ struct inode *inode = page->mapping->host;
+ struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+ int bytes = index == file_end ?
+ (i_size_read(inode) & (msblk->block_size - 1)) :
+ msblk->block_size;
+
+ squashfs_copy_cache(page, NULL, bytes, 0);
return 0;
+}
+
+static int squashfs_readpage(struct file *file, struct page *page)
+{
+ struct inode *inode = page->mapping->host;
+ struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+ int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
+ int file_end = i_size_read(inode) >> msblk->block_log;
+ int res;
+ void *pageaddr;
+
+ TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
+ page->index, squashfs_i(inode)->start);
+
+ if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT))
+ goto out;
+
+ if (index < file_end || squashfs_i(inode)->fragment_block ==
+ SQUASHFS_INVALID_BLK) {
+ u64 block = 0;
+ int bsize = read_blocklist(inode, index, &block);
+ if (bsize < 0)
+ goto error_out;
+
+ if (bsize == 0)
+ res = squashfs_readpage_sparse(page, index, file_end);
+ else
+ res = squashfs_readpage_block(page, block, bsize);
+ } else
+ res = squashfs_readpage_fragment(page);
+
+ if (!res)
+ return 0;
error_out:
SetPageError(page);
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
new file mode 100644
index 0000000..f2310d2
--- /dev/null
+++ b/fs/squashfs/file_cache.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/* Read separately compressed datablock and memcopy into page cache */
+int squashfs_readpage_block(struct page *page, u64 block, int bsize)
+{
+ struct inode *i = page->mapping->host;
+ struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+ block, bsize);
+ int res = buffer->error;
+
+ if (res)
+ ERROR("Unable to read page, block %llx, size %x\n", block,
+ bsize);
+ else
+ squashfs_copy_cache(page, buffer, buffer->length, 0);
+
+ squashfs_cache_put(buffer);
+ return res;
+}
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
new file mode 100644
index 0000000..43e7a7e
--- /dev/null
+++ b/fs/squashfs/file_direct.c
@@ -0,0 +1,176 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+#include "page_actor.h"
+
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+ int pages, struct page **page);
+
+/* Read separately compressed datablock directly into page cache */
+int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
+
+{
+ struct inode *inode = target_page->mapping->host;
+ struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+
+ int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+ int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+ int start_index = target_page->index & ~mask;
+ int end_index = start_index | mask;
+ int i, n, pages, missing_pages, bytes, res = -ENOMEM;
+ struct page **page;
+ struct squashfs_page_actor *actor;
+ void *pageaddr;
+
+ if (end_index > file_end)
+ end_index = file_end;
+
+ pages = end_index - start_index + 1;
+
+ page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL);
+ if (page == NULL)
+ return res;
+
+ /*
+ * Create a "page actor" which will kmap and kunmap the
+ * page cache pages appropriately within the decompressor
+ */
+ actor = squashfs_page_actor_init_special(page, pages, 0);
+ if (actor == NULL)
+ goto out;
+
+ /* Try to grab all the pages covered by the Squashfs block */
+ for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) {
+ page[i] = (n == target_page->index) ? target_page :
+ grab_cache_page_nowait(target_page->mapping, n);
+
+ if (page[i] == NULL) {
+ missing_pages++;
+ continue;
+ }
+
+ if (PageUptodate(page[i])) {
+ unlock_page(page[i]);
+ page_cache_release(page[i]);
+ page[i] = NULL;
+ missing_pages++;
+ }
+ }
+
+ if (missing_pages) {
+ /*
+ * Couldn't get one or more pages, this page has either
+ * been VM reclaimed, but others are still in the page cache
+ * and uptodate, or we're racing with another thread in
+ * squashfs_readpage also trying to grab them. Fall back to
+ * using an intermediate buffer.
+ */
+ res = squashfs_read_cache(target_page, block, bsize, pages,
+ page);
+ if (res < 0)
+ goto mark_errored;
+
+ goto out;
+ }
+
+ /* Decompress directly into the page cache buffers */
+ res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
+ if (res < 0)
+ goto mark_errored;
+
+ /* Last page may have trailing bytes not filled */
+ bytes = res % PAGE_CACHE_SIZE;
+ if (bytes) {
+ pageaddr = kmap_atomic(page[pages - 1]);
+ memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
+ kunmap_atomic(pageaddr);
+ }
+
+ /* Mark pages as uptodate, unlock and release */
+ for (i = 0; i < pages; i++) {
+ flush_dcache_page(page[i]);
+ SetPageUptodate(page[i]);
+ unlock_page(page[i]);
+ if (page[i] != target_page)
+ page_cache_release(page[i]);
+ }
+
+ kfree(actor);
+ kfree(page);
+
+ return 0;
+
+mark_errored:
+ /* Decompression failed, mark pages as errored. Target_page is
+ * dealt with by the caller
+ */
+ for (i = 0; i < pages; i++) {
+ if (page[i] == NULL || page[i] == target_page)
+ continue;
+ flush_dcache_page(page[i]);
+ SetPageError(page[i]);
+ unlock_page(page[i]);
+ page_cache_release(page[i]);
+ }
+
+out:
+ kfree(actor);
+ kfree(page);
+ return res;
+}
+
+
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+ int pages, struct page **page)
+{
+ struct inode *i = target_page->mapping->host;
+ struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+ block, bsize);
+ int bytes = buffer->length, res = buffer->error, n, offset = 0;
+ void *pageaddr;
+
+ if (res) {
+ ERROR("Unable to read page, block %llx, size %x\n", block,
+ bsize);
+ goto out;
+ }
+
+ for (n = 0; n < pages && bytes > 0; n++,
+ bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
+ int avail = min_t(int, bytes, PAGE_CACHE_SIZE);
+
+ if (page[n] == NULL)
+ continue;
+
+ pageaddr = kmap_atomic(page[n]);
+ squashfs_copy_data(pageaddr, buffer, offset, avail);
+ memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+ kunmap_atomic(pageaddr);
+ flush_dcache_page(page[n]);
+ SetPageUptodate(page[n]);
+ unlock_page(page[n]);
+ if (page[n] != target_page)
+ page_cache_release(page[n]);
+ }
+
+out:
+ squashfs_cache_put(buffer);
+ return res;
+}
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
new file mode 100644
index 0000000..c31e2bc
--- /dev/null
+++ b/fs/squashfs/lz4_wrapper.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright (c) 2013, 2014
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/lz4.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs.h"
+#include "decompressor.h"
+#include "page_actor.h"
+
+#define LZ4_LEGACY 1
+
+struct lz4_comp_opts {
+ __le32 version;
+ __le32 flags;
+};
+
+struct squashfs_lz4 {
+ void *input;
+ void *output;
+};
+
+
+static void *lz4_comp_opts(struct squashfs_sb_info *msblk,
+ void *buff, int len)
+{
+ struct lz4_comp_opts *comp_opts = buff;
+
+ /* LZ4 compressed filesystems always have compression options */
+ if (comp_opts == NULL || len < sizeof(*comp_opts))
+ return ERR_PTR(-EIO);
+
+ if (le32_to_cpu(comp_opts->version) != LZ4_LEGACY) {
+ /* LZ4 format currently used by the kernel is the 'legacy'
+ * format */
+ ERROR("Unknown LZ4 version\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ return NULL;
+}
+
+
+static void *lz4_init(struct squashfs_sb_info *msblk, void *buff)
+{
+ int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
+ struct squashfs_lz4 *stream;
+
+ stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+ if (stream == NULL)
+ goto failed;
+ stream->input = vmalloc(block_size);
+ if (stream->input == NULL)
+ goto failed2;
+ stream->output = vmalloc(block_size);
+ if (stream->output == NULL)
+ goto failed3;
+
+ return stream;
+
+failed3:
+ vfree(stream->input);
+failed2:
+ kfree(stream);
+failed:
+ ERROR("Failed to initialise LZ4 decompressor\n");
+ return ERR_PTR(-ENOMEM);
+}
+
+
+static void lz4_free(void *strm)
+{
+ struct squashfs_lz4 *stream = strm;
+
+ if (stream) {
+ vfree(stream->input);
+ vfree(stream->output);
+ }
+ kfree(stream);
+}
+
+
+static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
+ struct buffer_head **bh, int b, int offset, int length,
+ struct squashfs_page_actor *output)
+{
+ struct squashfs_lz4 *stream = strm;
+ void *buff = stream->input, *data;
+ int avail, i, bytes = length, res;
+ size_t dest_len = output->length;
+
+ for (i = 0; i < b; i++) {
+ avail = min(bytes, msblk->devblksize - offset);
+ memcpy(buff, bh[i]->b_data + offset, avail);
+ buff += avail;
+ bytes -= avail;
+ offset = 0;
+ put_bh(bh[i]);
+ }
+
+ res = lz4_decompress_unknownoutputsize(stream->input, length,
+ stream->output, &dest_len);
+ if (res)
+ return -EIO;
+
+ bytes = dest_len;
+ data = squashfs_first_page(output);
+ buff = stream->output;
+ while (data) {
+ if (bytes <= PAGE_CACHE_SIZE) {
+ memcpy(data, buff, bytes);
+ break;
+ }
+ memcpy(data, buff, PAGE_CACHE_SIZE);
+ buff += PAGE_CACHE_SIZE;
+ bytes -= PAGE_CACHE_SIZE;
+ data = squashfs_next_page(output);
+ }
+ squashfs_finish_page(output);
+
+ return dest_len;
+}
+
+const struct squashfs_decompressor squashfs_lz4_comp_ops = {
+ .init = lz4_init,
+ .comp_opts = lz4_comp_opts,
+ .free = lz4_free,
+ .decompress = lz4_uncompress,
+ .id = LZ4_COMPRESSION,
+ .name = "lz4",
+ .supported = 1
+};
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 00f4dfc..244b9fb 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -31,13 +31,14 @@
#include "squashfs_fs_sb.h"
#include "squashfs.h"
#include "decompressor.h"
+#include "page_actor.h"
struct squashfs_lzo {
void *input;
void *output;
};
-static void *lzo_init(struct squashfs_sb_info *msblk, void *buff, int len)
+static void *lzo_init(struct squashfs_sb_info *msblk, void *buff)
{
int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
@@ -74,22 +75,16 @@
}
-static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer,
- struct buffer_head **bh, int b, int offset, int length, int srclength,
- int pages)
+static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
+ struct buffer_head **bh, int b, int offset, int length,
+ struct squashfs_page_actor *output)
{
- struct squashfs_lzo *stream = msblk->stream;
- void *buff = stream->input;
+ struct squashfs_lzo *stream = strm;
+ void *buff = stream->input, *data;
int avail, i, bytes = length, res;
- size_t out_len = srclength;
-
- mutex_lock(&msblk->read_data_mutex);
+ size_t out_len = output->length;
for (i = 0; i < b; i++) {
- wait_on_buffer(bh[i]);
- if (!buffer_uptodate(bh[i]))
- goto block_release;
-
avail = min(bytes, msblk->devblksize - offset);
memcpy(buff, bh[i]->b_data + offset, avail);
buff += avail;
@@ -104,24 +99,24 @@
goto failed;
res = bytes = (int)out_len;
- for (i = 0, buff = stream->output; bytes && i < pages; i++) {
- avail = min_t(int, bytes, PAGE_CACHE_SIZE);
- memcpy(buffer[i], buff, avail);
- buff += avail;
- bytes -= avail;
+ data = squashfs_first_page(output);
+ buff = stream->output;
+ while (data) {
+ if (bytes <= PAGE_CACHE_SIZE) {
+ memcpy(data, buff, bytes);
+ break;
+ } else {
+ memcpy(data, buff, PAGE_CACHE_SIZE);
+ buff += PAGE_CACHE_SIZE;
+ bytes -= PAGE_CACHE_SIZE;
+ data = squashfs_next_page(output);
+ }
}
+ squashfs_finish_page(output);
- mutex_unlock(&msblk->read_data_mutex);
return res;
-block_release:
- for (; i < b; i++)
- put_bh(bh[i]);
-
failed:
- mutex_unlock(&msblk->read_data_mutex);
-
- ERROR("lzo decompression failed, data probably corrupt\n");
return -EIO;
}
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index 7834a51..67cad77 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -79,7 +79,8 @@
int len)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- int i, size, length = 0, err;
+ int i, length = 0, err;
+ unsigned int size;
struct squashfs_dir_index *index;
char *str;
@@ -103,6 +104,8 @@
size = le32_to_cpu(index->size) + 1;
+ if (size > SQUASHFS_NAME_LEN)
+ break;
err = squashfs_read_metadata(sb, index->name, &index_start,
&index_offset, size);
@@ -144,7 +147,8 @@
struct squashfs_dir_entry *dire;
u64 block = squashfs_i(dir)->start + msblk->directory_table;
int offset = squashfs_i(dir)->offset;
- int err, length, dir_count, size;
+ int err, length;
+ unsigned int dir_count, size;
TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset);
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
new file mode 100644
index 0000000..5a1c11f
--- /dev/null
+++ b/fs/squashfs/page_actor.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include "page_actor.h"
+
+/*
+ * This file contains implementations of page_actor for decompressing into
+ * an intermediate buffer, and for decompressing directly into the
+ * page cache.
+ *
+ * Calling code should avoid sleeping between calls to squashfs_first_page()
+ * and squashfs_finish_page().
+ */
+
+/* Implementation of page_actor for decompressing into intermediate buffer */
+static void *cache_first_page(struct squashfs_page_actor *actor)
+{
+ actor->next_page = 1;
+ return actor->buffer[0];
+}
+
+static void *cache_next_page(struct squashfs_page_actor *actor)
+{
+ if (actor->next_page == actor->pages)
+ return NULL;
+
+ return actor->buffer[actor->next_page++];
+}
+
+static void cache_finish_page(struct squashfs_page_actor *actor)
+{
+ /* empty */
+}
+
+struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
+ int pages, int length)
+{
+ struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+ if (actor == NULL)
+ return NULL;
+
+ actor->length = length ? : pages * PAGE_CACHE_SIZE;
+ actor->buffer = buffer;
+ actor->pages = pages;
+ actor->next_page = 0;
+ actor->squashfs_first_page = cache_first_page;
+ actor->squashfs_next_page = cache_next_page;
+ actor->squashfs_finish_page = cache_finish_page;
+ return actor;
+}
+
+/* Implementation of page_actor for decompressing directly into page cache. */
+static void *direct_first_page(struct squashfs_page_actor *actor)
+{
+ actor->next_page = 1;
+ return actor->pageaddr = kmap_atomic(actor->page[0]);
+}
+
+static void *direct_next_page(struct squashfs_page_actor *actor)
+{
+ if (actor->pageaddr)
+ kunmap_atomic(actor->pageaddr);
+
+ return actor->pageaddr = actor->next_page == actor->pages ? NULL :
+ kmap_atomic(actor->page[actor->next_page++]);
+}
+
+static void direct_finish_page(struct squashfs_page_actor *actor)
+{
+ if (actor->pageaddr)
+ kunmap_atomic(actor->pageaddr);
+}
+
+struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
+ int pages, int length)
+{
+ struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+ if (actor == NULL)
+ return NULL;
+
+ actor->length = length ? : pages * PAGE_CACHE_SIZE;
+ actor->page = page;
+ actor->pages = pages;
+ actor->next_page = 0;
+ actor->pageaddr = NULL;
+ actor->squashfs_first_page = direct_first_page;
+ actor->squashfs_next_page = direct_next_page;
+ actor->squashfs_finish_page = direct_finish_page;
+ return actor;
+}
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
new file mode 100644
index 0000000..26dd820
--- /dev/null
+++ b/fs/squashfs/page_actor.h
@@ -0,0 +1,81 @@
+#ifndef PAGE_ACTOR_H
+#define PAGE_ACTOR_H
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef CONFIG_SQUASHFS_FILE_DIRECT
+struct squashfs_page_actor {
+ void **page;
+ int pages;
+ int length;
+ int next_page;
+};
+
+static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
+ int pages, int length)
+{
+ struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+ if (actor == NULL)
+ return NULL;
+
+ actor->length = length ? : pages * PAGE_CACHE_SIZE;
+ actor->page = page;
+ actor->pages = pages;
+ actor->next_page = 0;
+ return actor;
+}
+
+static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
+{
+ actor->next_page = 1;
+ return actor->page[0];
+}
+
+static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
+{
+ return actor->next_page == actor->pages ? NULL :
+ actor->page[actor->next_page++];
+}
+
+static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
+{
+ /* empty */
+}
+#else
+struct squashfs_page_actor {
+ union {
+ void **buffer;
+ struct page **page;
+ };
+ void *pageaddr;
+ void *(*squashfs_first_page)(struct squashfs_page_actor *);
+ void *(*squashfs_next_page)(struct squashfs_page_actor *);
+ void (*squashfs_finish_page)(struct squashfs_page_actor *);
+ int pages;
+ int length;
+ int next_page;
+};
+
+extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int);
+extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page
+ **, int, int);
+static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
+{
+ return actor->squashfs_first_page(actor);
+}
+static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
+{
+ return actor->squashfs_next_page(actor);
+}
+static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
+{
+ actor->squashfs_finish_page(actor);
+}
+#endif
+#endif
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index d126651..887d6d2 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -25,11 +25,11 @@
#define ERROR(s, args...) pr_err("SQUASHFS error: "s, ## args)
-#define WARNING(s, args...) pr_warning("SQUASHFS: "s, ## args)
+#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args)
/* block.c */
-extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *,
- int, int);
+extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
+ struct squashfs_page_actor *);
/* cache.c */
extern struct squashfs_cache *squashfs_cache_init(char *, int, int);
@@ -48,7 +48,14 @@
/* decompressor.c */
extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int);
-extern void *squashfs_decompressor_init(struct super_block *, unsigned short);
+extern void *squashfs_decompressor_setup(struct super_block *, unsigned short);
+
+/* decompressor_xxx.c */
+extern void *squashfs_decompressor_create(struct squashfs_sb_info *, void *);
+extern void squashfs_decompressor_destroy(struct squashfs_sb_info *);
+extern int squashfs_decompress(struct squashfs_sb_info *, struct buffer_head **,
+ int, int, int, struct squashfs_page_actor *);
+extern int squashfs_max_decompressors(void);
/* export.c */
extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64, u64,
@@ -59,6 +66,13 @@
extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
u64, u64, unsigned int);
+/* file.c */
+void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
+ int);
+
+/* file_xxx.c */
+extern int squashfs_readpage_block(struct page *, u64, int);
+
/* id.c */
extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
extern __le64 *squashfs_read_id_index_table(struct super_block *, u64, u64,
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 9e2349d..506f4ba 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -87,7 +87,7 @@
#define SQUASHFS_COMP_OPTS(flags) SQUASHFS_BIT(flags, \
SQUASHFS_COMP_OPT)
-/* Max number of types and file types */
+/* Inode types including extended types */
#define SQUASHFS_DIR_TYPE 1
#define SQUASHFS_REG_TYPE 2
#define SQUASHFS_SYMLINK_TYPE 3
@@ -103,6 +103,9 @@
#define SQUASHFS_LFIFO_TYPE 13
#define SQUASHFS_LSOCKET_TYPE 14
+/* Max type value stored in directory entry */
+#define SQUASHFS_MAX_DIR_TYPE 7
+
/* Xattr types */
#define SQUASHFS_XATTR_USER 0
#define SQUASHFS_XATTR_TRUSTED 1
@@ -237,6 +240,7 @@
#define LZMA_COMPRESSION 2
#define LZO_COMPRESSION 3
#define XZ_COMPRESSION 4
+#define LZ4_COMPRESSION 5
struct squashfs_super_block {
__le32 s_magic;
diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h
index 52934a2..1da565c 100644
--- a/fs/squashfs/squashfs_fs_sb.h
+++ b/fs/squashfs/squashfs_fs_sb.h
@@ -50,6 +50,7 @@
wait_queue_head_t wait_queue;
struct squashfs_cache *cache;
void **data;
+ struct squashfs_page_actor *actor;
};
struct squashfs_sb_info {
@@ -63,10 +64,9 @@
__le64 *id_table;
__le64 *fragment_index;
__le64 *xattr_id_table;
- struct mutex read_data_mutex;
struct mutex meta_index_mutex;
struct meta_index *meta_index;
- void *stream;
+ struct squashfs_stream *stream;
__le64 *inode_lookup_table;
u64 inode_table;
u64 directory_table;
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 60553a9..5056bab 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -27,6 +27,8 @@
* the filesystem.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/slab.h>
@@ -98,7 +100,6 @@
msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
msblk->devblksize_log2 = ffz(~msblk->devblksize);
- mutex_init(&msblk->read_data_mutex);
mutex_init(&msblk->meta_index_mutex);
/*
@@ -206,13 +207,14 @@
goto failed_mount;
/* Allocate read_page block */
- msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size);
+ msblk->read_page = squashfs_cache_init("data",
+ squashfs_max_decompressors(), msblk->block_size);
if (msblk->read_page == NULL) {
ERROR("Failed to allocate read_page block\n");
goto failed_mount;
}
- msblk->stream = squashfs_decompressor_init(sb, flags);
+ msblk->stream = squashfs_decompressor_setup(sb, flags);
if (IS_ERR(msblk->stream)) {
err = PTR_ERR(msblk->stream);
msblk->stream = NULL;
@@ -336,7 +338,7 @@
squashfs_cache_delete(msblk->block_cache);
squashfs_cache_delete(msblk->fragment_cache);
squashfs_cache_delete(msblk->read_page);
- squashfs_decompressor_free(msblk, msblk->stream);
+ squashfs_decompressor_destroy(msblk);
kfree(msblk->inode_lookup_table);
kfree(msblk->fragment_index);
kfree(msblk->id_table);
@@ -371,6 +373,7 @@
static int squashfs_remount(struct super_block *sb, int *flags, char *data)
{
+ sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
@@ -383,7 +386,7 @@
squashfs_cache_delete(sbi->block_cache);
squashfs_cache_delete(sbi->fragment_cache);
squashfs_cache_delete(sbi->read_page);
- squashfs_decompressor_free(sbi, sbi->stream);
+ squashfs_decompressor_destroy(sbi);
kfree(sbi->id_table);
kfree(sbi->fragment_index);
kfree(sbi->meta_index);
@@ -447,8 +450,7 @@
return err;
}
- printk(KERN_INFO "squashfs: version 4.0 (2009/01/31) "
- "Phillip Lougher\n");
+ pr_info("version 4.0 (2009/01/31) Phillip Lougher\n");
return 0;
}
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 1760b7d1..c609624 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -32,44 +32,70 @@
#include "squashfs_fs_sb.h"
#include "squashfs.h"
#include "decompressor.h"
+#include "page_actor.h"
struct squashfs_xz {
struct xz_dec *state;
struct xz_buf buf;
};
-struct comp_opts {
+struct disk_comp_opts {
__le32 dictionary_size;
__le32 flags;
};
-static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff,
- int len)
+struct comp_opts {
+ int dict_size;
+};
+
+static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk,
+ void *buff, int len)
{
- struct comp_opts *comp_opts = buff;
- struct squashfs_xz *stream;
- int dict_size = msblk->block_size;
- int err, n;
+ struct disk_comp_opts *comp_opts = buff;
+ struct comp_opts *opts;
+ int err = 0, n;
+
+ opts = kmalloc(sizeof(*opts), GFP_KERNEL);
+ if (opts == NULL) {
+ err = -ENOMEM;
+ goto out2;
+ }
if (comp_opts) {
/* check compressor options are the expected length */
if (len < sizeof(*comp_opts)) {
err = -EIO;
- goto failed;
+ goto out;
}
- dict_size = le32_to_cpu(comp_opts->dictionary_size);
+ opts->dict_size = le32_to_cpu(comp_opts->dictionary_size);
/* the dictionary size should be 2^n or 2^n+2^(n+1) */
- n = ffs(dict_size) - 1;
- if (dict_size != (1 << n) && dict_size != (1 << n) +
+ n = ffs(opts->dict_size) - 1;
+ if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) +
(1 << (n + 1))) {
err = -EIO;
- goto failed;
+ goto out;
}
- }
+ } else
+ /* use defaults */
+ opts->dict_size = max_t(int, msblk->block_size,
+ SQUASHFS_METADATA_SIZE);
- dict_size = max_t(int, dict_size, SQUASHFS_METADATA_SIZE);
+ return opts;
+
+out:
+ kfree(opts);
+out2:
+ return ERR_PTR(err);
+}
+
+
+static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff)
+{
+ struct comp_opts *comp_opts = buff;
+ struct squashfs_xz *stream;
+ int err;
stream = kmalloc(sizeof(*stream), GFP_KERNEL);
if (stream == NULL) {
@@ -77,7 +103,7 @@
goto failed;
}
- stream->state = xz_dec_init(XZ_PREALLOC, dict_size);
+ stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size);
if (stream->state == NULL) {
kfree(stream);
err = -ENOMEM;
@@ -103,42 +129,37 @@
}
-static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer,
- struct buffer_head **bh, int b, int offset, int length, int srclength,
- int pages)
+static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
+ struct buffer_head **bh, int b, int offset, int length,
+ struct squashfs_page_actor *output)
{
enum xz_ret xz_err;
- int avail, total = 0, k = 0, page = 0;
- struct squashfs_xz *stream = msblk->stream;
-
- mutex_lock(&msblk->read_data_mutex);
+ int avail, total = 0, k = 0;
+ struct squashfs_xz *stream = strm;
xz_dec_reset(stream->state);
stream->buf.in_pos = 0;
stream->buf.in_size = 0;
stream->buf.out_pos = 0;
stream->buf.out_size = PAGE_CACHE_SIZE;
- stream->buf.out = buffer[page++];
+ stream->buf.out = squashfs_first_page(output);
do {
if (stream->buf.in_pos == stream->buf.in_size && k < b) {
avail = min(length, msblk->devblksize - offset);
length -= avail;
- wait_on_buffer(bh[k]);
- if (!buffer_uptodate(bh[k]))
- goto release_mutex;
-
stream->buf.in = bh[k]->b_data + offset;
stream->buf.in_size = avail;
stream->buf.in_pos = 0;
offset = 0;
}
- if (stream->buf.out_pos == stream->buf.out_size
- && page < pages) {
- stream->buf.out = buffer[page++];
- stream->buf.out_pos = 0;
- total += PAGE_CACHE_SIZE;
+ if (stream->buf.out_pos == stream->buf.out_size) {
+ stream->buf.out = squashfs_next_page(output);
+ if (stream->buf.out != NULL) {
+ stream->buf.out_pos = 0;
+ total += PAGE_CACHE_SIZE;
+ }
}
xz_err = xz_dec_run(stream->state, &stream->buf);
@@ -147,23 +168,14 @@
put_bh(bh[k++]);
} while (xz_err == XZ_OK);
- if (xz_err != XZ_STREAM_END) {
- ERROR("xz_dec_run error, data probably corrupt\n");
- goto release_mutex;
- }
+ squashfs_finish_page(output);
- if (k < b) {
- ERROR("xz_uncompress error, input remaining\n");
- goto release_mutex;
- }
+ if (xz_err != XZ_STREAM_END || k < b)
+ goto out;
- total += stream->buf.out_pos;
- mutex_unlock(&msblk->read_data_mutex);
- return total;
+ return total + stream->buf.out_pos;
-release_mutex:
- mutex_unlock(&msblk->read_data_mutex);
-
+out:
for (; k < b; k++)
put_bh(bh[k]);
@@ -172,6 +184,7 @@
const struct squashfs_decompressor squashfs_xz_comp_ops = {
.init = squashfs_xz_init,
+ .comp_opts = squashfs_xz_comp_opts,
.free = squashfs_xz_free,
.decompress = squashfs_xz_uncompress,
.id = XZ_COMPRESSION,
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 55d918f..8727cab 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -32,8 +32,9 @@
#include "squashfs_fs_sb.h"
#include "squashfs.h"
#include "decompressor.h"
+#include "page_actor.h"
-static void *zlib_init(struct squashfs_sb_info *dummy, void *buff, int len)
+static void *zlib_init(struct squashfs_sb_info *dummy, void *buff)
{
z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL);
if (stream == NULL)
@@ -61,44 +62,37 @@
}
-static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
- struct buffer_head **bh, int b, int offset, int length, int srclength,
- int pages)
+static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
+ struct buffer_head **bh, int b, int offset, int length,
+ struct squashfs_page_actor *output)
{
- int zlib_err, zlib_init = 0;
- int k = 0, page = 0;
- z_stream *stream = msblk->stream;
+ int zlib_err, zlib_init = 0, k = 0;
+ z_stream *stream = strm;
- mutex_lock(&msblk->read_data_mutex);
-
- stream->avail_out = 0;
+ stream->avail_out = PAGE_CACHE_SIZE;
+ stream->next_out = squashfs_first_page(output);
stream->avail_in = 0;
do {
if (stream->avail_in == 0 && k < b) {
int avail = min(length, msblk->devblksize - offset);
length -= avail;
- wait_on_buffer(bh[k]);
- if (!buffer_uptodate(bh[k]))
- goto release_mutex;
-
stream->next_in = bh[k]->b_data + offset;
stream->avail_in = avail;
offset = 0;
}
- if (stream->avail_out == 0 && page < pages) {
- stream->next_out = buffer[page++];
- stream->avail_out = PAGE_CACHE_SIZE;
+ if (stream->avail_out == 0) {
+ stream->next_out = squashfs_next_page(output);
+ if (stream->next_out != NULL)
+ stream->avail_out = PAGE_CACHE_SIZE;
}
if (!zlib_init) {
zlib_err = zlib_inflateInit(stream);
if (zlib_err != Z_OK) {
- ERROR("zlib_inflateInit returned unexpected "
- "result 0x%x, srclength %d\n",
- zlib_err, srclength);
- goto release_mutex;
+ squashfs_finish_page(output);
+ goto out;
}
zlib_init = 1;
}
@@ -109,29 +103,21 @@
put_bh(bh[k++]);
} while (zlib_err == Z_OK);
- if (zlib_err != Z_STREAM_END) {
- ERROR("zlib_inflate error, data probably corrupt\n");
- goto release_mutex;
- }
+ squashfs_finish_page(output);
+
+ if (zlib_err != Z_STREAM_END)
+ goto out;
zlib_err = zlib_inflateEnd(stream);
- if (zlib_err != Z_OK) {
- ERROR("zlib_inflate error, data probably corrupt\n");
- goto release_mutex;
- }
+ if (zlib_err != Z_OK)
+ goto out;
- if (k < b) {
- ERROR("zlib_uncompress error, data remaining\n");
- goto release_mutex;
- }
+ if (k < b)
+ goto out;
- length = stream->total_out;
- mutex_unlock(&msblk->read_data_mutex);
- return length;
+ return stream->total_out;
-release_mutex:
- mutex_unlock(&msblk->read_data_mutex);
-
+out:
for (; k < b; k++)
put_bh(bh[k]);
diff --git a/fs/super.c b/fs/super.c
index 97280e7..05358d7 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -154,15 +154,22 @@
static const struct super_operations default_op;
if (s) {
- if (security_sb_alloc(s)) {
- /*
- * We cannot call security_sb_free() without
- * security_sb_alloc() succeeding. So bail out manually
- */
- kfree(s);
- s = NULL;
- goto out;
+ if (security_sb_alloc(s))
+ goto out_free_sb;
+
+#ifdef CONFIG_SMP
+ s->s_files = alloc_percpu(struct list_head);
+ if (!s->s_files)
+ goto err_out;
+ else {
+ int i;
+
+ for_each_possible_cpu(i)
+ INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i));
}
+#else
+ INIT_LIST_HEAD(&s->s_files);
+#endif
if (init_sb_writers(s, type))
goto err_out;
s->s_flags = flags;
@@ -212,7 +219,12 @@
return s;
err_out:
security_sb_free(s);
+#ifdef CONFIG_SMP
+ if (s->s_files)
+ free_percpu(s->s_files);
+#endif
destroy_sb_writers(s);
+out_free_sb:
kfree(s);
s = NULL;
goto out;
@@ -226,6 +238,9 @@
*/
static inline void destroy_super(struct super_block *s)
{
+#ifdef CONFIG_SMP
+ free_percpu(s->s_files);
+#endif
destroy_sb_writers(s);
security_sb_free(s);
WARN_ON(!list_empty(&s->s_mounts));
@@ -396,6 +411,11 @@
evict_inodes(sb);
+ if (sb->s_dio_done_wq) {
+ destroy_workqueue(sb->s_dio_done_wq);
+ sb->s_dio_done_wq = NULL;
+ }
+
if (sop->put_super)
sop->put_super(sb);
@@ -707,8 +727,7 @@
make sure there are no rw files opened */
if (remount_ro) {
if (force) {
- sb->s_readonly_remount = 1;
- smp_wmb();
+ mark_files_ro(sb);
} else {
retval = sb_prepare_remount_readonly(sb);
if (retval)
@@ -753,7 +772,7 @@
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
- list_for_each_entry(sb, &super_blocks, s_list) {
+ list_for_each_entry_reverse(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
sb->s_count++;
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 7b3792e..2829b66 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -60,6 +60,7 @@
{
struct sysv_sb_info *sbi = SYSV_SB(sb);
+ sync_filesystem(sb);
if (sbi->s_forced_ro)
*flags |= MS_RDONLY;
return 0;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 32b644f..0013142 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -8,6 +8,7 @@
*
*/
+#include <linux/alarmtimer.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
@@ -26,7 +27,10 @@
#include <linux/rcupdate.h>
struct timerfd_ctx {
- struct hrtimer tmr;
+ union {
+ struct hrtimer tmr;
+ struct alarm alarm;
+ } t;
ktime_t tintv;
ktime_t moffs;
wait_queue_head_t wqh;
@@ -41,14 +45,19 @@
static LIST_HEAD(cancel_list);
static DEFINE_SPINLOCK(cancel_lock);
+static inline bool isalarm(struct timerfd_ctx *ctx)
+{
+ return ctx->clockid == CLOCK_REALTIME_ALARM ||
+ ctx->clockid == CLOCK_BOOTTIME_ALARM;
+}
+
/*
* This gets called when the timer event triggers. We set the "expired"
* flag, but we do not re-arm the timer (in case it's necessary,
* tintv.tv64 != 0) until the timer is accessed.
*/
-static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+static void timerfd_triggered(struct timerfd_ctx *ctx)
{
- struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
unsigned long flags;
spin_lock_irqsave(&ctx->wqh.lock, flags);
@@ -56,10 +65,25 @@
ctx->ticks++;
wake_up_locked(&ctx->wqh);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+}
+static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+{
+ struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx,
+ t.tmr);
+ timerfd_triggered(ctx);
return HRTIMER_NORESTART;
}
+static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm,
+ ktime_t now)
+{
+ struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx,
+ t.alarm);
+ timerfd_triggered(ctx);
+ return ALARMTIMER_NORESTART;
+}
+
/*
* Called when the clock was set to cancel the timers in the cancel
* list. This will wake up processes waiting on these timers. The
@@ -107,8 +131,9 @@
static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
{
- if (ctx->clockid == CLOCK_REALTIME && (flags & TFD_TIMER_ABSTIME) &&
- (flags & TFD_TIMER_CANCEL_ON_SET)) {
+ if ((ctx->clockid == CLOCK_REALTIME ||
+ ctx->clockid == CLOCK_REALTIME_ALARM) &&
+ (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
if (!ctx->might_cancel) {
ctx->might_cancel = true;
spin_lock(&cancel_lock);
@@ -124,7 +149,11 @@
{
ktime_t remaining;
- remaining = hrtimer_expires_remaining(&ctx->tmr);
+ if (isalarm(ctx))
+ remaining = alarm_expires_remaining(&ctx->t.alarm);
+ else
+ remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+
return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
}
@@ -142,11 +171,28 @@
ctx->expired = 0;
ctx->ticks = 0;
ctx->tintv = timespec_to_ktime(ktmr->it_interval);
- hrtimer_init(&ctx->tmr, clockid, htmode);
- hrtimer_set_expires(&ctx->tmr, texp);
- ctx->tmr.function = timerfd_tmrproc;
+
+ if (isalarm(ctx)) {
+ alarm_init(&ctx->t.alarm,
+ ctx->clockid == CLOCK_REALTIME_ALARM ?
+ ALARM_REALTIME : ALARM_BOOTTIME,
+ timerfd_alarmproc);
+ } else {
+ hrtimer_init(&ctx->t.tmr, clockid, htmode);
+ hrtimer_set_expires(&ctx->t.tmr, texp);
+ ctx->t.tmr.function = timerfd_tmrproc;
+ }
+
if (texp.tv64 != 0) {
- hrtimer_start(&ctx->tmr, texp, htmode);
+ if (isalarm(ctx)) {
+ if (flags & TFD_TIMER_ABSTIME)
+ alarm_start(&ctx->t.alarm, texp);
+ else
+ alarm_start_relative(&ctx->t.alarm, texp);
+ } else {
+ hrtimer_start(&ctx->t.tmr, texp, htmode);
+ }
+
if (timerfd_canceled(ctx))
return -ECANCELED;
}
@@ -158,7 +204,11 @@
struct timerfd_ctx *ctx = file->private_data;
timerfd_remove_cancel(ctx);
- hrtimer_cancel(&ctx->tmr);
+
+ if (isalarm(ctx))
+ alarm_cancel(&ctx->t.alarm);
+ else
+ hrtimer_cancel(&ctx->t.tmr);
kfree_rcu(ctx, rcu);
return 0;
}
@@ -215,9 +265,15 @@
* callback to avoid DoS attacks specifying a very
* short timer period.
*/
- ticks += hrtimer_forward_now(&ctx->tmr,
- ctx->tintv) - 1;
- hrtimer_restart(&ctx->tmr);
+ if (isalarm(ctx)) {
+ ticks += alarm_forward_now(
+ &ctx->t.alarm, ctx->tintv) - 1;
+ alarm_restart(&ctx->t.alarm);
+ } else {
+ ticks += hrtimer_forward_now(&ctx->t.tmr,
+ ctx->tintv) - 1;
+ hrtimer_restart(&ctx->t.tmr);
+ }
}
ctx->expired = 0;
ctx->ticks = 0;
@@ -259,7 +315,10 @@
if ((flags & ~TFD_CREATE_FLAGS) ||
(clockid != CLOCK_MONOTONIC &&
- clockid != CLOCK_REALTIME))
+ clockid != CLOCK_REALTIME &&
+ clockid != CLOCK_REALTIME_ALARM &&
+ clockid != CLOCK_BOOTTIME &&
+ clockid != CLOCK_BOOTTIME_ALARM))
return -EINVAL;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -268,7 +327,15 @@
init_waitqueue_head(&ctx->wqh);
ctx->clockid = clockid;
- hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
+
+ if (isalarm(ctx))
+ alarm_init(&ctx->t.alarm,
+ ctx->clockid == CLOCK_REALTIME_ALARM ?
+ ALARM_REALTIME : ALARM_BOOTTIME,
+ timerfd_alarmproc);
+ else
+ hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS);
+
ctx->moffs = ktime_get_monotonic_offset();
ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
@@ -305,8 +372,14 @@
*/
for (;;) {
spin_lock_irq(&ctx->wqh.lock);
- if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
- break;
+
+ if (isalarm(ctx)) {
+ if (alarm_try_to_cancel(&ctx->t.alarm) >= 0)
+ break;
+ } else {
+ if (hrtimer_try_to_cancel(&ctx->t.tmr) >= 0)
+ break;
+ }
spin_unlock_irq(&ctx->wqh.lock);
cpu_relax();
}
@@ -317,8 +390,12 @@
* We do not update "ticks" and "expired" since the timer will be
* re-programmed again in the following timerfd_setup() call.
*/
- if (ctx->expired && ctx->tintv.tv64)
- hrtimer_forward_now(&ctx->tmr, ctx->tintv);
+ if (ctx->expired && ctx->tintv.tv64) {
+ if (isalarm(ctx))
+ alarm_forward_now(&ctx->t.alarm, ctx->tintv);
+ else
+ hrtimer_forward_now(&ctx->t.tmr, ctx->tintv);
+ }
old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
old->it_interval = ktime_to_timespec(ctx->tintv);
@@ -345,9 +422,18 @@
spin_lock_irq(&ctx->wqh.lock);
if (ctx->expired && ctx->tintv.tv64) {
ctx->expired = 0;
- ctx->ticks +=
- hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1;
- hrtimer_restart(&ctx->tmr);
+
+ if (isalarm(ctx)) {
+ ctx->ticks +=
+ alarm_forward_now(
+ &ctx->t.alarm, ctx->tintv) - 1;
+ alarm_restart(&ctx->t.alarm);
+ } else {
+ ctx->ticks +=
+ hrtimer_forward_now(&ctx->t.tmr, ctx->tintv)
+ - 1;
+ hrtimer_restart(&ctx->t.tmr);
+ }
}
t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
t->it_interval = ktime_to_timespec(ctx->tintv);
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index a335e4e..2c3aa9d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1278,13 +1278,14 @@
return err;
}
-static void ubifs_invalidatepage(struct page *page, unsigned long offset)
+static void ubifs_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
struct ubifs_info *c = inode->i_sb->s_fs_info;
ubifs_assert(PagePrivate(page));
- if (offset)
+ if (offset || length < PAGE_CACHE_SIZE)
/* Partial page remains dirty */
return;
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 05115d7..3bf098a 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1840,6 +1840,7 @@
int err;
struct ubifs_info *c = sb->s_fs_info;
+ sync_filesystem(sb);
dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags);
err = ubifs_parse_options(c, data, 1);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 839a2ba..32f5297 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -629,6 +629,7 @@
struct udf_options uopt;
struct udf_sb_info *sbi = UDF_SB(sb);
int error = 0;
+ sync_filesystem(sb);
if (sbi->s_lvid_bh) {
int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 329f2f5..b8c6791 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1280,6 +1280,7 @@
unsigned new_mount_opt, ufstype;
unsigned flags;
+ sync_filesystem(sb);
lock_ufs(sb);
mutex_lock(&UFS_SB(sb)->s_lock);
uspi = UFS_SB(sb)->s_uspi;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index cfbb4c1..923996c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -86,14 +86,6 @@
bh->b_end_io(bh, !ioend->io_error);
}
- if (ioend->io_iocb) {
- inode_dio_done(ioend->io_inode);
- if (ioend->io_isasync) {
- aio_complete(ioend->io_iocb, ioend->io_error ?
- ioend->io_error : ioend->io_result, 0);
- }
- }
-
mempool_free(ioend, xfs_ioend_pool);
}
@@ -281,7 +273,6 @@
* all the I/O from calling the completion routine too early.
*/
atomic_set(&ioend->io_remaining, 1);
- ioend->io_isasync = 0;
ioend->io_isdirect = 0;
ioend->io_error = 0;
ioend->io_list = NULL;
@@ -291,8 +282,6 @@
ioend->io_buffer_tail = NULL;
ioend->io_offset = 0;
ioend->io_size = 0;
- ioend->io_iocb = NULL;
- ioend->io_result = 0;
ioend->io_append_trans = NULL;
INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -843,10 +832,11 @@
STATIC void
xfs_vm_invalidatepage(
struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
trace_xfs_invalidatepage(page->mapping->host, page, offset);
- block_invalidatepage(page, offset);
+ block_invalidatepage(page, offset, PAGE_CACHE_SIZE - offset);
}
/*
@@ -910,7 +900,7 @@
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_invalidate:
- xfs_vm_invalidatepage(page, 0);
+ xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE);
return;
}
@@ -1290,8 +1280,10 @@
if (create || !ISUNWRITTEN(&imap))
xfs_map_buffer(inode, bh_result, &imap, offset);
if (create && ISUNWRITTEN(&imap)) {
- if (direct)
+ if (direct) {
bh_result->b_private = inode;
+ set_buffer_defer_completion(bh_result);
+ }
set_buffer_unwritten(bh_result);
}
}
@@ -1388,9 +1380,7 @@
struct kiocb *iocb,
loff_t offset,
ssize_t size,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct xfs_ioend *ioend = iocb->private;
@@ -1412,17 +1402,10 @@
ioend->io_offset = offset;
ioend->io_size = size;
- ioend->io_iocb = iocb;
- ioend->io_result = ret;
if (private && size > 0)
ioend->io_type = XFS_IO_UNWRITTEN;
- if (is_async) {
- ioend->io_isasync = 1;
- xfs_finish_ioend(ioend);
- } else {
- xfs_finish_ioend_sync(ioend);
- }
+ xfs_finish_ioend_sync(ioend);
}
STATIC ssize_t
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index c325abb..f94dd45 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -45,7 +45,6 @@
unsigned int io_type; /* delalloc / unwritten */
int io_error; /* I/O error code */
atomic_t io_remaining; /* hold count */
- unsigned int io_isasync : 1; /* needs aio_complete */
unsigned int io_isdirect : 1;/* direct I/O */
struct inode *io_inode; /* file being written to */
struct buffer_head *io_buffer_head;/* buffer linked list head */
@@ -54,8 +53,6 @@
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
struct xfs_trans *io_append_trans;/* xact. for size update */
- struct kiocb *io_iocb;
- int io_result;
} xfs_ioend_t;
extern const struct address_space_operations xfs_address_space_operations;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3033ba5..478c0ad 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1218,6 +1218,7 @@
char *p;
int error;
+ sync_filesystem(sb);
while ((p = strsep(&options, ",")) != NULL) {
int token;
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 639d7a4..01613b3 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -46,5 +46,20 @@
#define read_barrier_depends() do {} while (0)
#define smp_read_barrier_depends() do {} while (0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
index 2be8a2d..effb600 100644
--- a/include/asm-generic/dma-coherent.h
+++ b/include/asm-generic/dma-coherent.h
@@ -1,3 +1,5 @@
+#if !defined(__i386__) && !defined(__amd64__)
+
#ifndef DMA_COHERENT_H
#define DMA_COHERENT_H
@@ -33,3 +35,46 @@
#endif
#endif
+
+#else /* CMA is a crutch for brain-damaged hardware that causes untold pain */
+
+#ifndef DMA_COHERENT_H
+#define DMA_COHERENT_H
+
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+/*
+ * These three functions are only for dma allocator.
+ * Don't use them in device drivers.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+ dma_addr_t *dma_handle, void **ret);
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
+
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, size_t size, int *ret);
+/*
+ * Standard interface
+ */
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+extern int
+dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags);
+
+extern void
+dma_release_declared_memory(struct device *dev);
+
+extern void *
+dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size);
+#else
+#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
+#endif
+
+#endif
+
+
+
+
+#endif
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index d17784e..344c195 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -87,6 +87,9 @@
#endif /* SMP */
+/* 3.18 backport */
+#define raw_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+
#ifndef PER_CPU_BASE_SECTION
#ifdef CONFIG_SMP
#define PER_CPU_BASE_SECTION ".data..percpu"
diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
new file mode 100644
index 0000000..663ac3d
--- /dev/null
+++ b/include/asm-generic/seccomp.h
@@ -0,0 +1,29 @@
+/*
+ * include/asm-generic/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi <at> linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_GENERIC_SECCOMP_H
+#define _ASM_GENERIC_SECCOMP_H
+
+#include <asm-generic/unistd.h>
+
+#if defined(CONFIG_COMPAT) && !defined(__NR_seccomp_read_32)
+#define __NR_seccomp_read_32 __NR_read
+#define __NR_seccomp_write_32 __NR_write
+#define __NR_seccomp_exit_32 __NR_exit
+#define __NR_seccomp_sigreturn_32 __NR_rt_sigreturn
+#endif /* CONFIG_COMPAT && ! already defined */
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_rt_sigreturn
+
+#endif /* _ASM_GENERIC_SECCOMP_H */
+
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
new file mode 100644
index 0000000..f57eb7b
--- /dev/null
+++ b/include/asm-generic/simd.h
@@ -0,0 +1,14 @@
+
+#include <linux/hardirq.h>
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ * instructions or access the SIMD register file
+ *
+ * As architectures typically don't preserve the SIMD register file when
+ * taking an interrupt, !in_interrupt() should be a reasonable default.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+ return !in_interrupt();
+}
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 5b09392..d401e54 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -144,8 +144,6 @@
/**
* syscall_get_arch - return the AUDIT_ARCH for the current system call
- * @task: task of interest, must be in system call entry tracing
- * @regs: task_pt_regs() of @task
*
* Returns the AUDIT_ARCH_* based on the system call convention in use.
*
@@ -155,5 +153,5 @@
* Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
* provide an implementation of this.
*/
-int syscall_get_arch(struct task_struct *task, struct pt_regs *regs);
+int syscall_get_arch(void);
#endif /* _ASM_SYSCALL_H */
diff --git a/include/crypto/ablk_helper.h b/include/crypto/ablk_helper.h
new file mode 100644
index 0000000..4f93df5
--- /dev/null
+++ b/include/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+ struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+ unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 418d270..063f8ef 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@
void *page;
u8 *buffer;
u8 *iv;
+ unsigned int ivsize;
int flags;
- unsigned int blocksize;
+ unsigned int walk_blocksize;
+ unsigned int cipher_blocksize;
+ unsigned int alignmask;
};
struct ablkcipher_walk {
@@ -192,6 +195,10 @@
int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
struct blkcipher_walk *walk,
unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk,
+ struct crypto_aead *tfm,
+ unsigned int blocksize);
int ablkcipher_walk_done(struct ablkcipher_request *req,
struct ablkcipher_walk *walk, int err);
diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h
new file mode 100644
index 0000000..8dabc39
--- /dev/null
+++ b/include/keys/system_keyring.h
@@ -0,0 +1,23 @@
+/* System keyring containing trusted public keys.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _KEYS_SYSTEM_KEYRING_H
+#define _KEYS_SYSTEM_KEYRING_H
+
+#ifdef CONFIG_SYSTEM_TRUSTED_KEYRING
+
+#include <linux/key.h>
+
+extern struct key *system_trusted_keyring;
+
+#endif
+
+#endif /* _KEYS_SYSTEM_KEYRING_H */
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
new file mode 100644
index 0000000..a460889
--- /dev/null
+++ b/include/linux/Kbuild
@@ -0,0 +1,2 @@
+header-y += if_pppolac.h
+header-y += if_pppopns.h
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 9069694..a899402 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -44,10 +44,14 @@
void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
int alarm_start(struct alarm *alarm, ktime_t start);
+int alarm_start_relative(struct alarm *alarm, ktime_t start);
+void alarm_restart(struct alarm *alarm);
int alarm_try_to_cancel(struct alarm *alarm);
int alarm_cancel(struct alarm *alarm);
u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval);
+ktime_t alarm_expires_remaining(const struct alarm *alarm);
/* Provide way to access the rtc device being used by alarmtimers */
struct rtc_device *alarmtimer_get_rtcdev(void);
diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h
index 32a89cf..9d1d9ca 100644
--- a/include/linux/amba/mmci.h
+++ b/include/linux/amba/mmci.h
@@ -5,6 +5,15 @@
#define AMBA_MMCI_H
#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+
+struct embedded_sdio_data {
+ struct sdio_cis cis;
+ struct sdio_cccr cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+};
/*
@@ -73,6 +82,9 @@
bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
void *dma_rx_param;
void *dma_tx_param;
+ unsigned int status_irq;
+ struct embedded_sdio_data *embedded_sdio;
+ int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id);
};
#endif
diff --git a/include/linux/android_aid.h b/include/linux/android_aid.h
new file mode 100644
index 0000000..06264b8
--- /dev/null
+++ b/include/linux/android_aid.h
@@ -0,0 +1,28 @@
+/* include/linux/android_aid.h
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_ANDROID_AID_H
+#define _LINUX_ANDROID_AID_H
+
+/* AIDs that the kernel treats differently */
+#define AID_OBSOLETE_000 3001 /* was NET_BT_ADMIN */
+#define AID_OBSOLETE_001 3002 /* was NET_BT */
+#define AID_INET 3003
+#define AID_NET_RAW 3004
+#define AID_NET_ADMIN 3005
+#define AID_NET_BW_STATS 3006 /* read bandwidth statistics */
+#define AID_NET_BW_ACCT 3007 /* change bandwidth statistics accounting */
+
+#endif
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c1dde8e..28db15dd 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -21,6 +21,9 @@
*/
#include <asm/bitops.h>
+/* 3.18 backport */
+#define smp_mb__after_atomic() smp_mb__after_clear_bit()
+
#define for_each_set_bit(bit, addr, size) \
for ((bit) = find_first_bit((addr), (size)); \
(bit) < (size); \
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 9e52b0626..a3bd299 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -36,6 +36,7 @@
BH_Quiet, /* Buffer Error Prinks to be quiet */
BH_Meta, /* Buffer contains metadata */
BH_Prio, /* Buffer should be submitted with REQ_PRIO */
+ BH_Defer_Completion, /* Defer AIO completion to workqueue */
BH_PrivateStart,/* not a state bit, but the first bit available
* for private allocation by other entities
@@ -128,6 +129,7 @@
BUFFER_FNS(Unwritten, unwritten)
BUFFER_FNS(Meta, meta)
BUFFER_FNS(Prio, prio)
+BUFFER_FNS(Defer_Completion, defer_completion)
#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK)
@@ -198,7 +200,8 @@
* Generic address_space_operations implementations for buffer_head-backed
* address_spaces.
*/
-void block_invalidatepage(struct page *page, unsigned long offset);
+void block_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length);
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc);
int block_write_full_page_endio(struct page *page, get_block_t *get_block,
@@ -294,6 +297,18 @@
return __bread(sb->s_bdev, block, sb->s_blocksize);
}
+static inline struct buffer_head *
+sb_bread_unmovable(struct super_block *sb, sector_t block)
+{
+ return sb_bread(sb, block);
+}
+
+static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
+ sector_t block, unsigned size)
+{
+ return __getblk(bdev, block, size);
+}
+
static inline void
sb_breadahead(struct super_block *sb, sector_t block)
{
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8852d37..a6fc777 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -578,6 +578,7 @@
void (*css_offline)(struct cgroup *cgrp);
void (*css_free)(struct cgroup *cgrp);
+ int (*allow_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
@@ -868,6 +869,17 @@
unsigned short css_depth(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
+/*
+ * Default Android check for whether the current process is allowed to move a
+ * task across cgroups, either because CAP_SYS_NICE is set or because the uid
+ * of the calling process is the same as the moved task or because we are
+ * running as root.
+ * Returns 0 if this is allowed, or -EACCES otherwise.
+ */
+int subsys_cgroup_allow_attach(struct cgroup *cgrp,
+ struct cgroup_taskset *tset);
+
+
#else /* !CONFIG_CGROUPS */
static inline int cgroup_init_early(void) { return 0; }
@@ -891,6 +903,11 @@
return 0;
}
+static inline int subsys_cgroup_allow_attach(struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
+{
+ return 0;
+}
#endif /* !CONFIG_CGROUPS */
#endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a2ce6f8..6977192 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -302,6 +302,11 @@
# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
#endif
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
/* Compile time object size, -1 for unknown */
#ifndef __compiletime_object_size
# define __compiletime_object_size(obj) -1
@@ -341,6 +346,10 @@
#define compiletime_assert(condition, msg) \
_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
+#define compiletime_assert_atomic_type(t) \
+ compiletime_assert(__native_word(t), \
+ "Need native word sized stores/loads for atomicity.")
+
/*
* Prevent the compiler from merging or refetching accesses. The compiler
* is also forbidden from reordering successive instances of ACCESS_ONCE(),
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 9f3c7e8..a4a0d43 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -119,26 +119,46 @@
{ .notifier_call = fn, .priority = pri }; \
register_cpu_notifier(&fn##_nb); \
}
+
+#define __cpu_notifier(fn, pri) { \
+ static struct notifier_block fn##_nb = \
+ { .notifier_call = fn, .priority = pri }; \
+ __register_cpu_notifier(&fn##_nb); \
+}
#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0)
#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+
#ifdef CONFIG_HOTPLUG_CPU
extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
extern void unregister_cpu_notifier(struct notifier_block *nb);
+extern void __unregister_cpu_notifier(struct notifier_block *nb);
#else
#ifndef MODULE
extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
#else
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
+
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
#endif
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
+
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
#endif
int cpu_up(unsigned int cpu);
@@ -146,19 +166,32 @@
extern void cpu_maps_update_begin(void);
extern void cpu_maps_update_done(void);
+#define cpu_notifier_register_begin cpu_maps_update_begin
+#define cpu_notifier_register_done cpu_maps_update_done
+
#else /* CONFIG_SMP */
#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0)
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
+
static inline void cpu_maps_update_begin(void)
{
}
@@ -167,6 +200,14 @@
{
}
+static inline void cpu_notifier_register_begin(void)
+{
+}
+
+static inline void cpu_notifier_register_done(void)
+{
+}
+
#endif /* CONFIG_SMP */
extern struct bus_type cpu_subsys;
@@ -178,8 +219,11 @@
extern void cpu_hotplug_disable(void);
extern void cpu_hotplug_enable(void);
#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
+#define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri)
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
+#define __register_hotcpu_notifier(nb) __register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
+#define __unregister_hotcpu_notifier(nb) __unregister_cpu_notifier(nb)
void clear_tasks_mm_cpumask(int cpu);
int cpu_down(unsigned int cpu);
@@ -203,9 +247,12 @@
#define cpu_hotplug_disable() do { } while (0)
#define cpu_hotplug_enable() do { } while (0)
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
+#define __register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotcpu_notifier(nb) ({ (void)(nb); })
+#define __unregister_hotcpu_notifier(nb) ({ (void)(nb); })
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
@@ -232,4 +279,11 @@
void arch_cpu_idle_exit(void);
void arch_cpu_idle_dead(void);
+#define IDLE_START 1
+#define IDLE_END 2
+
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+void idle_notifier_call_chain(unsigned long val);
+
#endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h
new file mode 100644
index 0000000..c4d4eb8
--- /dev/null
+++ b/include/linux/cpufeature.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CPUFEATURE_H
+#define __LINUX_CPUFEATURE_H
+
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+
+#include <linux/mod_devicetable.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Macros imported from <asm/cpufeature.h>:
+ * - cpu_feature(x) ordinal value of feature called 'x'
+ * - cpu_have_feature(u32 n) whether feature #n is available
+ * - MAX_CPU_FEATURES upper bound for feature ordinal values
+ * Optional:
+ * - CPU_FEATURE_TYPEFMT format string fragment for printing the cpu type
+ * - CPU_FEATURE_TYPEVAL set of values matching the format string above
+ */
+
+#ifndef CPU_FEATURE_TYPEFMT
+#define CPU_FEATURE_TYPEFMT "%s"
+#endif
+
+#ifndef CPU_FEATURE_TYPEVAL
+#define CPU_FEATURE_TYPEVAL ELF_PLATFORM
+#endif
+
+/*
+ * Use module_cpu_feature_match(feature, module_init_function) to
+ * declare that
+ * a) the module shall be probed upon discovery of CPU feature 'feature'
+ * (typically at boot time using udev)
+ * b) the module must not be loaded if CPU feature 'feature' is not present
+ * (not even by manual insmod).
+ *
+ * For a list of legal values for 'feature', please consult the file
+ * 'asm/cpufeature.h' of your favorite architecture.
+ */
+#define module_cpu_feature_match(x, __init) \
+static struct cpu_feature const cpu_feature_match_ ## x[] = \
+ { { .feature = cpu_feature(x) }, { } }; \
+MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \
+ \
+static int cpu_feature_match_ ## x ## _init(void) \
+{ \
+ if (!cpu_have_feature(cpu_feature(x))) \
+ return -ENODEV; \
+ return __init(); \
+} \
+module_init(cpu_feature_match_ ## x ## _init)
+
+#endif
+#endif
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1a81b74..d23ed25 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -21,6 +21,7 @@
#include <linux/workqueue.h>
#include <linux/cpumask.h>
#include <asm/div64.h>
+#include <asm/cputime.h>
#define CPUFREQ_NAME_LEN 16
/* Print length for names. Extra 1 space for accomodating '\n' in prints */
@@ -341,6 +342,7 @@
int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
int cpufreq_update_policy(unsigned int cpu);
bool have_governor_per_policy(void);
+struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
#ifdef CONFIG_CPU_FREQ
/* query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it */
@@ -394,6 +396,9 @@
#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
extern struct cpufreq_governor cpufreq_gov_conservative;
#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE)
+extern struct cpufreq_governor cpufreq_gov_interactive;
+#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_interactive)
#endif
@@ -433,4 +438,11 @@
void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy);
void cpufreq_frequency_table_put_attr(unsigned int cpu);
+
+/*********************************************************************
+ * CPUFREQ STATS *
+ *********************************************************************/
+
+void acct_update_power(struct task_struct *p, cputime_t cputime);
+
#endif /* _LINUX_CPUFREQ_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index c1999d1..7bd16b9 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -158,6 +158,7 @@
char *(*d_dname)(struct dentry *, char *, int);
struct vfsmount *(*d_automount)(struct path *);
int (*d_manage)(struct dentry *, bool);
+ void (*d_canonical_path)(const struct path *, struct path *);
} ____cacheline_aligned;
/*
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 21ca773..822c135 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -51,7 +51,7 @@
extern void debug_show_all_locks(void);
extern void debug_show_held_locks(struct task_struct *task);
extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void debug_check_no_locks_held(struct task_struct *task);
+extern void debug_check_no_locks_held(void);
#else
static inline void debug_show_all_locks(void)
{
@@ -67,7 +67,7 @@
}
static inline void
-debug_check_no_locks_held(struct task_struct *task)
+debug_check_no_locks_held(void)
{
}
#endif
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ef5bd3f..134dc8d 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -381,6 +381,12 @@
void *dm_get_mdptr(struct mapped_device *md);
/*
+ * Export the device via the ioctl interface (uses mdptr).
+ */
+int dm_ioctl_export(struct mapped_device *md, const char *name,
+ const char *uuid);
+
+/*
* A device can still be used while suspended, but I/O is deferred.
*/
int dm_suspend(struct mapped_device *md, unsigned suspend_flags);
diff --git a/include/linux/err.h b/include/linux/err.h
index f2edce2..9b8c28d 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -60,6 +60,9 @@
return 0;
}
+/* for backport */
+#define PTR_ERR_OR_ZERO(p) PTR_RET(p)
+
#endif
#endif /* _LINUX_ERR_H */
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index e70df40..7fd81b8 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -3,6 +3,7 @@
#ifndef FREEZER_H_INCLUDED
#define FREEZER_H_INCLUDED
+#include <linux/debug_locks.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/atomic.h>
@@ -46,7 +47,11 @@
extern void thaw_processes(void);
extern void thaw_kernel_threads(void);
-static inline bool try_to_freeze(void)
+/*
+ * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION
+ * If try_to_freeze causes a lockdep warning it means the caller may deadlock
+ */
+static inline bool try_to_freeze_unsafe(void)
{
might_sleep();
if (likely(!freezing(current)))
@@ -54,6 +59,13 @@
return __refrigerator(false);
}
+static inline bool try_to_freeze(void)
+{
+ if (!(current->flags & PF_NOFREEZE))
+ debug_check_no_locks_held();
+ return try_to_freeze_unsafe();
+}
+
extern bool freeze_task(struct task_struct *p);
extern bool set_freezable(void);
@@ -115,6 +127,14 @@
try_to_freeze();
}
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline void freezer_count_unsafe(void)
+{
+ current->flags &= ~PF_FREEZER_SKIP;
+ smp_mb();
+ try_to_freeze_unsafe();
+}
+
/**
* freezer_should_skip - whether to skip a task when determining frozen
* state is reached
@@ -139,28 +159,86 @@
}
/*
- * These macros are intended to be used whenever you want allow a sleeping
+ * These functions are intended to be used whenever you want allow a sleeping
* task to be frozen. Note that neither return any clear indication of
* whether a freeze event happened while in this function.
*/
/* Like schedule(), but should not block the freezer. */
-#define freezable_schedule() \
-({ \
- freezer_do_not_count(); \
- schedule(); \
- freezer_count(); \
-})
+static inline void freezable_schedule(void)
+{
+ freezer_do_not_count();
+ schedule();
+ freezer_count();
+}
+
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline void freezable_schedule_unsafe(void)
+{
+ freezer_do_not_count();
+ schedule();
+ freezer_count_unsafe();
+}
+
+/*
+ * Like freezable_schedule_timeout(), but should not block the freezer. Do not
+ * call this with locks held.
+ */
+static inline long freezable_schedule_timeout(long timeout)
+{
+ long __retval;
+ freezer_do_not_count();
+ __retval = schedule_timeout(timeout);
+ freezer_count();
+ return __retval;
+}
+
+/*
+ * Like schedule_timeout_interruptible(), but should not block the freezer. Do not
+ * call this with locks held.
+ */
+static inline long freezable_schedule_timeout_interruptible(long timeout)
+{
+ long __retval;
+ freezer_do_not_count();
+ __retval = schedule_timeout_interruptible(timeout);
+ freezer_count();
+ return __retval;
+}
/* Like schedule_timeout_killable(), but should not block the freezer. */
-#define freezable_schedule_timeout_killable(timeout) \
-({ \
- long __retval; \
- freezer_do_not_count(); \
- __retval = schedule_timeout_killable(timeout); \
- freezer_count(); \
- __retval; \
-})
+static inline long freezable_schedule_timeout_killable(long timeout)
+{
+ long __retval;
+ freezer_do_not_count();
+ __retval = schedule_timeout_killable(timeout);
+ freezer_count();
+ return __retval;
+}
+
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+static inline long freezable_schedule_timeout_killable_unsafe(long timeout)
+{
+ long __retval;
+ freezer_do_not_count();
+ __retval = schedule_timeout_killable(timeout);
+ freezer_count_unsafe();
+ return __retval;
+}
+
+/*
+ * Like schedule_hrtimeout_range(), but should not block the freezer. Do not
+ * call this with locks held.
+ */
+static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
+ unsigned long delta, const enum hrtimer_mode mode)
+{
+ int __retval;
+ freezer_do_not_count();
+ __retval = schedule_hrtimeout_range(expires, delta, mode);
+ freezer_count();
+ return __retval;
+}
/*
* Freezer-friendly wrappers around wait_event_interruptible(),
@@ -177,33 +255,45 @@
__retval; \
})
+/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
+#define wait_event_freezekillable_unsafe(wq, condition) \
+({ \
+ int __retval; \
+ freezer_do_not_count(); \
+ __retval = wait_event_killable(wq, (condition)); \
+ freezer_count_unsafe(); \
+ __retval; \
+})
+
#define wait_event_freezable(wq, condition) \
({ \
int __retval; \
- for (;;) { \
- __retval = wait_event_interruptible(wq, \
- (condition) || freezing(current)); \
- if (__retval || (condition)) \
- break; \
- try_to_freeze(); \
- } \
+ freezer_do_not_count(); \
+ __retval = wait_event_interruptible(wq, (condition)); \
+ freezer_count(); \
__retval; \
})
#define wait_event_freezable_timeout(wq, condition, timeout) \
({ \
long __retval = timeout; \
- for (;;) { \
- __retval = wait_event_interruptible_timeout(wq, \
- (condition) || freezing(current), \
- __retval); \
- if (__retval <= 0 || (condition)) \
- break; \
- try_to_freeze(); \
- } \
+ freezer_do_not_count(); \
+ __retval = wait_event_interruptible_timeout(wq, (condition), \
+ __retval); \
+ freezer_count(); \
__retval; \
})
+#define wait_event_freezable_exclusive(wq, condition) \
+({ \
+ int __retval; \
+ freezer_do_not_count(); \
+ __retval = wait_event_interruptible_exclusive(wq, condition); \
+ freezer_count(); \
+ __retval; \
+})
+
+
#else /* !CONFIG_FREEZER */
static inline bool frozen(struct task_struct *p) { return false; }
static inline bool freezing(struct task_struct *p) { return false; }
@@ -225,18 +315,37 @@
#define freezable_schedule() schedule()
+#define freezable_schedule_unsafe() schedule()
+
+#define freezable_schedule_timeout(timeout) schedule_timeout(timeout)
+
+#define freezable_schedule_timeout_interruptible(timeout) \
+ schedule_timeout_interruptible(timeout)
+
#define freezable_schedule_timeout_killable(timeout) \
schedule_timeout_killable(timeout)
+#define freezable_schedule_timeout_killable_unsafe(timeout) \
+ schedule_timeout_killable(timeout)
+
+#define freezable_schedule_hrtimeout_range(expires, delta, mode) \
+ schedule_hrtimeout_range(expires, delta, mode)
+
#define wait_event_freezable(wq, condition) \
wait_event_interruptible(wq, condition)
#define wait_event_freezable_timeout(wq, condition, timeout) \
wait_event_interruptible_timeout(wq, condition, timeout)
+#define wait_event_freezable_exclusive(wq, condition) \
+ wait_event_interruptible_exclusive(wq, condition)
+
#define wait_event_freezekillable(wq, condition) \
wait_event_killable(wq, condition)
+#define wait_event_freezekillable_unsafe(wq, condition) \
+ wait_event_killable(wq, condition)
+
#endif /* !CONFIG_FREEZER */
#endif /* FREEZER_H_INCLUDED */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5c9dc84..5628c42 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -46,6 +46,7 @@
struct cred;
struct swap_info_struct;
struct seq_file;
+struct workqueue_struct;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -63,8 +64,7 @@
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
- ssize_t bytes, void *private, int ret,
- bool is_async);
+ ssize_t bytes, void *private);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
@@ -365,7 +365,7 @@
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
sector_t (*bmap)(struct address_space *, sector_t);
- void (*invalidatepage) (struct page *, unsigned long);
+ void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -632,9 +632,14 @@
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
- I_MUTEX_QUOTA
+ I_MUTEX_QUOTA,
+ I_MUTEX_NONDIR2,
+ I_MUTEX_PARENT2,
};
+void lock_two_nondirectories(struct inode *, struct inode*);
+void unlock_two_nondirectories(struct inode *, struct inode*);
+
/*
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
@@ -762,7 +767,12 @@
#define FILE_MNT_WRITE_RELEASED 2
struct file {
+ /*
+ * fu_list becomes invalid after file_free is called and queued via
+ * fu_rcuhead for RCU freeing
+ */
union {
+ struct list_head fu_list;
struct llist_node fu_llist;
struct rcu_head fu_rcuhead;
} f_u;
@@ -776,6 +786,9 @@
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
+#ifdef CONFIG_SMP
+ int f_sb_list_cpu;
+#endif
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
@@ -1251,6 +1264,11 @@
struct list_head s_inodes; /* all inodes */
struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */
+#ifdef CONFIG_SMP
+ struct list_head __percpu *s_files;
+#else
+ struct list_head s_files;
+#endif
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
struct list_head s_dentry_lru; /* unused dentry lru */
@@ -1311,6 +1329,9 @@
/* Being remounted read-only */
int s_readonly_remount;
+
+ /* AIO completions deferred from interrupt context */
+ struct workqueue_struct *s_dio_done_wq;
};
/* superblock cache pruning functions */
@@ -1495,6 +1516,17 @@
* to have different dirent layouts depending on the binary type.
*/
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct dir_context {
+ const filldir_t actor;
+ loff_t pos;
+};
+
+static inline bool dir_emit(struct dir_context *ctx,
+ const char *name, int namelen,
+ u64 ino, unsigned type)
+{
+ return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0;
+}
struct block_device_operations;
/* These macros are for out of kernel modules to test that
@@ -1511,6 +1543,7 @@
ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
int (*readdir) (struct file *, void *, filldir_t);
+ int (*iterate) (struct file *, struct dir_context *);
unsigned int (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
@@ -2460,6 +2493,9 @@
void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);
+extern void inode_set_flags(struct inode *inode, unsigned int flags,
+ unsigned int mask);
+
extern const struct file_operations generic_ro_fops;
#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
@@ -2484,6 +2520,7 @@
void inode_set_bytes(struct inode *inode, loff_t bytes);
extern int vfs_readdir(struct file *, filldir_t, void *);
+extern int iterate_dir(struct file *, struct dir_context *);
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
@@ -2678,4 +2715,11 @@
inode->i_flags |= S_NOSEC;
}
+static inline bool dir_relax(struct inode *inode)
+{
+ mutex_unlock(&inode->i_mutex);
+ mutex_lock(&inode->i_mutex);
+ return !IS_DEADDIR(inode);
+}
+
#endif /* _LINUX_FS_H */
diff --git a/include/linux/gpio_event.h b/include/linux/gpio_event.h
new file mode 100644
index 0000000..2613fc5
--- /dev/null
+++ b/include/linux/gpio_event.h
@@ -0,0 +1,170 @@
+/* include/linux/gpio_event.h
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_GPIO_EVENT_H
+#define _LINUX_GPIO_EVENT_H
+
+#include <linux/input.h>
+
+struct gpio_event_input_devs {
+ int count;
+ struct input_dev *dev[];
+};
+enum {
+ GPIO_EVENT_FUNC_UNINIT = 0x0,
+ GPIO_EVENT_FUNC_INIT = 0x1,
+ GPIO_EVENT_FUNC_SUSPEND = 0x2,
+ GPIO_EVENT_FUNC_RESUME = 0x3,
+};
+struct gpio_event_info {
+ int (*func)(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info,
+ void **data, int func);
+ int (*event)(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info,
+ void **data, unsigned int dev, unsigned int type,
+ unsigned int code, int value); /* out events */
+ bool no_suspend;
+};
+
+struct gpio_event_platform_data {
+ const char *name;
+ struct gpio_event_info **info;
+ size_t info_count;
+ int (*power)(const struct gpio_event_platform_data *pdata, bool on);
+ const char *names[]; /* If name is NULL, names contain a NULL */
+ /* terminated list of input devices to create */
+};
+
+#define GPIO_EVENT_DEV_NAME "gpio-event"
+
+/* Key matrix */
+
+enum gpio_event_matrix_flags {
+ /* unset: drive active output low, set: drive active output high */
+ GPIOKPF_ACTIVE_HIGH = 1U << 0,
+ GPIOKPF_DEBOUNCE = 1U << 1,
+ GPIOKPF_REMOVE_SOME_PHANTOM_KEYS = 1U << 2,
+ GPIOKPF_REMOVE_PHANTOM_KEYS = GPIOKPF_REMOVE_SOME_PHANTOM_KEYS |
+ GPIOKPF_DEBOUNCE,
+ GPIOKPF_DRIVE_INACTIVE = 1U << 3,
+ GPIOKPF_LEVEL_TRIGGERED_IRQ = 1U << 4,
+ GPIOKPF_PRINT_UNMAPPED_KEYS = 1U << 16,
+ GPIOKPF_PRINT_MAPPED_KEYS = 1U << 17,
+ GPIOKPF_PRINT_PHANTOM_KEYS = 1U << 18,
+};
+
+#define MATRIX_CODE_BITS (10)
+#define MATRIX_KEY_MASK ((1U << MATRIX_CODE_BITS) - 1)
+#define MATRIX_KEY(dev, code) \
+ (((dev) << MATRIX_CODE_BITS) | (code & MATRIX_KEY_MASK))
+
+extern int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_matrix_info {
+ /* initialize to gpio_event_matrix_func */
+ struct gpio_event_info info;
+ /* size must be ninputs * noutputs */
+ const unsigned short *keymap;
+ unsigned int *input_gpios;
+ unsigned int *output_gpios;
+ unsigned int ninputs;
+ unsigned int noutputs;
+ /* time to wait before reading inputs after driving each output */
+ ktime_t settle_time;
+ /* time to wait before scanning the keypad a second time */
+ ktime_t debounce_delay;
+ ktime_t poll_time;
+ unsigned flags;
+};
+
+/* Directly connected inputs and outputs */
+
+enum gpio_event_direct_flags {
+ GPIOEDF_ACTIVE_HIGH = 1U << 0,
+/* GPIOEDF_USE_DOWN_IRQ = 1U << 1, */
+/* GPIOEDF_USE_IRQ = (1U << 2) | GPIOIDF_USE_DOWN_IRQ, */
+ GPIOEDF_PRINT_KEYS = 1U << 8,
+ GPIOEDF_PRINT_KEY_DEBOUNCE = 1U << 9,
+ GPIOEDF_PRINT_KEY_UNSTABLE = 1U << 10,
+};
+
+struct gpio_event_direct_entry {
+ uint32_t gpio:16;
+ uint32_t code:10;
+ uint32_t dev:6;
+};
+
+/* inputs */
+extern int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_input_info {
+ /* initialize to gpio_event_input_func */
+ struct gpio_event_info info;
+ ktime_t debounce_time;
+ ktime_t poll_time;
+ uint16_t flags;
+ uint16_t type;
+ const struct gpio_event_direct_entry *keymap;
+ size_t keymap_size;
+};
+
+/* outputs */
+extern int gpio_event_output_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+extern int gpio_event_output_event(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data,
+ unsigned int dev, unsigned int type,
+ unsigned int code, int value);
+struct gpio_event_output_info {
+ /* initialize to gpio_event_output_func and gpio_event_output_event */
+ struct gpio_event_info info;
+ uint16_t flags;
+ uint16_t type;
+ const struct gpio_event_direct_entry *keymap;
+ size_t keymap_size;
+};
+
+
+/* axes */
+
+enum gpio_event_axis_flags {
+ GPIOEAF_PRINT_UNKNOWN_DIRECTION = 1U << 16,
+ GPIOEAF_PRINT_RAW = 1U << 17,
+ GPIOEAF_PRINT_EVENT = 1U << 18,
+};
+
+extern int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+ struct gpio_event_info *info, void **data, int func);
+struct gpio_event_axis_info {
+ /* initialize to gpio_event_axis_func */
+ struct gpio_event_info info;
+ uint8_t count; /* number of gpios for this axis */
+ uint8_t dev; /* device index when using multiple input devices */
+ uint8_t type; /* EV_REL or EV_ABS */
+ uint16_t code;
+ uint16_t decoded_size;
+ uint16_t (*map)(struct gpio_event_axis_info *info, uint16_t in);
+ uint32_t *gpio;
+ uint32_t flags;
+};
+#define gpio_axis_2bit_gray_map gpio_axis_4bit_gray_map
+#define gpio_axis_3bit_gray_map gpio_axis_4bit_gray_map
+uint16_t gpio_axis_4bit_gray_map(
+ struct gpio_event_axis_info *info, uint16_t in);
+uint16_t gpio_axis_5bit_singletrack_map(
+ struct gpio_event_axis_info *info, uint16_t in);
+
+#endif
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 4f8aa47..40e9c9d 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -649,8 +649,8 @@
int (*input_mapped)(struct hid_device *hdev,
struct hid_input *hidinput, struct hid_field *field,
struct hid_usage *usage, unsigned long **bit, int *max);
- void (*input_configured)(struct hid_device *hdev,
- struct hid_input *hidinput);
+ int (*input_configured)(struct hid_device *hdev,
+ struct hid_input *hidinput);
void (*feature_mapping)(struct hid_device *hdev,
struct hid_field *field,
struct hid_usage *usage);
diff --git a/include/linux/if_pppolac.h b/include/linux/if_pppolac.h
new file mode 100644
index 0000000..e40aa10
--- /dev/null
+++ b/include/linux/if_pppolac.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOLAC_H
+#define __LINUX_IF_PPPOLAC_H
+
+#include <uapi/linux/if_pppolac.h>
+
+#endif /* __LINUX_IF_PPPOLAC_H */
diff --git a/include/linux/if_pppopns.h b/include/linux/if_pppopns.h
new file mode 100644
index 0000000..4ac621a9
--- /dev/null
+++ b/include/linux/if_pppopns.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOPNS_H
+#define __LINUX_IF_PPPOPNS_H
+
+#include <uapi/linux/if_pppopns.h>
+
+#endif /* __LINUX_IF_PPPOPNS_H */
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index aff7ad8..dccd621 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -41,6 +41,25 @@
u32 seq_sent, seq_recv;
int ppp_flags;
};
+
+struct pppolac_opt {
+ __u32 local;
+ __u32 remote;
+ __u32 recv_sequence;
+ __u32 xmit_sequence;
+ atomic_t sequencing;
+ int (*backlog_rcv)(struct sock *sk_udp, struct sk_buff *skb);
+};
+
+struct pppopns_opt {
+ __u16 local;
+ __u16 remote;
+ __u32 recv_sequence;
+ __u32 xmit_sequence;
+ void (*data_ready)(struct sock *sk_raw, int length);
+ int (*backlog_rcv)(struct sock *sk_raw, struct sk_buff *skb);
+};
+
#include <net/sock.h>
struct pppox_sock {
@@ -51,6 +70,8 @@
union {
struct pppoe_opt pppoe;
struct pptp_opt pptp;
+ struct pppolac_opt lac;
+ struct pppopns_opt pns;
} proto;
__be16 num;
};
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 46da024..25de5e7 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -3,6 +3,7 @@
#include <uapi/linux/inet_diag.h>
+struct net;
struct sock;
struct inet_hashinfo;
struct nlattr;
@@ -23,6 +24,10 @@
void (*idiag_get_info)(struct sock *sk,
struct inet_diag_msg *r,
void *info);
+
+ int (*destroy)(struct sk_buff *in_skb,
+ struct inet_diag_req_v2 *req);
+
__u16 idiag_type;
};
@@ -39,6 +44,10 @@
struct sk_buff *in_skb, const struct nlmsghdr *nlh,
struct inet_diag_req_v2 *req);
+struct sock *inet_diag_find_one_icsk(struct net *net,
+ struct inet_hashinfo *hashinfo,
+ struct inet_diag_req_v2 *req);
+
int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
extern int inet_diag_register(const struct inet_diag_handler *handler);
diff --git a/include/linux/initramfs.h b/include/linux/initramfs.h
new file mode 100644
index 0000000..fc7da63
--- /dev/null
+++ b/include/linux/initramfs.h
@@ -0,0 +1,32 @@
+/*
+ * include/linux/initramfs.h
+ *
+ * Copyright (C) 2015, Google
+ * Rom Lemarchand <romlem@android.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _LINUX_INITRAMFS_H
+#define _LINUX_INITRAMFS_H
+
+#include <linux/kconfig.h>
+
+#if IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+
+int __init default_rootfs(void);
+
+#endif
+
+#endif /* _LINUX_INITRAMFS_H */
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index b8b7dc7..17e06f1 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -36,10 +36,12 @@
__s32 accept_ra_rt_info_max_plen;
#endif
#endif
+ __s32 accept_ra_rt_table;
__s32 proxy_ndp;
__s32 accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
__s32 optimistic_dad;
+ __s32 use_optimistic;
#endif
#ifdef CONFIG_IPV6_MROUTE
__s32 mc_forwarding;
@@ -48,6 +50,7 @@
__s32 accept_dad;
__s32 force_tllao;
__s32 ndisc_notify;
+ __s32 use_oif_addrs_only;
void *sysctl;
};
@@ -217,7 +220,7 @@
struct ipv6_ac_socklist *ipv6_ac_list;
struct ipv6_fl_socklist __rcu *ipv6_fl_list;
- struct ipv6_txoptions *opt;
+ struct ipv6_txoptions __rcu *opt;
struct sk_buff *pktoptions;
struct sk_buff *rxpmtu;
struct {
@@ -270,9 +273,9 @@
}
#if IS_ENABLED(CONFIG_IPV6)
-static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
+static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
{
- return inet_sk(__sk)->pinet6;
+ return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL;
}
static inline struct inet6_request_sock *
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 7d4a932..8c8779b 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -26,7 +26,6 @@
#include <linux/buffer_head.h>
#include <linux/journal-head.h>
#include <linux/stddef.h>
-#include <linux/bit_spinlock.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/slab.h>
@@ -57,17 +56,13 @@
*/
#define JBD2_EXPENSIVE_CHECKING
extern ushort jbd2_journal_enable_debug;
+void __jbd2_debug(int level, const char *file, const char *func,
+ unsigned int line, const char *fmt, ...);
-#define jbd_debug(n, f, a...) \
- do { \
- if ((n) <= jbd2_journal_enable_debug) { \
- printk (KERN_DEBUG "(%s, %d): %s: ", \
- __FILE__, __LINE__, __func__); \
- printk (f, ## a); \
- } \
- } while (0)
+#define jbd_debug(n, fmt, a...) \
+ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a)
#else
-#define jbd_debug(f, a...) /**/
+#define jbd_debug(n, fmt, a...) /**/
#endif
extern void *jbd2_alloc(size_t size, gfp_t flags);
@@ -164,7 +159,11 @@
* journal_block_tag (in the descriptor). The other h_chksum* fields are
* not used.
*
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum. Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
*/
struct commit_header {
__be32 h_magic;
@@ -184,6 +183,14 @@
* raw struct shouldn't be used for pointer math or sizeof() - use
* journal_tag_bytes(journal) instead to compute this.
*/
+typedef struct journal_block_tag3_s
+{
+ __be32 t_blocknr; /* The on-disk block number */
+ __be32 t_flags; /* See below */
+ __be32 t_blocknr_high; /* most-significant high 32bits. */
+ __be32 t_checksum; /* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
typedef struct journal_block_tag_s
{
__be32 t_blocknr; /* The on-disk block number */
@@ -192,9 +199,6 @@
__be32 t_blocknr_high; /* most-significant high 32bits. */
} journal_block_tag_t;
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
/* Tail of descriptor block, for checksumming */
struct jbd2_journal_block_tail {
__be32 t_checksum; /* crc32c(uuid+descr_block) */
@@ -289,6 +293,7 @@
#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002
#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004
#define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010
/* Features known to this kernel version: */
#define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM
@@ -296,12 +301,41 @@
#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \
JBD2_FEATURE_INCOMPAT_64BIT | \
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
- JBD2_FEATURE_INCOMPAT_CSUM_V2)
+ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+ JBD2_FEATURE_INCOMPAT_CSUM_V3)
#ifdef __KERNEL__
#include <linux/fs.h>
#include <linux/sched.h>
+
+enum jbd_state_bits {
+ BH_JBD /* Has an attached ext3 journal_head */
+ = BH_PrivateStart,
+ BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
+ BH_Freed, /* Has been freed (truncated) */
+ BH_Revoked, /* Has been revoked from the log */
+ BH_RevokeValid, /* Revoked flag is valid */
+ BH_JBDDirty, /* Is dirty but journaled */
+ BH_State, /* Pins most journal_head state */
+ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
+ BH_Shadow, /* IO on shadow buffer is running */
+ BH_Verified, /* Metadata block has been verified ok */
+ BH_JBDPrivateStart, /* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+BUFFER_FNS(Shadow, shadow)
+BUFFER_FNS(Verified, verified)
+
#include <linux/jbd_common.h>
#define J_ASSERT(assert) BUG_ON(!(assert))
@@ -382,8 +416,15 @@
struct jbd2_journal_handle
{
- /* Which compound transaction is this update a part of? */
- transaction_t *h_transaction;
+ union {
+ /* Which compound transaction is this update a part of? */
+ transaction_t *h_transaction;
+ /* Which journal handle belongs to - used iff h_reserved set */
+ journal_t *h_journal;
+ };
+
+ /* Handle reserved for finishing the logical operation */
+ handle_t *h_rsv_handle;
/* Number of remaining buffers we are allowed to dirty: */
int h_buffer_credits;
@@ -398,6 +439,7 @@
/* Flags [no locking] */
unsigned int h_sync: 1; /* sync-on-close */
unsigned int h_jdata: 1; /* force data journaling */
+ unsigned int h_reserved: 1; /* handle with reserved credits */
unsigned int h_aborted: 1; /* fatal error on handle */
unsigned int h_type: 8; /* for handle statistics */
unsigned int h_line_no: 16; /* for handle statistics */
@@ -524,12 +566,6 @@
struct journal_head *t_checkpoint_io_list;
/*
- * Doubly-linked circular list of temporary buffers currently undergoing
- * IO in the log [j_list_lock]
- */
- struct journal_head *t_iobuf_list;
-
- /*
* Doubly-linked circular list of metadata buffers being shadowed by log
* IO. The IO buffers on the iobuf list and the shadow buffers on this
* list match each other one for one at all times. [j_list_lock]
@@ -537,12 +573,6 @@
struct journal_head *t_shadow_list;
/*
- * Doubly-linked circular list of control buffers being written to the
- * log. [j_list_lock]
- */
- struct journal_head *t_log_list;
-
- /*
* List of inodes whose data we've modified in data=ordered mode.
* [j_list_lock]
*/
@@ -671,11 +701,10 @@
* waiting for checkpointing
* @j_wait_transaction_locked: Wait queue for waiting for a locked transaction
* to start committing, or for a barrier lock to be released
- * @j_wait_logspace: Wait queue for waiting for checkpointing to complete
* @j_wait_done_commit: Wait queue for waiting for commit to complete
- * @j_wait_checkpoint: Wait queue to trigger checkpointing
* @j_wait_commit: Wait queue to trigger commit
* @j_wait_updates: Wait queue to wait for updates to complete
+ * @j_wait_reserved: Wait queue to wait for reserved buffer credits to drop
* @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints
* @j_head: Journal head - identifies the first unused block in the journal
* @j_tail: Journal tail - identifies the oldest still-used block in the
@@ -689,6 +718,7 @@
* journal
* @j_fs_dev: Device which holds the client fs. For internal journal this will
* be equal to j_dev
+ * @j_reserved_credits: Number of buffers reserved from the running transaction
* @j_maxlen: Total maximum capacity of the journal region on disk.
* @j_list_lock: Protects the buffer lists and internal buffer state.
* @j_inode: Optional inode where we store the journal. If present, all journal
@@ -778,21 +808,18 @@
*/
wait_queue_head_t j_wait_transaction_locked;
- /* Wait queue for waiting for checkpointing to complete */
- wait_queue_head_t j_wait_logspace;
-
/* Wait queue for waiting for commit to complete */
wait_queue_head_t j_wait_done_commit;
- /* Wait queue to trigger checkpointing */
- wait_queue_head_t j_wait_checkpoint;
-
/* Wait queue to trigger commit */
wait_queue_head_t j_wait_commit;
/* Wait queue to wait for updates to complete */
wait_queue_head_t j_wait_updates;
+ /* Wait queue to wait for reserved buffer credits to drop */
+ wait_queue_head_t j_wait_reserved;
+
/* Semaphore for locking against concurrent checkpoints */
struct mutex j_checkpoint_mutex;
@@ -847,6 +874,9 @@
/* Total maximum capacity of the journal region on disk. */
unsigned int j_maxlen;
+ /* Number of buffers reserved from the running transaction */
+ atomic_t j_reserved_credits;
+
/*
* Protects the buffer lists and internal buffer state.
*/
@@ -992,9 +1022,17 @@
extern void __journal_free_buffer(struct journal_head *bh);
extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
extern void __journal_clean_data_list(transaction_t *transaction);
+static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh)
+{
+ list_add_tail(&bh->b_assoc_buffers, head);
+}
+static inline void jbd2_unfile_log_bh(struct buffer_head *bh)
+{
+ list_del_init(&bh->b_assoc_buffers);
+}
/* Log buffer allocation */
-extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *);
+struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal);
int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
unsigned long *block);
@@ -1005,7 +1043,7 @@
extern void jbd2_journal_commit_transaction(journal_t *);
/* Checkpoint list management */
-int __jbd2_journal_clean_checkpoint_list(journal_t *journal);
+void __jbd2_journal_clean_checkpoint_list(journal_t *journal);
int __jbd2_journal_remove_checkpoint(struct journal_head *);
void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
@@ -1040,11 +1078,10 @@
struct jbd2_buffer_trigger_type *triggers);
/* Buffer IO */
-extern int
-jbd2_journal_write_metadata_buffer(transaction_t *transaction,
- struct journal_head *jh_in,
- struct journal_head **jh_out,
- unsigned long long blocknr);
+extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
+ struct journal_head *jh_in,
+ struct buffer_head **bh_out,
+ sector_t blocknr);
/* Transaction locking */
extern void __wait_on_journal (journal_t *);
@@ -1077,10 +1114,14 @@
*/
extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
-extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask,
- unsigned int type, unsigned int line_no);
+extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks,
+ gfp_t gfp_mask, unsigned int type,
+ unsigned int line_no);
extern int jbd2_journal_restart(handle_t *, int nblocks);
extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask);
+extern int jbd2_journal_start_reserved(handle_t *handle,
+ unsigned int type, unsigned int line_no);
+extern void jbd2_journal_free_reserved(handle_t *handle);
extern int jbd2_journal_extend (handle_t *, int nblocks);
extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
@@ -1091,7 +1132,7 @@
extern int jbd2_journal_forget (handle_t *, struct buffer_head *);
extern void journal_sync_buffer (struct buffer_head *);
extern int jbd2_journal_invalidatepage(journal_t *,
- struct page *, unsigned long);
+ struct page *, unsigned int, unsigned int);
extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
extern int jbd2_journal_stop(handle_t *);
extern int jbd2_journal_flush (journal_t *);
@@ -1126,6 +1167,7 @@
extern int jbd2_journal_clear_err (journal_t *);
extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
extern int jbd2_journal_force_commit(journal_t *);
+extern int jbd2_journal_force_commit_nested(journal_t *);
extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
extern int jbd2_journal_begin_ordered_truncate(journal_t *journal,
struct jbd2_inode *inode, loff_t new_size);
@@ -1179,8 +1221,10 @@
extern void jbd2_journal_destroy_revoke(journal_t *);
extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
-extern void jbd2_journal_write_revoke_records(journal_t *,
- transaction_t *, int);
+extern void jbd2_journal_write_revoke_records(journal_t *journal,
+ transaction_t *transaction,
+ struct list_head *log_bufs,
+ int write_op);
/* Recovery revoke support */
extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);
@@ -1196,11 +1240,9 @@
* transitions on demand.
*/
-int __jbd2_log_space_left(journal_t *); /* Called with journal locked */
int jbd2_log_start_commit(journal_t *journal, tid_t tid);
int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
-int jbd2_journal_force_commit_nested(journal_t *journal);
int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
int jbd2_complete_transaction(journal_t *journal, tid_t tid);
int jbd2_log_do_checkpoint(journal_t *journal);
@@ -1236,7 +1278,7 @@
static inline int is_handle_aborted(handle_t *handle)
{
- if (handle->h_aborted)
+ if (handle->h_aborted || !handle->h_transaction)
return 1;
return is_journal_aborted(handle->h_transaction->t_journal);
}
@@ -1266,17 +1308,47 @@
extern int jbd2_journal_blocks_per_page(struct inode *inode);
extern size_t journal_tag_bytes(journal_t *journal);
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+ JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+ return 1;
+
+ return 0;
+}
+
+/*
+ * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
+ * transaction control blocks.
+ */
+#define JBD2_CONTROL_BLOCKS_SHIFT 5
+
/*
* Return the minimum number of blocks which must be free in the journal
* before a new transaction may be started. Must be called under j_state_lock.
*/
-static inline int jbd_space_needed(journal_t *journal)
+static inline int jbd2_space_needed(journal_t *journal)
{
int nblocks = journal->j_max_transaction_buffers;
- if (journal->j_committing_transaction)
- nblocks += atomic_read(&journal->j_committing_transaction->
- t_outstanding_credits);
- return nblocks;
+ return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT);
+}
+
+/*
+ * Return number of free blocks in the log. Must be called under j_state_lock.
+ */
+static inline unsigned long jbd2_log_space_left(journal_t *journal)
+{
+ /* Allow for rounding errors */
+ unsigned long free = journal->j_free - 32;
+
+ if (journal->j_committing_transaction) {
+ unsigned long committing = atomic_read(&journal->
+ j_committing_transaction->t_outstanding_credits);
+
+ /* Transaction + control blocks */
+ free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT);
+ }
+ return free;
}
/*
@@ -1287,11 +1359,9 @@
#define BJ_None 0 /* Not journaled */
#define BJ_Metadata 1 /* Normal journaled metadata */
#define BJ_Forget 2 /* Buffer superseded by this transaction */
-#define BJ_IO 3 /* Buffer is for temporary IO use */
-#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */
-#define BJ_LogCtl 5 /* Buffer contains log descriptors */
-#define BJ_Reserved 6 /* Buffer is reserved for access by journal */
-#define BJ_Types 7
+#define BJ_Shadow 3 /* Buffer contents being shadowed to the log */
+#define BJ_Reserved 4 /* Buffer is reserved for access by journal */
+#define BJ_Types 5
extern int jbd_blocks_per_page(struct inode *inode);
@@ -1320,6 +1390,19 @@
return *(u32 *)desc.ctx;
}
+/* Return most recent uncommitted transaction */
+static inline tid_t jbd2_get_latest_transaction(journal_t *journal)
+{
+ tid_t tid;
+
+ read_lock(&journal->j_state_lock);
+ tid = journal->j_commit_request;
+ if (journal->j_running_transaction)
+ tid = journal->j_running_transaction->t_tid;
+ read_unlock(&journal->j_state_lock);
+ return tid;
+}
+
#ifdef __KERNEL__
#define buffer_trace_init(bh) do {} while (0)
diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h
index 6133679..3dc5343 100644
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -1,31 +1,7 @@
#ifndef _LINUX_JBD_STATE_H
#define _LINUX_JBD_STATE_H
-enum jbd_state_bits {
- BH_JBD /* Has an attached ext3 journal_head */
- = BH_PrivateStart,
- BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
- BH_Freed, /* Has been freed (truncated) */
- BH_Revoked, /* Has been revoked from the log */
- BH_RevokeValid, /* Revoked flag is valid */
- BH_JBDDirty, /* Is dirty but journaled */
- BH_State, /* Pins most journal_head state */
- BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
- BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */
- BH_Verified, /* Metadata block has been verified ok */
- BH_JBDPrivateStart, /* First bit available for private use by FS */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-BUFFER_FNS(Verified, verified)
+#include <linux/bit_spinlock.h>
static inline struct buffer_head *jh2bh(struct journal_head *jh)
{
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5f4554b..089774b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -805,4 +805,7 @@
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
#endif
+/* To identify board information in panic logs, set this */
+extern char *mach_panic_string;
+
#endif
diff --git a/include/linux/key.h b/include/linux/key.h
index 4dfde11..b2752c3 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -72,6 +72,15 @@
#define KEY_PERM_UNDEF 0xffffffff
+/* New permission defines for backport */
+#define KEY_NEED_VIEW 0x01 /* Require permission to view attributes */
+#define KEY_NEED_READ 0x02 /* Require permission to read content */
+#define KEY_NEED_WRITE 0x04 /* Require permission to update / modify */
+#define KEY_NEED_SEARCH 0x08 /* Require permission to search (keyring) or find (key) */
+#define KEY_NEED_LINK 0x10 /* Require permission to link */
+#define KEY_NEED_SETATTR 0x20 /* Require permission to change attributes */
+#define KEY_NEED_ALL 0x3f /* All the above permissions */
+
struct seq_file;
struct user_struct;
struct signal_struct;
diff --git a/include/linux/keychord.h b/include/linux/keychord.h
new file mode 100644
index 0000000..08cf540
--- /dev/null
+++ b/include/linux/keychord.h
@@ -0,0 +1,23 @@
+/*
+ * Key chord input driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef __LINUX_KEYCHORD_H_
+#define __LINUX_KEYCHORD_H_
+
+#include <uapi/linux/keychord.h>
+
+#endif /* __LINUX_KEYCHORD_H_ */
diff --git a/include/linux/keycombo.h b/include/linux/keycombo.h
new file mode 100644
index 0000000..c6db262
--- /dev/null
+++ b/include/linux/keycombo.h
@@ -0,0 +1,36 @@
+/*
+ * include/linux/keycombo.h - platform data structure for keycombo driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYCOMBO_H
+#define _LINUX_KEYCOMBO_H
+
+#define KEYCOMBO_NAME "keycombo"
+
+/*
+ * if key_down_fn and key_up_fn are both present, you are guaranteed that
+ * key_down_fn will return before key_up_fn is called, and that key_up_fn
+ * is called iff key_down_fn is called.
+ */
+struct keycombo_platform_data {
+ void (*key_down_fn)(void *);
+ void (*key_up_fn)(void *);
+ void *priv;
+ int key_down_delay; /* Time in ms */
+ int *keys_up;
+ int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYCOMBO_H */
diff --git a/include/linux/keyreset.h b/include/linux/keyreset.h
new file mode 100644
index 0000000..2e34afa
--- /dev/null
+++ b/include/linux/keyreset.h
@@ -0,0 +1,29 @@
+/*
+ * include/linux/keyreset.h - platform data structure for resetkeys driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYRESET_H
+#define _LINUX_KEYRESET_H
+
+#define KEYRESET_NAME "keyreset"
+
+struct keyreset_platform_data {
+ int (*reset_fn)(void);
+ int key_down_delay;
+ int *keys_up;
+ int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYRESET_H */
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 1cc89e9..ffb9c9d 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -40,6 +40,11 @@
} fam;
};
+struct lsm_ioctlop_audit {
+ struct path path;
+ u16 cmd;
+};
+
/* Auxiliary data to use in generating the audit record. */
struct common_audit_data {
char type;
@@ -53,6 +58,7 @@
#define LSM_AUDIT_DATA_KMOD 8
#define LSM_AUDIT_DATA_INODE 9
#define LSM_AUDIT_DATA_DENTRY 10
+#define LSM_AUDIT_DATA_IOCTL_OP 11
union {
struct path path;
struct dentry *dentry;
@@ -68,6 +74,7 @@
} key_struct;
#endif
char *kmod_name;
+ struct lsm_ioctlop_audit *op;
} u;
/* this union contains LSM specific data */
union {
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
new file mode 100644
index 0000000..4356686
--- /dev/null
+++ b/include/linux/lz4.h
@@ -0,0 +1,87 @@
+#ifndef __LZ4_H__
+#define __LZ4_H__
+/*
+ * LZ4 Kernel Interface
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define LZ4_MEM_COMPRESS (4096 * sizeof(unsigned char *))
+#define LZ4HC_MEM_COMPRESS (65538 * sizeof(unsigned char *))
+
+/*
+ * lz4_compressbound()
+ * Provides the maximum size that LZ4 may output in a "worst case" scenario
+ * (input data not compressible)
+ */
+static inline size_t lz4_compressbound(size_t isize)
+{
+ return isize + (isize / 255) + 16;
+}
+
+/*
+ * lz4_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+ /*
+ * lz4hc_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+/*
+ * lz4_decompress()
+ * src : source address of the compressed data
+ * src_len : is the input size, whcih is returned after decompress done
+ * dest : output buffer address of the decompressed data
+ * actual_dest_len: is the size of uncompressed data, supposing it's known
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ * slightly faster than lz4_decompress_unknownoutputsize()
+ */
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len);
+
+/*
+ * lz4_decompress_unknownoutputsize()
+ * src : source address of the compressed data
+ * src_len : is the input size, therefore the compressed size
+ * dest : output buffer address of the decompressed data
+ * dest_len: is the max size of the destination buffer, which is
+ * returned with actual size of decompressed data after
+ * decompress done
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ */
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len);
+#endif
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 2913b86..69ed5f5 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -31,6 +31,15 @@
}
/**
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
+ */
+static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+ *remainder = dividend % divisor;
+ return dividend / divisor;
+}
+
+/**
* div64_u64 - unsigned 64bit divide with 64bit divisor
*/
static inline u64 div64_u64(u64 dividend, u64 divisor)
@@ -63,6 +72,10 @@
extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder);
#endif
+#ifndef div64_u64_rem
+extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder);
+#endif
+
#ifndef div64_u64
extern u64 div64_u64(u64 dividend, u64 divisor);
#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 53b0d70..3ac54d0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -40,6 +40,17 @@
#define sysctl_legacy_va_layout 0
#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+extern const int mmap_rnd_bits_min;
+extern const int mmap_rnd_bits_max;
+extern int mmap_rnd_bits __read_mostly;
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+extern const int mmap_rnd_compat_bits_min;
+extern const int mmap_rnd_compat_bits_max;
+extern int mmap_rnd_compat_bits __read_mostly;
+#endif
+
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -325,6 +336,8 @@
}
#endif
+extern void kvfree(const void *addr);
+
static inline void compound_lock(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -923,6 +936,7 @@
extern void show_free_areas(unsigned int flags);
extern bool skip_free_areas_node(unsigned int flags, int nid);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file);
int shmem_zero_setup(struct vm_area_struct *);
extern int can_do_mlock(void);
@@ -1057,7 +1071,8 @@
struct page *get_dump_page(unsigned long addr);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
-extern void do_invalidatepage(struct page *page, unsigned long offset);
+extern void do_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length);
int __set_page_dirty_nobuffers(struct page *page);
int __set_page_dirty_no_writeback(struct page *page);
@@ -1179,6 +1194,11 @@
mm->hiwater_vm = mm->total_vm;
}
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+ mm->hiwater_rss = get_mm_rss(mm);
+}
+
static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
struct mm_struct *mm)
{
@@ -1501,7 +1521,7 @@
extern struct vm_area_struct *vma_merge(struct mm_struct *,
struct vm_area_struct *prev, unsigned long addr, unsigned long end,
unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
- struct mempolicy *);
+ struct mempolicy *, const char __user *);
extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
extern int split_vma(struct mm_struct *,
struct vm_area_struct *, unsigned long addr, int new_below);
@@ -1838,6 +1858,12 @@
static inline bool page_is_guard(struct page *page) { return false; }
#endif /* CONFIG_DEBUG_PAGEALLOC */
+/* 3.18 backport */
+static inline void truncate_inode_pages_final(struct address_space *mapping)
+{
+ truncate_inode_pages(mapping, 0);
+}
+
#if MAX_NUMNODES > 1
void __init setup_nr_node_ids(void);
#else
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 10a9a17..5911ae6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -255,6 +255,10 @@
* For areas with an address space and backing store,
* linkage into the address_space->i_mmap interval tree, or
* linkage of vma in the address_space->i_mmap_nonlinear list.
+ *
+ * For private anonymous mappings, a pointer to a null terminated string
+ * in the user process containing the name given to the vma, or NULL
+ * if unnamed.
*/
union {
struct {
@@ -262,6 +266,7 @@
unsigned long rb_subtree_last;
} linear;
struct list_head nonlinear;
+ const char __user *anon_name;
} shared;
/*
@@ -465,6 +470,15 @@
return mm->cpu_vm_mask_var;
}
+/* Return the name for an anonymous mapping or NULL for a file-backed mapping */
+static inline const char __user *vma_get_anon_name(struct vm_area_struct *vma)
+{
+ if (vma->vm_file)
+ return NULL;
+
+ return vma->shared.anon_name;
+}
+
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
/*
* Memory barriers to keep this state in sync are graciously provided by
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index f31725b..6a5c754 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -512,6 +512,7 @@
void (*remove)(struct mmc_card *);
int (*suspend)(struct mmc_card *);
int (*resume)(struct mmc_card *);
+ void (*shutdown)(struct mmc_card *);
};
extern int mmc_register_driver(struct mmc_driver *);
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 39613b9..4392c9a 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -133,6 +133,8 @@
struct completion completion;
void (*done)(struct mmc_request *);/* completion function */
struct mmc_host *host;
+ ktime_t io_start;
+ int lat_hist_enabled;
};
struct mmc_card;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index e326ae2..da4e745 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -15,6 +15,7 @@
#include <linux/sched.h>
#include <linux/device.h>
#include <linux/fault-inject.h>
+#include <linux/wakelock.h>
#include <linux/mmc/core.h>
#include <linux/mmc/pm.h>
@@ -195,6 +196,35 @@
struct regulator *vqmmc; /* Optional Vccq supply */
};
+/*
+ * X-axis for IO latency histogram support.
+ */
+static const u_int64_t latency_x_axis_us[] = {
+ 100,
+ 200,
+ 300,
+ 400,
+ 500,
+ 600,
+ 700,
+ 800,
+ 900,
+ 1000,
+ 1200,
+ 1400,
+ 1600,
+ 1800,
+ 2000,
+ 2500,
+ 3000,
+ 4000,
+ 5000,
+ 6000,
+ 7000,
+ 9000,
+ 10000
+};
+
struct mmc_host {
struct device *parent;
struct device class_dev;
@@ -264,7 +294,7 @@
#define MMC_CAP2_BOOTPART_NOACC (1 << 0) /* Boot partition no access */
#define MMC_CAP2_CACHE_CTRL (1 << 1) /* Allow cache control */
-#define MMC_CAP2_POWEROFF_NOTIFY (1 << 2) /* Notify poweroff supported */
+#define MMC_CAP2_FULL_PWR_CYCLE (1 << 2) /* Can do full power cycle */
#define MMC_CAP2_NO_MULTI_READ (1 << 3) /* Multiblock reads don't work */
#define MMC_CAP2_NO_SLEEP_CMD (1 << 4) /* Don't allow sleep command */
#define MMC_CAP2_HS200_1_8V_SDR (1 << 5) /* can support */
@@ -329,12 +359,17 @@
int claim_cnt; /* "claim" nesting count */
struct delayed_work detect;
+ struct wake_lock detect_wake_lock;
int detect_change; /* card detect flag */
struct mmc_slot slot;
const struct mmc_bus_ops *bus_ops; /* current bus driver */
unsigned int bus_refs; /* reference counter */
+ unsigned int bus_resume_flags;
+#define MMC_BUSRESUME_MANUAL_RESUME (1 << 0)
+#define MMC_BUSRESUME_NEEDS_RESUME (1 << 1)
+
unsigned int sdio_irqs;
struct task_struct *sdio_irq_thread;
bool sdio_irq_pending;
@@ -362,6 +397,24 @@
unsigned int slotno; /* used for sdio acpi binding */
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ struct {
+ struct sdio_cis *cis;
+ struct sdio_cccr *cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+ } embedded_sdio_data;
+#endif
+
+#define MMC_IO_LAT_HIST_DISABLE 0
+#define MMC_IO_LAT_HIST_ENABLE 1
+#define MMC_IO_LAT_HIST_ZERO 2
+ int latency_hist_enabled;
+ u_int64_t latency_y_axis_read[ARRAY_SIZE(latency_x_axis_us) + 1];
+ u_int64_t latency_reads_elems;
+ u_int64_t latency_y_axis_write[ARRAY_SIZE(latency_x_axis_us) + 1];
+ u_int64_t latency_writes_elems;
+
unsigned long private[0] ____cacheline_aligned;
};
@@ -371,6 +424,14 @@
void mmc_free_host(struct mmc_host *);
void mmc_of_parse(struct mmc_host *host);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+extern void mmc_set_embedded_sdio_data(struct mmc_host *host,
+ struct sdio_cis *cis,
+ struct sdio_cccr *cccr,
+ struct sdio_embedded_func *funcs,
+ int num_funcs);
+#endif
+
static inline void *mmc_priv(struct mmc_host *host)
{
return (void *)host->private;
@@ -381,6 +442,18 @@
#define mmc_dev(x) ((x)->parent)
#define mmc_classdev(x) (&(x)->class_dev)
#define mmc_hostname(x) (dev_name(&(x)->class_dev))
+#define mmc_bus_needs_resume(host) ((host)->bus_resume_flags & MMC_BUSRESUME_NEEDS_RESUME)
+#define mmc_bus_manual_resume(host) ((host)->bus_resume_flags & MMC_BUSRESUME_MANUAL_RESUME)
+
+static inline void mmc_set_bus_resume_policy(struct mmc_host *host, int manual)
+{
+ if (manual)
+ host->bus_resume_flags |= MMC_BUSRESUME_MANUAL_RESUME;
+ else
+ host->bus_resume_flags &= ~MMC_BUSRESUME_MANUAL_RESUME;
+}
+
+extern int mmc_resume_bus(struct mmc_host *host);
int mmc_suspend_host(struct mmc_host *);
int mmc_resume_host(struct mmc_host *);
@@ -391,8 +464,6 @@
void mmc_detect_change(struct mmc_host *, unsigned long delay);
void mmc_request_done(struct mmc_host *, struct mmc_request *);
-int mmc_cache_ctrl(struct mmc_host *, u8);
-
static inline void mmc_signal_sdio_irq(struct mmc_host *host)
{
host->ops->enable_sdio_irq(host, 0);
diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h
index 4a13920..6e2d6a1 100644
--- a/include/linux/mmc/pm.h
+++ b/include/linux/mmc/pm.h
@@ -26,5 +26,6 @@
#define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */
#define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */
+#define MMC_PM_IGNORE_PM_NOTIFY (1 << 2) /* ignore mmc pm notify */
#endif /* LINUX_MMC_PM_H */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
old mode 100644
new mode 100755
index 50f0bc9..dc680c4
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -23,6 +23,14 @@
typedef void (sdio_irq_handler_t)(struct sdio_func *);
/*
+ * Structure used to hold embedded SDIO device data from platform layer
+ */
+struct sdio_embedded_func {
+ uint8_t f_class;
+ uint32_t f_maxblksize;
+};
+
+/*
* SDIO function CIS tuple (unknown to the core)
*/
struct sdio_func_tuple {
@@ -130,6 +138,8 @@
extern unsigned int sdio_align_size(struct sdio_func *func, unsigned int sz);
extern u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret);
+extern u8 sdio_readb_ext(struct sdio_func *func, unsigned int addr, int *err_ret,
+ unsigned in);
extern u16 sdio_readw(struct sdio_func *func, unsigned int addr, int *err_ret);
extern u32 sdio_readl(struct sdio_func *func, unsigned int addr, int *err_ret);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5c76737..17aba3d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -773,10 +773,10 @@
extern struct mutex zonelists_mutex;
void build_all_zonelists(pg_data_t *pgdat, struct zone *zone);
void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
-bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags);
+bool zone_watermark_ok(struct zone *z, unsigned int order,
+ unsigned long mark, int classzone_idx, int alloc_flags);
+bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
+ unsigned long mark, int classzone_idx, int alloc_flags);
enum memmap_context {
MEMMAP_EARLY,
MEMMAP_HOTPLUG,
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index d313648..d292528 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -569,6 +569,15 @@
#define X86_MODEL_ANY 0
#define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */
+/*
+ * Generic table type for matching CPU features.
+ * @feature: the bit number of the feature (0 - 65535)
+ */
+
+struct cpu_feature {
+ __u16 feature;
+};
+
#define IPACK_ANY_FORMAT 0xff
#define IPACK_ANY_ID (~0)
struct ipack_device_id {
diff --git a/include/linux/netfilter/xt_qtaguid.h b/include/linux/netfilter/xt_qtaguid.h
new file mode 100644
index 0000000..ca60fbd
--- /dev/null
+++ b/include/linux/netfilter/xt_qtaguid.h
@@ -0,0 +1,13 @@
+#ifndef _XT_QTAGUID_MATCH_H
+#define _XT_QTAGUID_MATCH_H
+
+/* For now we just replace the xt_owner.
+ * FIXME: make iptables aware of qtaguid. */
+#include <linux/netfilter/xt_owner.h>
+
+#define XT_QTAGUID_UID XT_OWNER_UID
+#define XT_QTAGUID_GID XT_OWNER_GID
+#define XT_QTAGUID_SOCKET XT_OWNER_SOCKET
+#define xt_qtaguid_match_info xt_owner_match_info
+
+#endif /* _XT_QTAGUID_MATCH_H */
diff --git a/include/linux/netfilter/xt_quota2.h b/include/linux/netfilter/xt_quota2.h
new file mode 100644
index 0000000..eadc690
--- /dev/null
+++ b/include/linux/netfilter/xt_quota2.h
@@ -0,0 +1,25 @@
+#ifndef _XT_QUOTA_H
+#define _XT_QUOTA_H
+
+enum xt_quota_flags {
+ XT_QUOTA_INVERT = 1 << 0,
+ XT_QUOTA_GROW = 1 << 1,
+ XT_QUOTA_PACKET = 1 << 2,
+ XT_QUOTA_NO_CHANGE = 1 << 3,
+ XT_QUOTA_MASK = 0x0F,
+};
+
+struct xt_quota_counter;
+
+struct xt_quota_mtinfo2 {
+ char name[15];
+ u_int8_t flags;
+
+ /* Comparison-invariant */
+ aligned_u64 quota;
+
+ /* Used internally by the kernel */
+ struct xt_quota_counter *master __attribute__((aligned(8)));
+};
+
+#endif /* _XT_QUOTA_H */
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index db50840..c8f8aa0 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -14,8 +14,11 @@
* may be used to reset the timeout - for code which intentionally
* disables interrupts for a long time. This call is stateless.
*/
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR_NMI)
#include <asm/nmi.h>
+#endif
+
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
extern void touch_nmi_watchdog(void);
#else
static inline void touch_nmi_watchdog(void)
diff --git a/include/linux/of.h b/include/linux/of.h
index 5e9d352..9528241 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -354,6 +354,11 @@
return NULL;
}
+static inline struct device_node *of_find_node_by_path(const char *path)
+{
+ return NULL;
+}
+
static inline struct device_node *of_get_parent(const struct device_node *node)
{
return NULL;
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index ed136ad..7e190a9 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -91,6 +91,27 @@
extern int of_flat_dt_match(unsigned long node, const char *const *matches);
extern unsigned long of_get_flat_dt_root(void);
+/*
+ * early_init_dt_scan_chosen - scan the device tree for ramdisk and bootargs
+ *
+ * The boot arguments will be placed into the memory pointed to by @data.
+ * That memory should be COMMAND_LINE_SIZE big and initialized to be a valid
+ * (possibly empty) string. Logic for what will be in @data after this
+ * function finishes:
+ *
+ * - CONFIG_CMDLINE_FORCE=true
+ * CONFIG_CMDLINE
+ * - CONFIG_CMDLINE_EXTEND=true, @data is non-empty string
+ * @data + dt bootargs (even if dt bootargs are empty)
+ * - CONFIG_CMDLINE_EXTEND=true, @data is empty string
+ * CONFIG_CMDLINE + dt bootargs (even if dt bootargs are empty)
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=non-empty:
+ * dt bootargs
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is non-empty string
+ * @data is left unchanged
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is empty string
+ * CONFIG_CMDLINE (or "" if that's not defined)
+ */
extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data);
extern void early_init_dt_check_for_initrd(unsigned long node);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6d53675..dd7d45b 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -317,13 +317,23 @@
extern void cancel_dirty_page(struct page *page, unsigned int account_size);
int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
+int __test_set_page_writeback(struct page *page, bool keep_write);
+
+#define test_set_page_writeback(page) \
+ __test_set_page_writeback(page, false)
+#define test_set_page_writeback_keepwrite(page) \
+ __test_set_page_writeback(page, true)
static inline void set_page_writeback(struct page *page)
{
test_set_page_writeback(page);
}
+static inline void set_page_writeback_keepwrite(struct page *page)
+{
+ test_set_page_writeback_keepwrite(page);
+}
+
#ifdef CONFIG_PAGEFLAGS_EXTENDED
/*
* System with lots of page flags available. This allows separate
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e3dea75..e1dc09d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -243,8 +243,21 @@
typedef int filler_t(void *, struct page *);
-extern struct page * find_get_page(struct address_space *mapping,
- pgoff_t index);
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan);
+
+extern struct page * find_get_page_flags(struct address_space *mapping,
+ pgoff_t index, int fgp_flags);
+
+#define FGP_ACCESSED 0x00000001
+
+static inline struct page* find_get_page(struct address_space *mapping,
+ pgoff_t index)
+{
+ return find_get_page_flags(mapping, index, 0);
+}
+
+
extern struct page * find_lock_page(struct address_space *mapping,
pgoff_t index);
extern struct page * find_or_create_page(struct address_space *mapping,
@@ -391,7 +404,7 @@
return 0;
}
-/*
+/*
* Wait for a page to be unlocked.
*
* This must be called with the caller "holding" the page,
@@ -404,7 +417,7 @@
wait_on_page_bit(page, PG_locked);
}
-/*
+/*
* Wait for a page to complete writeback
*/
static inline void wait_on_page_writeback(struct page *page)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 229a757..1a9b911 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -707,6 +707,11 @@
loff_t *ppos);
+static inline bool perf_paranoid_any(void)
+{
+ return sysctl_perf_event_paranoid > 2;
+}
+
static inline bool perf_paranoid_tracepoint_raw(void)
{
return sysctl_perf_event_paranoid > -1;
diff --git a/include/linux/platform_data/ds2482.h b/include/linux/platform_data/ds2482.h
new file mode 100644
index 0000000..5a6879e2a
--- /dev/null
+++ b/include/linux/platform_data/ds2482.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __PLATFORM_DATA_DS2482__
+#define __PLATFORM_DATA_DS2482__
+
+struct ds2482_platform_data {
+ int slpz_gpio;
+};
+
+#endif /* __PLATFORM_DATA_DS2482__ */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 3828cef..03d921f 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -15,6 +15,7 @@
#include <linux/workqueue.h>
#include <linux/leds.h>
+#include <linux/types.h>
struct device;
@@ -140,6 +141,12 @@
POWER_SUPPLY_PROP_TIME_TO_FULL_AVG,
POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */
POWER_SUPPLY_PROP_SCOPE,
+ /* Local extensions */
+ POWER_SUPPLY_PROP_USB_HC,
+ POWER_SUPPLY_PROP_USB_OTG,
+ POWER_SUPPLY_PROP_CHARGE_ENABLED,
+ /* Local extensions of type int64_t */
+ POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT,
/* Properties of type `const char *' */
POWER_SUPPLY_PROP_MODEL_NAME,
POWER_SUPPLY_PROP_MANUFACTURER,
@@ -160,6 +167,7 @@
union power_supply_propval {
int intval;
const char *strval;
+ int64_t int64val;
};
struct power_supply {
@@ -194,6 +202,8 @@
/* private */
struct device *dev;
struct work_struct changed_work;
+ spinlock_t changed_lock;
+ bool changed;
#ifdef CONFIG_THERMAL
struct thermal_zone_device *tzd;
struct thermal_cooling_device *tcd;
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index 75d0176..2898841 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -35,6 +35,7 @@
PSTORE_TYPE_MCE = 1,
PSTORE_TYPE_CONSOLE = 2,
PSTORE_TYPE_FTRACE = 3,
+ PSTORE_TYPE_PMSG = 4, /* Backport: 7 in upstream 3.19.0-rc3 */
PSTORE_TYPE_UNKNOWN = 255
};
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 4af3fdc..712757f 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -68,6 +68,8 @@
ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
char *str, size_t len);
+void ramoops_console_write_buf(const char *buf, size_t size);
+
/*
* Ramoops platform data
* @mem_size memory size for ramoops
@@ -81,6 +83,7 @@
unsigned long record_size;
unsigned long console_size;
unsigned long ftrace_size;
+ unsigned long pmsg_size;
int dump_oops;
struct persistent_ram_ecc_info ecc_info;
};
diff --git a/include/linux/random.h b/include/linux/random.h
index bf9085e..1b91d7d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -24,6 +24,7 @@
#endif
unsigned int get_random_int(void);
+unsigned long get_random_long(void);
unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
u32 prandom_u32(void);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 0022c1b..aa870a4 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -68,6 +68,10 @@
extern struct rb_node *rb_first(const struct rb_root *);
extern struct rb_node *rb_last(const struct rb_root *);
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
/* Fast replacement of a single node without remove/rebalance/add/rebalance */
extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
struct rb_root *root);
@@ -81,4 +85,22 @@
*rb_link = node;
}
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
+ * given type safe against removal of rb_node entry
+ *
+ * @pos: the 'type *' to use as a loop cursor.
+ * @n: another 'type *' to use as temporary storage
+ * @root: 'rb_root *' of the rbtree.
+ * @field: the name of the rb_node field within 'type'.
+ */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+ for (pos = rb_entry(rb_first_postorder(root), typeof(*pos), field),\
+ n = rb_entry(rb_next_postorder(&pos->field), \
+ typeof(*pos), field); \
+ &pos->field; \
+ pos = n, \
+ n = rb_entry(rb_next_postorder(&pos->field), \
+ typeof(*pos), field))
+
#endif /* _LINUX_RBTREE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7728941..0c16b9f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1124,13 +1124,12 @@
* execve */
unsigned in_iowait:1;
- /* task may not gain privileges */
- unsigned no_new_privs:1;
-
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+ unsigned long atomic_flags; /* Flags needing atomic access. */
+
pid_t pid;
pid_t tgid;
@@ -1171,6 +1170,7 @@
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
+ unsigned long long cpu_power;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
#endif
@@ -1620,6 +1620,9 @@
extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern int task_free_register(struct notifier_block *n);
+extern int task_free_unregister(struct notifier_block *n);
+
/*
* Per process flags
*/
@@ -1700,6 +1703,19 @@
current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}
+/* Per-process atomic flags. */
+#define PFA_NO_NEW_PRIVS 0x00000001 /* May not gain new privileges. */
+
+static inline bool task_no_new_privs(struct task_struct *p)
+{
+ return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
+static inline void task_set_no_new_privs(struct task_struct *p)
+{
+ set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
/*
* task->jobctl flags
*/
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd..9687691 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,6 +3,8 @@
#include <uapi/linux/seccomp.h>
+#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC)
+
#ifdef CONFIG_SECCOMP
#include <linux/thread_info.h>
@@ -14,11 +16,11 @@
*
* @mode: indicates one of the valid values above for controlled
* system calls available to a process.
- * @filter: The metadata and ruleset for determining what system calls
- * are allowed for a task.
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ * accessed without locking during system call entry.
*
* @filter must only be accessed from the context of current as there
- * is no locking.
+ * is no read locking.
*/
struct seccomp {
int mode;
diff --git a/include/linux/security.h b/include/linux/security.h
index 4e50307..afb3d29 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1402,6 +1402,11 @@
struct security_operations {
char name[SECURITY_NAME_MAX + 1];
+ int (*binder_set_context_mgr) (struct task_struct *mgr);
+ int (*binder_transaction) (struct task_struct *from, struct task_struct *to);
+ int (*binder_transfer_binder) (struct task_struct *from, struct task_struct *to);
+ int (*binder_transfer_file) (struct task_struct *from, struct task_struct *to, struct file *file);
+
int (*ptrace_access_check) (struct task_struct *child, unsigned int mode);
int (*ptrace_traceme) (struct task_struct *parent);
int (*capget) (struct task_struct *target,
@@ -1690,6 +1695,10 @@
/* Security operations */
+int security_binder_set_context_mgr(struct task_struct *mgr);
+int security_binder_transaction(struct task_struct *from, struct task_struct *to);
+int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to);
+int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file);
int security_ptrace_access_check(struct task_struct *child, unsigned int mode);
int security_ptrace_traceme(struct task_struct *parent);
int security_capget(struct task_struct *target,
@@ -1869,6 +1878,26 @@
return 0;
}
+static inline int security_binder_set_context_mgr(struct task_struct *mgr)
+{
+ return 0;
+}
+
+static inline int security_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+ return 0;
+}
+
+static inline int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+ return 0;
+}
+
+static inline int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+ return 0;
+}
+
static inline int security_ptrace_access_check(struct task_struct *child,
unsigned int mode)
{
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 87d4bbc..a782f3c 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -60,6 +60,7 @@
void (*pm)(struct uart_port *, unsigned int state,
unsigned int oldstate);
int (*set_wake)(struct uart_port *, unsigned int state);
+ void (*wake_peer)(struct uart_port *);
/*
* Return a string describing the type of the port
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 46cca4c..1a3b383 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -11,6 +11,7 @@
struct sock_diag_handler {
__u8 family;
int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh);
+ int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh);
};
int sock_diag_register(const struct sock_diag_handler *h);
@@ -26,4 +27,5 @@
int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype);
+int sock_diag_destroy(struct sock *sk, int err);
#endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 0ed878d..210cb16 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -111,6 +111,7 @@
extern void * memchr(const void *,int,__kernel_size_t);
#endif
void *memchr_inv(const void *s, int c, size_t n);
+char *strreplace(char *s, char old, char new);
extern char *kstrdup(const char *s, gfp_t gfp);
extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index d4e3f16..a348213 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -363,7 +363,7 @@
extern bool pm_get_wakeup_count(unsigned int *count, bool block);
extern bool pm_save_wakeup_count(unsigned int count);
extern void pm_wakep_autosleep_enabled(bool set);
-
+extern void pm_get_active_wakeup_sources(char *pending_sources, size_t max);
static inline void lock_system_sleep(void)
{
current->flags |= PF_FREEZER_SKIP;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 1701ce4..d11f6c8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -389,6 +389,7 @@
extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
extern int page_swapcount(struct page *);
+extern int swp_swapcount(swp_entry_t entry);
extern struct swap_info_struct *page_swap_info(struct page *);
extern int reuse_swap_page(struct page *);
extern int try_to_free_swap(struct page *);
@@ -489,6 +490,11 @@
return 0;
}
+static inline int swp_swapcount(swp_entry_t entry)
+{
+ return 0;
+}
+
#define reuse_swap_page(page) (page_mapcount(page) == 1)
static inline int try_to_free_swap(struct page *page)
diff --git a/include/linux/switch.h b/include/linux/switch.h
new file mode 100644
index 0000000..3e4c748
--- /dev/null
+++ b/include/linux/switch.h
@@ -0,0 +1,53 @@
+/*
+ * Switch class driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef __LINUX_SWITCH_H__
+#define __LINUX_SWITCH_H__
+
+struct switch_dev {
+ const char *name;
+ struct device *dev;
+ int index;
+ int state;
+
+ ssize_t (*print_name)(struct switch_dev *sdev, char *buf);
+ ssize_t (*print_state)(struct switch_dev *sdev, char *buf);
+};
+
+struct gpio_switch_platform_data {
+ const char *name;
+ unsigned gpio;
+
+ /* if NULL, switch_dev.name will be printed */
+ const char *name_on;
+ const char *name_off;
+ /* if NULL, "0" or "1" will be printed */
+ const char *state_on;
+ const char *state_off;
+};
+
+extern int switch_dev_register(struct switch_dev *sdev);
+extern void switch_dev_unregister(struct switch_dev *sdev);
+
+static inline int switch_get_state(struct switch_dev *sdev)
+{
+ return sdev->state;
+}
+
+extern void switch_set_state(struct switch_dev *sdev, int state);
+
+#endif /* __LINUX_SWITCH_H__ */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e1bc430..988ad05 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -183,6 +183,7 @@
__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
#define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
+#if !defined(__i386) && !defined(__amd64__)
#define __SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
@@ -195,6 +196,21 @@
} \
SYSCALL_ALIAS(sys##name, SyS##name); \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+#else
+#define __SYSCALL_DEFINEx(x, name, ...) \
+ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ { \
+ long ret; \
+ ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
+ return ret; \
+ } \
+ SYSCALL_ALIAS(sys##name, SyS##name); \
+ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+#endif
asmlinkage long sys_time(time_t __user *tloc);
asmlinkage long sys_stime(time_t __user *tptr);
@@ -846,4 +862,6 @@
asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
unsigned long idx1, unsigned long idx2);
asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
+asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs);
#endif
diff --git a/include/linux/uid_stat.h b/include/linux/uid_stat.h
new file mode 100644
index 0000000..6bd6c4e
--- /dev/null
+++ b/include/linux/uid_stat.h
@@ -0,0 +1,29 @@
+/* include/linux/uid_stat.h
+ *
+ * Copyright (C) 2008-2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __uid_stat_h
+#define __uid_stat_h
+
+/* Contains definitions for resource tracking per uid. */
+
+#ifdef CONFIG_UID_STAT
+int uid_stat_tcp_snd(uid_t uid, int size);
+int uid_stat_tcp_rcv(uid_t uid, int size);
+#else
+#define uid_stat_tcp_snd(uid, size) do {} while (0);
+#define uid_stat_tcp_rcv(uid, size) do {} while (0);
+#endif
+
+#endif /* _LINUX_UID_STAT_H */
diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h
new file mode 100644
index 0000000..af42ed3
--- /dev/null
+++ b/include/linux/usb/class-dual-role.h
@@ -0,0 +1,128 @@
+#ifndef __LINUX_CLASS_DUAL_ROLE_H__
+#define __LINUX_CLASS_DUAL_ROLE_H__
+
+#include <linux/workqueue.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device;
+
+enum dual_role_supported_modes {
+ DUAL_ROLE_SUPPORTED_MODES_DFP_AND_UFP = 0,
+ DUAL_ROLE_SUPPORTED_MODES_DFP,
+ DUAL_ROLE_SUPPORTED_MODES_UFP,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_MODE_UFP = 0,
+ DUAL_ROLE_PROP_MODE_DFP,
+ DUAL_ROLE_PROP_MODE_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_MODE_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_PR_SRC = 0,
+ DUAL_ROLE_PROP_PR_SNK,
+ DUAL_ROLE_PROP_PR_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_PR_TOTAL,
+
+};
+
+enum {
+ DUAL_ROLE_PROP_DR_HOST = 0,
+ DUAL_ROLE_PROP_DR_DEVICE,
+ DUAL_ROLE_PROP_DR_NONE,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_DR_TOTAL,
+};
+
+enum {
+ DUAL_ROLE_PROP_VCONN_SUPPLY_NO = 0,
+ DUAL_ROLE_PROP_VCONN_SUPPLY_YES,
+/*The following should be the last element*/
+ DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL,
+};
+
+enum dual_role_property {
+ DUAL_ROLE_PROP_SUPPORTED_MODES = 0,
+ DUAL_ROLE_PROP_MODE,
+ DUAL_ROLE_PROP_PR,
+ DUAL_ROLE_PROP_DR,
+ DUAL_ROLE_PROP_VCONN_SUPPLY,
+};
+
+struct dual_role_phy_instance;
+
+/* Description of typec port */
+struct dual_role_phy_desc {
+ /* /sys/class/dual_role_usb/<name>/ */
+ const char *name;
+ enum dual_role_supported_modes supported_modes;
+ enum dual_role_property *properties;
+ size_t num_properties;
+
+ /* Callback for "cat /sys/class/dual_role_usb/<name>/<property>" */
+ int (*get_property)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val);
+ /* Callback for "echo <value> >
+ * /sys/class/dual_role_usb/<name>/<property>" */
+ int (*set_property)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val);
+ /* Decides whether userspace can change a specific property */
+ int (*property_is_writeable)(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop);
+};
+
+struct dual_role_phy_instance {
+ const struct dual_role_phy_desc *desc;
+
+ /* Driver private data */
+ void *drv_data;
+
+ struct device dev;
+ struct work_struct changed_work;
+};
+
+#if IS_ENABLED(CONFIG_DUAL_ROLE_USB_INTF)
+extern void dual_role_instance_changed(struct dual_role_phy_instance
+ *dual_role);
+extern struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc);
+extern void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role);
+extern int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ unsigned int *val);
+extern int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+ enum dual_role_property prop,
+ const unsigned int *val);
+extern int dual_role_property_is_writeable(struct dual_role_phy_instance
+ *dual_role,
+ enum dual_role_property prop);
+extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role);
+#else /* CONFIG_DUAL_ROLE_USB_INTF */
+static void dual_role_instance_changed(struct dual_role_phy_instance
+ *dual_role){}
+static struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+ const struct dual_role_phy_desc *desc)
+{
+ return ERR_PTR(-ENOSYS);
+}
+static void devm_dual_role_instance_unregister(struct device *dev,
+ struct dual_role_phy_instance
+ *dual_role){}
+static void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role)
+{
+ return ERR_PTR(-ENOSYS);
+}
+#endif /* CONFIG_DUAL_ROLE_USB_INTF */
+#endif /* __LINUX_CLASS_DUAL_ROLE_H__ */
diff --git a/include/linux/usb/f_accessory.h b/include/linux/usb/f_accessory.h
new file mode 100644
index 0000000..ebe3c4d
--- /dev/null
+++ b/include/linux/usb/f_accessory.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_ACCESSORY_H
+#define __LINUX_USB_F_ACCESSORY_H
+
+#include <uapi/linux/usb/f_accessory.h>
+
+#endif /* __LINUX_USB_F_ACCESSORY_H */
diff --git a/include/linux/usb/f_mtp.h b/include/linux/usb/f_mtp.h
new file mode 100644
index 0000000..4e84177
--- /dev/null
+++ b/include/linux/usb/f_mtp.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_MTP_H
+#define __LINUX_USB_F_MTP_H
+
+#include <uapi/linux/usb/f_mtp.h>
+
+#endif /* __LINUX_USB_F_MTP_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index c8e5760..569d33b6 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -959,5 +959,33 @@
return 0;
return out_of_line_wait_on_bit_lock(word, bit, action, mode);
}
-
+
+/* 3.18 backport */
+extern int bit_wait_io(void *);
+
+/**
+ * wait_on_bit_io - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared. This is similar to wait_on_bit(), but calls
+ * io_schedule() instead of schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_io(void *word, int bit, unsigned mode)
+{
+ might_sleep();
+ if (!test_bit(bit, word))
+ return 0;
+ return out_of_line_wait_on_bit(word, bit,
+ bit_wait_io,
+ mode);
+}
+
#endif
diff --git a/include/linux/wakelock.h b/include/linux/wakelock.h
new file mode 100644
index 0000000..f4a698a
--- /dev/null
+++ b/include/linux/wakelock.h
@@ -0,0 +1,67 @@
+/* include/linux/wakelock.h
+ *
+ * Copyright (C) 2007-2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_WAKELOCK_H
+#define _LINUX_WAKELOCK_H
+
+#include <linux/ktime.h>
+#include <linux/device.h>
+
+/* A wake_lock prevents the system from entering suspend or other low power
+ * states when active. If the type is set to WAKE_LOCK_SUSPEND, the wake_lock
+ * prevents a full system suspend.
+ */
+
+enum {
+ WAKE_LOCK_SUSPEND, /* Prevent suspend */
+ WAKE_LOCK_TYPE_COUNT
+};
+
+struct wake_lock {
+ struct wakeup_source ws;
+};
+
+static inline void wake_lock_init(struct wake_lock *lock, int type,
+ const char *name)
+{
+ wakeup_source_init(&lock->ws, name);
+}
+
+static inline void wake_lock_destroy(struct wake_lock *lock)
+{
+ wakeup_source_trash(&lock->ws);
+}
+
+static inline void wake_lock(struct wake_lock *lock)
+{
+ __pm_stay_awake(&lock->ws);
+}
+
+static inline void wake_lock_timeout(struct wake_lock *lock, long timeout)
+{
+ __pm_wakeup_event(&lock->ws, jiffies_to_msecs(timeout));
+}
+
+static inline void wake_unlock(struct wake_lock *lock)
+{
+ __pm_relax(&lock->ws);
+}
+
+static inline int wake_lock_active(struct wake_lock *lock)
+{
+ return lock->ws.active;
+}
+
+#endif
diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h
new file mode 100644
index 0000000..ad8b769
--- /dev/null
+++ b/include/linux/wakeup_reason.h
@@ -0,0 +1,27 @@
+/*
+ * include/linux/wakeup_reason.h
+ *
+ * Logs the reason which caused the kernel to resume
+ * from the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_WAKEUP_REASON_H
+#define _LINUX_WAKEUP_REASON_H
+
+#define MAX_SUSPEND_ABORT_LEN 256
+
+void log_wakeup_reason(int irq);
+void log_suspend_abort_reason(const char *fmt, ...);
+int check_wakeup_reason(int irq);
+
+#endif /* _LINUX_WAKEUP_REASON_H */
diff --git a/include/linux/wifi_tiwlan.h b/include/linux/wifi_tiwlan.h
new file mode 100644
index 0000000..f07e067
--- /dev/null
+++ b/include/linux/wifi_tiwlan.h
@@ -0,0 +1,27 @@
+/* include/linux/wifi_tiwlan.h
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef _LINUX_WIFI_TIWLAN_H_
+#define _LINUX_WIFI_TIWLAN_H_
+
+#include <linux/wlan_plat.h>
+
+#define WMPA_NUMBER_OF_SECTIONS 3
+#define WMPA_NUMBER_OF_BUFFERS 160
+#define WMPA_SECTION_HEADER 24
+#define WMPA_SECTION_SIZE_0 (WMPA_NUMBER_OF_BUFFERS * 64)
+#define WMPA_SECTION_SIZE_1 (WMPA_NUMBER_OF_BUFFERS * 256)
+#define WMPA_SECTION_SIZE_2 (WMPA_NUMBER_OF_BUFFERS * 2048)
+
+#endif
diff --git a/include/linux/wlan_plat.h b/include/linux/wlan_plat.h
new file mode 100644
index 0000000..0607a6e
--- /dev/null
+++ b/include/linux/wlan_plat.h
@@ -0,0 +1,39 @@
+/* include/linux/wlan_plat.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef _LINUX_WLAN_PLAT_H_
+#define _LINUX_WLAN_PLAT_H_
+
+#define WLAN_PLAT_NODFS_FLAG 0x01
+#define WLAN_PLAT_AP_FLAG 0x02
+
+struct wifi_platform_data {
+ int (*set_power)(int val);
+ int (*set_reset)(int val);
+ int (*set_carddetect)(int val);
+ void *(*mem_prealloc)(int section, unsigned long size);
+ int (*get_mac_addr)(unsigned char *buf);
+ int (*get_wake_irq)(void);
+ void *(*get_country_code)(char *ccode, u32 flags);
+#ifdef CONFIG_PARTIALRESUME
+#define WIFI_PR_INIT 0
+#define WIFI_PR_NOTIFY_RESUME 1
+#define WIFI_PR_VOTE_FOR_RESUME 2
+#define WIFI_PR_VOTE_FOR_SUSPEND 3
+#define WIFI_PR_WAIT_FOR_READY 4
+ bool (*partial_resume)(int action);
+#endif
+};
+
+#endif
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 579a500..abfe117 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -78,6 +78,7 @@
unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
+ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
};
/*
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
new file mode 100644
index 0000000..56529b3
--- /dev/null
+++ b/include/linux/zpool.h
@@ -0,0 +1,107 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for the zbud and zsmalloc memory
+ * storage pool implementations. Typically, this is used to
+ * store compressed memory.
+ */
+
+#ifndef _ZPOOL_H_
+#define _ZPOOL_H_
+
+struct zpool;
+
+struct zpool_ops {
+ int (*evict)(struct zpool *pool, unsigned long handle);
+};
+
+/*
+ * Control how a handle is mapped. It will be ignored if the
+ * implementation does not support it. Its use is optional.
+ * Note that this does not refer to memory protection, it
+ * refers to how the memory will be copied in/out if copying
+ * is necessary during mapping; read-write is the safest as
+ * it copies the existing memory in on map, and copies the
+ * changed memory back out on unmap. Write-only does not copy
+ * in the memory and should only be used for initialization.
+ * If in doubt, use ZPOOL_MM_DEFAULT which is read-write.
+ */
+enum zpool_mapmode {
+ ZPOOL_MM_RW, /* normal read-write mapping */
+ ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */
+ ZPOOL_MM_WO, /* write-only (no copy-in at map time) */
+
+ ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
+};
+
+struct zpool *zpool_create_pool(char *type, char *name,
+ gfp_t gfp, struct zpool_ops *ops);
+
+char *zpool_get_type(struct zpool *pool);
+
+void zpool_destroy_pool(struct zpool *pool);
+
+int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp,
+ unsigned long *handle);
+
+void zpool_free(struct zpool *pool, unsigned long handle);
+
+int zpool_shrink(struct zpool *pool, unsigned int pages,
+ unsigned int *reclaimed);
+
+void *zpool_map_handle(struct zpool *pool, unsigned long handle,
+ enum zpool_mapmode mm);
+
+void zpool_unmap_handle(struct zpool *pool, unsigned long handle);
+
+u64 zpool_get_total_size(struct zpool *pool);
+
+
+/**
+ * struct zpool_driver - driver implementation for zpool
+ * @type: name of the driver.
+ * @list: entry in the list of zpool drivers.
+ * @create: create a new pool.
+ * @destroy: destroy a pool.
+ * @malloc: allocate mem from a pool.
+ * @free: free mem from a pool.
+ * @shrink: shrink the pool.
+ * @map: map a handle.
+ * @unmap: unmap a handle.
+ * @total_size: get total size of a pool.
+ *
+ * This is created by a zpool implementation and registered
+ * with zpool.
+ */
+struct zpool_driver {
+ char *type;
+ struct module *owner;
+ atomic_t refcount;
+ struct list_head list;
+
+ void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops);
+ void (*destroy)(void *pool);
+
+ int (*malloc)(void *pool, size_t size, gfp_t gfp,
+ unsigned long *handle);
+ void (*free)(void *pool, unsigned long handle);
+
+ int (*shrink)(void *pool, unsigned int pages,
+ unsigned int *reclaimed);
+
+ void *(*map)(void *pool, unsigned long handle,
+ enum zpool_mapmode mm);
+ void (*unmap)(void *pool, unsigned long handle);
+
+ u64 (*total_size)(void *pool);
+};
+
+void zpool_register_driver(struct zpool_driver *driver);
+
+int zpool_unregister_driver(struct zpool_driver *driver);
+
+int zpool_evict(void *pool, unsigned long handle);
+
+#endif
diff --git a/drivers/staging/zsmalloc/zsmalloc.h b/include/linux/zsmalloc.h
similarity index 67%
rename from drivers/staging/zsmalloc/zsmalloc.h
rename to include/linux/zsmalloc.h
index 46dbd05..1338190 100644
--- a/drivers/staging/zsmalloc/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -2,6 +2,7 @@
* zsmalloc memory allocator
*
* Copyright (C) 2011 Nitin Gupta
+ * Copyright (C) 2012, 2013 Minchan Kim
*
* This code is released using a dual license strategy: BSD/GPL
* You can choose the license that better fits your requirements.
@@ -18,17 +19,24 @@
/*
* zsmalloc mapping modes
*
- * NOTE: These only make a difference when a mapped object spans pages
-*/
+ * NOTE: These only make a difference when a mapped object spans pages.
+ * They also have no effect when PGTABLE_MAPPING is selected.
+ */
enum zs_mapmode {
ZS_MM_RW, /* normal read-write mapping */
ZS_MM_RO, /* read-only (no copy-out at unmap time) */
ZS_MM_WO /* write-only (no copy-in at map time) */
+ /*
+ * NOTE: ZS_MM_WO should only be used for initializing new
+ * (uninitialized) allocations. Partial writes to already
+ * initialized allocations should use ZS_MM_RW to preserve the
+ * existing data.
+ */
};
struct zs_pool;
-struct zs_pool *zs_create_pool(gfp_t flags);
+struct zs_pool *zs_create_pool(char *name, gfp_t flags);
void zs_destroy_pool(struct zs_pool *pool);
unsigned long zs_malloc(struct zs_pool *pool, size_t size);
@@ -38,6 +46,7 @@
enum zs_mapmode mm);
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
-u64 zs_get_total_size_bytes(struct zs_pool *pool);
+unsigned long zs_get_total_pages(struct zs_pool *pool);
+unsigned long zs_compact(struct zs_pool *pool);
#endif
diff --git a/include/net/activity_stats.h b/include/net/activity_stats.h
new file mode 100644
index 0000000..10e4c15
--- /dev/null
+++ b/include/net/activity_stats.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ */
+
+#ifndef __activity_stats_h
+#define __activity_stats_h
+
+#ifdef CONFIG_NET_ACTIVITY_STATS
+void activity_stats_update(void);
+#else
+#define activity_stats_update(void) {}
+#endif
+
+#endif /* _NET_ACTIVITY_STATS_H */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 2510068..2cbf0ba 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -190,6 +190,8 @@
extern void addrconf_prefix_rcv(struct net_device *dev,
u8 *opt, int len, bool sllao);
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table);
+
/*
* anycast prototypes (anycast.c)
*/
@@ -201,6 +203,7 @@
extern int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
const struct in6_addr *addr);
+extern void ipv6_ac_destroy_dev(struct inet6_dev *idev);
/* Device notifier */
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 0ef0006..db43501 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -199,8 +199,10 @@
#define ESCO_2EV5 0x0100
#define ESCO_3EV5 0x0200
-#define SCO_ESCO_MASK (ESCO_HV1 | ESCO_HV2 | ESCO_HV3)
-#define EDR_ESCO_MASK (ESCO_2EV3 | ESCO_3EV3 | ESCO_2EV5 | ESCO_3EV5)
+#define SCO_ESCO_MASK (ESCO_HV1 | ESCO_HV2 | ESCO_HV3)
+#define EDR_ESCO_MASK (ESCO_2EV3 | ESCO_3EV3 | ESCO_2EV5 | ESCO_3EV5)
+#define ALL_ESCO_MASK (SCO_ESCO_MASK | ESCO_EV3 | ESCO_EV4 | ESCO_EV5 | \
+ EDR_ESCO_MASK)
/* ACL flags */
#define ACL_START_NO_FLUSH 0x00
@@ -1629,6 +1631,9 @@
__u8 out;
__u16 state;
__u32 link_mode;
+ __u32 mtu;
+ __u32 cnt;
+ __u32 pkts;
};
struct hci_dev_req {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7cb6d36..57123ee 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -581,7 +581,8 @@
void hci_setup_sync(struct hci_conn *conn, __u16 handle);
void hci_sco_setup(struct hci_conn *conn, __u8 status);
-struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst);
+struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type,
+ __u16 pkt_type, bdaddr_t *dst);
int hci_conn_del(struct hci_conn *conn);
void hci_conn_hash_flush(struct hci_dev *hdev);
void hci_conn_check_pending(struct hci_dev *hdev);
@@ -591,7 +592,8 @@
void hci_chan_list_flush(struct hci_conn *conn);
struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle);
-struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst,
+struct hci_conn *hci_connect(struct hci_dev *hdev, int type,
+ __u16 pkt_type, bdaddr_t *dst,
__u8 dst_type, __u8 sec_level, __u8 auth_type);
int hci_conn_check_link_mode(struct hci_conn *conn);
int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
@@ -654,7 +656,7 @@
if (conn->state == BT_CONNECTED) {
timeo = conn->disc_timeout;
if (!conn->out)
- timeo *= 2;
+ timeo *= 20;
} else {
timeo = msecs_to_jiffies(10);
}
diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h
index 1e35c43..6d1857a 100644
--- a/include/net/bluetooth/sco.h
+++ b/include/net/bluetooth/sco.h
@@ -37,6 +37,7 @@
struct sockaddr_sco {
sa_family_t sco_family;
bdaddr_t sco_bdaddr;
+ __u16 sco_pkt_type;
};
/* SCO socket options */
@@ -72,7 +73,8 @@
struct sco_pinfo {
struct bt_sock bt;
- __u32 flags;
+ __u16 pkt_type;
+
struct sco_conn *conn;
};
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 26b5b69..f94696c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1268,10 +1268,12 @@
/**
* struct cfg80211_match_set - sets of attributes to match
*
- * @ssid: SSID to be matched
+ * @ssid: SSID to be matched; may be zero-length for no match (RSSI only)
+ * @rssi_thold: don't report scan results below this threshold (in s32 dBm)
*/
struct cfg80211_match_set {
struct cfg80211_ssid ssid;
+ s32 rssi_thold;
};
/**
@@ -1293,7 +1295,10 @@
* @dev: the interface
* @scan_start: start time of the scheduled scan
* @channels: channels to scan
- * @rssi_thold: don't report scan results below this threshold (in s32 dBm)
+ * @min_rssi_thold: for drivers only supporting a single threshold, this
+ * contains the minimum over all matchsets
+ * @owner_nlportid: netlink portid of owner (if this should is a request
+ * owned by a particular socket)
*/
struct cfg80211_sched_scan_request {
struct cfg80211_ssid *ssids;
@@ -1305,12 +1310,14 @@
u32 flags;
struct cfg80211_match_set *match_sets;
int n_match_sets;
- s32 rssi_thold;
+ s32 min_rssi_thold;
+ s32 rssi_thold; /* just for backward compatible */
/* internal */
struct wiphy *wiphy;
struct net_device *dev;
unsigned long scan_start;
+ u32 owner_nlportid;
/* keep last */
struct ieee80211_channel *channels[0];
@@ -2254,22 +2261,28 @@
* enum wiphy_flags - wiphy capability flags
*
* @WIPHY_FLAG_CUSTOM_REGULATORY: tells us the driver for this device
- * has its own custom regulatory domain and cannot identify the
- * ISO / IEC 3166 alpha2 it belongs to. When this is enabled
- * we will disregard the first regulatory hint (when the
- * initiator is %REGDOM_SET_BY_CORE).
- * @WIPHY_FLAG_STRICT_REGULATORY: tells us the driver for this device will
- * ignore regulatory domain settings until it gets its own regulatory
- * domain via its regulatory_hint() unless the regulatory hint is
- * from a country IE. After its gets its own regulatory domain it will
- * only allow further regulatory domain settings to further enhance
- * compliance. For example if channel 13 and 14 are disabled by this
- * regulatory domain no user regulatory domain can enable these channels
- * at a later time. This can be used for devices which do not have
- * calibration information guaranteed for frequencies or settings
- * outside of its regulatory domain. If used in combination with
- * WIPHY_FLAG_CUSTOM_REGULATORY the inspected country IE power settings
- * will be followed.
+ * has its own custom regulatory domain and cannot identify the
+ * ISO / IEC 3166 alpha2 it belongs to. When this is enabled
+ * we will disregard the first regulatory hint (when the
+ * initiator is %REGDOM_SET_BY_CORE). wiphys can set the custom
+ * regulatory domain using wiphy_apply_custom_regulatory()
+ * prior to wiphy registration.
+ * @WIPHY_FLAG_STRICT_REGULATORY: tells us that the wiphy for this device
+ * has regulatory domain that it wishes to be considered as the
+ * superset for regulatory rules. After this device gets its regulatory
+ * domain programmed further regulatory hints shall only be considered
+ * for this device to enhance regulatory compliance, forcing the
+ * device to only possibly use subsets of the original regulatory
+ * rules. For example if channel 13 and 14 are disabled by this
+ * device's regulatory domain no user specified regulatory hint which
+ * has these channels enabled would enable them for this wiphy,
+ * the device's original regulatory domain will be trusted as the
+ * base. You can program the superset of regulatory rules for this
+ * wiphy with regulatory_hint() for cards programmed with an
+ * ISO3166-alpha2 country code. wiphys that use regulatory_hint()
+ * will have their wiphy->regd programmed once the regulatory
+ * domain is set, and all other regulatory hints will be ignored
+ * until their own regulatory domain gets programmed.
* @WIPHY_FLAG_DISABLE_BEACON_HINTS: enable this if your driver needs to ensure
* that passive scan flags and beaconing flags may not be lifted by
* cfg80211 due to regulatory beacon hints. For more information on beacon
@@ -2467,6 +2480,34 @@
};
/**
+ * enum wiphy_vendor_command_flags - validation flags for vendor commands
+ * @WIPHY_VENDOR_CMD_NEED_WDEV: vendor command requires wdev
+ * @WIPHY_VENDOR_CMD_NEED_NETDEV: vendor command requires netdev
+ * @WIPHY_VENDOR_CMD_NEED_RUNNING: interface/wdev must be up & running
+ * (must be combined with %_WDEV or %_NETDEV)
+ */
+enum wiphy_vendor_command_flags {
+ WIPHY_VENDOR_CMD_NEED_WDEV = BIT(0),
+ WIPHY_VENDOR_CMD_NEED_NETDEV = BIT(1),
+ WIPHY_VENDOR_CMD_NEED_RUNNING = BIT(2),
+};
+
+/**
+ * struct wiphy_vendor_command - vendor command definition
+ * @info: vendor command identifying information, as used in nl80211
+ * @flags: flags, see &enum wiphy_vendor_command_flags
+ * @doit: callback for the operation, note that wdev is %NULL if the
+ * flags didn't ask for a wdev and non-%NULL otherwise; the data
+ * pointer may be %NULL if userspace provided no data at all
+ */
+struct wiphy_vendor_command {
+ struct nl80211_vendor_cmd_info info;
+ u32 flags;
+ int (*doit)(struct wiphy *wiphy, struct wireless_dev *wdev,
+ const void *data, int data_len);
+};
+
+/**
* struct wiphy - wireless hardware description
* @reg_notifier: the driver's regulatory notification callback,
* note that if your driver uses wiphy_apply_custom_regulatory()
@@ -2573,6 +2614,12 @@
* 802.11-2012 8.4.2.29 for the defined fields.
* @extended_capabilities_mask: mask of the valid values
* @extended_capabilities_len: length of the extended capabilities
+ * @country_ie_pref: country IE processing preferences specified
+ * by enum nl80211_country_ie_pref
+ * @vendor_commands: array of vendor commands supported by the hardware
+ * @n_vendor_commands: number of vendor commands
+ * @vendor_events: array of vendor events supported by the hardware
+ * @n_vendor_events: number of vendor events
*/
struct wiphy {
/* assign these fields before you register the wiphy */
@@ -2642,6 +2689,8 @@
const u8 *extended_capabilities, *extended_capabilities_mask;
u8 extended_capabilities_len;
+ u8 country_ie_pref;
+
/* If multiple wiphys are registered and you're handed e.g.
* a regular netdev with assigned ieee80211_ptr, you won't
* know whether it points to a wiphy your driver has registered
@@ -2681,6 +2730,10 @@
const struct iw_handler_def *wext;
#endif
+ const struct wiphy_vendor_command *vendor_commands;
+ const struct nl80211_vendor_cmd_info *vendor_events;
+ int n_vendor_commands, n_vendor_events;
+
char priv[0] __aligned(NETDEV_ALIGN);
};
@@ -2842,6 +2895,7 @@
* @p2p_started: true if this is a P2P Device that has been started
* @cac_started: true if DFS channel availability check has been started
* @cac_start_time: timestamp (jiffies) when the dfs state was entered.
+ * @owner_nlportid: (private) owner socket port ID
*/
struct wireless_dev {
struct wiphy *wiphy;
@@ -2896,6 +2950,8 @@
bool cac_started;
unsigned long cac_start_time;
+ u32 owner_nlportid;
+
#ifdef CONFIG_CFG80211_WEXT
/* wext data */
struct {
@@ -3591,6 +3647,121 @@
*/
void wiphy_rfkill_stop_polling(struct wiphy *wiphy);
+/**
+ * DOC: Vendor commands
+ *
+ * Occasionally, there are special protocol or firmware features that
+ * can't be implemented very openly. For this and similar cases, the
+ * vendor command functionality allows implementing the features with
+ * (typically closed-source) userspace and firmware, using nl80211 as
+ * the configuration mechanism.
+ *
+ * A driver supporting vendor commands must register them as an array
+ * in struct wiphy, with handlers for each one, each command has an
+ * OUI and sub command ID to identify it.
+ *
+ * Note that this feature should not be (ab)used to implement protocol
+ * features that could openly be shared across drivers. In particular,
+ * it must never be required to use vendor commands to implement any
+ * "normal" functionality that higher-level userspace like connection
+ * managers etc. need.
+ */
+
+struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
+ enum nl80211_commands cmd,
+ enum nl80211_attrs attr,
+ int approxlen);
+
+struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+ enum nl80211_commands cmd,
+ enum nl80211_attrs attr,
+ int vendor_event_idx,
+ int approxlen, gfp_t gfp);
+
+void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp);
+
+/**
+ * cfg80211_vendor_cmd_alloc_reply_skb - allocate vendor command reply
+ * @wiphy: the wiphy
+ * @approxlen: an upper bound of the length of the data that will
+ * be put into the skb
+ *
+ * This function allocates and pre-fills an skb for a reply to
+ * a vendor command. Since it is intended for a reply, calling
+ * it outside of a vendor command's doit() operation is invalid.
+ *
+ * The returned skb is pre-filled with some identifying data in
+ * a way that any data that is put into the skb (with skb_put(),
+ * nla_put() or similar) will end up being within the
+ * %NL80211_ATTR_VENDOR_DATA attribute, so all that needs to be done
+ * with the skb is adding data for the corresponding userspace tool
+ * which can then read that data out of the testdata attribute. You
+ * must not modify the skb in any other way.
+ *
+ * When done, call cfg80211_vendor_cmd_reply() with the skb and return
+ * its error code as the result of the doit() operation.
+ *
+ * Return: An allocated and pre-filled skb. %NULL if any errors happen.
+ */
+static inline struct sk_buff *
+cfg80211_vendor_cmd_alloc_reply_skb(struct wiphy *wiphy, int approxlen)
+{
+ return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_VENDOR,
+ NL80211_ATTR_VENDOR_DATA, approxlen);
+}
+
+/**
+ * cfg80211_vendor_cmd_reply - send the reply skb
+ * @skb: The skb, must have been allocated with
+ * cfg80211_vendor_cmd_alloc_reply_skb()
+ *
+ * Since calling this function will usually be the last thing
+ * before returning from the vendor command doit() you should
+ * return the error code. Note that this function consumes the
+ * skb regardless of the return value.
+ *
+ * Return: An error code or 0 on success.
+ */
+int cfg80211_vendor_cmd_reply(struct sk_buff *skb);
+
+/**
+ * cfg80211_vendor_event_alloc - allocate vendor-specific event skb
+ * @wiphy: the wiphy
+ * @event_idx: index of the vendor event in the wiphy's vendor_events
+ * @approxlen: an upper bound of the length of the data that will
+ * be put into the skb
+ * @gfp: allocation flags
+ *
+ * This function allocates and pre-fills an skb for an event on the
+ * vendor-specific multicast group.
+ *
+ * When done filling the skb, call cfg80211_vendor_event() with the
+ * skb to send the event.
+ *
+ * Return: An allocated and pre-filled skb. %NULL if any errors happen.
+ */
+static inline struct sk_buff *
+cfg80211_vendor_event_alloc(struct wiphy *wiphy, int approxlen,
+ int event_idx, gfp_t gfp)
+{
+ return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_VENDOR,
+ NL80211_ATTR_VENDOR_DATA,
+ event_idx, approxlen, gfp);
+}
+
+/**
+ * cfg80211_vendor_event - send the event
+ * @skb: The skb, must have been allocated with cfg80211_vendor_event_alloc()
+ * @gfp: allocation flags
+ *
+ * This function sends the given @skb, which must have been allocated
+ * by cfg80211_vendor_event_alloc(), as an event. It always consumes it.
+ */
+static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp)
+{
+ __cfg80211_send_event_skb(skb, gfp);
+}
+
#ifdef CONFIG_NL80211_TESTMODE
/**
* DOC: Test mode
@@ -3626,8 +3797,12 @@
*
* Return: An allocated and pre-filled skb. %NULL if any errors happen.
*/
-struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
- int approxlen);
+static inline struct sk_buff *
+cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, int approxlen)
+{
+ return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_TESTMODE,
+ NL80211_ATTR_TESTDATA, approxlen);
+}
/**
* cfg80211_testmode_reply - send the reply skb
@@ -3641,7 +3816,10 @@
*
* Return: An error code or 0 on success.
*/
-int cfg80211_testmode_reply(struct sk_buff *skb);
+static inline int cfg80211_testmode_reply(struct sk_buff *skb)
+{
+ return cfg80211_vendor_cmd_reply(skb);
+}
/**
* cfg80211_testmode_alloc_event_skb - allocate testmode event
@@ -3664,8 +3842,13 @@
*
* Return: An allocated and pre-filled skb. %NULL if any errors happen.
*/
-struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
- int approxlen, gfp_t gfp);
+static inline struct sk_buff *
+cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, int approxlen, gfp_t gfp)
+{
+ return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_TESTMODE,
+ NL80211_ATTR_TESTDATA, -1,
+ approxlen, gfp);
+}
/**
* cfg80211_testmode_event - send the event
@@ -3677,7 +3860,10 @@
* by cfg80211_testmode_alloc_event_skb(), as an event. It always
* consumes it.
*/
-void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp);
+static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
+{
+ __cfg80211_send_event_skb(skb, gfp);
+}
#define CFG80211_TESTMODE_CMD(cmd) .testmode_cmd = (cmd),
#define CFG80211_TESTMODE_DUMP(cmd) .testmode_dump = (cmd),
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index e361f48..4ac12e14 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -23,6 +23,8 @@
struct fib_rule __rcu *ctarget;
char iifname[IFNAMSIZ];
char oifname[IFNAMSIZ];
+ kuid_t uid_start;
+ kuid_t uid_end;
struct rcu_head rcu;
struct net * fr_net;
};
@@ -80,7 +82,9 @@
[FRA_FWMARK] = { .type = NLA_U32 }, \
[FRA_FWMASK] = { .type = NLA_U32 }, \
[FRA_TABLE] = { .type = NLA_U32 }, \
- [FRA_GOTO] = { .type = NLA_U32 }
+ [FRA_GOTO] = { .type = NLA_U32 }, \
+ [FRA_UID_START] = { .type = NLA_U32 }, \
+ [FRA_UID_END] = { .type = NLA_U32 }
static inline void fib_rule_get(struct fib_rule *rule)
{
diff --git a/include/net/flow.h b/include/net/flow.h
index 628e11b..1426681f 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -10,6 +10,15 @@
#include <linux/socket.h>
#include <linux/in6.h>
#include <linux/atomic.h>
+#include <linux/uidgid.h>
+
+/*
+ * ifindex generation is per-net namespace, and loopback is
+ * always the 1st device in ns (see net_dev_init), thus any
+ * loopback device should get ifindex 1
+ */
+
+#define LOOPBACK_IFINDEX 1
struct flowi_common {
int flowic_oif;
@@ -23,6 +32,7 @@
#define FLOWI_FLAG_CAN_SLEEP 0x02
#define FLOWI_FLAG_KNOWN_NH 0x04
__u32 flowic_secid;
+ kuid_t flowic_uid;
};
union flowi_uli {
@@ -59,6 +69,7 @@
#define flowi4_proto __fl_common.flowic_proto
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
+#define flowi4_uid __fl_common.flowic_uid
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -78,16 +89,18 @@
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ kuid_t uid)
{
fl4->flowi4_oif = oif;
- fl4->flowi4_iif = 0;
+ fl4->flowi4_iif = LOOPBACK_IFINDEX;
fl4->flowi4_mark = mark;
fl4->flowi4_tos = tos;
fl4->flowi4_scope = scope;
fl4->flowi4_proto = proto;
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
+ fl4->flowi4_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
@@ -115,6 +128,7 @@
#define flowi6_proto __fl_common.flowic_proto
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
+#define flowi6_uid __fl_common.flowic_uid
struct in6_addr daddr;
struct in6_addr saddr;
__be32 flowlabel;
@@ -158,6 +172,7 @@
#define flowi_proto u.__fl_common.flowic_proto
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
+#define flowi_uid u.__fl_common.flowic_uid
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 7235ae7..9528e10f 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -88,6 +88,7 @@
acked : 1,
no_srccheck: 1;
kmemcheck_bitfield_end(flags);
+ u32 ir_mark;
struct ip_options_rcu *opt;
};
@@ -96,6 +97,14 @@
return (struct inet_request_sock *)sk;
}
+static inline u32 inet_request_mark(struct sock *sk, struct sk_buff *skb)
+{
+ if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)
+ return skb->mark;
+
+ return sk->sk_mark;
+}
+
struct inet_cork {
unsigned int flags;
__be32 addr;
diff --git a/include/net/ip.h b/include/net/ip.h
index ea9be6b..a04070b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -155,6 +155,7 @@
/* -1 if not needed */
int bound_dev_if;
u8 tos;
+ kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
@@ -227,6 +228,9 @@
extern void ip_static_sysctl_init(void);
+#define IP4_REPLY_MARK(net, mark) \
+ ((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0)
+
static inline bool ip_is_fragment(const struct iphdr *iph)
{
return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 8d977b3..6be6deb 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -136,7 +136,7 @@
const struct in6_addr *gwaddr);
extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark);
+ int oif, u32 mark, kuid_t uid);
extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk,
__be32 mtu);
extern void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 413e23b..21f2b90 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -111,6 +111,9 @@
#define IP6_MF 0x0001
+#define IP6_REPLY_MARK(net, mark) \
+ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0)
+
#include <net/sock.h>
/* sysctls */
@@ -200,6 +203,7 @@
*/
struct ipv6_txoptions {
+ atomic_t refcnt;
/* Length of this structure */
int tot_len;
@@ -212,7 +216,7 @@
struct ipv6_opt_hdr *dst0opt;
struct ipv6_rt_hdr *srcrt; /* Routing Header */
struct ipv6_opt_hdr *dst1opt;
-
+ struct rcu_head rcu;
/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
};
@@ -243,6 +247,24 @@
struct rcu_head rcu;
};
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+ struct ipv6_txoptions *opt;
+
+ rcu_read_lock();
+ opt = rcu_dereference(np->opt);
+ if (opt && !atomic_inc_not_zero(&opt->refcnt))
+ opt = NULL;
+ rcu_read_unlock();
+ return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+ if (opt && atomic_dec_and_test(&opt->refcnt))
+ kfree_rcu(opt, rcu);
+}
+
extern struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
extern struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
struct ip6_flowlabel * fl,
@@ -260,6 +282,12 @@
extern void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len);
+
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+ struct sock *sk, struct flowi6 *fl6);
+
extern int ip6_ra_control(struct sock *sk, int sel);
extern int ipv6_parse_hopopts(struct sk_buff *skb);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index b176978..b064d6d 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/sysctl.h>
+#include <net/flow.h>
#include <net/netns/core.h>
#include <net/netns/mib.h>
#include <net/netns/unix.h>
@@ -120,14 +121,6 @@
atomic_t rt_genid;
};
-/*
- * ifindex generation is per-net namespace, and loopback is
- * always the 1st device in ns (see net_dev_init), thus any
- * loopback device should get ifindex 1
- */
-
-#define LOOPBACK_IFINDEX 1
-
#include <linux/seq_file_net.h>
/* Init's network namespace */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 03e6378..4f6c720 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -65,6 +65,9 @@
int sysctl_tcp_ecn;
+ int sysctl_fwmark_reflect;
+ int sysctl_tcp_fwmark_accept;
+
kgid_t sysctl_ping_group_range[2];
long sysctl_tcp_mem[3];
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 005e2c2..4b9f99e 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -28,6 +28,7 @@
int ip6_rt_mtu_expires;
int ip6_rt_min_advmss;
int icmpv6_time;
+ int fwmark_reflect;
};
struct netns_ipv6 {
diff --git a/include/net/ping.h b/include/net/ping.h
index 682b5ae..6b6e9a4 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -13,6 +13,7 @@
#ifndef _PING_H
#define _PING_H
+#include <net/icmp.h>
#include <net/netns/hash.h>
/* PING_HTABLE_SIZE must be power of 2 */
@@ -28,6 +29,19 @@
*/
#define GID_T_MAX (((gid_t)~0U) >> 1)
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+ int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len);
+ int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg,
+ struct sk_buff *skb);
+ int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+ void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+ __be16 port, u32 info, u8 *payload);
+ int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+ const struct net_device *dev, int strict);
+};
+
struct ping_table {
struct hlist_nulls_head hash[PING_HTABLE_SIZE];
rwlock_t lock;
@@ -39,10 +53,39 @@
};
extern struct proto ping_prot;
+extern struct ping_table ping_table;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+struct pingfakehdr {
+ struct icmphdr icmph;
+ struct iovec *iov;
+ sa_family_t family;
+ __wsum wcheck;
+};
-extern void ping_rcv(struct sk_buff *);
-extern void ping_err(struct sk_buff *, u32 info);
+int ping_get_port(struct sock *sk, unsigned short ident);
+void ping_hash(struct sock *sk);
+void ping_unhash(struct sock *sk);
+
+int ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+ struct sk_buff *);
+
+int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len, int noblock, int flags, int *addr_len);
+int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+ void *user_icmph, size_t icmph_len);
+int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len);
+int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len);
+int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+void ping_rcv(struct sk_buff *skb);
#ifdef CONFIG_PROC_FS
extern int __init ping_proc_init(void);
@@ -50,6 +93,7 @@
#endif
void __init ping_init(void);
-
+int __init pingv6_init(void);
+void pingv6_exit(void);
#endif /* _PING_H */
diff --git a/include/net/route.h b/include/net/route.h
index 2ea40c1..647bb2a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -142,7 +142,7 @@
flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
RT_SCOPE_UNIVERSE, proto,
sk ? inet_sk_flowi_flags(sk) : 0,
- daddr, saddr, dport, sport);
+ daddr, saddr, dport, sport, sk ? sock_i_uid(sk) : 0);
if (sk)
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
@@ -253,7 +253,8 @@
flow_flags |= FLOWI_FLAG_CAN_SLEEP;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
- protocol, flow_flags, dst, src, dport, sport);
+ protocol, flow_flags, dst, src, dport, sport,
+ sock_i_uid(sk));
}
static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/include/net/sock.h b/include/net/sock.h
index 2317d12..783d0af 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -67,6 +67,7 @@
#include <linux/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>
+#include <net/tcp_states.h>
struct cgroup;
struct cgroup_subsys;
@@ -1008,6 +1009,7 @@
void (*destroy_cgroup)(struct mem_cgroup *memcg);
struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
#endif
+ int (*diag_destroy)(struct sock *sk, int err);
};
/*
@@ -2254,6 +2256,15 @@
return NULL;
}
+/* This helper checks if a socket is a full socket,
+ * ie _not_ a timewait or request socket.
+ * TODO: Check for TCPF_NEW_SYN_RECV when that starts to exist.
+ */
+static inline bool sk_fullsock(const struct sock *sk)
+{
+ return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT);
+}
+
extern void sock_enable_timestamp(struct sock *sk, int flag);
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
extern int sock_get_timestampns(struct sock *, struct timespec __user *);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 29a1a63..64c0c31 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -288,6 +288,7 @@
extern int sysctl_tcp_limit_output_bytes;
extern int sysctl_tcp_challenge_ack_limit;
extern int sysctl_tcp_min_tso_segs;
+extern int sysctl_tcp_default_init_rwnd;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -1043,6 +1044,8 @@
extern void tcp_done(struct sock *sk);
+int tcp_abort(struct sock *sk, int err);
+
static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
rx_opt->dsack = 0;
@@ -1553,6 +1556,8 @@
extern int tcp_gro_complete(struct sk_buff *skb);
extern int tcp4_gro_complete(struct sk_buff *skb);
+extern int tcp_nuke_addr(struct net *net, struct sockaddr *addr);
+
#ifdef CONFIG_PROC_FS
extern int tcp4_proc_init(void);
extern void tcp4_proc_exit(void);
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index 938b7fd..eb40e71 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -11,6 +11,7 @@
extern struct proto udpv6_prot;
extern struct proto udplitev6_prot;
extern struct proto tcpv6_prot;
+extern struct proto pingv6_prot;
struct flowi6;
@@ -21,6 +22,8 @@
extern void ipv6_frag_exit(void);
/* transport protocols */
+extern int pingv6_init(void);
+extern void pingv6_exit(void);
extern int rawv6_init(void);
extern void rawv6_exit(void);
extern int udpv6_init(void);
diff --git a/include/trace/events/cpufreq_interactive.h b/include/trace/events/cpufreq_interactive.h
new file mode 100644
index 0000000..951e6ca
--- /dev/null
+++ b/include/trace/events/cpufreq_interactive.h
@@ -0,0 +1,112 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpufreq_interactive
+
+#if !defined(_TRACE_CPUFREQ_INTERACTIVE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUFREQ_INTERACTIVE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(set,
+ TP_PROTO(u32 cpu_id, unsigned long targfreq,
+ unsigned long actualfreq),
+ TP_ARGS(cpu_id, targfreq, actualfreq),
+
+ TP_STRUCT__entry(
+ __field( u32, cpu_id )
+ __field(unsigned long, targfreq )
+ __field(unsigned long, actualfreq )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu_id = (u32) cpu_id;
+ __entry->targfreq = targfreq;
+ __entry->actualfreq = actualfreq;
+ ),
+
+ TP_printk("cpu=%u targ=%lu actual=%lu",
+ __entry->cpu_id, __entry->targfreq,
+ __entry->actualfreq)
+);
+
+DEFINE_EVENT(set, cpufreq_interactive_setspeed,
+ TP_PROTO(u32 cpu_id, unsigned long targfreq,
+ unsigned long actualfreq),
+ TP_ARGS(cpu_id, targfreq, actualfreq)
+);
+
+DECLARE_EVENT_CLASS(loadeval,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, cpu_id )
+ __field(unsigned long, load )
+ __field(unsigned long, curtarg )
+ __field(unsigned long, curactual )
+ __field(unsigned long, newtarg )
+ ),
+
+ TP_fast_assign(
+ __entry->cpu_id = cpu_id;
+ __entry->load = load;
+ __entry->curtarg = curtarg;
+ __entry->curactual = curactual;
+ __entry->newtarg = newtarg;
+ ),
+
+ TP_printk("cpu=%lu load=%lu cur=%lu actual=%lu targ=%lu",
+ __entry->cpu_id, __entry->load, __entry->curtarg,
+ __entry->curactual, __entry->newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_target,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_already,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_notyet,
+ TP_PROTO(unsigned long cpu_id, unsigned long load,
+ unsigned long curtarg, unsigned long curactual,
+ unsigned long newtarg),
+ TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+TRACE_EVENT(cpufreq_interactive_boost,
+ TP_PROTO(const char *s),
+ TP_ARGS(s),
+ TP_STRUCT__entry(
+ __string(s, s)
+ ),
+ TP_fast_assign(
+ __assign_str(s, s);
+ ),
+ TP_printk("%s", __get_str(s))
+);
+
+TRACE_EVENT(cpufreq_interactive_unboost,
+ TP_PROTO(const char *s),
+ TP_ARGS(s),
+ TP_STRUCT__entry(
+ __string(s, s)
+ ),
+ TP_fast_assign(
+ __assign_str(s, s);
+ ),
+ TP_printk("%s", __get_str(s))
+);
+
+#endif /* _TRACE_CPUFREQ_INTERACTIVE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 8ee15b9..ff4bd1b 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -14,11 +14,67 @@
struct ext4_inode_info;
struct mpage_da_data;
struct ext4_map_blocks;
-struct ext4_extent;
struct extent_status;
#define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
+#define show_mballoc_flags(flags) __print_flags(flags, "|", \
+ { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \
+ { EXT4_MB_HINT_RESERVED, "HINT_RESV" }, \
+ { EXT4_MB_HINT_METADATA, "HINT_MDATA" }, \
+ { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \
+ { EXT4_MB_HINT_BEST, "HINT_BEST" }, \
+ { EXT4_MB_HINT_DATA, "HINT_DATA" }, \
+ { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \
+ { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \
+ { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \
+ { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \
+ { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \
+ { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \
+ { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \
+ { EXT4_MB_USE_RESERVED, "USE_RESV" })
+
+#define show_map_flags(flags) __print_flags(flags, "|", \
+ { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \
+ { EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \
+ { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \
+ { EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \
+ { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \
+ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \
+ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \
+ { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \
+ { EXT4_GET_BLOCKS_NO_LOCK, "NO_LOCK" }, \
+ { EXT4_GET_BLOCKS_NO_PUT_HOLE, "NO_PUT_HOLE" })
+
+#define show_mflags(flags) __print_flags(flags, "", \
+ { EXT4_MAP_NEW, "N" }, \
+ { EXT4_MAP_MAPPED, "M" }, \
+ { EXT4_MAP_UNWRITTEN, "U" }, \
+ { EXT4_MAP_BOUNDARY, "B" }, \
+ { EXT4_MAP_FROM_CLUSTER, "C" })
+
+#define show_free_flags(flags) __print_flags(flags, "|", \
+ { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \
+ { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \
+ { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \
+ { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \
+ { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\
+ { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" })
+
+#define show_extent_status(status) __print_flags(status, "", \
+ { EXTENT_STATUS_WRITTEN, "W" }, \
+ { EXTENT_STATUS_UNWRITTEN, "U" }, \
+ { EXTENT_STATUS_DELAYED, "D" }, \
+ { EXTENT_STATUS_HOLE, "H" })
+
+#define show_falloc_mode(mode) __print_flags(mode, "|", \
+ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \
+ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \
+ { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}, \
+ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \
+ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"})
+
+
TRACE_EVENT(ext4_free_inode,
TP_PROTO(struct inode *inode),
@@ -281,7 +337,7 @@
TP_ARGS(inode, pos, len, copied)
);
-TRACE_EVENT(ext4_da_writepages,
+TRACE_EVENT(ext4_writepages,
TP_PROTO(struct inode *inode, struct writeback_control *wbc),
TP_ARGS(inode, wbc),
@@ -324,46 +380,62 @@
);
TRACE_EVENT(ext4_da_write_pages,
- TP_PROTO(struct inode *inode, struct mpage_da_data *mpd),
+ TP_PROTO(struct inode *inode, pgoff_t first_page,
+ struct writeback_control *wbc),
- TP_ARGS(inode, mpd),
+ TP_ARGS(inode, first_page, wbc),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
- __field( __u64, b_blocknr )
- __field( __u32, b_size )
- __field( __u32, b_state )
- __field( unsigned long, first_page )
- __field( int, io_done )
- __field( int, pages_written )
- __field( int, sync_mode )
+ __field( pgoff_t, first_page )
+ __field( long, nr_to_write )
+ __field( int, sync_mode )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
- __entry->b_blocknr = mpd->b_blocknr;
- __entry->b_size = mpd->b_size;
- __entry->b_state = mpd->b_state;
- __entry->first_page = mpd->first_page;
- __entry->io_done = mpd->io_done;
- __entry->pages_written = mpd->pages_written;
- __entry->sync_mode = mpd->wbc->sync_mode;
+ __entry->first_page = first_page;
+ __entry->nr_to_write = wbc->nr_to_write;
+ __entry->sync_mode = wbc->sync_mode;
),
- TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x "
- "first_page %lu io_done %d pages_written %d sync_mode %d",
+ TP_printk("dev %d,%d ino %lu first_page %lu nr_to_write %ld "
+ "sync_mode %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino,
- __entry->b_blocknr, __entry->b_size,
- __entry->b_state, __entry->first_page,
- __entry->io_done, __entry->pages_written,
- __entry->sync_mode
- )
+ (unsigned long) __entry->ino, __entry->first_page,
+ __entry->nr_to_write, __entry->sync_mode)
);
-TRACE_EVENT(ext4_da_writepages_result,
+TRACE_EVENT(ext4_da_write_pages_extent,
+ TP_PROTO(struct inode *inode, struct ext4_map_blocks *map),
+
+ TP_ARGS(inode, map),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( ino_t, ino )
+ __field( __u64, lblk )
+ __field( __u32, len )
+ __field( __u32, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->lblk = map->m_lblk;
+ __entry->len = map->m_len;
+ __entry->flags = map->m_flags;
+ ),
+
+ TP_printk("dev %d,%d ino %lu lblk %llu len %u flags %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino, __entry->lblk, __entry->len,
+ show_mflags(__entry->flags))
+);
+
+TRACE_EVENT(ext4_writepages_result,
TP_PROTO(struct inode *inode, struct writeback_control *wbc,
int ret, int pages_written),
@@ -444,16 +516,16 @@
);
DECLARE_EVENT_CLASS(ext4_invalidatepage_op,
- TP_PROTO(struct page *page, unsigned long offset),
+ TP_PROTO(struct page *page, unsigned int offset, unsigned int length),
- TP_ARGS(page, offset),
+ TP_ARGS(page, offset, length),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( pgoff_t, index )
- __field( unsigned long, offset )
-
+ __field( unsigned int, offset )
+ __field( unsigned int, length )
),
TP_fast_assign(
@@ -461,24 +533,26 @@
__entry->ino = page->mapping->host->i_ino;
__entry->index = page->index;
__entry->offset = offset;
+ __entry->length = length;
),
- TP_printk("dev %d,%d ino %lu page_index %lu offset %lu",
+ TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
- (unsigned long) __entry->index, __entry->offset)
+ (unsigned long) __entry->index,
+ __entry->offset, __entry->length)
);
DEFINE_EVENT(ext4_invalidatepage_op, ext4_invalidatepage,
- TP_PROTO(struct page *page, unsigned long offset),
+ TP_PROTO(struct page *page, unsigned int offset, unsigned int length),
- TP_ARGS(page, offset)
+ TP_ARGS(page, offset, length)
);
DEFINE_EVENT(ext4_invalidatepage_op, ext4_journalled_invalidatepage,
- TP_PROTO(struct page *page, unsigned long offset),
+ TP_PROTO(struct page *page, unsigned int offset, unsigned int length),
- TP_ARGS(page, offset)
+ TP_ARGS(page, offset, length)
);
TRACE_EVENT(ext4_discard_blocks,
@@ -673,10 +747,10 @@
__entry->flags = ar->flags;
),
- TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu "
+ TP_printk("dev %d,%d ino %lu flags %s len %u lblk %u goal %llu "
"lleft %u lright %u pleft %llu pright %llu ",
MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino, __entry->flags,
+ (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags),
__entry->len, __entry->logical, __entry->goal,
__entry->lleft, __entry->lright, __entry->pleft,
__entry->pright)
@@ -715,10 +789,10 @@
__entry->flags = ar->flags;
),
- TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u "
+ TP_printk("dev %d,%d ino %lu flags %s len %u block %llu lblk %u "
"goal %llu lleft %u lright %u pleft %llu pright %llu",
MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino, __entry->flags,
+ (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags),
__entry->len, __entry->block, __entry->logical,
__entry->goal, __entry->lleft, __entry->lright,
__entry->pleft, __entry->pright)
@@ -748,11 +822,11 @@
__entry->mode = inode->i_mode;
),
- TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d",
+ TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
__entry->mode, __entry->block, __entry->count,
- __entry->flags)
+ show_free_flags(__entry->flags))
);
TRACE_EVENT(ext4_sync_file_enter,
@@ -903,7 +977,7 @@
),
TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u "
- "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x "
+ "result %u/%d/%u@%u blks %u grps %u cr %u flags %s "
"tail %u broken %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
@@ -914,7 +988,7 @@
__entry->result_group, __entry->result_start,
__entry->result_len, __entry->result_logical,
__entry->found, __entry->groups, __entry->cr,
- __entry->flags, __entry->tail,
+ show_mballoc_flags(__entry->flags), __entry->tail,
__entry->buddy ? 1 << __entry->buddy : 0)
);
@@ -1260,7 +1334,7 @@
__entry->rw, __entry->ret)
);
-TRACE_EVENT(ext4_fallocate_enter,
+DECLARE_EVENT_CLASS(ext4__fallocate_mode,
TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
TP_ARGS(inode, offset, len, mode),
@@ -1268,23 +1342,45 @@
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
- __field( loff_t, pos )
- __field( loff_t, len )
+ __field( loff_t, offset )
+ __field( loff_t, len )
__field( int, mode )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
- __entry->pos = offset;
+ __entry->offset = offset;
__entry->len = len;
__entry->mode = mode;
),
- TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d",
+ TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino, __entry->pos,
- __entry->len, __entry->mode)
+ (unsigned long) __entry->ino,
+ __entry->offset, __entry->len,
+ show_falloc_mode(__entry->mode))
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter,
+
+ TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+ TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole,
+
+ TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+ TP_ARGS(inode, offset, len, mode)
+);
+
+DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range,
+
+ TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode),
+
+ TP_ARGS(inode, offset, len, mode)
);
TRACE_EVENT(ext4_fallocate_exit,
@@ -1316,31 +1412,6 @@
__entry->ret)
);
-TRACE_EVENT(ext4_punch_hole,
- TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
-
- TP_ARGS(inode, offset, len),
-
- TP_STRUCT__entry(
- __field( dev_t, dev )
- __field( ino_t, ino )
- __field( loff_t, offset )
- __field( loff_t, len )
- ),
-
- TP_fast_assign(
- __entry->dev = inode->i_sb->s_dev;
- __entry->ino = inode->i_ino;
- __entry->offset = offset;
- __entry->len = len;
- ),
-
- TP_printk("dev %d,%d ino %lu offset %lld len %lld",
- MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino,
- __entry->offset, __entry->len)
-);
-
TRACE_EVENT(ext4_unlink_enter,
TP_PROTO(struct inode *parent, struct dentry *dentry),
@@ -1425,7 +1496,7 @@
TP_ARGS(inode)
);
-/* 'ux' is the uninitialized extent. */
+/* 'ux' is the unwritten extent. */
TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
struct ext4_extent *ux),
@@ -1461,7 +1532,7 @@
);
/*
- * 'ux' is the uninitialized extent.
+ * 'ux' is the unwritten extent.
* 'ix' is the initialized extent to which blocks are transferred.
*/
TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath,
@@ -1528,10 +1599,10 @@
__entry->flags = flags;
),
- TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u",
+ TP_printk("dev %d,%d ino %lu lblk %u len %u flags %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
- __entry->lblk, __entry->len, __entry->flags)
+ __entry->lblk, __entry->len, show_map_flags(__entry->flags))
);
DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter,
@@ -1549,47 +1620,53 @@
);
DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
- TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
+ TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map,
+ int ret),
- TP_ARGS(inode, map, ret),
+ TP_ARGS(inode, flags, map, ret),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
+ __field( unsigned int, flags )
__field( ext4_fsblk_t, pblk )
__field( ext4_lblk_t, lblk )
__field( unsigned int, len )
- __field( unsigned int, flags )
+ __field( unsigned int, mflags )
__field( int, ret )
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
+ __entry->flags = flags;
__entry->pblk = map->m_pblk;
__entry->lblk = map->m_lblk;
__entry->len = map->m_len;
- __entry->flags = map->m_flags;
+ __entry->mflags = map->m_flags;
__entry->ret = ret;
),
- TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u flags %x ret %d",
+ TP_printk("dev %d,%d ino %lu flags %s lblk %u pblk %llu len %u "
+ "mflags %s ret %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
- __entry->lblk, __entry->pblk,
- __entry->len, __entry->flags, __entry->ret)
+ show_map_flags(__entry->flags), __entry->lblk, __entry->pblk,
+ __entry->len, show_mflags(__entry->mflags), __entry->ret)
);
DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit,
- TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
+ TP_PROTO(struct inode *inode, unsigned flags,
+ struct ext4_map_blocks *map, int ret),
- TP_ARGS(inode, map, ret)
+ TP_ARGS(inode, flags, map, ret)
);
DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit,
- TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
+ TP_PROTO(struct inode *inode, unsigned flags,
+ struct ext4_map_blocks *map, int ret),
- TP_ARGS(inode, map, ret)
+ TP_ARGS(inode, flags, map, ret)
);
TRACE_EVENT(ext4_ext_load_extent,
@@ -1638,25 +1715,50 @@
);
TRACE_EVENT(ext4_journal_start,
- TP_PROTO(struct super_block *sb, int nblocks, unsigned long IP),
+ TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks,
+ unsigned long IP),
- TP_ARGS(sb, nblocks, IP),
+ TP_ARGS(sb, blocks, rsv_blocks, IP),
TP_STRUCT__entry(
__field( dev_t, dev )
__field(unsigned long, ip )
- __field( int, nblocks )
+ __field( int, blocks )
+ __field( int, rsv_blocks )
),
TP_fast_assign(
- __entry->dev = sb->s_dev;
- __entry->ip = IP;
- __entry->nblocks = nblocks;
+ __entry->dev = sb->s_dev;
+ __entry->ip = IP;
+ __entry->blocks = blocks;
+ __entry->rsv_blocks = rsv_blocks;
),
- TP_printk("dev %d,%d nblocks %d caller %pF",
+ TP_printk("dev %d,%d blocks, %d rsv_blocks, %d caller %pF",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->nblocks, (void *)__entry->ip)
+ __entry->blocks, __entry->rsv_blocks, (void *)__entry->ip)
+);
+
+TRACE_EVENT(ext4_journal_start_reserved,
+ TP_PROTO(struct super_block *sb, int blocks, unsigned long IP),
+
+ TP_ARGS(sb, blocks, IP),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field(unsigned long, ip )
+ __field( int, blocks )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->ip = IP;
+ __entry->blocks = blocks;
+ ),
+
+ TP_printk("dev %d,%d blocks, %d caller %pF",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->blocks, (void *)__entry->ip)
);
DECLARE_EVENT_CLASS(ext4__trim,
@@ -1708,7 +1810,7 @@
TP_ARGS(sb, group, start, len)
);
-TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
+TRACE_EVENT(ext4_ext_handle_unwritten_extents,
TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags,
unsigned int allocated, ext4_fsblk_t newblock),
@@ -1736,12 +1838,12 @@
__entry->newblk = newblock;
),
- TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %x "
+ TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %s "
"allocated %d newblock %llu",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
(unsigned) __entry->lblk, (unsigned long long) __entry->pblk,
- __entry->len, __entry->flags,
+ __entry->len, show_map_flags(__entry->flags),
(unsigned int) __entry->allocated,
(unsigned long long) __entry->newblk)
);
@@ -1769,10 +1871,10 @@
__entry->ret = ret;
),
- TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d",
+ TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %s ret %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->lblk, (unsigned long long) __entry->pblk,
- __entry->len, __entry->flags, __entry->ret)
+ __entry->len, show_mflags(__entry->flags), __entry->ret)
);
TRACE_EVENT(ext4_ext_put_in_cache,
@@ -1926,7 +2028,7 @@
TRACE_EVENT(ext4_remove_blocks,
TP_PROTO(struct inode *inode, struct ext4_extent *ex,
ext4_lblk_t from, ext4_fsblk_t to,
- ext4_fsblk_t partial_cluster),
+ long long partial_cluster),
TP_ARGS(inode, ex, from, to, partial_cluster),
@@ -1935,7 +2037,7 @@
__field( ino_t, ino )
__field( ext4_lblk_t, from )
__field( ext4_lblk_t, to )
- __field( ext4_fsblk_t, partial )
+ __field( long long, partial )
__field( ext4_fsblk_t, ee_pblk )
__field( ext4_lblk_t, ee_lblk )
__field( unsigned short, ee_len )
@@ -1953,7 +2055,7 @@
),
TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]"
- "from %u to %u partial_cluster %u",
+ "from %u to %u partial_cluster %lld",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
(unsigned) __entry->ee_lblk,
@@ -1961,19 +2063,20 @@
(unsigned short) __entry->ee_len,
(unsigned) __entry->from,
(unsigned) __entry->to,
- (unsigned) __entry->partial)
+ (long long) __entry->partial)
);
TRACE_EVENT(ext4_ext_rm_leaf,
TP_PROTO(struct inode *inode, ext4_lblk_t start,
- struct ext4_extent *ex, ext4_fsblk_t partial_cluster),
+ struct ext4_extent *ex,
+ long long partial_cluster),
TP_ARGS(inode, start, ex, partial_cluster),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
- __field( ext4_fsblk_t, partial )
+ __field( long long, partial )
__field( ext4_lblk_t, start )
__field( ext4_lblk_t, ee_lblk )
__field( ext4_fsblk_t, ee_pblk )
@@ -1991,14 +2094,14 @@
),
TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]"
- "partial_cluster %u",
+ "partial_cluster %lld",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
(unsigned) __entry->start,
(unsigned) __entry->ee_lblk,
(unsigned long long) __entry->ee_pblk,
(unsigned short) __entry->ee_len,
- (unsigned) __entry->partial)
+ (long long) __entry->partial)
);
TRACE_EVENT(ext4_ext_rm_idx,
@@ -2025,14 +2128,16 @@
);
TRACE_EVENT(ext4_ext_remove_space,
- TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth),
+ TP_PROTO(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t end, int depth),
- TP_ARGS(inode, start, depth),
+ TP_ARGS(inode, start, end, depth),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( ext4_lblk_t, start )
+ __field( ext4_lblk_t, end )
__field( int, depth )
),
@@ -2040,28 +2145,31 @@
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->start = start;
+ __entry->end = end;
__entry->depth = depth;
),
- TP_printk("dev %d,%d ino %lu since %u depth %d",
+ TP_printk("dev %d,%d ino %lu since %u end %u depth %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
(unsigned) __entry->start,
+ (unsigned) __entry->end,
__entry->depth)
);
TRACE_EVENT(ext4_ext_remove_space_done,
- TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth,
- ext4_lblk_t partial, __le16 eh_entries),
+ TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end,
+ int depth, long long partial, __le16 eh_entries),
- TP_ARGS(inode, start, depth, partial, eh_entries),
+ TP_ARGS(inode, start, end, depth, partial, eh_entries),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( ext4_lblk_t, start )
+ __field( ext4_lblk_t, end )
__field( int, depth )
- __field( ext4_lblk_t, partial )
+ __field( long long, partial )
__field( unsigned short, eh_entries )
),
@@ -2069,22 +2177,24 @@
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->start = start;
+ __entry->end = end;
__entry->depth = depth;
__entry->partial = partial;
__entry->eh_entries = le16_to_cpu(eh_entries);
),
- TP_printk("dev %d,%d ino %lu since %u depth %d partial %u "
+ TP_printk("dev %d,%d ino %lu since %u end %u depth %d partial %lld "
"remaining_entries %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
(unsigned) __entry->start,
+ (unsigned) __entry->end,
__entry->depth,
- (unsigned) __entry->partial,
+ (long long) __entry->partial,
(unsigned short) __entry->eh_entries)
);
-TRACE_EVENT(ext4_es_insert_extent,
+DECLARE_EVENT_CLASS(ext4__es_extent,
TP_PROTO(struct inode *inode, struct extent_status *es),
TP_ARGS(inode, es),
@@ -2095,7 +2205,7 @@
__field( ext4_lblk_t, lblk )
__field( ext4_lblk_t, len )
__field( ext4_fsblk_t, pblk )
- __field( unsigned long long, status )
+ __field( char, status )
),
TP_fast_assign(
@@ -2107,11 +2217,23 @@
__entry->status = ext4_es_status(es);
),
- TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx",
+ TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
__entry->lblk, __entry->len,
- __entry->pblk, __entry->status)
+ __entry->pblk, show_extent_status(__entry->status))
+);
+
+DEFINE_EVENT(ext4__es_extent, ext4_es_insert_extent,
+ TP_PROTO(struct inode *inode, struct extent_status *es),
+
+ TP_ARGS(inode, es)
+);
+
+DEFINE_EVENT(ext4__es_extent, ext4_es_cache_extent,
+ TP_PROTO(struct inode *inode, struct extent_status *es),
+
+ TP_ARGS(inode, es)
);
TRACE_EVENT(ext4_es_remove_extent,
@@ -2172,7 +2294,7 @@
__field( ext4_lblk_t, lblk )
__field( ext4_lblk_t, len )
__field( ext4_fsblk_t, pblk )
- __field( unsigned long long, status )
+ __field( char, status )
),
TP_fast_assign(
@@ -2184,11 +2306,11 @@
__entry->status = ext4_es_status(es);
),
- TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx",
+ TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
__entry->lblk, __entry->len,
- __entry->pblk, __entry->status)
+ __entry->pblk, show_extent_status(__entry->status))
);
TRACE_EVENT(ext4_es_lookup_extent_enter,
@@ -2225,7 +2347,7 @@
__field( ext4_lblk_t, lblk )
__field( ext4_lblk_t, len )
__field( ext4_fsblk_t, pblk )
- __field( unsigned long long, status )
+ __field( char, status )
__field( int, found )
),
@@ -2239,15 +2361,15 @@
__entry->found = found;
),
- TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %llx",
+ TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino, __entry->found,
__entry->lblk, __entry->len,
__entry->found ? __entry->pblk : 0,
- __entry->found ? __entry->status : 0)
+ show_extent_status(__entry->found ? __entry->status : 0))
);
-TRACE_EVENT(ext4_es_shrink_enter,
+DECLARE_EVENT_CLASS(ext4__es_shrink_enter,
TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
TP_ARGS(sb, nr_to_scan, cache_cnt),
@@ -2269,26 +2391,94 @@
__entry->nr_to_scan, __entry->cache_cnt)
);
-TRACE_EVENT(ext4_es_shrink_exit,
- TP_PROTO(struct super_block *sb, int shrunk_nr, int cache_cnt),
+DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count,
+ TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
- TP_ARGS(sb, shrunk_nr, cache_cnt),
+ TP_ARGS(sb, nr_to_scan, cache_cnt)
+);
+
+DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter,
+ TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
+
+ TP_ARGS(sb, nr_to_scan, cache_cnt)
+);
+
+TRACE_EVENT(ext4_es_shrink_scan_exit,
+ TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt),
+
+ TP_ARGS(sb, nr_shrunk, cache_cnt),
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( int, shrunk_nr )
+ __field( int, nr_shrunk )
__field( int, cache_cnt )
),
TP_fast_assign(
__entry->dev = sb->s_dev;
- __entry->shrunk_nr = shrunk_nr;
+ __entry->nr_shrunk = nr_shrunk;
__entry->cache_cnt = cache_cnt;
),
- TP_printk("dev %d,%d shrunk_nr %d cache_cnt %d",
+ TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->shrunk_nr, __entry->cache_cnt)
+ __entry->nr_shrunk, __entry->cache_cnt)
+);
+
+TRACE_EVENT(ext4_collapse_range,
+ TP_PROTO(struct inode *inode, loff_t offset, loff_t len),
+
+ TP_ARGS(inode, offset, len),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, offset)
+ __field(loff_t, len)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->offset = offset;
+ __entry->len = len;
+ ),
+
+ TP_printk("dev %d,%d ino %lu offset %lld len %lld",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ __entry->offset, __entry->len)
+);
+
+TRACE_EVENT(ext4_es_shrink,
+ TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time,
+ int skip_precached, int nr_skipped, int retried),
+
+ TP_ARGS(sb, nr_shrunk, scan_time, skip_precached, nr_skipped, retried),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( int, nr_shrunk )
+ __field( unsigned long long, scan_time )
+ __field( int, skip_precached )
+ __field( int, nr_skipped )
+ __field( int, retried )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->nr_shrunk = nr_shrunk;
+ __entry->scan_time = div_u64(scan_time, 1000);
+ __entry->skip_precached = skip_precached;
+ __entry->nr_skipped = nr_skipped;
+ __entry->retried = retried;
+ ),
+
+ TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu skip_precached %d "
+ "nr_skipped %d retried %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk,
+ __entry->scan_time, __entry->skip_precached,
+ __entry->nr_skipped, __entry->retried)
);
#endif /* _TRACE_EXT4_H */
diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h
index 0421f49..e3175d0 100644
--- a/include/trace/events/filemap.h
+++ b/include/trace/events/filemap.h
@@ -52,6 +52,52 @@
TP_ARGS(page)
);
+DECLARE_EVENT_CLASS(mm_filemap_find_page_cache_miss,
+
+ TP_PROTO(struct file *file, loff_t pos, size_t count, int read),
+
+ TP_ARGS(file, pos, count, read),
+
+ TP_STRUCT__entry(
+ __array(char, path, MAX_FILTER_STR_VAL)
+ __field(char *, path_name)
+ __field(loff_t, pos)
+ __field(size_t, count)
+ __field(int, miss)
+ ),
+
+ TP_fast_assign(
+ __entry->path_name = d_path(&file->f_path, __entry->path, MAX_FILTER_STR_VAL);
+ __entry->pos = pos;
+ __entry->count = count;
+ __entry->miss = 0;
+ if ((pos & ~PAGE_CACHE_MASK) || (count % PAGE_SIZE) || read) {
+ unsigned long ret;
+ rcu_read_lock();
+ ret = (count ? page_cache_next_hole(file->f_mapping,
+ (pos >> PAGE_CACHE_SHIFT), ((count - 1) >> PAGE_CACHE_SHIFT) + 1) : 0);
+ rcu_read_unlock();
+ __entry->miss = (ret >= (pos >> PAGE_CACHE_SHIFT) &&
+ ret <= ((pos + count - 1) >> PAGE_CACHE_SHIFT));
+ }
+ ),
+
+ TP_printk("path_name %s pos %lld count %zu miss %s",
+ __entry->path_name,
+ __entry->pos, __entry->count,
+ (__entry->miss ? "yes" : "no"))
+);
+
+DEFINE_EVENT(mm_filemap_find_page_cache_miss, mm_filemap_do_generic_file_read,
+ TP_PROTO(struct file *file, loff_t pos, size_t count, int read),
+ TP_ARGS(file, pos, count, read)
+ );
+
+DEFINE_EVENT(mm_filemap_find_page_cache_miss, mm_filemap_generic_perform_write,
+ TP_PROTO(struct file *file, loff_t pos, size_t count, int read),
+ TP_ARGS(file, pos, count, read)
+ );
+
#endif /* _TRACE_FILEMAP_H */
/* This part must be outside protection */
diff --git a/include/trace/events/gpu.h b/include/trace/events/gpu.h
new file mode 100644
index 0000000..7e15cdf
--- /dev/null
+++ b/include/trace/events/gpu.h
@@ -0,0 +1,143 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gpu
+
+#if !defined(_TRACE_GPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GPU_H
+
+#include <linux/tracepoint.h>
+#include <linux/time.h>
+
+#define show_secs_from_ns(ns) \
+ ({ \
+ u64 t = ns + (NSEC_PER_USEC / 2); \
+ do_div(t, NSEC_PER_SEC); \
+ t; \
+ })
+
+#define show_usecs_from_ns(ns) \
+ ({ \
+ u64 t = ns + (NSEC_PER_USEC / 2) ; \
+ u32 rem; \
+ do_div(t, NSEC_PER_USEC); \
+ rem = do_div(t, USEC_PER_SEC); \
+ })
+
+/*
+ * The gpu_sched_switch event indicates that a switch from one GPU context to
+ * another occurred on one of the GPU hardware blocks.
+ *
+ * The gpu_name argument identifies the GPU hardware block. Each independently
+ * scheduled GPU hardware block should have a different name. This may be used
+ * in different ways for different GPUs. For example, if a GPU includes
+ * multiple processing cores it may use names "GPU 0", "GPU 1", etc. If a GPU
+ * includes a separately scheduled 2D and 3D hardware block, it might use the
+ * names "2D" and "3D".
+ *
+ * The timestamp argument is the timestamp at which the switch occurred on the
+ * GPU. These timestamps are in units of nanoseconds and must use
+ * approximately the same time as sched_clock, though they need not come from
+ * any CPU clock. The timestamps for a single hardware block must be
+ * monotonically nondecreasing. This means that if a variable compensation
+ * offset is used to translate from some other clock to the sched_clock, then
+ * care must be taken when increasing that offset, and doing so may result in
+ * multiple events with the same timestamp.
+ *
+ * The next_ctx_id argument identifies the next context that was running on
+ * the GPU hardware block. A value of 0 indicates that the hardware block
+ * will be idle.
+ *
+ * The next_prio argument indicates the priority of the next context at the
+ * time of the event. The exact numeric values may mean different things for
+ * different GPUs, but they should follow the rule that lower values indicate a
+ * higher priority.
+ *
+ * The next_job_id argument identifies the batch of work that the GPU will be
+ * working on. This should correspond to a job_id that was previously traced
+ * as a gpu_job_enqueue event when the batch of work was created.
+ */
+TRACE_EVENT(gpu_sched_switch,
+
+ TP_PROTO(const char *gpu_name, u64 timestamp,
+ u32 next_ctx_id, s32 next_prio, u32 next_job_id),
+
+ TP_ARGS(gpu_name, timestamp, next_ctx_id, next_prio, next_job_id),
+
+ TP_STRUCT__entry(
+ __string( gpu_name, gpu_name )
+ __field( u64, timestamp )
+ __field( u32, next_ctx_id )
+ __field( s32, next_prio )
+ __field( u32, next_job_id )
+ ),
+
+ TP_fast_assign(
+ __assign_str(gpu_name, gpu_name);
+ __entry->timestamp = timestamp;
+ __entry->next_ctx_id = next_ctx_id;
+ __entry->next_prio = next_prio;
+ __entry->next_job_id = next_job_id;
+ ),
+
+ TP_printk("gpu_name=%s ts=%llu.%06lu next_ctx_id=%lu next_prio=%ld "
+ "next_job_id=%lu",
+ __get_str(gpu_name),
+ (unsigned long long)show_secs_from_ns(__entry->timestamp),
+ (unsigned long)show_usecs_from_ns(__entry->timestamp),
+ (unsigned long)__entry->next_ctx_id,
+ (long)__entry->next_prio,
+ (unsigned long)__entry->next_job_id)
+);
+
+/*
+ * The gpu_job_enqueue event indicates that a batch of work has been queued up
+ * to be processed by the GPU. This event is not intended to indicate that
+ * the batch of work has been submitted to the GPU hardware, but rather that
+ * it has been submitted to the GPU kernel driver.
+ *
+ * This event should be traced on the thread that initiated the work being
+ * queued. For example, if a batch of work is submitted to the kernel by a
+ * userland thread, the event should be traced on that thread.
+ *
+ * The ctx_id field identifies the GPU context in which the batch of work
+ * being queued is to be run.
+ *
+ * The job_id field identifies the batch of work being queued within the given
+ * GPU context. The first batch of work submitted for a given GPU context
+ * should have a job_id of 0, and each subsequent batch of work should
+ * increment the job_id by 1.
+ *
+ * The type field identifies the type of the job being enqueued. The job
+ * types may be different for different GPU hardware. For example, a GPU may
+ * differentiate between "2D", "3D", and "compute" jobs.
+ */
+TRACE_EVENT(gpu_job_enqueue,
+
+ TP_PROTO(u32 ctx_id, u32 job_id, const char *type),
+
+ TP_ARGS(ctx_id, job_id, type),
+
+ TP_STRUCT__entry(
+ __field( u32, ctx_id )
+ __field( u32, job_id )
+ __string( type, type )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx_id = ctx_id;
+ __entry->job_id = job_id;
+ __assign_str(type, type);
+ ),
+
+ TP_printk("ctx_id=%lu job_id=%lu type=%s",
+ (unsigned long)__entry->ctx_id,
+ (unsigned long)__entry->job_id,
+ __get_str(type))
+);
+
+#undef show_secs_from_ns
+#undef show_usecs_from_ns
+
+#endif /* _TRACE_GPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 6bc943e..4ad10ba 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -267,8 +267,8 @@
TRACE_EVENT(mm_page_alloc_extfrag,
TP_PROTO(struct page *page,
- int alloc_order, int fallback_order,
- int alloc_migratetype, int fallback_migratetype),
+ int alloc_order, int fallback_order,
+ int alloc_migratetype, int fallback_migratetype),
TP_ARGS(page,
alloc_order, fallback_order,
@@ -280,6 +280,7 @@
__field( int, fallback_order )
__field( int, alloc_migratetype )
__field( int, fallback_migratetype )
+ __field( int, change_ownership )
),
TP_fast_assign(
@@ -288,6 +289,8 @@
__entry->fallback_order = fallback_order;
__entry->alloc_migratetype = alloc_migratetype;
__entry->fallback_migratetype = fallback_migratetype;
+ __entry->change_ownership = (alloc_migratetype ==
+ get_pageblock_migratetype(page));
),
TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
@@ -299,7 +302,7 @@
__entry->alloc_migratetype,
__entry->fallback_migratetype,
__entry->fallback_order < pageblock_order,
- __entry->alloc_migratetype == __entry->fallback_migratetype)
+ __entry->change_ownership)
);
#endif /* _TRACE_KMEM_H */
diff --git a/include/trace/events/mmc.h b/include/trace/events/mmc.h
new file mode 100644
index 0000000..82b368d
--- /dev/null
+++ b/include/trace/events/mmc.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mmc
+
+#if !defined(_TRACE_MMC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MMC_H
+
+#include <linux/tracepoint.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/core.h>
+
+/*
+ * Unconditional logging of mmc block erase operations,
+ * including cmd, address, size
+ */
+DECLARE_EVENT_CLASS(mmc_blk_erase_class,
+ TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+ TP_ARGS(cmd, addr, size),
+ TP_STRUCT__entry(
+ __field(unsigned int, cmd)
+ __field(unsigned int, addr)
+ __field(unsigned int, size)
+ ),
+ TP_fast_assign(
+ __entry->cmd = cmd;
+ __entry->addr = addr;
+ __entry->size = size;
+ ),
+ TP_printk("cmd=%u,addr=0x%08x,size=0x%08x",
+ __entry->cmd, __entry->addr, __entry->size)
+);
+
+DEFINE_EVENT(mmc_blk_erase_class, mmc_blk_erase_start,
+ TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+ TP_ARGS(cmd, addr, size));
+
+DEFINE_EVENT(mmc_blk_erase_class, mmc_blk_erase_end,
+ TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+ TP_ARGS(cmd, addr, size));
+
+/*
+ * Logging of start of read or write mmc block operation,
+ * including cmd, address, size
+ */
+DECLARE_EVENT_CLASS(mmc_blk_rw_class,
+ TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+ TP_ARGS(cmd, addr, data),
+ TP_STRUCT__entry(
+ __field(unsigned int, cmd)
+ __field(unsigned int, addr)
+ __field(unsigned int, size)
+ ),
+ TP_fast_assign(
+ __entry->cmd = cmd;
+ __entry->addr = addr;
+ __entry->size = data->blocks;
+ ),
+ TP_printk("cmd=%u,addr=0x%08x,size=0x%08x",
+ __entry->cmd, __entry->addr, __entry->size)
+);
+
+DEFINE_EVENT_CONDITION(mmc_blk_rw_class, mmc_blk_rw_start,
+ TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+ TP_ARGS(cmd, addr, data),
+ TP_CONDITION(((cmd == MMC_READ_MULTIPLE_BLOCK) ||
+ (cmd == MMC_WRITE_MULTIPLE_BLOCK)) &&
+ data));
+
+DEFINE_EVENT_CONDITION(mmc_blk_rw_class, mmc_blk_rw_end,
+ TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+ TP_ARGS(cmd, addr, data),
+ TP_CONDITION(((cmd == MMC_READ_MULTIPLE_BLOCK) ||
+ (cmd == MMC_WRITE_MULTIPLE_BLOCK)) &&
+ data));
+#endif /* _TRACE_MMC_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 427acab..3702a76 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -48,6 +48,31 @@
TP_ARGS(frequency, cpu_id)
);
+TRACE_EVENT(cpu_frequency_limits,
+
+ TP_PROTO(unsigned int max_freq, unsigned int min_freq,
+ unsigned int cpu_id),
+
+ TP_ARGS(max_freq, min_freq, cpu_id),
+
+ TP_STRUCT__entry(
+ __field( u32, min_freq )
+ __field( u32, max_freq )
+ __field( u32, cpu_id )
+ ),
+
+ TP_fast_assign(
+ __entry->min_freq = min_freq;
+ __entry->max_freq = max_freq;
+ __entry->cpu_id = cpu_id;
+ ),
+
+ TP_printk("min=%lu max=%lu cpu_id=%lu",
+ (unsigned long)__entry->min_freq,
+ (unsigned long)__entry->max_freq,
+ (unsigned long)__entry->cpu_id)
+);
+
TRACE_EVENT(machine_suspend,
TP_PROTO(unsigned int state),
@@ -146,6 +171,25 @@
TP_ARGS(name, state, cpu_id)
);
+TRACE_EVENT(clock_set_parent,
+
+ TP_PROTO(const char *name, const char *parent_name),
+
+ TP_ARGS(name, parent_name),
+
+ TP_STRUCT__entry(
+ __string( name, name )
+ __string( parent_name, parent_name )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, name);
+ __assign_str(parent_name, parent_name);
+ ),
+
+ TP_printk("%s parent=%s", __get_str(name), __get_str(parent_name))
+);
+
/*
* The power domain events are used for power domains transitions
*/
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e5586ca..303e963 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -182,6 +182,31 @@
__entry->orig_cpu, __entry->dest_cpu)
);
+/*
+ * Tracepoint for a CPU going offline/online:
+ */
+TRACE_EVENT(sched_cpu_hotplug,
+
+ TP_PROTO(int affected_cpu, int error, int status),
+
+ TP_ARGS(affected_cpu, error, status),
+
+ TP_STRUCT__entry(
+ __field( int, affected_cpu )
+ __field( int, error )
+ __field( int, status )
+ ),
+
+ TP_fast_assign(
+ __entry->affected_cpu = affected_cpu;
+ __entry->error = error;
+ __entry->status = status;
+ ),
+
+ TP_printk("cpu %d %s error=%d", __entry->affected_cpu,
+ __entry->status ? "online" : "offline", __entry->error)
+);
+
DECLARE_EVENT_CLASS(sched_process_template,
TP_PROTO(struct task_struct *p),
@@ -210,7 +235,7 @@
DEFINE_EVENT(sched_process_template, sched_process_free,
TP_PROTO(struct task_struct *p),
TP_ARGS(p));
-
+
/*
* Tracepoint for a task exiting:
@@ -369,6 +394,30 @@
TP_ARGS(tsk, delay));
/*
+ * Tracepoint for recording the cause of uninterruptible sleep.
+ */
+TRACE_EVENT(sched_blocked_reason,
+
+ TP_PROTO(struct task_struct *tsk),
+
+ TP_ARGS(tsk),
+
+ TP_STRUCT__entry(
+ __field( pid_t, pid )
+ __field( void*, caller )
+ __field( bool, io_wait )
+ ),
+
+ TP_fast_assign(
+ __entry->pid = tsk->pid;
+ __entry->caller = (void*)get_wchan(tsk);
+ __entry->io_wait = tsk->in_iowait;
+ ),
+
+ TP_printk("pid=%d iowait=%d caller=%pS", __entry->pid, __entry->io_wait, __entry->caller)
+);
+
+/*
* Tracepoint for accounting runtime (time the task is executing
* on a CPU).
*/
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 0cc74c4..b422ad5 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -692,9 +692,19 @@
__SYSCALL(__NR_kcmp, sys_kcmp)
#define __NR_finit_module 273
__SYSCALL(__NR_finit_module, sys_finit_module)
+/* Backporting seccomp, skip a few ...
+ * #define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+ * #define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+ * #define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+ */
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
#undef __NR_syscalls
-#define __NR_syscalls 274
+#define __NR_syscalls 278
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index bdc6e87..639cd24 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
+header-y += android/
header-y += byteorder/
header-y += can/
header-y += caif/
diff --git a/include/uapi/linux/android/Kbuild b/include/uapi/linux/android/Kbuild
new file mode 100644
index 0000000..ca011ee
--- /dev/null
+++ b/include/uapi/linux/android/Kbuild
@@ -0,0 +1,2 @@
+# UAPI Header export list
+header-y += binder.h
diff --git a/drivers/staging/android/binder.h b/include/uapi/linux/android/binder.h
similarity index 77%
rename from drivers/staging/android/binder.h
rename to include/uapi/linux/android/binder.h
index dbe81ce..c653800 100644
--- a/drivers/staging/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -17,8 +17,8 @@
*
*/
-#ifndef _LINUX_BINDER_H
-#define _LINUX_BINDER_H
+#ifndef _UAPI_LINUX_BINDER_H
+#define _UAPI_LINUX_BINDER_H
#include <linux/ioctl.h>
@@ -39,6 +39,14 @@
FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100,
};
+#ifdef BINDER_IPC_32BIT
+typedef __u32 binder_size_t;
+typedef __u32 binder_uintptr_t;
+#else
+typedef __u64 binder_size_t;
+typedef __u64 binder_uintptr_t;
+#endif
+
/*
* This is the flattened representation of a Binder object for transfer
* between processes. The 'offsets' supplied as part of a binder transaction
@@ -48,17 +56,17 @@
*/
struct flat_binder_object {
/* 8 bytes for large_flat_header. */
- unsigned long type;
- unsigned long flags;
+ __u32 type;
+ __u32 flags;
/* 8 bytes of data. */
union {
- void __user *binder; /* local object */
- signed long handle; /* remote object */
+ binder_uintptr_t binder; /* local object */
+ __u32 handle; /* remote object */
};
/* extra data associated with local object */
- void __user *cookie;
+ binder_uintptr_t cookie;
};
/*
@@ -67,26 +75,30 @@
*/
struct binder_write_read {
- signed long write_size; /* bytes to write */
- signed long write_consumed; /* bytes consumed by driver */
- unsigned long write_buffer;
- signed long read_size; /* bytes to read */
- signed long read_consumed; /* bytes consumed by driver */
- unsigned long read_buffer;
+ binder_size_t write_size; /* bytes to write */
+ binder_size_t write_consumed; /* bytes consumed by driver */
+ binder_uintptr_t write_buffer;
+ binder_size_t read_size; /* bytes to read */
+ binder_size_t read_consumed; /* bytes consumed by driver */
+ binder_uintptr_t read_buffer;
};
/* Use with BINDER_VERSION, driver fills in fields. */
struct binder_version {
/* driver protocol version -- increment with incompatible change */
- signed long protocol_version;
+ __s32 protocol_version;
};
/* This is the current protocol version. */
+#ifdef BINDER_IPC_32BIT
#define BINDER_CURRENT_PROTOCOL_VERSION 7
+#else
+#define BINDER_CURRENT_PROTOCOL_VERSION 8
+#endif
#define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read)
#define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64)
-#define BINDER_SET_MAX_THREADS _IOW('b', 5, size_t)
+#define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32)
#define BINDER_SET_IDLE_PRIORITY _IOW('b', 6, __s32)
#define BINDER_SET_CONTEXT_MGR _IOW('b', 7, __s32)
#define BINDER_THREAD_EXIT _IOW('b', 8, __s32)
@@ -119,18 +131,20 @@
* identifying the target and contents of the transaction.
*/
union {
- size_t handle; /* target descriptor of command transaction */
- void *ptr; /* target descriptor of return transaction */
+ /* target descriptor of command transaction */
+ __u32 handle;
+ /* target descriptor of return transaction */
+ binder_uintptr_t ptr;
} target;
- void *cookie; /* target object cookie */
- unsigned int code; /* transaction command */
+ binder_uintptr_t cookie; /* target object cookie */
+ __u32 code; /* transaction command */
/* General information about the transaction. */
- unsigned int flags;
+ __u32 flags;
pid_t sender_pid;
uid_t sender_euid;
- size_t data_size; /* number of bytes of data */
- size_t offsets_size; /* number of bytes of offsets */
+ binder_size_t data_size; /* number of bytes of data */
+ binder_size_t offsets_size; /* number of bytes of offsets */
/* If this transaction is inline, the data immediately
* follows here; otherwise, it ends with a pointer to
@@ -139,32 +153,37 @@
union {
struct {
/* transaction data */
- const void __user *buffer;
+ binder_uintptr_t buffer;
/* offsets from buffer to flat_binder_object structs */
- const void __user *offsets;
+ binder_uintptr_t offsets;
} ptr;
- uint8_t buf[8];
+ __u8 buf[8];
} data;
};
struct binder_ptr_cookie {
- void *ptr;
- void *cookie;
+ binder_uintptr_t ptr;
+ binder_uintptr_t cookie;
};
+struct binder_handle_cookie {
+ __u32 handle;
+ binder_uintptr_t cookie;
+} __packed;
+
struct binder_pri_desc {
- int priority;
- int desc;
+ __s32 priority;
+ __u32 desc;
};
struct binder_pri_ptr_cookie {
- int priority;
- void *ptr;
- void *cookie;
+ __s32 priority;
+ binder_uintptr_t ptr;
+ binder_uintptr_t cookie;
};
enum binder_driver_return_protocol {
- BR_ERROR = _IOR('r', 0, int),
+ BR_ERROR = _IOR('r', 0, __s32),
/*
* int: error code
*/
@@ -178,7 +197,7 @@
* binder_transaction_data: the received command.
*/
- BR_ACQUIRE_RESULT = _IOR('r', 4, int),
+ BR_ACQUIRE_RESULT = _IOR('r', 4, __s32),
/*
* not currently supported
* int: 0 if the last bcATTEMPT_ACQUIRE was not successful.
@@ -235,11 +254,11 @@
* stop threadpool thread
*/
- BR_DEAD_BINDER = _IOR('r', 15, void *),
+ BR_DEAD_BINDER = _IOR('r', 15, binder_uintptr_t),
/*
* void *: cookie
*/
- BR_CLEAR_DEATH_NOTIFICATION_DONE = _IOR('r', 16, void *),
+ BR_CLEAR_DEATH_NOTIFICATION_DONE = _IOR('r', 16, binder_uintptr_t),
/*
* void *: cookie
*/
@@ -258,22 +277,22 @@
* binder_transaction_data: the sent command.
*/
- BC_ACQUIRE_RESULT = _IOW('c', 2, int),
+ BC_ACQUIRE_RESULT = _IOW('c', 2, __s32),
/*
* not currently supported
* int: 0 if the last BR_ATTEMPT_ACQUIRE was not successful.
* Else you have acquired a primary reference on the object.
*/
- BC_FREE_BUFFER = _IOW('c', 3, int),
+ BC_FREE_BUFFER = _IOW('c', 3, binder_uintptr_t),
/*
* void *: ptr to transaction data received on a read
*/
- BC_INCREFS = _IOW('c', 4, int),
- BC_ACQUIRE = _IOW('c', 5, int),
- BC_RELEASE = _IOW('c', 6, int),
- BC_DECREFS = _IOW('c', 7, int),
+ BC_INCREFS = _IOW('c', 4, __u32),
+ BC_ACQUIRE = _IOW('c', 5, __u32),
+ BC_RELEASE = _IOW('c', 6, __u32),
+ BC_DECREFS = _IOW('c', 7, __u32),
/*
* int: descriptor
*/
@@ -308,23 +327,23 @@
* of looping threads it has available.
*/
- BC_REQUEST_DEATH_NOTIFICATION = _IOW('c', 14, struct binder_ptr_cookie),
+ BC_REQUEST_DEATH_NOTIFICATION = _IOW('c', 14, struct binder_handle_cookie),
/*
- * void *: ptr to binder
+ * int: handle
* void *: cookie
*/
- BC_CLEAR_DEATH_NOTIFICATION = _IOW('c', 15, struct binder_ptr_cookie),
+ BC_CLEAR_DEATH_NOTIFICATION = _IOW('c', 15, struct binder_handle_cookie),
/*
- * void *: ptr to binder
+ * int: handle
* void *: cookie
*/
- BC_DEAD_BINDER_DONE = _IOW('c', 16, void *),
+ BC_DEAD_BINDER_DONE = _IOW('c', 16, binder_uintptr_t),
/*
* void *: cookie
*/
};
-#endif /* _LINUX_BINDER_H */
+#endif /* _UAPI_LINUX_BINDER_H */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 75cef3f..ce8750f 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -324,6 +324,8 @@
/* distinguish syscall tables */
#define __AUDIT_ARCH_64BIT 0x80000000
#define __AUDIT_ARCH_LE 0x40000000
+
+#define AUDIT_ARCH_AARCH64 (EM_AARCH64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
#define AUDIT_ARCH_ALPHA (EM_ALPHA|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
#define AUDIT_ARCH_ARM (EM_ARM|__AUDIT_ARCH_LE)
#define AUDIT_ARCH_ARMEB (EM_ARM)
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 8e2b7ba..59c17a2 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -22,6 +22,7 @@
#define EM_PPC 20 /* PowerPC */
#define EM_PPC64 21 /* PowerPC64 */
#define EM_SPU 23 /* Cell BE SPU */
+#define EM_ARM 40 /* ARM 32 bit */
#define EM_SH 42 /* SuperH */
#define EM_SPARCV9 43 /* SPARC v9 64-bit */
#define EM_IA_64 50 /* HP/Intel IA-64 */
@@ -34,6 +35,7 @@
#define EM_MN10300 89 /* Panasonic/MEI MN10300, AM33 */
#define EM_BLACKFIN 106 /* ADI Blackfin Processor */
#define EM_TI_C6000 140 /* TI C6X DSPs */
+#define EM_AARCH64 183 /* ARM 64 bit */
#define EM_FRV 0x5441 /* Fujitsu FR-V */
#define EM_AVR32 0x18ad /* Atmel AVR32 */
diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h
index 990c4cc..bc5e796 100644
--- a/include/uapi/linux/falloc.h
+++ b/include/uapi/linux/falloc.h
@@ -5,5 +5,41 @@
#define FALLOC_FL_PUNCH_HOLE 0x02 /* de-allocates range */
#define FALLOC_FL_NO_HIDE_STALE 0x04 /* reserved codepoint */
+/*
+ * FALLOC_FL_COLLAPSE_RANGE is used to remove a range of a file
+ * without leaving a hole in the file. The contents of the file beyond
+ * the range being removed is appended to the start offset of the range
+ * being removed (i.e. the hole that was punched is "collapsed"),
+ * resulting in a file layout that looks like the range that was
+ * removed never existed. As such collapsing a range of a file changes
+ * the size of the file, reducing it by the same length of the range
+ * that has been removed by the operation.
+ *
+ * Different filesystems may implement different limitations on the
+ * granularity of the operation. Most will limit operations to
+ * filesystem block size boundaries, but this boundary may be larger or
+ * smaller depending on the filesystem and/or the configuration of the
+ * filesystem or file.
+ *
+ * Attempting to collapse a range that crosses the end of the file is
+ * considered an illegal operation - just use ftruncate(2) if you need
+ * to collapse a range that crosses EOF.
+ */
+#define FALLOC_FL_COLLAPSE_RANGE 0x08
+
+/*
+ * FALLOC_FL_ZERO_RANGE is used to convert a range of file to zeros preferably
+ * without issuing data IO. Blocks should be preallocated for the regions that
+ * span holes in the file, and the entire range is preferable converted to
+ * unwritten extents - even though file system may choose to zero out the
+ * extent or do whatever which will result in reading zeros from the range
+ * while the range remains allocated for the file.
+ *
+ * This can be also used to preallocate blocks past EOF in the same way as
+ * with fallocate. Flag FALLOC_FL_KEEP_SIZE should cause the inode
+ * size to remain the same.
+ */
+#define FALLOC_FL_ZERO_RANGE 0x10
+
#endif /* _UAPI_FALLOC_H_ */
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 51da65b..9dcdb62 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -49,6 +49,8 @@
FRA_TABLE, /* Extended table id */
FRA_FWMASK, /* mask for netfilter mark */
FRA_OIFNAME,
+ FRA_UID_START, /* UID range */
+ FRA_UID_END,
__FRA_MAX
};
diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h
index d830747..0c51d61 100644
--- a/include/uapi/linux/fiemap.h
+++ b/include/uapi/linux/fiemap.h
@@ -40,6 +40,7 @@
#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */
#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */
+#define FIEMAP_FLAG_CACHE 0x00000004 /* request caching of the extents */
#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index a4ed56c..5014a5c 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -154,6 +154,8 @@
#define FITHAW _IOWR('X', 120, int) /* Thaw */
#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
+#define FIDTRIM _IOWR('f', 128, struct fstrim_range) /* Deep discard trim */
+
#define FS_IOC_GETFLAGS _IOR('f', 1, long)
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 60bb2f9..c590276 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -343,6 +343,7 @@
FUSE_BATCH_FORGET = 42,
FUSE_FALLOCATE = 43,
FUSE_READDIRPLUS = 44,
+ FUSE_CANONICAL_PATH= 2016,
/* CUSE specific operations */
CUSE_INIT = 4096,
diff --git a/include/uapi/linux/if_pppolac.h b/include/uapi/linux/if_pppolac.h
new file mode 100644
index 0000000..b7eb8153
--- /dev/null
+++ b/include/uapi/linux/if_pppolac.h
@@ -0,0 +1,33 @@
+/* include/uapi/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOLAC_H
+#define _UAPI_LINUX_IF_PPPOLAC_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppolac {
+ sa_family_t sa_family; /* AF_PPPOX */
+ unsigned int sa_protocol; /* PX_PROTO_OLAC */
+ int udp_socket;
+ struct __attribute__((packed)) {
+ __u16 tunnel, session;
+ } local, remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOLAC_H */
diff --git a/include/uapi/linux/if_pppopns.h b/include/uapi/linux/if_pppopns.h
new file mode 100644
index 0000000..a392b52
--- /dev/null
+++ b/include/uapi/linux/if_pppopns.h
@@ -0,0 +1,32 @@
+/* include/uapi/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOPNS_H
+#define _UAPI_LINUX_IF_PPPOPNS_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppopns {
+ sa_family_t sa_family; /* AF_PPPOX */
+ unsigned int sa_protocol; /* PX_PROTO_OPNS */
+ int tcp_socket;
+ __u16 local;
+ __u16 remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOPNS_H */
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index e36a4ae..87f478b 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -23,6 +23,8 @@
#include <linux/socket.h>
#include <linux/if_ether.h>
#include <linux/if_pppol2tp.h>
+#include <linux/if_pppolac.h>
+#include <linux/if_pppopns.h>
/* For user-space programs to pick up these definitions
* which they wouldn't get otherwise without defining __KERNEL__
@@ -56,7 +58,9 @@
#define PX_PROTO_OE 0 /* Currently just PPPoE */
#define PX_PROTO_OL2TP 1 /* Now L2TP also */
#define PX_PROTO_PPTP 2
-#define PX_MAX_PROTO 3
+#define PX_PROTO_OLAC 3
+#define PX_PROTO_OPNS 4
+#define PX_MAX_PROTO 5
struct sockaddr_pppox {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index 4649ee3..a86f530 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -153,6 +153,9 @@
#define EVIOCGRAB _IOW('E', 0x90, int) /* Grab/Release device */
+#define EVIOCGSUSPENDBLOCK _IOR('E', 0x91, int) /* get suspend block enable */
+#define EVIOCSSUSPENDBLOCK _IOW('E', 0x91, int) /* set suspend block enable */
+
#define EVIOCSCLOCKID _IOW('E', 0xa0, int) /* Set clockid to be used for timestamps */
/*
@@ -458,10 +461,14 @@
#define KEY_VIDEO_NEXT 241 /* drive next video source */
#define KEY_VIDEO_PREV 242 /* drive previous video source */
#define KEY_BRIGHTNESS_CYCLE 243 /* brightness up, after max is min */
-#define KEY_BRIGHTNESS_ZERO 244 /* brightness off, use ambient */
+#define KEY_BRIGHTNESS_AUTO 244 /* Set Auto Brightness: manual
+ brightness control is off,
+ rely on ambient */
+#define KEY_BRIGHTNESS_ZERO KEY_BRIGHTNESS_AUTO
#define KEY_DISPLAY_OFF 245 /* display device to off state */
-#define KEY_WIMAX 246
+#define KEY_WWAN 246 /* Wireless WAN (LTE, UMTS, GSM, etc.) */
+#define KEY_WIMAX KEY_WWAN
#define KEY_RFKILL 247 /* Key that controls all radios */
#define KEY_MICMUTE 248 /* Mute / unmute the microphone */
@@ -506,11 +513,15 @@
#define BTN_DEAD 0x12f
#define BTN_GAMEPAD 0x130
-#define BTN_A 0x130
-#define BTN_B 0x131
+#define BTN_SOUTH 0x130
+#define BTN_A BTN_SOUTH
+#define BTN_EAST 0x131
+#define BTN_B BTN_EAST
#define BTN_C 0x132
-#define BTN_X 0x133
-#define BTN_Y 0x134
+#define BTN_NORTH 0x133
+#define BTN_X BTN_NORTH
+#define BTN_WEST 0x134
+#define BTN_Y BTN_WEST
#define BTN_Z 0x135
#define BTN_TL 0x136
#define BTN_TR 0x137
@@ -623,6 +634,7 @@
#define KEY_ADDRESSBOOK 0x1ad /* AL Contacts/Address Book */
#define KEY_MESSENGER 0x1ae /* AL Instant Messaging */
#define KEY_DISPLAYTOGGLE 0x1af /* Turn display (LCD) on and off */
+#define KEY_BRIGHTNESS_TOGGLE KEY_DISPLAYTOGGLE
#define KEY_SPELLCHECK 0x1b0 /* AL Spell Check */
#define KEY_LOGOFF 0x1b1 /* AL Logoff */
@@ -707,6 +719,24 @@
#define KEY_ATTENDANT_TOGGLE 0x21d /* Attendant call on or off */
#define KEY_LIGHTS_TOGGLE 0x21e /* Reading light on or off */
+#define BTN_DPAD_UP 0x220
+#define BTN_DPAD_DOWN 0x221
+#define BTN_DPAD_LEFT 0x222
+#define BTN_DPAD_RIGHT 0x223
+
+#define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */
+
+#define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */
+#define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */
+#define KEY_JOURNAL 0x242 /* AL Log/Journal/Timecard */
+#define KEY_CONTROLPANEL 0x243 /* AL Control Panel */
+#define KEY_APPSELECT 0x244 /* AL Select Task/Application */
+#define KEY_SCREENSAVER 0x245 /* AL Screen Saver */
+#define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */
+
+#define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */
+#define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */
+
#define BTN_TRIGGER_HAPPY 0x2c0
#define BTN_TRIGGER_HAPPY1 0x2c0
#define BTN_TRIGGER_HAPPY2 0x2c1
@@ -844,6 +874,7 @@
#define SW_FRONT_PROXIMITY 0x0b /* set = front proximity sensor active */
#define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */
#define SW_LINEIN_INSERT 0x0d /* set = inserted */
+#define SW_MUTE_DEVICE 0x0e /* set = device disabled */
#define SW_MAX 0x0f
#define SW_CNT (SW_MAX+1)
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 4bda4cf..15ac588 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -160,6 +160,9 @@
DEVCONF_ACCEPT_DAD,
DEVCONF_FORCE_TLLAO,
DEVCONF_NDISC_NOTIFY,
+ DEVCONF_ACCEPT_RA_RT_TABLE,
+ DEVCONF_USE_OPTIMISTIC,
+ DEVCONF_USE_OIF_ADDRS_ONLY,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/keychord.h b/include/uapi/linux/keychord.h
new file mode 100644
index 0000000..ea7cf4d
--- /dev/null
+++ b/include/uapi/linux/keychord.h
@@ -0,0 +1,52 @@
+/*
+ * Key chord input driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef _UAPI_LINUX_KEYCHORD_H_
+#define _UAPI_LINUX_KEYCHORD_H_
+
+#include <linux/input.h>
+
+#define KEYCHORD_VERSION 1
+
+/*
+ * One or more input_keychord structs are written to /dev/keychord
+ * at once to specify the list of keychords to monitor.
+ * Reading /dev/keychord returns the id of a keychord when the
+ * keychord combination is pressed. A keychord is signalled when
+ * all of the keys in the keycode list are in the pressed state.
+ * The order in which the keys are pressed does not matter.
+ * The keychord will not be signalled if keys not in the keycode
+ * list are pressed.
+ * Keychords will not be signalled on key release events.
+ */
+struct input_keychord {
+ /* should be KEYCHORD_VERSION */
+ __u16 version;
+ /*
+ * client specified ID, returned from read()
+ * when this keychord is pressed.
+ */
+ __u16 id;
+
+ /* number of keycodes in this keychord */
+ __u16 count;
+
+ /* variable length array of keycodes */
+ __u16 keycodes[];
+};
+
+#endif /* _UAPI_LINUX_KEYCHORD_H_ */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 2944278..04c5ff2 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -52,6 +52,8 @@
#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
+#define SDCARDFS_SUPER_MAGIC 0xb550ca10
+
#define SMB_SUPER_MAGIC 0x517B
#define CGROUP_SUPER_MAGIC 0x27e0eb
diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h
index f055e58..db4ae0c 100644
--- a/include/uapi/linux/msdos_fs.h
+++ b/include/uapi/linux/msdos_fs.h
@@ -104,6 +104,7 @@
/* <linux/videotext.h> has used 0x72 ('r') in collision, so skip a few */
#define FAT_IOCTL_GET_ATTRIBUTES _IOR('r', 0x10, __u32)
#define FAT_IOCTL_SET_ATTRIBUTES _IOW('r', 0x11, __u32)
+#define VFAT_IOCTL_GET_VOLUME_ID _IOR('r', 0x12, __u32)
struct fat_boot_sector {
__u8 ignored[3]; /* Boot strap short or near jump */
@@ -161,6 +162,17 @@
__le32 reserved2[4];
};
+struct fat_boot_bsx {
+ __u8 drive; /* drive number */
+ __u8 reserved1;
+ __u8 signature; /* extended boot signature */
+ __u8 vol_id[4]; /* volume ID */
+ __u8 vol_label[11]; /* volume label */
+ __u8 type[8]; /* file system type */
+};
+#define FAT16_BSX_OFFSET 36 /* offset of fat_boot_bsx in FAT12 and FAT16 */
+#define FAT32_BSX_OFFSET 64 /* offset of fat_boot_bsx in FAT32 */
+
struct msdos_dir_entry {
__u8 name[MSDOS_NAME];/* name and extension */
__u8 attr; /* attribute bits */
diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h
index 208ae93..faaa28b 100644
--- a/include/uapi/linux/netfilter/xt_IDLETIMER.h
+++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h
@@ -4,6 +4,7 @@
* Header file for Xtables timer target module.
*
* Copyright (C) 2004, 2010 Nokia Corporation
+ *
* Written by Timo Teras <ext-timo.teras@nokia.com>
*
* Converted to x_tables and forward-ported to 2.6.34
@@ -32,12 +33,19 @@
#include <linux/types.h>
#define MAX_IDLETIMER_LABEL_SIZE 28
+#define NLMSG_MAX_SIZE 64
+
+#define NL_EVENT_TYPE_INACTIVE 0
+#define NL_EVENT_TYPE_ACTIVE 1
struct idletimer_tg_info {
__u32 timeout;
char label[MAX_IDLETIMER_LABEL_SIZE];
+ /* Use netlink messages for notification in addition to sysfs */
+ __u8 send_nl_msg;
+
/* for kernel module internal use only */
struct idletimer_tg *timer __attribute__((aligned(8)));
};
diff --git a/include/uapi/linux/netfilter/xt_socket.h b/include/uapi/linux/netfilter/xt_socket.h
index 26d7217..6359456 100644
--- a/include/uapi/linux/netfilter/xt_socket.h
+++ b/include/uapi/linux/netfilter/xt_socket.h
@@ -11,4 +11,10 @@
__u8 flags;
};
+void xt_socket_put_sk(struct sock *sk);
+struct sock *xt_socket_get4_sk(const struct sk_buff *skb,
+ struct xt_action_param *par);
+struct sock *xt_socket_get6_sk(const struct sk_buff *skb,
+ struct xt_action_param *par);
+
#endif /* _XT_SOCKET_H */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index d1e48b5..f6e0d97 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -646,6 +646,28 @@
* @NL80211_CMD_CRIT_PROTOCOL_STOP: Indicates the connection reliability can
* return back to normal.
*
+ * @NL80211_CMD_GET_COALESCE: Get currently supported coalesce rules.
+ * @NL80211_CMD_SET_COALESCE: Configure coalesce rules or clear existing rules.
+ *
+ * @NL80211_CMD_CHANNEL_SWITCH: Perform a channel switch by announcing the
+ * the new channel information (Channel Switch Announcement - CSA)
+ * in the beacon for some time (as defined in the
+ * %NL80211_ATTR_CH_SWITCH_COUNT parameter) and then change to the
+ * new channel. Userspace provides the new channel information (using
+ * %NL80211_ATTR_WIPHY_FREQ and the attributes determining channel
+ * width). %NL80211_ATTR_CH_SWITCH_BLOCK_TX may be supplied to inform
+ * other station that transmission must be blocked until the channel
+ * switch is complete.
+ *
+ * @NL80211_CMD_VENDOR: Vendor-specified command/event. The command is specified
+ * by the %NL80211_ATTR_VENDOR_ID attribute and a sub-command in
+ * %NL80211_ATTR_VENDOR_SUBCMD. Parameter(s) can be transported in
+ * %NL80211_ATTR_VENDOR_DATA.
+ * For feature advertisement, the %NL80211_ATTR_VENDOR_DATA attribute is
+ * used in the wiphy data as a nested attribute containing descriptions
+ * (&struct nl80211_vendor_cmd_info) of the supported vendor commands.
+ * This may also be sent as an event with the same attributes.
+ *
* @NL80211_CMD_MAX: highest used command number
* @__NL80211_CMD_AFTER_LAST: internal use
*/
@@ -808,6 +830,13 @@
NL80211_CMD_CRIT_PROTOCOL_START,
NL80211_CMD_CRIT_PROTOCOL_STOP,
+ NL80211_CMD_GET_COALESCE,
+ NL80211_CMD_SET_COALESCE,
+
+ NL80211_CMD_CHANNEL_SWITCH,
+
+ NL80211_CMD_VENDOR,
+
/* add new commands above here */
/* used to define NL80211_CMD_MAX below */
@@ -1429,6 +1458,72 @@
* @NL80211_ATTR_MAX_CRIT_PROT_DURATION: duration in milliseconds in which
* the connection should have increased reliability (u16).
*
+ * @NL80211_ATTR_PEER_AID: Association ID for the peer TDLS station (u16).
+ * This is similar to @NL80211_ATTR_STA_AID but with a difference of being
+ * allowed to be used with the first @NL80211_CMD_SET_STATION command to
+ * update a TDLS peer STA entry.
+ *
+ * @NL80211_ATTR_COALESCE_RULE: Coalesce rule information.
+ *
+ * @NL80211_ATTR_CH_SWITCH_COUNT: u32 attribute specifying the number of TBTT's
+ * until the channel switch event.
+ * @NL80211_ATTR_CH_SWITCH_BLOCK_TX: flag attribute specifying that transmission
+ * must be blocked on the current channel (before the channel switch
+ * operation).
+ * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information
+ * for the time while performing a channel switch.
+ * @NL80211_ATTR_CSA_C_OFF_BEACON: Offset of the channel switch counter
+ * field in the beacons tail (%NL80211_ATTR_BEACON_TAIL).
+ * @NL80211_ATTR_CSA_C_OFF_PRESP: Offset of the channel switch counter
+ * field in the probe response (%NL80211_ATTR_PROBE_RESP).
+ *
+ * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32.
+ * As specified in the &enum nl80211_rxmgmt_flags.
+ *
+ * @NL80211_ATTR_STA_SUPPORTED_CHANNELS: array of supported channels.
+ *
+ * @NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES: array of supported
+ * supported operating classes.
+ *
+ * @NL80211_ATTR_HANDLE_DFS: A flag indicating whether user space
+ * controls DFS operation in IBSS mode. If the flag is included in
+ * %NL80211_CMD_JOIN_IBSS request, the driver will allow use of DFS
+ * channels and reports radar events to userspace. Userspace is required
+ * to react to radar events, e.g. initiate a channel switch or leave the
+ * IBSS network.
+ *
+ * @NL80211_ATTR_VENDOR_ID: The vendor ID, either a 24-bit OUI or, if
+ * %NL80211_VENDOR_ID_IS_LINUX is set, a special Linux ID (not used yet)
+ * @NL80211_ATTR_VENDOR_SUBCMD: vendor sub-command
+ * @NL80211_ATTR_VENDOR_DATA: data for the vendor command, if any; this
+ * attribute is also used for vendor command feature advertisement
+ * @NL80211_ATTR_VENDOR_EVENTS: used for event list advertising in the wiphy
+ * info, containing a nested array of possible events
+ *
+ * @NL80211_ATTR_QOS_MAP: IP DSCP mapping for Interworking QoS mapping. This
+ * data is in the format defined for the payload of the QoS Map Set element
+ * in IEEE Std 802.11-2012, 8.4.2.97.
+ *
+ * @NL80211_ATTR_MAC_HINT: MAC address recommendation as initial BSS
+ * @NL80211_ATTR_WIPHY_FREQ_HINT: frequency of the recommended initial BSS
+ *
+ * @NL80211_ATTR_MAX_AP_ASSOC_STA: Device attribute that indicates how many
+ * associated stations are supported in AP mode (including P2P GO); u32.
+ * Since drivers may not have a fixed limit on the maximum number (e.g.,
+ * other concurrent operations may affect this), drivers are allowed to
+ * advertise values that cannot always be met. In such cases, an attempt
+ * to add a new station entry with @NL80211_CMD_NEW_STATION may fail.
+ *
+ * @NL80211_ATTR_TDLS_PEER_CAPABILITY: flags for TDLS peer capabilities, u32.
+ * As specified in the &enum nl80211_tdls_peer_capability.
+ *
+ * @NL80211_ATTR_IFACE_SOCKET_OWNER: flag attribute, if set during interface
+ * creation then the new interface will be owned by the netlink socket
+ * that created it and will be destroyed when the socket is closed.
+ * If set during scheduled scan start then the new scan req will be
+ * owned by the netlink socket that created it and the scheduled scan will
+ * be stopped when the socket is closed.
+ *
* @NL80211_ATTR_MAX: highest attribute number currently defined
* @__NL80211_ATTR_AFTER_LAST: internal use
*/
@@ -1727,6 +1822,46 @@
NL80211_ATTR_CRIT_PROT_ID,
NL80211_ATTR_MAX_CRIT_PROT_DURATION,
+ NL80211_ATTR_PEER_AID,
+
+ NL80211_ATTR_COALESCE_RULE,
+
+ NL80211_ATTR_CH_SWITCH_COUNT,
+ NL80211_ATTR_CH_SWITCH_BLOCK_TX,
+ NL80211_ATTR_CSA_IES,
+ NL80211_ATTR_CSA_C_OFF_BEACON,
+ NL80211_ATTR_CSA_C_OFF_PRESP,
+
+ NL80211_ATTR_RXMGMT_FLAGS,
+
+ NL80211_ATTR_STA_SUPPORTED_CHANNELS,
+
+ NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES,
+
+ NL80211_ATTR_HANDLE_DFS,
+
+ NL80211_ATTR_SUPPORT_5_MHZ,
+ NL80211_ATTR_SUPPORT_10_MHZ,
+
+ NL80211_ATTR_OPMODE_NOTIF,
+
+ NL80211_ATTR_VENDOR_ID,
+ NL80211_ATTR_VENDOR_SUBCMD,
+ NL80211_ATTR_VENDOR_DATA,
+
+ NL80211_ATTR_VENDOR_EVENTS,
+
+ NL80211_ATTR_QOS_MAP,
+
+ NL80211_ATTR_MAC_HINT,
+ NL80211_ATTR_WIPHY_FREQ_HINT,
+
+ NL80211_ATTR_MAX_AP_ASSOC_STA,
+
+ NL80211_ATTR_TDLS_PEER_CAPABILITY,
+
+ NL80211_ATTR_IFACE_SOCKET_OWNER,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
@@ -2278,9 +2413,15 @@
* enum nl80211_sched_scan_match_attr - scheduled scan match attributes
* @__NL80211_SCHED_SCAN_MATCH_ATTR_INVALID: attribute number 0 is reserved
* @NL80211_SCHED_SCAN_MATCH_ATTR_SSID: SSID to be used for matching,
- * only report BSS with matching SSID.
+ * only report BSS with matching SSID.
* @NL80211_SCHED_SCAN_MATCH_ATTR_RSSI: RSSI threshold (in dBm) for reporting a
- * BSS in scan results. Filtering is turned off if not specified.
+ * BSS in scan results. Filtering is turned off if not specified. Note that
+ * if this attribute is in a match set of its own, then it is treated as
+ * the default value for all matchsets with an SSID, rather than being a
+ * matchset of its own without an RSSI filter. This is due to problems with
+ * how this API was implemented in the past. Also, due to the same problem,
+ * the only way to create a matchset with only an RSSI filter (with this
+ * attribute) is if there's only a single matchset with the RSSI attribute.
* @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter
* attribute number currently defined
* @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use
@@ -3721,4 +3862,24 @@
/* maximum duration for critical protocol measures */
#define NL80211_CRIT_PROTO_MAX_DURATION 5000 /* msec */
+/*
+ * If this flag is unset, the lower 24 bits are an OUI, if set
+ * a Linux nl80211 vendor ID is used (no such IDs are allocated
+ * yet, so that's not valid so far)
+ */
+#define NL80211_VENDOR_ID_IS_LINUX 0x80000000
+
+/**
+ * struct nl80211_vendor_cmd_info - vendor command data
+ * @vendor_id: If the %NL80211_VENDOR_ID_IS_LINUX flag is clear, then the
+ * value is a 24-bit OUI; if it is set then a separately allocated ID
+ * may be used, but no such IDs are allocated yet. New IDs should be
+ * added to this file when needed.
+ * @subcmd: sub-command ID for the command
+ */
+struct nl80211_vendor_cmd_info {
+ __u32 vendor_id;
+ __u32 subcmd;
+};
+
#endif /* __LINUX_NL80211_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 289760f..28bb0b3 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -149,4 +149,13 @@
#define PR_GET_TID_ADDRESS 40
+/* Sets the timerslack for arbitrary threads
+ * arg2 slack value, 0 means "use default"
+ * arg3 pid of the thread whose timer slack needs to be set
+ */
+#define PR_SET_TIMERSLACK_PID 41
+
+#define PR_SET_VMA 0x53564d41
+# define PR_SET_VMA_ANON_NAME 0
+
#endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 7a2144e..07c1146 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -297,6 +297,7 @@
RTA_TABLE,
RTA_MARK,
RTA_MFC_STATS,
+ RTA_UID,
__RTA_MAX
};
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index ac2dc9f..0f238a4 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -10,6 +10,13 @@
#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+
/*
* All BPF programs must return a 32-bit value.
* The bottom 16-bits are for optional return data.
diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h
index b00e29e..472adbb 100644
--- a/include/uapi/linux/sock_diag.h
+++ b/include/uapi/linux/sock_diag.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#define SOCK_DIAG_BY_FAMILY 20
+#define SOCK_DESTROY_BACKPORT 21
struct sock_diag_req {
__u8 sdiag_family;
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index 7997a50..f7ffe36 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -65,6 +65,7 @@
#define SIOCDIFADDR 0x8936 /* delete PA address */
#define SIOCSIFHWBROADCAST 0x8937 /* set hardware broadcast addr */
#define SIOCGIFCOUNT 0x8938 /* get number of devices */
+#define SIOCKILLADDR 0x8939 /* kill sockets with this local addr */
#define SIOCGIFBR 0x8940 /* Bridging support */
#define SIOCSIFBR 0x8941 /* Set bridging options */
diff --git a/include/uapi/linux/usb/f_accessory.h b/include/uapi/linux/usb/f_accessory.h
new file mode 100644
index 0000000..0baeb7d
--- /dev/null
+++ b/include/uapi/linux/usb/f_accessory.h
@@ -0,0 +1,146 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_ACCESSORY_H
+#define _UAPI_LINUX_USB_F_ACCESSORY_H
+
+/* Use Google Vendor ID when in accessory mode */
+#define USB_ACCESSORY_VENDOR_ID 0x18D1
+
+
+/* Product ID to use when in accessory mode */
+#define USB_ACCESSORY_PRODUCT_ID 0x2D00
+
+/* Product ID to use when in accessory mode and adb is enabled */
+#define USB_ACCESSORY_ADB_PRODUCT_ID 0x2D01
+
+/* Indexes for strings sent by the host via ACCESSORY_SEND_STRING */
+#define ACCESSORY_STRING_MANUFACTURER 0
+#define ACCESSORY_STRING_MODEL 1
+#define ACCESSORY_STRING_DESCRIPTION 2
+#define ACCESSORY_STRING_VERSION 3
+#define ACCESSORY_STRING_URI 4
+#define ACCESSORY_STRING_SERIAL 5
+
+/* Control request for retrieving device's protocol version
+ *
+ * requestType: USB_DIR_IN | USB_TYPE_VENDOR
+ * request: ACCESSORY_GET_PROTOCOL
+ * value: 0
+ * index: 0
+ * data version number (16 bits little endian)
+ * 1 for original accessory support
+ * 2 adds HID and device to host audio support
+ */
+#define ACCESSORY_GET_PROTOCOL 51
+
+/* Control request for host to send a string to the device
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SEND_STRING
+ * value: 0
+ * index: string ID
+ * data zero terminated UTF8 string
+ *
+ * The device can later retrieve these strings via the
+ * ACCESSORY_GET_STRING_* ioctls
+ */
+#define ACCESSORY_SEND_STRING 52
+
+/* Control request for starting device in accessory mode.
+ * The host sends this after setting all its strings to the device.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_START
+ * value: 0
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_START 53
+
+/* Control request for registering a HID device.
+ * Upon registering, a unique ID is sent by the accessory in the
+ * value parameter. This ID will be used for future commands for
+ * the device
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_REGISTER_HID_DEVICE
+ * value: Accessory assigned ID for the HID device
+ * index: total length of the HID report descriptor
+ * data none
+ */
+#define ACCESSORY_REGISTER_HID 54
+
+/* Control request for unregistering a HID device.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_REGISTER_HID
+ * value: Accessory assigned ID for the HID device
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_UNREGISTER_HID 55
+
+/* Control request for sending the HID report descriptor.
+ * If the HID descriptor is longer than the endpoint zero max packet size,
+ * the descriptor will be sent in multiple ACCESSORY_SET_HID_REPORT_DESC
+ * commands. The data for the descriptor must be sent sequentially
+ * if multiple packets are needed.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SET_HID_REPORT_DESC
+ * value: Accessory assigned ID for the HID device
+ * index: offset of data in descriptor
+ * (needed when HID descriptor is too big for one packet)
+ * data the HID report descriptor
+ */
+#define ACCESSORY_SET_HID_REPORT_DESC 56
+
+/* Control request for sending HID events.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SEND_HID_EVENT
+ * value: Accessory assigned ID for the HID device
+ * index: 0
+ * data the HID report for the event
+ */
+#define ACCESSORY_SEND_HID_EVENT 57
+
+/* Control request for setting the audio mode.
+ *
+ * requestType: USB_DIR_OUT | USB_TYPE_VENDOR
+ * request: ACCESSORY_SET_AUDIO_MODE
+ * value: 0 - no audio
+ * 1 - device to host, 44100 16-bit stereo PCM
+ * index: 0
+ * data none
+ */
+#define ACCESSORY_SET_AUDIO_MODE 58
+
+/* ioctls for retrieving strings set by the host */
+#define ACCESSORY_GET_STRING_MANUFACTURER _IOW('M', 1, char[256])
+#define ACCESSORY_GET_STRING_MODEL _IOW('M', 2, char[256])
+#define ACCESSORY_GET_STRING_DESCRIPTION _IOW('M', 3, char[256])
+#define ACCESSORY_GET_STRING_VERSION _IOW('M', 4, char[256])
+#define ACCESSORY_GET_STRING_URI _IOW('M', 5, char[256])
+#define ACCESSORY_GET_STRING_SERIAL _IOW('M', 6, char[256])
+/* returns 1 if there is a start request pending */
+#define ACCESSORY_IS_START_REQUESTED _IO('M', 7)
+/* returns audio mode (set via the ACCESSORY_SET_AUDIO_MODE control request) */
+#define ACCESSORY_GET_AUDIO_MODE _IO('M', 8)
+
+#endif /* _UAPI_LINUX_USB_F_ACCESSORY_H */
diff --git a/include/uapi/linux/usb/f_mtp.h b/include/uapi/linux/usb/f_mtp.h
new file mode 100644
index 0000000..5032918
--- /dev/null
+++ b/include/uapi/linux/usb/f_mtp.h
@@ -0,0 +1,61 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_MTP_H
+#define _UAPI_LINUX_USB_F_MTP_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+struct mtp_file_range {
+ /* file descriptor for file to transfer */
+ int fd;
+ /* offset in file for start of transfer */
+ loff_t offset;
+ /* number of bytes to transfer */
+ int64_t length;
+ /* MTP command ID for data header,
+ * used only for MTP_SEND_FILE_WITH_HEADER
+ */
+ uint16_t command;
+ /* MTP transaction ID for data header,
+ * used only for MTP_SEND_FILE_WITH_HEADER
+ */
+ uint32_t transaction_id;
+};
+
+struct mtp_event {
+ /* size of the event */
+ size_t length;
+ /* event data to send */
+ void *data;
+};
+
+/* Sends the specified file range to the host */
+#define MTP_SEND_FILE _IOW('M', 0, struct mtp_file_range)
+/* Receives data from the host and writes it to a file.
+ * The file is created if it does not exist.
+ */
+#define MTP_RECEIVE_FILE _IOW('M', 1, struct mtp_file_range)
+/* Sends an event to the host via the interrupt endpoint */
+#define MTP_SEND_EVENT _IOW('M', 3, struct mtp_event)
+/* Sends the specified file range to the host,
+ * with a 12 byte MTP data packet header at the beginning.
+ */
+#define MTP_SEND_FILE_WITH_HEADER _IOW('M', 4, struct mtp_file_range)
+
+#endif /* _UAPI_LINUX_USB_F_MTP_H */
diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h
index 602dc6c..165e705 100644
--- a/include/uapi/sound/compress_params.h
+++ b/include/uapi/sound/compress_params.h
@@ -57,6 +57,7 @@
#define MAX_NUM_CODECS 32
#define MAX_NUM_CODEC_DESCRIPTORS 32
#define MAX_NUM_BITRATES 32
+#define MAX_NUM_SAMPLE_RATES 32
/* Codecs are listed linearly to allow for extensibility */
#define SND_AUDIOCODEC_PCM ((__u32) 0x00000001)
@@ -324,7 +325,8 @@
/** struct snd_codec_desc - description of codec capabilities
* @max_ch: Maximum number of audio channels
- * @sample_rates: Sampling rates in Hz, use SNDRV_PCM_RATE_xxx for this
+ * @sample_rates: Sampling rates in Hz, use values like 48000 for this
+ * @num_sample_rates: Number of valid values in sample_rates array
* @bit_rate: Indexed array containing supported bit rates
* @num_bitrates: Number of valid values in bit_rate array
* @rate_control: value is specified by SND_RATECONTROLMODE defines.
@@ -346,7 +348,8 @@
struct snd_codec_desc {
__u32 max_ch;
- __u32 sample_rates;
+ __u32 sample_rates[MAX_NUM_SAMPLE_RATES];
+ __u32 num_sample_rates;
__u32 bit_rate[MAX_NUM_BITRATES];
__u32 num_bitrates;
__u32 rate_control;
@@ -364,7 +367,8 @@
* @ch_out: Number of output channels. In case of contradiction between
* this field and the channelMode field, the channelMode field
* overrides.
- * @sample_rate: Audio sample rate of input data
+ * @sample_rate: Audio sample rate of input data in Hz, use values like 48000
+ * for this.
* @bit_rate: Bitrate of encoded data. May be ignored by decoders
* @rate_control: Encoding rate control. See SND_RATECONTROLMODE defines.
* Encoders may rely on profiles for quality levels.
diff --git a/include/uapi/video/adf.h b/include/uapi/video/adf.h
new file mode 100644
index 0000000..c5d2e62
--- /dev/null
+++ b/include/uapi/video/adf.h
@@ -0,0 +1,321 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_VIDEO_ADF_H_
+#define _UAPI_VIDEO_ADF_H_
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#include <drm/drm_fourcc.h>
+#include <drm/drm_mode.h>
+
+#define ADF_NAME_LEN 32
+#define ADF_MAX_CUSTOM_DATA_SIZE 4096
+
+enum adf_interface_type {
+ ADF_INTF_DSI = 0,
+ ADF_INTF_eDP = 1,
+ ADF_INTF_DPI = 2,
+ ADF_INTF_VGA = 3,
+ ADF_INTF_DVI = 4,
+ ADF_INTF_HDMI = 5,
+ ADF_INTF_MEMORY = 6,
+ ADF_INTF_TYPE_DEVICE_CUSTOM = 128,
+ ADF_INTF_TYPE_MAX = (~(__u32)0),
+};
+
+#define ADF_INTF_FLAG_PRIMARY (1 << 0)
+#define ADF_INTF_FLAG_EXTERNAL (1 << 1)
+
+enum adf_event_type {
+ ADF_EVENT_VSYNC = 0,
+ ADF_EVENT_HOTPLUG = 1,
+ ADF_EVENT_DEVICE_CUSTOM = 128,
+ ADF_EVENT_TYPE_MAX = 255,
+};
+
+/**
+ * struct adf_set_event - start or stop subscribing to ADF events
+ *
+ * @type: the type of event to (un)subscribe
+ * @enabled: subscribe or unsubscribe
+ *
+ * After subscribing to an event, userspace may poll() the ADF object's fd
+ * to wait for events or read() to consume the event's data.
+ *
+ * ADF reserves event types 0 to %ADF_EVENT_DEVICE_CUSTOM-1 for its own events.
+ * Devices may use event types %ADF_EVENT_DEVICE_CUSTOM to %ADF_EVENT_TYPE_MAX-1
+ * for driver-private events.
+ */
+struct adf_set_event {
+ __u8 type;
+ __u8 enabled;
+};
+
+/**
+ * struct adf_event - common header for ADF event data
+ *
+ * @type: event type
+ * @length: total size of event data, header inclusive
+ */
+struct adf_event {
+ __u8 type;
+ __u32 length;
+};
+
+/**
+ * struct adf_vsync_event - ADF vsync event
+ *
+ * @base: event header (see &struct adf_event)
+ * @timestamp: time of vsync event, in nanoseconds
+ */
+struct adf_vsync_event {
+ struct adf_event base;
+ __aligned_u64 timestamp;
+};
+
+/**
+ * struct adf_vsync_event - ADF display hotplug event
+ *
+ * @base: event header (see &struct adf_event)
+ * @connected: whether a display is now connected to the interface
+ */
+struct adf_hotplug_event {
+ struct adf_event base;
+ __u8 connected;
+};
+
+#define ADF_MAX_PLANES 4
+/**
+ * struct adf_buffer_config - description of buffer displayed by adf_post_config
+ *
+ * @overlay_engine: id of the target overlay engine
+ * @w: width of display region in pixels
+ * @h: height of display region in pixels
+ * @format: DRM-style fourcc, see drm_fourcc.h for standard formats
+ * @fd: dma_buf fd for each plane
+ * @offset: location of first pixel to scan out, in bytes
+ * @pitch: stride (i.e. length of a scanline including padding) in bytes
+ * @n_planes: number of planes in buffer
+ * @acquire_fence: sync_fence fd which will clear when the buffer is
+ * ready for display, or <0 if the buffer is already ready
+ */
+struct adf_buffer_config {
+ __u32 overlay_engine;
+
+ __u32 w;
+ __u32 h;
+ __u32 format;
+
+ __s32 fd[ADF_MAX_PLANES];
+ __u32 offset[ADF_MAX_PLANES];
+ __u32 pitch[ADF_MAX_PLANES];
+ __u8 n_planes;
+
+ __s32 acquire_fence;
+};
+#define ADF_MAX_BUFFERS (4096 / sizeof(struct adf_buffer_config))
+
+/**
+ * struct adf_post_config - request to flip to a new set of buffers
+ *
+ * @n_interfaces: number of interfaces targeted by the flip (input)
+ * @interfaces: ids of interfaces targeted by the flip (input)
+ * @n_bufs: number of buffers displayed (input)
+ * @bufs: description of buffers displayed (input)
+ * @custom_data_size: size of driver-private data (input)
+ * @custom_data: driver-private data (input)
+ * @complete_fence: sync_fence fd which will clear when this
+ * configuration has left the screen (output)
+ */
+struct adf_post_config {
+ size_t n_interfaces;
+ __u32 __user *interfaces;
+
+ size_t n_bufs;
+ struct adf_buffer_config __user *bufs;
+
+ size_t custom_data_size;
+ void __user *custom_data;
+
+ __s32 complete_fence;
+};
+#define ADF_MAX_INTERFACES (4096 / sizeof(__u32))
+
+/**
+ * struct adf_simple_buffer_allocate - request to allocate a "simple" buffer
+ *
+ * @w: width of buffer in pixels (input)
+ * @h: height of buffer in pixels (input)
+ * @format: DRM-style fourcc (input)
+ *
+ * @fd: dma_buf fd (output)
+ * @offset: location of first pixel, in bytes (output)
+ * @pitch: length of a scanline including padding, in bytes (output)
+ *
+ * Simple buffers are analogous to DRM's "dumb" buffers. They have a single
+ * plane of linear RGB data which can be allocated and scanned out without
+ * any driver-private ioctls or data.
+ *
+ * @format must be a standard RGB format defined in drm_fourcc.h.
+ *
+ * ADF clients must NOT assume that an interface can scan out a simple buffer
+ * allocated by a different ADF interface, even if the two interfaces belong to
+ * the same ADF device.
+ */
+struct adf_simple_buffer_alloc {
+ __u16 w;
+ __u16 h;
+ __u32 format;
+
+ __s32 fd;
+ __u32 offset;
+ __u32 pitch;
+};
+
+/**
+ * struct adf_simple_post_config - request to flip to a single buffer without
+ * driver-private data
+ *
+ * @buf: description of buffer displayed (input)
+ * @complete_fence: sync_fence fd which will clear when this buffer has left the
+ * screen (output)
+ */
+struct adf_simple_post_config {
+ struct adf_buffer_config buf;
+ __s32 complete_fence;
+};
+
+/**
+ * struct adf_attachment_config - description of attachment between an overlay
+ * engine and an interface
+ *
+ * @overlay_engine: id of the overlay engine
+ * @interface: id of the interface
+ */
+struct adf_attachment_config {
+ __u32 overlay_engine;
+ __u32 interface;
+};
+
+/**
+ * struct adf_device_data - describes a display device
+ *
+ * @name: display device's name
+ * @n_attachments: the number of current attachments
+ * @attachments: list of current attachments
+ * @n_allowed_attachments: the number of allowed attachments
+ * @allowed_attachments: list of allowed attachments
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_device_data {
+ char name[ADF_NAME_LEN];
+
+ size_t n_attachments;
+ struct adf_attachment_config __user *attachments;
+
+ size_t n_allowed_attachments;
+ struct adf_attachment_config __user *allowed_attachments;
+
+ size_t custom_data_size;
+ void __user *custom_data;
+};
+#define ADF_MAX_ATTACHMENTS (4096 / sizeof(struct adf_attachment_config))
+
+/**
+ * struct adf_device_data - describes a display interface
+ *
+ * @name: display interface's name
+ * @type: interface type (see enum @adf_interface_type)
+ * @id: which interface of type @type;
+ * e.g. interface DSI.1 -> @type=@ADF_INTF_TYPE_DSI, @id=1
+ * @flags: informational flags (bitmask of %ADF_INTF_FLAG_* values)
+ * @dpms_state: DPMS state (one of @DRM_MODE_DPMS_* defined in drm_mode.h)
+ * @hotplug_detect: whether a display is plugged in
+ * @width_mm: screen width in millimeters, or 0 if unknown
+ * @height_mm: screen height in millimeters, or 0 if unknown
+ * @current_mode: current display mode
+ * @n_available_modes: the number of hardware display modes
+ * @available_modes: list of hardware display modes
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_interface_data {
+ char name[ADF_NAME_LEN];
+
+ __u32 type;
+ __u32 id;
+ /* e.g. type=ADF_INTF_TYPE_DSI, id=1 => DSI.1 */
+ __u32 flags;
+
+ __u8 dpms_state;
+ __u8 hotplug_detect;
+ __u16 width_mm;
+ __u16 height_mm;
+
+ struct drm_mode_modeinfo current_mode;
+ size_t n_available_modes;
+ struct drm_mode_modeinfo __user *available_modes;
+
+ size_t custom_data_size;
+ void __user *custom_data;
+};
+#define ADF_MAX_MODES (4096 / sizeof(struct drm_mode_modeinfo))
+
+/**
+ * struct adf_overlay_engine_data - describes an overlay engine
+ *
+ * @name: overlay engine's name
+ * @n_supported_formats: number of supported formats
+ * @supported_formats: list of supported formats
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_overlay_engine_data {
+ char name[ADF_NAME_LEN];
+
+ size_t n_supported_formats;
+ __u32 __user *supported_formats;
+
+ size_t custom_data_size;
+ void __user *custom_data;
+};
+#define ADF_MAX_SUPPORTED_FORMATS (4096 / sizeof(__u32))
+
+#define ADF_IOCTL_TYPE 'D'
+#define ADF_IOCTL_NR_CUSTOM 128
+
+#define ADF_SET_EVENT _IOW(ADF_IOCTL_TYPE, 0, struct adf_set_event)
+#define ADF_BLANK _IOW(ADF_IOCTL_TYPE, 1, __u8)
+#define ADF_POST_CONFIG _IOW(ADF_IOCTL_TYPE, 2, struct adf_post_config)
+#define ADF_SET_MODE _IOW(ADF_IOCTL_TYPE, 3, \
+ struct drm_mode_modeinfo)
+#define ADF_GET_DEVICE_DATA _IOR(ADF_IOCTL_TYPE, 4, struct adf_device_data)
+#define ADF_GET_INTERFACE_DATA _IOR(ADF_IOCTL_TYPE, 5, \
+ struct adf_interface_data)
+#define ADF_GET_OVERLAY_ENGINE_DATA \
+ _IOR(ADF_IOCTL_TYPE, 6, \
+ struct adf_overlay_engine_data)
+#define ADF_SIMPLE_POST_CONFIG _IOW(ADF_IOCTL_TYPE, 7, \
+ struct adf_simple_post_config)
+#define ADF_SIMPLE_BUFFER_ALLOC _IOW(ADF_IOCTL_TYPE, 8, \
+ struct adf_simple_buffer_alloc)
+#define ADF_ATTACH _IOW(ADF_IOCTL_TYPE, 9, \
+ struct adf_attachment_config)
+#define ADF_DETACH _IOW(ADF_IOCTL_TYPE, 10, \
+ struct adf_attachment_config)
+
+#endif /* _UAPI_VIDEO_ADF_H_ */
diff --git a/include/video/adf.h b/include/video/adf.h
new file mode 100644
index 0000000..34f10e5
--- /dev/null
+++ b/include/video/adf.h
@@ -0,0 +1,502 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_H
+#define _VIDEO_ADF_H
+
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <uapi/video/adf.h>
+#include "sync.h"
+
+struct adf_obj;
+struct adf_obj_ops;
+struct adf_device;
+struct adf_device_ops;
+struct adf_interface;
+struct adf_interface_ops;
+struct adf_overlay_engine;
+struct adf_overlay_engine_ops;
+
+/**
+ * struct adf_buffer - buffer displayed by adf_post
+ *
+ * @overlay_engine: target overlay engine
+ * @w: width of display region in pixels
+ * @h: height of display region in pixels
+ * @format: DRM-style fourcc, see drm_fourcc.h for standard formats
+ * @dma_bufs: dma_buf for each plane
+ * @offset: location of first pixel to scan out, in bytes
+ * @pitch: length of a scanline including padding, in bytes
+ * @n_planes: number of planes in buffer
+ * @acquire_fence: sync_fence which will clear when the buffer is
+ * ready for display
+ *
+ * &struct adf_buffer is the in-kernel counterpart to the userspace-facing
+ * &struct adf_buffer_config.
+ */
+struct adf_buffer {
+ struct adf_overlay_engine *overlay_engine;
+
+ u32 w;
+ u32 h;
+ u32 format;
+
+ struct dma_buf *dma_bufs[ADF_MAX_PLANES];
+ u32 offset[ADF_MAX_PLANES];
+ u32 pitch[ADF_MAX_PLANES];
+ u8 n_planes;
+
+ struct sync_fence *acquire_fence;
+};
+
+/**
+ * struct adf_buffer_mapping - state for mapping a &struct adf_buffer into the
+ * display device
+ *
+ * @attachments: dma-buf attachment for each plane
+ * @sg_tables: SG tables for each plane
+ */
+struct adf_buffer_mapping {
+ struct dma_buf_attachment *attachments[ADF_MAX_PLANES];
+ struct sg_table *sg_tables[ADF_MAX_PLANES];
+};
+
+/**
+ * struct adf_post - request to flip to a new set of buffers
+ *
+ * @n_bufs: number of buffers displayed
+ * @bufs: buffers displayed
+ * @mappings: in-device mapping state for each buffer
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ *
+ * &struct adf_post is the in-kernel counterpart to the userspace-facing
+ * &struct adf_post_config.
+ */
+struct adf_post {
+ size_t n_bufs;
+ struct adf_buffer *bufs;
+ struct adf_buffer_mapping *mappings;
+
+ size_t custom_data_size;
+ void *custom_data;
+};
+
+/**
+ * struct adf_attachment - description of attachment between an overlay engine
+ * and an interface
+ *
+ * @overlay_engine: the overlay engine
+ * @interface: the interface
+ *
+ * &struct adf_attachment is the in-kernel counterpart to the userspace-facing
+ * &struct adf_attachment_config.
+ */
+struct adf_attachment {
+ struct adf_overlay_engine *overlay_engine;
+ struct adf_interface *interface;
+};
+
+struct adf_pending_post {
+ struct list_head head;
+ struct adf_post config;
+ void *state;
+};
+
+enum adf_obj_type {
+ ADF_OBJ_OVERLAY_ENGINE = 0,
+ ADF_OBJ_INTERFACE = 1,
+ ADF_OBJ_DEVICE = 2,
+};
+
+/**
+ * struct adf_obj_ops - common ADF object implementation ops
+ *
+ * @open: handle opening the object's device node
+ * @release: handle releasing an open file
+ * @ioctl: handle custom ioctls
+ *
+ * @supports_event: return whether the object supports generating events of type
+ * @type
+ * @set_event: enable or disable events of type @type
+ * @event_type_str: return a string representation of custom event @type
+ * (@type >= %ADF_EVENT_DEVICE_CUSTOM).
+ *
+ * @custom_data: copy up to %ADF_MAX_CUSTOM_DATA_SIZE bytes of driver-private
+ * data into @data (allocated by ADF) and return the number of copied bytes
+ * in @size. Return 0 on success or an error code (<0) on failure.
+ */
+struct adf_obj_ops {
+ /* optional */
+ int (*open)(struct adf_obj *obj, struct inode *inode,
+ struct file *file);
+ /* optional */
+ void (*release)(struct adf_obj *obj, struct inode *inode,
+ struct file *file);
+ /* optional */
+ long (*ioctl)(struct adf_obj *obj, unsigned int cmd, unsigned long arg);
+
+ /* optional */
+ bool (*supports_event)(struct adf_obj *obj, enum adf_event_type type);
+ /* required if supports_event is implemented */
+ void (*set_event)(struct adf_obj *obj, enum adf_event_type type,
+ bool enabled);
+ /* optional */
+ const char *(*event_type_str)(struct adf_obj *obj,
+ enum adf_event_type type);
+
+ /* optional */
+ int (*custom_data)(struct adf_obj *obj, void *data, size_t *size);
+};
+
+struct adf_obj {
+ enum adf_obj_type type;
+ char name[ADF_NAME_LEN];
+ struct adf_device *parent;
+
+ const struct adf_obj_ops *ops;
+
+ struct device dev;
+
+ struct spinlock file_lock;
+ struct list_head file_list;
+
+ struct mutex event_lock;
+ struct rb_root event_refcount;
+
+ int id;
+ int minor;
+};
+
+/**
+ * struct adf_device_quirks - common display device quirks
+ *
+ * @buffer_padding: whether the last scanline of a buffer extends to the
+ * buffer's pitch (@ADF_BUFFER_PADDED_TO_PITCH) or just to the visible
+ * width (@ADF_BUFFER_UNPADDED)
+ */
+struct adf_device_quirks {
+ /* optional, defaults to ADF_BUFFER_PADDED_TO_PITCH */
+ enum {
+ ADF_BUFFER_PADDED_TO_PITCH = 0,
+ ADF_BUFFER_UNPADDED = 1,
+ } buffer_padding;
+};
+
+/**
+ * struct adf_device_ops - display device implementation ops
+ *
+ * @owner: device's module
+ * @base: common operations (see &struct adf_obj_ops)
+ * @quirks: device's quirks (see &struct adf_device_quirks)
+ *
+ * @attach: attach overlay engine @eng to interface @intf. Return 0 on success
+ * or error code (<0) on failure.
+ * @detach: detach overlay engine @eng from interface @intf. Return 0 on
+ * success or error code (<0) on failure.
+ *
+ * @validate_custom_format: validate the number and size of planes
+ * in buffers with a custom format (i.e., not one of the @DRM_FORMAT_*
+ * types defined in drm/drm_fourcc.h). Return 0 if the buffer is valid or
+ * an error code (<0) otherwise.
+ *
+ * @validate: validate that the proposed configuration @cfg is legal. The
+ * driver may optionally allocate and return some driver-private state in
+ * @driver_state, which will be passed to the corresponding post(). The
+ * driver may NOT commit any changes to hardware. Return 0 if @cfg is
+ * valid or an error code (<0) otherwise.
+ * @complete_fence: create a hardware-backed sync fence to be signaled when
+ * @cfg is removed from the screen. If unimplemented, ADF automatically
+ * creates an sw_sync fence. Return the sync fence on success or a
+ * PTR_ERR() on failure.
+ * @post: flip @cfg onto the screen. Wait for the display to begin scanning out
+ * @cfg before returning.
+ * @advance_timeline: signal the sync fence for the last configuration to leave
+ * the display. If unimplemented, ADF automatically advances an sw_sync
+ * timeline.
+ * @state_free: free driver-private state allocated during validate()
+ */
+struct adf_device_ops {
+ /* required */
+ struct module *owner;
+ const struct adf_obj_ops base;
+ /* optional */
+ const struct adf_device_quirks quirks;
+
+ /* optional */
+ int (*attach)(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+ /* optional */
+ int (*detach)(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+
+ /* required if any of the device's overlay engines supports at least one
+ custom format */
+ int (*validate_custom_format)(struct adf_device *dev,
+ struct adf_buffer *buf);
+
+ /* required */
+ int (*validate)(struct adf_device *dev, struct adf_post *cfg,
+ void **driver_state);
+ /* optional */
+ struct sync_fence *(*complete_fence)(struct adf_device *dev,
+ struct adf_post *cfg, void *driver_state);
+ /* required */
+ void (*post)(struct adf_device *dev, struct adf_post *cfg,
+ void *driver_state);
+ /* required if complete_fence is implemented */
+ void (*advance_timeline)(struct adf_device *dev,
+ struct adf_post *cfg, void *driver_state);
+ /* required if validate allocates driver state */
+ void (*state_free)(struct adf_device *dev, void *driver_state);
+};
+
+struct adf_attachment_list {
+ struct adf_attachment attachment;
+ struct list_head head;
+};
+
+struct adf_device {
+ struct adf_obj base;
+ struct device *dev;
+
+ const struct adf_device_ops *ops;
+
+ struct mutex client_lock;
+
+ struct idr interfaces;
+ size_t n_interfaces;
+ struct idr overlay_engines;
+
+ struct list_head post_list;
+ struct mutex post_lock;
+ struct kthread_worker post_worker;
+ struct task_struct *post_thread;
+ struct kthread_work post_work;
+
+ struct list_head attached;
+ size_t n_attached;
+ struct list_head attach_allowed;
+ size_t n_attach_allowed;
+
+ struct adf_pending_post *onscreen;
+
+ struct sw_sync_timeline *timeline;
+ int timeline_max;
+};
+
+/**
+ * struct adf_interface_ops - display interface implementation ops
+ *
+ * @base: common operations (see &struct adf_obj_ops)
+ *
+ * @blank: change the display's DPMS state. Return 0 on success or error
+ * code (<0) on failure.
+ *
+ * @alloc_simple_buffer: allocate a buffer with the specified @w, @h, and
+ * @format. @format will be a standard RGB format (i.e.,
+ * adf_format_is_rgb(@format) == true). Return 0 on success or error code
+ * (<0) on failure. On success, return the buffer, offset, and pitch in
+ * @dma_buf, @offset, and @pitch respectively.
+ * @describe_simple_post: provide driver-private data needed to post a single
+ * buffer @buf. Copy up to ADF_MAX_CUSTOM_DATA_SIZE bytes into @data
+ * (allocated by ADF) and return the number of bytes in @size. Return 0 on
+ * success or error code (<0) on failure.
+ *
+ * @modeset: change the interface's mode. @mode is not necessarily part of the
+ * modelist passed to adf_hotplug_notify_connected(); the driver may
+ * accept or reject custom modes at its discretion. Return 0 on success or
+ * error code (<0) if the mode could not be set.
+ *
+ * @screen_size: copy the screen dimensions in millimeters into @width_mm
+ * and @height_mm. Return 0 on success or error code (<0) if the display
+ * dimensions are unknown.
+ *
+ * @type_str: return a string representation of custom @intf->type
+ * (@intf->type >= @ADF_INTF_TYPE_DEVICE_CUSTOM).
+ */
+struct adf_interface_ops {
+ const struct adf_obj_ops base;
+
+ /* optional */
+ int (*blank)(struct adf_interface *intf, u8 state);
+
+ /* optional */
+ int (*alloc_simple_buffer)(struct adf_interface *intf,
+ u16 w, u16 h, u32 format,
+ struct dma_buf **dma_buf, u32 *offset, u32 *pitch);
+ /* optional */
+ int (*describe_simple_post)(struct adf_interface *intf,
+ struct adf_buffer *fb, void *data, size_t *size);
+
+ /* optional */
+ int (*modeset)(struct adf_interface *intf,
+ struct drm_mode_modeinfo *mode);
+
+ /* optional */
+ int (*screen_size)(struct adf_interface *intf, u16 *width_mm,
+ u16 *height_mm);
+
+ /* optional */
+ const char *(*type_str)(struct adf_interface *intf);
+};
+
+struct adf_interface {
+ struct adf_obj base;
+ const struct adf_interface_ops *ops;
+
+ struct drm_mode_modeinfo current_mode;
+
+ enum adf_interface_type type;
+ u32 idx;
+ u32 flags;
+
+ wait_queue_head_t vsync_wait;
+ ktime_t vsync_timestamp;
+ rwlock_t vsync_lock;
+
+ u8 dpms_state;
+
+ bool hotplug_detect;
+ struct drm_mode_modeinfo *modelist;
+ size_t n_modes;
+ rwlock_t hotplug_modelist_lock;
+};
+
+/**
+ * struct adf_interface_ops - overlay engine implementation ops
+ *
+ * @base: common operations (see &struct adf_obj_ops)
+ *
+ * @supported_formats: list of fourccs the overlay engine can scan out
+ * @n_supported_formats: length of supported_formats, up to
+ * ADF_MAX_SUPPORTED_FORMATS
+ */
+struct adf_overlay_engine_ops {
+ const struct adf_obj_ops base;
+
+ /* required */
+ const u32 *supported_formats;
+ /* required */
+ const size_t n_supported_formats;
+};
+
+struct adf_overlay_engine {
+ struct adf_obj base;
+
+ const struct adf_overlay_engine_ops *ops;
+};
+
+#define adf_obj_to_device(ptr) \
+ container_of((ptr), struct adf_device, base)
+
+#define adf_obj_to_interface(ptr) \
+ container_of((ptr), struct adf_interface, base)
+
+#define adf_obj_to_overlay_engine(ptr) \
+ container_of((ptr), struct adf_overlay_engine, base)
+
+int __printf(4, 5) adf_device_init(struct adf_device *dev,
+ struct device *parent, const struct adf_device_ops *ops,
+ const char *fmt, ...);
+void adf_device_destroy(struct adf_device *dev);
+int __printf(7, 8) adf_interface_init(struct adf_interface *intf,
+ struct adf_device *dev, enum adf_interface_type type, u32 idx,
+ u32 flags, const struct adf_interface_ops *ops, const char *fmt,
+ ...);
+void adf_interface_destroy(struct adf_interface *intf);
+static inline struct adf_device *adf_interface_parent(
+ struct adf_interface *intf)
+{
+ return intf->base.parent;
+}
+int __printf(4, 5) adf_overlay_engine_init(struct adf_overlay_engine *eng,
+ struct adf_device *dev,
+ const struct adf_overlay_engine_ops *ops, const char *fmt, ...);
+void adf_overlay_engine_destroy(struct adf_overlay_engine *eng);
+static inline struct adf_device *adf_overlay_engine_parent(
+ struct adf_overlay_engine *eng)
+{
+ return eng->base.parent;
+}
+
+int adf_attachment_allow(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+
+const char *adf_obj_type_str(enum adf_obj_type type);
+const char *adf_interface_type_str(struct adf_interface *intf);
+const char *adf_event_type_str(struct adf_obj *obj, enum adf_event_type type);
+
+#define ADF_FORMAT_STR_SIZE 5
+void adf_format_str(u32 format, char buf[ADF_FORMAT_STR_SIZE]);
+int adf_format_validate_yuv(struct adf_device *dev, struct adf_buffer *buf,
+ u8 num_planes, u8 hsub, u8 vsub, u8 cpp[]);
+/**
+ * adf_format_validate_rgb - validate the number and size of planes in buffers
+ * with a custom RGB format.
+ *
+ * @dev: ADF device performing the validation
+ * @buf: buffer to validate
+ * @cpp: expected bytes per pixel
+ *
+ * adf_format_validate_rgb() is intended to be called as a helper from @dev's
+ * validate_custom_format() op. @buf must have a single RGB plane.
+ *
+ * Returns 0 if @buf has a single plane with sufficient size, or -EINVAL
+ * otherwise.
+ */
+static inline int adf_format_validate_rgb(struct adf_device *dev,
+ struct adf_buffer *buf, u8 cpp)
+{
+ return adf_format_validate_yuv(dev, buf, 1, 1, 1, &cpp);
+}
+
+int adf_event_get(struct adf_obj *obj, enum adf_event_type type);
+int adf_event_put(struct adf_obj *obj, enum adf_event_type type);
+int adf_event_notify(struct adf_obj *obj, struct adf_event *event);
+
+static inline void adf_vsync_get(struct adf_interface *intf)
+{
+ adf_event_get(&intf->base, ADF_EVENT_VSYNC);
+}
+
+static inline void adf_vsync_put(struct adf_interface *intf)
+{
+ adf_event_put(&intf->base, ADF_EVENT_VSYNC);
+}
+
+int adf_vsync_wait(struct adf_interface *intf, long timeout);
+void adf_vsync_notify(struct adf_interface *intf, ktime_t timestamp);
+
+int adf_hotplug_notify_connected(struct adf_interface *intf,
+ struct drm_mode_modeinfo *modelist, size_t n_modes);
+void adf_hotplug_notify_disconnected(struct adf_interface *intf);
+
+void adf_modeinfo_set_name(struct drm_mode_modeinfo *mode);
+void adf_modeinfo_set_vrefresh(struct drm_mode_modeinfo *mode);
+
+#endif /* _VIDEO_ADF_H */
diff --git a/include/video/adf_client.h b/include/video/adf_client.h
new file mode 100644
index 0000000..983f2b6
--- /dev/null
+++ b/include/video/adf_client.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_CLIENT_H_
+#define _VIDEO_ADF_CLIENT_H_
+
+#include <video/adf.h>
+
+int adf_interface_blank(struct adf_interface *intf, u8 state);
+u8 adf_interface_dpms_state(struct adf_interface *intf);
+
+void adf_interface_current_mode(struct adf_interface *intf,
+ struct drm_mode_modeinfo *mode);
+size_t adf_interface_modelist(struct adf_interface *intf,
+ struct drm_mode_modeinfo *modelist, size_t n_modes);
+int adf_interface_set_mode(struct adf_interface *intf,
+ struct drm_mode_modeinfo *mode);
+int adf_interface_get_screen_size(struct adf_interface *intf, u16 *width,
+ u16 *height);
+int adf_interface_simple_buffer_alloc(struct adf_interface *intf, u16 w, u16 h,
+ u32 format, struct dma_buf **dma_buf, u32 *offset, u32 *pitch);
+struct sync_fence *adf_interface_simple_post(struct adf_interface *intf,
+ struct adf_buffer *buf);
+
+bool adf_overlay_engine_supports_format(struct adf_overlay_engine *eng,
+ u32 format);
+
+size_t adf_device_attachments(struct adf_device *dev,
+ struct adf_attachment *attachments, size_t n_attachments);
+size_t adf_device_attachments_allowed(struct adf_device *dev,
+ struct adf_attachment *attachments, size_t n_attachments);
+bool adf_device_attached(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+bool adf_device_attach_allowed(struct adf_device *dev,
+ struct adf_overlay_engine *eng, struct adf_interface *intf);
+int adf_device_attach(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+int adf_device_detach(struct adf_device *dev, struct adf_overlay_engine *eng,
+ struct adf_interface *intf);
+
+struct sync_fence *adf_device_post(struct adf_device *dev,
+ struct adf_interface **intfs, size_t n_intfs,
+ struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+ size_t custom_data_size);
+struct sync_fence *adf_device_post_nocopy(struct adf_device *dev,
+ struct adf_interface **intfs, size_t n_intfs,
+ struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+ size_t custom_data_size);
+
+#endif /* _VIDEO_ADF_CLIENT_H_ */
diff --git a/include/video/adf_fbdev.h b/include/video/adf_fbdev.h
new file mode 100644
index 0000000..b722c6b
--- /dev/null
+++ b/include/video/adf_fbdev.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_FBDEV_H_
+#define _VIDEO_ADF_FBDEV_H_
+
+#include <linux/fb.h>
+#include <linux/mutex.h>
+#include <video/adf.h>
+
+struct adf_fbdev {
+ struct adf_interface *intf;
+ struct adf_overlay_engine *eng;
+ struct fb_info *info;
+ u32 pseudo_palette[16];
+
+ unsigned int refcount;
+ struct mutex refcount_lock;
+
+ struct dma_buf *dma_buf;
+ u32 offset;
+ u32 pitch;
+ void *vaddr;
+ u32 format;
+
+ u16 default_xres_virtual;
+ u16 default_yres_virtual;
+ u32 default_format;
+};
+
+#if IS_ENABLED(CONFIG_ADF_FBDEV)
+void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+ struct fb_videomode *vmode);
+void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+ struct drm_mode_modeinfo *mode);
+
+int adf_fbdev_init(struct adf_fbdev *fbdev, struct adf_interface *interface,
+ struct adf_overlay_engine *eng,
+ u16 xres_virtual, u16 yres_virtual, u32 format,
+ struct fb_ops *fbops, const char *fmt, ...);
+void adf_fbdev_destroy(struct adf_fbdev *fbdev);
+
+int adf_fbdev_open(struct fb_info *info, int user);
+int adf_fbdev_release(struct fb_info *info, int user);
+int adf_fbdev_check_var(struct fb_var_screeninfo *var, struct fb_info *info);
+int adf_fbdev_set_par(struct fb_info *info);
+int adf_fbdev_blank(int blank, struct fb_info *info);
+int adf_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *info);
+int adf_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma);
+#else
+static inline void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+ struct fb_videomode *vmode)
+{
+ WARN_ONCE(1, "%s: CONFIG_ADF_FBDEV is disabled\n", __func__);
+}
+
+static inline void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+ struct drm_mode_modeinfo *mode)
+{
+ WARN_ONCE(1, "%s: CONFIG_ADF_FBDEV is disabled\n", __func__);
+}
+
+static inline int adf_fbdev_init(struct adf_fbdev *fbdev,
+ struct adf_interface *interface,
+ struct adf_overlay_engine *eng,
+ u16 xres_virtual, u16 yres_virtual, u32 format,
+ struct fb_ops *fbops, const char *fmt, ...)
+{
+ return -ENODEV;
+}
+
+static inline void adf_fbdev_destroy(struct adf_fbdev *fbdev) { }
+
+static inline int adf_fbdev_open(struct fb_info *info, int user)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_release(struct fb_info *info, int user)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_check_var(struct fb_var_screeninfo *var,
+ struct fb_info *info)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_set_par(struct fb_info *info)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_blank(int blank, struct fb_info *info)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_pan_display(struct fb_var_screeninfo *var,
+ struct fb_info *info)
+{
+ return -ENODEV;
+}
+
+static inline int adf_fbdev_mmap(struct fb_info *info,
+ struct vm_area_struct *vma)
+{
+ return -ENODEV;
+}
+#endif
+
+#endif /* _VIDEO_ADF_FBDEV_H_ */
diff --git a/include/video/adf_format.h b/include/video/adf_format.h
new file mode 100644
index 0000000..e03182c
--- /dev/null
+++ b/include/video/adf_format.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_FORMAT_H
+#define _VIDEO_ADF_FORMAT_H
+
+bool adf_format_is_standard(u32 format);
+bool adf_format_is_rgb(u32 format);
+u8 adf_format_num_planes(u32 format);
+u8 adf_format_bpp(u32 format);
+u8 adf_format_plane_cpp(u32 format, int plane);
+u8 adf_format_horz_chroma_subsampling(u32 format);
+u8 adf_format_vert_chroma_subsampling(u32 format);
+
+#endif /* _VIDEO_ADF_FORMAT_H */
diff --git a/include/video/adf_memblock.h b/include/video/adf_memblock.h
new file mode 100644
index 0000000..6256e0e
--- /dev/null
+++ b/include/video/adf_memblock.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_MEMBLOCK_H_
+#define _VIDEO_ADF_MEMBLOCK_H_
+
+struct dma_buf *adf_memblock_export(phys_addr_t base, size_t size, int flags);
+
+#endif /* _VIDEO_ADF_MEMBLOCK_H_ */
diff --git a/init/Kconfig b/init/Kconfig
index 8fa4f75..f1e35bd 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1251,6 +1251,12 @@
config HAVE_PCSPKR_PLATFORM
bool
+config PANIC_TIMEOUT
+ int "Default panic timeout"
+ default 0
+ help
+ Set default panic timeout.
+
menuconfig EXPERT
bool "Configure standard kernel features (expert users)"
# Unhide debug options, to make the on-by-default options visible
@@ -1624,6 +1630,18 @@
default 0 if BASE_FULL
default 1 if !BASE_FULL
+config SYSTEM_TRUSTED_KEYRING
+ bool "Provide system-wide ring of trusted keys"
+ depends on KEYS
+ help
+ Provide a system keyring to which trusted keys can be added. Keys in
+ the keyring are considered to be trusted. Keys may be added at will
+ by the kernel from compiled-in data and from hardware key stores, but
+ userspace may only add extra keys if those keys can be verified by
+ keys already in the keyring.
+
+ Keys in this keyring are used by module signature checking.
+
menuconfig MODULES
bool "Enable loadable module support"
help
@@ -1696,6 +1714,7 @@
config MODULE_SIG
bool "Module signature verification"
depends on MODULES
+ select SYSTEM_TRUSTED_KEYRING
select KEYS
select CRYPTO
select ASYMMETRIC_KEY_TYPE
diff --git a/init/Makefile b/init/Makefile
index 7bc47ee..243f61d 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -3,11 +3,8 @@
#
obj-y := main.o version.o mounts.o
-ifneq ($(CONFIG_BLK_DEV_INITRD),y)
obj-y += noinitramfs.o
-else
obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o
-endif
obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
ifneq ($(CONFIG_ARCH_INIT_TASK),y)
@@ -18,6 +15,7 @@
mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o
mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o
mounts-$(CONFIG_BLK_DEV_MD) += do_mounts_md.o
+mounts-$(CONFIG_BLK_DEV_DM) += do_mounts_dm.o
# dependencies on generated files need to be listed explicitly
$(obj)/version.o: include/generated/compile.h
diff --git a/init/do_mounts.c b/init/do_mounts.c
index a2b49f2..b3cc00f 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -551,6 +551,7 @@
wait_for_device_probe();
md_run_setup();
+ dm_run_setup();
if (saved_root_name[0]) {
root_device_name = saved_root_name;
diff --git a/init/do_mounts.h b/init/do_mounts.h
index f5b978a..09d2286 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -74,3 +74,13 @@
static inline void md_run_setup(void) {}
#endif
+
+#ifdef CONFIG_BLK_DEV_DM
+
+void dm_run_setup(void);
+
+#else
+
+static inline void dm_run_setup(void) {}
+
+#endif
diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c
new file mode 100644
index 0000000..46e0b73
--- /dev/null
+++ b/init/do_mounts_dm.c
@@ -0,0 +1,411 @@
+/* do_mounts_dm.c
+ * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * All Rights Reserved.
+ * Based on do_mounts_md.c
+ *
+ * This file is released under the GPL.
+ */
+#include <linux/device-mapper.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+
+#include "do_mounts.h"
+
+#define DM_MAX_NAME 32
+#define DM_MAX_UUID 129
+#define DM_NO_UUID "none"
+
+#define DM_MSG_PREFIX "init"
+
+/* Separators used for parsing the dm= argument. */
+#define DM_FIELD_SEP ' '
+#define DM_LINE_SEP ','
+
+/*
+ * When the device-mapper and any targets are compiled into the kernel
+ * (not a module), one target may be created and used as the root device at
+ * boot time with the parameters given with the boot line dm=...
+ * The code for that is here.
+ */
+
+struct dm_setup_target {
+ sector_t begin;
+ sector_t length;
+ char *type;
+ char *params;
+ /* simple singly linked list */
+ struct dm_setup_target *next;
+};
+
+static struct {
+ int minor;
+ int ro;
+ char name[DM_MAX_NAME];
+ char uuid[DM_MAX_UUID];
+ char *targets;
+ struct dm_setup_target *target;
+ int target_count;
+} dm_setup_args __initdata;
+
+static __initdata int dm_early_setup;
+
+static size_t __init get_dm_option(char *str, char **next, char sep)
+{
+ size_t len = 0;
+ char *endp = NULL;
+
+ if (!str)
+ return 0;
+
+ endp = strchr(str, sep);
+ if (!endp) { /* act like strchrnul */
+ len = strlen(str);
+ endp = str + len;
+ } else {
+ len = endp - str;
+ }
+
+ if (endp == str)
+ return 0;
+
+ if (!next)
+ return len;
+
+ if (*endp == 0) {
+ /* Don't advance past the nul. */
+ *next = endp;
+ } else {
+ *next = endp + 1;
+ }
+ return len;
+}
+
+static int __init dm_setup_args_init(void)
+{
+ dm_setup_args.minor = 0;
+ dm_setup_args.ro = 0;
+ dm_setup_args.target = NULL;
+ dm_setup_args.target_count = 0;
+ return 0;
+}
+
+static int __init dm_setup_cleanup(void)
+{
+ struct dm_setup_target *target = dm_setup_args.target;
+ struct dm_setup_target *old_target = NULL;
+ while (target) {
+ kfree(target->type);
+ kfree(target->params);
+ old_target = target;
+ target = target->next;
+ kfree(old_target);
+ dm_setup_args.target_count--;
+ }
+ BUG_ON(dm_setup_args.target_count);
+ return 0;
+}
+
+static char * __init dm_setup_parse_device_args(char *str)
+{
+ char *next = NULL;
+ size_t len = 0;
+
+ /* Grab the logical name of the device to be exported to udev */
+ len = get_dm_option(str, &next, DM_FIELD_SEP);
+ if (!len) {
+ DMERR("failed to parse device name");
+ goto parse_fail;
+ }
+ len = min(len + 1, sizeof(dm_setup_args.name));
+ strlcpy(dm_setup_args.name, str, len); /* includes nul */
+ str = skip_spaces(next);
+
+ /* Grab the UUID value or "none" */
+ len = get_dm_option(str, &next, DM_FIELD_SEP);
+ if (!len) {
+ DMERR("failed to parse device uuid");
+ goto parse_fail;
+ }
+ len = min(len + 1, sizeof(dm_setup_args.uuid));
+ strlcpy(dm_setup_args.uuid, str, len);
+ str = skip_spaces(next);
+
+ /* Determine if the table/device will be read only or read-write */
+ if (!strncmp("ro,", str, 3)) {
+ dm_setup_args.ro = 1;
+ } else if (!strncmp("rw,", str, 3)) {
+ dm_setup_args.ro = 0;
+ } else {
+ DMERR("failed to parse table mode");
+ goto parse_fail;
+ }
+ str = skip_spaces(str + 3);
+
+ return str;
+
+parse_fail:
+ return NULL;
+}
+
+static void __init dm_substitute_devices(char *str, size_t str_len)
+{
+ char *candidate = str;
+ char *candidate_end = str;
+ char old_char;
+ size_t len = 0;
+ dev_t dev;
+
+ if (str_len < 3)
+ return;
+
+ while (str && *str) {
+ candidate = strchr(str, '/');
+ if (!candidate)
+ break;
+
+ /* Avoid embedded slashes */
+ if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) {
+ str = strchr(candidate, DM_FIELD_SEP);
+ continue;
+ }
+
+ len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP);
+ str = skip_spaces(candidate_end);
+ if (len < 3 || len > 37) /* name_to_dev_t max; maj:mix min */
+ continue;
+
+ /* Temporarily terminate with a nul */
+ if (*candidate_end)
+ candidate_end--;
+ old_char = *candidate_end;
+ *candidate_end = '\0';
+
+ DMDEBUG("converting candidate device '%s' to dev_t", candidate);
+ /* Use the boot-time specific device naming */
+ dev = name_to_dev_t(candidate);
+ *candidate_end = old_char;
+
+ DMDEBUG(" -> %u", dev);
+ /* No suitable replacement found */
+ if (!dev)
+ continue;
+
+ /* Rewrite the /dev/path as a major:minor */
+ len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev));
+ if (!len) {
+ DMERR("error substituting device major/minor.");
+ break;
+ }
+ candidate += len;
+ /* Pad out with spaces (fixing our nul) */
+ while (candidate < candidate_end)
+ *(candidate++) = DM_FIELD_SEP;
+ }
+}
+
+static int __init dm_setup_parse_targets(char *str)
+{
+ char *next = NULL;
+ size_t len = 0;
+ struct dm_setup_target **target = NULL;
+
+ /* Targets are defined as per the table format but with a
+ * comma as a newline separator. */
+ target = &dm_setup_args.target;
+ while (str && *str) {
+ *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL);
+ if (!*target) {
+ DMERR("failed to allocate memory for target %d",
+ dm_setup_args.target_count);
+ goto parse_fail;
+ }
+ dm_setup_args.target_count++;
+
+ (*target)->begin = simple_strtoull(str, &next, 10);
+ if (!next || *next != DM_FIELD_SEP) {
+ DMERR("failed to parse starting sector for target %d",
+ dm_setup_args.target_count - 1);
+ goto parse_fail;
+ }
+ str = skip_spaces(next + 1);
+
+ (*target)->length = simple_strtoull(str, &next, 10);
+ if (!next || *next != DM_FIELD_SEP) {
+ DMERR("failed to parse length for target %d",
+ dm_setup_args.target_count - 1);
+ goto parse_fail;
+ }
+ str = skip_spaces(next + 1);
+
+ len = get_dm_option(str, &next, DM_FIELD_SEP);
+ if (!len ||
+ !((*target)->type = kstrndup(str, len, GFP_KERNEL))) {
+ DMERR("failed to parse type for target %d",
+ dm_setup_args.target_count - 1);
+ goto parse_fail;
+ }
+ str = skip_spaces(next);
+
+ len = get_dm_option(str, &next, DM_LINE_SEP);
+ if (!len ||
+ !((*target)->params = kstrndup(str, len, GFP_KERNEL))) {
+ DMERR("failed to parse params for target %d",
+ dm_setup_args.target_count - 1);
+ goto parse_fail;
+ }
+ str = skip_spaces(next);
+
+ /* Before moving on, walk through the copied target and
+ * attempt to replace all /dev/xxx with the major:minor number.
+ * It may not be possible to resolve them traditionally at
+ * boot-time. */
+ dm_substitute_devices((*target)->params, len);
+
+ target = &((*target)->next);
+ }
+ DMDEBUG("parsed %d targets", dm_setup_args.target_count);
+
+ return 0;
+
+parse_fail:
+ return 1;
+}
+
+/*
+ * Parse the command-line parameters given our kernel, but do not
+ * actually try to invoke the DM device now; that is handled by
+ * dm_setup_drive after the low-level disk drivers have initialised.
+ * dm format is as follows:
+ * dm="name uuid fmode,[table line 1],[table line 2],..."
+ * May be used with root=/dev/dm-0 as it always uses the first dm minor.
+ */
+
+static int __init dm_setup(char *str)
+{
+ dm_setup_args_init();
+
+ str = dm_setup_parse_device_args(str);
+ if (!str) {
+ DMDEBUG("str is NULL");
+ goto parse_fail;
+ }
+
+ /* Target parsing is delayed until we have dynamic memory */
+ dm_setup_args.targets = str;
+
+ printk(KERN_INFO "dm: will configure '%s' on dm-%d\n",
+ dm_setup_args.name, dm_setup_args.minor);
+
+ dm_early_setup = 1;
+ return 1;
+
+parse_fail:
+ printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n");
+ return 0;
+}
+
+
+static void __init dm_setup_drive(void)
+{
+ struct mapped_device *md = NULL;
+ struct dm_table *table = NULL;
+ struct dm_setup_target *target;
+ char *uuid = dm_setup_args.uuid;
+ fmode_t fmode = FMODE_READ;
+
+ /* Finish parsing the targets. */
+ if (dm_setup_parse_targets(dm_setup_args.targets))
+ goto parse_fail;
+
+ if (dm_create(dm_setup_args.minor, &md)) {
+ DMDEBUG("failed to create the device");
+ goto dm_create_fail;
+ }
+ DMDEBUG("created device '%s'", dm_device_name(md));
+
+ /* In addition to flagging the table below, the disk must be
+ * set explicitly ro/rw. */
+ set_disk_ro(dm_disk(md), dm_setup_args.ro);
+
+ if (!dm_setup_args.ro)
+ fmode |= FMODE_WRITE;
+ if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) {
+ DMDEBUG("failed to create the table");
+ goto dm_table_create_fail;
+ }
+
+ target = dm_setup_args.target;
+ while (target) {
+ DMINFO("adding target '%llu %llu %s %s'",
+ (unsigned long long) target->begin,
+ (unsigned long long) target->length, target->type,
+ target->params);
+ if (dm_table_add_target(table, target->type, target->begin,
+ target->length, target->params)) {
+ DMDEBUG("failed to add the target to the table");
+ goto add_target_fail;
+ }
+ target = target->next;
+ }
+
+ if (dm_table_complete(table)) {
+ DMDEBUG("failed to complete the table");
+ goto table_complete_fail;
+ }
+
+ /* Suspend the device so that we can bind it to the table. */
+ if (dm_suspend(md, 0)) {
+ DMDEBUG("failed to suspend the device pre-bind");
+ goto suspend_fail;
+ }
+
+ /* Bind the table to the device. This is the only way to associate
+ * md->map with the table and set the disk capacity directly. */
+ if (dm_swap_table(md, table)) { /* should return NULL. */
+ DMDEBUG("failed to bind the device to the table");
+ goto table_bind_fail;
+ }
+
+ /* Finally, resume and the device should be ready. */
+ if (dm_resume(md)) {
+ DMDEBUG("failed to resume the device");
+ goto resume_fail;
+ }
+
+ /* Export the dm device via the ioctl interface */
+ if (!strcmp(DM_NO_UUID, dm_setup_args.uuid))
+ uuid = NULL;
+ if (dm_ioctl_export(md, dm_setup_args.name, uuid)) {
+ DMDEBUG("failed to export device with given name and uuid");
+ goto export_fail;
+ }
+ printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor);
+
+ dm_setup_cleanup();
+ return;
+
+export_fail:
+resume_fail:
+table_bind_fail:
+suspend_fail:
+table_complete_fail:
+add_target_fail:
+ dm_table_put(table);
+dm_table_create_fail:
+ dm_put(md);
+dm_create_fail:
+ dm_setup_cleanup();
+parse_fail:
+ printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n",
+ dm_setup_args.minor, dm_setup_args.name);
+}
+
+__setup("dm=", dm_setup);
+
+void __init dm_run_setup(void)
+{
+ if (!dm_early_setup)
+ return;
+ printk(KERN_INFO "dm: attempting early device configuration.\n");
+ dm_setup_drive();
+}
diff --git a/init/initramfs.c b/init/initramfs.c
index a67ef9d..43ae0cc 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -18,6 +18,7 @@
#include <linux/dirent.h>
#include <linux/syscalls.h>
#include <linux/utime.h>
+#include <linux/initramfs.h>
static __initdata char *message;
static void __init error(char *x)
@@ -579,9 +580,25 @@
}
#endif
+static int __initdata do_skip_initramfs;
+
+static int __init skip_initramfs_param(char *str)
+{
+ if (*str)
+ return 0;
+ do_skip_initramfs = 1;
+ return 1;
+}
+__setup("skip_initramfs", skip_initramfs_param);
+
static int __init populate_rootfs(void)
{
- char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
+ char *err;
+
+ if (do_skip_initramfs)
+ return default_rootfs();
+
+ err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
if (err)
panic(err); /* Failed to decompress INTERNAL initramfs */
if (initrd_start) {
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 267739d..bcc8bcb0 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -21,11 +21,16 @@
#include <linux/stat.h>
#include <linux/kdev_t.h>
#include <linux/syscalls.h>
+#include <linux/kconfig.h>
+#include <linux/initramfs.h>
/*
* Create a simple rootfs that is similar to the default initramfs
*/
-static int __init default_rootfs(void)
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+static
+#endif
+int __init default_rootfs(void)
{
int err;
@@ -49,4 +54,6 @@
printk(KERN_WARNING "Failed to create a rootfs\n");
return err;
}
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
rootfs_initcall(default_rootfs);
+#endif
diff --git a/kernel/Makefile b/kernel/Makefile
index 271fd31..984bc58 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -52,8 +52,9 @@
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
obj-$(CONFIG_KEXEC) += kexec.o
@@ -140,19 +141,52 @@
$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
$(call if_changed,bc)
+###############################################################################
+#
+# Roll all the X.509 certificates that we can find together and pull them into
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
+#
+# We look in the source root and the build root for all files whose name ends
+# in ".x509". Unfortunately, this will generate duplicate filenames, so we
+# have make canonicalise the pathnames and then sort them to discard the
+# duplicates.
+#
+###############################################################################
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
+X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+ $(or $(realpath $(CERT)),$(CERT))))
+
+ifeq ($(X509_CERTIFICATES),)
+$(warning *** No X.509 certificates found ***)
+endif
+
+ifneq ($(wildcard $(obj)/.x509.list),)
+ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
+$(info X.509 certificate list changed)
+$(shell rm $(obj)/.x509.list)
+endif
+endif
+
+kernel/system_certificates.o: $(obj)/x509_certificate_list
+
+quiet_cmd_x509certs = CERTS $@
+ cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)")
+
+targets += $(obj)/x509_certificate_list
+$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
+ $(call if_changed,x509certs)
+
+targets += $(obj)/.x509.list
+$(obj)/.x509.list:
+ @echo $(X509_CERTIFICATES) >$@
+
+clean-files := x509_certificate_list .x509.list
+endif
+
ifeq ($(CONFIG_MODULE_SIG),y)
-#
-# Pull the signing certificate and any extra certificates into the kernel
-#
-
-quiet_cmd_touch = TOUCH $@
- cmd_touch = touch $@
-
-extra_certificates:
- $(call cmd,touch)
-
-kernel/modsign_certificate.o: signing_key.x509 extra_certificates
-
###############################################################################
#
# If module signing is requested, say by allyesconfig, but a key has not been
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ef13060..fcf0aef 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2106,6 +2106,43 @@
return retval;
}
+static int cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys *ss;
+ int ret;
+
+ for_each_subsys(cgrp->root, ss) {
+ if (ss->allow_attach) {
+ ret = ss->allow_attach(cgrp, tset);
+ if (ret)
+ return ret;
+ } else {
+ return -EACCES;
+ }
+ }
+
+ return 0;
+}
+
+int subsys_cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+ const struct cred *cred = current_cred(), *tcred;
+ struct task_struct *task;
+
+ if (capable(CAP_SYS_NICE))
+ return 0;
+
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ tcred = __task_cred(task);
+
+ if (current != task && cred->euid != tcred->uid &&
+ cred->euid != tcred->suid)
+ return -EACCES;
+ }
+
+ return 0;
+}
+
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
* function to attach either it or all tasks in its threadgroup. Will lock
@@ -2137,9 +2174,18 @@
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
!uid_eq(cred->euid, tcred->suid)) {
- rcu_read_unlock();
- ret = -EACCES;
- goto out_unlock_cgroup;
+ /*
+ * if the default permission check fails, give each
+ * cgroup a chance to extend the permission check
+ */
+ struct cgroup_taskset tset = { };
+ tset.single.task = tsk;
+ tset.single.cgrp = cgrp;
+ ret = cgroup_allow_attach(cgrp, &tset);
+ if (ret) {
+ rcu_read_unlock();
+ goto out_unlock_cgroup;
+ }
}
} else
tsk = current;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index bc255e2..cf33817 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -20,6 +20,8 @@
#include <linux/gfp.h>
#include <linux/suspend.h>
+#include <trace/events/sched.h>
+
#include "smpboot.h"
#ifdef CONFIG_SMP
@@ -27,18 +29,23 @@
static DEFINE_MUTEX(cpu_add_remove_lock);
/*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_begin);
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_done);
static RAW_NOTIFIER_HEAD(cpu_chain);
@@ -169,6 +176,11 @@
return ret;
}
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+ return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
int *nr_calls)
{
@@ -192,6 +204,7 @@
BUG_ON(cpu_notify(val, v));
}
EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
void __ref unregister_cpu_notifier(struct notifier_block *nb)
{
@@ -201,6 +214,12 @@
}
EXPORT_SYMBOL(unregister_cpu_notifier);
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+ raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
@@ -340,6 +359,7 @@
out_release:
cpu_hotplug_done();
+ trace_sched_cpu_hotplug(cpu, err, 0);
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
return err;
@@ -415,6 +435,7 @@
__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
out:
cpu_hotplug_done();
+ trace_sched_cpu_hotplug(cpu, ret, 1);
return ret;
}
@@ -526,6 +547,7 @@
void __ref enable_nonboot_cpus(void)
{
int cpu, error;
+ struct device *cpu_device;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
@@ -541,6 +563,12 @@
error = _cpu_up(cpu, 1);
if (!error) {
printk(KERN_INFO "CPU%d is up\n", cpu);
+ cpu_device = get_cpu_device(cpu);
+ if (!cpu_device)
+ pr_err("%s: failed to get cpu%d device\n",
+ __func__, cpu);
+ else
+ kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
continue;
}
printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
@@ -728,3 +756,23 @@
{
cpumask_copy(to_cpumask(cpu_online_bits), src);
}
+
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+
+void idle_notifier_call_chain(unsigned long val)
+{
+ atomic_notifier_call_chain(&idle_notifier, val, NULL);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_call_chain);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0506d44..2d4438b 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -86,6 +86,10 @@
bool dbg_is_early = true;
/* Next cpu to become the master debug core */
int dbg_switch_cpu;
+/* Flag for entering kdb when a panic occurs */
+static bool break_on_panic = true;
+/* Flag for entering kdb when an exception occurs */
+static bool break_on_exception = true;
/* Use kdb or gdbserver mode */
int dbg_kdb_mode = 1;
@@ -100,6 +104,8 @@
module_param(kgdb_use_con, int, 0644);
module_param(kgdbreboot, int, 0644);
+module_param(break_on_panic, bool, 0644);
+module_param(break_on_exception, bool, 0644);
/*
* Holds information about breakpoints in a kernel. These breakpoints are
@@ -678,6 +684,9 @@
if (arch_kgdb_ops.enable_nmi)
arch_kgdb_ops.enable_nmi(0);
+ if (unlikely(signo != SIGTRAP && !break_on_exception))
+ return 1;
+
ks->cpu = raw_smp_processor_id();
ks->ex_vector = evector;
ks->signo = signo;
@@ -784,6 +793,9 @@
unsigned long val,
void *data)
{
+ if (!break_on_panic)
+ return NOTIFY_DONE;
+
if (dbg_kdb_mode)
kdb_printf("PANIC: %s\n", (char *)data);
kgdb_breakpoint();
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 14ff484..4b0fb2f 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@
int i;
int diag, dtab_count;
int key;
-
+ static int last_crlf;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
if (diag)
@@ -237,6 +237,9 @@
return buffer;
if (key != 9)
tab = 0;
+ if (key != 10 && key != 13)
+ last_crlf = 0;
+
switch (key) {
case 8: /* backspace */
if (cp > buffer) {
@@ -254,7 +257,12 @@
*cp = tmp;
}
break;
- case 13: /* enter */
+ case 10: /* new line */
+ case 13: /* carriage return */
+ /* handle \n after \r */
+ if (last_crlf && last_crlf != key)
+ break;
+ last_crlf = key;
*lastchar++ = '\n';
*lastchar++ = '\0';
if (!KDB_STATE(KGDB_TRANS)) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0f52078..b7045ba 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -157,8 +157,13 @@
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
+ * 3 - disallow all unpriv perf event use
*/
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
int sysctl_perf_event_paranoid __read_mostly = 1;
+#endif
/* Minimum for 512 kiB + 1 user control page */
int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -6725,6 +6730,9 @@
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
+ if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 0dbeae3..36cc21d 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -68,7 +68,14 @@
goto out;
}
-#ifdef CONFIG_MODULES
+/*
+ * Disable the request_module here to avoid trying to
+ * load the personality-8 module, which doesn't exist,
+ * and results in selinux audit noise.
+ * Disabling this here avoids folks adding module_request
+ * to their sepolicy, which is maybe too generous
+ */
+#if 0
read_unlock(&exec_domains_lock);
request_module("personality-%d", pers);
read_lock(&exec_domains_lock);
diff --git a/kernel/exit.c b/kernel/exit.c
index 717efbd..33fde71 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -841,7 +841,7 @@
/*
* Make sure we are holding no locks:
*/
- debug_check_no_locks_held(tsk);
+ debug_check_no_locks_held();
/*
* We can do this unlocked here. The futex code uses this flag
* just to verify whether the pi state cleanup has been done
diff --git a/kernel/fork.c b/kernel/fork.c
index 2358bd4..6038b37 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -198,6 +198,9 @@
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+/* Notifier list called when a task struct is freed */
+static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
+
static void account_kernel_stack(struct thread_info *ti, int account)
{
struct zone *zone = page_zone(virt_to_page(ti));
@@ -231,6 +234,18 @@
free_signal_struct(sig);
}
+int task_free_register(struct notifier_block *n)
+{
+ return atomic_notifier_chain_register(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_register);
+
+int task_free_unregister(struct notifier_block *n)
+{
+ return atomic_notifier_chain_unregister(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_unregister);
+
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
@@ -242,6 +257,7 @@
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
+ atomic_notifier_call_chain(&task_free_notifier, 0, tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
@@ -311,6 +327,15 @@
goto free_ti;
tsk->stack = ti;
+#ifdef CONFIG_SECCOMP
+ /*
+ * We must handle setting up seccomp filters once we're under
+ * the sighand lock in case orig has changed between now and
+ * then. Until then, filter must be NULL to avoid messing up
+ * the usage counts on the error path calling free_task.
+ */
+ tsk->seccomp.filter = NULL;
+#endif
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
@@ -697,7 +722,8 @@
mm = get_task_mm(task);
if (mm && mm != current->mm &&
- !ptrace_may_access(task, mode)) {
+ !ptrace_may_access(task, mode) &&
+ !capable(CAP_SYS_RESOURCE)) {
mmput(mm);
mm = ERR_PTR(-EACCES);
}
@@ -1091,6 +1117,39 @@
p->flags = new_flags;
}
+static void copy_seccomp(struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+ /*
+ * Must be called with sighand->lock held, which is common to
+ * all threads in the group. Holding cred_guard_mutex is not
+ * needed because this new task is not yet running and cannot
+ * be racing exec.
+ */
+ assert_spin_locked(¤t->sighand->siglock);
+
+ /* Ref-count the new filter user, and assign it. */
+ get_seccomp_filter(current);
+ p->seccomp = current->seccomp;
+
+ /*
+ * Explicitly enable no_new_privs here in case it got set
+ * between the task_struct being duplicated and holding the
+ * sighand lock. The seccomp state and nnp must be in sync.
+ */
+ if (task_no_new_privs(current))
+ task_set_no_new_privs(p);
+
+ /*
+ * If the parent gained a seccomp mode after copying thread
+ * flags and between before we held the sighand lock, we have
+ * to manually enable the seccomp thread flag here.
+ */
+ if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
+ set_tsk_thread_flag(p, TIF_SECCOMP);
+#endif
+}
+
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
@@ -1195,7 +1254,6 @@
goto fork_out;
ftrace_graph_init_task(p);
- get_seccomp_filter(p);
rt_mutex_init_task(p);
@@ -1241,6 +1299,7 @@
p->utime = p->stime = p->gtime = 0;
p->utimescaled = p->stimescaled = 0;
+ p->cpu_power = 0;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
p->prev_cputime.utime = p->prev_cputime.stime = 0;
#endif
@@ -1438,6 +1497,12 @@
spin_lock(¤t->sighand->siglock);
/*
+ * Copy seccomp details explicitly here, in case they were changed
+ * before holding sighand lock.
+ */
+ copy_seccomp(p);
+
+ /*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
* fork. Restart if a signal comes in before we add the new process to
diff --git a/kernel/freezer.c b/kernel/freezer.c
index bd733f6..4ada72f 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -119,6 +119,18 @@
{
unsigned long flags;
+ /*
+ * This check can race with freezer_do_not_count, but worst case that
+ * will result in an extra wakeup being sent to the task. It does not
+ * race with freezer_count(), the barriers in freezer_count() and
+ * freezer_should_skip() ensure that either freezer_count() sees
+ * freezing == true in try_to_freeze() and freezes, or
+ * freezer_should_skip() sees !PF_FREEZE_SKIP and freezes the task
+ * normally.
+ */
+ if (freezer_should_skip(p))
+ return false;
+
spin_lock_irqsave(&freezer_lock, flags);
if (!freezing(p) || frozen(p)) {
spin_unlock_irqrestore(&freezer_lock, flags);
diff --git a/kernel/futex.c b/kernel/futex.c
index edc4bea..fea18ac 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -62,6 +62,7 @@
#include <linux/ptrace.h>
#include <linux/sched/rt.h>
#include <linux/hugetlb.h>
+#include <linux/freezer.h>
#include <asm/futex.h>
@@ -1935,7 +1936,7 @@
* is no timeout, or if it has yet to expire.
*/
if (!timeout || timeout->task)
- schedule();
+ freezable_schedule();
}
__set_current_state(TASK_RUNNING);
}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index aadf4b7..1e84be1 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -47,6 +47,7 @@
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/timer.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
@@ -1565,7 +1566,7 @@
t->task = NULL;
if (likely(t->task))
- schedule();
+ freezable_schedule();
hrtimer_cancel(&t->timer);
mode = HRTIMER_MODE_ABS;
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index abcd6ca..da5f2ff 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -10,7 +10,7 @@
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/syscore_ops.h>
-
+#include <linux/wakeup_reason.h>
#include "internals.h"
/**
@@ -103,14 +103,18 @@
int irq;
for_each_irq_desc(irq, desc) {
- /*
- * Only interrupts which are marked as wakeup source
- * and have not been disabled before the suspend check
- * can abort suspend.
- */
if (irqd_is_wakeup_set(&desc->irq_data)) {
- if (desc->depth == 1 && desc->istate & IRQS_PENDING)
+ if (desc->istate & IRQS_PENDING) {
+ log_suspend_abort_reason("Wakeup IRQ %d %s pending",
+ irq,
+ desc->action && desc->action->name ?
+ desc->action->name : "");
+ pr_info("Wakeup IRQ %d %s pending, suspend aborted\n",
+ irq,
+ desc->action && desc->action->name ?
+ desc->action->name : "");
return -EBUSY;
+ }
continue;
}
/*
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 1f3186b..e16c45b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4090,7 +4090,7 @@
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
-static void print_held_locks_bug(struct task_struct *curr)
+static void print_held_locks_bug(void)
{
if (!debug_locks_off())
return;
@@ -4099,22 +4099,21 @@
printk("\n");
printk("=====================================\n");
- printk("[ BUG: lock held at task exit time! ]\n");
+ printk("[ BUG: %s/%d still has locks held! ]\n",
+ current->comm, task_pid_nr(current));
print_kernel_ident();
printk("-------------------------------------\n");
- printk("%s/%d is exiting with locks still held!\n",
- curr->comm, task_pid_nr(curr));
- lockdep_print_held_locks(curr);
-
+ lockdep_print_held_locks(current);
printk("\nstack backtrace:\n");
dump_stack();
}
-void debug_check_no_locks_held(struct task_struct *task)
+void debug_check_no_locks_held(void)
{
- if (unlikely(task->lockdep_depth > 0))
- print_held_locks_bug(task);
+ if (unlikely(current->lockdep_depth > 0))
+ print_held_locks_bug();
}
+EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
void debug_show_all_locks(void)
{
diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S
deleted file mode 100644
index 4a9a86d..0000000
--- a/kernel/modsign_certificate.S
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <linux/export.h>
-
-#define GLOBAL(name) \
- .globl VMLINUX_SYMBOL(name); \
- VMLINUX_SYMBOL(name):
-
- .section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
- .incbin "signing_key.x509"
- .incbin "extra_certificates"
-GLOBAL(modsign_certificate_list_end)
diff --git a/kernel/module-internal.h b/kernel/module-internal.h
index 24f9247..915e123 100644
--- a/kernel/module-internal.h
+++ b/kernel/module-internal.h
@@ -9,6 +9,4 @@
* 2 of the Licence, or (at your option) any later version.
*/
-extern struct key *modsign_keyring;
-
extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index f2970bd..0034e36 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -14,6 +14,7 @@
#include <crypto/public_key.h>
#include <crypto/hash.h>
#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
#include "module-internal.h"
/*
@@ -157,7 +158,7 @@
pr_debug("Look up: \"%s\"\n", id);
- key = keyring_search(make_key_ref(modsign_keyring, 1),
+ key = keyring_search(make_key_ref(system_trusted_keyring, 1),
&key_type_asymmetric, id);
if (IS_ERR(key))
pr_warn("Request for unknown module key '%s' err %ld\n",
diff --git a/kernel/panic.c b/kernel/panic.c
index d3d74c4..59bf94e 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,13 +27,19 @@
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
+/* Machine specific panic information string */
+char *mach_panic_string;
+
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
-int panic_timeout;
+#ifndef CONFIG_PANIC_TIMEOUT
+#define CONFIG_PANIC_TIMEOUT 0
+#endif
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
@@ -378,6 +384,11 @@
void print_oops_end_marker(void)
{
init_oops_id();
+
+ if (mach_panic_string)
+ printk(KERN_WARNING "Board Information: %s\n",
+ mach_panic_string);
+
printk(KERN_WARNING "---[ end trace %016llx ]---\n",
(unsigned long long)oops_id);
}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 5dfdc9e..f8cc6c4 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -18,6 +18,14 @@
Turning OFF this setting is NOT recommended! If in doubt, say Y.
+config HAS_WAKELOCK
+ bool
+ default y
+
+config WAKELOCK
+ bool
+ default y
+
config HIBERNATE_CALLBACKS
bool
@@ -274,3 +282,10 @@
config CPU_PM
bool
depends on SUSPEND || CPU_IDLE
+
+config SUSPEND_TIME
+ bool "Log time spent in suspend"
+ ---help---
+ Prints the time spent in suspend in the kernel log, and
+ keeps statistics on the time spent in suspend in
+ /sys/kernel/debug/suspend_time
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 29472bf..74c713b 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -11,5 +11,8 @@
block_io.o
obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o
obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
+obj-$(CONFIG_SUSPEND_TIME) += suspend_time.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
+
+obj-$(CONFIG_SUSPEND) += wakeup_reason.o
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0695319..d1ccce3 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -17,7 +17,7 @@
#include <linux/delay.h>
#include <linux/workqueue.h>
#include <linux/kmod.h>
-
+#include <linux/wakeup_reason.h>
/*
* Timeout for stopping processes
*/
@@ -30,9 +30,13 @@
unsigned int todo;
bool wq_busy = false;
struct timeval start, end;
- u64 elapsed_csecs64;
- unsigned int elapsed_csecs;
+ u64 elapsed_msecs64;
+ unsigned int elapsed_msecs;
bool wakeup = false;
+ int sleep_usecs = USEC_PER_MSEC;
+#ifdef CONFIG_PM_SLEEP
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+#endif
do_gettimeofday(&start);
@@ -62,42 +66,51 @@
break;
if (pm_wakeup_pending()) {
+#ifdef CONFIG_PM_SLEEP
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
+#endif
wakeup = true;
break;
}
/*
* We need to retry, but first give the freezing tasks some
- * time to enter the refrigerator.
+ * time to enter the refrigerator. Start with an initial
+ * 1 ms sleep followed by exponential backoff until 8 ms.
*/
- msleep(10);
+ usleep_range(sleep_usecs / 2, sleep_usecs);
+ if (sleep_usecs < 8 * USEC_PER_MSEC)
+ sleep_usecs *= 2;
}
do_gettimeofday(&end);
- elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
- do_div(elapsed_csecs64, NSEC_PER_SEC / 100);
- elapsed_csecs = elapsed_csecs64;
+ elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
+ do_div(elapsed_msecs64, NSEC_PER_MSEC);
+ elapsed_msecs = elapsed_msecs64;
- if (todo) {
+ if (wakeup) {
printk("\n");
- printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds "
- "(%d tasks refusing to freeze, wq_busy=%d):\n",
- wakeup ? "aborted" : "failed",
- elapsed_csecs / 100, elapsed_csecs % 100,
+ printk(KERN_ERR "Freezing of tasks aborted after %d.%03d seconds",
+ elapsed_msecs / 1000, elapsed_msecs % 1000);
+ } else if (todo) {
+ printk("\n");
+ printk(KERN_ERR "Freezing of tasks failed after %d.%03d seconds"
+ " (%d tasks refusing to freeze, wq_busy=%d):\n",
+ elapsed_msecs / 1000, elapsed_msecs % 1000,
todo - wq_busy, wq_busy);
- if (!wakeup) {
- read_lock(&tasklist_lock);
- do_each_thread(g, p) {
- if (p != current && !freezer_should_skip(p)
- && freezing(p) && !frozen(p))
- sched_show_task(p);
- } while_each_thread(g, p);
- read_unlock(&tasklist_lock);
- }
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ if (p != current && !freezer_should_skip(p)
+ && freezing(p) && !frozen(p))
+ sched_show_task(p);
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
} else {
- printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100,
- elapsed_csecs % 100);
+ printk("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000,
+ elapsed_msecs % 1000);
}
return todo ? -EBUSY : 0;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 903c517..e2446e0 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -25,7 +25,9 @@
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/ftrace.h>
+#include <linux/rtc.h>
#include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
#include "power.h"
@@ -138,7 +140,7 @@
error = suspend_freeze_processes();
if (!error)
return 0;
-
+ log_suspend_abort_reason("One or more tasks refusing to freeze");
suspend_stats.failed_freeze++;
dpm_save_failed_step(SUSPEND_FREEZE);
Finish:
@@ -168,7 +170,8 @@
*/
static int suspend_enter(suspend_state_t state, bool *wakeup)
{
- int error;
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+ int error, last_dev;
if (need_suspend_ops(state) && suspend_ops->prepare) {
error = suspend_ops->prepare();
@@ -178,7 +181,11 @@
error = dpm_suspend_end(PMSG_SUSPEND);
if (error) {
+ last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+ last_dev %= REC_FAILED_NUM;
printk(KERN_ERR "PM: Some devices failed to power down\n");
+ log_suspend_abort_reason("%s device failed to power down",
+ suspend_stats.failed_devs[last_dev]);
goto Platform_finish;
}
@@ -203,8 +210,10 @@
}
error = disable_nonboot_cpus();
- if (error || suspend_test(TEST_CPUS))
+ if (error || suspend_test(TEST_CPUS)) {
+ log_suspend_abort_reason("Disabling non-boot cpus failed");
goto Enable_cpus;
+ }
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
@@ -215,6 +224,11 @@
if (!(suspend_test(TEST_CORE) || *wakeup)) {
error = suspend_ops->enter(state);
events_check_enabled = false;
+ } else if (*wakeup) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
+ error = -EBUSY;
}
syscore_resume();
}
@@ -262,6 +276,7 @@
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
+ log_suspend_abort_reason("Some devices failed to suspend");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
@@ -358,6 +373,18 @@
return error;
}
+static void pm_suspend_marker(char *annotation)
+{
+ struct timespec ts;
+ struct rtc_time tm;
+
+ getnstimeofday(&ts);
+ rtc_time_to_tm(ts.tv_sec, &tm);
+ pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n",
+ annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
+}
+
/**
* pm_suspend - Externally visible function for suspending the system.
* @state: System sleep state to enter.
@@ -372,6 +399,7 @@
if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
return -EINVAL;
+ pm_suspend_marker("entry");
error = enter_state(state);
if (error) {
suspend_stats.fail++;
@@ -379,6 +407,7 @@
} else {
suspend_stats.success++;
}
+ pm_suspend_marker("exit");
return error;
}
EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/suspend_time.c b/kernel/power/suspend_time.c
new file mode 100644
index 0000000..d2a65da
--- /dev/null
+++ b/kernel/power/suspend_time.c
@@ -0,0 +1,111 @@
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/syscore_ops.h>
+#include <linux/time.h>
+
+static struct timespec suspend_time_before;
+static unsigned int time_in_suspend_bins[32];
+
+#ifdef CONFIG_DEBUG_FS
+static int suspend_time_debug_show(struct seq_file *s, void *data)
+{
+ int bin;
+ seq_printf(s, "time (secs) count\n");
+ seq_printf(s, "------------------\n");
+ for (bin = 0; bin < 32; bin++) {
+ if (time_in_suspend_bins[bin] == 0)
+ continue;
+ seq_printf(s, "%4d - %4d %4u\n",
+ bin ? 1 << (bin - 1) : 0, 1 << bin,
+ time_in_suspend_bins[bin]);
+ }
+ return 0;
+}
+
+static int suspend_time_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, suspend_time_debug_show, NULL);
+}
+
+static const struct file_operations suspend_time_debug_fops = {
+ .open = suspend_time_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init suspend_time_debug_init(void)
+{
+ struct dentry *d;
+
+ d = debugfs_create_file("suspend_time", 0755, NULL, NULL,
+ &suspend_time_debug_fops);
+ if (!d) {
+ pr_err("Failed to create suspend_time debug file\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+late_initcall(suspend_time_debug_init);
+#endif
+
+static int suspend_time_syscore_suspend(void)
+{
+ read_persistent_clock(&suspend_time_before);
+
+ return 0;
+}
+
+static void suspend_time_syscore_resume(void)
+{
+ struct timespec after;
+
+ read_persistent_clock(&after);
+
+ after = timespec_sub(after, suspend_time_before);
+
+ time_in_suspend_bins[fls(after.tv_sec)]++;
+
+ pr_info("Suspended for %lu.%03lu seconds\n", after.tv_sec,
+ after.tv_nsec / NSEC_PER_MSEC);
+}
+
+static struct syscore_ops suspend_time_syscore_ops = {
+ .suspend = suspend_time_syscore_suspend,
+ .resume = suspend_time_syscore_resume,
+};
+
+static int suspend_time_syscore_init(void)
+{
+ register_syscore_ops(&suspend_time_syscore_ops);
+
+ return 0;
+}
+
+static void suspend_time_syscore_exit(void)
+{
+ unregister_syscore_ops(&suspend_time_syscore_ops);
+}
+module_init(suspend_time_syscore_init);
+module_exit(suspend_time_syscore_exit);
diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c
new file mode 100644
index 0000000..f18fb16
--- /dev/null
+++ b/kernel/power/wakeup_reason.c
@@ -0,0 +1,216 @@
+/*
+ * kernel/power/wakeup_reason.c
+ *
+ * Logs the reasons which caused the kernel to resume from
+ * the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/wakeup_reason.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+
+
+#define MAX_WAKEUP_REASON_IRQS 32
+static int irq_list[MAX_WAKEUP_REASON_IRQS];
+static int irqcount;
+static bool suspend_abort;
+static char abort_reason[MAX_SUSPEND_ABORT_LEN];
+static struct kobject *wakeup_reason;
+static DEFINE_SPINLOCK(resume_reason_lock);
+
+static struct timespec last_xtime; /* wall time before last suspend */
+static struct timespec curr_xtime; /* wall time after last suspend */
+static struct timespec last_stime; /* total_sleep_time before last suspend */
+static struct timespec curr_stime; /* total_sleep_time after last suspend */
+
+static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ int irq_no, buf_offset = 0;
+ struct irq_desc *desc;
+ spin_lock(&resume_reason_lock);
+ if (suspend_abort) {
+ buf_offset = sprintf(buf, "Abort: %s", abort_reason);
+ } else {
+ for (irq_no = 0; irq_no < irqcount; irq_no++) {
+ desc = irq_to_desc(irq_list[irq_no]);
+ if (desc && desc->action && desc->action->name)
+ buf_offset += sprintf(buf + buf_offset, "%d %s\n",
+ irq_list[irq_no], desc->action->name);
+ else
+ buf_offset += sprintf(buf + buf_offset, "%d\n",
+ irq_list[irq_no]);
+ }
+ }
+ spin_unlock(&resume_reason_lock);
+ return buf_offset;
+}
+
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct timespec sleep_time;
+ struct timespec total_time;
+ struct timespec suspend_resume_time;
+
+ sleep_time = timespec_sub(curr_stime, last_stime);
+ total_time = timespec_sub(curr_xtime, last_xtime);
+ suspend_resume_time = timespec_sub(total_time, sleep_time);
+
+ /*
+ * suspend_resume_time is calculated from sleep_time. Userspace would
+ * always need both. Export them in pair here.
+ */
+ return sprintf(buf, "%lu.%09lu %lu.%09lu\n",
+ suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec,
+ sleep_time.tv_sec, sleep_time.tv_nsec);
+}
+
+static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
+
+static struct attribute *attrs[] = {
+ &resume_reason.attr,
+ &suspend_time.attr,
+ NULL,
+};
+static struct attribute_group attr_group = {
+ .attrs = attrs,
+};
+
+/*
+ * logs all the wake up reasons to the kernel
+ * stores the irqs to expose them to the userspace via sysfs
+ */
+void log_wakeup_reason(int irq)
+{
+ struct irq_desc *desc;
+ desc = irq_to_desc(irq);
+ if (desc && desc->action && desc->action->name)
+ printk(KERN_INFO "Resume caused by IRQ %d, %s\n", irq,
+ desc->action->name);
+ else
+ printk(KERN_INFO "Resume caused by IRQ %d\n", irq);
+
+ spin_lock(&resume_reason_lock);
+ if (irqcount == MAX_WAKEUP_REASON_IRQS) {
+ spin_unlock(&resume_reason_lock);
+ printk(KERN_WARNING "Resume caused by more than %d IRQs\n",
+ MAX_WAKEUP_REASON_IRQS);
+ return;
+ }
+
+ irq_list[irqcount++] = irq;
+ spin_unlock(&resume_reason_lock);
+}
+
+int check_wakeup_reason(int irq)
+{
+ int irq_no;
+ int ret = false;
+
+ spin_lock(&resume_reason_lock);
+ for (irq_no = 0; irq_no < irqcount; irq_no++)
+ if (irq_list[irq_no] == irq) {
+ ret = true;
+ break;
+ }
+ spin_unlock(&resume_reason_lock);
+ return ret;
+}
+
+void log_suspend_abort_reason(const char *fmt, ...)
+{
+ va_list args;
+
+ spin_lock(&resume_reason_lock);
+
+ //Suspend abort reason has already been logged.
+ if (suspend_abort) {
+ spin_unlock(&resume_reason_lock);
+ return;
+ }
+
+ suspend_abort = true;
+ va_start(args, fmt);
+ vsnprintf(abort_reason, MAX_SUSPEND_ABORT_LEN, fmt, args);
+ va_end(args);
+ spin_unlock(&resume_reason_lock);
+}
+
+/* Detects a suspend and clears all the previous wake up reasons*/
+static int wakeup_reason_pm_event(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ struct timespec xtom; /* wall_to_monotonic, ignored */
+
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ spin_lock(&resume_reason_lock);
+ irqcount = 0;
+ suspend_abort = false;
+ spin_unlock(&resume_reason_lock);
+
+ get_xtime_and_monotonic_and_sleep_offset(&last_xtime, &xtom,
+ &last_stime);
+ break;
+ case PM_POST_SUSPEND:
+ get_xtime_and_monotonic_and_sleep_offset(&curr_xtime, &xtom,
+ &curr_stime);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block wakeup_reason_pm_notifier_block = {
+ .notifier_call = wakeup_reason_pm_event,
+};
+
+/* Initializes the sysfs parameter
+ * registers the pm_event notifier
+ */
+int __init wakeup_reason_init(void)
+{
+ int retval;
+
+ retval = register_pm_notifier(&wakeup_reason_pm_notifier_block);
+ if (retval)
+ printk(KERN_WARNING "[%s] failed to register PM notifier %d\n",
+ __func__, retval);
+
+ wakeup_reason = kobject_create_and_add("wakeup_reasons", kernel_kobj);
+ if (!wakeup_reason) {
+ printk(KERN_WARNING "[%s] failed to create a sysfs kobject\n",
+ __func__);
+ return 1;
+ }
+ retval = sysfs_create_group(wakeup_reason, &attr_group);
+ if (retval) {
+ kobject_put(wakeup_reason);
+ printk(KERN_WARNING "[%s] failed to create a sysfs group %d\n",
+ __func__, retval);
+ }
+ return 0;
+}
+
+late_initcall(wakeup_reason_init);
diff --git a/kernel/printk.c b/kernel/printk.c
index ee8f6be..85d03fe 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -51,6 +51,10 @@
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+extern void printascii(char *);
+#endif
+
/* printk's without a loglevel use this.. */
#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL
@@ -1578,6 +1582,10 @@
}
}
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+ printascii(text);
+#endif
+
if (level == -1)
level = default_message_loglevel;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 655d611..dd2eded 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7104,13 +7104,24 @@
return (nested == preempt_offset);
}
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+ __might_sleep_init_called = 1;
+ return 0;
+}
+early_initcall(__might_sleep_init);
+
void __might_sleep(const char *file, int line, int preempt_offset)
{
static unsigned long prev_jiffy; /* ratelimiting */
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ oops_in_progress)
+ return;
+ if (system_state != SYSTEM_RUNNING &&
+ (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
@@ -8082,6 +8093,7 @@
.css_offline = cpu_cgroup_css_offline,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
+ .allow_attach = subsys_cgroup_allow_attach,
.exit = cpu_cgroup_exit,
.subsys_id = cpu_cgroup_subsys_id,
.base_cftypes = cpu_files,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index c23a8fd..8cda97c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1,3 +1,4 @@
+#include <linux/cpufreq.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/tsacct_kern.h>
@@ -149,6 +150,11 @@
/* Account for user time used */
acct_account_cputime(p);
+
+#ifdef CONFIG_CPU_FREQ_STAT
+ /* Account power usage for user time */
+ acct_update_power(p, cputime);
+#endif
}
/*
@@ -199,6 +205,11 @@
/* Account for system time used */
acct_account_cputime(p);
+
+#ifdef CONFIG_CPU_FREQ_STAT
+ /* Account power usage for system time */
+ acct_update_power(p, cputime);
+#endif
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c7ab8ea..f7f801e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1650,6 +1650,7 @@
}
trace_sched_stat_blocked(tsk, delta);
+ trace_sched_blocked_reason(tsk);
/*
* Blocking time is in units of nanosecs, so shift by
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a1004..ba54fc2 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -18,15 +18,17 @@
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
/* #define SECCOMP_DEBUG 1 */
#ifdef CONFIG_SECCOMP_FILTER
#include <asm/syscall.h>
#include <linux/filter.h>
+#include <linux/pid.h>
#include <linux/ptrace.h>
#include <linux/security.h>
-#include <linux/slab.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>
@@ -95,7 +97,7 @@
if (off == BPF_DATA(nr))
return syscall_get_nr(current, regs);
if (off == BPF_DATA(arch))
- return syscall_get_arch(current, regs);
+ return syscall_get_arch();
if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
unsigned long value;
int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
@@ -201,32 +203,170 @@
*/
static u32 seccomp_run_filters(int syscall)
{
- struct seccomp_filter *f;
+ struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
- if (WARN_ON(current->seccomp.filter == NULL))
+ if (unlikely(WARN_ON(f == NULL)))
return SECCOMP_RET_KILL;
+ /* Make sure cross-thread synced filter points somewhere sane. */
+ smp_read_barrier_depends();
+
/*
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
- for (f = current->seccomp.filter; f; f = f->prev) {
+ for (; f; f = f->prev) {
u32 cur_ret = sk_run_filter(NULL, f->insns);
+
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
ret = cur_ret;
}
return ret;
}
+#endif /* CONFIG_SECCOMP_FILTER */
+
+static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
+{
+ assert_spin_locked(¤t->sighand->siglock);
+
+ if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
+ return false;
+
+ return true;
+}
+
+static inline void seccomp_assign_mode(struct task_struct *task,
+ unsigned long seccomp_mode)
+{
+ assert_spin_locked(&task->sighand->siglock);
+
+ task->seccomp.mode = seccomp_mode;
+ /*
+ * Make sure TIF_SECCOMP cannot be set before the mode (and
+ * filter) is set.
+ */
+ smp_mb();
+ set_tsk_thread_flag(task, TIF_SECCOMP);
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+/* Returns 1 if the parent is an ancestor of the child. */
+static int is_ancestor(struct seccomp_filter *parent,
+ struct seccomp_filter *child)
+{
+ /* NULL is the root ancestor. */
+ if (parent == NULL)
+ return 1;
+ for (; child; child = child->prev)
+ if (child == parent)
+ return 1;
+ return 0;
+}
/**
- * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * seccomp_can_sync_threads: checks if all threads can be synchronized
+ *
+ * Expects sighand and cred_guard_mutex locks to be held.
+ *
+ * Returns 0 on success, -ve on error, or the pid of a thread which was
+ * either not in the correct seccomp mode or it did not have an ancestral
+ * seccomp filter.
+ */
+static inline pid_t seccomp_can_sync_threads(void)
+{
+ struct task_struct *thread, *caller;
+
+ BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ assert_spin_locked(¤t->sighand->siglock);
+
+ /* Validate all threads being eligible for synchronization. */
+ caller = current;
+ for_each_thread(caller, thread) {
+ pid_t failed;
+
+ /* Skip current, since it is initiating the sync. */
+ if (thread == caller)
+ continue;
+
+ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
+ (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
+ is_ancestor(thread->seccomp.filter,
+ caller->seccomp.filter)))
+ continue;
+
+ /* Return the first thread that cannot be synchronized. */
+ failed = task_pid_vnr(thread);
+ /* If the pid cannot be resolved, then return -ESRCH */
+ if (unlikely(WARN_ON(failed == 0)))
+ failed = -ESRCH;
+ return failed;
+ }
+
+ return 0;
+}
+
+/**
+ * seccomp_sync_threads: sets all threads to use current's filter
+ *
+ * Expects sighand and cred_guard_mutex locks to be held, and for
+ * seccomp_can_sync_threads() to have returned success already
+ * without dropping the locks.
+ *
+ */
+static inline void seccomp_sync_threads(void)
+{
+ struct task_struct *thread, *caller;
+
+ BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex));
+ assert_spin_locked(¤t->sighand->siglock);
+
+ /* Synchronize all threads. */
+ caller = current;
+ for_each_thread(caller, thread) {
+ /* Skip current, since it needs no changes. */
+ if (thread == caller)
+ continue;
+
+ /* Get a task reference for the new leaf node. */
+ get_seccomp_filter(caller);
+ /*
+ * Drop the task reference to the shared ancestor since
+ * current's path will hold a reference. (This also
+ * allows a put before the assignment.)
+ */
+ put_seccomp_filter(thread);
+ smp_store_release(&thread->seccomp.filter,
+ caller->seccomp.filter);
+ /*
+ * Opt the other thread into seccomp if needed.
+ * As threads are considered to be trust-realm
+ * equivalent (see ptrace_may_access), it is safe to
+ * allow one thread to transition the other.
+ */
+ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) {
+ /*
+ * Don't let an unprivileged task work around
+ * the no_new_privs restriction by creating
+ * a thread that sets it up, enters seccomp,
+ * then dies.
+ */
+ if (task_no_new_privs(caller))
+ task_set_no_new_privs(thread);
+
+ seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+ }
+ }
+}
+
+/**
+ * seccomp_prepare_filter: Prepares a seccomp filter for use.
* @fprog: BPF program to install
*
- * Returns 0 on success or an errno on failure.
+ * Returns filter on success or an ERR_PTR on failure.
*/
-static long seccomp_attach_filter(struct sock_fprog *fprog)
+static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
{
struct seccomp_filter *filter;
unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
@@ -234,12 +374,13 @@
long ret;
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
+ BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));
for (filter = current->seccomp.filter; filter; filter = filter->prev)
total_insns += filter->len + 4; /* include a 4 instr penalty */
if (total_insns > MAX_INSNS_PER_PATH)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
/*
* Installing a seccomp filter requires that the task have
@@ -247,16 +388,16 @@
* This avoids scenarios where unprivileged tasks can affect the
* behavior of privileged children.
*/
- if (!current->no_new_privs &&
+ if (!task_no_new_privs(current) &&
security_capable_noaudit(current_cred(), current_user_ns(),
CAP_SYS_ADMIN) != 0)
- return -EACCES;
+ return ERR_PTR(-EACCES);
/* Allocate a new seccomp_filter */
filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
GFP_KERNEL|__GFP_NOWARN);
if (!filter)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);;
atomic_set(&filter->usage, 1);
filter->len = fprog->len;
@@ -275,28 +416,24 @@
if (ret)
goto fail;
- /*
- * If there is an existing filter, make it the prev and don't drop its
- * task reference.
- */
- filter->prev = current->seccomp.filter;
- current->seccomp.filter = filter;
- return 0;
+ return filter;
+
fail:
kfree(filter);
- return ret;
+ return ERR_PTR(ret);
}
/**
- * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog
* @user_filter: pointer to the user data containing a sock_fprog.
*
* Returns 0 on success and non-zero otherwise.
*/
-long seccomp_attach_user_filter(char __user *user_filter)
+static struct seccomp_filter *
+seccomp_prepare_user_filter(const char __user *user_filter)
{
struct sock_fprog fprog;
- long ret = -EFAULT;
+ struct seccomp_filter *filter = ERR_PTR(-EFAULT);
#ifdef CONFIG_COMPAT
if (is_compat_task()) {
@@ -309,9 +446,56 @@
#endif
if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
goto out;
- ret = seccomp_attach_filter(&fprog);
+ filter = seccomp_prepare_filter(&fprog);
out:
- return ret;
+ return filter;
+}
+
+/**
+ * seccomp_attach_filter: validate and attach filter
+ * @flags: flags to change filter behavior
+ * @filter: seccomp filter to add to the current process
+ *
+ * Caller must be holding current->sighand->siglock lock.
+ *
+ * Returns 0 on success, -ve on error.
+ */
+static long seccomp_attach_filter(unsigned int flags,
+ struct seccomp_filter *filter)
+{
+ unsigned long total_insns;
+ struct seccomp_filter *walker;
+
+ assert_spin_locked(¤t->sighand->siglock);
+
+ /* Validate resulting filter length. */
+ total_insns = filter->len;
+ for (walker = current->seccomp.filter; walker; walker = walker->prev)
+ total_insns += walker->len + 4; /* 4 instr penalty */
+ if (total_insns > MAX_INSNS_PER_PATH)
+ return -ENOMEM;
+
+ /* If thread sync has been requested, check that it is possible. */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
+ int ret;
+
+ ret = seccomp_can_sync_threads();
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * If there is an existing filter, make it the prev and don't drop its
+ * task reference.
+ */
+ filter->prev = current->seccomp.filter;
+ current->seccomp.filter = filter;
+
+ /* Now that the new filter is in place, synchronize to all threads. */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+ seccomp_sync_threads();
+
+ return 0;
}
/* get_seccomp_filter - increments the reference count of the filter on @tsk */
@@ -324,6 +508,13 @@
atomic_inc(&orig->usage);
}
+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+ if (filter) {
+ kfree(filter);
+ }
+}
+
/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
void put_seccomp_filter(struct task_struct *tsk)
{
@@ -332,7 +523,7 @@
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
orig = orig->prev;
- kfree(freeme);
+ seccomp_filter_free(freeme);
}
}
@@ -351,7 +542,7 @@
info.si_code = SYS_SECCOMP;
info.si_call_addr = (void __user *)KSTK_EIP(current);
info.si_errno = reason;
- info.si_arch = syscall_get_arch(current, task_pt_regs(current));
+ info.si_arch = syscall_get_arch();
info.si_syscall = syscall;
force_sig_info(SIGSYS, &info, current);
}
@@ -376,12 +567,17 @@
int __secure_computing(int this_syscall)
{
- int mode = current->seccomp.mode;
int exit_sig = 0;
int *syscall;
u32 ret;
- switch (mode) {
+ /*
+ * Make sure that any changes to mode from another thread have
+ * been seen after TIF_SECCOMP was seen.
+ */
+ rmb();
+
+ switch (current->seccomp.mode) {
case SECCOMP_MODE_STRICT:
syscall = mode1_syscalls;
#ifdef CONFIG_COMPAT
@@ -404,7 +600,9 @@
ret &= SECCOMP_RET_ACTION;
switch (ret) {
case SECCOMP_RET_ERRNO:
- /* Set the low-order 16-bits as a errno. */
+ /* Set low-order bits as an errno, capped at MAX_ERRNO. */
+ if (data > MAX_ERRNO)
+ data = MAX_ERRNO;
syscall_set_return_value(current, regs,
-data, 0);
goto skip;
@@ -467,47 +665,152 @@
}
/**
- * prctl_set_seccomp: configures current->seccomp.mode
- * @seccomp_mode: requested mode to use
- * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
- *
- * This function may be called repeatedly with a @seccomp_mode of
- * SECCOMP_MODE_FILTER to install additional filters. Every filter
- * successfully installed will be evaluated (in reverse order) for each system
- * call the task makes.
+ * seccomp_set_mode_strict: internal function for setting strict seccomp
*
* Once current->seccomp.mode is non-zero, it may not be changed.
*
* Returns 0 on success or -EINVAL on failure.
*/
-long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+static long seccomp_set_mode_strict(void)
{
+ const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
long ret = -EINVAL;
- if (current->seccomp.mode &&
- current->seccomp.mode != seccomp_mode)
+ spin_lock_irq(¤t->sighand->siglock);
+
+ if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
+#ifdef TIF_NOTSC
+ disable_TSC();
+#endif
+ seccomp_assign_mode(current, seccomp_mode);
+ ret = 0;
+
+out:
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ return ret;
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+/**
+ * seccomp_set_mode_filter: internal function for setting seccomp filter
+ * @flags: flags to change filter behavior
+ * @filter: struct sock_fprog containing filter
+ *
+ * This function may be called repeatedly to install additional filters.
+ * Every filter successfully installed will be evaluated (in reverse order)
+ * for each system call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+static long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
+{
+ const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
+ struct seccomp_filter *prepared = NULL;
+ long ret = -EINVAL;
+
+ /* Validate flags. */
+ if (flags & ~SECCOMP_FILTER_FLAG_MASK)
+ return -EINVAL;
+
+ /* Prepare the new filter before holding any locks. */
+ prepared = seccomp_prepare_user_filter(filter);
+ if (IS_ERR(prepared))
+ return PTR_ERR(prepared);
+
+ /*
+ * Make sure we cannot change seccomp or nnp state via TSYNC
+ * while another thread is in the middle of calling exec.
+ */
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
+ mutex_lock_killable(¤t->signal->cred_guard_mutex))
+ goto out_free;
+
+ spin_lock_irq(¤t->sighand->siglock);
+
+ if (!seccomp_may_assign_mode(seccomp_mode))
+ goto out;
+
+ ret = seccomp_attach_filter(flags, prepared);
+ if (ret)
+ goto out;
+ /* Do not free the successfully attached filter. */
+ prepared = NULL;
+
+ seccomp_assign_mode(current, seccomp_mode);
+out:
+ spin_unlock_irq(¤t->sighand->siglock);
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+ mutex_unlock(¤t->signal->cred_guard_mutex);
+out_free:
+ seccomp_filter_free(prepared);
+ return ret;
+}
+#else
+static inline long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
+{
+ return -EINVAL;
+}
+#endif
+
+/* Common entry point for both prctl and syscall. */
+static long do_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs)
+{
+ switch (op) {
+ case SECCOMP_SET_MODE_STRICT:
+ if (flags != 0 || uargs != NULL)
+ return -EINVAL;
+ return seccomp_set_mode_strict();
+ case SECCOMP_SET_MODE_FILTER:
+ return seccomp_set_mode_filter(flags, uargs);
+ default:
+ return -EINVAL;
+ }
+}
+
+SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
+ const char __user *, uargs)
+{
+ return do_seccomp(op, flags, uargs);
+}
+
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+{
+ unsigned int op;
+ char __user *uargs;
+
switch (seccomp_mode) {
case SECCOMP_MODE_STRICT:
- ret = 0;
-#ifdef TIF_NOTSC
- disable_TSC();
-#endif
+ op = SECCOMP_SET_MODE_STRICT;
+ /*
+ * Setting strict mode through prctl always ignored filter,
+ * so make sure it is always NULL here to pass the internal
+ * check in do_seccomp().
+ */
+ uargs = NULL;
break;
-#ifdef CONFIG_SECCOMP_FILTER
case SECCOMP_MODE_FILTER:
- ret = seccomp_attach_user_filter(filter);
- if (ret)
- goto out;
+ op = SECCOMP_SET_MODE_FILTER;
+ uargs = filter;
break;
-#endif
default:
- goto out;
+ return -EINVAL;
}
- current->seccomp.mode = seccomp_mode;
- set_thread_flag(TIF_SECCOMP);
-out:
- return ret;
+ /* prctl interface doesn't have flags, so they are always zero. */
+ return do_seccomp(op, 0, uargs);
}
diff --git a/kernel/signal.c b/kernel/signal.c
index 7b81c53..408f944 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2849,7 +2849,7 @@
recalc_sigpending();
spin_unlock_irq(&tsk->sighand->siglock);
- timeout = schedule_timeout_interruptible(timeout);
+ timeout = freezable_schedule_timeout_interruptible(timeout);
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, &tsk->real_blocked);
diff --git a/kernel/sys.c b/kernel/sys.c
index 2bbd9a7..a3bef5b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -42,6 +42,9 @@
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/mempolicy.h>
+#include <linux/sched.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
@@ -2099,10 +2102,158 @@
}
#endif
+#ifdef CONFIG_MMU
+static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end,
+ const char __user *name_addr)
+{
+ struct mm_struct * mm = vma->vm_mm;
+ int error = 0;
+ pgoff_t pgoff;
+
+ if (name_addr == vma_get_anon_name(vma)) {
+ *prev = vma;
+ goto out;
+ }
+
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+ *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
+ vma->vm_file, pgoff, vma_policy(vma),
+ name_addr);
+ if (*prev) {
+ vma = *prev;
+ goto success;
+ }
+
+ *prev = vma;
+
+ if (start != vma->vm_start) {
+ error = split_vma(mm, vma, start, 1);
+ if (error)
+ goto out;
+ }
+
+ if (end != vma->vm_end) {
+ error = split_vma(mm, vma, end, 0);
+ if (error)
+ goto out;
+ }
+
+success:
+ if (!vma->vm_file)
+ vma->shared.anon_name = name_addr;
+
+out:
+ if (error == -ENOMEM)
+ error = -EAGAIN;
+ return error;
+}
+
+static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
+ unsigned long arg)
+{
+ unsigned long tmp;
+ struct vm_area_struct * vma, *prev;
+ int unmapped_error = 0;
+ int error = -EINVAL;
+
+ /*
+ * If the interval [start,end) covers some unmapped address
+ * ranges, just ignore them, but return -ENOMEM at the end.
+ * - this matches the handling in madvise.
+ */
+ vma = find_vma_prev(current->mm, start, &prev);
+ if (vma && start > vma->vm_start)
+ prev = vma;
+
+ for (;;) {
+ /* Still start < end. */
+ error = -ENOMEM;
+ if (!vma)
+ return error;
+
+ /* Here start < (end|vma->vm_end). */
+ if (start < vma->vm_start) {
+ unmapped_error = -ENOMEM;
+ start = vma->vm_start;
+ if (start >= end)
+ return error;
+ }
+
+ /* Here vma->vm_start <= start < (end|vma->vm_end) */
+ tmp = vma->vm_end;
+ if (end < tmp)
+ tmp = end;
+
+ /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+ error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
+ (const char __user *)arg);
+ if (error)
+ return error;
+ start = tmp;
+ if (prev && start < prev->vm_end)
+ start = prev->vm_end;
+ error = unmapped_error;
+ if (start >= end)
+ return error;
+ if (prev)
+ vma = prev->vm_next;
+ else /* madvise_remove dropped mmap_sem */
+ vma = find_vma(current->mm, start);
+ }
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ struct mm_struct *mm = current->mm;
+ int error;
+ unsigned long len;
+ unsigned long end;
+
+ if (start & ~PAGE_MASK)
+ return -EINVAL;
+ len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+ /* Check to see whether len was rounded up from small -ve to zero */
+ if (len_in && !len)
+ return -EINVAL;
+
+ end = start + len;
+ if (end < start)
+ return -EINVAL;
+
+ if (end == start)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+
+ switch (opt) {
+ case PR_SET_VMA_ANON_NAME:
+ error = prctl_set_vma_anon_name(start, end, arg);
+ break;
+ default:
+ error = -EINVAL;
+ }
+
+ up_write(&mm->mmap_sem);
+
+ return error;
+}
+#else /* CONFIG_MMU */
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ return -EINVAL;
+}
+#endif
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
struct task_struct *me = current;
+ struct task_struct *tsk;
unsigned char comm[sizeof(me->comm)];
long error;
@@ -2245,6 +2396,26 @@
case PR_GET_TID_ADDRESS:
error = prctl_get_tid_address(me, (int __user **)arg2);
break;
+ case PR_SET_TIMERSLACK_PID:
+ if (task_pid_vnr(current) != (pid_t)arg3 &&
+ !capable(CAP_SYS_NICE))
+ return -EPERM;
+ rcu_read_lock();
+ tsk = find_task_by_vpid((pid_t)arg3);
+ if (tsk == NULL) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ if (arg2 <= 0)
+ tsk->timer_slack_ns =
+ tsk->default_timer_slack_ns;
+ else
+ tsk->timer_slack_ns = arg2;
+ put_task_struct(tsk);
+ error = 0;
+ break;
case PR_SET_CHILD_SUBREAPER:
me->signal->is_child_subreaper = !!arg2;
break;
@@ -2256,12 +2427,15 @@
if (arg2 != 1 || arg3 || arg4 || arg5)
return -EINVAL;
- current->no_new_privs = 1;
+ task_set_no_new_privs(current);
break;
case PR_GET_NO_NEW_PRIVS:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- return current->no_new_privs ? 1 : 0;
+ return task_no_new_privs(current) ? 1 : 0;
+ case PR_SET_VMA:
+ error = prctl_set_vma(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7078052..7e7fc0a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -209,3 +209,6 @@
/* compare kernel pointers */
cond_syscall(sys_kcmp);
+
+/* operate on Secure Computing state */
+cond_syscall(sys_seccomp);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4fd49fe..443f72d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -105,6 +105,8 @@
extern unsigned int core_pipe_limit;
#endif
extern int pid_max;
+extern int extra_free_kbytes;
+extern int min_free_order_shift;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
extern int compat_log;
@@ -1282,6 +1284,21 @@
.extra1 = &zero,
},
{
+ .procname = "extra_free_kbytes",
+ .data = &extra_free_kbytes,
+ .maxlen = sizeof(extra_free_kbytes),
+ .mode = 0644,
+ .proc_handler = min_free_kbytes_sysctl_handler,
+ .extra1 = &zero,
+ },
+ {
+ .procname = "min_free_order_shift",
+ .data = &min_free_order_shift,
+ .maxlen = sizeof(min_free_order_shift),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec
+ },
+ {
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
@@ -1459,6 +1476,28 @@
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+ {
+ .procname = "mmap_rnd_bits",
+ .data = &mmap_rnd_bits,
+ .maxlen = sizeof(mmap_rnd_bits),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&mmap_rnd_bits_min,
+ .extra2 = (void *)&mmap_rnd_bits_max,
+ },
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+ {
+ .procname = "mmap_rnd_compat_bits",
+ .data = &mmap_rnd_compat_bits,
+ .maxlen = sizeof(mmap_rnd_compat_bits),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&mmap_rnd_compat_bits_min,
+ .extra2 = (void *)&mmap_rnd_compat_bits_max,
+ },
+#endif
{ }
};
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
new file mode 100644
index 0000000..552d47b
--- /dev/null
+++ b/kernel/system_certificates.S
@@ -0,0 +1,12 @@
+#include <linux/export.h>
+#include <linux/init.h>
+
+#define GLOBAL(name) \
+ .globl VMLINUX_SYMBOL(name); \
+ VMLINUX_SYMBOL(name):
+
+ __INITRODATA
+
+GLOBAL(system_certificate_list)
+ .incbin "kernel/x509_certificate_list"
+GLOBAL(system_certificate_list_end)
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
new file mode 100644
index 0000000..51c3514
--- /dev/null
+++ b/kernel/system_keyring.c
@@ -0,0 +1,103 @@
+/* System trusted keyring for trusted public keys
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "module-internal.h"
+
+struct key *system_trusted_keyring;
+EXPORT_SYMBOL_GPL(system_trusted_keyring);
+
+extern __initconst const u8 system_certificate_list[];
+extern __initconst const u8 system_certificate_list_end[];
+
+/*
+ * Load the compiled-in keys
+ */
+static __init int system_trusted_keyring_init(void)
+{
+ pr_notice("Initialise system trusted keyring\n");
+
+ system_trusted_keyring =
+ keyring_alloc(".system_keyring",
+ KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ if (IS_ERR(system_trusted_keyring))
+ panic("Can't allocate system trusted keyring\n");
+
+ return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(system_trusted_keyring_init);
+
+/*
+ * Load the compiled-in list of X.509 certificates.
+ */
+static __init int load_system_certificate_list(void)
+{
+ key_ref_t key;
+ const u8 *p, *end;
+ size_t plen;
+
+ pr_notice("Loading compiled-in X.509 certificates\n");
+
+ end = system_certificate_list_end;
+ p = system_certificate_list;
+ while (p < end) {
+ /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+ * than 256 bytes in size.
+ */
+ if (end - p < 4)
+ goto dodgy_cert;
+ if (p[0] != 0x30 &&
+ p[1] != 0x82)
+ goto dodgy_cert;
+ plen = (p[2] << 8) | p[3];
+ plen += 4;
+ if (plen > end - p)
+ goto dodgy_cert;
+
+ key = key_create_or_update(make_key_ref(system_trusted_keyring, 1),
+ "asymmetric",
+ NULL,
+ p,
+ plen,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW,
+ KEY_ALLOC_NOT_IN_QUOTA);
+ if (IS_ERR(key)) {
+ pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+ PTR_ERR(key));
+ } else {
+ pr_notice("Loaded X.509 cert '%s'\n",
+ key_ref_to_ptr(key)->description);
+ key_ref_put(key);
+ }
+ p += plen;
+ }
+
+ return 0;
+
+dodgy_cert:
+ pr_err("Problem parsing in-kernel X.509 certificate list\n");
+ return 0;
+}
+late_initcall(load_system_certificate_list);
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 7d19fca..bb08d09 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -199,6 +199,12 @@
}
+ktime_t alarm_expires_remaining(const struct alarm *alarm)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+ return ktime_sub(alarm->node.expires, base->gettime());
+}
+
#ifdef CONFIG_RTC_CLASS
/**
* alarmtimer_suspend - Suspend time callback
@@ -305,7 +311,7 @@
}
/**
- * alarm_start - Sets an alarm to fire
+ * alarm_start - Sets an absolute alarm to fire
* @alarm: ptr to alarm to set
* @start: time to run the alarm
*/
@@ -325,6 +331,31 @@
}
/**
+ * alarm_start_relative - Sets a relative alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time relative to now to run the alarm
+ */
+int alarm_start_relative(struct alarm *alarm, ktime_t start)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+
+ start = ktime_add(start, base->gettime());
+ return alarm_start(alarm, start);
+}
+
+void alarm_restart(struct alarm *alarm)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+ unsigned long flags;
+
+ spin_lock_irqsave(&base->lock, flags);
+ hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+ hrtimer_restart(&alarm->timer);
+ alarmtimer_enqueue(base, alarm);
+ spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
* alarm_try_to_cancel - Tries to cancel an alarm timer
* @alarm: ptr to alarm to be canceled
*
@@ -394,6 +425,12 @@
return overrun;
}
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+ struct alarm_base *base = &alarm_bases[alarm->type];
+
+ return alarm_forward(alarm, base->gettime(), interval);
+}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 015f85a..e24c188 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -82,6 +82,9 @@
select CONTEXT_SWITCH_TRACER
bool
+config GPU_TRACEPOINTS
+ bool
+
config CONTEXT_SWITCH_TRACER
bool
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d7e2068..4501212 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -60,5 +60,6 @@
endif
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c
new file mode 100644
index 0000000..a4b3f00
--- /dev/null
+++ b/kernel/trace/gpu-traces.c
@@ -0,0 +1,23 @@
+/*
+ * GPU tracepoints
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/gpu.h>
+
+EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch);
+EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eff26a9..3415bfd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -730,6 +730,7 @@
"irq-info",
"markers",
"function-trace",
+ "print-tgid",
NULL
};
@@ -1242,6 +1243,7 @@
static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
+static unsigned saved_tgids[SAVED_CMDLINES];
static int cmdline_idx;
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -1443,6 +1445,7 @@
}
memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+ saved_tgids[idx] = tsk->tgid;
arch_spin_unlock(&trace_cmdline_lock);
@@ -1480,6 +1483,25 @@
preempt_enable();
}
+int trace_find_tgid(int pid)
+{
+ unsigned map;
+ int tgid;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+ map = map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ tgid = saved_tgids[map];
+ else
+ tgid = -1;
+
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ return tgid;
+}
+
void tracing_record_cmdline(struct task_struct *tsk)
{
if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
@@ -2435,6 +2457,13 @@
seq_puts(m, "# | | | | |\n");
}
+static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# TASK-PID TGID CPU# TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | | |\n");
+}
+
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
print_event_info(buf, m);
@@ -2447,6 +2476,18 @@
seq_puts(m, "# | | | |||| | |\n");
}
+static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# _-----=> irqs-off\n");
+ seq_puts(m, "# / _----=> need-resched\n");
+ seq_puts(m, "# | / _---=> hardirq/softirq\n");
+ seq_puts(m, "# || / _--=> preempt-depth\n");
+ seq_puts(m, "# ||| / delay\n");
+ seq_puts(m, "# TASK-PID TGID CPU# |||| TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | |||| | |\n");
+}
+
void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
@@ -2747,9 +2788,15 @@
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_irq_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header_irq(iter->trace_buffer, m);
else
- print_func_help_header(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header(iter->trace_buffer, m);
}
}
}
@@ -3601,9 +3648,53 @@
}
static const struct file_operations tracing_saved_cmdlines_fops = {
- .open = tracing_open_generic,
- .read = tracing_saved_cmdlines_read,
- .llseek = generic_file_llseek,
+ .open = tracing_open_generic,
+ .read = tracing_saved_cmdlines_read,
+ .llseek = generic_file_llseek,
+};
+
+static ssize_t
+tracing_saved_tgids_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int pid;
+ int i;
+
+ file_buf = kmalloc(SAVED_CMDLINES*(16+1+16), GFP_KERNEL);
+ if (!file_buf)
+ return -ENOMEM;
+
+ buf = file_buf;
+
+ for (i = 0; i < SAVED_CMDLINES; i++) {
+ int tgid;
+ int r;
+
+ pid = map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ tgid = trace_find_tgid(pid);
+ r = sprintf(buf, "%d %d\n", pid, tgid);
+ buf += r;
+ len += r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, len);
+
+ kfree(file_buf);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_tgids_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_tgids_read,
+ .llseek = generic_file_llseek,
};
static ssize_t
@@ -6160,6 +6251,9 @@
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
+ trace_create_file("saved_tgids", 0444, d_tracer,
+ tr, &tracing_saved_tgids_fops);
+
trace_create_file("trace_clock", 0644, d_tracer, tr,
&trace_clock_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index fe57607..b8a1ac7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -654,6 +654,7 @@
extern cycle_t ftrace_now(int cpu);
extern void trace_find_cmdline(int pid, char comm[]);
+extern int trace_find_tgid(int pid);
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
@@ -867,6 +868,7 @@
TRACE_ITER_IRQ_INFO = 0x800000,
TRACE_ITER_MARKERS = 0x1000000,
TRACE_ITER_FUNCTION = 0x2000000,
+ TRACE_ITER_TGID = 0x4000000,
};
/*
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 8388bc9..28dd40c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -46,6 +46,8 @@
#define TRACE_GRAPH_PRINT_DURATION 0x10
#define TRACE_GRAPH_PRINT_ABS_TIME 0x20
#define TRACE_GRAPH_PRINT_IRQS 0x40
+#define TRACE_GRAPH_PRINT_FLAT 0x80
+
static unsigned int max_depth;
@@ -64,6 +66,8 @@
{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
/* Display interrupts */
{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
+ /* Use standard trace formatting rather than hierarchical */
+ { TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) },
{ } /* Empty entry */
};
@@ -1234,6 +1238,9 @@
int cpu = iter->cpu;
int ret;
+ if (flags & TRACE_GRAPH_PRINT_FLAT)
+ return TRACE_TYPE_UNHANDLED;
+
if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
return TRACE_TYPE_HANDLED;
@@ -1291,13 +1298,6 @@
return print_graph_function_flags(iter, tracer_flags.val);
}
-static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags,
- struct trace_event *event)
-{
- return print_graph_function(iter);
-}
-
static void print_lat_header(struct seq_file *s, u32 flags)
{
static const char spaces[] = " " /* 16 spaces */
@@ -1364,6 +1364,11 @@
{
struct trace_iterator *iter = s->private;
+ if (flags & TRACE_GRAPH_PRINT_FLAT) {
+ trace_default_header(s);
+ return;
+ }
+
if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
return;
@@ -1434,20 +1439,6 @@
return 0;
}
-static struct trace_event_functions graph_functions = {
- .trace = print_graph_function_event,
-};
-
-static struct trace_event graph_trace_entry_event = {
- .type = TRACE_GRAPH_ENT,
- .funcs = &graph_functions,
-};
-
-static struct trace_event graph_trace_ret_event = {
- .type = TRACE_GRAPH_RET,
- .funcs = &graph_functions
-};
-
static struct tracer graph_trace __read_mostly = {
.name = "function_graph",
.open = graph_trace_open,
@@ -1523,16 +1514,6 @@
{
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
- if (!register_ftrace_event(&graph_trace_entry_event)) {
- pr_warning("Warning: could not register graph trace events\n");
- return 1;
- }
-
- if (!register_ftrace_event(&graph_trace_ret_event)) {
- pr_warning("Warning: could not register graph trace events\n");
- return 1;
- }
-
return register_tracer(&graph_trace);
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index bb922d9..a68e5e3 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -702,11 +702,25 @@
unsigned long secs, usec_rem;
char comm[TASK_COMM_LEN];
int ret;
+ int tgid;
trace_find_cmdline(entry->pid, comm);
- ret = trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+ if (!ret)
+ return 0;
+
+ if (trace_flags & TRACE_ITER_TGID) {
+ tgid = trace_find_tgid(entry->pid);
+ if (tgid < 0)
+ ret = trace_seq_puts(s, "(-----) ");
+ else
+ ret = trace_seq_printf(s, "(%5d) ", tgid);
+ if (!ret)
+ return 0;
+ }
+
+ ret = trace_seq_printf(s, "[%03d] ", iter->cpu);
if (!ret)
return 0;
@@ -1035,6 +1049,168 @@
.funcs = &trace_fn_funcs,
};
+/* TRACE_GRAPH_ENT */
+static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_puts(s, "graph_ent: func="))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->graph_ent.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!trace_seq_puts(s, "\n"))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(&iter->seq, "%lx %d\n",
+ field->graph_ent.func,
+ field->graph_ent.depth))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.func);
+ SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD_RET(s, field->graph_ent.func);
+ SEQ_PUT_FIELD_RET(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ent_funcs = {
+ .trace = trace_graph_ent_trace,
+ .raw = trace_graph_ent_raw,
+ .hex = trace_graph_ent_hex,
+ .binary = trace_graph_ent_bin,
+};
+
+static struct trace_event trace_graph_ent_event = {
+ .type = TRACE_GRAPH_ENT,
+ .funcs = &trace_graph_ent_funcs,
+};
+
+/* TRACE_GRAPH_RET */
+static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, entry);
+
+ if (!trace_seq_puts(s, "graph_ret: func="))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->ret.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!trace_seq_puts(s, "\n"))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n",
+ field->ret.func,
+ field->ret.calltime,
+ field->ret.rettime,
+ field->ret.overrun,
+ field->ret.depth));
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD_RET(s, field->ret.func);
+ SEQ_PUT_HEX_FIELD_RET(s, field->ret.calltime);
+ SEQ_PUT_HEX_FIELD_RET(s, field->ret.rettime);
+ SEQ_PUT_HEX_FIELD_RET(s, field->ret.overrun);
+ SEQ_PUT_HEX_FIELD_RET(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD_RET(s, field->ret.func);
+ SEQ_PUT_FIELD_RET(s, field->ret.calltime);
+ SEQ_PUT_FIELD_RET(s, field->ret.rettime);
+ SEQ_PUT_FIELD_RET(s, field->ret.overrun);
+ SEQ_PUT_FIELD_RET(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ret_funcs = {
+ .trace = trace_graph_ret_trace,
+ .raw = trace_graph_ret_raw,
+ .hex = trace_graph_ret_hex,
+ .binary = trace_graph_ret_bin,
+};
+
+static struct trace_event trace_graph_ret_event = {
+ .type = TRACE_GRAPH_RET,
+ .funcs = &trace_graph_ret_funcs,
+};
+
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
@@ -1425,6 +1601,8 @@
static struct trace_event *events[] __initdata = {
&trace_fn_event,
+ &trace_graph_ent_event,
+ &trace_graph_ret_event,
&trace_ctx_event,
&trace_wake_event,
&trace_stack_event,
diff --git a/kernel/wait.c b/kernel/wait.c
index 6698e0c..bca170e 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -287,3 +287,12 @@
return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
}
EXPORT_SYMBOL(bit_waitqueue);
+
+__sched int bit_wait_io(void *word)
+{
+ if (signal_pending_state(current->state, current))
+ return 1;
+ io_schedule();
+ return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 05039e3..e092e5a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -45,6 +45,11 @@
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static cpumask_t __read_mostly watchdog_cpus;
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
@@ -178,7 +183,7 @@
__raw_get_cpu_var(watchdog_touch_ts) = 0;
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/* watchdog detector functions */
static int is_hardlockup(void)
{
@@ -192,6 +197,76 @@
}
#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static unsigned int watchdog_next_cpu(unsigned int cpu)
+{
+ cpumask_t cpus = watchdog_cpus;
+ unsigned int next_cpu;
+
+ next_cpu = cpumask_next(cpu, &cpus);
+ if (next_cpu >= nr_cpu_ids)
+ next_cpu = cpumask_first(&cpus);
+
+ if (next_cpu == cpu)
+ return nr_cpu_ids;
+
+ return next_cpu;
+}
+
+static int is_hardlockup_other_cpu(unsigned int cpu)
+{
+ unsigned long hrint = per_cpu(hrtimer_interrupts, cpu);
+
+ if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+ return 1;
+
+ per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+ return 0;
+}
+
+static void watchdog_check_hardlockup_other_cpu(void)
+{
+ unsigned int next_cpu;
+
+ /*
+ * Test for hardlockups every 3 samples. The sample period is
+ * watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
+ * watchdog_thresh (over by 20%).
+ */
+ if (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
+ return;
+
+ /* check for a hardlockup on the next cpu */
+ next_cpu = watchdog_next_cpu(smp_processor_id());
+ if (next_cpu >= nr_cpu_ids)
+ return;
+
+ smp_rmb();
+
+ if (per_cpu(watchdog_nmi_touch, next_cpu) == true) {
+ per_cpu(watchdog_nmi_touch, next_cpu) = false;
+ return;
+ }
+
+ if (is_hardlockup_other_cpu(next_cpu)) {
+ /* only warn once */
+ if (per_cpu(hard_watchdog_warn, next_cpu) == true)
+ return;
+
+ if (hardlockup_panic)
+ panic("Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+ else
+ WARN(1, "Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+
+ per_cpu(hard_watchdog_warn, next_cpu) = true;
+ } else {
+ per_cpu(hard_watchdog_warn, next_cpu) = false;
+ }
+}
+#else
+static inline void watchdog_check_hardlockup_other_cpu(void) { return; }
+#endif
+
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp();
@@ -203,7 +278,7 @@
return 0;
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
@@ -251,7 +326,7 @@
__this_cpu_write(hard_watchdog_warn, false);
return;
}
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
static void watchdog_interrupt_count(void)
{
@@ -271,6 +346,9 @@
/* kick the hardlockup detector */
watchdog_interrupt_count();
+ /* test for hardlockups on the next cpu */
+ watchdog_check_hardlockup_other_cpu();
+
/* kick the softlockup detector */
wake_up_process(__this_cpu_read(softlockup_watchdog));
@@ -395,7 +473,7 @@
__touch_watchdog();
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/*
* People like the simple clean cpu node info on boot.
* Reduce the watchdog noise by only printing messages
@@ -471,9 +549,44 @@
return;
}
#else
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static int watchdog_nmi_enable(unsigned int cpu)
+{
+ /*
+ * The new cpu will be marked online before the first hrtimer interrupt
+ * runs on it. If another cpu tests for a hardlockup on the new cpu
+ * before it has run its first hrtimer, it will get a false positive.
+ * Touch the watchdog on the new cpu to delay the first check for at
+ * least 3 sampling periods to guarantee one hrtimer has run on the new
+ * cpu.
+ */
+ per_cpu(watchdog_nmi_touch, cpu) = true;
+ smp_wmb();
+ cpumask_set_cpu(cpu, &watchdog_cpus);
+ return 0;
+}
+
+static void watchdog_nmi_disable(unsigned int cpu)
+{
+ unsigned int next_cpu = watchdog_next_cpu(cpu);
+
+ /*
+ * Offlining this cpu will cause the cpu before this one to start
+ * checking the one after this one. If this cpu just finished checking
+ * the next cpu and updating hrtimer_interrupts_saved, and then the
+ * previous cpu checks it within one sample period, it will trigger a
+ * false positive. Touch the watchdog on the next cpu to prevent it.
+ */
+ if (next_cpu < nr_cpu_ids)
+ per_cpu(watchdog_nmi_touch, next_cpu) = true;
+ smp_wmb();
+ cpumask_clear_cpu(cpu, &watchdog_cpus);
+}
+#else
static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
/* prepare/enable/disable routines */
/* sysctl functions */
diff --git a/lib/Kconfig b/lib/Kconfig
index fe01d41..06d94d8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -189,6 +189,15 @@
config LZO_DECOMPRESS
tristate
+config LZ4_COMPRESS
+ tristate
+
+config LZ4HC_COMPRESS
+ tristate
+
+config LZ4_DECOMPRESS
+ tristate
+
source "lib/xz/Kconfig"
#
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 74fdc5c..d317c1a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -191,15 +191,27 @@
The overhead should be minimal. A periodic hrtimer runs to
generate interrupts and kick the watchdog task every 4 seconds.
An NMI is generated every 10 seconds or so to check for hardlockups.
+ If NMIs are not available on the platform, every 12 seconds the
+ hrtimer interrupt on one cpu will be used to check for hardlockups
+ on the next cpu.
The frequency of hrtimer and NMI events and the soft and hard lockup
thresholds can be controlled through the sysctl watchdog_thresh.
-config HARDLOCKUP_DETECTOR
+config HARDLOCKUP_DETECTOR_NMI
def_bool y
depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
+config HARDLOCKUP_DETECTOR_OTHER_CPU
+ def_bool y
+ depends on LOCKUP_DETECTOR && SMP
+ depends on !HARDLOCKUP_DETECTOR_NMI && !HAVE_NMI_WATCHDOG
+
+config HARDLOCKUP_DETECTOR
+ def_bool y
+ depends on HARDLOCKUP_DETECTOR_NMI || HARDLOCKUP_DETECTOR_OTHER_CPU
+
config BOOTPARAM_HARDLOCKUP_PANIC
bool "Panic (Reboot) On Hard Lockups"
depends on HARDLOCKUP_DETECTOR
@@ -669,8 +681,9 @@
mutexes and rwsems.
config STACKTRACE
- bool
+ bool "Stacktrace"
depends on STACKTRACE_SUPPORT
+ default y
config DEBUG_STACK_USAGE
bool "Stack utilization instrumentation"
diff --git a/lib/Makefile b/lib/Makefile
index 9efe480..b6d7848 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -76,6 +76,9 @@
obj-$(CONFIG_BCH) += bch.o
obj-$(CONFIG_LZO_COMPRESS) += lzo/
obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_LZ4_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
obj-$(CONFIG_XZ_DEC) += xz/
obj-$(CONFIG_RAID6_PQ) += raid6/
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 11b9b01..b1c8852 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -69,7 +69,7 @@
/* Extract a tag from the data */
tag = data[dp++];
- if (tag == 0) {
+ if (tag == ASN1_EOC) {
/* It appears to be an EOC. */
if (data[dp++] != 0)
goto invalid_eoc;
@@ -91,10 +91,8 @@
/* Extract the length */
len = data[dp++];
- if (len <= 0x7f) {
- dp += len;
- goto next_tag;
- }
+ if (len <= 0x7f)
+ goto check_length;
if (unlikely(len == ASN1_INDEFINITE_LENGTH)) {
/* Indefinite length */
@@ -105,14 +103,18 @@
}
n = len - 0x80;
- if (unlikely(n > sizeof(size_t) - 1))
+ if (unlikely(n > sizeof(len) - 1))
goto length_too_long;
if (unlikely(n > datalen - dp))
goto data_overrun_error;
- for (len = 0; n > 0; n--) {
+ len = 0;
+ for (; n > 0; n--) {
len <<= 8;
len |= data[dp++];
}
+check_length:
+ if (len > datalen - dp)
+ goto data_overrun_error;
dp += len;
goto next_tag;
@@ -208,9 +210,8 @@
unsigned char tmp;
/* Skip conditional matches if possible */
- if ((op & ASN1_OP_MATCH__COND &&
- flags & FLAG_MATCHED) ||
- dp == datalen) {
+ if ((op & ASN1_OP_MATCH__COND && flags & FLAG_MATCHED) ||
+ (op & ASN1_OP_MATCH__SKIP && dp == datalen)) {
pc += asn1_op_lengths[op];
goto next_op;
}
diff --git a/lib/div64.c b/lib/div64.c
index a163b6c..4382ad7 100644
--- a/lib/div64.c
+++ b/lib/div64.c
@@ -79,6 +79,46 @@
#endif
/**
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
+ * @dividend: 64bit dividend
+ * @divisor: 64bit divisor
+ * @remainder: 64bit remainder
+ *
+ * This implementation is a comparable to algorithm used by div64_u64.
+ * But this operation, which includes math for calculating the remainder,
+ * is kept distinct to avoid slowing down the div64_u64 operation on 32bit
+ * systems.
+ */
+#ifndef div64_u64_rem
+u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+ u32 high = divisor >> 32;
+ u64 quot;
+
+ if (high == 0) {
+ u32 rem32;
+ quot = div_u64_rem(dividend, divisor, &rem32);
+ *remainder = rem32;
+ } else {
+ int n = 1 + fls(high);
+ quot = div_u64(dividend >> n, divisor >> n);
+
+ if (quot != 0)
+ quot--;
+
+ *remainder = dividend - quot * divisor;
+ if (*remainder >= divisor) {
+ quot++;
+ *remainder -= divisor;
+ }
+ }
+
+ return quot;
+}
+EXPORT_SYMBOL(div64_u64_rem);
+#endif
+
+/**
* div64_u64 - unsigned 64bit divide with 64bit divisor
* @dividend: 64bit dividend
* @divisor: 64bit divisor
diff --git a/lib/lz4/Makefile b/lib/lz4/Makefile
new file mode 100644
index 0000000..8085d04
--- /dev/null
+++ b/lib/lz4/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_LZ4_COMPRESS) += lz4_compress.o
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4hc_compress.o
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4_decompress.o
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
new file mode 100644
index 0000000..28321d8
--- /dev/null
+++ b/lib/lz4/lz4_compress.c
@@ -0,0 +1,443 @@
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+/*
+ * LZ4_compressCtx :
+ * -----------------
+ * Compress 'isize' bytes from 'source' into an output buffer 'dest' of
+ * maximum size 'maxOutputSize'. * If it cannot achieve it, compression
+ * will stop, and result of the function will be zero.
+ * return : the number of bytes written in buffer 'dest', or 0 if the
+ * compression fails
+ */
+static inline int lz4_compressctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ HTYPE *hashtable = (HTYPE *)ctx;
+ const u8 *ip = (u8 *)source;
+#if LZ4_ARCH64
+ const BYTE * const base = ip;
+#else
+ const int base = 0;
+#endif
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (unlikely(forwardip > mflimit))
+ goto _last_literals;
+
+ forwardh = LZ4_HASH_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = ip - base;
+ } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source) &&
+ unlikely(ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS) +
+ (length >> 8) > oend))
+ return 0;
+
+ if (length >= (int)RUN_MASK) {
+ int len;
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+ while (likely(ip < MATCHLIMIT - (STEPSIZE - 1))) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+ /* Encode MatchLength */
+ length = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)ML_MASK) {
+ *token += ML_MASK;
+ length -= ML_MASK;
+ for (; length > 509 ; length -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (length > 254) {
+ length -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)length;
+ } else
+ *token += length;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH_VALUE(ip)];
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (((char *)op - dest) + lastrun + 1
+ + ((lastrun + 255 - RUN_MASK) / 255) > (u32)maxoutputsize)
+ return 0;
+
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+static inline int lz4_compress64kctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ u16 *hashtable = (u16 *)ctx;
+ const u8 *ip = (u8 *) source;
+ const u8 *anchor = ip;
+ const u8 *const base = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int len, length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (forwardip > mflimit)
+ goto _last_literals;
+
+ forwardh = LZ4_HASH64K_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = (u16)(ip - base);
+ } while (A32(ref) != A32(ip));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source)
+ && (ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* Check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS)
+ + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+
+ while (ip < MATCHLIMIT - (STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+
+ /* Encode MatchLength */
+ len = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (len >> 8) > oend))
+ return 0;
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH64K_VALUE(ip-2)] = (u16)(ip - 2 - base);
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH64K_VALUE(ip)];
+ hashtable[LZ4_HASH64K_VALUE(ip)] = (u16)(ip - base);
+ if (A32(ref) == A32(ip)) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (op + lastrun + 1 + (lastrun - RUN_MASK + 255) / 255 > oend)
+ return 0;
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ if (src_len < LZ4_64KLIMIT)
+ out_len = lz4_compress64kctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+ else
+ out_len = lz4_compressctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+
+ return 0;
+exit:
+ return ret;
+}
+EXPORT_SYMBOL(lz4_compress);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("LZ4 compressor");
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
new file mode 100644
index 0000000..6324d6d
--- /dev/null
+++ b/lib/lz4/lz4_decompress.c
@@ -0,0 +1,330 @@
+/*
+ * LZ4 Decompressor for Linux kernel
+ *
+ * Copyright (C) 2013 LG Electronics Co., Ltd. (http://www.lge.com/)
+ *
+ * Based on LZ4 implementation by Yann Collet.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ */
+
+#ifndef STATIC
+#include <linux/module.h>
+#include <linux/kernel.h>
+#endif
+#include <linux/lz4.h>
+
+#include <asm/unaligned.h>
+
+#include "lz4defs.h"
+
+static int lz4_uncompress(const char *source, char *dest, int osize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *ref;
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + osize;
+ BYTE *cpy;
+ unsigned token;
+ size_t length;
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ while (1) {
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ size_t len;
+
+ len = *ip++;
+ for (; len == 255; length += 255)
+ len = *ip++;
+ if (unlikely(length > (size_t)(length + len)))
+ goto _output_error;
+ length += len;
+ }
+
+ /* copy literals */
+ cpy = op + length;
+ if (unlikely(cpy > oend - COPYLENGTH)) {
+ /*
+ * Error: not enough place for another match
+ * (min 4) + 5 literals
+ */
+ if (cpy != oend)
+ goto _output_error;
+
+ memcpy(op, ip, length);
+ ip += length;
+ break; /* EOF */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+
+ /* Error: offset create reference outside destination buffer */
+ if (unlikely(ref < (BYTE *const) dest))
+ goto _output_error;
+
+ /* get matchlength */
+ length = token & ML_MASK;
+ if (length == ML_MASK) {
+ for (; *ip == 255; length += 255)
+ ip++;
+ if (unlikely(length > (size_t)(length + *ip)))
+ goto _output_error;
+ length += *ip++;
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op-ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE - 4);
+ if (cpy > (oend - COPYLENGTH)) {
+
+ /* Error: request to write beyond destination buffer */
+ if (cpy > oend)
+ goto _output_error;
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *)ip) - source);
+
+ /* write overflow error detected */
+_output_error:
+ return -1;
+}
+
+static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
+ int isize, size_t maxoutputsize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *const iend = ip + isize;
+ const BYTE *ref;
+
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + maxoutputsize;
+ BYTE *cpy;
+
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ /* Main Loop */
+ while (ip < iend) {
+
+ unsigned token;
+ size_t length;
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ int s = 255;
+ while ((ip < iend) && (s == 255)) {
+ s = *ip++;
+ length += s;
+ }
+ }
+ /* copy literals */
+ cpy = op + length;
+ if ((cpy > oend - COPYLENGTH) ||
+ (ip + length > iend - COPYLENGTH)) {
+
+ if (cpy > oend)
+ goto _output_error;/* writes beyond buffer */
+
+ if (ip + length != iend)
+ goto _output_error;/*
+ * Error: LZ4 format requires
+ * to consume all input
+ * at this stage
+ */
+ memcpy(op, ip, length);
+ op += length;
+ break;/* Necessarily EOF, due to parsing restrictions */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+ if (ref < (BYTE * const) dest)
+ goto _output_error;
+ /*
+ * Error : offset creates reference
+ * outside of destination buffer
+ */
+
+ /* get matchlength */
+ length = (token & ML_MASK);
+ if (length == ML_MASK) {
+ while (ip < iend) {
+ int s = *ip++;
+ length += s;
+ if (s == 255)
+ continue;
+ break;
+ }
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op - ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE-4);
+ if (cpy > oend - COPYLENGTH) {
+ if (cpy > oend)
+ goto _output_error; /* write outside of buf */
+
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *) op) - dest);
+
+ /* write overflow error detected */
+_output_error:
+ return (int) (-(((char *) ip) - source));
+}
+
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len)
+{
+ int ret = -1;
+ int input_len = 0;
+
+ input_len = lz4_uncompress(src, dest, actual_dest_len);
+ if (input_len < 0)
+ goto exit_0;
+ *src_len = input_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL(lz4_decompress);
+#endif
+
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len,
+ *dest_len);
+ if (out_len < 0)
+ goto exit_0;
+ *dest_len = out_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL(lz4_decompress_unknownoutputsize);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("LZ4 Decompressor");
+#endif
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
new file mode 100644
index 0000000..abcecdc
--- /dev/null
+++ b/lib/lz4/lz4defs.h
@@ -0,0 +1,156 @@
+/*
+ * lz4defs.h -- architecture specific defines
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Detects 64 bits mode
+ */
+#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \
+ || defined(__ppc64__) || defined(__LP64__))
+#define LZ4_ARCH64 1
+#else
+#define LZ4_ARCH64 0
+#endif
+
+/*
+ * Architecture-specific macros
+ */
+#define BYTE u8
+typedef struct _U16_S { u16 v; } U16_S;
+typedef struct _U32_S { u32 v; } U32_S;
+typedef struct _U64_S { u64 v; } U64_S;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \
+ || defined(CONFIG_ARM) && __LINUX_ARM_ARCH__ >= 6 \
+ && defined(ARM_EFFICIENT_UNALIGNED_ACCESS)
+
+#define A16(x) (((U16_S *)(x))->v)
+#define A32(x) (((U32_S *)(x))->v)
+#define A64(x) (((U64_S *)(x))->v)
+
+#define PUT4(s, d) (A32(d) = A32(s))
+#define PUT8(s, d) (A64(d) = A64(s))
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ A16(p) = v; \
+ p += 2; \
+ } while (0)
+#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
+
+#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v))
+#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v))
+#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v))
+
+#define PUT4(s, d) \
+ put_unaligned(get_unaligned((const u32 *) s), (u32 *) d)
+#define PUT8(s, d) \
+ put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
+
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ put_unaligned(v, (u16 *)(p)); \
+ p += 2; \
+ } while (0)
+#endif
+
+#define COPYLENGTH 8
+#define ML_BITS 4
+#define ML_MASK ((1U << ML_BITS) - 1)
+#define RUN_BITS (8 - ML_BITS)
+#define RUN_MASK ((1U << RUN_BITS) - 1)
+#define MEMORY_USAGE 14
+#define MINMATCH 4
+#define SKIPSTRENGTH 6
+#define LASTLITERALS 5
+#define MFLIMIT (COPYLENGTH + MINMATCH)
+#define MINLENGTH (MFLIMIT + 1)
+#define MAXD_LOG 16
+#define MAXD (1 << MAXD_LOG)
+#define MAXD_MASK (u32)(MAXD - 1)
+#define MAX_DISTANCE (MAXD - 1)
+#define HASH_LOG (MAXD_LOG - 1)
+#define HASHTABLESIZE (1 << HASH_LOG)
+#define MAX_NB_ATTEMPTS 256
+#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
+#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT - 1))
+#define HASHLOG64K ((MEMORY_USAGE - 2) + 1)
+#define HASH64KTABLESIZE (1U << HASHLOG64K)
+#define LZ4_HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - (MEMORY_USAGE-2)))
+#define LZ4_HASH64K_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASHLOG64K))
+#define HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASH_LOG))
+
+#if LZ4_ARCH64/* 64-bit */
+#define STEPSIZE 8
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT8(s, d); \
+ d += 8; \
+ s += 8; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) LZ4_COPYSTEP(s, d)
+
+#define LZ4_SECURECOPY(s, d, e) \
+ do { \
+ if (d < e) { \
+ LZ4_WILDCOPY(s, d, e); \
+ } \
+ } while (0)
+#define HTYPE u32
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3)
+#endif
+
+#else /* 32-bit */
+#define STEPSIZE 4
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT4(s, d); \
+ d += 4; \
+ s += 4; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) \
+ do { \
+ LZ4_COPYSTEP(s, d); \
+ LZ4_COPYSTEP(s, d); \
+ } while (0)
+
+#define LZ4_SECURECOPY LZ4_WILDCOPY
+#define HTYPE const u8*
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3)
+#endif
+
+#endif
+
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
+ (d = s - get_unaligned_le16(p))
+
+#define LZ4_WILDCOPY(s, d, e) \
+ do { \
+ LZ4_COPYPACKET(s, d); \
+ } while (d < e)
+
+#define LZ4_BLINDCOPY(s, d, l) \
+ do { \
+ u8 *e = (d) + l; \
+ LZ4_WILDCOPY(s, d, e); \
+ d = e; \
+ } while (0)
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
new file mode 100644
index 0000000..f344f76
--- /dev/null
+++ b/lib/lz4/lz4hc_compress.c
@@ -0,0 +1,539 @@
+/*
+ * LZ4 HC - High Compression Mode of LZ4
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+struct lz4hc_data {
+ const u8 *base;
+ HTYPE hashtable[HASHTABLESIZE];
+ u16 chaintable[MAXD];
+ const u8 *nexttoupdate;
+} __attribute__((__packed__));
+
+static inline int lz4hc_init(struct lz4hc_data *hc4, const u8 *base)
+{
+ memset((void *)hc4->hashtable, 0, sizeof(hc4->hashtable));
+ memset(hc4->chaintable, 0xFF, sizeof(hc4->chaintable));
+
+#if LZ4_ARCH64
+ hc4->nexttoupdate = base + 1;
+#else
+ hc4->nexttoupdate = base;
+#endif
+ hc4->base = base;
+ return 1;
+}
+
+/* Update chains up to ip (excluded) */
+static inline void lz4hc_insert(struct lz4hc_data *hc4, const u8 *ip)
+{
+ u16 *chaintable = hc4->chaintable;
+ HTYPE *hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+
+ while (hc4->nexttoupdate < ip) {
+ const u8 *p = hc4->nexttoupdate;
+ size_t delta = p - (hashtable[HASH_VALUE(p)] + base);
+ if (delta > MAX_DISTANCE)
+ delta = MAX_DISTANCE;
+ chaintable[(size_t)(p) & MAXD_MASK] = (u16)delta;
+ hashtable[HASH_VALUE(p)] = (p) - base;
+ hc4->nexttoupdate++;
+ }
+}
+
+static inline size_t lz4hc_commonlength(const u8 *p1, const u8 *p2,
+ const u8 *const matchlimit)
+{
+ const u8 *p1t = p1;
+
+ while (p1t < matchlimit - (STEPSIZE - 1)) {
+#if LZ4_ARCH64
+ u64 diff = A64(p2) ^ A64(p1t);
+#else
+ u32 diff = A32(p2) ^ A32(p1t);
+#endif
+ if (!diff) {
+ p1t += STEPSIZE;
+ p2 += STEPSIZE;
+ continue;
+ }
+ p1t += LZ4_NBCOMMONBYTES(diff);
+ return p1t - p1;
+ }
+#if LZ4_ARCH64
+ if ((p1t < (matchlimit-3)) && (A32(p2) == A32(p1t))) {
+ p1t += 4;
+ p2 += 4;
+ }
+#endif
+
+ if ((p1t < (matchlimit - 1)) && (A16(p2) == A16(p1t))) {
+ p1t += 2;
+ p2 += 2;
+ }
+ if ((p1t < matchlimit) && (*p2 == *p1t))
+ p1t++;
+ return p1t - p1;
+}
+
+static inline int lz4hc_insertandfindbestmatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *const matchlimit, const u8 **matchpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+ const u8 *ref;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ int nbattempts = MAX_NB_ATTEMPTS;
+ size_t repl = 0, ml = 0;
+ u16 delta;
+
+ /* HC4 match finder */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ /* potential repetition */
+ if (ref >= ip-4) {
+ /* confirmed */
+ if (A32(ref) == A32(ip)) {
+ delta = (u16)(ip-ref);
+ repl = ml = lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ *matchpos = ref;
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ while ((ref >= ip - MAX_DISTANCE) && nbattempts) {
+ nbattempts--;
+ if (*(ref + ml) == *(ip + ml)) {
+ if (A32(ref) == A32(ip)) {
+ size_t mlt =
+ lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ if (mlt > ml) {
+ ml = mlt;
+ *matchpos = ref;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ /* Complete table */
+ if (repl) {
+ const BYTE *ptr = ip;
+ const BYTE *end;
+ end = ip + repl - (MINMATCH-1);
+ /* Pre-Load */
+ while (ptr < end - delta) {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ ptr++;
+ }
+ do {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ /* Head of chain */
+ hashtable[HASH_VALUE(ptr)] = (ptr) - base;
+ ptr++;
+ } while (ptr < end);
+ hc4->nexttoupdate = end;
+ }
+
+ return (int)ml;
+}
+
+static inline int lz4hc_insertandgetwidermatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *startlimit, const u8 *matchlimit, int longest,
+ const u8 **matchpos, const u8 **startpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ const u8 *ref;
+ int nbattempts = MAX_NB_ATTEMPTS;
+ int delta = (int)(ip - startlimit);
+
+ /* First Match */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ while ((ref >= ip - MAX_DISTANCE) && (ref >= hc4->base)
+ && (nbattempts)) {
+ nbattempts--;
+ if (*(startlimit + longest) == *(ref - delta + longest)) {
+ if (A32(ref) == A32(ip)) {
+ const u8 *reft = ref + MINMATCH;
+ const u8 *ipt = ip + MINMATCH;
+ const u8 *startt = ip;
+
+ while (ipt < matchlimit-(STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(reft) ^ A64(ipt);
+ #else
+ u32 diff = A32(reft) ^ A32(ipt);
+ #endif
+
+ if (!diff) {
+ ipt += STEPSIZE;
+ reft += STEPSIZE;
+ continue;
+ }
+ ipt += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ipt < (matchlimit - 3))
+ && (A32(reft) == A32(ipt))) {
+ ipt += 4;
+ reft += 4;
+ }
+ ipt += 2;
+ #endif
+ if ((ipt < (matchlimit - 1))
+ && (A16(reft) == A16(ipt))) {
+ reft += 2;
+ }
+ if ((ipt < matchlimit) && (*reft == *ipt))
+ ipt++;
+_endcount:
+ reft = ref;
+
+ while ((startt > startlimit)
+ && (reft > hc4->base)
+ && (startt[-1] == reft[-1])) {
+ startt--;
+ reft--;
+ }
+
+ if ((ipt - startt) > longest) {
+ longest = (int)(ipt - startt);
+ *matchpos = reft;
+ *startpos = startt;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+ return longest;
+}
+
+static inline int lz4_encodesequence(const u8 **ip, u8 **op, const u8 **anchor,
+ int ml, const u8 *ref)
+{
+ int length, len;
+ u8 *token;
+
+ /* Encode Literal length */
+ length = (int)(*ip - *anchor);
+ token = (*op)++;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *(*op)++ = 255;
+ *(*op)++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(*anchor, *op, length);
+
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(*op, (u16)(*ip - ref));
+
+ /* Encode MatchLength */
+ len = (int)(ml - MINMATCH);
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *(*op)++ = 255;
+ *(*op)++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *(*op)++ = 255;
+ }
+ *(*op)++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Prepare next loop */
+ *ip += ml;
+ *anchor = *ip;
+
+ return 0;
+}
+
+static int lz4_compresshcctx(struct lz4hc_data *ctx,
+ const char *source,
+ char *dest,
+ int isize)
+{
+ const u8 *ip = (const u8 *)source;
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ const u8 *const matchlimit = (iend - LASTLITERALS);
+
+ u8 *op = (u8 *)dest;
+
+ int ml, ml2, ml3, ml0;
+ const u8 *ref = NULL;
+ const u8 *start2 = NULL;
+ const u8 *ref2 = NULL;
+ const u8 *start3 = NULL;
+ const u8 *ref3 = NULL;
+ const u8 *start0;
+ const u8 *ref0;
+ int lastrun;
+
+ ip++;
+
+ /* Main Loop */
+ while (ip < mflimit) {
+ ml = lz4hc_insertandfindbestmatch(ctx, ip, matchlimit, (&ref));
+ if (!ml) {
+ ip++;
+ continue;
+ }
+
+ /* saved, in case we would skip too much */
+ start0 = ip;
+ ref0 = ref;
+ ml0 = ml;
+_search2:
+ if (ip+ml < mflimit)
+ ml2 = lz4hc_insertandgetwidermatch(ctx, ip + ml - 2,
+ ip + 1, matchlimit, ml, &ref2, &start2);
+ else
+ ml2 = ml;
+ /* No better match */
+ if (ml2 == ml) {
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ continue;
+ }
+
+ if (start0 < ip) {
+ /* empirical */
+ if (start2 < ip + ml0) {
+ ip = start0;
+ ref = ref0;
+ ml = ml0;
+ }
+ }
+ /*
+ * Here, start0==ip
+ * First Match too small : removed
+ */
+ if ((start2 - ip) < 3) {
+ ml = ml2;
+ ip = start2;
+ ref = ref2;
+ goto _search2;
+ }
+
+_search3:
+ /*
+ * Currently we have :
+ * ml2 > ml1, and
+ * ip1+3 <= ip2 (usually < ip1+ml1)
+ */
+ if ((start2 - ip) < OPTIMAL_ML) {
+ int correction;
+ int new_ml = ml;
+ if (new_ml > OPTIMAL_ML)
+ new_ml = OPTIMAL_ML;
+ if (ip + new_ml > start2 + ml2 - MINMATCH)
+ new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
+ correction = new_ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ }
+ /*
+ * Now, we have start2 = ip+new_ml,
+ * with new_ml=min(ml, OPTIMAL_ML=18)
+ */
+ if (start2 + ml2 < mflimit)
+ ml3 = lz4hc_insertandgetwidermatch(ctx,
+ start2 + ml2 - 3, start2, matchlimit,
+ ml2, &ref3, &start3);
+ else
+ ml3 = ml2;
+
+ /* No better match : 2 sequences to encode */
+ if (ml3 == ml2) {
+ /* ip & ref are known; Now for ml */
+ if (start2 < ip+ml)
+ ml = (int)(start2 - ip);
+
+ /* Now, encode 2 sequences */
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start2;
+ lz4_encodesequence(&ip, &op, &anchor, ml2, ref2);
+ continue;
+ }
+
+ /* Not enough space for match 2 : remove it */
+ if (start3 < ip + ml + 3) {
+ /*
+ * can write Seq1 immediately ==> Seq2 is removed,
+ * so Seq3 becomes Seq1
+ */
+ if (start3 >= (ip + ml)) {
+ if (start2 < ip + ml) {
+ int correction =
+ (int)(ip + ml - start2);
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ if (ml2 < MINMATCH) {
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ }
+ }
+
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start3;
+ ref = ref3;
+ ml = ml3;
+
+ start0 = start2;
+ ref0 = ref2;
+ ml0 = ml2;
+ goto _search2;
+ }
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ goto _search3;
+ }
+
+ /*
+ * OK, now we have 3 ascending matches; let's write at least
+ * the first one ip & ref are known; Now for ml
+ */
+ if (start2 < ip + ml) {
+ if ((start2 - ip) < (int)ML_MASK) {
+ int correction;
+ if (ml > OPTIMAL_ML)
+ ml = OPTIMAL_ML;
+ if (ip + ml > start2 + ml2 - MINMATCH)
+ ml = (int)(start2 - ip) + ml2
+ - MINMATCH;
+ correction = ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ } else
+ ml = (int)(start2 - ip);
+ }
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+
+ ip = start2;
+ ref = ref2;
+ ml = ml2;
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+
+ goto _search3;
+ }
+
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8) lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int) (((char *)op) - dest);
+}
+
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ struct lz4hc_data *hc4 = (struct lz4hc_data *)wrkmem;
+ lz4hc_init(hc4, (const u8 *)src);
+ out_len = lz4_compresshcctx((struct lz4hc_data *)hc4, (const u8 *)src,
+ (char *)dst, (int)src_len);
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+ return 0;
+
+exit:
+ return ret;
+}
+EXPORT_SYMBOL(lz4hc_compress);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("LZ4HC compressor");
diff --git a/lib/rbtree.c b/lib/rbtree.c
index c0e31fe..65f4eff 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -518,3 +518,43 @@
*new = *victim;
}
EXPORT_SYMBOL(rb_replace_node);
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+ for (;;) {
+ if (node->rb_left)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+ else
+ return (struct rb_node *)node;
+ }
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+ const struct rb_node *parent;
+ if (!node)
+ return NULL;
+ parent = rb_parent(node);
+
+ /* If we're sitting on node, we've already seen our children */
+ if (parent && node == parent->rb_left && parent->rb_right) {
+ /* If we are the parent's left node, go to the parent's right
+ * node then all the way down to the left */
+ return rb_left_deepest_node(parent->rb_right);
+ } else
+ /* Otherwise we are the parent's right node, and the parent
+ * should be next */
+ return (struct rb_node *)parent;
+}
+EXPORT_SYMBOL(rb_next_postorder);
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+ if (!root->rb_node)
+ return NULL;
+
+ return rb_left_deepest_node(root->rb_node);
+}
+EXPORT_SYMBOL(rb_first_postorder);
diff --git a/lib/string.c b/lib/string.c
index cb9ea21..fbe0d96 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -840,3 +840,20 @@
return check_bytes8(start, value, bytes % 8);
}
EXPORT_SYMBOL(memchr_inv);
+
+/**
+ * strreplace - Replace all occurrences of character in string.
+ * @s: The string to operate on.
+ * @old: The character being replaced.
+ * @new: The character @old is replaced with.
+ *
+ * Returns pointer to the nul byte at the end of @s.
+ */
+char *strreplace(char *s, char old, char new)
+{
+ for (; *s; ++s)
+ if (*s == old)
+ *s = new;
+ return s;
+}
+EXPORT_SYMBOL(strreplace);
diff --git a/mm/Kconfig b/mm/Kconfig
index e742d06..72ea99c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -477,3 +477,45 @@
and swap data is stored as normal on the matching swap device.
If unsure, say Y to enable frontswap.
+
+config ZPOOL
+ tristate "Common API for compressed memory storage"
+ default n
+ help
+ Compressed memory storage API. This allows using either zbud or
+ zsmalloc.
+
+config ZSMALLOC
+ bool "Memory allocator for compressed pages"
+ depends on MMU
+ default n
+ help
+ zsmalloc is a slab-based memory allocator designed to store
+ compressed RAM pages. zsmalloc uses virtual memory mapping
+ in order to reduce fragmentation. However, this results in a
+ non-standard allocator interface where a handle, not a pointer, is
+ returned by an alloc(). This handle must be mapped in order to
+ access the allocated space.
+
+config PGTABLE_MAPPING
+ bool "Use page table mapping to access object in zsmalloc"
+ depends on ZSMALLOC
+ help
+ By default, zsmalloc uses a copy-based object mapping method to
+ access allocations that span two pages. However, if a particular
+ architecture (ex, ARM) performs VM mapping faster than copying,
+ then you should select this. This causes zsmalloc to use page table
+ mapping rather than copying for object mapping.
+
+ You can check speed with zsmalloc benchmark:
+ https://github.com/spartacus06/zsmapbench
+
+config ZSMALLOC_STAT
+ bool "Export zsmalloc statistics"
+ depends on ZSMALLOC
+ select DEBUG_FS
+ help
+ This option enables code in the zsmalloc to collect various
+ statistics about whats happening in zsmalloc and exports that
+ information to userspace via debugfs.
+ If unsure, say N.
diff --git a/mm/Makefile b/mm/Makefile
index 72c5acb..fa2e7df 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -58,3 +58,5 @@
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
obj-$(CONFIG_CLEANCACHE) += cleancache.o
obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
+obj-$(CONFIG_ZPOOL) += zpool.o
+obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/mm/filemap.c b/mm/filemap.c
index 725a100..d299dcf 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -684,6 +684,47 @@
}
/**
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ struct page *page;
+
+ page = radix_tree_lookup(&mapping->page_tree, index);
+ if (!page || radix_tree_exceptional_entry(page))
+ break;
+ index++;
+ if (index == 0)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
* find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
@@ -691,7 +732,8 @@
* Is there a pagecache struct page at the given (mapping, offset) tuple?
* If yes, increment its refcount and return it; if no, return NULL.
*/
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset,
+ int fgp_flags)
{
void **pagep;
struct page *page;
@@ -728,6 +770,8 @@
}
}
out:
+ if (page && (fgp_flags & FGP_ACCESSED))
+ mark_page_accessed(page);
rcu_read_unlock();
return page;
@@ -1109,6 +1153,8 @@
unsigned int prev_offset;
int error;
+ trace_mm_filemap_do_generic_file_read(filp, *ppos, desc->count, 1);
+
index = *ppos >> PAGE_CACHE_SHIFT;
prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
@@ -1503,7 +1549,7 @@
static int page_cache_read(struct file *file, pgoff_t offset)
{
struct address_space *mapping = file->f_mapping;
- struct page *page;
+ struct page *page;
int ret;
do {
@@ -1520,7 +1566,7 @@
page_cache_release(page);
} while (ret == AOP_TRUNCATED_PAGE);
-
+
return ret;
}
@@ -2307,6 +2353,8 @@
ssize_t written = 0;
unsigned int flags = 0;
+ trace_mm_filemap_generic_perform_write(file, pos, iov_iter_count(i), 0);
+
/*
* Copies from kernel address space cannot fail (NFSD is a big user).
*/
@@ -2406,7 +2454,7 @@
written += status;
*ppos = pos + status;
}
-
+
return written ? written : status;
}
EXPORT_SYMBOL(generic_file_buffered_write);
diff --git a/mm/madvise.c b/mm/madvise.c
index 7055883..85d1a54 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -102,7 +102,8 @@
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
- vma->vm_file, pgoff, vma_policy(vma));
+ vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 437ae2c..460218d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6796,6 +6796,12 @@
return ret;
}
+static int mem_cgroup_allow_attach(struct cgroup *cgroup,
+ struct cgroup_taskset *tset)
+{
+ return subsys_cgroup_allow_attach(cgroup, tset);
+}
+
static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
struct cgroup_taskset *tset)
{
@@ -6964,6 +6970,11 @@
{
return 0;
}
+static int mem_cgroup_allow_attach(struct cgroup *cgroup,
+ struct cgroup_taskset *tset)
+{
+ return 0;
+}
static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
struct cgroup_taskset *tset)
{
@@ -6999,6 +7010,7 @@
.can_attach = mem_cgroup_can_attach,
.cancel_attach = mem_cgroup_cancel_attach,
.attach = mem_cgroup_move_task,
+ .allow_attach = mem_cgroup_allow_attach,
.bind = mem_cgroup_bind,
.base_cftypes = mem_cgroup_files,
.early_init = 0,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b2061bb..420e4b9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -725,7 +725,7 @@
((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff,
- new_pol);
+ new_pol, vma_get_anon_name(vma));
if (prev) {
vma = prev;
next = vma->vm_next;
diff --git a/mm/mlock.c b/mm/mlock.c
index 713e462..b680dfd 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -23,10 +23,10 @@
int can_do_mlock(void)
{
- if (capable(CAP_IPC_LOCK))
- return 1;
if (rlimit(RLIMIT_MEMLOCK) != 0)
return 1;
+ if (capable(CAP_IPC_LOCK))
+ return 1;
return 0;
}
EXPORT_SYMBOL(can_do_mlock);
@@ -289,7 +289,8 @@
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
- vma->vm_file, pgoff, vma_policy(vma));
+ vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mmap.c b/mm/mmap.c
index 70ff9b4..3252660 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -52,6 +52,18 @@
#define arch_rebalance_pgtables(addr, len) (addr)
#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
+const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
+int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
+const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
+int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
+#endif
+
+
static void unmap_region(struct mm_struct *mm,
struct vm_area_struct *vma, struct vm_area_struct *prev,
unsigned long start, unsigned long end);
@@ -893,7 +905,8 @@
* per-vma resources, so we don't attempt to merge those.
*/
static inline int is_mergeable_vma(struct vm_area_struct *vma,
- struct file *file, unsigned long vm_flags)
+ struct file *file, unsigned long vm_flags,
+ const char __user *anon_name)
{
if (vma->vm_flags ^ vm_flags)
return 0;
@@ -901,6 +914,8 @@
return 0;
if (vma->vm_ops && vma->vm_ops->close)
return 0;
+ if (vma_get_anon_name(vma) != anon_name)
+ return 0;
return 1;
}
@@ -931,9 +946,10 @@
*/
static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
- struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags) &&
+ if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
if (vma->vm_pgoff == vm_pgoff)
return 1;
@@ -950,9 +966,10 @@
*/
static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
- struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags) &&
+ if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
pgoff_t vm_pglen;
vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
@@ -963,9 +980,9 @@
}
/*
- * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
- * whether that can be merged with its predecessor or its successor.
- * Or both (it neatly fills a hole).
+ * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
+ * figure out whether that can be merged with its predecessor or its
+ * successor. Or both (it neatly fills a hole).
*
* In most cases - when called for mmap, brk or mremap - [addr,end) is
* certain not to be mapped by the time vma_merge is called; but when
@@ -995,7 +1012,8 @@
struct vm_area_struct *prev, unsigned long addr,
unsigned long end, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
- pgoff_t pgoff, struct mempolicy *policy)
+ pgoff_t pgoff, struct mempolicy *policy,
+ const char __user *anon_name)
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
@@ -1021,15 +1039,15 @@
*/
if (prev && prev->vm_end == addr &&
mpol_equal(vma_policy(prev), policy) &&
- can_vma_merge_after(prev, vm_flags,
- anon_vma, file, pgoff)) {
+ can_vma_merge_after(prev, vm_flags, anon_vma,
+ file, pgoff, anon_name)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
- can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen) &&
+ can_vma_merge_before(next, vm_flags, anon_vma,
+ file, pgoff+pglen, anon_name) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma, NULL)) {
/* cases 1, 6 */
@@ -1049,8 +1067,8 @@
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
- can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen)) {
+ can_vma_merge_before(next, vm_flags, anon_vma,
+ file, pgoff+pglen, anon_name)) {
if (prev && addr < prev->vm_end) /* case 4 */
err = vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL);
@@ -1519,7 +1537,8 @@
/*
* Can we just expand an old mapping?
*/
- vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
+ NULL, NULL);
if (vma)
goto out;
@@ -2666,7 +2685,7 @@
/* Can we just expand an old private anonymous mapping? */
vma = vma_merge(mm, prev, addr, addr + len, flags,
- NULL, NULL, pgoff, NULL);
+ NULL, NULL, pgoff, NULL, NULL);
if (vma)
goto out;
@@ -2824,7 +2843,8 @@
if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
return NULL; /* should never get here */
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
- vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (new_vma) {
/*
* Source vma may have been merged into new_vma
diff --git a/mm/mprotect.c b/mm/mprotect.c
index e9f65aa..3c44c97 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -278,7 +278,8 @@
*/
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
- vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
goto success;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b034f79..2e8a975 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2249,7 +2249,7 @@
return ret;
}
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
{
struct address_space *mapping = page_mapping(page);
int ret;
@@ -2271,9 +2271,10 @@
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
- radix_tree_tag_clear(&mapping->page_tree,
- page_index(page),
- PAGECACHE_TAG_TOWRITE);
+ if (!keep_write)
+ radix_tree_tag_clear(&mapping->page_tree,
+ page_index(page),
+ PAGECACHE_TAG_TOWRITE);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);
@@ -2283,7 +2284,7 @@
return ret;
}
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
/*
* Return true if any of the pages in the mapping are marked with the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 494a081..5d2f0fc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -196,7 +196,20 @@
"Movable",
};
+/*
+ * Try to keep at least this much lowmem free. Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
int min_free_kbytes = 1024;
+int min_free_order_shift = 1;
+
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
@@ -395,7 +408,8 @@
return bad;
}
-static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+static inline void prep_zero_page(struct page *page, unsigned int order,
+ gfp_t gfp_flags)
{
int i;
@@ -439,7 +453,7 @@
static inline void clear_page_guard_flag(struct page *page) { }
#endif
-static inline void set_page_order(struct page *page, int order)
+static inline void set_page_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
@@ -488,7 +502,7 @@
* For recording page's order, we use page_private(page).
*/
static inline int page_is_buddy(struct page *page, struct page *buddy,
- int order)
+ unsigned int order)
{
if (!pfn_valid_within(page_to_pfn(buddy)))
return 0;
@@ -686,7 +700,9 @@
spin_unlock(&zone->lock);
}
-static void free_one_page(struct zone *zone, struct page *page, int order,
+static void free_one_page(struct zone *zone,
+ struct page *page,
+ unsigned int order,
int migratetype)
{
spin_lock(&zone->lock);
@@ -856,7 +872,7 @@
return 0;
}
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags)
{
int i;
@@ -905,6 +921,7 @@
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
+ set_freepage_migratetype(page, migratetype);
return page;
}
@@ -1012,20 +1029,63 @@
}
}
+/*
+ * When we are falling back to another migratetype during allocation, try to
+ * steal extra free pages from the same pageblocks to satisfy further
+ * allocations, instead of polluting multiple pageblocks.
+ *
+ * If we are stealing a relatively large buddy page, it is likely there will
+ * be more free pages in the pageblock, so try to steal them all. For
+ * reclaimable and unmovable allocations, we steal regardless of page size,
+ * as fragmentation caused by those allocations polluting movable pageblocks
+ * is worse than movable allocations stealing from unmovable and reclaimable
+ * pageblocks.
+ *
+ * If we claim more than half of the pageblock, change pageblock's migratetype
+ * as well.
+ */
+static void try_to_steal_freepages(struct zone *zone, struct page *page,
+ int start_type, int fallback_type)
+{
+ int current_order = page_order(page);
+
+ /* Take ownership for orders >= pageblock_order */
+ if (current_order >= pageblock_order) {
+ change_pageblock_range(page, current_order, start_type);
+ return;
+ }
+
+ if (current_order >= pageblock_order / 2 ||
+ start_type == MIGRATE_RECLAIMABLE ||
+ start_type == MIGRATE_UNMOVABLE ||
+ page_group_by_mobility_disabled) {
+ int pages;
+
+ pages = move_freepages_block(zone, page, start_type);
+
+ /* Claim the whole block if over half of it is free */
+ if (pages >= (1 << (pageblock_order-1)) ||
+ page_group_by_mobility_disabled)
+ set_pageblock_migratetype(page, start_type);
+ }
+}
+
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
+__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
{
struct free_area * area;
- int current_order;
+ unsigned int current_order;
struct page *page;
- int migratetype, i;
/* Find the largest possible block of pages in the other list */
- for (current_order = MAX_ORDER-1; current_order >= order;
- --current_order) {
+ for (current_order = MAX_ORDER-1;
+ current_order >= order && current_order <= MAX_ORDER-1;
+ --current_order) {
+ int i;
for (i = 0;; i++) {
- migratetype = fallbacks[start_migratetype][i];
+ int migratetype = fallbacks[start_migratetype][i];
+ int buddy_type = start_migratetype;
/* MIGRATE_RESERVE handled later if necessary */
if (migratetype == MIGRATE_RESERVE)
@@ -1039,48 +1099,36 @@
struct page, lru);
area->nr_free--;
- /*
- * If breaking a large block of pages, move all free
- * pages to the preferred allocation list. If falling
- * back for a reclaimable kernel allocation, be more
- * aggressive about taking ownership of free pages
- *
- * On the other hand, never change migration
- * type of MIGRATE_CMA pageblocks nor move CMA
- * pages on different free lists. We don't
- * want unmovable pages to be allocated from
- * MIGRATE_CMA areas.
- */
- if (!is_migrate_cma(migratetype) &&
- (unlikely(current_order >= pageblock_order / 2) ||
- start_migratetype == MIGRATE_RECLAIMABLE ||
- page_group_by_mobility_disabled)) {
- int pages;
- pages = move_freepages_block(zone, page,
- start_migratetype);
-
- /* Claim the whole block if over half of it is free */
- if (pages >= (1 << (pageblock_order-1)) ||
- page_group_by_mobility_disabled)
- set_pageblock_migratetype(page,
- start_migratetype);
-
- migratetype = start_migratetype;
+ if (!is_migrate_cma(migratetype)) {
+ try_to_steal_freepages(zone, page,
+ start_migratetype,
+ migratetype);
+ } else {
+ /*
+ * When borrowing from MIGRATE_CMA, we need to
+ * release the excess buddy pages to CMA
+ * itself, and we do not try to steal extra
+ * free pages.
+ */
+ buddy_type = migratetype;
}
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
- /* Take ownership for orders >= pageblock_order */
- if (current_order >= pageblock_order &&
- !is_migrate_cma(migratetype))
- change_pageblock_range(page, current_order,
- start_migratetype);
-
expand(zone, page, order, current_order, area,
- is_migrate_cma(migratetype)
- ? migratetype : start_migratetype);
+ buddy_type);
+
+ /*
+ * The freepage_migratetype may differ from pageblock's
+ * migratetype depending on the decisions in
+ * try_to_steal_freepages(). This is OK as long as it
+ * does not differ for MIGRATE_CMA pageblocks. For CMA
+ * we need to make sure unallocated pages flushed from
+ * pcp lists are returned to the correct freelist.
+ */
+ set_freepage_migratetype(page, buddy_type);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, migratetype);
@@ -1131,7 +1179,7 @@
unsigned long count, struct list_head *list,
int migratetype, int cold)
{
- int mt = migratetype, i;
+ int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
@@ -1152,14 +1200,8 @@
list_add(&page->lru, list);
else
list_add_tail(&page->lru, list);
- if (IS_ENABLED(CONFIG_CMA)) {
- mt = get_pageblock_migratetype(page);
- if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
- mt = migratetype;
- }
- set_freepage_migratetype(page, mt);
list = &page->lru;
- if (is_migrate_cma(mt))
+ if (is_migrate_cma(get_freepage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
@@ -1281,7 +1323,7 @@
{
unsigned long pfn, max_zone_pfn;
unsigned long flags;
- int order, t;
+ unsigned int order, t;
struct list_head *curr;
if (!zone->spanned_pages)
@@ -1475,8 +1517,8 @@
*/
static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
- struct zone *zone, int order, gfp_t gfp_flags,
- int migratetype)
+ struct zone *zone, unsigned int order,
+ gfp_t gfp_flags, int migratetype)
{
unsigned long flags;
struct page *page;
@@ -1525,7 +1567,7 @@
if (!page)
goto failed;
__mod_zone_freepage_state(zone, -(1 << order),
- get_pageblock_migratetype(page));
+ get_freepage_migratetype(page));
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
@@ -1623,8 +1665,9 @@
* Return true if free pages are above 'mark'. This takes into account the order
* of the allocation.
*/
-static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags, long free_pages)
+static bool __zone_watermark_ok(struct zone *z, unsigned int order,
+ unsigned long mark, int classzone_idx, int alloc_flags,
+ long free_pages)
{
/* free_pages my go negative - that's OK */
long min = mark;
@@ -1650,7 +1693,7 @@
free_pages -= z->free_area[o].nr_free << o;
/* Require fewer higher order pages to be free */
- min >>= 1;
+ min >>= min_free_order_shift;
if (free_pages <= min)
return false;
@@ -1658,15 +1701,15 @@
return true;
}
-bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, int alloc_flags)
{
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
-bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags)
+bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
+ unsigned long mark, int classzone_idx, int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
@@ -3980,7 +4023,7 @@
static void __meminit zone_init_free_lists(struct zone *zone)
{
- int order, t;
+ unsigned int order, t;
for_each_migratetype_order(order, t) {
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
zone->free_area[order].nr_free = 0;
@@ -5330,6 +5373,7 @@
static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
@@ -5341,11 +5385,14 @@
}
for_each_zone(zone) {
- u64 tmp;
+ u64 min, low;
spin_lock_irqsave(&zone->lock, flags);
- tmp = (u64)pages_min * zone->managed_pages;
- do_div(tmp, lowmem_pages);
+ min = (u64)pages_min * zone->managed_pages;
+ do_div(min, lowmem_pages);
+ low = (u64)pages_low * zone->managed_pages;
+ do_div(low, vm_total_pages);
+
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -5366,11 +5413,13 @@
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = tmp;
+ zone->watermark[WMARK_MIN] = min;
}
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) +
+ low + (min >> 2);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+ low + (min >> 1);
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
@@ -5483,7 +5532,7 @@
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
- * changes.
+ * or extra_free_kbytes changes.
*/
int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
@@ -6114,7 +6163,7 @@
{
struct page *page;
struct zone *zone;
- int order, i;
+ unsigned int order, i;
unsigned long pfn;
unsigned long flags;
/* find the first valid pfn */
@@ -6170,7 +6219,7 @@
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
- int order;
+ unsigned int order;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
diff --git a/mm/page_io.c b/mm/page_io.c
index a8a3ef4..ba05b64 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -21,6 +21,7 @@
#include <linux/writeback.h>
#include <linux/frontswap.h>
#include <linux/aio.h>
+#include <linux/blkdev.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
@@ -80,9 +81,54 @@
imajor(bio->bi_bdev->bd_inode),
iminor(bio->bi_bdev->bd_inode),
(unsigned long long)bio->bi_sector);
- } else {
- SetPageUptodate(page);
+ goto out;
}
+
+ SetPageUptodate(page);
+
+ /*
+ * There is no guarantee that the page is in swap cache - the software
+ * suspend code (at least) uses end_swap_bio_read() against a non-
+ * swapcache page. So we must check PG_swapcache before proceeding with
+ * this optimization.
+ */
+ if (likely(PageSwapCache(page))) {
+ struct swap_info_struct *sis;
+
+ sis = page_swap_info(page);
+ if (sis->flags & SWP_BLKDEV) {
+ /*
+ * The swap subsystem performs lazy swap slot freeing,
+ * expecting that the page will be swapped out again.
+ * So we can avoid an unnecessary write if the page
+ * isn't redirtied.
+ * This is good for real swap storage because we can
+ * reduce unnecessary I/O and enhance wear-leveling
+ * if an SSD is used as the as swap device.
+ * But if in-memory swap device (eg zram) is used,
+ * this causes a duplicated copy between uncompressed
+ * data in VM-owned memory and compressed data in
+ * zram-owned memory. So let's free zram-owned memory
+ * and make the VM-owned decompressed page *dirty*,
+ * so the page should be swapped out somewhere again if
+ * we again wish to reclaim it.
+ */
+ struct gendisk *disk = sis->bdev->bd_disk;
+ if (disk->fops->swap_slot_free_notify) {
+ swp_entry_t entry;
+ unsigned long offset;
+
+ entry.val = page_private(page);
+ offset = swp_offset(entry);
+
+ SetPageDirty(page);
+ disk->fops->swap_slot_free_notify(sis->bdev,
+ offset);
+ }
+ }
+ }
+
+out:
unlock_page(page);
bio_put(bio);
}
diff --git a/mm/readahead.c b/mm/readahead.c
index daed28d..829a77c 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -48,7 +48,7 @@
if (!trylock_page(page))
BUG();
page->mapping = mapping;
- do_invalidatepage(page, 0);
+ do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
page->mapping = NULL;
unlock_page(page);
}
diff --git a/mm/shmem.c b/mm/shmem.c
index cc02b6c..87e496f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3028,6 +3028,14 @@
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
@@ -3041,10 +3049,7 @@
if (IS_ERR(file))
return PTR_ERR(file);
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
+ shmem_set_file(vma, file);
return 0;
}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 746af55b..f2b93ec 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -672,6 +672,48 @@
}
/*
+ * How many references to @entry are currently swapped out?
+ * This considers COUNT_CONTINUED so it returns exact answer.
+ */
+int swp_swapcount(swp_entry_t entry)
+{
+ int count, tmp_count, n;
+ struct swap_info_struct *p;
+ struct page *page;
+ pgoff_t offset;
+ unsigned char *map;
+
+ p = swap_info_get(entry);
+ if (!p)
+ return 0;
+
+ count = swap_count(p->swap_map[swp_offset(entry)]);
+ if (!(count & COUNT_CONTINUED))
+ goto out;
+
+ count &= ~COUNT_CONTINUED;
+ n = SWAP_MAP_MAX + 1;
+
+ offset = swp_offset(entry);
+ page = vmalloc_to_page(p->swap_map + offset);
+ offset &= ~PAGE_MASK;
+ VM_BUG_ON(page_private(page) != SWP_CONTINUED);
+
+ do {
+ page = list_entry(page->lru.next, struct page, lru);
+ map = kmap_atomic(page);
+ tmp_count = map[offset];
+ kunmap_atomic(map);
+
+ count += (tmp_count & ~COUNT_CONTINUED) * n;
+ n *= (SWAP_CONT_MAX + 1);
+ } while (tmp_count & COUNT_CONTINUED);
+out:
+ spin_unlock(&p->lock);
+ return count;
+}
+
+/*
* We can write to an anon page without COW if there are no other references
* to it. And as a side-effect, free up its swap: because the old content
* on disk will never be read, and seeking back there to write new content
diff --git a/mm/truncate.c b/mm/truncate.c
index 2d6151f..3c10b7c 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -27,7 +27,8 @@
/**
* do_invalidatepage - invalidate part or all of a page
* @page: the page which is affected
- * @offset: the index of the truncation point
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
*
* do_invalidatepage() is called when all or part of the page has become
* invalidated by a truncate operation.
@@ -38,16 +39,18 @@
* point. Because the caller is about to free (and possibly reuse) those
* blocks on-disk.
*/
-void do_invalidatepage(struct page *page, unsigned long offset)
+void do_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
- void (*invalidatepage)(struct page *, unsigned long);
+ void (*invalidatepage)(struct page *, unsigned int, unsigned int);
+
invalidatepage = page->mapping->a_ops->invalidatepage;
#ifdef CONFIG_BLOCK
if (!invalidatepage)
invalidatepage = block_invalidatepage;
#endif
if (invalidatepage)
- (*invalidatepage)(page, offset);
+ (*invalidatepage)(page, offset, length);
}
static inline void truncate_partial_page(struct page *page, unsigned partial)
@@ -55,7 +58,7 @@
zero_user_segment(page, partial, PAGE_CACHE_SIZE);
cleancache_invalidate_page(page->mapping, page);
if (page_has_private(page))
- do_invalidatepage(page, partial);
+ do_invalidatepage(page, partial, PAGE_CACHE_SIZE - partial);
}
/*
@@ -104,7 +107,7 @@
return -EIO;
if (page_has_private(page))
- do_invalidatepage(page, 0);
+ do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
cancel_dirty_page(page, PAGE_CACHE_SIZE);
diff --git a/mm/util.c b/mm/util.c
index 0b17252..f68b2db 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -7,6 +7,7 @@
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/vmalloc.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -381,6 +382,15 @@
}
EXPORT_SYMBOL(vm_mmap);
+void kvfree(const void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+EXPORT_SYMBOL(kvfree);
+
struct address_space *page_mapping(struct page *page)
{
struct address_space *mapping = page->mapping;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d456560..bd4f271 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -28,6 +28,7 @@
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/llist.h>
+#include <linux/sizes.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a1e3bec..9c786b9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -43,6 +43,7 @@
#include <linux/sysctl.h>
#include <linux/oom.h>
#include <linux/prefetch.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -155,6 +156,40 @@
return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
}
+struct dentry *debug_file;
+
+static int debug_shrinker_show(struct seq_file *s, void *unused)
+{
+ struct shrinker *shrinker;
+ struct shrink_control sc;
+
+ sc.gfp_mask = -1;
+ sc.nr_to_scan = 0;
+
+ down_read(&shrinker_rwsem);
+ list_for_each_entry(shrinker, &shrinker_list, list) {
+ char name[64];
+ int num_objs;
+
+ num_objs = shrinker->shrink(shrinker, &sc);
+ seq_printf(s, "%pf %d\n", shrinker->shrink, num_objs);
+ }
+ up_read(&shrinker_rwsem);
+ return 0;
+}
+
+static int debug_shrinker_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, debug_shrinker_show, inode->i_private);
+}
+
+static const struct file_operations debug_shrinker_fops = {
+ .open = debug_shrinker_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
/*
* Add a shrinker callback to be called from the vm
*/
@@ -167,6 +202,15 @@
}
EXPORT_SYMBOL(register_shrinker);
+static int __init add_shrinker_debug(void)
+{
+ debugfs_create_file("shrinker", 0644, NULL, NULL,
+ &debug_shrinker_fops);
+ return 0;
+}
+
+late_initcall(add_shrinker_debug);
+
/*
* Remove one
*/
diff --git a/mm/zpool.c b/mm/zpool.c
new file mode 100644
index 0000000..bacdab6
--- /dev/null
+++ b/mm/zpool.c
@@ -0,0 +1,366 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for memory storage pool implementations.
+ * Typically, this is used to store compressed memory.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/zpool.h>
+
+struct zpool {
+ char *type;
+
+ struct zpool_driver *driver;
+ void *pool;
+ struct zpool_ops *ops;
+
+ struct list_head list;
+};
+
+static LIST_HEAD(drivers_head);
+static DEFINE_SPINLOCK(drivers_lock);
+
+static LIST_HEAD(pools_head);
+static DEFINE_SPINLOCK(pools_lock);
+
+/**
+ * zpool_register_driver() - register a zpool implementation.
+ * @driver: driver to register
+ */
+void zpool_register_driver(struct zpool_driver *driver)
+{
+ spin_lock(&drivers_lock);
+ atomic_set(&driver->refcount, 0);
+ list_add(&driver->list, &drivers_head);
+ spin_unlock(&drivers_lock);
+}
+EXPORT_SYMBOL(zpool_register_driver);
+
+/**
+ * zpool_unregister_driver() - unregister a zpool implementation.
+ * @driver: driver to unregister.
+ *
+ * Module usage counting is used to prevent using a driver
+ * while/after unloading, so if this is called from module
+ * exit function, this should never fail; if called from
+ * other than the module exit function, and this returns
+ * failure, the driver is in use and must remain available.
+ */
+int zpool_unregister_driver(struct zpool_driver *driver)
+{
+ int ret = 0, refcount;
+
+ spin_lock(&drivers_lock);
+ refcount = atomic_read(&driver->refcount);
+ WARN_ON(refcount < 0);
+ if (refcount > 0)
+ ret = -EBUSY;
+ else
+ list_del(&driver->list);
+ spin_unlock(&drivers_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(zpool_unregister_driver);
+
+/**
+ * zpool_evict() - evict callback from a zpool implementation.
+ * @pool: pool to evict from.
+ * @handle: handle to evict.
+ *
+ * This can be used by zpool implementations to call the
+ * user's evict zpool_ops struct evict callback.
+ */
+int zpool_evict(void *pool, unsigned long handle)
+{
+ struct zpool *zpool;
+
+ spin_lock(&pools_lock);
+ list_for_each_entry(zpool, &pools_head, list) {
+ if (zpool->pool == pool) {
+ spin_unlock(&pools_lock);
+ if (!zpool->ops || !zpool->ops->evict)
+ return -EINVAL;
+ return zpool->ops->evict(zpool, handle);
+ }
+ }
+ spin_unlock(&pools_lock);
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL(zpool_evict);
+
+static struct zpool_driver *zpool_get_driver(char *type)
+{
+ struct zpool_driver *driver;
+
+ spin_lock(&drivers_lock);
+ list_for_each_entry(driver, &drivers_head, list) {
+ if (!strcmp(driver->type, type)) {
+ bool got = try_module_get(driver->owner);
+
+ if (got)
+ atomic_inc(&driver->refcount);
+ spin_unlock(&drivers_lock);
+ return got ? driver : NULL;
+ }
+ }
+
+ spin_unlock(&drivers_lock);
+ return NULL;
+}
+
+static void zpool_put_driver(struct zpool_driver *driver)
+{
+ atomic_dec(&driver->refcount);
+ module_put(driver->owner);
+}
+
+/**
+ * zpool_create_pool() - Create a new zpool
+ * @type The type of the zpool to create (e.g. zbud, zsmalloc)
+ * @name The name of the zpool (e.g. zram0, zswap)
+ * @gfp The GFP flags to use when allocating the pool.
+ * @ops The optional ops callback.
+ *
+ * This creates a new zpool of the specified type. The gfp flags will be
+ * used when allocating memory, if the implementation supports it. If the
+ * ops param is NULL, then the created zpool will not be shrinkable.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: New zpool on success, NULL on failure.
+ */
+struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+ struct zpool_ops *ops)
+{
+ struct zpool_driver *driver;
+ struct zpool *zpool;
+
+ pr_info("creating pool type %s\n", type);
+
+ driver = zpool_get_driver(type);
+
+ if (!driver) {
+ request_module("zpool-%s", type);
+ driver = zpool_get_driver(type);
+ }
+
+ if (!driver) {
+ pr_err("no driver for type %s\n", type);
+ return NULL;
+ }
+
+ zpool = kmalloc(sizeof(*zpool), gfp);
+ if (!zpool) {
+ pr_err("couldn't create zpool - out of memory\n");
+ zpool_put_driver(driver);
+ return NULL;
+ }
+
+ zpool->type = driver->type;
+ zpool->driver = driver;
+ zpool->pool = driver->create(name, gfp, ops);
+ zpool->ops = ops;
+
+ if (!zpool->pool) {
+ pr_err("couldn't create %s pool\n", type);
+ zpool_put_driver(driver);
+ kfree(zpool);
+ return NULL;
+ }
+
+ pr_info("created %s pool\n", type);
+
+ spin_lock(&pools_lock);
+ list_add(&zpool->list, &pools_head);
+ spin_unlock(&pools_lock);
+
+ return zpool;
+}
+
+/**
+ * zpool_destroy_pool() - Destroy a zpool
+ * @pool The zpool to destroy.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when destroying different pools. The same
+ * pool should only be destroyed once, and should not be used
+ * after it is destroyed.
+ *
+ * This destroys an existing zpool. The zpool should not be in use.
+ */
+void zpool_destroy_pool(struct zpool *zpool)
+{
+ pr_info("destroying pool type %s\n", zpool->type);
+
+ spin_lock(&pools_lock);
+ list_del(&zpool->list);
+ spin_unlock(&pools_lock);
+ zpool->driver->destroy(zpool->pool);
+ zpool_put_driver(zpool->driver);
+ kfree(zpool);
+}
+
+/**
+ * zpool_get_type() - Get the type of the zpool
+ * @pool The zpool to check
+ *
+ * This returns the type of the pool.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: The type of zpool.
+ */
+char *zpool_get_type(struct zpool *zpool)
+{
+ return zpool->type;
+}
+
+/**
+ * zpool_malloc() - Allocate memory
+ * @pool The zpool to allocate from.
+ * @size The amount of memory to allocate.
+ * @gfp The GFP flags to use when allocating memory.
+ * @handle Pointer to the handle to set
+ *
+ * This allocates the requested amount of memory from the pool.
+ * The gfp flags will be used when allocating memory, if the
+ * implementation supports it. The provided @handle will be
+ * set to the allocated object handle.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error.
+ */
+int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp,
+ unsigned long *handle)
+{
+ return zpool->driver->malloc(zpool->pool, size, gfp, handle);
+}
+
+/**
+ * zpool_free() - Free previously allocated memory
+ * @pool The zpool that allocated the memory.
+ * @handle The handle to the memory to free.
+ *
+ * This frees previously allocated memory. This does not guarantee
+ * that the pool will actually free memory, only that the memory
+ * in the pool will become available for use by the pool.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when freeing different handles. The same
+ * handle should only be freed once, and should not be used
+ * after freeing.
+ */
+void zpool_free(struct zpool *zpool, unsigned long handle)
+{
+ zpool->driver->free(zpool->pool, handle);
+}
+
+/**
+ * zpool_shrink() - Shrink the pool size
+ * @pool The zpool to shrink.
+ * @pages The number of pages to shrink the pool.
+ * @reclaimed The number of pages successfully evicted.
+ *
+ * This attempts to shrink the actual memory size of the pool
+ * by evicting currently used handle(s). If the pool was
+ * created with no zpool_ops, or the evict call fails for any
+ * of the handles, this will fail. If non-NULL, the @reclaimed
+ * parameter will be set to the number of pages reclaimed,
+ * which may be more than the number of pages requested.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error/failure.
+ */
+int zpool_shrink(struct zpool *zpool, unsigned int pages,
+ unsigned int *reclaimed)
+{
+ return zpool->driver->shrink(zpool->pool, pages, reclaimed);
+}
+
+/**
+ * zpool_map_handle() - Map a previously allocated handle into memory
+ * @pool The zpool that the handle was allocated from
+ * @handle The handle to map
+ * @mm How the memory should be mapped
+ *
+ * This maps a previously allocated handle into memory. The @mm
+ * param indicates to the implementation how the memory will be
+ * used, i.e. read-only, write-only, read-write. If the
+ * implementation does not support it, the memory will be treated
+ * as read-write.
+ *
+ * This may hold locks, disable interrupts, and/or preemption,
+ * and the zpool_unmap_handle() must be called to undo those
+ * actions. The code that uses the mapped handle should complete
+ * its operatons on the mapped handle memory quickly and unmap
+ * as soon as possible. As the implementation may use per-cpu
+ * data, multiple handles should not be mapped concurrently on
+ * any cpu.
+ *
+ * Returns: A pointer to the handle's mapped memory area.
+ */
+void *zpool_map_handle(struct zpool *zpool, unsigned long handle,
+ enum zpool_mapmode mapmode)
+{
+ return zpool->driver->map(zpool->pool, handle, mapmode);
+}
+
+/**
+ * zpool_unmap_handle() - Unmap a previously mapped handle
+ * @pool The zpool that the handle was allocated from
+ * @handle The handle to unmap
+ *
+ * This unmaps a previously mapped handle. Any locks or other
+ * actions that the implementation took in zpool_map_handle()
+ * will be undone here. The memory area returned from
+ * zpool_map_handle() should no longer be used after this.
+ */
+void zpool_unmap_handle(struct zpool *zpool, unsigned long handle)
+{
+ zpool->driver->unmap(zpool->pool, handle);
+}
+
+/**
+ * zpool_get_total_size() - The total size of the pool
+ * @pool The zpool to check
+ *
+ * This returns the total size in bytes of the pool.
+ *
+ * Returns: Total size of the zpool in bytes.
+ */
+u64 zpool_get_total_size(struct zpool *zpool)
+{
+ return zpool->driver->total_size(zpool->pool);
+}
+
+static int __init init_zpool(void)
+{
+ pr_info("loaded\n");
+ return 0;
+}
+
+static void __exit exit_zpool(void)
+{
+ pr_info("unloaded\n");
+}
+
+module_init(init_zpool);
+module_exit(exit_zpool);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("Common API for compressed memory storage");
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
new file mode 100644
index 0000000..613653a
--- /dev/null
+++ b/mm/zsmalloc.c
@@ -0,0 +1,1948 @@
+/*
+ * zsmalloc memory allocator
+ *
+ * Copyright (C) 2011 Nitin Gupta
+ * Copyright (C) 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the license that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+/*
+ * Following is how we use various fields and flags of underlying
+ * struct page(s) to form a zspage.
+ *
+ * Usage of struct page fields:
+ * page->first_page: points to the first component (0-order) page
+ * page->index (union with page->freelist): offset of the first object
+ * starting in this page. For the first page, this is
+ * always 0, so we use this field (aka freelist) to point
+ * to the first free object in zspage.
+ * page->lru: links together all component pages (except the first page)
+ * of a zspage
+ *
+ * For _first_ page only:
+ *
+ * page->private (union with page->first_page): refers to the
+ * component page after the first page
+ * If the page is first_page for huge object, it stores handle.
+ * Look at size_class->huge.
+ * page->freelist: points to the first free object in zspage.
+ * Free objects are linked together using in-place
+ * metadata.
+ * page->objects: maximum number of objects we can store in this
+ * zspage (class->zspage_order * PAGE_SIZE / class->size)
+ * page->lru: links together first pages of various zspages.
+ * Basically forming list of zspages in a fullness group.
+ * page->mapping: class index and fullness group of the zspage
+ *
+ * Usage of struct page flags:
+ * PG_private: identifies the first component page
+ * PG_private2: identifies the last component page
+ *
+ */
+
+#ifdef CONFIG_ZSMALLOC_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+#include <linux/cpumask.h>
+#include <linux/cpu.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/debugfs.h>
+#include <linux/zsmalloc.h>
+#include <linux/zpool.h>
+
+/*
+ * This must be power of 2 and greater than of equal to sizeof(link_free).
+ * These two conditions ensure that any 'struct link_free' itself doesn't
+ * span more than 1 page which avoids complex case of mapping 2 pages simply
+ * to restore link_free pointer values.
+ */
+#define ZS_ALIGN 8
+
+/*
+ * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
+ * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
+ */
+#define ZS_MAX_ZSPAGE_ORDER 2
+#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
+
+#define ZS_HANDLE_SIZE (sizeof(unsigned long))
+
+/*
+ * Object location (<PFN>, <obj_idx>) is encoded as
+ * as single (unsigned long) handle value.
+ *
+ * Note that object index <obj_idx> is relative to system
+ * page <PFN> it is stored in, so for each sub-page belonging
+ * to a zspage, obj_idx starts with 0.
+ *
+ * This is made more complicated by various memory models and PAE.
+ */
+
+#ifndef MAX_PHYSMEM_BITS
+#ifdef CONFIG_HIGHMEM64G
+#define MAX_PHYSMEM_BITS 36
+#else /* !CONFIG_HIGHMEM64G */
+/*
+ * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
+ * be PAGE_SHIFT
+ */
+#define MAX_PHYSMEM_BITS BITS_PER_LONG
+#endif
+#endif
+#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
+
+/*
+ * Memory for allocating for handle keeps object position by
+ * encoding <page, obj_idx> and the encoded value has a room
+ * in least bit(ie, look at obj_to_location).
+ * We use the bit to synchronize between object access by
+ * user and migration.
+ */
+#define HANDLE_PIN_BIT 0
+
+/*
+ * Head in allocated object should have OBJ_ALLOCATED_TAG
+ * to identify the object was allocated or not.
+ * It's okay to add the status bit in the least bit because
+ * header keeps handle which is 4byte-aligned address so we
+ * have room for two bit at least.
+ */
+#define OBJ_ALLOCATED_TAG 1
+#define OBJ_TAG_BITS 1
+#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
+#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
+
+#define MAX(a, b) ((a) >= (b) ? (a) : (b))
+/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
+#define ZS_MIN_ALLOC_SIZE \
+ MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
+/* each chunk includes extra space to keep handle */
+#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
+
+/*
+ * On systems with 4K page size, this gives 255 size classes! There is a
+ * trader-off here:
+ * - Large number of size classes is potentially wasteful as free page are
+ * spread across these classes
+ * - Small number of size classes causes large internal fragmentation
+ * - Probably its better to use specific size classes (empirically
+ * determined). NOTE: all those class sizes must be set as multiple of
+ * ZS_ALIGN to make sure link_free itself never has to span 2 pages.
+ *
+ * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
+ * (reason above)
+ */
+#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
+
+/*
+ * We do not maintain any list for completely empty or full pages
+ */
+enum fullness_group {
+ ZS_ALMOST_FULL,
+ ZS_ALMOST_EMPTY,
+ _ZS_NR_FULLNESS_GROUPS,
+
+ ZS_EMPTY,
+ ZS_FULL
+};
+
+enum zs_stat_type {
+ OBJ_ALLOCATED,
+ OBJ_USED,
+ CLASS_ALMOST_FULL,
+ CLASS_ALMOST_EMPTY,
+ NR_ZS_STAT_TYPE,
+};
+
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static struct dentry *zs_stat_root;
+
+struct zs_size_stat {
+ unsigned long objs[NR_ZS_STAT_TYPE];
+};
+
+#endif
+
+/*
+ * number of size_classes
+ */
+static int zs_size_classes;
+
+/*
+ * We assign a page to ZS_ALMOST_EMPTY fullness group when:
+ * n <= N / f, where
+ * n = number of allocated objects
+ * N = total number of objects zspage can store
+ * f = fullness_threshold_frac
+ *
+ * Similarly, we assign zspage to:
+ * ZS_ALMOST_FULL when n > N / f
+ * ZS_EMPTY when n == 0
+ * ZS_FULL when n == N
+ *
+ * (see: fix_fullness_group())
+ */
+static const int fullness_threshold_frac = 4;
+
+struct size_class {
+ /*
+ * Size of objects stored in this class. Must be multiple
+ * of ZS_ALIGN.
+ */
+ int size;
+ unsigned int index;
+
+ /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
+ int pages_per_zspage;
+ /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
+ bool huge;
+
+#ifdef CONFIG_ZSMALLOC_STAT
+ struct zs_size_stat stats;
+#endif
+
+ spinlock_t lock;
+
+ struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
+};
+
+/*
+ * Placed within free objects to form a singly linked list.
+ * For every zspage, first_page->freelist gives head of this list.
+ *
+ * This must be power of 2 and less than or equal to ZS_ALIGN
+ */
+struct link_free {
+ union {
+ /*
+ * Position of next free chunk (encodes <PFN, obj_idx>)
+ * It's valid for non-allocated object
+ */
+ void *next;
+ /*
+ * Handle of allocated object.
+ */
+ unsigned long handle;
+ };
+};
+
+struct zs_pool {
+ char *name;
+
+ struct size_class **size_class;
+ struct kmem_cache *handle_cachep;
+
+ gfp_t flags; /* allocation flags used when growing pool */
+ atomic_long_t pages_allocated;
+
+#ifdef CONFIG_ZSMALLOC_STAT
+ struct dentry *stat_dentry;
+#endif
+};
+
+/*
+ * A zspage's class index and fullness group
+ * are encoded in its (first)page->mapping
+ */
+#define CLASS_IDX_BITS 28
+#define FULLNESS_BITS 4
+#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1)
+#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1)
+
+struct mapping_area {
+#ifdef CONFIG_PGTABLE_MAPPING
+ struct vm_struct *vm; /* vm area for mapping object that span pages */
+#else
+ char *vm_buf; /* copy buffer for objects that span pages */
+#endif
+ char *vm_addr; /* address of kmap_atomic()'ed pages */
+ enum zs_mapmode vm_mm; /* mapping mode */
+ bool huge;
+};
+
+static int create_handle_cache(struct zs_pool *pool)
+{
+ pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
+ 0, 0, NULL);
+ return pool->handle_cachep ? 0 : 1;
+}
+
+static void destroy_handle_cache(struct zs_pool *pool)
+{
+ if (pool->handle_cachep)
+ kmem_cache_destroy(pool->handle_cachep);
+}
+
+static unsigned long alloc_handle(struct zs_pool *pool)
+{
+ return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
+ pool->flags & ~__GFP_HIGHMEM);
+}
+
+static void free_handle(struct zs_pool *pool, unsigned long handle)
+{
+ kmem_cache_free(pool->handle_cachep, (void *)handle);
+}
+
+static void record_obj(unsigned long handle, unsigned long obj)
+{
+ *(unsigned long *)handle = obj;
+}
+
+/* zpool driver */
+
+#ifdef CONFIG_ZPOOL
+
+static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops)
+{
+ return zs_create_pool(name, gfp);
+}
+
+static void zs_zpool_destroy(void *pool)
+{
+ zs_destroy_pool(pool);
+}
+
+static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
+ unsigned long *handle)
+{
+ *handle = zs_malloc(pool, size);
+ return *handle ? 0 : -1;
+}
+static void zs_zpool_free(void *pool, unsigned long handle)
+{
+ zs_free(pool, handle);
+}
+
+static int zs_zpool_shrink(void *pool, unsigned int pages,
+ unsigned int *reclaimed)
+{
+ return -EINVAL;
+}
+
+static void *zs_zpool_map(void *pool, unsigned long handle,
+ enum zpool_mapmode mm)
+{
+ enum zs_mapmode zs_mm;
+
+ switch (mm) {
+ case ZPOOL_MM_RO:
+ zs_mm = ZS_MM_RO;
+ break;
+ case ZPOOL_MM_WO:
+ zs_mm = ZS_MM_WO;
+ break;
+ case ZPOOL_MM_RW: /* fallthru */
+ default:
+ zs_mm = ZS_MM_RW;
+ break;
+ }
+
+ return zs_map_object(pool, handle, zs_mm);
+}
+static void zs_zpool_unmap(void *pool, unsigned long handle)
+{
+ zs_unmap_object(pool, handle);
+}
+
+static u64 zs_zpool_total_size(void *pool)
+{
+ return zs_get_total_pages(pool) << PAGE_SHIFT;
+}
+
+static struct zpool_driver zs_zpool_driver = {
+ .type = "zsmalloc",
+ .owner = THIS_MODULE,
+ .create = zs_zpool_create,
+ .destroy = zs_zpool_destroy,
+ .malloc = zs_zpool_malloc,
+ .free = zs_zpool_free,
+ .shrink = zs_zpool_shrink,
+ .map = zs_zpool_map,
+ .unmap = zs_zpool_unmap,
+ .total_size = zs_zpool_total_size,
+};
+
+MODULE_ALIAS("zpool-zsmalloc");
+#endif /* CONFIG_ZPOOL */
+
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+ return pages_per_zspage * PAGE_SIZE / size;
+}
+
+/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
+static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+
+static int is_first_page(struct page *page)
+{
+ return PagePrivate(page);
+}
+
+static int is_last_page(struct page *page)
+{
+ return PagePrivate2(page);
+}
+
+static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
+ enum fullness_group *fullness)
+{
+ unsigned long m;
+ BUG_ON(!is_first_page(page));
+
+ m = (unsigned long)page->mapping;
+ *fullness = m & FULLNESS_MASK;
+ *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
+}
+
+static void set_zspage_mapping(struct page *page, unsigned int class_idx,
+ enum fullness_group fullness)
+{
+ unsigned long m;
+ BUG_ON(!is_first_page(page));
+
+ m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
+ (fullness & FULLNESS_MASK);
+ page->mapping = (struct address_space *)m;
+}
+
+/*
+ * zsmalloc divides the pool into various size classes where each
+ * class maintains a list of zspages where each zspage is divided
+ * into equal sized chunks. Each allocation falls into one of these
+ * classes depending on its size. This function returns index of the
+ * size class which has chunk size big enough to hold the give size.
+ */
+static int get_size_class_index(int size)
+{
+ int idx = 0;
+
+ if (likely(size > ZS_MIN_ALLOC_SIZE))
+ idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
+ ZS_SIZE_CLASS_DELTA);
+
+ return min(zs_size_classes - 1, idx);
+}
+
+#ifdef CONFIG_ZSMALLOC_STAT
+
+static inline void zs_stat_inc(struct size_class *class,
+ enum zs_stat_type type, unsigned long cnt)
+{
+ class->stats.objs[type] += cnt;
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+ enum zs_stat_type type, unsigned long cnt)
+{
+ class->stats.objs[type] -= cnt;
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+ enum zs_stat_type type)
+{
+ return class->stats.objs[type];
+}
+
+static int __init zs_stat_init(void)
+{
+ if (!debugfs_initialized())
+ return -ENODEV;
+
+ zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
+ if (!zs_stat_root)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+ debugfs_remove_recursive(zs_stat_root);
+}
+
+static int zs_stats_size_show(struct seq_file *s, void *v)
+{
+ int i;
+ struct zs_pool *pool = s->private;
+ struct size_class *class;
+ int objs_per_zspage;
+ unsigned long class_almost_full, class_almost_empty;
+ unsigned long obj_allocated, obj_used, pages_used;
+ unsigned long total_class_almost_full = 0, total_class_almost_empty = 0;
+ unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
+
+ seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s\n",
+ "class", "size", "almost_full", "almost_empty",
+ "obj_allocated", "obj_used", "pages_used",
+ "pages_per_zspage");
+
+ for (i = 0; i < zs_size_classes; i++) {
+ class = pool->size_class[i];
+
+ if (class->index != i)
+ continue;
+
+ spin_lock(&class->lock);
+ class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL);
+ class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY);
+ obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
+ obj_used = zs_stat_get(class, OBJ_USED);
+ spin_unlock(&class->lock);
+
+ objs_per_zspage = get_maxobj_per_zspage(class->size,
+ class->pages_per_zspage);
+ pages_used = obj_allocated / objs_per_zspage *
+ class->pages_per_zspage;
+
+ seq_printf(s, " %5u %5u %11lu %12lu %13lu %10lu %10lu %16d\n",
+ i, class->size, class_almost_full, class_almost_empty,
+ obj_allocated, obj_used, pages_used,
+ class->pages_per_zspage);
+
+ total_class_almost_full += class_almost_full;
+ total_class_almost_empty += class_almost_empty;
+ total_objs += obj_allocated;
+ total_used_objs += obj_used;
+ total_pages += pages_used;
+ }
+
+ seq_puts(s, "\n");
+ seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu\n",
+ "Total", "", total_class_almost_full,
+ total_class_almost_empty, total_objs,
+ total_used_objs, total_pages);
+
+ return 0;
+}
+
+static int zs_stats_size_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, zs_stats_size_show, inode->i_private);
+}
+
+static const struct file_operations zs_stat_size_ops = {
+ .open = zs_stats_size_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+ struct dentry *entry;
+
+ if (!zs_stat_root)
+ return -ENODEV;
+
+ entry = debugfs_create_dir(name, zs_stat_root);
+ if (!entry) {
+ pr_warn("debugfs dir <%s> creation failed\n", name);
+ return -ENOMEM;
+ }
+ pool->stat_dentry = entry;
+
+ entry = debugfs_create_file("classes", S_IFREG | S_IRUGO,
+ pool->stat_dentry, pool, &zs_stat_size_ops);
+ if (!entry) {
+ pr_warn("%s: debugfs file entry <%s> creation failed\n",
+ name, "classes");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+ debugfs_remove_recursive(pool->stat_dentry);
+}
+
+#else /* CONFIG_ZSMALLOC_STAT */
+
+static inline void zs_stat_inc(struct size_class *class,
+ enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline void zs_stat_dec(struct size_class *class,
+ enum zs_stat_type type, unsigned long cnt)
+{
+}
+
+static inline unsigned long zs_stat_get(struct size_class *class,
+ enum zs_stat_type type)
+{
+ return 0;
+}
+
+static int __init zs_stat_init(void)
+{
+ return 0;
+}
+
+static void __exit zs_stat_exit(void)
+{
+}
+
+static inline int zs_pool_stat_create(char *name, struct zs_pool *pool)
+{
+ return 0;
+}
+
+static inline void zs_pool_stat_destroy(struct zs_pool *pool)
+{
+}
+
+#endif
+
+
+/*
+ * For each size class, zspages are divided into different groups
+ * depending on how "full" they are. This was done so that we could
+ * easily find empty or nearly empty zspages when we try to shrink
+ * the pool (not yet implemented). This function returns fullness
+ * status of the given page.
+ */
+static enum fullness_group get_fullness_group(struct page *page)
+{
+ int inuse, max_objects;
+ enum fullness_group fg;
+ BUG_ON(!is_first_page(page));
+
+ inuse = page->inuse;
+ max_objects = page->objects;
+
+ if (inuse == 0)
+ fg = ZS_EMPTY;
+ else if (inuse == max_objects)
+ fg = ZS_FULL;
+ else if (inuse <= 3 * max_objects / fullness_threshold_frac)
+ fg = ZS_ALMOST_EMPTY;
+ else
+ fg = ZS_ALMOST_FULL;
+
+ return fg;
+}
+
+/*
+ * Each size class maintains various freelists and zspages are assigned
+ * to one of these freelists based on the number of live objects they
+ * have. This functions inserts the given zspage into the freelist
+ * identified by <class, fullness_group>.
+ */
+static void insert_zspage(struct page *page, struct size_class *class,
+ enum fullness_group fullness)
+{
+ struct page **head;
+
+ BUG_ON(!is_first_page(page));
+
+ if (fullness >= _ZS_NR_FULLNESS_GROUPS)
+ return;
+
+ head = &class->fullness_list[fullness];
+ if (*head)
+ list_add_tail(&page->lru, &(*head)->lru);
+
+ *head = page;
+ zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
+ CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
+}
+
+/*
+ * This function removes the given zspage from the freelist identified
+ * by <class, fullness_group>.
+ */
+static void remove_zspage(struct page *page, struct size_class *class,
+ enum fullness_group fullness)
+{
+ struct page **head;
+
+ BUG_ON(!is_first_page(page));
+
+ if (fullness >= _ZS_NR_FULLNESS_GROUPS)
+ return;
+
+ head = &class->fullness_list[fullness];
+ BUG_ON(!*head);
+ if (list_empty(&(*head)->lru))
+ *head = NULL;
+ else if (*head == page)
+ *head = (struct page *)list_entry((*head)->lru.next,
+ struct page, lru);
+
+ list_del_init(&page->lru);
+ zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ?
+ CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
+}
+
+/*
+ * Each size class maintains zspages in different fullness groups depending
+ * on the number of live objects they contain. When allocating or freeing
+ * objects, the fullness status of the page can change, say, from ALMOST_FULL
+ * to ALMOST_EMPTY when freeing an object. This function checks if such
+ * a status change has occurred for the given page and accordingly moves the
+ * page from the freelist of the old fullness group to that of the new
+ * fullness group.
+ */
+static enum fullness_group fix_fullness_group(struct size_class *class,
+ struct page *page)
+{
+ int class_idx;
+ enum fullness_group currfg, newfg;
+
+ BUG_ON(!is_first_page(page));
+
+ get_zspage_mapping(page, &class_idx, &currfg);
+ newfg = get_fullness_group(page);
+ if (newfg == currfg)
+ goto out;
+
+ remove_zspage(page, class, currfg);
+ insert_zspage(page, class, newfg);
+ set_zspage_mapping(page, class_idx, newfg);
+
+out:
+ return newfg;
+}
+
+/*
+ * We have to decide on how many pages to link together
+ * to form a zspage for each size class. This is important
+ * to reduce wastage due to unusable space left at end of
+ * each zspage which is given as:
+ * wastage = Zp % class_size
+ * usage = Zp - wastage
+ * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
+ *
+ * For example, for size class of 3/8 * PAGE_SIZE, we should
+ * link together 3 PAGE_SIZE sized pages to form a zspage
+ * since then we can perfectly fit in 8 such objects.
+ */
+static int get_pages_per_zspage(int class_size)
+{
+ int i, max_usedpc = 0;
+ /* zspage order which gives maximum used size per KB */
+ int max_usedpc_order = 1;
+
+ for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
+ int zspage_size;
+ int waste, usedpc;
+
+ zspage_size = i * PAGE_SIZE;
+ waste = zspage_size % class_size;
+ usedpc = (zspage_size - waste) * 100 / zspage_size;
+
+ if (usedpc > max_usedpc) {
+ max_usedpc = usedpc;
+ max_usedpc_order = i;
+ }
+ }
+
+ return max_usedpc_order;
+}
+
+/*
+ * A single 'zspage' is composed of many system pages which are
+ * linked together using fields in struct page. This function finds
+ * the first/head page, given any component page of a zspage.
+ */
+static struct page *get_first_page(struct page *page)
+{
+ if (is_first_page(page))
+ return page;
+ else
+ return page->first_page;
+}
+
+static struct page *get_next_page(struct page *page)
+{
+ struct page *next;
+
+ if (is_last_page(page))
+ next = NULL;
+ else if (is_first_page(page))
+ next = (struct page *)page_private(page);
+ else
+ next = list_entry(page->lru.next, struct page, lru);
+
+ return next;
+}
+
+/*
+ * Encode <page, obj_idx> as a single handle value.
+ * We use the least bit of handle for tagging.
+ */
+static void *location_to_obj(struct page *page, unsigned long obj_idx)
+{
+ unsigned long obj;
+
+ if (!page) {
+ BUG_ON(obj_idx);
+ return NULL;
+ }
+
+ obj = page_to_pfn(page) << OBJ_INDEX_BITS;
+ obj |= ((obj_idx) & OBJ_INDEX_MASK);
+ obj <<= OBJ_TAG_BITS;
+
+ return (void *)obj;
+}
+
+/*
+ * Decode <page, obj_idx> pair from the given object handle. We adjust the
+ * decoded obj_idx back to its original value since it was adjusted in
+ * location_to_obj().
+ */
+static void obj_to_location(unsigned long obj, struct page **page,
+ unsigned long *obj_idx)
+{
+ obj >>= OBJ_TAG_BITS;
+ *page = pfn_to_page(obj >> OBJ_INDEX_BITS);
+ *obj_idx = (obj & OBJ_INDEX_MASK);
+}
+
+static unsigned long handle_to_obj(unsigned long handle)
+{
+ return *(unsigned long *)handle;
+}
+
+static unsigned long obj_to_head(struct size_class *class, struct page *page,
+ void *obj)
+{
+ if (class->huge) {
+ VM_BUG_ON(!is_first_page(page));
+ return *(unsigned long *)page_private(page);
+ } else
+ return *(unsigned long *)obj;
+}
+
+static unsigned long obj_idx_to_offset(struct page *page,
+ unsigned long obj_idx, int class_size)
+{
+ unsigned long off = 0;
+
+ if (!is_first_page(page))
+ off = page->index;
+
+ return off + obj_idx * class_size;
+}
+
+static inline int trypin_tag(unsigned long handle)
+{
+ unsigned long *ptr = (unsigned long *)handle;
+
+ return !test_and_set_bit_lock(HANDLE_PIN_BIT, ptr);
+}
+
+static void pin_tag(unsigned long handle)
+{
+ while (!trypin_tag(handle));
+}
+
+static void unpin_tag(unsigned long handle)
+{
+ unsigned long *ptr = (unsigned long *)handle;
+
+ clear_bit_unlock(HANDLE_PIN_BIT, ptr);
+}
+
+static void reset_page(struct page *page)
+{
+ clear_bit(PG_private, &page->flags);
+ clear_bit(PG_private_2, &page->flags);
+ set_page_private(page, 0);
+ page->mapping = NULL;
+ page->freelist = NULL;
+ page_mapcount_reset(page);
+}
+
+static void free_zspage(struct page *first_page)
+{
+ struct page *nextp, *tmp, *head_extra;
+
+ BUG_ON(!is_first_page(first_page));
+ BUG_ON(first_page->inuse);
+
+ head_extra = (struct page *)page_private(first_page);
+
+ reset_page(first_page);
+ __free_page(first_page);
+
+ /* zspage with only 1 system page */
+ if (!head_extra)
+ return;
+
+ list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
+ list_del(&nextp->lru);
+ reset_page(nextp);
+ __free_page(nextp);
+ }
+ reset_page(head_extra);
+ __free_page(head_extra);
+}
+
+/* Initialize a newly allocated zspage */
+static void init_zspage(struct page *first_page, struct size_class *class)
+{
+ unsigned long off = 0;
+ struct page *page = first_page;
+
+ BUG_ON(!is_first_page(first_page));
+ while (page) {
+ struct page *next_page;
+ struct link_free *link;
+ unsigned int i = 1;
+ void *vaddr;
+
+ /*
+ * page->index stores offset of first object starting
+ * in the page. For the first page, this is always 0,
+ * so we use first_page->index (aka ->freelist) to store
+ * head of corresponding zspage's freelist.
+ */
+ if (page != first_page)
+ page->index = off;
+
+ vaddr = kmap_atomic(page);
+ link = (struct link_free *)vaddr + off / sizeof(*link);
+
+ while ((off += class->size) < PAGE_SIZE) {
+ link->next = location_to_obj(page, i++);
+ link += class->size / sizeof(*link);
+ }
+
+ /*
+ * We now come to the last (full or partial) object on this
+ * page, which must point to the first object on the next
+ * page (if present)
+ */
+ next_page = get_next_page(page);
+ link->next = location_to_obj(next_page, 0);
+ kunmap_atomic(vaddr);
+ page = next_page;
+ off %= PAGE_SIZE;
+ }
+}
+
+/*
+ * Allocate a zspage for the given size class
+ */
+static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
+{
+ int i, error;
+ struct page *first_page = NULL, *uninitialized_var(prev_page);
+
+ /*
+ * Allocate individual pages and link them together as:
+ * 1. first page->private = first sub-page
+ * 2. all sub-pages are linked together using page->lru
+ * 3. each sub-page is linked to the first page using page->first_page
+ *
+ * For each size class, First/Head pages are linked together using
+ * page->lru. Also, we set PG_private to identify the first page
+ * (i.e. no other sub-page has this flag set) and PG_private_2 to
+ * identify the last page.
+ */
+ error = -ENOMEM;
+ for (i = 0; i < class->pages_per_zspage; i++) {
+ struct page *page;
+
+ page = alloc_page(flags);
+ if (!page)
+ goto cleanup;
+
+ INIT_LIST_HEAD(&page->lru);
+ if (i == 0) { /* first page */
+ SetPagePrivate(page);
+ set_page_private(page, 0);
+ first_page = page;
+ first_page->inuse = 0;
+ }
+ if (i == 1)
+ set_page_private(first_page, (unsigned long)page);
+ if (i >= 1)
+ page->first_page = first_page;
+ if (i >= 2)
+ list_add(&page->lru, &prev_page->lru);
+ if (i == class->pages_per_zspage - 1) /* last page */
+ SetPagePrivate2(page);
+ prev_page = page;
+ }
+
+ init_zspage(first_page, class);
+
+ first_page->freelist = location_to_obj(first_page, 0);
+ /* Maximum number of objects we can store in this zspage */
+ first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
+
+ error = 0; /* Success */
+
+cleanup:
+ if (unlikely(error) && first_page) {
+ free_zspage(first_page);
+ first_page = NULL;
+ }
+
+ return first_page;
+}
+
+static struct page *find_get_zspage(struct size_class *class)
+{
+ int i;
+ struct page *page;
+
+ for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
+ page = class->fullness_list[i];
+ if (page)
+ break;
+ }
+
+ return page;
+}
+
+#ifdef CONFIG_PGTABLE_MAPPING
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+ /*
+ * Make sure we don't leak memory if a cpu UP notification
+ * and zs_init() race and both call zs_cpu_up() on the same cpu
+ */
+ if (area->vm)
+ return 0;
+ area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
+ if (!area->vm)
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+ if (area->vm)
+ free_vm_area(area->vm);
+ area->vm = NULL;
+}
+
+static inline void *__zs_map_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
+ area->vm_addr = area->vm->addr;
+ return area->vm_addr + off;
+}
+
+static inline void __zs_unmap_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ unsigned long addr = (unsigned long)area->vm_addr;
+
+ unmap_kernel_range(addr, PAGE_SIZE * 2);
+}
+
+#else /* CONFIG_PGTABLE_MAPPING */
+
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+ /*
+ * Make sure we don't leak memory if a cpu UP notification
+ * and zs_init() race and both call zs_cpu_up() on the same cpu
+ */
+ if (area->vm_buf)
+ return 0;
+ area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL);
+ if (!area->vm_buf)
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+ kfree(area->vm_buf);
+ area->vm_buf = NULL;
+}
+
+static void *__zs_map_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ int sizes[2];
+ void *addr;
+ char *buf = area->vm_buf;
+
+ /* disable page faults to match kmap_atomic() return conditions */
+ pagefault_disable();
+
+ /* no read fastpath */
+ if (area->vm_mm == ZS_MM_WO)
+ goto out;
+
+ sizes[0] = PAGE_SIZE - off;
+ sizes[1] = size - sizes[0];
+
+ /* copy object to per-cpu buffer */
+ addr = kmap_atomic(pages[0]);
+ memcpy(buf, addr + off, sizes[0]);
+ kunmap_atomic(addr);
+ addr = kmap_atomic(pages[1]);
+ memcpy(buf + sizes[0], addr, sizes[1]);
+ kunmap_atomic(addr);
+out:
+ return area->vm_buf;
+}
+
+static void __zs_unmap_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ int sizes[2];
+ void *addr;
+ char *buf;
+
+ /* no write fastpath */
+ if (area->vm_mm == ZS_MM_RO)
+ goto out;
+
+ buf = area->vm_buf;
+ if (!area->huge) {
+ buf = buf + ZS_HANDLE_SIZE;
+ size -= ZS_HANDLE_SIZE;
+ off += ZS_HANDLE_SIZE;
+ }
+
+ sizes[0] = PAGE_SIZE - off;
+ sizes[1] = size - sizes[0];
+
+ /* copy per-cpu buffer to object */
+ addr = kmap_atomic(pages[0]);
+ memcpy(addr + off, buf, sizes[0]);
+ kunmap_atomic(addr);
+ addr = kmap_atomic(pages[1]);
+ memcpy(addr, buf + sizes[0], sizes[1]);
+ kunmap_atomic(addr);
+
+out:
+ /* enable page faults to match kunmap_atomic() return conditions */
+ pagefault_enable();
+}
+
+#endif /* CONFIG_PGTABLE_MAPPING */
+
+static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
+ void *pcpu)
+{
+ int ret, cpu = (long)pcpu;
+ struct mapping_area *area;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ area = &per_cpu(zs_map_area, cpu);
+ ret = __zs_cpu_up(area);
+ if (ret)
+ return notifier_from_errno(ret);
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ area = &per_cpu(zs_map_area, cpu);
+ __zs_cpu_down(area);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block zs_cpu_nb = {
+ .notifier_call = zs_cpu_notifier
+};
+
+static int zs_register_cpu_notifier(void)
+{
+ int cpu, uninitialized_var(ret);
+
+ cpu_notifier_register_begin();
+
+ __register_cpu_notifier(&zs_cpu_nb);
+ for_each_online_cpu(cpu) {
+ ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+ if (notifier_to_errno(ret))
+ break;
+ }
+
+ cpu_notifier_register_done();
+ return notifier_to_errno(ret);
+}
+
+static void zs_unregister_cpu_notifier(void)
+{
+ int cpu;
+
+ cpu_notifier_register_begin();
+
+ for_each_online_cpu(cpu)
+ zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
+ __unregister_cpu_notifier(&zs_cpu_nb);
+
+ cpu_notifier_register_done();
+}
+
+static void init_zs_size_classes(void)
+{
+ int nr;
+
+ nr = (ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / ZS_SIZE_CLASS_DELTA + 1;
+ if ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) % ZS_SIZE_CLASS_DELTA)
+ nr += 1;
+
+ zs_size_classes = nr;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+ if (prev->pages_per_zspage != pages_per_zspage)
+ return false;
+
+ if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+ != get_maxobj_per_zspage(size, pages_per_zspage))
+ return false;
+
+ return true;
+}
+
+static bool zspage_full(struct page *page)
+{
+ BUG_ON(!is_first_page(page));
+
+ return page->inuse == page->objects;
+}
+
+unsigned long zs_get_total_pages(struct zs_pool *pool)
+{
+ return atomic_long_read(&pool->pages_allocated);
+}
+EXPORT_SYMBOL_GPL(zs_get_total_pages);
+
+/**
+ * zs_map_object - get address of allocated object from handle.
+ * @pool: pool from which the object was allocated
+ * @handle: handle returned from zs_malloc
+ *
+ * Before using an object allocated from zs_malloc, it must be mapped using
+ * this function. When done with the object, it must be unmapped using
+ * zs_unmap_object.
+ *
+ * Only one object can be mapped per cpu at a time. There is no protection
+ * against nested mappings.
+ *
+ * This function returns with preemption and page faults disabled.
+ */
+void *zs_map_object(struct zs_pool *pool, unsigned long handle,
+ enum zs_mapmode mm)
+{
+ struct page *page;
+ unsigned long obj, obj_idx, off;
+
+ unsigned int class_idx;
+ enum fullness_group fg;
+ struct size_class *class;
+ struct mapping_area *area;
+ struct page *pages[2];
+ void *ret;
+
+ BUG_ON(!handle);
+
+ /*
+ * Because we use per-cpu mapping areas shared among the
+ * pools/users, we can't allow mapping in interrupt context
+ * because it can corrupt another users mappings.
+ */
+ BUG_ON(in_interrupt());
+
+ /* From now on, migration cannot move the object */
+ pin_tag(handle);
+
+ obj = handle_to_obj(handle);
+ obj_to_location(obj, &page, &obj_idx);
+ get_zspage_mapping(get_first_page(page), &class_idx, &fg);
+ class = pool->size_class[class_idx];
+ off = obj_idx_to_offset(page, obj_idx, class->size);
+
+ area = &get_cpu_var(zs_map_area);
+ area->vm_mm = mm;
+ if (off + class->size <= PAGE_SIZE) {
+ /* this object is contained entirely within a page */
+ area->vm_addr = kmap_atomic(page);
+ ret = area->vm_addr + off;
+ goto out;
+ }
+
+ /* this object spans two pages */
+ pages[0] = page;
+ pages[1] = get_next_page(page);
+ BUG_ON(!pages[1]);
+
+ ret = __zs_map_object(area, pages, off, class->size);
+out:
+ if (!class->huge)
+ ret += ZS_HANDLE_SIZE;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(zs_map_object);
+
+void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
+{
+ struct page *page;
+ unsigned long obj, obj_idx, off;
+
+ unsigned int class_idx;
+ enum fullness_group fg;
+ struct size_class *class;
+ struct mapping_area *area;
+
+ BUG_ON(!handle);
+
+ obj = handle_to_obj(handle);
+ obj_to_location(obj, &page, &obj_idx);
+ get_zspage_mapping(get_first_page(page), &class_idx, &fg);
+ class = pool->size_class[class_idx];
+ off = obj_idx_to_offset(page, obj_idx, class->size);
+
+ area = this_cpu_ptr(&zs_map_area);
+ if (off + class->size <= PAGE_SIZE)
+ kunmap_atomic(area->vm_addr);
+ else {
+ struct page *pages[2];
+
+ pages[0] = page;
+ pages[1] = get_next_page(page);
+ BUG_ON(!pages[1]);
+
+ __zs_unmap_object(area, pages, off, class->size);
+ }
+ put_cpu_var(zs_map_area);
+ unpin_tag(handle);
+}
+EXPORT_SYMBOL_GPL(zs_unmap_object);
+
+static unsigned long obj_malloc(struct page *first_page,
+ struct size_class *class, unsigned long handle)
+{
+ unsigned long obj;
+ struct link_free *link;
+
+ struct page *m_page;
+ unsigned long m_objidx, m_offset;
+ void *vaddr;
+
+ handle |= OBJ_ALLOCATED_TAG;
+ obj = (unsigned long)first_page->freelist;
+ obj_to_location(obj, &m_page, &m_objidx);
+ m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
+
+ vaddr = kmap_atomic(m_page);
+ link = (struct link_free *)vaddr + m_offset / sizeof(*link);
+ first_page->freelist = link->next;
+ if (!class->huge)
+ /* record handle in the header of allocated chunk */
+ link->handle = handle;
+ else
+ /* record handle in first_page->private */
+ set_page_private(first_page, handle);
+ kunmap_atomic(vaddr);
+ first_page->inuse++;
+ zs_stat_inc(class, OBJ_USED, 1);
+
+ return obj;
+}
+
+
+/**
+ * zs_malloc - Allocate block of given size from pool.
+ * @pool: pool to allocate from
+ * @size: size of block to allocate
+ *
+ * On success, handle to the allocated object is returned,
+ * otherwise 0.
+ * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
+ */
+unsigned long zs_malloc(struct zs_pool *pool, size_t size)
+{
+ unsigned long handle, obj;
+ struct size_class *class;
+ struct page *first_page;
+
+ if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
+ return 0;
+
+ handle = alloc_handle(pool);
+ if (!handle)
+ return 0;
+
+ /* extra space in chunk to keep the handle */
+ size += ZS_HANDLE_SIZE;
+ class = pool->size_class[get_size_class_index(size)];
+
+ spin_lock(&class->lock);
+ first_page = find_get_zspage(class);
+
+ if (!first_page) {
+ spin_unlock(&class->lock);
+ first_page = alloc_zspage(class, pool->flags);
+ if (unlikely(!first_page)) {
+ free_handle(pool, handle);
+ return 0;
+ }
+
+ set_zspage_mapping(first_page, class->index, ZS_EMPTY);
+ atomic_long_add(class->pages_per_zspage,
+ &pool->pages_allocated);
+
+ spin_lock(&class->lock);
+ zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+ class->size, class->pages_per_zspage));
+ }
+
+ obj = obj_malloc(first_page, class, handle);
+ /* Now move the zspage to another fullness group, if required */
+ fix_fullness_group(class, first_page);
+ record_obj(handle, obj);
+ spin_unlock(&class->lock);
+
+ return handle;
+}
+EXPORT_SYMBOL_GPL(zs_malloc);
+
+static void obj_free(struct zs_pool *pool, struct size_class *class,
+ unsigned long obj)
+{
+ struct link_free *link;
+ struct page *first_page, *f_page;
+ unsigned long f_objidx, f_offset;
+ void *vaddr;
+ int class_idx;
+ enum fullness_group fullness;
+
+ BUG_ON(!obj);
+
+ obj &= ~OBJ_ALLOCATED_TAG;
+ obj_to_location(obj, &f_page, &f_objidx);
+ first_page = get_first_page(f_page);
+
+ get_zspage_mapping(first_page, &class_idx, &fullness);
+ f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
+
+ vaddr = kmap_atomic(f_page);
+
+ /* Insert this object in containing zspage's freelist */
+ link = (struct link_free *)(vaddr + f_offset);
+ link->next = first_page->freelist;
+ if (class->huge)
+ set_page_private(first_page, 0);
+ kunmap_atomic(vaddr);
+ first_page->freelist = (void *)obj;
+ first_page->inuse--;
+ zs_stat_dec(class, OBJ_USED, 1);
+}
+
+void zs_free(struct zs_pool *pool, unsigned long handle)
+{
+ struct page *first_page, *f_page;
+ unsigned long obj, f_objidx;
+ int class_idx;
+ struct size_class *class;
+ enum fullness_group fullness;
+
+ if (unlikely(!handle))
+ return;
+
+ pin_tag(handle);
+ obj = handle_to_obj(handle);
+ obj_to_location(obj, &f_page, &f_objidx);
+ first_page = get_first_page(f_page);
+
+ get_zspage_mapping(first_page, &class_idx, &fullness);
+ class = pool->size_class[class_idx];
+
+ spin_lock(&class->lock);
+ obj_free(pool, class, obj);
+ fullness = fix_fullness_group(class, first_page);
+ if (fullness == ZS_EMPTY) {
+ zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+ class->size, class->pages_per_zspage));
+ atomic_long_sub(class->pages_per_zspage,
+ &pool->pages_allocated);
+ free_zspage(first_page);
+ }
+ spin_unlock(&class->lock);
+ unpin_tag(handle);
+
+ free_handle(pool, handle);
+}
+EXPORT_SYMBOL_GPL(zs_free);
+
+static void zs_object_copy(unsigned long src, unsigned long dst,
+ struct size_class *class)
+{
+ struct page *s_page, *d_page;
+ unsigned long s_objidx, d_objidx;
+ unsigned long s_off, d_off;
+ void *s_addr, *d_addr;
+ int s_size, d_size, size;
+ int written = 0;
+
+ s_size = d_size = class->size;
+
+ obj_to_location(src, &s_page, &s_objidx);
+ obj_to_location(dst, &d_page, &d_objidx);
+
+ s_off = obj_idx_to_offset(s_page, s_objidx, class->size);
+ d_off = obj_idx_to_offset(d_page, d_objidx, class->size);
+
+ if (s_off + class->size > PAGE_SIZE)
+ s_size = PAGE_SIZE - s_off;
+
+ if (d_off + class->size > PAGE_SIZE)
+ d_size = PAGE_SIZE - d_off;
+
+ s_addr = kmap_atomic(s_page);
+ d_addr = kmap_atomic(d_page);
+
+ while (1) {
+ size = min(s_size, d_size);
+ memcpy(d_addr + d_off, s_addr + s_off, size);
+ written += size;
+
+ if (written == class->size)
+ break;
+
+ s_off += size;
+ s_size -= size;
+ d_off += size;
+ d_size -= size;
+
+ if (s_off >= PAGE_SIZE) {
+ kunmap_atomic(d_addr);
+ kunmap_atomic(s_addr);
+ s_page = get_next_page(s_page);
+ BUG_ON(!s_page);
+ s_addr = kmap_atomic(s_page);
+ d_addr = kmap_atomic(d_page);
+ s_size = class->size - written;
+ s_off = 0;
+ }
+
+ if (d_off >= PAGE_SIZE) {
+ kunmap_atomic(d_addr);
+ d_page = get_next_page(d_page);
+ BUG_ON(!d_page);
+ d_addr = kmap_atomic(d_page);
+ d_size = class->size - written;
+ d_off = 0;
+ }
+ }
+
+ kunmap_atomic(d_addr);
+ kunmap_atomic(s_addr);
+}
+
+/*
+ * Find alloced object in zspage from index object and
+ * return handle.
+ */
+static unsigned long find_alloced_obj(struct page *page, int index,
+ struct size_class *class)
+{
+ unsigned long head;
+ int offset = 0;
+ unsigned long handle = 0;
+ void *addr = kmap_atomic(page);
+
+ if (!is_first_page(page))
+ offset = page->index;
+ offset += class->size * index;
+
+ while (offset < PAGE_SIZE) {
+ head = obj_to_head(class, page, addr + offset);
+ if (head & OBJ_ALLOCATED_TAG) {
+ handle = head & ~OBJ_ALLOCATED_TAG;
+ if (trypin_tag(handle))
+ break;
+ handle = 0;
+ }
+
+ offset += class->size;
+ index++;
+ }
+
+ kunmap_atomic(addr);
+ return handle;
+}
+
+struct zs_compact_control {
+ /* Source page for migration which could be a subpage of zspage. */
+ struct page *s_page;
+ /* Destination page for migration which should be a first page
+ * of zspage. */
+ struct page *d_page;
+ /* Starting object index within @s_page which used for live object
+ * in the subpage. */
+ int index;
+ /* how many of objects are migrated */
+ int nr_migrated;
+};
+
+static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
+ struct zs_compact_control *cc)
+{
+ unsigned long used_obj, free_obj;
+ unsigned long handle;
+ struct page *s_page = cc->s_page;
+ struct page *d_page = cc->d_page;
+ unsigned long index = cc->index;
+ int nr_migrated = 0;
+ int ret = 0;
+
+ while (1) {
+ handle = find_alloced_obj(s_page, index, class);
+ if (!handle) {
+ s_page = get_next_page(s_page);
+ if (!s_page)
+ break;
+ index = 0;
+ continue;
+ }
+
+ /* Stop if there is no more space */
+ if (zspage_full(d_page)) {
+ unpin_tag(handle);
+ ret = -ENOMEM;
+ break;
+ }
+
+ used_obj = handle_to_obj(handle);
+ free_obj = obj_malloc(d_page, class, handle);
+ zs_object_copy(used_obj, free_obj, class);
+ index++;
+ record_obj(handle, free_obj);
+ unpin_tag(handle);
+ obj_free(pool, class, used_obj);
+ nr_migrated++;
+ }
+
+ /* Remember last position in this iteration */
+ cc->s_page = s_page;
+ cc->index = index;
+ cc->nr_migrated = nr_migrated;
+
+ return ret;
+}
+
+static struct page *alloc_target_page(struct size_class *class)
+{
+ int i;
+ struct page *page;
+
+ for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
+ page = class->fullness_list[i];
+ if (page) {
+ remove_zspage(page, class, i);
+ break;
+ }
+ }
+
+ return page;
+}
+
+static void putback_zspage(struct zs_pool *pool, struct size_class *class,
+ struct page *first_page)
+{
+ enum fullness_group fullness;
+
+ BUG_ON(!is_first_page(first_page));
+
+ fullness = get_fullness_group(first_page);
+ insert_zspage(first_page, class, fullness);
+ set_zspage_mapping(first_page, class->index, fullness);
+
+ if (fullness == ZS_EMPTY) {
+ zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage(
+ class->size, class->pages_per_zspage));
+ atomic_long_sub(class->pages_per_zspage,
+ &pool->pages_allocated);
+
+ free_zspage(first_page);
+ }
+}
+
+static struct page *isolate_source_page(struct size_class *class)
+{
+ struct page *page;
+
+ page = class->fullness_list[ZS_ALMOST_EMPTY];
+ if (page)
+ remove_zspage(page, class, ZS_ALMOST_EMPTY);
+
+ return page;
+}
+
+static unsigned long __zs_compact(struct zs_pool *pool,
+ struct size_class *class)
+{
+ int nr_to_migrate;
+ struct zs_compact_control cc;
+ struct page *src_page;
+ struct page *dst_page = NULL;
+ unsigned long nr_total_migrated = 0;
+
+ spin_lock(&class->lock);
+ while ((src_page = isolate_source_page(class))) {
+
+ BUG_ON(!is_first_page(src_page));
+
+ /* The goal is to migrate all live objects in source page */
+ nr_to_migrate = src_page->inuse;
+ cc.index = 0;
+ cc.s_page = src_page;
+
+ while ((dst_page = alloc_target_page(class))) {
+ cc.d_page = dst_page;
+ /*
+ * If there is no more space in dst_page, try to
+ * allocate another zspage.
+ */
+ if (!migrate_zspage(pool, class, &cc))
+ break;
+
+ putback_zspage(pool, class, dst_page);
+ nr_total_migrated += cc.nr_migrated;
+ nr_to_migrate -= cc.nr_migrated;
+ }
+
+ /* Stop if we couldn't find slot */
+ if (dst_page == NULL)
+ break;
+
+ putback_zspage(pool, class, dst_page);
+ putback_zspage(pool, class, src_page);
+ spin_unlock(&class->lock);
+ nr_total_migrated += cc.nr_migrated;
+ cond_resched();
+ spin_lock(&class->lock);
+ }
+
+ if (src_page)
+ putback_zspage(pool, class, src_page);
+
+ spin_unlock(&class->lock);
+
+ return nr_total_migrated;
+}
+
+unsigned long zs_compact(struct zs_pool *pool)
+{
+ int i;
+ unsigned long nr_migrated = 0;
+ struct size_class *class;
+
+ for (i = zs_size_classes - 1; i >= 0; i--) {
+ class = pool->size_class[i];
+ if (!class)
+ continue;
+ if (class->index != i)
+ continue;
+ nr_migrated += __zs_compact(pool, class);
+ }
+
+ return nr_migrated;
+}
+EXPORT_SYMBOL_GPL(zs_compact);
+
+/**
+ * zs_create_pool - Creates an allocation pool to work from.
+ * @flags: allocation flags used to allocate pool metadata
+ *
+ * This function must be called before anything when using
+ * the zsmalloc allocator.
+ *
+ * On success, a pointer to the newly created pool is returned,
+ * otherwise NULL.
+ */
+struct zs_pool *zs_create_pool(char *name, gfp_t flags)
+{
+ int i;
+ struct zs_pool *pool;
+ struct size_class *prev_class = NULL;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return NULL;
+
+ pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *),
+ GFP_KERNEL);
+ if (!pool->size_class) {
+ kfree(pool);
+ return NULL;
+ }
+
+ pool->name = kstrdup(name, GFP_KERNEL);
+ if (!pool->name)
+ goto err;
+
+ if (create_handle_cache(pool))
+ goto err;
+
+ /*
+ * Iterate reversly, because, size of size_class that we want to use
+ * for merging should be larger or equal to current size.
+ */
+ for (i = zs_size_classes - 1; i >= 0; i--) {
+ int size;
+ int pages_per_zspage;
+ struct size_class *class;
+
+ size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
+ if (size > ZS_MAX_ALLOC_SIZE)
+ size = ZS_MAX_ALLOC_SIZE;
+ pages_per_zspage = get_pages_per_zspage(size);
+
+ /*
+ * size_class is used for normal zsmalloc operation such
+ * as alloc/free for that size. Although it is natural that we
+ * have one size_class for each size, there is a chance that we
+ * can get more memory utilization if we use one size_class for
+ * many different sizes whose size_class have same
+ * characteristics. So, we makes size_class point to
+ * previous size_class if possible.
+ */
+ if (prev_class) {
+ if (can_merge(prev_class, size, pages_per_zspage)) {
+ pool->size_class[i] = prev_class;
+ continue;
+ }
+ }
+
+ class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+ if (!class)
+ goto err;
+
+ class->size = size;
+ class->index = i;
+ class->pages_per_zspage = pages_per_zspage;
+ if (pages_per_zspage == 1 &&
+ get_maxobj_per_zspage(size, pages_per_zspage) == 1)
+ class->huge = true;
+ spin_lock_init(&class->lock);
+ pool->size_class[i] = class;
+
+ prev_class = class;
+ }
+
+ pool->flags = flags;
+
+ if (zs_pool_stat_create(name, pool))
+ goto err;
+
+ return pool;
+
+err:
+ zs_destroy_pool(pool);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(zs_create_pool);
+
+void zs_destroy_pool(struct zs_pool *pool)
+{
+ int i;
+
+ zs_pool_stat_destroy(pool);
+
+ for (i = 0; i < zs_size_classes; i++) {
+ int fg;
+ struct size_class *class = pool->size_class[i];
+
+ if (!class)
+ continue;
+
+ if (class->index != i)
+ continue;
+
+ for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
+ if (class->fullness_list[fg]) {
+ pr_info("Freeing non-empty class with size %db, fullness group %d\n",
+ class->size, fg);
+ }
+ }
+ kfree(class);
+ }
+
+ destroy_handle_cache(pool);
+ kfree(pool->size_class);
+ kfree(pool->name);
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(zs_destroy_pool);
+
+static int __init zs_init(void)
+{
+ int ret = zs_register_cpu_notifier();
+
+ if (ret)
+ goto notifier_fail;
+
+ init_zs_size_classes();
+
+#ifdef CONFIG_ZPOOL
+ zpool_register_driver(&zs_zpool_driver);
+#endif
+
+ ret = zs_stat_init();
+ if (ret) {
+ pr_err("zs stat initialization failed\n");
+ goto stat_fail;
+ }
+ return 0;
+
+stat_fail:
+#ifdef CONFIG_ZPOOL
+ zpool_unregister_driver(&zs_zpool_driver);
+#endif
+notifier_fail:
+ zs_unregister_cpu_notifier();
+
+ return ret;
+}
+
+static void __exit zs_exit(void)
+{
+#ifdef CONFIG_ZPOOL
+ zpool_unregister_driver(&zs_zpool_driver);
+#endif
+ zs_unregister_cpu_notifier();
+
+ zs_stat_exit();
+}
+
+module_init(zs_init);
+module_exit(zs_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
diff --git a/net/Kconfig b/net/Kconfig
index 2ddc904..c5e34cf 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -81,6 +81,20 @@
endif # if INET
+config ANDROID_PARANOID_NETWORK
+ bool "Only allow certain groups to create sockets"
+ default y
+ help
+ none
+
+config NET_ACTIVITY_STATS
+ bool "Network activity statistics tracking"
+ default y
+ help
+ Network activity statistics are useful for tracking wireless
+ modem activity on 2G, 3G, 4G wireless networks. Counts number of
+ transmissions and groups them in specified time buckets.
+
config NETWORK_SECMARK
bool "Security Marking"
help
@@ -220,7 +234,7 @@
source "net/netlink/Kconfig"
config RPS
- boolean
+ boolean "RPS"
depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
default y
diff --git a/net/Makefile b/net/Makefile
index 091e7b04..67d460a 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -70,3 +70,4 @@
obj-$(CONFIG_NFC) += nfc/
obj-$(CONFIG_OPENVSWITCH) += openvswitch/
obj-$(CONFIG_VSOCKETS) += vmw_vsock/
+obj-$(CONFIG_NET_ACTIVITY_STATS) += activity_stats.o
diff --git a/net/activity_stats.c b/net/activity_stats.c
new file mode 100644
index 0000000..4609ce2
--- /dev/null
+++ b/net/activity_stats.c
@@ -0,0 +1,119 @@
+/* net/activity_stats.c
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/suspend.h>
+#include <net/net_namespace.h>
+
+/*
+ * Track transmission rates in buckets (power of 2).
+ * 1,2,4,8...512 seconds.
+ *
+ * Buckets represent the count of network transmissions at least
+ * N seconds apart, where N is 1 << bucket index.
+ */
+#define BUCKET_MAX 10
+
+/* Track network activity frequency */
+static unsigned long activity_stats[BUCKET_MAX];
+static ktime_t last_transmit;
+static ktime_t suspend_time;
+static DEFINE_SPINLOCK(activity_lock);
+
+void activity_stats_update(void)
+{
+ int i;
+ unsigned long flags;
+ ktime_t now;
+ s64 delta;
+
+ spin_lock_irqsave(&activity_lock, flags);
+ now = ktime_get();
+ delta = ktime_to_ns(ktime_sub(now, last_transmit));
+
+ for (i = BUCKET_MAX - 1; i >= 0; i--) {
+ /*
+ * Check if the time delta between network activity is within the
+ * minimum bucket range.
+ */
+ if (delta < (1000000000ULL << i))
+ continue;
+
+ activity_stats[i]++;
+ last_transmit = now;
+ break;
+ }
+ spin_unlock_irqrestore(&activity_lock, flags);
+}
+
+static int activity_stats_show(struct seq_file *m, void *v)
+{
+ int i;
+ int ret;
+
+ seq_printf(m, "Min Bucket(sec) Count\n");
+
+ for (i = 0; i < BUCKET_MAX; i++) {
+ ret = seq_printf(m, "%15d %lu\n", 1 << i, activity_stats[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int activity_stats_notifier(struct notifier_block *nb,
+ unsigned long event, void *dummy)
+{
+ switch (event) {
+ case PM_SUSPEND_PREPARE:
+ suspend_time = ktime_get_real();
+ break;
+
+ case PM_POST_SUSPEND:
+ suspend_time = ktime_sub(ktime_get_real(), suspend_time);
+ last_transmit = ktime_sub(last_transmit, suspend_time);
+ }
+
+ return 0;
+}
+
+static int activity_stats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, activity_stats_show, PDE_DATA(inode));
+}
+
+static const struct file_operations activity_stats_fops = {
+ .open = activity_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static struct notifier_block activity_stats_notifier_block = {
+ .notifier_call = activity_stats_notifier,
+};
+
+static int __init activity_stats_init(void)
+{
+ proc_create("activity", S_IRUGO,
+ init_net.proc_net_stat, &activity_stats_fops);
+ return register_pm_notifier(&activity_stats_notifier_block);
+}
+
+subsys_initcall(activity_stats_init);
+
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 6629cdc..f7c3682 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -30,6 +30,11 @@
#include <net/bluetooth/bluetooth.h>
#include <linux/proc_fs.h>
+#ifndef CONFIG_BT_SOCK_DEBUG
+#undef BT_DBG
+#define BT_DBG(D...)
+#endif
+
#define VERSION "2.16"
/* Bluetooth sockets */
@@ -103,11 +108,40 @@
}
EXPORT_SYMBOL(bt_sock_unregister);
+#ifdef CONFIG_PARANOID_NETWORK
+static inline int current_has_bt_admin(void)
+{
+ return !current_euid();
+}
+
+static inline int current_has_bt(void)
+{
+ return current_has_bt_admin();
+}
+# else
+static inline int current_has_bt_admin(void)
+{
+ return 1;
+}
+
+static inline int current_has_bt(void)
+{
+ return 1;
+}
+#endif
+
static int bt_sock_create(struct net *net, struct socket *sock, int proto,
int kern)
{
int err;
+ if (proto == BTPROTO_RFCOMM || proto == BTPROTO_SCO ||
+ proto == BTPROTO_L2CAP) {
+ if (!current_has_bt())
+ return -EPERM;
+ } else if (!current_has_bt_admin())
+ return -EPERM;
+
if (net != &init_net)
return -EAFNOSUPPORT;
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index d459ed4..a3f3380 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -113,7 +113,7 @@
bdaddr_t *dst = mgr->l2cap_conn->dst;
struct hci_conn *hcon;
- hcon = hci_conn_add(hdev, AMP_LINK, dst);
+ hcon = hci_conn_add(hdev, AMP_LINK, 0, dst);
if (!hcon)
return NULL;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 8e7290a..c9b2d50 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -354,7 +354,8 @@
&conn->dst);
}
-struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
+struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type,
+ __u16 pkt_type, bdaddr_t *dst)
{
struct hci_conn *conn;
@@ -382,14 +383,22 @@
conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK;
break;
case SCO_LINK:
- if (lmp_esco_capable(hdev))
- conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
- (hdev->esco_type & EDR_ESCO_MASK);
- else
- conn->pkt_type = hdev->pkt_type & SCO_PTYPE_MASK;
- break;
+ if (!pkt_type)
+ pkt_type = SCO_ESCO_MASK;
case ESCO_LINK:
- conn->pkt_type = hdev->esco_type & ~EDR_ESCO_MASK;
+ if (!pkt_type)
+ pkt_type = ALL_ESCO_MASK;
+ if (lmp_esco_capable(hdev)) {
+ /* HCI Setup Synchronous Connection Command uses
+ reverse logic on the EDR_ESCO_MASK bits */
+ conn->pkt_type = (pkt_type ^ EDR_ESCO_MASK) &
+ hdev->esco_type;
+ } else {
+ /* Legacy HCI Add Sco Connection Command uses a
+ shifted bitmask */
+ conn->pkt_type = (pkt_type << 5) & hdev->pkt_type &
+ SCO_PTYPE_MASK;
+ }
break;
}
@@ -520,7 +529,7 @@
if (le)
return ERR_PTR(-EBUSY);
- le = hci_conn_add(hdev, LE_LINK, dst);
+ le = hci_conn_add(hdev, LE_LINK, 0, dst);
if (!le)
return ERR_PTR(-ENOMEM);
@@ -543,7 +552,7 @@
acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
if (!acl) {
- acl = hci_conn_add(hdev, ACL_LINK, dst);
+ acl = hci_conn_add(hdev, ACL_LINK, 0, dst);
if (!acl)
return ERR_PTR(-ENOMEM);
}
@@ -561,7 +570,8 @@
}
static struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type,
- bdaddr_t *dst, u8 sec_level, u8 auth_type)
+ __u16 pkt_type, bdaddr_t *dst,
+ u8 sec_level, u8 auth_type)
{
struct hci_conn *acl;
struct hci_conn *sco;
@@ -572,7 +582,7 @@
sco = hci_conn_hash_lookup_ba(hdev, type, dst);
if (!sco) {
- sco = hci_conn_add(hdev, type, dst);
+ sco = hci_conn_add(hdev, type, pkt_type, dst);
if (!sco) {
hci_conn_drop(acl);
return ERR_PTR(-ENOMEM);
@@ -602,7 +612,8 @@
}
/* Create SCO, ACL or LE connection. */
-struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst,
+struct hci_conn *hci_connect(struct hci_dev *hdev, int type,
+ __u16 pkt_type, bdaddr_t *dst,
__u8 dst_type, __u8 sec_level, __u8 auth_type)
{
BT_DBG("%s dst %pMR type 0x%x", hdev->name, dst, type);
@@ -614,7 +625,7 @@
return hci_connect_acl(hdev, dst, sec_level, auth_type);
case SCO_LINK:
case ESCO_LINK:
- return hci_connect_sco(hdev, type, dst, sec_level, auth_type);
+ return hci_connect_sco(hdev, type, pkt_type, dst, sec_level, auth_type);
}
return ERR_PTR(-EINVAL);
@@ -883,6 +894,15 @@
(ci + n)->out = c->out;
(ci + n)->state = c->state;
(ci + n)->link_mode = c->link_mode;
+ if (c->type == SCO_LINK) {
+ (ci + n)->mtu = hdev->sco_mtu;
+ (ci + n)->cnt = hdev->sco_cnt;
+ (ci + n)->pkts = hdev->sco_pkts;
+ } else {
+ (ci + n)->mtu = hdev->acl_mtu;
+ (ci + n)->cnt = hdev->acl_cnt;
+ (ci + n)->pkts = hdev->acl_pkts;
+ }
if (++n >= req.conn_num)
break;
}
@@ -919,6 +939,15 @@
ci.out = conn->out;
ci.state = conn->state;
ci.link_mode = conn->link_mode;
+ if (req.type == SCO_LINK) {
+ ci.mtu = hdev->sco_mtu;
+ ci.cnt = hdev->sco_cnt;
+ ci.pkts = hdev->sco_pkts;
+ } else {
+ ci.mtu = hdev->acl_mtu;
+ ci.cnt = hdev->acl_cnt;
+ ci.pkts = hdev->acl_pkts;
+ }
}
hci_dev_unlock(hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
old mode 100644
new mode 100755
index 5daf7ab..1526fb2
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1119,7 +1119,7 @@
}
} else {
if (!conn) {
- conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr);
+ conn = hci_conn_add(hdev, ACL_LINK, 0, &cp->bdaddr);
if (conn) {
conn->out = true;
conn->link_mode |= HCI_LM_MASTER;
@@ -1748,6 +1748,15 @@
hci_conn_check_pending(hdev);
}
+static inline bool is_sco_active(struct hci_dev *hdev)
+{
+ if (hci_conn_hash_lookup_state(hdev, SCO_LINK, BT_CONNECTED) ||
+ (hci_conn_hash_lookup_state(hdev, ESCO_LINK,
+ BT_CONNECTED)))
+ return true;
+ return false;
+}
+
static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
{
struct hci_ev_conn_request *ev = (void *) skb->data;
@@ -1775,7 +1784,8 @@
conn = hci_conn_hash_lookup_ba(hdev, ev->link_type,
&ev->bdaddr);
if (!conn) {
- conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr);
+ /* pkt_type not yet used for incoming connections */
+ conn = hci_conn_add(hdev, ev->link_type, 0, &ev->bdaddr);
if (!conn) {
BT_ERR("No memory for new connection");
hci_dev_unlock(hdev);
@@ -1794,7 +1804,8 @@
bacpy(&cp.bdaddr, &ev->bdaddr);
- if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER))
+ if (lmp_rswitch_capable(hdev) && ((mask & HCI_LM_MASTER)
+ || is_sco_active(hdev)))
cp.role = 0x00; /* Become master */
else
cp.role = 0x01; /* Remain slave */
@@ -2963,6 +2974,7 @@
hci_conn_add_sysfs(conn);
break;
+ case 0x10: /* Connection Accept Timeout */
case 0x11: /* Unsupported Feature or Parameter Value */
case 0x1c: /* SCO interval rejected */
case 0x1a: /* Unsupported Remote Feature */
@@ -3540,7 +3552,7 @@
conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
if (!conn) {
- conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr);
+ conn = hci_conn_add(hdev, LE_LINK, 0, &ev->bdaddr);
if (!conn) {
BT_ERR("No memory for new connection");
goto unlock;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 68843a2..c11a28b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1793,10 +1793,10 @@
auth_type = l2cap_get_auth_type(chan);
if (chan->dcid == L2CAP_CID_LE_DATA)
- hcon = hci_connect(hdev, LE_LINK, dst, dst_type,
+ hcon = hci_connect(hdev, LE_LINK, 0, dst, dst_type,
chan->sec_level, auth_type);
else
- hcon = hci_connect(hdev, ACL_LINK, dst, dst_type,
+ hcon = hci_connect(hdev, ACL_LINK, 0, dst, dst_type,
chan->sec_level, auth_type);
if (IS_ERR(hcon)) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 8208a13..3e57454 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2205,10 +2205,10 @@
auth_type = HCI_AT_DEDICATED_BONDING_MITM;
if (cp->addr.type == BDADDR_BREDR)
- conn = hci_connect(hdev, ACL_LINK, &cp->addr.bdaddr,
+ conn = hci_connect(hdev, ACL_LINK, 0, &cp->addr.bdaddr,
cp->addr.type, sec_level, auth_type);
else
- conn = hci_connect(hdev, LE_LINK, &cp->addr.bdaddr,
+ conn = hci_connect(hdev, LE_LINK, 0, &cp->addr.bdaddr,
cp->addr.type, sec_level, auth_type);
if (IS_ERR(conn)) {
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 19ba192..3ca5e40 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -436,7 +436,6 @@
switch (d->state) {
case BT_CONNECT:
- case BT_CONFIG:
if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
set_bit(RFCOMM_AUTH_REJECT, &d->flags);
rfcomm_schedule();
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 7ca014d..0daa100 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -328,15 +328,19 @@
static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
- struct sockaddr_rc *sa = (struct sockaddr_rc *) addr;
+ struct sockaddr_rc sa;
struct sock *sk = sock->sk;
- int err = 0;
-
- BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr);
+ int len, err = 0;
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ memset(&sa, 0, sizeof(sa));
+ len = min_t(unsigned int, sizeof(sa), addr_len);
+ memcpy(&sa, addr, len);
+
+ BT_DBG("sk %p %pMR", sk, &sa.rc_bdaddr);
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
@@ -351,12 +355,12 @@
write_lock(&rfcomm_sk_list.lock);
- if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) {
+ if (sa.rc_channel && __rfcomm_get_sock_by_addr(sa.rc_channel, &sa.rc_bdaddr)) {
err = -EADDRINUSE;
} else {
/* Save source address */
- bacpy(&bt_sk(sk)->src, &sa->rc_bdaddr);
- rfcomm_pi(sk)->channel = sa->rc_channel;
+ bacpy(&bt_sk(sk)->src, &sa.rc_bdaddr);
+ rfcomm_pi(sk)->channel = sa.rc_channel;
sk->sk_state = BT_BOUND;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index b586a32..de9c955 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -158,6 +158,7 @@
{
bdaddr_t *src = &bt_sk(sk)->src;
bdaddr_t *dst = &bt_sk(sk)->dst;
+ __u16 pkt_type = sco_pi(sk)->pkt_type;
struct sco_conn *conn;
struct hci_conn *hcon;
struct hci_dev *hdev;
@@ -173,11 +174,13 @@
if (lmp_esco_capable(hdev) && !disable_esco)
type = ESCO_LINK;
- else
+ else {
type = SCO_LINK;
+ pkt_type &= SCO_ESCO_MASK;
+ }
- hcon = hci_connect(hdev, type, dst, BDADDR_BREDR, BT_SECURITY_LOW,
- HCI_AT_NO_BONDING);
+ hcon = hci_connect(hdev, type, pkt_type, dst, BDADDR_BREDR,
+ BT_SECURITY_LOW, HCI_AT_NO_BONDING);
if (IS_ERR(hcon)) {
err = PTR_ERR(hcon);
goto done;
@@ -445,19 +448,20 @@
return 0;
}
-static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
{
- struct sockaddr_sco *sa = (struct sockaddr_sco *) addr;
+ struct sockaddr_sco sa;
struct sock *sk = sock->sk;
- int err = 0;
+ int len, err = 0;
- BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
+ BT_DBG("sk %p %pMR", sk, &sa.sco_bdaddr);
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
- if (addr_len < sizeof(struct sockaddr_sco))
- return -EINVAL;
+ memset(&sa, 0, sizeof(sa));
+ len = min_t(unsigned int, sizeof(sa), alen);
+ memcpy(&sa, addr, len);
lock_sock(sk);
@@ -471,7 +475,8 @@
goto done;
}
- bacpy(&bt_sk(sk)->src, &sa->sco_bdaddr);
+ bacpy(&bt_sk(sk)->src, &sa.sco_bdaddr);
+ sco_pi(sk)->pkt_type = sa.sco_pkt_type;
sk->sk_state = BT_BOUND;
@@ -482,26 +487,34 @@
static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
{
- struct sockaddr_sco *sa = (struct sockaddr_sco *) addr;
struct sock *sk = sock->sk;
- int err;
+ struct sockaddr_sco sa;
+ int len, err;
BT_DBG("sk %p", sk);
- if (alen < sizeof(struct sockaddr_sco) ||
- addr->sa_family != AF_BLUETOOTH)
+ if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
- if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND)
- return -EBADFD;
-
- if (sk->sk_type != SOCK_SEQPACKET)
- return -EINVAL;
+ memset(&sa, 0, sizeof(sa));
+ len = min_t(unsigned int, sizeof(sa), alen);
+ memcpy(&sa, addr, len);
lock_sock(sk);
+ if (sk->sk_type != SOCK_SEQPACKET) {
+ err = -EINVAL;
+ goto done;
+ }
+
+ if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+ err = -EBADFD;
+ goto done;
+ }
+
/* Set destination address and psm */
- bacpy(&bt_sk(sk)->dst, &sa->sco_bdaddr);
+ bacpy(&bt_sk(sk)->dst, &sa.sco_bdaddr);
+ sco_pi(sk)->pkt_type = sa.sco_pkt_type;
err = sco_connect(sk);
if (err)
@@ -625,6 +638,7 @@
bacpy(&sa->sco_bdaddr, &bt_sk(sk)->dst);
else
bacpy(&sa->sco_bdaddr, &bt_sk(sk)->src);
+ sa->sco_pkt_type = sco_pi(sk)->pkt_type;
return 0;
}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9673128..239e0e8 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -41,11 +41,6 @@
}
#endif
- u64_stats_update_begin(&brstats->syncp);
- brstats->tx_packets++;
- brstats->tx_bytes += skb->len;
- u64_stats_update_end(&brstats->syncp);
-
if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
goto out;
@@ -54,6 +49,12 @@
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
+ u64_stats_update_begin(&brstats->syncp);
+ brstats->tx_packets++;
+ /* Exclude ETH_HLEN from byte stats for consistency with Rx chain */
+ brstats->tx_bytes += skb->len;
+ u64_stats_update_end(&brstats->syncp);
+
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb);
else if (is_multicast_ether_addr(dest)) {
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 84340a2..ba1b50e 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,6 +31,8 @@
r->pref = pref;
r->table = table;
r->flags = flags;
+ r->uid_start = INVALID_UID;
+ r->uid_end = INVALID_UID;
r->fr_net = hold_net(ops->fro_net);
/* The lock is not required here, the list in unreacheable
@@ -179,6 +181,23 @@
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
+static inline kuid_t fib_nl_uid(struct nlattr *nla)
+{
+ return make_kuid(current_user_ns(), nla_get_u32(nla));
+}
+
+static int nla_put_uid(struct sk_buff *skb, int idx, kuid_t uid)
+{
+ return nla_put_u32(skb, idx, from_kuid_munged(current_user_ns(), uid));
+}
+
+static int fib_uid_range_match(struct flowi *fl, struct fib_rule *rule)
+{
+ return (!uid_valid(rule->uid_start) && !uid_valid(rule->uid_end)) ||
+ (uid_gte(fl->flowi_uid, rule->uid_start) &&
+ uid_lte(fl->flowi_uid, rule->uid_end));
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags)
{
@@ -193,6 +212,9 @@
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
goto out;
+ if (!fib_uid_range_match(fl, rule))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -363,6 +385,19 @@
} else if (rule->action == FR_ACT_GOTO)
goto errout_free;
+ /* UID start and end must either both be valid or both unspecified. */
+ rule->uid_start = rule->uid_end = INVALID_UID;
+ if (tb[FRA_UID_START] || tb[FRA_UID_END]) {
+ if (tb[FRA_UID_START] && tb[FRA_UID_END]) {
+ rule->uid_start = fib_nl_uid(tb[FRA_UID_START]);
+ rule->uid_end = fib_nl_uid(tb[FRA_UID_END]);
+ }
+ if (!uid_valid(rule->uid_start) ||
+ !uid_valid(rule->uid_end) ||
+ !uid_lte(rule->uid_start, rule->uid_end))
+ goto errout_free;
+ }
+
err = ops->configure(rule, skb, frh, tb);
if (err < 0)
goto errout_free;
@@ -469,6 +504,14 @@
(rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
continue;
+ if (tb[FRA_UID_START] &&
+ !uid_eq(rule->uid_start, fib_nl_uid(tb[FRA_UID_START])))
+ continue;
+
+ if (tb[FRA_UID_END] &&
+ !uid_eq(rule->uid_end, fib_nl_uid(tb[FRA_UID_END])))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -525,7 +568,9 @@
+ nla_total_size(4) /* FRA_PRIORITY */
+ nla_total_size(4) /* FRA_TABLE */
+ nla_total_size(4) /* FRA_FWMARK */
- + nla_total_size(4); /* FRA_FWMASK */
+ + nla_total_size(4) /* FRA_FWMASK */
+ + nla_total_size(4) /* FRA_UID_START */
+ + nla_total_size(4); /* FRA_UID_END */
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -579,7 +624,11 @@
((rule->mark_mask || rule->mark) &&
nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
(rule->target &&
- nla_put_u32(skb, FRA_GOTO, rule->target)))
+ nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+ (uid_valid(rule->uid_start) &&
+ nla_put_uid(skb, FRA_UID_START, rule->uid_start)) ||
+ (uid_valid(rule->uid_end) &&
+ nla_put_uid(skb, FRA_UID_END, rule->uid_end)))
goto nla_put_failure;
if (ops->fill(rule, skb, frh) < 0)
goto nla_put_failure;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b49e8ba..cdd7716 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -928,6 +928,7 @@
neigh->nud_state = NUD_PROBE;
neigh->updated = jiffies;
atomic_set(&neigh->probes, 0);
+ notify = 1;
next = now + neigh->parms->retrans_time;
}
} else {
@@ -1155,6 +1156,8 @@
if (new != old) {
neigh_del_timer(neigh);
+ if (new & NUD_PROBE)
+ atomic_set(&neigh->probes, 0);
if (new & NUD_IN_TIMER)
neigh_add_timer(neigh, (jiffies +
((new & NUD_REACHABLE) ?
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c38e7a2..3f78978 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -135,7 +135,7 @@
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
-static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
struct sock_diag_req *req = nlmsg_data(nlh);
@@ -155,8 +155,12 @@
hndl = sock_diag_handlers[req->sdiag_family];
if (hndl == NULL)
err = -ENOENT;
- else
+ else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
err = hndl->dump(skb, nlh);
+ else if (nlh->nlmsg_type == SOCK_DESTROY_BACKPORT && hndl->destroy)
+ err = hndl->destroy(skb, nlh);
+ else
+ err = -EOPNOTSUPP;
mutex_unlock(&sock_diag_table_mutex);
return err;
@@ -182,7 +186,8 @@
return ret;
case SOCK_DIAG_BY_FAMILY:
- return __sock_diag_rcv_msg(skb, nlh);
+ case SOCK_DESTROY_BACKPORT:
+ return __sock_diag_cmd(skb, nlh);
default:
return -EINVAL;
}
@@ -197,6 +202,18 @@
mutex_unlock(&sock_diag_mutex);
}
+int sock_diag_destroy(struct sock *sk, int err)
+{
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!sk->sk_prot->diag_destroy)
+ return -EOPNOTSUPP;
+
+ return sk->sk_prot->diag_destroy(sk, err);
+}
+EXPORT_SYMBOL_GPL(sock_diag_destroy);
+
static int __net_init diag_net_init(struct net *net)
{
struct netlink_kernel_cfg cfg = {
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6cf9f77..86eedba 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -235,7 +235,9 @@
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst)) {
@@ -252,7 +254,10 @@
&ireq6->loc_addr,
&ireq6->rmt_addr);
fl6.daddr = ireq6->rmt_addr;
- err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ rcu_read_lock();
+ err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -448,6 +453,7 @@
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
@@ -571,13 +577,15 @@
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
- if (np->opt != NULL)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt != NULL)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
@@ -829,6 +837,7 @@
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -931,7 +940,8 @@
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
if (IS_ERR(dst)) {
@@ -951,9 +961,8 @@
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt != NULL)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 8603ca8..0ee167c 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -433,6 +433,19 @@
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
+config INET_DIAG_DESTROY
+ bool "INET: allow privileged process to administratively close sockets"
+ depends on INET_DIAG
+ default n
+ ---help---
+ Provides a SOCK_DESTROY_BACKPORT operation that allows privileged processes
+ (e.g., a connection manager or a network administration tool such as
+ ss) to close sockets opened by other processes. Closing a socket in
+ this way interrupts any blocking read/write/connect operations on
+ the socket and causes future socket calls to behave as if the socket
+ had been disconnected.
+ If unsure, say N.
+
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 089cb9f..5a9af0a 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -15,6 +15,7 @@
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
+obj-$(CONFIG_SYSFS) += sysfs_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 975c369..14ad21e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -119,6 +119,19 @@
#include <linux/mroute.h>
#endif
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
@@ -284,6 +297,9 @@
int try_loading_module = 0;
int err;
+ if (!current_has_network())
+ return -EACCES;
+
if (unlikely(!inet_ehash_secret))
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
build_ehash_secret();
@@ -339,8 +355,7 @@
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
@@ -908,6 +923,7 @@
case SIOCSIFPFLAGS:
case SIOCGIFPFLAGS:
case SIOCSIFFLAGS:
+ case SIOCKILLADDR:
err = devinet_ioctl(net, cmd, (void __user *)arg);
break;
default:
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e40eef4..b151e0a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -59,6 +59,7 @@
#include <net/arp.h>
#include <net/ip.h>
+#include <net/tcp.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
@@ -918,6 +919,7 @@
case SIOCSIFBRDADDR: /* Set the broadcast address */
case SIOCSIFDSTADDR: /* Set the destination address */
case SIOCSIFNETMASK: /* Set the netmask for the interface */
+ case SIOCKILLADDR: /* Nuke all sockets on this address */
ret = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto out;
@@ -969,7 +971,8 @@
}
ret = -EADDRNOTAVAIL;
- if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
+ if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS
+ && cmd != SIOCKILLADDR)
goto done;
switch (cmd) {
@@ -1096,6 +1099,9 @@
inet_insert_ifa(ifa);
}
break;
+ case SIOCKILLADDR: /* Nuke all connections on this address */
+ ret = tcp_nuke_addr(net, (struct sockaddr *) sin);
+ break;
}
done:
rtnl_unlock();
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4556cd2..4a7cf03 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -250,7 +250,7 @@
bool dev_match;
fl4.flowi4_oif = 0;
- fl4.flowi4_iif = oif;
+ fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
fl4.daddr = src;
fl4.saddr = dst;
fl4.flowi4_tos = tos;
@@ -531,6 +531,7 @@
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index bc773a1..d00d8f9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -629,6 +629,7 @@
.daddr = nh->nh_gw,
.flowi4_scope = cfg->fc_scope + 1,
.flowi4_oif = nh->nh_oif,
+ .flowi4_iif = LOOPBACK_IFINDEX,
};
/* It is not necessary, but requires a bit of thinking */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ea78ef5..5af8781 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -337,6 +337,7 @@
struct sock *sk;
struct inet_sock *inet;
__be32 daddr, saddr;
+ u32 mark = IP4_REPLY_MARK(net, skb->mark);
if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
return;
@@ -349,6 +350,7 @@
icmp_param->data.icmph.checksum = 0;
inet->tos = ip_hdr(skb)->tos;
+ sk->sk_mark = mark;
daddr = ipc.addr = ip_hdr(skb)->saddr;
saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
@@ -361,6 +363,7 @@
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.saddr = saddr;
+ fl4.flowi4_mark = mark;
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
@@ -379,7 +382,7 @@
struct flowi4 *fl4,
struct sk_buff *skb_in,
const struct iphdr *iph,
- __be32 saddr, u8 tos,
+ __be32 saddr, u8 tos, u32 mark,
int type, int code,
struct icmp_bxm *param)
{
@@ -391,6 +394,7 @@
fl4->daddr = (param->replyopts.opt.opt.srr ?
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
+ fl4->flowi4_mark = mark;
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
@@ -488,6 +492,7 @@
struct flowi4 fl4;
__be32 saddr;
u8 tos;
+ u32 mark;
struct net *net;
struct sock *sk;
@@ -584,6 +589,7 @@
tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
+ mark = IP4_REPLY_MARK(net, skb_in->mark);
if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
goto out_unlock;
@@ -600,11 +606,12 @@
icmp_param.skb = skb_in;
icmp_param.offset = skb_network_offset(skb_in);
inet_sk(sk)->tos = tos;
+ sk->sk_mark = mark;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts.opt;
ipc.tx_flags = 0;
- rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
+ rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
type, code, &icmp_param);
if (IS_ERR(rt))
goto out_unlock;
@@ -937,7 +944,8 @@
void icmp_err(struct sk_buff *skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int offset = iph->ihl<<2;
+ struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
int type = icmp_hdr(skb)->type;
int code = icmp_hdr(skb)->code;
struct net *net = dev_net(skb->dev);
@@ -947,7 +955,7 @@
* triggered by ICMP_ECHOREPLY which sent from kernel.
*/
if (icmph->type != ICMP_ECHOREPLY) {
- ping_err(skb, info);
+ ping_err(skb, offset, info);
return;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6acb541..6dfec2f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -417,12 +417,13 @@
struct net *net = sock_net(sk);
int flags = inet_sk_flowi_flags(sk);
- flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol,
flags,
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+ ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
+ sock_i_uid(sk));
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -454,11 +455,12 @@
rcu_read_lock();
opt = rcu_dereference(newinet->inet_opt);
- flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+ ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport,
+ sock_i_uid(sk));
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -688,6 +690,8 @@
inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
newsk->sk_write_space = sk_stream_write_space;
+ newsk->sk_mark = inet_rsk(req)->ir_mark;
+
newicsk->icsk_retransmits = 0;
newicsk->icsk_backoff = 0;
newicsk->icsk_probes_out = 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 14a1ed6..a897652 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -304,15 +304,12 @@
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh);
}
-int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
- const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req)
+struct sock *inet_diag_find_one_icsk(struct net *net,
+ struct inet_hashinfo *hashinfo,
+ struct inet_diag_req_v2 *req)
{
- int err;
struct sock *sk;
- struct sk_buff *rep;
- struct net *net = sock_net(in_skb->sk);
- err = -EINVAL;
if (req->sdiag_family == AF_INET) {
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
@@ -320,25 +317,53 @@
}
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
- sk = inet6_lookup(net, hashinfo,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if);
+ if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+ sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
+ req->id.idiag_dport, req->id.idiag_src[3],
+ req->id.idiag_sport, req->id.idiag_if);
+ else
+ sk = inet6_lookup(net, hashinfo,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ req->id.idiag_if);
}
#endif
else {
- goto out_nosk;
+ return ERR_PTR(-EINVAL);
}
- err = -ENOENT;
- if (sk == NULL)
- goto out_nosk;
+ if (!sk)
+ return ERR_PTR(-ENOENT);
- err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
- if (err)
- goto out;
+ if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
+ /* NOTE: forward-ports should use sock_gen_put(sk) instead. */
+ if (sk->sk_state == TCP_TIME_WAIT)
+ inet_twsk_put((struct inet_timewait_sock *)sk);
+ else
+ sock_put(sk);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
+
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
+ struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct inet_diag_req_v2 *req)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *rep;
+ struct sock *sk;
+ int err;
+
+ sk = inet_diag_find_one_icsk(net, hashinfo, req);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
@@ -367,12 +392,11 @@
else
sock_put(sk);
}
-out_nosk:
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
-static int inet_diag_get_exact(struct sk_buff *in_skb,
+static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
struct inet_diag_req_v2 *req)
{
@@ -382,8 +406,12 @@
handler = inet_diag_lock_handler(req->sdiag_protocol);
if (IS_ERR(handler))
err = PTR_ERR(handler);
- else
+ else if (cmd == SOCK_DIAG_BY_FAMILY)
err = handler->dump_one(in_skb, nlh, req);
+ else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy)
+ err = handler->destroy(in_skb, req);
+ else
+ err = -EOPNOTSUPP;
inet_diag_unlock_handler(handler);
return err;
@@ -1083,7 +1111,7 @@
req.idiag_states = rc->idiag_states;
req.id = rc->id;
- return inet_diag_get_exact(in_skb, nlh, &req);
+ return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req);
}
static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -1117,7 +1145,7 @@
return inet_diag_get_exact_compat(skb, nlh);
}
-static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h)
{
int hdrlen = sizeof(struct inet_diag_req_v2);
struct net *net = sock_net(skb->sk);
@@ -1125,7 +1153,8 @@
if (nlmsg_len(h) < hdrlen)
return -EINVAL;
- if (h->nlmsg_flags & NLM_F_DUMP) {
+ if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY &&
+ h->nlmsg_flags & NLM_F_DUMP) {
if (nlmsg_attrlen(h, hdrlen)) {
struct nlattr *attr;
attr = nlmsg_find_attr(h, hdrlen,
@@ -1143,17 +1172,19 @@
}
}
- return inet_diag_get_exact(skb, h, nlmsg_data(h));
+ return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h));
}
static const struct sock_diag_handler inet_diag_handler = {
.family = AF_INET,
- .dump = inet_diag_handler_dump,
+ .dump = inet_diag_handler_cmd,
+ .destroy = inet_diag_handler_cmd,
};
static const struct sock_diag_handler inet6_diag_handler = {
.family = AF_INET6,
- .dump = inet_diag_handler_dump,
+ .dump = inet_diag_handler_cmd,
+ .destroy = inet_diag_handler_cmd,
};
int inet_diag_register(const struct inet_diag_handler *h)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 57e7450..47d2361 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1482,12 +1482,14 @@
daddr = replyopts.opt.opt.faddr;
}
- flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+ flowi4_init_output(&fl4, arg->bound_dev_if,
+ IP4_REPLY_MARK(net, skb->mark),
RT_TOS(arg->tos),
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
daddr, saddr,
- tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+ arg->uid);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 89570f0..7562dcb 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -454,7 +454,7 @@
struct mr_table *mrt;
struct flowi4 fl4 = {
.flowi4_oif = dev->ifindex,
- .flowi4_iif = skb->skb_iif,
+ .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi4_mark = skb->mark,
};
int err;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index e7916c1..fcd5e8e 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -71,7 +71,8 @@
config IP_NF_MATCH_RPFILTER
tristate '"rpfilter" reverse path filter match support'
- depends on NETFILTER_ADVANCED && (IP_NF_MANGLE || IP_NF_RAW)
+ depends on NETFILTER_ADVANCED
+ depends on IP_NF_MANGLE || IP_NF_RAW
---help---
This option allows you to match packets whose replies would
go out via the interface the packet came in.
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index c49dcd0..4bfaedf 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -89,11 +89,8 @@
if (ipv4_is_multicast(iph->daddr)) {
if (ipv4_is_zeronet(iph->saddr))
return ipv4_is_local_multicast(iph->daddr) ^ invert;
- flow.flowi4_iif = 0;
- } else {
- flow.flowi4_iif = LOOPBACK_IFINDEX;
}
-
+ flow.flowi4_iif = LOOPBACK_IFINDEX;
flow.daddr = iph->saddr;
flow.saddr = rpfilter_get_saddr(iph->daddr);
flow.flowi4_oif = 0;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 459b957..ca222ea 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -33,7 +33,6 @@
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
-#include <net/ipv6.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
@@ -46,8 +45,18 @@
#include <net/inet_common.h>
#include <net/checksum.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
+#endif
-static struct ping_table ping_table;
+
+struct ping_table ping_table;
+struct pingv6_ops pingv6_ops;
+EXPORT_SYMBOL_GPL(pingv6_ops);
static u16 ping_port_rover;
@@ -58,6 +67,7 @@
pr_debug("hash(%d) = %d\n", num, res);
return res;
}
+EXPORT_SYMBOL_GPL(ping_hash);
static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
struct net *net, unsigned int num)
@@ -65,7 +75,7 @@
return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}
-static int ping_v4_get_port(struct sock *sk, unsigned short ident)
+int ping_get_port(struct sock *sk, unsigned short ident)
{
struct hlist_nulls_node *node;
struct hlist_nulls_head *hlist;
@@ -103,6 +113,10 @@
ping_portaddr_for_each_entry(sk2, node, hlist) {
isk2 = inet_sk(sk2);
+ /* BUG? Why is this reuse and not reuseaddr? ping.c
+ * doesn't turn off SO_REUSEADDR, and it doesn't expect
+ * that other ping processes can steal its packets.
+ */
if ((isk2->inet_num == ident) &&
(sk2 != sk) &&
(!sk2->sk_reuse || !sk->sk_reuse))
@@ -125,17 +139,18 @@
write_unlock_bh(&ping_table.lock);
return 1;
}
+EXPORT_SYMBOL_GPL(ping_get_port);
-static void ping_v4_hash(struct sock *sk)
+void ping_hash(struct sock *sk)
{
- pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
+ pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
BUG(); /* "Please do not press this button again." */
}
-static void ping_v4_unhash(struct sock *sk)
+void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
- pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
if (sk_hashed(sk)) {
write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
@@ -147,31 +162,63 @@
write_unlock_bh(&ping_table.lock);
}
}
+EXPORT_SYMBOL_GPL(ping_unhash);
-static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr,
- u16 ident, int dif)
+static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
struct sock *sk = NULL;
struct inet_sock *isk;
struct hlist_nulls_node *hnode;
+ int dif = skb->dev->ifindex;
- pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
- (int)ident, &daddr, dif);
+ if (skb->protocol == htons(ETH_P_IP)) {
+ pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
+ (int)ident, &ip_hdr(skb)->daddr, dif);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
+ (int)ident, &ipv6_hdr(skb)->daddr, dif);
+#endif
+ }
+
read_lock_bh(&ping_table.lock);
ping_portaddr_for_each_entry(sk, hnode, hslot) {
isk = inet_sk(sk);
- pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk,
- (int)isk->inet_num, &isk->inet_rcv_saddr,
- sk->sk_bound_dev_if);
-
pr_debug("iterate\n");
if (isk->inet_num != ident)
continue;
- if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr)
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ sk->sk_family == AF_INET) {
+ pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
+ (int) isk->inet_num, &isk->inet_rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (isk->inet_rcv_saddr &&
+ isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
+ continue;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6) &&
+ sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
+ (int) isk->inet_num,
+ &inet6_sk(sk)->rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (!ipv6_addr_any(&np->rcv_saddr) &&
+ !ipv6_addr_equal(&np->rcv_saddr,
+ &ipv6_hdr(skb)->daddr))
+ continue;
+#endif
+ } else {
continue;
+ }
+
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
continue;
@@ -201,7 +248,7 @@
}
-static int ping_init_sock(struct sock *sk)
+int ping_init_sock(struct sock *sk)
{
struct net *net = sock_net(sk);
kgid_t group = current_egid();
@@ -210,6 +257,9 @@
kgid_t low, high;
int ret = 0;
+ if (sk->sk_family == AF_INET6)
+ inet6_sk(sk)->ipv6only = 1;
+
inet_get_ping_group_range_net(net, &low, &high);
if (gid_lte(low, group) && gid_lte(group, high))
return 0;
@@ -233,8 +283,9 @@
put_group_info(group_info);
return ret;
}
+EXPORT_SYMBOL_GPL(ping_init_sock);
-static void ping_close(struct sock *sk, long timeout)
+void ping_close(struct sock *sk, long timeout)
{
pr_debug("ping_close(sk=%p,sk->num=%u)\n",
inet_sk(sk), inet_sk(sk)->inet_num);
@@ -242,36 +293,130 @@
sk_common_release(sk);
}
+EXPORT_SYMBOL_GPL(ping_close);
+/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
+int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
+ struct sockaddr *uaddr, int addr_len) {
+ struct net *net = sock_net(sk);
+ if (sk->sk_family == AF_INET) {
+ struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ int chk_addr_ret;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ if (addr->sin_family != AF_INET &&
+ !(addr->sin_family == AF_UNSPEC &&
+ addr->sin_addr.s_addr == htonl(INADDR_ANY)))
+ return -EAFNOSUPPORT;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
+ sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
+
+ chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+
+ if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+ chk_addr_ret = RTN_LOCAL;
+
+ if ((sysctl_ip_nonlocal_bind == 0 &&
+ isk->freebind == 0 && isk->transparent == 0 &&
+ chk_addr_ret != RTN_LOCAL) ||
+ chk_addr_ret == RTN_MULTICAST ||
+ chk_addr_ret == RTN_BROADCAST)
+ return -EADDRNOTAVAIL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
+ int addr_type, scoped, has_addr;
+ struct net_device *dev = NULL;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ if (addr->sin6_family != AF_INET6)
+ return -EAFNOSUPPORT;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
+ sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
+
+ addr_type = ipv6_addr_type(&addr->sin6_addr);
+ scoped = __ipv6_addr_needs_scope_id(addr_type);
+ if ((addr_type != IPV6_ADDR_ANY &&
+ !(addr_type & IPV6_ADDR_UNICAST)) ||
+ (scoped && !addr->sin6_scope_id))
+ return -EINVAL;
+
+ rcu_read_lock();
+ if (addr->sin6_scope_id) {
+ dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+ }
+ has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
+ scoped);
+ rcu_read_unlock();
+
+ if (!(isk->freebind || isk->transparent || has_addr ||
+ addr_type == IPV6_ADDR_ANY))
+ return -EADDRNOTAVAIL;
+
+ if (scoped)
+ sk->sk_bound_dev_if = addr->sin6_scope_id;
+#endif
+ } else {
+ return -EAFNOSUPPORT;
+ }
+ return 0;
+}
+
+void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
+{
+ if (saddr->sa_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
+ isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (saddr->sa_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ np->rcv_saddr = np->saddr = addr->sin6_addr;
+#endif
+ }
+}
+
+void ping_clear_saddr(struct sock *sk, int dif)
+{
+ sk->sk_bound_dev_if = dif;
+ if (sk->sk_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ isk->inet_rcv_saddr = isk->inet_saddr = 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+ memset(&np->saddr, 0, sizeof(np->saddr));
+#endif
+ }
+}
/*
* We need our own bind because there are no privileged id's == local ports.
* Moreover, we don't allow binding to multi- and broadcast addresses.
*/
-static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct inet_sock *isk = inet_sk(sk);
unsigned short snum;
- int chk_addr_ret;
int err;
+ int dif = sk->sk_bound_dev_if;
- if (addr_len < sizeof(struct sockaddr_in))
- return -EINVAL;
-
- pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n",
- sk, addr->sin_addr.s_addr, ntohs(addr->sin_port));
-
- chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
- if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
- chk_addr_ret = RTN_LOCAL;
-
- if ((sysctl_ip_nonlocal_bind == 0 &&
- isk->freebind == 0 && isk->transparent == 0 &&
- chk_addr_ret != RTN_LOCAL) ||
- chk_addr_ret == RTN_MULTICAST ||
- chk_addr_ret == RTN_BROADCAST)
- return -EADDRNOTAVAIL;
+ err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
+ if (err)
+ return err;
lock_sock(sk);
@@ -280,42 +425,50 @@
goto out;
err = -EADDRINUSE;
- isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
- snum = ntohs(addr->sin_port);
- if (ping_v4_get_port(sk, snum) != 0) {
- isk->inet_saddr = isk->inet_rcv_saddr = 0;
+ ping_set_saddr(sk, uaddr);
+ snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
+ if (ping_get_port(sk, snum) != 0) {
+ ping_clear_saddr(sk, dif);
goto out;
}
- pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n",
+ pr_debug("after bind(): num = %d, dif = %d\n",
(int)isk->inet_num,
- &isk->inet_rcv_saddr,
(int)sk->sk_bound_dev_if);
err = 0;
- if (isk->inet_rcv_saddr)
+ if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
+ (sk->sk_family == AF_INET6 &&
+ !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
isk->inet_sport = htons(isk->inet_num);
isk->inet_daddr = 0;
isk->inet_dport = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6)
+ memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+#endif
+
sk_dst_reset(sk);
out:
release_sock(sk);
pr_debug("ping_v4_bind -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_bind);
/*
* Is this a supported type of ICMP message?
*/
-static inline int ping_supported(int type, int code)
+static inline int ping_supported(int family, int type, int code)
{
- if (type == ICMP_ECHO && code == 0)
- return 1;
- return 0;
+ return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
+ (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
}
/*
@@ -323,30 +476,42 @@
* sort of error condition.
*/
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-
-void ping_err(struct sk_buff *skb, u32 info)
+void ping_err(struct sk_buff *skb, int offset, u32 info)
{
- struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int family;
+ struct icmphdr *icmph;
struct inet_sock *inet_sock;
- int type = icmp_hdr(skb)->type;
- int code = icmp_hdr(skb)->code;
+ int type;
+ int code;
struct net *net = dev_net(skb->dev);
struct sock *sk;
int harderr;
int err;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ family = AF_INET;
+ type = icmp_hdr(skb)->type;
+ code = icmp_hdr(skb)->code;
+ icmph = (struct icmphdr *)(skb->data + offset);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ family = AF_INET6;
+ type = icmp6_hdr(skb)->icmp6_type;
+ code = icmp6_hdr(skb)->icmp6_code;
+ icmph = (struct icmphdr *) (skb->data + offset);
+ } else {
+ BUG();
+ }
+
/* We assume the packet has already been checked by icmp_unreach */
- if (!ping_supported(icmph->type, icmph->code))
+ if (!ping_supported(family, icmph->type, icmph->code))
return;
- pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type,
- code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));
+ pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
+ skb->protocol, type, code, ntohs(icmph->un.echo.id),
+ ntohs(icmph->un.echo.sequence));
- sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
- ntohs(icmph->un.echo.id), skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk == NULL) {
pr_debug("no socket, dropping\n");
return; /* No socket for error */
@@ -357,72 +522,83 @@
harderr = 0;
inet_sock = inet_sk(sk);
- switch (type) {
- default:
- case ICMP_TIME_EXCEEDED:
- err = EHOSTUNREACH;
- break;
- case ICMP_SOURCE_QUENCH:
- /* This is not a real error but ping wants to see it.
- * Report it with some fake errno. */
- err = EREMOTEIO;
- break;
- case ICMP_PARAMETERPROB:
- err = EPROTO;
- harderr = 1;
- break;
- case ICMP_DEST_UNREACH:
- if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
- ipv4_sk_update_pmtu(skb, sk, info);
- if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
- err = EMSGSIZE;
- harderr = 1;
- break;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ switch (type) {
+ default:
+ case ICMP_TIME_EXCEEDED:
+ err = EHOSTUNREACH;
+ break;
+ case ICMP_SOURCE_QUENCH:
+ /* This is not a real error but ping wants to see it.
+ * Report it with some fake errno.
+ */
+ err = EREMOTEIO;
+ break;
+ case ICMP_PARAMETERPROB:
+ err = EPROTO;
+ harderr = 1;
+ break;
+ case ICMP_DEST_UNREACH:
+ if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
+ if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
+ err = EMSGSIZE;
+ harderr = 1;
+ break;
+ }
+ goto out;
}
- goto out;
+ err = EHOSTUNREACH;
+ if (code <= NR_ICMP_UNREACH) {
+ harderr = icmp_err_convert[code].fatal;
+ err = icmp_err_convert[code].errno;
+ }
+ break;
+ case ICMP_REDIRECT:
+ /* See ICMP_SOURCE_QUENCH */
+ ipv4_sk_redirect(skb, sk);
+ err = EREMOTEIO;
+ break;
}
- err = EHOSTUNREACH;
- if (code <= NR_ICMP_UNREACH) {
- harderr = icmp_err_convert[code].fatal;
- err = icmp_err_convert[code].errno;
- }
- break;
- case ICMP_REDIRECT:
- /* See ICMP_SOURCE_QUENCH */
- ipv4_sk_redirect(skb, sk);
- err = EREMOTEIO;
- break;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
+#endif
}
/*
* RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
- if (!inet_sock->recverr) {
+ if ((family == AF_INET && !inet_sock->recverr) ||
+ (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
- ip_icmp_error(sk, skb, err, 0 /* no remote port */,
- info, (u8 *)icmph);
+ if (family == AF_INET) {
+ ip_icmp_error(sk, skb, err, 0 /* no remote port */,
+ info, (u8 *)icmph);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
+ info, (u8 *)icmph);
+#endif
+ }
}
sk->sk_err = err;
sk->sk_error_report(sk);
out:
sock_put(sk);
}
+EXPORT_SYMBOL_GPL(ping_err);
/*
- * Copy and checksum an ICMP Echo packet from user space into a buffer.
+ * Copy and checksum an ICMP Echo packet from user space into a buffer
+ * starting from the payload.
*/
-struct pingfakehdr {
- struct icmphdr icmph;
- struct iovec *iov;
- __wsum wcheck;
-};
-
-static int ping_getfrag(void *from, char *to,
- int offset, int fraglen, int odd, struct sk_buff *skb)
+int ping_getfrag(void *from, char *to,
+ int offset, int fraglen, int odd, struct sk_buff *skb)
{
struct pingfakehdr *pfh = (struct pingfakehdr *)from;
@@ -433,20 +609,33 @@
pfh->iov, 0, fraglen - sizeof(struct icmphdr),
&pfh->wcheck))
return -EFAULT;
-
- return 0;
+ } else if (offset < sizeof(struct icmphdr)) {
+ BUG();
+ } else {
+ if (csum_partial_copy_fromiovecend
+ (to, pfh->iov, offset - sizeof(struct icmphdr),
+ fraglen, &pfh->wcheck))
+ return -EFAULT;
}
- if (offset < sizeof(struct icmphdr))
- BUG();
- if (csum_partial_copy_fromiovecend
- (to, pfh->iov, offset - sizeof(struct icmphdr),
- fraglen, &pfh->wcheck))
- return -EFAULT;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ /* For IPv6, checksum each skb as we go along, as expected by
+ * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
+ * wcheck, it will be finalized in ping_v4_push_pending_frames.
+ */
+ if (pfh->family == AF_INET6) {
+ skb->csum = pfh->wcheck;
+ skb->ip_summed = CHECKSUM_NONE;
+ pfh->wcheck = 0;
+ }
+#endif
+
return 0;
}
+EXPORT_SYMBOL_GPL(ping_getfrag);
-static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
- struct flowi4 *fl4)
+static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
+ struct flowi4 *fl4)
{
struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
@@ -458,24 +647,9 @@
return ip_push_pending_frames(sk, fl4);
}
-static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len)
-{
- struct net *net = sock_net(sk);
- struct flowi4 fl4;
- struct inet_sock *inet = inet_sk(sk);
- struct ipcm_cookie ipc;
- struct icmphdr user_icmph;
- struct pingfakehdr pfh;
- struct rtable *rt = NULL;
- struct ip_options_data opt_copy;
- int free = 0;
- __be32 saddr, daddr, faddr;
- u8 tos;
- int err;
-
- pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
-
+int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+ void *user_icmph, size_t icmph_len) {
+ u8 type, code;
if (len > 0xFFFF)
return -EMSGSIZE;
@@ -490,15 +664,53 @@
/*
* Fetch the ICMP header provided by the userland.
- * iovec is modified!
+ * iovec is modified! The ICMP header is consumed.
*/
-
- if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov,
- sizeof(struct icmphdr)))
+ if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
return -EFAULT;
- if (!ping_supported(user_icmph.type, user_icmph.code))
+
+ if (family == AF_INET) {
+ type = ((struct icmphdr *) user_icmph)->type;
+ code = ((struct icmphdr *) user_icmph)->code;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
+ code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
+#endif
+ } else {
+ BUG();
+ }
+
+ if (!ping_supported(family, type, code))
return -EINVAL;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ping_common_sendmsg);
+
+int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct net *net = sock_net(sk);
+ struct flowi4 fl4;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipcm_cookie ipc;
+ struct icmphdr user_icmph;
+ struct pingfakehdr pfh;
+ struct rtable *rt = NULL;
+ struct ip_options_data opt_copy;
+ int free = 0;
+ __be32 saddr, daddr, faddr;
+ u8 tos;
+ int err;
+
+ pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
/*
* Get and verify the address.
*/
@@ -508,7 +720,7 @@
if (msg->msg_namelen < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET)
- return -EINVAL;
+ return -EAFNOSUPPORT;
daddr = usin->sin_addr.s_addr;
/* no remote port */
} else {
@@ -570,7 +782,8 @@
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+ inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+ sock_i_uid(sk));
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
@@ -603,13 +816,14 @@
pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
pfh.iov = msg->msg_iov;
pfh.wcheck = 0;
+ pfh.family = AF_INET;
err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
0, &ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else
- err = ping_push_pending_frames(sk, &pfh, &fl4);
+ err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
release_sock(sk);
out:
@@ -630,10 +844,11 @@
goto out;
}
-static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len, int noblock, int flags, int *addr_len)
+int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *isk = inet_sk(sk);
+ int family = sk->sk_family;
struct sk_buff *skb;
int copied, err;
@@ -643,8 +858,16 @@
if (flags & MSG_OOB)
goto out;
- if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len, addr_len);
+ if (flags & MSG_ERRQUEUE) {
+ if (family == AF_INET) {
+ return ip_recv_error(sk, msg, len, addr_len);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ return pingv6_ops.ipv6_recv_error(sk, msg, len,
+ addr_len);
+#endif
+ }
+ }
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -663,18 +886,48 @@
sock_recv_timestamp(msg, sk, skb);
- /* Copy the address. */
- if (msg->msg_name) {
+ /* Copy the address and add cmsg data. */
+ if (family == AF_INET) {
struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
- sin->sin_family = AF_INET;
- sin->sin_port = 0 /* skb->h.uh->source */;
- sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
- memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
- *addr_len = sizeof(*sin);
+ if (sin) {
+ sin->sin_family = AF_INET;
+ sin->sin_port = 0 /* skb->h.uh->source */;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
+ memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
+ }
+
+ if (isk->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *ip6 = ipv6_hdr(skb);
+ struct sockaddr_in6 *sin6 =
+ (struct sockaddr_in6 *)msg->msg_name;
+
+ if (sin6) {
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = 0;
+ sin6->sin6_addr = ip6->saddr;
+ sin6->sin6_flowinfo = 0;
+ if (np->sndflow)
+ sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+ sin6->sin6_scope_id =
+ ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
+ *addr_len = sizeof(*sin6);
+ }
+
+ if (inet6_sk(sk)->rxopt.all)
+ pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
+#endif
+ } else {
+ BUG();
}
- if (isk->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+
err = copied;
done:
@@ -683,8 +936,9 @@
pr_debug("ping_recvmsg -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_recvmsg);
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
inet_sk(sk), inet_sk(sk)->inet_num, skb);
@@ -695,6 +949,7 @@
}
return 0;
}
+EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
/*
@@ -705,10 +960,7 @@
{
struct sock *sk;
struct net *net = dev_net(skb->dev);
- struct iphdr *iph = ip_hdr(skb);
struct icmphdr *icmph = icmp_hdr(skb);
- __be32 saddr = iph->saddr;
- __be32 daddr = iph->daddr;
/* We assume the packet has already been checked by icmp_rcv */
@@ -718,8 +970,7 @@
/* Push ICMP header back */
skb_push(skb, skb->data - (u8 *)icmph);
- sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id),
- skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk != NULL) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
@@ -733,6 +984,7 @@
/* We're called from icmp_rcv(). kfree_skb() is done there. */
}
+EXPORT_SYMBOL_GPL(ping_rcv);
struct proto ping_prot = {
.name = "PING",
@@ -743,14 +995,14 @@
.disconnect = udp_disconnect,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
- .sendmsg = ping_sendmsg,
+ .sendmsg = ping_v4_sendmsg,
.recvmsg = ping_recvmsg,
.bind = ping_bind,
.backlog_rcv = ping_queue_rcv_skb,
.release_cb = ip4_datagram_release_cb,
- .hash = ping_v4_hash,
- .unhash = ping_v4_unhash,
- .get_port = ping_v4_get_port,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
.obj_size = sizeof(struct inet_sock),
};
EXPORT_SYMBOL(ping_prot);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b4a1c42..b9c87c8 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -573,7 +573,8 @@
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP |
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
- daddr, saddr, 0, 0);
+ daddr, saddr, 0, 0,
+ sock_i_uid(sk));
if (!inet->hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 624ca8e..60d39fe 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -515,7 +515,7 @@
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(struct flowi4 *fl4, struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
@@ -531,11 +531,12 @@
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0,
+ sk ? sock_i_uid(sk) : 0);
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
- const struct sock *sk)
+ struct sock *sk)
{
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
@@ -546,7 +547,7 @@
__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
}
-static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
@@ -560,11 +561,12 @@
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0,
+ sock_i_uid(sk));
rcu_read_unlock();
}
-static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
const struct sk_buff *skb)
{
if (skb)
@@ -975,6 +977,9 @@
struct flowi4 fl4;
struct rtable *rt;
+ if (!mark)
+ mark = IP4_REPLY_MARK(net, skb->mark);
+
__build_flow_key(&fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
@@ -992,6 +997,10 @@
struct rtable *rt;
__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+ if (!fl4.flowi4_mark)
+ fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
+
rt = __ip_route_output_key(sock_net(sk), &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
@@ -2317,6 +2326,11 @@
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
@@ -2366,6 +2380,7 @@
int err;
int mark;
struct sk_buff *skb;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2393,6 +2408,10 @@
dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
@@ -2400,6 +2419,7 @@
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (iif) {
struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b05c96e..c94032b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -312,6 +312,7 @@
ireq->rmt_port = th->source;
ireq->loc_addr = ip_hdr(skb)->daddr;
ireq->rmt_addr = ip_hdr(skb)->saddr;
+ ireq->ir_mark = inet_request_mark(sk, skb);
ireq->ecn_ok = ecn_ok;
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
@@ -348,11 +349,12 @@
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
(opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
- ireq->loc_addr, th->source, th->dest);
+ ireq->loc_addr, th->source, th->dest,
+ sock_i_uid(sk));
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 90b26be..2c707a9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -138,6 +138,21 @@
return ret;
}
+/* Validate changes from /proc interface. */
+static int proc_tcp_default_init_rwnd(ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int old_value = *(int *)ctl->data;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
+
+ if (write && ret == 0 && (new_value < 3 || new_value > 100))
+ *(int *)ctl->data = old_value;
+
+ return ret;
+}
+
static int proc_tcp_congestion_control(ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -737,7 +752,7 @@
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
+ {
.procname = "tcp_thin_dupack",
.data = &sysctl_tcp_thin_dupack,
.maxlen = sizeof(int),
@@ -763,6 +778,13 @@
.extra2 = &gso_max_segs,
},
{
+ .procname = "tcp_default_init_rwnd",
+ .data = &sysctl_tcp_default_init_rwnd,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_default_init_rwnd
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
@@ -851,6 +873,20 @@
.mode = 0644,
.proc_handler = ipv4_tcp_mem,
},
+ {
+ .procname = "fwmark_reflect",
+ .data = &init_net.ipv4.sysctl_fwmark_reflect,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_fwmark_accept",
+ .data = &init_net.ipv4.sysctl_tcp_fwmark_accept,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ }
};
diff --git a/net/ipv4/sysfs_net_ipv4.c b/net/ipv4/sysfs_net_ipv4.c
new file mode 100644
index 0000000..0cbbf10
--- /dev/null
+++ b/net/ipv4/sysfs_net_ipv4.c
@@ -0,0 +1,88 @@
+/*
+ * net/ipv4/sysfs_net_ipv4.c
+ *
+ * sysfs-based networking knobs (so we can, unlike with sysctl, control perms)
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Robert Love <rlove@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <net/tcp.h>
+
+#define CREATE_IPV4_FILE(_name, _var) \
+static ssize_t _name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+{ \
+ return sprintf(buf, "%d\n", _var); \
+} \
+static ssize_t _name##_store(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ int val, ret; \
+ ret = sscanf(buf, "%d", &val); \
+ if (ret != 1) \
+ return -EINVAL; \
+ if (val < 0) \
+ return -EINVAL; \
+ _var = val; \
+ return count; \
+} \
+static struct kobj_attribute _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+CREATE_IPV4_FILE(tcp_wmem_min, sysctl_tcp_wmem[0]);
+CREATE_IPV4_FILE(tcp_wmem_def, sysctl_tcp_wmem[1]);
+CREATE_IPV4_FILE(tcp_wmem_max, sysctl_tcp_wmem[2]);
+
+CREATE_IPV4_FILE(tcp_rmem_min, sysctl_tcp_rmem[0]);
+CREATE_IPV4_FILE(tcp_rmem_def, sysctl_tcp_rmem[1]);
+CREATE_IPV4_FILE(tcp_rmem_max, sysctl_tcp_rmem[2]);
+
+static struct attribute *ipv4_attrs[] = {
+ &tcp_wmem_min_attr.attr,
+ &tcp_wmem_def_attr.attr,
+ &tcp_wmem_max_attr.attr,
+ &tcp_rmem_min_attr.attr,
+ &tcp_rmem_def_attr.attr,
+ &tcp_rmem_max_attr.attr,
+ NULL
+};
+
+static struct attribute_group ipv4_attr_group = {
+ .attrs = ipv4_attrs,
+};
+
+static __init int sysfs_ipv4_init(void)
+{
+ struct kobject *ipv4_kobject;
+ int ret;
+
+ ipv4_kobject = kobject_create_and_add("ipv4", kernel_kobj);
+ if (!ipv4_kobject)
+ return -ENOMEM;
+
+ ret = sysfs_create_group(ipv4_kobject, &ipv4_attr_group);
+ if (ret) {
+ kobject_put(ipv4_kobject);
+ return ret;
+ }
+
+ return 0;
+}
+
+subsys_initcall(sysfs_ipv4_init);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5d4bd6c..f9fe221 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -268,12 +268,16 @@
#include <linux/crypto.h>
#include <linux/time.h>
#include <linux/slab.h>
+#include <linux/uid_stat.h>
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
#include <net/netdma.h>
#include <net/sock.h>
@@ -1240,6 +1244,9 @@
tcp_push(sk, flags, mss_now, tp->nonagle);
out_nopush:
release_sock(sk);
+
+ if (copied + copied_syn)
+ uid_stat_tcp_snd(current_uid(), copied + copied_syn);
return copied + copied_syn;
do_fault:
@@ -1544,6 +1551,7 @@
if (copied > 0) {
tcp_recv_skb(sk, seq, &offset);
tcp_cleanup_rbuf(sk, copied);
+ uid_stat_tcp_rcv(current_uid(), copied);
}
return copied;
}
@@ -1948,6 +1956,9 @@
tcp_cleanup_rbuf(sk, copied);
release_sock(sk);
+
+ if (copied > 0)
+ uid_stat_tcp_rcv(current_uid(), copied);
return copied;
out:
@@ -1956,6 +1967,8 @@
recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
+ if (err > 0)
+ uid_stat_tcp_rcv(current_uid(), err);
goto out;
recv_sndq:
@@ -3358,6 +3371,43 @@
}
EXPORT_SYMBOL_GPL(tcp_done);
+int tcp_abort(struct sock *sk, int err)
+{
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ inet_twsk_put((struct inet_timewait_sock *)sk);
+ return -EOPNOTSUPP;
+ }
+
+ /* Don't race with userspace socket closes such as tcp_close. */
+ lock_sock(sk);
+
+ if (sk->sk_state == TCP_LISTEN) {
+ tcp_set_state(sk, TCP_CLOSE);
+ inet_csk_listen_stop(sk);
+ }
+
+ /* Don't race with BH socket closes such as inet_csk_listen_stop. */
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ sk->sk_err = err;
+ /* This barrier is coupled with smp_rmb() in tcp_poll() */
+ smp_wmb();
+ sk->sk_error_report(sk);
+ if (tcp_need_reset(sk->sk_state))
+ tcp_send_active_reset(sk, GFP_ATOMIC);
+ tcp_done(sk);
+ }
+
+ bh_unlock_sock(sk);
+ local_bh_enable();
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tcp_abort);
+
extern struct tcp_congestion_ops tcp_reno;
static __initdata unsigned long thash_entries;
@@ -3468,3 +3518,121 @@
tcp_tasklet_init();
}
+
+static int tcp_is_local(struct net *net, __be32 addr) {
+ struct rtable *rt;
+ struct flowi4 fl4 = { .daddr = addr };
+ int is_local;
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR_OR_NULL(rt))
+ return 0;
+
+ is_local = rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK);
+ ip_rt_put(rt);
+ return is_local;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int tcp_is_local6(struct net *net, struct in6_addr *addr) {
+ struct rt6_info *rt6 = rt6_lookup(net, addr, addr, 0, 0);
+ int is_local;
+
+ is_local = rt6 && rt6->dst.dev && (rt6->dst.dev->flags & IFF_LOOPBACK);
+ ip6_rt_put(rt6);
+ return is_local;
+}
+#endif
+
+/*
+ * tcp_nuke_addr - destroy all sockets on the given local address
+ * if local address is the unspecified address (0.0.0.0 or ::), destroy all
+ * sockets with local addresses that are not configured.
+ */
+int tcp_nuke_addr(struct net *net, struct sockaddr *addr)
+{
+ int family = addr->sa_family;
+ unsigned int bucket;
+
+ struct in_addr *in;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct in6_addr *in6;
+#endif
+ if (family == AF_INET) {
+ in = &((struct sockaddr_in *)addr)->sin_addr;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ } else if (family == AF_INET6) {
+ in6 = &((struct sockaddr_in6 *)addr)->sin6_addr;
+#endif
+ } else {
+ return -EAFNOSUPPORT;
+ }
+
+ for (bucket = 0; bucket <= tcp_hashinfo.ehash_mask; bucket++) {
+ struct hlist_nulls_node *node;
+ struct sock *sk;
+ spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, bucket);
+
+restart:
+ spin_lock_bh(lock);
+ sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[bucket].chain) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (sysctl_ip_dynaddr && sk->sk_state == TCP_SYN_SENT)
+ continue;
+ if (sock_flag(sk, SOCK_DEAD))
+ continue;
+
+ if (family == AF_INET) {
+ __be32 s4 = inet->inet_rcv_saddr;
+ if (s4 == LOOPBACK4_IPV6)
+ continue;
+
+ if (in->s_addr != s4 &&
+ !(in->s_addr == INADDR_ANY &&
+ !tcp_is_local(net, s4)))
+ continue;
+ }
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ if (family == AF_INET6) {
+ struct in6_addr *s6;
+ if (!inet->pinet6)
+ continue;
+
+ s6 = &inet->pinet6->rcv_saddr;
+ if (ipv6_addr_type(s6) == IPV6_ADDR_MAPPED)
+ continue;
+
+ if (!ipv6_addr_equal(in6, s6) &&
+ !(ipv6_addr_equal(in6, &in6addr_any) &&
+ !tcp_is_local6(net, s6)))
+ continue;
+ }
+#endif
+
+ sock_hold(sk);
+ spin_unlock_bh(lock);
+
+ lock_sock(sk);
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ smp_wmb(); /* be consistent with tcp_reset */
+ sk->sk_err = ETIMEDOUT;
+ sk->sk_error_report(sk);
+ tcp_done(sk);
+ }
+
+ bh_unlock_sock(sk);
+ local_bh_enable();
+ release_sock(sk);
+ sock_put(sk);
+
+ goto restart;
+ }
+ spin_unlock_bh(lock);
+ }
+
+ return 0;
+}
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index ed3f2ad..a56461c 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -11,6 +11,8 @@
#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/sock_diag.h>
#include <linux/inet_diag.h>
#include <linux/tcp.h>
@@ -46,11 +48,28 @@
return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
}
+#ifdef CONFIG_INET_DIAG_DESTROY
+static int tcp_diag_destroy(struct sk_buff *in_skb,
+ struct inet_diag_req_v2 *req)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
+
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ return sock_diag_destroy(sk, ECONNABORTED);
+}
+#endif
+
static const struct inet_diag_handler tcp_diag_handler = {
.dump = tcp_diag_dump,
.dump_one = tcp_diag_dump_one,
.idiag_get_info = tcp_diag_get_info,
.idiag_type = IPPROTO_TCP,
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = tcp_diag_destroy,
+#endif
};
static int __init tcp_diag_init(void)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f3b15bb..cd4cfb1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -99,6 +99,7 @@
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_DEFAULT_INIT_RCVWND;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
@@ -352,14 +353,14 @@
static void tcp_fixup_rcvbuf(struct sock *sk)
{
u32 mss = tcp_sk(sk)->advmss;
- u32 icwnd = TCP_DEFAULT_INIT_RCVWND;
+ u32 icwnd = sysctl_tcp_default_init_rwnd;
int rcvmem;
/* Limit to 10 segments if mss <= 1460,
* or 14600/mss segments, with a minimum of two segments.
*/
if (mss > 1460)
- icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
+ icwnd = max_t(u32, (1460 * icwnd) / mss, 2);
rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER);
while (tcp_win_from_space(rcvmem) < mss)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 11f27a4..7d34d43 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1531,6 +1531,7 @@
ireq->rmt_addr = saddr;
ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(skb);
+ ireq->ir_mark = inet_request_mark(sk, skb);
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
@@ -2898,6 +2899,7 @@
.destroy_cgroup = tcp_destroy_cgroup,
.proto_cgroup = tcp_proto_cgroup,
#endif
+ .diag_destroy = tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 276b283..3903972 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -232,14 +232,13 @@
}
/* Set initial window to a value enough for senders starting with
- * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
+ * initial congestion window of sysctl_tcp_default_init_rwnd. Place
* a limit on the initial window when mss is larger than 1460.
*/
if (mss > (1 << *rcv_wscale)) {
- int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
+ int init_cwnd = sysctl_tcp_default_init_rwnd;
if (mss > 1460)
- init_cwnd =
- max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
+ init_cwnd = max_t(u32, (1460 * init_cwnd) / mss, 2);
/* when initializing use the value from init_rcv_wnd
* rather than the default from above
*/
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 68174e4..364076e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -963,7 +963,8 @@
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sock_i_uid(sk));
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 9af088d..470a9c0 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -7,7 +7,7 @@
ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
addrlabel.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
- raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d0912ac..3eb4363 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -198,10 +198,12 @@
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
.accept_dad = 1,
+ .use_oif_addrs_only = 0,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -232,10 +234,12 @@
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
.accept_dad = 1,
+ .use_oif_addrs_only = 0,
};
/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
@@ -1173,6 +1177,9 @@
#endif
IPV6_SADDR_RULE_ORCHID,
IPV6_SADDR_RULE_PREFIX,
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+ IPV6_SADDR_RULE_NOT_OPTIMISTIC,
+#endif
IPV6_SADDR_RULE_MAX
};
@@ -1200,6 +1207,15 @@
return 0;
}
+static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+{
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+ return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+#else
+ return false;
+#endif
+}
+
static int ipv6_get_saddr_eval(struct net *net,
struct ipv6_saddr_score *score,
struct ipv6_saddr_dst *dst,
@@ -1260,10 +1276,16 @@
score->scopedist = ret;
break;
case IPV6_SADDR_RULE_PREFERRED:
+ {
/* Rule 3: Avoid deprecated and optimistic addresses */
+ u8 avoid = IFA_F_DEPRECATED;
+
+ if (!ipv6_use_optimistic_addr(score->ifa->idev))
+ avoid |= IFA_F_OPTIMISTIC;
ret = ipv6_saddr_preferred(score->addr_type) ||
- !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC));
+ !(score->ifa->flags & avoid);
break;
+ }
#ifdef CONFIG_IPV6_MIP6
case IPV6_SADDR_RULE_HOA:
{
@@ -1311,6 +1333,14 @@
ret = score->ifa->prefix_len;
score->matchlen = ret;
break;
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+ case IPV6_SADDR_RULE_NOT_OPTIMISTIC:
+ /* Optimistic addresses still have lower precedence than other
+ * preferred addresses.
+ */
+ ret = !(score->ifa->flags & IFA_F_OPTIMISTIC);
+ break;
+#endif
default:
ret = 0;
}
@@ -1358,9 +1388,15 @@
* include addresses assigned to interfaces
* belonging to the same site as the outgoing
* interface.)
+ * - "It is RECOMMENDED that the candidate source addresses
+ * be the set of unicast addresses assigned to the
+ * interface that will be used to send to the destination
+ * (the 'outgoing' interface)." (RFC 6724)
*/
+ idev = dst_dev ? __in6_dev_get(dst_dev) : NULL;
if (((dst_type & IPV6_ADDR_MULTICAST) ||
- dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) &&
+ dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL ||
+ (idev && idev->cnf.use_oif_addrs_only)) &&
dst.ifindex && dev->ifindex != dst.ifindex)
continue;
@@ -1506,7 +1542,9 @@
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr) &&
- !(ifp->flags&IFA_F_TENTATIVE) &&
+ (!(ifp->flags&IFA_F_TENTATIVE) ||
+ (ipv6_use_optimistic_addr(ifp->idev) &&
+ ifp->flags&IFA_F_OPTIMISTIC)) &&
(dev == NULL || ifp->idev->dev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
rcu_read_unlock_bh();
@@ -1946,6 +1984,31 @@
}
#endif
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+ /* Determines into what table to put autoconf PIO/RIO/default routes
+ * learned on this device.
+ *
+ * - If 0, use the same table for every device. This puts routes into
+ * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+ * (but note that these three are currently all equal to
+ * RT6_TABLE_MAIN).
+ * - If > 0, use the specified table.
+ * - If < 0, put routes into table dev->ifindex + (-rt_table).
+ */
+ struct inet6_dev *idev = in6_dev_get(dev);
+ u32 table;
+ int sysctl = idev->cnf.accept_ra_rt_table;
+ if (sysctl == 0) {
+ table = default_table;
+ } else if (sysctl > 0) {
+ table = (u32) sysctl;
+ } else {
+ table = (unsigned) dev->ifindex + (-sysctl);
+ }
+ in6_dev_put(idev);
+ return table;
+}
+
/*
* Add prefix route.
*/
@@ -1955,7 +2018,7 @@
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_PREFIX,
+ .fc_table = addrconf_rt_table(dev, RT6_TABLE_PREFIX),
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
@@ -1989,7 +2052,8 @@
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_PREFIX));
if (table == NULL)
return NULL;
@@ -3145,11 +3209,13 @@
write_unlock_bh(&idev->lock);
- /* Step 5: Discard multicast list */
- if (how)
+ /* Step 5: Discard anycast and multicast list */
+ if (how) {
+ ipv6_ac_destroy_dev(idev);
ipv6_mc_destroy_dev(idev);
- else
+ } else {
ipv6_mc_down(idev);
+ }
idev->tstamp = jiffies;
@@ -3263,8 +3329,15 @@
* Optimistic nodes can start receiving
* Frames right away
*/
- if (ifp->flags & IFA_F_OPTIMISTIC)
+ if (ifp->flags & IFA_F_OPTIMISTIC) {
ip6_ins_rt(ifp->rt);
+ if (ipv6_use_optimistic_addr(idev)) {
+ /* Because optimistic nodes can use this address,
+ * notify listeners. If DAD fails, RTM_DELADDR is sent.
+ */
+ ipv6_ifa_notify(RTM_NEWADDR, ifp);
+ }
+ }
addrconf_dad_kick(ifp);
out:
@@ -4205,10 +4278,12 @@
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad;
+ array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
#endif
#ifdef CONFIG_IPV6_MROUTE
array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
@@ -4217,6 +4292,7 @@
array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao;
array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
+ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only;
}
static inline size_t inet6_ifla6_size(void)
@@ -4914,6 +4990,13 @@
#endif
#endif
{
+ .procname = "accept_ra_rt_table",
+ .data = &ipv6_devconf.accept_ra_rt_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "proxy_ndp",
.data = &ipv6_devconf.proxy_ndp,
.maxlen = sizeof(int),
@@ -4936,6 +5019,14 @@
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "use_optimistic",
+ .data = &ipv6_devconf.use_optimistic,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+
+ },
#endif
#ifdef CONFIG_IPV6_MROUTE
{
@@ -4975,6 +5066,14 @@
.proc_handler = proc_dointvec
},
{
+ .procname = "use_oif_addrs_only",
+ .data = &ipv6_devconf.use_oif_addrs_only,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+
+ },
+ {
/* sentinel */
}
},
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a944f13..9a932cc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -49,6 +49,7 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
@@ -62,6 +63,20 @@
#include <asm/uaccess.h>
#include <linux/mroute6.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
+
MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
@@ -108,6 +123,9 @@
int try_loading_module = 0;
int err;
+ if (!current_has_network())
+ return -EACCES;
+
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
@@ -162,8 +180,7 @@
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
@@ -434,9 +451,11 @@
/* Free tx options */
- opt = xchg(&np->opt, NULL);
- if (opt != NULL)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
@@ -480,6 +499,21 @@
}
EXPORT_SYMBOL(inet6_getname);
+int inet6_killaddr_ioctl(struct net *net, void __user *arg) {
+ struct in6_ifreq ireq;
+ struct sockaddr_in6 sin6;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EACCES;
+
+ if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
+ return -EFAULT;
+
+ sin6.sin6_family = AF_INET6;
+ sin6.sin6_addr = ireq.ifr6_addr;
+ return tcp_nuke_addr(net, (struct sockaddr *) &sin6);
+}
+
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
@@ -503,6 +537,8 @@
return addrconf_del_ifaddr(net, (void __user *) arg);
case SIOCSIFDSTADDR:
return addrconf_set_dstaddr(net, (void __user *) arg);
+ case SIOCKILLADDR:
+ return inet6_killaddr_ioctl(net, (void __user *) arg);
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
@@ -663,9 +699,13 @@
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+ &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst)) {
@@ -843,6 +883,9 @@
if (err)
goto out_unregister_udplite_proto;
+ err = proto_register(&pingv6_prot, 1);
+ if (err)
+ goto out_unregister_ping_proto;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
@@ -933,6 +976,10 @@
if (err)
goto ipv6_packet_fail;
+ err = pingv6_init();
+ if (err)
+ goto pingv6_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -945,6 +992,8 @@
sysctl_fail:
ipv6_packet_cleanup();
#endif
+pingv6_fail:
+ pingv6_exit();
ipv6_packet_fail:
tcpv6_exit();
tcpv6_fail:
@@ -988,6 +1037,8 @@
rtnl_unregister_all(PF_INET6);
out_sock_register_fail:
rawv6_exit();
+out_unregister_ping_proto:
+ proto_unregister(&pingv6_prot);
out_unregister_raw_proto:
proto_unregister(&rawv6_prot);
out_unregister_udplite_proto:
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index bb02e17..b903e19 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -630,7 +630,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 5a80f15..1e97d08 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -341,6 +341,27 @@
return __ipv6_dev_ac_dec(idev, addr);
}
+void ipv6_ac_destroy_dev(struct inet6_dev *idev)
+{
+ struct ifacaddr6 *aca;
+
+ write_lock_bh(&idev->lock);
+ while ((aca = idev->ac_list) != NULL) {
+ idev->ac_list = aca->aca_next;
+ write_unlock_bh(&idev->lock);
+
+ addrconf_leave_solict(idev, &aca->aca_addr);
+
+ dst_hold(&aca->aca_rt->dst);
+ ip6_del_rt(aca->aca_rt);
+
+ aca_put(aca);
+
+ write_lock_bh(&idev->lock);
+ }
+ write_unlock_bh(&idev->lock);
+}
+
/*
* check if the interface has this anycast address
* called with rcu_read_lock()
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index b0d5d7e..193274c 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,14 +162,17 @@
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
fl6.flowi6_oif = np->mcast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- opt = flowlabel ? flowlabel->opt : np->opt;
+ rcu_read_lock();
+ opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
final_p = fl6_update_dst(&fl6, opt, &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
err = 0;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 40ffd72..fdc81cb 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -449,7 +449,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 8d67900..33dbd6c 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@
*((char **)&opt2->dst1opt) += dif;
if (opt2->srcrt)
*((char **)&opt2->srcrt) += dif;
+ atomic_set(&opt2->refcnt, 1);
}
return opt2;
}
@@ -790,7 +791,7 @@
return ERR_PTR(-ENOBUFS);
memset(opt2, 0, tot_len);
-
+ atomic_set(&opt2->refcnt, 1);
opt2->tot_len = tot_len;
p = (char *)(opt2 + 1);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index f66c1b6..06fc6bf 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -166,15 +166,15 @@
* to explore inner IPv6 header, eg. ICMPv6 error messages.
*
* If target header is found, its offset is set in *offset and return protocol
- * number. Otherwise, return -1.
+ * number. Otherwise, return -ENOENT or -EBADMSG.
*
* If the first fragment doesn't contain the final protocol header or
* NEXTHDR_NONE it is considered invalid.
*
* Note that non-1st fragment is special case that "the protocol number
* of last header" is "next header" field in Fragment header. In this case,
- * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
- * isn't NULL.
+ * *offset is meaningless. If fragoff is not NULL, the fragment offset is
+ * stored in *fragoff; if it is NULL, return -EINVAL.
*
* if flags is not NULL and it's a fragment, then the frag flag
* IP6_FH_F_FRAG will be set. If it's an AH header, the
@@ -253,9 +253,12 @@
if (target < 0 &&
((!ipv6_ext_hdr(hp->nexthdr)) ||
hp->nexthdr == NEXTHDR_NONE)) {
- if (fragoff)
+ if (fragoff) {
*fragoff = _frag_off;
- return hp->nexthdr;
+ return hp->nexthdr;
+ } else {
+ return -EINVAL;
+ }
}
if (!found)
return -ENOENT;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 2dee1d9..2a6a0e7 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -57,6 +57,7 @@
#include <net/ipv6.h>
#include <net/ip6_checksum.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
@@ -84,12 +85,18 @@
static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
+ /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
+ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
+
+ if (!(type & ICMPV6_INFOMSG_MASK))
+ if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
+ ping_err(skb, offset, ntohl(info));
}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -224,7 +231,8 @@
return (*op & 0xC0) == 0x80;
}
-static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len)
{
struct sk_buff *skb;
struct icmp6hdr *icmp6h;
@@ -307,8 +315,8 @@
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif
-static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
- struct sock *sk, struct flowi6 *fl6)
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+ struct sock *sk, struct flowi6 *fl6)
{
struct dst_entry *dst, *dst2;
struct flowi6 fl2;
@@ -389,6 +397,7 @@
int len;
int hlimit;
int err = 0;
+ u32 mark = IP6_REPLY_MARK(net, skb->mark);
if ((u8 *)hdr < skb->head ||
(skb->network_header + sizeof(*hdr)) > skb->tail)
@@ -454,6 +463,7 @@
fl6.daddr = hdr->saddr;
if (saddr)
fl6.saddr = *saddr;
+ fl6.flowi6_mark = mark;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
@@ -462,6 +472,7 @@
sk = icmpv6_xmit_lock(net);
if (sk == NULL)
return;
+ sk->sk_mark = mark;
np = inet6_sk(sk);
if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -543,6 +554,7 @@
struct dst_entry *dst;
int err = 0;
int hlimit;
+ u32 mark = IP6_REPLY_MARK(net, skb->mark);
saddr = &ipv6_hdr(skb)->daddr;
@@ -559,11 +571,13 @@
fl6.saddr = *saddr;
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
+ fl6.flowi6_mark = mark;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
if (sk == NULL)
return;
+ sk->sk_mark = mark;
np = inet6_sk(sk);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -697,7 +711,8 @@
skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
IPPROTO_ICMPV6, 0));
if (__skb_checksum_complete(skb)) {
- LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n",
+ LIMIT_NETDEBUG(KERN_DEBUG
+ "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
saddr, daddr);
goto csum_error;
}
@@ -718,7 +733,7 @@
break;
case ICMPV6_ECHO_REPLY:
- /* we couldn't care less */
+ ping_rcv(skb);
break;
case ICMPV6_PKT_TOOBIG:
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e4311cb..157f2b2 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -78,12 +78,15 @@
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = IPPROTO_TCP;
fl6->daddr = treq->rmt_addr;
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
fl6->saddr = treq->loc_addr;
fl6->flowi6_oif = treq->iif;
- fl6->flowi6_mark = sk->sk_mark;
+ fl6->flowi6_mark = inet_rsk(req)->ir_mark;
fl6->fl6_dport = inet_rsk(req)->rmt_port;
fl6->fl6_sport = inet_rsk(req)->loc_port;
+ fl6->flowi6_uid = sock_i_uid(sk);
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
@@ -211,9 +214,12 @@
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sock_i_uid(sk);
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = __inet6_csk_dst_check(sk, np->dst_cookie);
if (!dst) {
@@ -247,7 +253,8 @@
/* Restore final destination back after routing done */
fl6.daddr = np->daddr;
- res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
rcu_read_unlock();
return res;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 107f7528..b94a624 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -701,7 +701,7 @@
struct mr6_table *mrt;
struct flowi6 fl6 = {
.flowi6_oif = dev->ifindex,
- .flowi6_iif = skb->skb_iif,
+ .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_mark = skb->mark,
};
int err;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 7af5aee..a1beb59 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -78,7 +78,7 @@
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
xfrm_state_put(x);
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d1e2e8e..f4d2412 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -110,10 +110,12 @@
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
- opt = xchg(&inet6_sk(sk)->opt, opt);
+ opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+ opt);
} else {
spin_lock(&sk->sk_dst_lock);
- opt = xchg(&inet6_sk(sk)->opt, opt);
+ opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+ opt);
spin_unlock(&sk->sk_dst_lock);
}
sk_dst_reset(sk);
@@ -213,9 +215,12 @@
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
- opt = xchg(&np->opt, NULL);
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+ NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
@@ -385,7 +390,8 @@
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
- opt = ipv6_renew_options(sk, np->opt, optname,
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ opt = ipv6_renew_options(sk, opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
@@ -414,8 +420,10 @@
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
@@ -468,6 +476,7 @@
break;
memset(opt, 0, sizeof(*opt));
+ atomic_set(&opt->refcnt, 1);
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
@@ -484,8 +493,10 @@
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
case IPV6_UNICAST_HOPS:
@@ -1085,10 +1096,11 @@
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
+ struct ipv6_txoptions *opt;
lock_sock(sk);
- len = ipv6_getsockopt_sticky(sk, np->opt,
- optname, optval, len);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 4433ab40..8d03367 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -105,7 +105,8 @@
config IP6_NF_MATCH_RPFILTER
tristate '"rpfilter" reverse path filter match support'
- depends on NETFILTER_ADVANCED && (IP6_NF_MANGLE || IP6_NF_RAW)
+ depends on NETFILTER_ADVANCED
+ depends on IP6_NF_MANGLE || IP6_NF_RAW
---help---
This option allows you to match packets whose replies would
go out via the interface the packet came in.
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
new file mode 100644
index 0000000..27de137
--- /dev/null
+++ b/net/ipv6/ping.c
@@ -0,0 +1,226 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * "Ping" sockets
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Based on ipv4/ping.c code.
+ *
+ * Authors: Lorenzo Colitti (IPv6 support)
+ * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6),
+ * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32)
+ *
+ */
+
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/transp_v6.h>
+#include <net/ping.h>
+
+struct proto pingv6_prot = {
+ .name = "PINGv6",
+ .owner = THIS_MODULE,
+ .init = ping_init_sock,
+ .close = ping_close,
+ .connect = ip6_datagram_connect,
+ .disconnect = udp_disconnect,
+ .setsockopt = ipv6_setsockopt,
+ .getsockopt = ipv6_getsockopt,
+ .sendmsg = ping_v6_sendmsg,
+ .recvmsg = ping_recvmsg,
+ .bind = ping_bind,
+ .backlog_rcv = ping_queue_rcv_skb,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
+ .obj_size = sizeof(struct raw6_sock),
+};
+EXPORT_SYMBOL_GPL(pingv6_prot);
+
+static struct inet_protosw pingv6_protosw = {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_ICMPV6,
+ .prot = &pingv6_prot,
+ .ops = &inet6_dgram_ops,
+ .no_check = UDP_CSUM_DEFAULT,
+ .flags = INET_PROTOSW_REUSE,
+};
+
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len)
+{
+ return -EAFNOSUPPORT;
+}
+int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+ struct sk_buff *skb)
+{
+ return -EAFNOSUPPORT;
+}
+int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
+{
+ return -EAFNOSUPPORT;
+}
+void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
+ __be16 port, u32 info, u8 *payload) {}
+int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
+ const struct net_device *dev, int strict)
+{
+ return 0;
+}
+
+int __init pingv6_init(void)
+{
+ pingv6_ops.ipv6_recv_error = ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
+ return inet6_register_protosw(&pingv6_protosw);
+}
+
+/* This never gets called because it's not possible to unload the ipv6 module,
+ * but just in case.
+ */
+void pingv6_exit(void)
+{
+ pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
+ inet6_unregister_protosw(&pingv6_protosw);
+}
+
+int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct icmp6hdr user_icmph;
+ int addr_type;
+ struct in6_addr *daddr;
+ int oif = 0;
+ struct flowi6 fl6;
+ int err;
+ int hlimit;
+ struct dst_entry *dst;
+ struct rt6_info *rt;
+ struct pingfakehdr pfh;
+
+ pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
+ if (msg->msg_name) {
+ struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
+ if (msg->msg_namelen < sizeof(*u))
+ return -EINVAL;
+ if (u->sin6_family != AF_INET6) {
+ return -EAFNOSUPPORT;
+ }
+ daddr = &(u->sin6_addr);
+ if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr)))
+ oif = u->sin6_scope_id;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+ daddr = &np->daddr;
+ }
+
+ if (!oif)
+ oif = sk->sk_bound_dev_if;
+
+ if (!oif)
+ oif = np->sticky_pktinfo.ipi6_ifindex;
+
+ if (!oif && ipv6_addr_is_multicast(daddr))
+ oif = np->mcast_oif;
+ else if (!oif)
+ oif = np->ucast_oif;
+
+ addr_type = ipv6_addr_type(daddr);
+ if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
+ (addr_type & IPV6_ADDR_MAPPED) ||
+ (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if))
+ return -EINVAL;
+
+ /* TODO: use ip6_datagram_send_ctl to get options from cmsg */
+
+ memset(&fl6, 0, sizeof(fl6));
+
+ fl6.flowi6_proto = IPPROTO_ICMPV6;
+ fl6.saddr = np->saddr;
+ fl6.daddr = *daddr;
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
+ fl6.fl6_icmp_type = user_icmph.icmp6_type;
+ fl6.fl6_icmp_code = user_icmph.icmp6_code;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1);
+ if (IS_ERR(dst))
+ return PTR_ERR(dst);
+ rt = (struct rt6_info *) dst;
+
+ np = inet6_sk(sk);
+ if (!np)
+ return -EBADF;
+
+ pfh.icmph.type = user_icmph.icmp6_type;
+ pfh.icmph.code = user_icmph.icmp6_code;
+ pfh.icmph.checksum = 0;
+ pfh.icmph.un.echo.id = inet->inet_sport;
+ pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
+ pfh.iov = msg->msg_iov;
+ pfh.wcheck = 0;
+ pfh.family = AF_INET6;
+
+ if (ipv6_addr_is_multicast(&fl6.daddr))
+ hlimit = np->mcast_hops;
+ else
+ hlimit = np->hop_limit;
+ if (hlimit < 0)
+ hlimit = ip6_dst_hoplimit(dst);
+
+ lock_sock(sk);
+ err = ip6_append_data(sk, ping_getfrag, &pfh, len,
+ 0, hlimit,
+ np->tclass, NULL, &fl6, rt,
+ MSG_DONTWAIT, np->dontfrag);
+
+ if (err) {
+ ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
+ ICMP6_MIB_OUTERRORS);
+ ip6_flush_pending_frames(sk);
+ } else {
+ err = icmpv6_push_pending_frames(sk, &fl6,
+ (struct icmp6hdr *) &pfh.icmph,
+ len);
+ }
+ release_sock(sk);
+
+ if (err)
+ return err;
+
+ return len;
+}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 464b1c9..5693cf2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -726,6 +726,7 @@
static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len)
{
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions opt_space;
struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
struct in6_addr *daddr, *final_p, final;
@@ -759,6 +760,7 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
@@ -832,8 +834,10 @@
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -900,6 +904,7 @@
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err<0?err:len;
do_confirm:
dst_confirm(dst);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6ebefd4..206b70f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -93,13 +93,12 @@
struct sk_buff *skb);
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
- unsigned int pref);
-static struct rt6_info *rt6_get_route_info(struct net *net,
+ const struct in6_addr *gwaddr, unsigned int pref);
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex);
+ const struct in6_addr *gwaddr);
#endif
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
@@ -685,7 +684,6 @@
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
{
- struct net *net = dev_net(dev);
struct route_info *rinfo = (struct route_info *) opt;
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
@@ -730,8 +728,7 @@
if (rinfo->prefix_len == 0)
rt = rt6_get_dflt_router(gwaddr, dev);
else
- rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
- gwaddr, dev->ifindex);
+ rt = rt6_get_route_info(dev, prefix, rinfo->prefix_len, gwaddr);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -739,8 +736,7 @@
}
if (!rt && lifetime)
- rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
- pref);
+ rt = rt6_add_route_info(dev, prefix, rinfo->prefix_len, gwaddr, pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
@@ -1150,7 +1146,7 @@
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1158,11 +1154,12 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
- fl6.flowi6_mark = mark;
+ fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1174,7 +1171,7 @@
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sock_i_uid(sk));
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
@@ -1847,15 +1844,16 @@
}
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex)
+ const struct in6_addr *gwaddr)
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(net, RT6_TABLE_INFO);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_INFO));
if (!table)
return NULL;
@@ -1865,7 +1863,7 @@
goto out;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->dst.dev->ifindex != ifindex)
+ if (rt->dst.dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
@@ -1879,21 +1877,20 @@
return rt;
}
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
- unsigned int pref)
+ const struct in6_addr *gwaddr, unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_INFO,
+ .fc_table = addrconf_rt_table(dev, RT6_TABLE_INFO),
.fc_metric = IP6_RT_PRIO_USER,
- .fc_ifindex = ifindex,
+ .fc_ifindex = dev->ifindex,
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
- .fc_nlinfo.nl_net = net,
+ .fc_nlinfo.nl_net = dev_net(dev),
};
cfg.fc_dst = *prefix;
@@ -1905,7 +1902,7 @@
ip6_route_add(&cfg);
- return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(dev, prefix, prefixlen, gwaddr);
}
#endif
@@ -1914,7 +1911,8 @@
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_MAIN));
if (!table)
return NULL;
@@ -1936,7 +1934,7 @@
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_DFLT,
+ .fc_table = addrconf_rt_table(dev, RT6_TABLE_DFLT),
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -1953,28 +1951,17 @@
return rt6_get_dflt_router(gwaddr, dev);
}
+
+int rt6_addrconf_purge(struct rt6_info *rt, void *arg) {
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+ (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2))
+ return -1;
+ return 0;
+}
+
void rt6_purge_dflt_routers(struct net *net)
{
- struct rt6_info *rt;
- struct fib6_table *table;
-
- /* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (!table)
- return;
-
-restart:
- read_lock_bh(&table->tb6_lock);
- for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- ip6_del_rt(rt);
- goto restart;
- }
- }
- read_unlock_bh(&table->tb6_lock);
+ fib6_clean_all(net, rt6_addrconf_purge, 0, NULL);
}
static void rtmsg_to_fib6_config(struct net *net,
@@ -2259,6 +2246,7 @@
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2645,6 +2633,15 @@
if (tb[RTA_OIF])
oif = nla_get_u32(tb[RTA_OIF]);
+ if (tb[RTA_MARK])
+ fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index d5dda20..701d065 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -212,6 +212,8 @@
ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq6->iif = inet6_iif(skb);
+ ireq->ir_mark = inet_request_mark(sk, skb);
+
req->expires = 0UL;
req->num_retrans = 0;
ireq->ecn_ok = ecn_ok;
@@ -235,12 +237,13 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = ireq6->rmt_addr;
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index e85c48b..53a9f5a 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -24,6 +24,13 @@
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "fwmark_reflect",
+ .data = &init_net.ipv6.sysctl.fwmark_reflect,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 41c026f..95c795b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -133,6 +133,7 @@
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct rt6_info *rt;
struct flowi6 fl6;
struct dst_entry *dst;
@@ -252,8 +253,10 @@
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sock_i_uid(sk);
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -282,9 +285,9 @@
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen +
+ opt->opt_nflen;
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
@@ -480,7 +483,10 @@
fl6->daddr = treq->rmt_addr;
skb_set_queue_mapping(skb, queue_mapping);
- err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+ rcu_read_lock();
+ err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+ np->tclass);
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -791,6 +797,7 @@
fl6.flowi6_proto = IPPROTO_TCP;
if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
fl6.flowi6_oif = inet6_iif(skb);
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -999,6 +1006,7 @@
TCP_ECN_create_request(req, skb, sock_net(sk));
treq->iif = sk->sk_bound_dev_if;
+ inet_rsk(req)->ir_mark = inet_request_mark(sk, skb);
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
@@ -1087,6 +1095,7 @@
struct inet6_request_sock *treq;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct tcp6_sock *newtcp6sk;
+ struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
@@ -1220,13 +1229,15 @@
but we make one more one thing there: reattach optmem
to newsk.
*/
- if (np->opt)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
@@ -1948,6 +1959,7 @@
.proto_cgroup = tcp_proto_cgroup,
#endif
.clear_sk = tcp_v6_clear_sk,
+ .diag_destroy = tcp_abort,
};
static const struct inet6_protocol tcpv6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d234e6f..caf0d43 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1015,6 +1015,7 @@
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name;
struct in6_addr *daddr, *final_p, final;
struct ipv6_txoptions *opt = NULL;
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct flowi6 fl6;
struct dst_entry *dst;
@@ -1147,6 +1148,7 @@
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sock_i_uid(sk);
if (msg->msg_controllen) {
opt = &opt_space;
@@ -1168,8 +1170,10 @@
opt = NULL;
connected = 0;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -1270,6 +1274,7 @@
out:
dst_release(dst);
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
if (!err)
return len;
/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index db96af9..eadfb30 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -487,6 +487,7 @@
(struct sockaddr_l2tpip6 *) msg->msg_name;
struct in6_addr *daddr, *final_p, final;
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
@@ -577,8 +578,10 @@
opt = NULL;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -639,6 +642,7 @@
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err < 0 ? err : len;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 56d22ca..e3f1c92 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -195,7 +195,7 @@
config NF_CONNTRACK_H323
tristate "H.323 protocol support"
- depends on (IPV6 || IPV6=n)
+ depends on IPV6 || IPV6=n
depends on NETFILTER_ADVANCED
help
H.323 is a VoIP signalling protocol from ITU-T. As one of the most
@@ -583,7 +583,7 @@
config NETFILTER_XT_TARGET_HMARK
tristate '"HMARK" target support'
- depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
+ depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n
depends on NETFILTER_ADVANCED
---help---
This option adds the "HMARK" target.
@@ -713,7 +713,7 @@
config NETFILTER_XT_TARGET_TEE
tristate '"TEE" - packet cloning to alternate destination'
depends on NETFILTER_ADVANCED
- depends on (IPV6 || IPV6=n)
+ depends on IPV6 || IPV6=n
depends on !NF_CONNTRACK || NF_CONNTRACK
---help---
This option adds a "TEE" target with which a packet can be cloned and
@@ -724,6 +724,7 @@
depends on NETFILTER_TPROXY
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
+ depends on IPV6 || IPV6=n
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
help
@@ -758,7 +759,7 @@
config NETFILTER_XT_TARGET_TCPMSS
tristate '"TCPMSS" target support'
- depends on (IPV6 || IPV6=n)
+ depends on IPV6 || IPV6=n
default m if NETFILTER_ADVANCED=n
---help---
This option adds a `TCPMSS' target, which allows you to alter the
@@ -960,7 +961,7 @@
config NETFILTER_XT_MATCH_HASHLIMIT
tristate '"hashlimit" match support'
- depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
+ depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n
depends on NETFILTER_ADVANCED
help
This option adds a `hashlimit' match.
@@ -1089,6 +1090,8 @@
based on who created the socket: the user or group. It is also
possible to check whether a socket actually exists.
+ Conflicts with '"quota, tag, uid" match'
+
config NETFILTER_XT_MATCH_POLICY
tristate 'IPsec "policy" match support'
depends on XFRM
@@ -1122,6 +1125,22 @@
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_QTAGUID
+ bool '"quota, tag, owner" match and stats support'
+ depends on NETFILTER_XT_MATCH_SOCKET
+ depends on NETFILTER_XT_MATCH_OWNER=n
+ help
+ This option replaces the `owner' match. In addition to matching
+ on uid, it keeps stats based on a tag assigned to a socket.
+ The full tag is comprised of a UID and an accounting tag.
+ The tags are assignable to sockets from user space (e.g. a download
+ manager can assign the socket to another UID for accounting).
+ Stats and control are done via /proc/net/xt_qtaguid/.
+ It replaces owner as it takes the same arguments, but should
+ really be recognized by the iptables tool.
+
+ If unsure, say `N'.
+
config NETFILTER_XT_MATCH_QUOTA
tristate '"quota" match support'
depends on NETFILTER_ADVANCED
@@ -1132,6 +1151,30 @@
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+config NETFILTER_XT_MATCH_QUOTA2
+ tristate '"quota2" match support'
+ depends on NETFILTER_ADVANCED
+ help
+ This option adds a `quota2' match, which allows to match on a
+ byte counter correctly and not per CPU.
+ It allows naming the quotas.
+ This is based on http://xtables-addons.git.sourceforge.net
+
+ If you want to compile it as a module, say M here and read
+ <file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+
+config NETFILTER_XT_MATCH_QUOTA2_LOG
+ bool '"quota2" Netfilter LOG support'
+ depends on NETFILTER_XT_MATCH_QUOTA2
+ depends on IP_NF_TARGET_ULOG=n # not yes, not module, just no
+ default n
+ help
+ This option allows `quota2' to log ONCE when a quota limit
+ is passed. It logs via NETLINK using the NETLINK_NFLOG family.
+ It logs similarly to how ipt_ULOG would without data.
+
+ If unsure, say `N'.
+
config NETFILTER_XT_MATCH_RATEEST
tristate '"rateest" match support'
depends on NETFILTER_ADVANCED
@@ -1184,6 +1227,7 @@
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
depends on !NF_CONNTRACK || NF_CONNTRACK
+ depends on IPV6 || IPV6=n
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a1abf87..d9655f6 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -127,7 +127,9 @@
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QTAGUID) += xt_qtaguid_print.o xt_qtaguid.o
obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA2) += xt_quota2.o
obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o
obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o
obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index f407ebc1..ddf77f7 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -5,6 +5,7 @@
* After timer expires a kevent will be sent.
*
* Copyright (C) 2004, 2010 Nokia Corporation
+ *
* Written by Timo Teras <ext-timo.teras@nokia.com>
*
* Converted to x_tables and reworked for upstream inclusion
@@ -38,8 +39,16 @@
#include <linux/netfilter/xt_IDLETIMER.h>
#include <linux/kdev_t.h>
#include <linux/kobject.h>
+#include <linux/skbuff.h>
#include <linux/workqueue.h>
#include <linux/sysfs.h>
+#include <linux/rtc.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/suspend.h>
+#include <linux/notifier.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
struct idletimer_tg_attr {
struct attribute attr;
@@ -55,14 +64,110 @@
struct kobject *kobj;
struct idletimer_tg_attr attr;
+ struct timespec delayed_timer_trigger;
+ struct timespec last_modified_timer;
+ struct timespec last_suspend_time;
+ struct notifier_block pm_nb;
+
+ int timeout;
unsigned int refcnt;
+ bool work_pending;
+ bool send_nl_msg;
+ bool active;
+ uid_t uid;
};
static LIST_HEAD(idletimer_tg_list);
static DEFINE_MUTEX(list_mutex);
+static DEFINE_SPINLOCK(timestamp_lock);
static struct kobject *idletimer_tg_kobj;
+static bool check_for_delayed_trigger(struct idletimer_tg *timer,
+ struct timespec *ts)
+{
+ bool state;
+ struct timespec temp;
+ spin_lock_bh(×tamp_lock);
+ timer->work_pending = false;
+ if ((ts->tv_sec - timer->last_modified_timer.tv_sec) > timer->timeout ||
+ timer->delayed_timer_trigger.tv_sec != 0) {
+ state = false;
+ temp.tv_sec = timer->timeout;
+ temp.tv_nsec = 0;
+ if (timer->delayed_timer_trigger.tv_sec != 0) {
+ temp = timespec_add(timer->delayed_timer_trigger, temp);
+ ts->tv_sec = temp.tv_sec;
+ ts->tv_nsec = temp.tv_nsec;
+ timer->delayed_timer_trigger.tv_sec = 0;
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ } else {
+ temp = timespec_add(timer->last_modified_timer, temp);
+ ts->tv_sec = temp.tv_sec;
+ ts->tv_nsec = temp.tv_nsec;
+ }
+ } else {
+ state = timer->active;
+ }
+ spin_unlock_bh(×tamp_lock);
+ return state;
+}
+
+static void notify_netlink_uevent(const char *iface, struct idletimer_tg *timer)
+{
+ char iface_msg[NLMSG_MAX_SIZE];
+ char state_msg[NLMSG_MAX_SIZE];
+ char timestamp_msg[NLMSG_MAX_SIZE];
+ char uid_msg[NLMSG_MAX_SIZE];
+ char *envp[] = { iface_msg, state_msg, timestamp_msg, uid_msg, NULL };
+ int res;
+ struct timespec ts;
+ uint64_t time_ns;
+ bool state;
+
+ res = snprintf(iface_msg, NLMSG_MAX_SIZE, "INTERFACE=%s",
+ iface);
+ if (NLMSG_MAX_SIZE <= res) {
+ pr_err("message too long (%d)", res);
+ return;
+ }
+
+ get_monotonic_boottime(&ts);
+ state = check_for_delayed_trigger(timer, &ts);
+ res = snprintf(state_msg, NLMSG_MAX_SIZE, "STATE=%s",
+ state ? "active" : "inactive");
+
+ if (NLMSG_MAX_SIZE <= res) {
+ pr_err("message too long (%d)", res);
+ return;
+ }
+
+ if (state) {
+ res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=%u", timer->uid);
+ if (NLMSG_MAX_SIZE <= res)
+ pr_err("message too long (%d)", res);
+ } else {
+ res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=");
+ if (NLMSG_MAX_SIZE <= res)
+ pr_err("message too long (%d)", res);
+ }
+
+ time_ns = timespec_to_ns(&ts);
+ res = snprintf(timestamp_msg, NLMSG_MAX_SIZE, "TIME_NS=%llu", time_ns);
+ if (NLMSG_MAX_SIZE <= res) {
+ timestamp_msg[0] = '\0';
+ pr_err("message too long (%d)", res);
+ }
+
+ pr_debug("putting nlmsg: <%s> <%s> <%s> <%s>\n", iface_msg, state_msg,
+ timestamp_msg, uid_msg);
+ kobject_uevent_env(idletimer_tg_kobj, KOBJ_CHANGE, envp);
+ return;
+
+
+}
+
static
struct idletimer_tg *__idletimer_tg_find_by_label(const char *label)
{
@@ -83,6 +188,7 @@
{
struct idletimer_tg *timer;
unsigned long expires = 0;
+ unsigned long now = jiffies;
mutex_lock(&list_mutex);
@@ -92,11 +198,15 @@
mutex_unlock(&list_mutex);
- if (time_after(expires, jiffies))
+ if (time_after(expires, now))
return sprintf(buf, "%u\n",
- jiffies_to_msecs(expires - jiffies) / 1000);
+ jiffies_to_msecs(expires - now) / 1000);
- return sprintf(buf, "0\n");
+ if (timer->send_nl_msg)
+ return sprintf(buf, "0 %d\n",
+ jiffies_to_msecs(now - expires) / 1000);
+ else
+ return sprintf(buf, "0\n");
}
static void idletimer_tg_work(struct work_struct *work)
@@ -105,6 +215,9 @@
work);
sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name);
+
+ if (timer->send_nl_msg)
+ notify_netlink_uevent(timer->attr.attr.name, timer);
}
static void idletimer_tg_expired(unsigned long data)
@@ -112,8 +225,55 @@
struct idletimer_tg *timer = (struct idletimer_tg *) data;
pr_debug("timer %s expired\n", timer->attr.attr.name);
-
+ spin_lock_bh(×tamp_lock);
+ timer->active = false;
+ timer->work_pending = true;
schedule_work(&timer->work);
+ spin_unlock_bh(×tamp_lock);
+}
+
+static int idletimer_resume(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ struct timespec ts;
+ unsigned long time_diff, now = jiffies;
+ struct idletimer_tg *timer = container_of(notifier,
+ struct idletimer_tg, pm_nb);
+ if (!timer)
+ return NOTIFY_DONE;
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ get_monotonic_boottime(&timer->last_suspend_time);
+ break;
+ case PM_POST_SUSPEND:
+ spin_lock_bh(×tamp_lock);
+ if (!timer->active) {
+ spin_unlock_bh(×tamp_lock);
+ break;
+ }
+ /* since jiffies are not updated when suspended now represents
+ * the time it would have suspended */
+ if (time_after(timer->timer.expires, now)) {
+ get_monotonic_boottime(&ts);
+ ts = timespec_sub(ts, timer->last_suspend_time);
+ time_diff = timespec_to_jiffies(&ts);
+ if (timer->timer.expires > (time_diff + now)) {
+ mod_timer_pending(&timer->timer,
+ (timer->timer.expires - time_diff));
+ } else {
+ del_timer(&timer->timer);
+ timer->timer.expires = 0;
+ timer->active = false;
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ }
+ }
+ spin_unlock_bh(×tamp_lock);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
}
static int idletimer_tg_create(struct idletimer_tg_info *info)
@@ -145,6 +305,21 @@
setup_timer(&info->timer->timer, idletimer_tg_expired,
(unsigned long) info->timer);
info->timer->refcnt = 1;
+ info->timer->send_nl_msg = (info->send_nl_msg == 0) ? false : true;
+ info->timer->active = true;
+ info->timer->timeout = info->timeout;
+
+ info->timer->delayed_timer_trigger.tv_sec = 0;
+ info->timer->delayed_timer_trigger.tv_nsec = 0;
+ info->timer->work_pending = false;
+ info->timer->uid = 0;
+ get_monotonic_boottime(&info->timer->last_modified_timer);
+
+ info->timer->pm_nb.notifier_call = idletimer_resume;
+ ret = register_pm_notifier(&info->timer->pm_nb);
+ if (ret)
+ printk(KERN_WARNING "[%s] Failed to register pm notifier %d\n",
+ __func__, ret);
mod_timer(&info->timer->timer,
msecs_to_jiffies(info->timeout * 1000) + jiffies);
@@ -161,6 +336,46 @@
return ret;
}
+static void reset_timer(const struct idletimer_tg_info *info,
+ struct sk_buff *skb)
+{
+ unsigned long now = jiffies;
+ struct idletimer_tg *timer = info->timer;
+ bool timer_prev;
+
+ spin_lock_bh(×tamp_lock);
+ timer_prev = timer->active;
+ timer->active = true;
+ /* timer_prev is used to guard overflow problem in time_before*/
+ if (!timer_prev || time_before(timer->timer.expires, now)) {
+ pr_debug("Starting Checkentry timer (Expired, Jiffies): %lu, %lu\n",
+ timer->timer.expires, now);
+
+ /* Stores the uid resposible for waking up the radio */
+ if (skb && (skb->sk)) {
+ struct sock *sk = skb->sk;
+ read_lock_bh(&sk->sk_callback_lock);
+ if ((sk->sk_socket) && (sk->sk_socket->file) &&
+ (sk->sk_socket->file->f_cred))
+ timer->uid = sk->sk_socket->file->f_cred->uid;
+ read_unlock_bh(&sk->sk_callback_lock);
+ }
+
+ /* checks if there is a pending inactive notification*/
+ if (timer->work_pending)
+ timer->delayed_timer_trigger = timer->last_modified_timer;
+ else {
+ timer->work_pending = true;
+ schedule_work(&timer->work);
+ }
+ }
+
+ get_monotonic_boottime(&timer->last_modified_timer);
+ mod_timer(&timer->timer,
+ msecs_to_jiffies(info->timeout * 1000) + now);
+ spin_unlock_bh(×tamp_lock);
+}
+
/*
* The actual xt_tables plugin.
*/
@@ -168,15 +383,23 @@
const struct xt_action_param *par)
{
const struct idletimer_tg_info *info = par->targinfo;
+ unsigned long now = jiffies;
pr_debug("resetting timer %s, timeout period %u\n",
info->label, info->timeout);
BUG_ON(!info->timer);
- mod_timer(&info->timer->timer,
- msecs_to_jiffies(info->timeout * 1000) + jiffies);
+ info->timer->active = true;
+ if (time_before(info->timer->timer.expires, now)) {
+ schedule_work(&info->timer->work);
+ pr_debug("Starting timer %s (Expired, Jiffies): %lu, %lu\n",
+ info->label, info->timer->timer.expires, now);
+ }
+
+ /* TODO: Avoid modifying timers on each packet */
+ reset_timer(info, skb);
return XT_CONTINUE;
}
@@ -185,7 +408,7 @@
struct idletimer_tg_info *info = par->targinfo;
int ret;
- pr_debug("checkentry targinfo%s\n", info->label);
+ pr_debug("checkentry targinfo %s\n", info->label);
if (info->timeout == 0) {
pr_debug("timeout value is zero\n");
@@ -204,9 +427,7 @@
info->timer = __idletimer_tg_find_by_label(info->label);
if (info->timer) {
info->timer->refcnt++;
- mod_timer(&info->timer->timer,
- msecs_to_jiffies(info->timeout * 1000) + jiffies);
-
+ reset_timer(info, NULL);
pr_debug("increased refcnt of timer %s to %u\n",
info->label, info->timer->refcnt);
} else {
@@ -219,6 +440,7 @@
}
mutex_unlock(&list_mutex);
+
return 0;
}
@@ -236,11 +458,12 @@
list_del(&info->timer->entry);
del_timer_sync(&info->timer->timer);
sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr);
+ unregister_pm_notifier(&info->timer->pm_nb);
kfree(info->timer->attr.attr.name);
kfree(info->timer);
} else {
pr_debug("decreased refcnt of timer %s to %u\n",
- info->label, info->timer->refcnt);
+ info->label, info->timer->refcnt);
}
mutex_unlock(&list_mutex);
@@ -248,6 +471,7 @@
static struct xt_target idletimer_tg __read_mostly = {
.name = "IDLETIMER",
+ .revision = 1,
.family = NFPROTO_UNSPEC,
.target = idletimer_tg_target,
.targetsize = sizeof(struct idletimer_tg_info),
@@ -313,3 +537,4 @@
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("ipt_IDLETIMER");
MODULE_ALIAS("ip6t_IDLETIMER");
+MODULE_ALIAS("arpt_IDLETIMER");
diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c
new file mode 100644
index 0000000..cfa436a
--- /dev/null
+++ b/net/netfilter/xt_qtaguid.c
@@ -0,0 +1,3018 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * There are run-time debug flags enabled via the debug_mask module param, or
+ * via the DEFAULT_DEBUG_MASK. See xt_qtaguid_internal.h.
+ */
+#define DEBUG
+
+#include <linux/file.h>
+#include <linux/inetdevice.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_qtaguid.h>
+#include <linux/ratelimit.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+
+#include <linux/netfilter/xt_socket.h>
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+#include "../../fs/proc/internal.h"
+
+/*
+ * We only use the xt_socket funcs within a similar context to avoid unexpected
+ * return values.
+ */
+#define XT_SOCKET_SUPPORTED_HOOKS \
+ ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN))
+
+
+static const char *module_procdirname = "xt_qtaguid";
+static struct proc_dir_entry *xt_qtaguid_procdir;
+
+static unsigned int proc_iface_perms = S_IRUGO;
+module_param_named(iface_perms, proc_iface_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_stats_file;
+static unsigned int proc_stats_perms = S_IRUGO;
+module_param_named(stats_perms, proc_stats_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_ctrl_file;
+
+/* Everybody can write. But proc_ctrl_write_limited is true by default which
+ * limits what can be controlled. See the can_*() functions.
+ */
+static unsigned int proc_ctrl_perms = S_IRUGO | S_IWUGO;
+module_param_named(ctrl_perms, proc_ctrl_perms, uint, S_IRUGO | S_IWUSR);
+
+/* Limited by default, so the gid of the ctrl and stats proc entries
+ * will limit what can be done. See the can_*() functions.
+ */
+static bool proc_stats_readall_limited = true;
+static bool proc_ctrl_write_limited = true;
+
+module_param_named(stats_readall_limited, proc_stats_readall_limited, bool,
+ S_IRUGO | S_IWUSR);
+module_param_named(ctrl_write_limited, proc_ctrl_write_limited, bool,
+ S_IRUGO | S_IWUSR);
+
+/*
+ * Limit the number of active tags (via socket tags) for a given UID.
+ * Multiple processes could share the UID.
+ */
+static int max_sock_tags = DEFAULT_MAX_SOCK_TAGS;
+module_param(max_sock_tags, int, S_IRUGO | S_IWUSR);
+
+/*
+ * After the kernel has initiallized this module, it is still possible
+ * to make it passive.
+ * Setting passive to Y:
+ * - the iface stats handling will not act on notifications.
+ * - iptables matches will never match.
+ * - ctrl commands silently succeed.
+ * - stats are always empty.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool module_passive;
+module_param_named(passive, module_passive, bool, S_IRUGO | S_IWUSR);
+
+/*
+ * Control how qtaguid data is tracked per proc/uid.
+ * Setting tag_tracking_passive to Y:
+ * - don't create proc specific structs to track tags
+ * - don't check that active tag stats exceed some limits.
+ * - don't clean up socket tags on process exits.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool qtu_proc_handling_passive;
+module_param_named(tag_tracking_passive, qtu_proc_handling_passive, bool,
+ S_IRUGO | S_IWUSR);
+
+#define QTU_DEV_NAME "xt_qtaguid"
+
+uint qtaguid_debug_mask = DEFAULT_DEBUG_MASK;
+module_param_named(debug_mask, qtaguid_debug_mask, uint, S_IRUGO | S_IWUSR);
+
+/*---------------------------------------------------------------------------*/
+static const char *iface_stat_procdirname = "iface_stat";
+static struct proc_dir_entry *iface_stat_procdir;
+/*
+ * The iface_stat_all* will go away once userspace gets use to the new fields
+ * that have a format line.
+ */
+static const char *iface_stat_all_procfilename = "iface_stat_all";
+static struct proc_dir_entry *iface_stat_all_procfile;
+static const char *iface_stat_fmt_procfilename = "iface_stat_fmt";
+static struct proc_dir_entry *iface_stat_fmt_procfile;
+
+
+static LIST_HEAD(iface_stat_list);
+static DEFINE_SPINLOCK(iface_stat_list_lock);
+
+static struct rb_root sock_tag_tree = RB_ROOT;
+static DEFINE_SPINLOCK(sock_tag_list_lock);
+
+static struct rb_root tag_counter_set_tree = RB_ROOT;
+static DEFINE_SPINLOCK(tag_counter_set_list_lock);
+
+static struct rb_root uid_tag_data_tree = RB_ROOT;
+static DEFINE_SPINLOCK(uid_tag_data_tree_lock);
+
+static struct rb_root proc_qtu_data_tree = RB_ROOT;
+/* No proc_qtu_data_tree_lock; use uid_tag_data_tree_lock */
+
+static struct qtaguid_event_counts qtu_events;
+/*----------------------------------------------*/
+static bool can_manipulate_uids(void)
+{
+ /* root pwnd */
+ return in_egroup_p(xt_qtaguid_ctrl_file->gid)
+ || unlikely(!current_fsuid()) || unlikely(!proc_ctrl_write_limited)
+ || unlikely(current_fsuid() == xt_qtaguid_ctrl_file->uid);
+}
+
+static bool can_impersonate_uid(uid_t uid)
+{
+ return uid == current_fsuid() || can_manipulate_uids();
+}
+
+static bool can_read_other_uid_stats(uid_t uid)
+{
+ /* root pwnd */
+ return in_egroup_p(xt_qtaguid_stats_file->gid)
+ || unlikely(!current_fsuid()) || uid == current_fsuid()
+ || unlikely(!proc_stats_readall_limited)
+ || unlikely(current_fsuid() == xt_qtaguid_ctrl_file->uid);
+}
+
+static inline void dc_add_byte_packets(struct data_counters *counters, int set,
+ enum ifs_tx_rx direction,
+ enum ifs_proto ifs_proto,
+ int bytes,
+ int packets)
+{
+ counters->bpc[set][direction][ifs_proto].bytes += bytes;
+ counters->bpc[set][direction][ifs_proto].packets += packets;
+}
+
+static struct tag_node *tag_node_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct tag_node *data = rb_entry(node, struct tag_node, node);
+ int result;
+ RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+ " node=%p data=%p\n", tag, node, data);
+ result = tag_compare(tag, data->tag);
+ RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+ " data.tag=0x%llx (uid=%u) res=%d\n",
+ tag, data->tag, get_uid_from_tag(data->tag), result);
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void tag_node_tree_insert(struct tag_node *data, struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct tag_node *this = rb_entry(*new, struct tag_node,
+ node);
+ int result = tag_compare(data->tag, this->tag);
+ RB_DEBUG("qtaguid: %s(): tag=0x%llx"
+ " (uid=%u)\n", __func__,
+ this->tag,
+ get_uid_from_tag(this->tag));
+ parent = *new;
+ if (result < 0)
+ new = &((*new)->rb_left);
+ else if (result > 0)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void tag_stat_tree_insert(struct tag_stat *data, struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_stat *tag_stat_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_stat, tn.node);
+}
+
+static void tag_counter_set_tree_insert(struct tag_counter_set *data,
+ struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_counter_set *tag_counter_set_tree_search(struct rb_root *root,
+ tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_counter_set, tn.node);
+
+}
+
+static void tag_ref_tree_insert(struct tag_ref *data, struct rb_root *root)
+{
+ tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_ref *tag_ref_tree_search(struct rb_root *root, tag_t tag)
+{
+ struct tag_node *node = tag_node_tree_search(root, tag);
+ if (!node)
+ return NULL;
+ return rb_entry(&node->node, struct tag_ref, tn.node);
+}
+
+static struct sock_tag *sock_tag_tree_search(struct rb_root *root,
+ const struct sock *sk)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct sock_tag *data = rb_entry(node, struct sock_tag,
+ sock_node);
+ if (sk < data->sk)
+ node = node->rb_left;
+ else if (sk > data->sk)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void sock_tag_tree_insert(struct sock_tag *data, struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct sock_tag *this = rb_entry(*new, struct sock_tag,
+ sock_node);
+ parent = *new;
+ if (data->sk < this->sk)
+ new = &((*new)->rb_left);
+ else if (data->sk > this->sk)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->sock_node, parent, new);
+ rb_insert_color(&data->sock_node, root);
+}
+
+static void sock_tag_tree_erase(struct rb_root *st_to_free_tree)
+{
+ struct rb_node *node;
+ struct sock_tag *st_entry;
+
+ node = rb_first(st_to_free_tree);
+ while (node) {
+ st_entry = rb_entry(node, struct sock_tag, sock_node);
+ node = rb_next(node);
+ CT_DEBUG("qtaguid: %s(): "
+ "erase st: sk=%p tag=0x%llx (uid=%u)\n", __func__,
+ st_entry->sk,
+ st_entry->tag,
+ get_uid_from_tag(st_entry->tag));
+ rb_erase(&st_entry->sock_node, st_to_free_tree);
+ sockfd_put(st_entry->socket);
+ kfree(st_entry);
+ }
+}
+
+static struct proc_qtu_data *proc_qtu_data_tree_search(struct rb_root *root,
+ const pid_t pid)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct proc_qtu_data *data = rb_entry(node,
+ struct proc_qtu_data,
+ node);
+ if (pid < data->pid)
+ node = node->rb_left;
+ else if (pid > data->pid)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static void proc_qtu_data_tree_insert(struct proc_qtu_data *data,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct proc_qtu_data *this = rb_entry(*new,
+ struct proc_qtu_data,
+ node);
+ parent = *new;
+ if (data->pid < this->pid)
+ new = &((*new)->rb_left);
+ else if (data->pid > this->pid)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void uid_tag_data_tree_insert(struct uid_tag_data *data,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct uid_tag_data *this = rb_entry(*new,
+ struct uid_tag_data,
+ node);
+ parent = *new;
+ if (data->uid < this->uid)
+ new = &((*new)->rb_left);
+ else if (data->uid > this->uid)
+ new = &((*new)->rb_right);
+ else
+ BUG();
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static struct uid_tag_data *uid_tag_data_tree_search(struct rb_root *root,
+ uid_t uid)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct uid_tag_data *data = rb_entry(node,
+ struct uid_tag_data,
+ node);
+ if (uid < data->uid)
+ node = node->rb_left;
+ else if (uid > data->uid)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+/*
+ * Allocates a new uid_tag_data struct if needed.
+ * Returns a pointer to the found or allocated uid_tag_data.
+ * Returns a PTR_ERR on failures, and lock is not held.
+ * If found is not NULL:
+ * sets *found to true if not allocated.
+ * sets *found to false if allocated.
+ */
+struct uid_tag_data *get_uid_data(uid_t uid, bool *found_res)
+{
+ struct uid_tag_data *utd_entry;
+
+ /* Look for top level uid_tag_data for the UID */
+ utd_entry = uid_tag_data_tree_search(&uid_tag_data_tree, uid);
+ DR_DEBUG("qtaguid: get_uid_data(%u) utd=%p\n", uid, utd_entry);
+
+ if (found_res)
+ *found_res = utd_entry;
+ if (utd_entry)
+ return utd_entry;
+
+ utd_entry = kzalloc(sizeof(*utd_entry), GFP_ATOMIC);
+ if (!utd_entry) {
+ pr_err("qtaguid: get_uid_data(%u): "
+ "tag data alloc failed\n", uid);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ utd_entry->uid = uid;
+ utd_entry->tag_ref_tree = RB_ROOT;
+ uid_tag_data_tree_insert(utd_entry, &uid_tag_data_tree);
+ DR_DEBUG("qtaguid: get_uid_data(%u) new utd=%p\n", uid, utd_entry);
+ return utd_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *new_tag_ref(tag_t new_tag,
+ struct uid_tag_data *utd_entry)
+{
+ struct tag_ref *tr_entry;
+ int res;
+
+ if (utd_entry->num_active_tags + 1 > max_sock_tags) {
+ pr_info("qtaguid: new_tag_ref(0x%llx): "
+ "tag ref alloc quota exceeded. max=%d\n",
+ new_tag, max_sock_tags);
+ res = -EMFILE;
+ goto err_res;
+
+ }
+
+ tr_entry = kzalloc(sizeof(*tr_entry), GFP_ATOMIC);
+ if (!tr_entry) {
+ pr_err("qtaguid: new_tag_ref(0x%llx): "
+ "tag ref alloc failed\n",
+ new_tag);
+ res = -ENOMEM;
+ goto err_res;
+ }
+ tr_entry->tn.tag = new_tag;
+ /* tr_entry->num_sock_tags handled by caller */
+ utd_entry->num_active_tags++;
+ tag_ref_tree_insert(tr_entry, &utd_entry->tag_ref_tree);
+ DR_DEBUG("qtaguid: new_tag_ref(0x%llx): "
+ " inserted new tag ref %p\n",
+ new_tag, tr_entry);
+ return tr_entry;
+
+err_res:
+ return ERR_PTR(res);
+}
+
+static struct tag_ref *lookup_tag_ref(tag_t full_tag,
+ struct uid_tag_data **utd_res)
+{
+ struct uid_tag_data *utd_entry;
+ struct tag_ref *tr_entry;
+ bool found_utd;
+ uid_t uid = get_uid_from_tag(full_tag);
+
+ DR_DEBUG("qtaguid: lookup_tag_ref(tag=0x%llx (uid=%u))\n",
+ full_tag, uid);
+
+ utd_entry = get_uid_data(uid, &found_utd);
+ if (IS_ERR_OR_NULL(utd_entry)) {
+ if (utd_res)
+ *utd_res = utd_entry;
+ return NULL;
+ }
+
+ tr_entry = tag_ref_tree_search(&utd_entry->tag_ref_tree, full_tag);
+ if (utd_res)
+ *utd_res = utd_entry;
+ DR_DEBUG("qtaguid: lookup_tag_ref(0x%llx) utd_entry=%p tr_entry=%p\n",
+ full_tag, utd_entry, tr_entry);
+ return tr_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *get_tag_ref(tag_t full_tag,
+ struct uid_tag_data **utd_res)
+{
+ struct uid_tag_data *utd_entry;
+ struct tag_ref *tr_entry;
+
+ DR_DEBUG("qtaguid: get_tag_ref(0x%llx)\n",
+ full_tag);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ tr_entry = lookup_tag_ref(full_tag, &utd_entry);
+ BUG_ON(IS_ERR_OR_NULL(utd_entry));
+ if (!tr_entry)
+ tr_entry = new_tag_ref(full_tag, utd_entry);
+
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ if (utd_res)
+ *utd_res = utd_entry;
+ DR_DEBUG("qtaguid: get_tag_ref(0x%llx) utd=%p tr=%p\n",
+ full_tag, utd_entry, tr_entry);
+ return tr_entry;
+}
+
+/* Checks and maybe frees the UID Tag Data entry */
+static void put_utd_entry(struct uid_tag_data *utd_entry)
+{
+ /* Are we done with the UID tag data entry? */
+ if (RB_EMPTY_ROOT(&utd_entry->tag_ref_tree) &&
+ !utd_entry->num_pqd) {
+ DR_DEBUG("qtaguid: %s(): "
+ "erase utd_entry=%p uid=%u "
+ "by pid=%u tgid=%u uid=%u\n", __func__,
+ utd_entry, utd_entry->uid,
+ current->pid, current->tgid, current_fsuid());
+ BUG_ON(utd_entry->num_active_tags);
+ rb_erase(&utd_entry->node, &uid_tag_data_tree);
+ kfree(utd_entry);
+ } else {
+ DR_DEBUG("qtaguid: %s(): "
+ "utd_entry=%p still has %d tags %d proc_qtu_data\n",
+ __func__, utd_entry, utd_entry->num_active_tags,
+ utd_entry->num_pqd);
+ BUG_ON(!(utd_entry->num_active_tags ||
+ utd_entry->num_pqd));
+ }
+}
+
+/*
+ * If no sock_tags are using this tag_ref,
+ * decrements refcount of utd_entry, removes tr_entry
+ * from utd_entry->tag_ref_tree and frees.
+ */
+static void free_tag_ref_from_utd_entry(struct tag_ref *tr_entry,
+ struct uid_tag_data *utd_entry)
+{
+ DR_DEBUG("qtaguid: %s(): %p tag=0x%llx (uid=%u)\n", __func__,
+ tr_entry, tr_entry->tn.tag,
+ get_uid_from_tag(tr_entry->tn.tag));
+ if (!tr_entry->num_sock_tags) {
+ BUG_ON(!utd_entry->num_active_tags);
+ utd_entry->num_active_tags--;
+ rb_erase(&tr_entry->tn.node, &utd_entry->tag_ref_tree);
+ DR_DEBUG("qtaguid: %s(): erased %p\n", __func__, tr_entry);
+ kfree(tr_entry);
+ }
+}
+
+static void put_tag_ref_tree(tag_t full_tag, struct uid_tag_data *utd_entry)
+{
+ struct rb_node *node;
+ struct tag_ref *tr_entry;
+ tag_t acct_tag;
+
+ DR_DEBUG("qtaguid: %s(tag=0x%llx (uid=%u))\n", __func__,
+ full_tag, get_uid_from_tag(full_tag));
+ acct_tag = get_atag_from_tag(full_tag);
+ node = rb_first(&utd_entry->tag_ref_tree);
+ while (node) {
+ tr_entry = rb_entry(node, struct tag_ref, tn.node);
+ node = rb_next(node);
+ if (!acct_tag || tr_entry->tn.tag == full_tag)
+ free_tag_ref_from_utd_entry(tr_entry, utd_entry);
+ }
+}
+
+static ssize_t read_proc_u64(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ uint64_t *valuep = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", *valuep);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t read_proc_bool(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ bool *valuep = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%u\n", *valuep);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static int get_active_counter_set(tag_t tag)
+{
+ int active_set = 0;
+ struct tag_counter_set *tcs;
+
+ MT_DEBUG("qtaguid: get_active_counter_set(tag=0x%llx)"
+ " (uid=%u)\n",
+ tag, get_uid_from_tag(tag));
+ /* For now we only handle UID tags for active sets */
+ tag = get_utag_from_tag(tag);
+ spin_lock_bh(&tag_counter_set_list_lock);
+ tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (tcs)
+ active_set = tcs->active_set;
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ return active_set;
+}
+
+/*
+ * Find the entry for tracking the specified interface.
+ * Caller must hold iface_stat_list_lock
+ */
+static struct iface_stat *get_iface_entry(const char *ifname)
+{
+ struct iface_stat *iface_entry;
+
+ /* Find the entry for tracking the specified tag within the interface */
+ if (ifname == NULL) {
+ pr_info("qtaguid: iface_stat: get() NULL device name\n");
+ return NULL;
+ }
+
+ /* Iterate over interfaces */
+ list_for_each_entry(iface_entry, &iface_stat_list, list) {
+ if (!strcmp(ifname, iface_entry->ifname))
+ goto done;
+ }
+ iface_entry = NULL;
+done:
+ return iface_entry;
+}
+
+/* This is for fmt2 only */
+static void pp_iface_stat_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "ifname "
+ "total_skb_rx_bytes total_skb_rx_packets "
+ "total_skb_tx_bytes total_skb_tx_packets "
+ "rx_tcp_bytes rx_tcp_packets "
+ "rx_udp_bytes rx_udp_packets "
+ "rx_other_bytes rx_other_packets "
+ "tx_tcp_bytes tx_tcp_packets "
+ "tx_udp_bytes tx_udp_packets "
+ "tx_other_bytes tx_other_packets\n"
+ );
+}
+
+static void pp_iface_stat_line(struct seq_file *m,
+ struct iface_stat *iface_entry)
+{
+ struct data_counters *cnts;
+ int cnt_set = 0; /* We only use one set for the device */
+ cnts = &iface_entry->totals_via_skb;
+ seq_printf(m, "%s %llu %llu %llu %llu %llu %llu %llu %llu "
+ "%llu %llu %llu %llu %llu %llu %llu %llu\n",
+ iface_entry->ifname,
+ dc_sum_bytes(cnts, cnt_set, IFS_RX),
+ dc_sum_packets(cnts, cnt_set, IFS_RX),
+ dc_sum_bytes(cnts, cnt_set, IFS_TX),
+ dc_sum_packets(cnts, cnt_set, IFS_TX),
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+}
+
+struct proc_iface_stat_fmt_info {
+ int fmt;
+};
+
+static void *iface_stat_fmt_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_iface_stat_fmt_info *p = m->private;
+ loff_t n = *pos;
+
+ /*
+ * This lock will prevent iface_stat_update() from changing active,
+ * and in turn prevent an interface from unregistering itself.
+ */
+ spin_lock_bh(&iface_stat_list_lock);
+
+ if (unlikely(module_passive))
+ return NULL;
+
+ if (!n && p->fmt == 2)
+ pp_iface_stat_header(m);
+
+ return seq_list_start(&iface_stat_list, n);
+}
+
+static void *iface_stat_fmt_proc_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ return seq_list_next(p, &iface_stat_list, pos);
+}
+
+static void iface_stat_fmt_proc_stop(struct seq_file *m, void *p)
+{
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static int iface_stat_fmt_proc_show(struct seq_file *m, void *v)
+{
+ struct proc_iface_stat_fmt_info *p = m->private;
+ struct iface_stat *iface_entry;
+ struct rtnl_link_stats64 dev_stats, *stats;
+ struct rtnl_link_stats64 no_dev_stats = {0};
+
+
+ CT_DEBUG("qtaguid:proc iface_stat_fmt pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, current_fsuid());
+
+ iface_entry = list_entry(v, struct iface_stat, list);
+
+ if (iface_entry->active) {
+ stats = dev_get_stats(iface_entry->net_dev,
+ &dev_stats);
+ } else {
+ stats = &no_dev_stats;
+ }
+ /*
+ * If the meaning of the data changes, then update the fmtX
+ * string.
+ */
+ if (p->fmt == 1) {
+ seq_printf(m, "%s %d %llu %llu %llu %llu %llu %llu %llu %llu\n",
+ iface_entry->ifname,
+ iface_entry->active,
+ iface_entry->totals_via_dev[IFS_RX].bytes,
+ iface_entry->totals_via_dev[IFS_RX].packets,
+ iface_entry->totals_via_dev[IFS_TX].bytes,
+ iface_entry->totals_via_dev[IFS_TX].packets,
+ stats->rx_bytes, stats->rx_packets,
+ stats->tx_bytes, stats->tx_packets
+ );
+ } else {
+ pp_iface_stat_line(m, iface_entry);
+ }
+ return 0;
+}
+
+static const struct file_operations read_u64_fops = {
+ .read = read_proc_u64,
+ .llseek = default_llseek,
+};
+
+static const struct file_operations read_bool_fops = {
+ .read = read_proc_bool,
+ .llseek = default_llseek,
+};
+
+static void iface_create_proc_worker(struct work_struct *work)
+{
+ struct proc_dir_entry *proc_entry;
+ struct iface_stat_work *isw = container_of(work, struct iface_stat_work,
+ iface_work);
+ struct iface_stat *new_iface = isw->iface_entry;
+
+ /* iface_entries are not deleted, so safe to manipulate. */
+ proc_entry = proc_mkdir(new_iface->ifname, iface_stat_procdir);
+ if (IS_ERR_OR_NULL(proc_entry)) {
+ pr_err("qtaguid: iface_stat: create_proc(): alloc failed.\n");
+ kfree(isw);
+ return;
+ }
+
+ new_iface->proc_ptr = proc_entry;
+
+ proc_create_data("tx_bytes", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_TX].bytes);
+ proc_create_data("rx_bytes", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_RX].bytes);
+ proc_create_data("tx_packets", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_TX].packets);
+ proc_create_data("rx_packets", proc_iface_perms, proc_entry,
+ &read_u64_fops,
+ &new_iface->totals_via_dev[IFS_RX].packets);
+ proc_create_data("active", proc_iface_perms, proc_entry,
+ &read_bool_fops, &new_iface->active);
+
+ IF_DEBUG("qtaguid: iface_stat: create_proc(): done "
+ "entry=%p dev=%s\n", new_iface, new_iface->ifname);
+ kfree(isw);
+}
+
+/*
+ * Will set the entry's active state, and
+ * update the net_dev accordingly also.
+ */
+static void _iface_stat_set_active(struct iface_stat *entry,
+ struct net_device *net_dev,
+ bool activate)
+{
+ if (activate) {
+ entry->net_dev = net_dev;
+ entry->active = true;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "enable tracking. rfcnt=%d\n", __func__,
+ entry->ifname,
+ __this_cpu_read(*net_dev->pcpu_refcnt));
+ } else {
+ entry->active = false;
+ entry->net_dev = NULL;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "disable tracking. rfcnt=%d\n", __func__,
+ entry->ifname,
+ __this_cpu_read(*net_dev->pcpu_refcnt));
+
+ }
+}
+
+/* Caller must hold iface_stat_list_lock */
+static struct iface_stat *iface_alloc(struct net_device *net_dev)
+{
+ struct iface_stat *new_iface;
+ struct iface_stat_work *isw;
+
+ new_iface = kzalloc(sizeof(*new_iface), GFP_ATOMIC);
+ if (new_iface == NULL) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "iface_stat alloc failed\n", net_dev->name);
+ return NULL;
+ }
+ new_iface->ifname = kstrdup(net_dev->name, GFP_ATOMIC);
+ if (new_iface->ifname == NULL) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "ifname alloc failed\n", net_dev->name);
+ kfree(new_iface);
+ return NULL;
+ }
+ spin_lock_init(&new_iface->tag_stat_list_lock);
+ new_iface->tag_stat_tree = RB_ROOT;
+ _iface_stat_set_active(new_iface, net_dev, true);
+
+ /*
+ * ipv6 notifier chains are atomic :(
+ * No create_proc_read_entry() for you!
+ */
+ isw = kmalloc(sizeof(*isw), GFP_ATOMIC);
+ if (!isw) {
+ pr_err("qtaguid: iface_stat: create(%s): "
+ "work alloc failed\n", new_iface->ifname);
+ _iface_stat_set_active(new_iface, net_dev, false);
+ kfree(new_iface->ifname);
+ kfree(new_iface);
+ return NULL;
+ }
+ isw->iface_entry = new_iface;
+ INIT_WORK(&isw->iface_work, iface_create_proc_worker);
+ schedule_work(&isw->iface_work);
+ list_add(&new_iface->list, &iface_stat_list);
+ return new_iface;
+}
+
+static void iface_check_stats_reset_and_adjust(struct net_device *net_dev,
+ struct iface_stat *iface)
+{
+ struct rtnl_link_stats64 dev_stats, *stats;
+ bool stats_rewound;
+
+ stats = dev_get_stats(net_dev, &dev_stats);
+ /* No empty packets */
+ stats_rewound =
+ (stats->rx_bytes < iface->last_known[IFS_RX].bytes)
+ || (stats->tx_bytes < iface->last_known[IFS_TX].bytes);
+
+ IF_DEBUG("qtaguid: %s(%s): iface=%p netdev=%p "
+ "bytes rx/tx=%llu/%llu "
+ "active=%d last_known=%d "
+ "stats_rewound=%d\n", __func__,
+ net_dev ? net_dev->name : "?",
+ iface, net_dev,
+ stats->rx_bytes, stats->tx_bytes,
+ iface->active, iface->last_known_valid, stats_rewound);
+
+ if (iface->active && iface->last_known_valid && stats_rewound) {
+ pr_warn_once("qtaguid: iface_stat: %s(%s): "
+ "iface reset its stats unexpectedly\n", __func__,
+ net_dev->name);
+
+ iface->totals_via_dev[IFS_TX].bytes +=
+ iface->last_known[IFS_TX].bytes;
+ iface->totals_via_dev[IFS_TX].packets +=
+ iface->last_known[IFS_TX].packets;
+ iface->totals_via_dev[IFS_RX].bytes +=
+ iface->last_known[IFS_RX].bytes;
+ iface->totals_via_dev[IFS_RX].packets +=
+ iface->last_known[IFS_RX].packets;
+ iface->last_known_valid = false;
+ IF_DEBUG("qtaguid: %s(%s): iface=%p "
+ "used last known bytes rx/tx=%llu/%llu\n", __func__,
+ iface->ifname, iface, iface->last_known[IFS_RX].bytes,
+ iface->last_known[IFS_TX].bytes);
+ }
+}
+
+/*
+ * Create a new entry for tracking the specified interface.
+ * Do nothing if the entry already exists.
+ * Called when an interface is configured with a valid IP address.
+ */
+static void iface_stat_create(struct net_device *net_dev,
+ struct in_ifaddr *ifa)
+{
+ struct in_device *in_dev = NULL;
+ const char *ifname;
+ struct iface_stat *entry;
+ __be32 ipaddr = 0;
+ struct iface_stat *new_iface;
+
+ IF_DEBUG("qtaguid: iface_stat: create(%s): ifa=%p netdev=%p\n",
+ net_dev ? net_dev->name : "?",
+ ifa, net_dev);
+ if (!net_dev) {
+ pr_err("qtaguid: iface_stat: create(): no net dev\n");
+ return;
+ }
+
+ ifname = net_dev->name;
+ if (!ifa) {
+ in_dev = in_dev_get(net_dev);
+ if (!in_dev) {
+ pr_err("qtaguid: iface_stat: create(%s): no inet dev\n",
+ ifname);
+ return;
+ }
+ IF_DEBUG("qtaguid: iface_stat: create(%s): in_dev=%p\n",
+ ifname, in_dev);
+ for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): "
+ "ifa=%p ifa_label=%s\n",
+ ifname, ifa,
+ ifa->ifa_label ? ifa->ifa_label : "(null)");
+ if (ifa->ifa_label && !strcmp(ifname, ifa->ifa_label))
+ break;
+ }
+ }
+
+ if (!ifa) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): no matching IP\n",
+ ifname);
+ goto done_put;
+ }
+ ipaddr = ifa->ifa_local;
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(ifname);
+ if (entry != NULL) {
+ IF_DEBUG("qtaguid: iface_stat: create(%s): entry=%p\n",
+ ifname, entry);
+ iface_check_stats_reset_and_adjust(net_dev, entry);
+ _iface_stat_set_active(entry, net_dev, true);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "tracking now %d on ip=%pI4\n", __func__,
+ entry->ifname, true, &ipaddr);
+ goto done_unlock_put;
+ }
+
+ new_iface = iface_alloc(net_dev);
+ IF_DEBUG("qtaguid: iface_stat: create(%s): done "
+ "entry=%p ip=%pI4\n", ifname, new_iface, &ipaddr);
+done_unlock_put:
+ spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+ if (in_dev)
+ in_dev_put(in_dev);
+}
+
+static void iface_stat_create_ipv6(struct net_device *net_dev,
+ struct inet6_ifaddr *ifa)
+{
+ struct in_device *in_dev;
+ const char *ifname;
+ struct iface_stat *entry;
+ struct iface_stat *new_iface;
+ int addr_type;
+
+ IF_DEBUG("qtaguid: iface_stat: create6(): ifa=%p netdev=%p->name=%s\n",
+ ifa, net_dev, net_dev ? net_dev->name : "");
+ if (!net_dev) {
+ pr_err("qtaguid: iface_stat: create6(): no net dev!\n");
+ return;
+ }
+ ifname = net_dev->name;
+
+ in_dev = in_dev_get(net_dev);
+ if (!in_dev) {
+ pr_err("qtaguid: iface_stat: create6(%s): no inet dev\n",
+ ifname);
+ return;
+ }
+
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): in_dev=%p\n",
+ ifname, in_dev);
+
+ if (!ifa) {
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): no matching IP\n",
+ ifname);
+ goto done_put;
+ }
+ addr_type = ipv6_addr_type(&ifa->addr);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(ifname);
+ if (entry != NULL) {
+ IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+ ifname, entry);
+ iface_check_stats_reset_and_adjust(net_dev, entry);
+ _iface_stat_set_active(entry, net_dev, true);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "tracking now %d on ip=%pI6c\n", __func__,
+ entry->ifname, true, &ifa->addr);
+ goto done_unlock_put;
+ }
+
+ new_iface = iface_alloc(net_dev);
+ IF_DEBUG("qtaguid: iface_stat: create6(%s): done "
+ "entry=%p ip=%pI6c\n", ifname, new_iface, &ifa->addr);
+
+done_unlock_put:
+ spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+ in_dev_put(in_dev);
+}
+
+static struct sock_tag *get_sock_stat_nl(const struct sock *sk)
+{
+ MT_DEBUG("qtaguid: get_sock_stat_nl(sk=%p)\n", sk);
+ return sock_tag_tree_search(&sock_tag_tree, sk);
+}
+
+static struct sock_tag *get_sock_stat(const struct sock *sk)
+{
+ struct sock_tag *sock_tag_entry;
+ MT_DEBUG("qtaguid: get_sock_stat(sk=%p)\n", sk);
+ if (!sk)
+ return NULL;
+ spin_lock_bh(&sock_tag_list_lock);
+ sock_tag_entry = get_sock_stat_nl(sk);
+ spin_unlock_bh(&sock_tag_list_lock);
+ return sock_tag_entry;
+}
+
+static int ipx_proto(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ int thoff = 0, tproto;
+
+ switch (par->family) {
+ case NFPROTO_IPV6:
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
+ if (tproto < 0)
+ MT_DEBUG("%s(): transport header not found in ipv6"
+ " skb=%p\n", __func__, skb);
+ break;
+ case NFPROTO_IPV4:
+ tproto = ip_hdr(skb)->protocol;
+ break;
+ default:
+ tproto = IPPROTO_RAW;
+ }
+ return tproto;
+}
+
+static void
+data_counters_update(struct data_counters *dc, int set,
+ enum ifs_tx_rx direction, int proto, int bytes)
+{
+ switch (proto) {
+ case IPPROTO_TCP:
+ dc_add_byte_packets(dc, set, direction, IFS_TCP, bytes, 1);
+ break;
+ case IPPROTO_UDP:
+ dc_add_byte_packets(dc, set, direction, IFS_UDP, bytes, 1);
+ break;
+ case IPPROTO_IP:
+ default:
+ dc_add_byte_packets(dc, set, direction, IFS_PROTO_OTHER, bytes,
+ 1);
+ break;
+ }
+}
+
+/*
+ * Update stats for the specified interface. Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called when an device is being unregistered.
+ */
+static void iface_stat_update(struct net_device *net_dev, bool stash_only)
+{
+ struct rtnl_link_stats64 dev_stats, *stats;
+ struct iface_stat *entry;
+
+ stats = dev_get_stats(net_dev, &dev_stats);
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(net_dev->name);
+ if (entry == NULL) {
+ IF_DEBUG("qtaguid: iface_stat: update(%s): not tracked\n",
+ net_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+ net_dev->name, entry);
+ if (!entry->active) {
+ IF_DEBUG("qtaguid: %s(%s): already disabled\n", __func__,
+ net_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ if (stash_only) {
+ entry->last_known[IFS_TX].bytes = stats->tx_bytes;
+ entry->last_known[IFS_TX].packets = stats->tx_packets;
+ entry->last_known[IFS_RX].bytes = stats->rx_bytes;
+ entry->last_known[IFS_RX].packets = stats->rx_packets;
+ entry->last_known_valid = true;
+ IF_DEBUG("qtaguid: %s(%s): "
+ "dev stats stashed rx/tx=%llu/%llu\n", __func__,
+ net_dev->name, stats->rx_bytes, stats->tx_bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+ entry->totals_via_dev[IFS_TX].bytes += stats->tx_bytes;
+ entry->totals_via_dev[IFS_TX].packets += stats->tx_packets;
+ entry->totals_via_dev[IFS_RX].bytes += stats->rx_bytes;
+ entry->totals_via_dev[IFS_RX].packets += stats->rx_packets;
+ /* We don't need the last_known[] anymore */
+ entry->last_known_valid = false;
+ _iface_stat_set_active(entry, net_dev, false);
+ IF_DEBUG("qtaguid: %s(%s): "
+ "disable tracking. rx/tx=%llu/%llu\n", __func__,
+ net_dev->name, stats->rx_bytes, stats->tx_bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/*
+ * Update stats for the specified interface from the skb.
+ * Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called on each sk.
+ */
+static void iface_stat_update_from_skb(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ struct iface_stat *entry;
+ const struct net_device *el_dev;
+ enum ifs_tx_rx direction = par->in ? IFS_RX : IFS_TX;
+ int bytes = skb->len;
+ int proto;
+
+ if (!skb->dev) {
+ MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum);
+ el_dev = par->in ? : par->out;
+ } else {
+ const struct net_device *other_dev;
+ el_dev = skb->dev;
+ other_dev = par->in ? : par->out;
+ if (el_dev != other_dev) {
+ MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs "
+ "par->(in/out)=%p %s\n",
+ par->hooknum, el_dev, el_dev->name, other_dev,
+ other_dev->name);
+ }
+ }
+
+ if (unlikely(!el_dev)) {
+ pr_err_ratelimited("qtaguid[%d]: %s(): no par->in/out?!!\n",
+ par->hooknum, __func__);
+ BUG();
+ } else if (unlikely(!el_dev->name)) {
+ pr_err_ratelimited("qtaguid[%d]: %s(): no dev->name?!!\n",
+ par->hooknum, __func__);
+ BUG();
+ } else {
+ proto = ipx_proto(skb, par);
+ MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n",
+ par->hooknum, el_dev->name, el_dev->type,
+ par->family, proto);
+ }
+
+ spin_lock_bh(&iface_stat_list_lock);
+ entry = get_iface_entry(el_dev->name);
+ if (entry == NULL) {
+ IF_DEBUG("qtaguid: iface_stat: %s(%s): not tracked\n",
+ __func__, el_dev->name);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+
+ IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+ el_dev->name, entry);
+
+ data_counters_update(&entry->totals_via_skb, 0, direction, proto,
+ bytes);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static void tag_stat_update(struct tag_stat *tag_entry,
+ enum ifs_tx_rx direction, int proto, int bytes)
+{
+ int active_set;
+ active_set = get_active_counter_set(tag_entry->tn.tag);
+ MT_DEBUG("qtaguid: tag_stat_update(tag=0x%llx (uid=%u) set=%d "
+ "dir=%d proto=%d bytes=%d)\n",
+ tag_entry->tn.tag, get_uid_from_tag(tag_entry->tn.tag),
+ active_set, direction, proto, bytes);
+ data_counters_update(&tag_entry->counters, active_set, direction,
+ proto, bytes);
+ if (tag_entry->parent_counters)
+ data_counters_update(tag_entry->parent_counters, active_set,
+ direction, proto, bytes);
+}
+
+/*
+ * Create a new entry for tracking the specified {acct_tag,uid_tag} within
+ * the interface.
+ * iface_entry->tag_stat_list_lock should be held.
+ */
+static struct tag_stat *create_if_tag_stat(struct iface_stat *iface_entry,
+ tag_t tag)
+{
+ struct tag_stat *new_tag_stat_entry = NULL;
+ IF_DEBUG("qtaguid: iface_stat: %s(): ife=%p tag=0x%llx"
+ " (uid=%u)\n", __func__,
+ iface_entry, tag, get_uid_from_tag(tag));
+ new_tag_stat_entry = kzalloc(sizeof(*new_tag_stat_entry), GFP_ATOMIC);
+ if (!new_tag_stat_entry) {
+ pr_err("qtaguid: iface_stat: tag stat alloc failed\n");
+ goto done;
+ }
+ new_tag_stat_entry->tn.tag = tag;
+ tag_stat_tree_insert(new_tag_stat_entry, &iface_entry->tag_stat_tree);
+done:
+ return new_tag_stat_entry;
+}
+
+static void if_tag_stat_update(const char *ifname, uid_t uid,
+ const struct sock *sk, enum ifs_tx_rx direction,
+ int proto, int bytes)
+{
+ struct tag_stat *tag_stat_entry;
+ tag_t tag, acct_tag;
+ tag_t uid_tag;
+ struct data_counters *uid_tag_counters;
+ struct sock_tag *sock_tag_entry;
+ struct iface_stat *iface_entry;
+ struct tag_stat *new_tag_stat = NULL;
+ MT_DEBUG("qtaguid: if_tag_stat_update(ifname=%s "
+ "uid=%u sk=%p dir=%d proto=%d bytes=%d)\n",
+ ifname, uid, sk, direction, proto, bytes);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ iface_entry = get_iface_entry(ifname);
+ if (!iface_entry) {
+ pr_err_ratelimited("qtaguid: iface_stat: stat_update() "
+ "%s not found\n", ifname);
+ spin_unlock_bh(&iface_stat_list_lock);
+ return;
+ }
+ /* It is ok to process data when an iface_entry is inactive */
+
+ MT_DEBUG("qtaguid: iface_stat: stat_update() dev=%s entry=%p\n",
+ ifname, iface_entry);
+
+ /*
+ * Look for a tagged sock.
+ * It will have an acct_uid.
+ */
+ sock_tag_entry = get_sock_stat(sk);
+ if (sock_tag_entry) {
+ tag = sock_tag_entry->tag;
+ acct_tag = get_atag_from_tag(tag);
+ uid_tag = get_utag_from_tag(tag);
+ } else {
+ acct_tag = make_atag_from_value(0);
+ tag = combine_atag_with_uid(acct_tag, uid);
+ uid_tag = make_tag_from_uid(uid);
+ }
+ MT_DEBUG("qtaguid: iface_stat: stat_update(): "
+ " looking for tag=0x%llx (uid=%u) in ife=%p\n",
+ tag, get_uid_from_tag(tag), iface_entry);
+ /* Loop over tag list under this interface for {acct_tag,uid_tag} */
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+
+ tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+ tag);
+ if (tag_stat_entry) {
+ /*
+ * Updating the {acct_tag, uid_tag} entry handles both stats:
+ * {0, uid_tag} will also get updated.
+ */
+ tag_stat_update(tag_stat_entry, direction, proto, bytes);
+ goto unlock;
+ }
+
+ /* Loop over tag list under this interface for {0,uid_tag} */
+ tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+ uid_tag);
+ if (!tag_stat_entry) {
+ /* Here: the base uid_tag did not exist */
+ /*
+ * No parent counters. So
+ * - No {0, uid_tag} stats and no {acc_tag, uid_tag} stats.
+ */
+ new_tag_stat = create_if_tag_stat(iface_entry, uid_tag);
+ if (!new_tag_stat)
+ goto unlock;
+ uid_tag_counters = &new_tag_stat->counters;
+ } else {
+ uid_tag_counters = &tag_stat_entry->counters;
+ }
+
+ if (acct_tag) {
+ /* Create the child {acct_tag, uid_tag} and hook up parent. */
+ new_tag_stat = create_if_tag_stat(iface_entry, tag);
+ if (!new_tag_stat)
+ goto unlock;
+ new_tag_stat->parent_counters = uid_tag_counters;
+ } else {
+ /*
+ * For new_tag_stat to be still NULL here would require:
+ * {0, uid_tag} exists
+ * and {acct_tag, uid_tag} doesn't exist
+ * AND acct_tag == 0.
+ * Impossible. This reassures us that new_tag_stat
+ * below will always be assigned.
+ */
+ BUG_ON(!new_tag_stat);
+ }
+ tag_stat_update(new_tag_stat, direction, proto, bytes);
+unlock:
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static int iface_netdev_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr) {
+ struct net_device *dev = ptr;
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: netdev_event(): "
+ "ev=0x%lx/%s netdev=%p->name=%s\n",
+ event, netdev_evt_str(event), dev, dev ? dev->name : "");
+
+ switch (event) {
+ case NETDEV_UP:
+ iface_stat_create(dev, NULL);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static int iface_inet6addr_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct inet6_ifaddr *ifa = ptr;
+ struct net_device *dev;
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: inet6addr_event(): "
+ "ev=0x%lx/%s ifa=%p\n",
+ event, netdev_evt_str(event), ifa);
+
+ switch (event) {
+ case NETDEV_UP:
+ BUG_ON(!ifa || !ifa->idev);
+ dev = (struct net_device *)ifa->idev->dev;
+ iface_stat_create_ipv6(dev, ifa);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ BUG_ON(!ifa || !ifa->idev);
+ dev = (struct net_device *)ifa->idev->dev;
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static int iface_inetaddr_event_handler(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = ptr;
+ struct net_device *dev;
+
+ if (unlikely(module_passive))
+ return NOTIFY_DONE;
+
+ IF_DEBUG("qtaguid: iface_stat: inetaddr_event(): "
+ "ev=0x%lx/%s ifa=%p\n",
+ event, netdev_evt_str(event), ifa);
+
+ switch (event) {
+ case NETDEV_UP:
+ BUG_ON(!ifa || !ifa->ifa_dev);
+ dev = ifa->ifa_dev->dev;
+ iface_stat_create(dev, ifa);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ BUG_ON(!ifa || !ifa->ifa_dev);
+ dev = ifa->ifa_dev->dev;
+ iface_stat_update(dev, event == NETDEV_DOWN);
+ atomic64_inc(&qtu_events.iface_events);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block iface_netdev_notifier_blk = {
+ .notifier_call = iface_netdev_event_handler,
+};
+
+static struct notifier_block iface_inetaddr_notifier_blk = {
+ .notifier_call = iface_inetaddr_event_handler,
+};
+
+static struct notifier_block iface_inet6addr_notifier_blk = {
+ .notifier_call = iface_inet6addr_event_handler,
+};
+
+static const struct seq_operations iface_stat_fmt_proc_seq_ops = {
+ .start = iface_stat_fmt_proc_start,
+ .next = iface_stat_fmt_proc_next,
+ .stop = iface_stat_fmt_proc_stop,
+ .show = iface_stat_fmt_proc_show,
+};
+
+static int proc_iface_stat_fmt_open(struct inode *inode, struct file *file)
+{
+ struct proc_iface_stat_fmt_info *s;
+
+ s = __seq_open_private(file, &iface_stat_fmt_proc_seq_ops,
+ sizeof(struct proc_iface_stat_fmt_info));
+ if (!s)
+ return -ENOMEM;
+
+ s->fmt = (uintptr_t)PDE_DATA(inode);
+ return 0;
+}
+
+static const struct file_operations proc_iface_stat_fmt_fops = {
+ .open = proc_iface_stat_fmt_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static int __init iface_stat_init(struct proc_dir_entry *parent_procdir)
+{
+ int err;
+
+ iface_stat_procdir = proc_mkdir(iface_stat_procdirname, parent_procdir);
+ if (!iface_stat_procdir) {
+ pr_err("qtaguid: iface_stat: init failed to create proc entry\n");
+ err = -1;
+ goto err;
+ }
+
+ iface_stat_all_procfile = proc_create_data(iface_stat_all_procfilename,
+ proc_iface_perms,
+ parent_procdir,
+ &proc_iface_stat_fmt_fops,
+ (void *)1 /* fmt1 */);
+ if (!iface_stat_all_procfile) {
+ pr_err("qtaguid: iface_stat: init "
+ " failed to create stat_old proc entry\n");
+ err = -1;
+ goto err_zap_entry;
+ }
+
+ iface_stat_fmt_procfile = proc_create_data(iface_stat_fmt_procfilename,
+ proc_iface_perms,
+ parent_procdir,
+ &proc_iface_stat_fmt_fops,
+ (void *)2 /* fmt2 */);
+ if (!iface_stat_fmt_procfile) {
+ pr_err("qtaguid: iface_stat: init "
+ " failed to create stat_all proc entry\n");
+ err = -1;
+ goto err_zap_all_stats_entry;
+ }
+
+
+ err = register_netdevice_notifier(&iface_netdev_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register dev event handler\n");
+ goto err_zap_all_stats_entries;
+ }
+ err = register_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register ipv4 dev event handler\n");
+ goto err_unreg_nd;
+ }
+
+ err = register_inet6addr_notifier(&iface_inet6addr_notifier_blk);
+ if (err) {
+ pr_err("qtaguid: iface_stat: init "
+ "failed to register ipv6 dev event handler\n");
+ goto err_unreg_ip4_addr;
+ }
+ return 0;
+
+err_unreg_ip4_addr:
+ unregister_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+err_unreg_nd:
+ unregister_netdevice_notifier(&iface_netdev_notifier_blk);
+err_zap_all_stats_entries:
+ remove_proc_entry(iface_stat_fmt_procfilename, parent_procdir);
+err_zap_all_stats_entry:
+ remove_proc_entry(iface_stat_all_procfilename, parent_procdir);
+err_zap_entry:
+ remove_proc_entry(iface_stat_procdirname, parent_procdir);
+err:
+ return err;
+}
+
+static struct sock *qtaguid_find_sk(const struct sk_buff *skb,
+ struct xt_action_param *par)
+{
+ struct sock *sk;
+ unsigned int hook_mask = (1 << par->hooknum);
+
+ MT_DEBUG("qtaguid: find_sk(skb=%p) hooknum=%d family=%d\n", skb,
+ par->hooknum, par->family);
+
+ /*
+ * Let's not abuse the the xt_socket_get*_sk(), or else it will
+ * return garbage SKs.
+ */
+ if (!(hook_mask & XT_SOCKET_SUPPORTED_HOOKS))
+ return NULL;
+
+ switch (par->family) {
+ case NFPROTO_IPV6:
+ sk = xt_socket_get6_sk(skb, par);
+ break;
+ case NFPROTO_IPV4:
+ sk = xt_socket_get4_sk(skb, par);
+ break;
+ default:
+ return NULL;
+ }
+
+ if (sk) {
+ MT_DEBUG("qtaguid: %p->sk_proto=%u "
+ "->sk_state=%d\n", sk, sk->sk_protocol, sk->sk_state);
+ /*
+ * When in TCP_TIME_WAIT the sk is not a "struct sock" but
+ * "struct inet_timewait_sock" which is missing fields.
+ */
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ xt_socket_put_sk(sk);
+ sk = NULL;
+ }
+ }
+ return sk;
+}
+
+static void account_for_uid(const struct sk_buff *skb,
+ const struct sock *alternate_sk, uid_t uid,
+ struct xt_action_param *par)
+{
+ const struct net_device *el_dev;
+
+ if (!skb->dev) {
+ MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum);
+ el_dev = par->in ? : par->out;
+ } else {
+ const struct net_device *other_dev;
+ el_dev = skb->dev;
+ other_dev = par->in ? : par->out;
+ if (el_dev != other_dev) {
+ MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs "
+ "par->(in/out)=%p %s\n",
+ par->hooknum, el_dev, el_dev->name, other_dev,
+ other_dev->name);
+ }
+ }
+
+ if (unlikely(!el_dev)) {
+ pr_info("qtaguid[%d]: no par->in/out?!!\n", par->hooknum);
+ } else if (unlikely(!el_dev->name)) {
+ pr_info("qtaguid[%d]: no dev->name?!!\n", par->hooknum);
+ } else {
+ int proto = ipx_proto(skb, par);
+ MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n",
+ par->hooknum, el_dev->name, el_dev->type,
+ par->family, proto);
+
+ if_tag_stat_update(el_dev->name, uid,
+ skb->sk ? skb->sk : alternate_sk,
+ par->in ? IFS_RX : IFS_TX,
+ proto, skb->len);
+ }
+}
+
+static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_qtaguid_match_info *info = par->matchinfo;
+ const struct file *filp;
+ bool got_sock = false;
+ struct sock *sk;
+ uid_t sock_uid;
+ bool res;
+ bool set_sk_callback_lock = false;
+
+ if (unlikely(module_passive))
+ return (info->match ^ info->invert) == 0;
+
+ MT_DEBUG("qtaguid[%d]: entered skb=%p par->in=%p/out=%p fam=%d\n",
+ par->hooknum, skb, par->in, par->out, par->family);
+
+ atomic64_inc(&qtu_events.match_calls);
+ if (skb == NULL) {
+ res = (info->match ^ info->invert) == 0;
+ goto ret_res;
+ }
+
+ switch (par->hooknum) {
+ case NF_INET_PRE_ROUTING:
+ case NF_INET_POST_ROUTING:
+ atomic64_inc(&qtu_events.match_calls_prepost);
+ iface_stat_update_from_skb(skb, par);
+ /*
+ * We are done in pre/post. The skb will get processed
+ * further alter.
+ */
+ res = (info->match ^ info->invert);
+ goto ret_res;
+ break;
+ /* default: Fall through and do UID releated work */
+ }
+
+ sk = skb->sk;
+ /*
+ * When in TCP_TIME_WAIT the sk is not a "struct sock" but
+ * "struct inet_timewait_sock" which is missing fields.
+ * So we ignore it.
+ */
+ if (sk && sk->sk_state == TCP_TIME_WAIT)
+ sk = NULL;
+ if (sk == NULL) {
+ /*
+ * A missing sk->sk_socket happens when packets are in-flight
+ * and the matching socket is already closed and gone.
+ */
+ sk = qtaguid_find_sk(skb, par);
+ /*
+ * If we got the socket from the find_sk(), we will need to put
+ * it back, as nf_tproxy_get_sock_v4() got it.
+ */
+ got_sock = sk;
+ if (sk)
+ atomic64_inc(&qtu_events.match_found_sk_in_ct);
+ else
+ atomic64_inc(&qtu_events.match_found_no_sk_in_ct);
+ } else {
+ atomic64_inc(&qtu_events.match_found_sk);
+ }
+ MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d fam=%d proto=%d\n",
+ par->hooknum, sk, got_sock, par->family, ipx_proto(skb, par));
+ if (sk != NULL) {
+ set_sk_callback_lock = true;
+ read_lock_bh(&sk->sk_callback_lock);
+ MT_DEBUG("qtaguid[%d]: sk=%p->sk_socket=%p->file=%p\n",
+ par->hooknum, sk, sk->sk_socket,
+ sk->sk_socket ? sk->sk_socket->file : (void *)-1LL);
+ filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+ MT_DEBUG("qtaguid[%d]: filp...uid=%u\n",
+ par->hooknum, filp ? filp->f_cred->fsuid : -1);
+ }
+
+ if (sk == NULL || sk->sk_socket == NULL) {
+ /*
+ * Here, the qtaguid_find_sk() using connection tracking
+ * couldn't find the owner, so for now we just count them
+ * against the system.
+ */
+ /*
+ * TODO: unhack how to force just accounting.
+ * For now we only do iface stats when the uid-owner is not
+ * requested.
+ */
+ if (!(info->match & XT_QTAGUID_UID))
+ account_for_uid(skb, sk, 0, par);
+ MT_DEBUG("qtaguid[%d]: leaving (sk?sk->sk_socket)=%p\n",
+ par->hooknum,
+ sk ? sk->sk_socket : NULL);
+ res = (info->match ^ info->invert) == 0;
+ atomic64_inc(&qtu_events.match_no_sk);
+ goto put_sock_ret_res;
+ } else if (info->match & info->invert & XT_QTAGUID_SOCKET) {
+ res = false;
+ goto put_sock_ret_res;
+ }
+ filp = sk->sk_socket->file;
+ if (filp == NULL) {
+ MT_DEBUG("qtaguid[%d]: leaving filp=NULL\n", par->hooknum);
+ account_for_uid(skb, sk, 0, par);
+ res = ((info->match ^ info->invert) &
+ (XT_QTAGUID_UID | XT_QTAGUID_GID)) == 0;
+ atomic64_inc(&qtu_events.match_no_sk_file);
+ goto put_sock_ret_res;
+ }
+ sock_uid = filp->f_cred->fsuid;
+ /*
+ * TODO: unhack how to force just accounting.
+ * For now we only do iface stats when the uid-owner is not requested
+ */
+ if (!(info->match & XT_QTAGUID_UID))
+ account_for_uid(skb, sk, sock_uid, par);
+
+ /*
+ * The following two tests fail the match when:
+ * id not in range AND no inverted condition requested
+ * or id in range AND inverted condition requested
+ * Thus (!a && b) || (a && !b) == a ^ b
+ */
+ if (info->match & XT_QTAGUID_UID)
+ if ((filp->f_cred->fsuid >= info->uid_min &&
+ filp->f_cred->fsuid <= info->uid_max) ^
+ !(info->invert & XT_QTAGUID_UID)) {
+ MT_DEBUG("qtaguid[%d]: leaving uid not matching\n",
+ par->hooknum);
+ res = false;
+ goto put_sock_ret_res;
+ }
+ if (info->match & XT_QTAGUID_GID)
+ if ((filp->f_cred->fsgid >= info->gid_min &&
+ filp->f_cred->fsgid <= info->gid_max) ^
+ !(info->invert & XT_QTAGUID_GID)) {
+ MT_DEBUG("qtaguid[%d]: leaving gid not matching\n",
+ par->hooknum);
+ res = false;
+ goto put_sock_ret_res;
+ }
+
+ MT_DEBUG("qtaguid[%d]: leaving matched\n", par->hooknum);
+ res = true;
+
+put_sock_ret_res:
+ if (got_sock)
+ xt_socket_put_sk(sk);
+ if (set_sk_callback_lock)
+ read_unlock_bh(&sk->sk_callback_lock);
+ret_res:
+ MT_DEBUG("qtaguid[%d]: left %d\n", par->hooknum, res);
+ return res;
+}
+
+#ifdef DDEBUG
+/* This function is not in xt_qtaguid_print.c because of locks visibility */
+static void prdebug_full_state(int indent_level, const char *fmt, ...)
+{
+ va_list args;
+ char *fmt_buff;
+ char *buff;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ fmt_buff = kasprintf(GFP_ATOMIC,
+ "qtaguid: %s(): %s {\n", __func__, fmt);
+ BUG_ON(!fmt_buff);
+ va_start(args, fmt);
+ buff = kvasprintf(GFP_ATOMIC,
+ fmt_buff, args);
+ BUG_ON(!buff);
+ pr_debug("%s", buff);
+ kfree(fmt_buff);
+ kfree(buff);
+ va_end(args);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ prdebug_sock_tag_tree(indent_level, &sock_tag_tree);
+ spin_unlock_bh(&sock_tag_list_lock);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree);
+ prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+
+ spin_lock_bh(&iface_stat_list_lock);
+ prdebug_iface_stat_list(indent_level, &iface_stat_list);
+ spin_unlock_bh(&iface_stat_list_lock);
+
+ pr_debug("qtaguid: %s(): }\n", __func__);
+}
+#else
+static void prdebug_full_state(int indent_level, const char *fmt, ...) {}
+#endif
+
+struct proc_ctrl_print_info {
+ struct sock *sk; /* socket found by reading to sk_pos */
+ loff_t sk_pos;
+};
+
+static void *qtaguid_ctrl_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct proc_ctrl_print_info *pcpi = m->private;
+ struct sock_tag *sock_tag_entry = v;
+ struct rb_node *node;
+
+ (*pos)++;
+
+ if (!v || v == SEQ_START_TOKEN)
+ return NULL;
+
+ node = rb_next(&sock_tag_entry->sock_node);
+ if (!node) {
+ pcpi->sk = NULL;
+ sock_tag_entry = SEQ_START_TOKEN;
+ } else {
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ pcpi->sk = sock_tag_entry->sk;
+ }
+ pcpi->sk_pos = *pos;
+ return sock_tag_entry;
+}
+
+static void *qtaguid_ctrl_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_ctrl_print_info *pcpi = m->private;
+ struct sock_tag *sock_tag_entry;
+ struct rb_node *node;
+
+ spin_lock_bh(&sock_tag_list_lock);
+
+ if (unlikely(module_passive))
+ return NULL;
+
+ if (*pos == 0) {
+ pcpi->sk_pos = 0;
+ node = rb_first(&sock_tag_tree);
+ if (!node) {
+ pcpi->sk = NULL;
+ return SEQ_START_TOKEN;
+ }
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ pcpi->sk = sock_tag_entry->sk;
+ } else {
+ sock_tag_entry = (pcpi->sk ? get_sock_stat_nl(pcpi->sk) :
+ NULL) ?: SEQ_START_TOKEN;
+ if (*pos != pcpi->sk_pos) {
+ /* seq_read skipped a next call */
+ *pos = pcpi->sk_pos;
+ return qtaguid_ctrl_proc_next(m, sock_tag_entry, pos);
+ }
+ }
+ return sock_tag_entry;
+}
+
+static void qtaguid_ctrl_proc_stop(struct seq_file *m, void *v)
+{
+ spin_unlock_bh(&sock_tag_list_lock);
+}
+
+/*
+ * Procfs reader to get all active socket tags using style "1)" as described in
+ * fs/proc/generic.c
+ */
+static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v)
+{
+ struct sock_tag *sock_tag_entry = v;
+ uid_t uid;
+ long f_count;
+
+ CT_DEBUG("qtaguid: proc ctrl pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, current_fsuid());
+
+ if (sock_tag_entry != SEQ_START_TOKEN) {
+ uid = get_uid_from_tag(sock_tag_entry->tag);
+ CT_DEBUG("qtaguid: proc_read(): sk=%p tag=0x%llx (uid=%u) "
+ "pid=%u\n",
+ sock_tag_entry->sk,
+ sock_tag_entry->tag,
+ uid,
+ sock_tag_entry->pid
+ );
+ f_count = atomic_long_read(
+ &sock_tag_entry->socket->file->f_count);
+ seq_printf(m, "sock=%p tag=0x%llx (uid=%u) pid=%u "
+ "f_count=%lu\n",
+ sock_tag_entry->sk,
+ sock_tag_entry->tag, uid,
+ sock_tag_entry->pid, f_count);
+ } else {
+ seq_printf(m, "events: sockets_tagged=%llu "
+ "sockets_untagged=%llu "
+ "counter_set_changes=%llu "
+ "delete_cmds=%llu "
+ "iface_events=%llu "
+ "match_calls=%llu "
+ "match_calls_prepost=%llu "
+ "match_found_sk=%llu "
+ "match_found_sk_in_ct=%llu "
+ "match_found_no_sk_in_ct=%llu "
+ "match_no_sk=%llu "
+ "match_no_sk_file=%llu\n",
+ (u64)atomic64_read(&qtu_events.sockets_tagged),
+ (u64)atomic64_read(&qtu_events.sockets_untagged),
+ (u64)atomic64_read(&qtu_events.counter_set_changes),
+ (u64)atomic64_read(&qtu_events.delete_cmds),
+ (u64)atomic64_read(&qtu_events.iface_events),
+ (u64)atomic64_read(&qtu_events.match_calls),
+ (u64)atomic64_read(&qtu_events.match_calls_prepost),
+ (u64)atomic64_read(&qtu_events.match_found_sk),
+ (u64)atomic64_read(&qtu_events.match_found_sk_in_ct),
+ (u64)atomic64_read(&qtu_events.match_found_no_sk_in_ct),
+ (u64)atomic64_read(&qtu_events.match_no_sk),
+ (u64)atomic64_read(&qtu_events.match_no_sk_file));
+
+ /* Count the following as part of the last item_index */
+ prdebug_full_state(0, "proc ctrl");
+ }
+
+ return 0;
+}
+
+/*
+ * Delete socket tags, and stat tags associated with a given
+ * accouting tag and uid.
+ */
+static int ctrl_cmd_delete(const char *input)
+{
+ char cmd;
+ uid_t uid;
+ uid_t entry_uid;
+ tag_t acct_tag;
+ tag_t tag;
+ int res, argc;
+ struct iface_stat *iface_entry;
+ struct rb_node *node;
+ struct sock_tag *st_entry;
+ struct rb_root st_to_free_tree = RB_ROOT;
+ struct tag_stat *ts_entry;
+ struct tag_counter_set *tcs_entry;
+ struct tag_ref *tr_entry;
+ struct uid_tag_data *utd_entry;
+
+ argc = sscanf(input, "%c %llu %u", &cmd, &acct_tag, &uid);
+ CT_DEBUG("qtaguid: ctrl_delete(%s): argc=%d cmd=%c "
+ "user_tag=0x%llx uid=%u\n", input, argc, cmd,
+ acct_tag, uid);
+ if (argc < 2) {
+ res = -EINVAL;
+ goto err;
+ }
+ if (!valid_atag(acct_tag)) {
+ pr_info("qtaguid: ctrl_delete(%s): invalid tag\n", input);
+ res = -EINVAL;
+ goto err;
+ }
+ if (argc < 3) {
+ uid = current_fsuid();
+ } else if (!can_impersonate_uid(uid)) {
+ pr_info("qtaguid: ctrl_delete(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, current_fsuid());
+ res = -EPERM;
+ goto err;
+ }
+
+ tag = combine_atag_with_uid(acct_tag, uid);
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "looking for tag=0x%llx (uid=%u)\n",
+ input, tag, uid);
+
+ /* Delete socket tags */
+ spin_lock_bh(&sock_tag_list_lock);
+ node = rb_first(&sock_tag_tree);
+ while (node) {
+ st_entry = rb_entry(node, struct sock_tag, sock_node);
+ entry_uid = get_uid_from_tag(st_entry->tag);
+ node = rb_next(node);
+ if (entry_uid != uid)
+ continue;
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): st tag=0x%llx (uid=%u)\n",
+ input, st_entry->tag, entry_uid);
+
+ if (!acct_tag || st_entry->tag == tag) {
+ rb_erase(&st_entry->sock_node, &sock_tag_tree);
+ /* Can't sockfd_put() within spinlock, do it later. */
+ sock_tag_tree_insert(st_entry, &st_to_free_tree);
+ tr_entry = lookup_tag_ref(st_entry->tag, NULL);
+ BUG_ON(tr_entry->num_sock_tags <= 0);
+ tr_entry->num_sock_tags--;
+ /*
+ * TODO: remove if, and start failing.
+ * This is a hack to work around the fact that in some
+ * places we have "if (IS_ERR_OR_NULL(pqd_entry))"
+ * and are trying to work around apps
+ * that didn't open the /dev/xt_qtaguid.
+ */
+ if (st_entry->list.next && st_entry->list.prev)
+ list_del(&st_entry->list);
+ }
+ }
+ spin_unlock_bh(&sock_tag_list_lock);
+
+ sock_tag_tree_erase(&st_to_free_tree);
+
+ /* Delete tag counter-sets */
+ spin_lock_bh(&tag_counter_set_list_lock);
+ /* Counter sets are only on the uid tag, not full tag */
+ tcs_entry = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (tcs_entry) {
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "erase tcs: tag=0x%llx (uid=%u) set=%d\n",
+ input,
+ tcs_entry->tn.tag,
+ get_uid_from_tag(tcs_entry->tn.tag),
+ tcs_entry->active_set);
+ rb_erase(&tcs_entry->tn.node, &tag_counter_set_tree);
+ kfree(tcs_entry);
+ }
+ spin_unlock_bh(&tag_counter_set_list_lock);
+
+ /*
+ * If acct_tag is 0, then all entries belonging to uid are
+ * erased.
+ */
+ spin_lock_bh(&iface_stat_list_lock);
+ list_for_each_entry(iface_entry, &iface_stat_list, list) {
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+ node = rb_first(&iface_entry->tag_stat_tree);
+ while (node) {
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ entry_uid = get_uid_from_tag(ts_entry->tn.tag);
+ node = rb_next(node);
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "ts tag=0x%llx (uid=%u)\n",
+ input, ts_entry->tn.tag, entry_uid);
+
+ if (entry_uid != uid)
+ continue;
+ if (!acct_tag || ts_entry->tn.tag == tag) {
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "erase ts: %s 0x%llx %u\n",
+ input, iface_entry->ifname,
+ get_atag_from_tag(ts_entry->tn.tag),
+ entry_uid);
+ rb_erase(&ts_entry->tn.node,
+ &iface_entry->tag_stat_tree);
+ kfree(ts_entry);
+ }
+ }
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ }
+ spin_unlock_bh(&iface_stat_list_lock);
+
+ /* Cleanup the uid_tag_data */
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ node = rb_first(&uid_tag_data_tree);
+ while (node) {
+ utd_entry = rb_entry(node, struct uid_tag_data, node);
+ entry_uid = utd_entry->uid;
+ node = rb_next(node);
+
+ CT_DEBUG("qtaguid: ctrl_delete(%s): "
+ "utd uid=%u\n",
+ input, entry_uid);
+
+ if (entry_uid != uid)
+ continue;
+ /*
+ * Go over the tag_refs, and those that don't have
+ * sock_tags using them are freed.
+ */
+ put_tag_ref_tree(tag, utd_entry);
+ put_utd_entry(utd_entry);
+ }
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+
+ atomic64_inc(&qtu_events.delete_cmds);
+ res = 0;
+
+err:
+ return res;
+}
+
+static int ctrl_cmd_counter_set(const char *input)
+{
+ char cmd;
+ uid_t uid = 0;
+ tag_t tag;
+ int res, argc;
+ struct tag_counter_set *tcs;
+ int counter_set;
+
+ argc = sscanf(input, "%c %d %u", &cmd, &counter_set, &uid);
+ CT_DEBUG("qtaguid: ctrl_counterset(%s): argc=%d cmd=%c "
+ "set=%d uid=%u\n", input, argc, cmd,
+ counter_set, uid);
+ if (argc != 3) {
+ res = -EINVAL;
+ goto err;
+ }
+ if (counter_set < 0 || counter_set >= IFS_MAX_COUNTER_SETS) {
+ pr_info("qtaguid: ctrl_counterset(%s): invalid counter_set range\n",
+ input);
+ res = -EINVAL;
+ goto err;
+ }
+ if (!can_manipulate_uids()) {
+ pr_info("qtaguid: ctrl_counterset(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, current_fsuid());
+ res = -EPERM;
+ goto err;
+ }
+
+ tag = make_tag_from_uid(uid);
+ spin_lock_bh(&tag_counter_set_list_lock);
+ tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+ if (!tcs) {
+ tcs = kzalloc(sizeof(*tcs), GFP_ATOMIC);
+ if (!tcs) {
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ pr_err("qtaguid: ctrl_counterset(%s): "
+ "failed to alloc counter set\n",
+ input);
+ res = -ENOMEM;
+ goto err;
+ }
+ tcs->tn.tag = tag;
+ tag_counter_set_tree_insert(tcs, &tag_counter_set_tree);
+ CT_DEBUG("qtaguid: ctrl_counterset(%s): added tcs tag=0x%llx "
+ "(uid=%u) set=%d\n",
+ input, tag, get_uid_from_tag(tag), counter_set);
+ }
+ tcs->active_set = counter_set;
+ spin_unlock_bh(&tag_counter_set_list_lock);
+ atomic64_inc(&qtu_events.counter_set_changes);
+ res = 0;
+
+err:
+ return res;
+}
+
+static int ctrl_cmd_tag(const char *input)
+{
+ char cmd;
+ int sock_fd = 0;
+ uid_t uid = 0;
+ tag_t acct_tag = make_atag_from_value(0);
+ tag_t full_tag;
+ struct socket *el_socket;
+ int res, argc;
+ struct sock_tag *sock_tag_entry;
+ struct tag_ref *tag_ref_entry;
+ struct uid_tag_data *uid_tag_data_entry;
+ struct proc_qtu_data *pqd_entry;
+
+ /* Unassigned args will get defaulted later. */
+ argc = sscanf(input, "%c %d %llu %u", &cmd, &sock_fd, &acct_tag, &uid);
+ CT_DEBUG("qtaguid: ctrl_tag(%s): argc=%d cmd=%c sock_fd=%d "
+ "acct_tag=0x%llx uid=%u\n", input, argc, cmd, sock_fd,
+ acct_tag, uid);
+ if (argc < 2) {
+ res = -EINVAL;
+ goto err;
+ }
+ el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */
+ if (!el_socket) {
+ pr_info("qtaguid: ctrl_tag(%s): failed to lookup"
+ " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+ input, sock_fd, res, current->pid, current->tgid,
+ current_fsuid());
+ goto err;
+ }
+ CT_DEBUG("qtaguid: ctrl_tag(%s): socket->...->f_count=%ld ->sk=%p\n",
+ input, atomic_long_read(&el_socket->file->f_count),
+ el_socket->sk);
+ if (argc < 3) {
+ acct_tag = make_atag_from_value(0);
+ } else if (!valid_atag(acct_tag)) {
+ pr_info("qtaguid: ctrl_tag(%s): invalid tag\n", input);
+ res = -EINVAL;
+ goto err_put;
+ }
+ CT_DEBUG("qtaguid: ctrl_tag(%s): "
+ "pid=%u tgid=%u uid=%u euid=%u fsuid=%u "
+ "ctrl.gid=%u in_group()=%d in_egroup()=%d\n",
+ input, current->pid, current->tgid, current_uid(),
+ current_euid(), current_fsuid(),
+ xt_qtaguid_ctrl_file->gid,
+ in_group_p(xt_qtaguid_ctrl_file->gid),
+ in_egroup_p(xt_qtaguid_ctrl_file->gid));
+ if (argc < 4) {
+ uid = current_fsuid();
+ } else if (!can_impersonate_uid(uid)) {
+ pr_info("qtaguid: ctrl_tag(%s): "
+ "insufficient priv from pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, current_fsuid());
+ res = -EPERM;
+ goto err_put;
+ }
+ full_tag = combine_atag_with_uid(acct_tag, uid);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+ tag_ref_entry = get_tag_ref(full_tag, &uid_tag_data_entry);
+ if (IS_ERR(tag_ref_entry)) {
+ res = PTR_ERR(tag_ref_entry);
+ spin_unlock_bh(&sock_tag_list_lock);
+ goto err_put;
+ }
+ tag_ref_entry->num_sock_tags++;
+ if (sock_tag_entry) {
+ struct tag_ref *prev_tag_ref_entry;
+
+ CT_DEBUG("qtaguid: ctrl_tag(%s): retag for sk=%p "
+ "st@%p ...->f_count=%ld\n",
+ input, el_socket->sk, sock_tag_entry,
+ atomic_long_read(&el_socket->file->f_count));
+ /*
+ * This is a re-tagging, so release the sock_fd that was
+ * locked at the time of the 1st tagging.
+ * There is still the ref from this call's sockfd_lookup() so
+ * it can be done within the spinlock.
+ */
+ sockfd_put(sock_tag_entry->socket);
+ prev_tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag,
+ &uid_tag_data_entry);
+ BUG_ON(IS_ERR_OR_NULL(prev_tag_ref_entry));
+ BUG_ON(prev_tag_ref_entry->num_sock_tags <= 0);
+ prev_tag_ref_entry->num_sock_tags--;
+ sock_tag_entry->tag = full_tag;
+ } else {
+ CT_DEBUG("qtaguid: ctrl_tag(%s): newtag for sk=%p\n",
+ input, el_socket->sk);
+ sock_tag_entry = kzalloc(sizeof(*sock_tag_entry),
+ GFP_ATOMIC);
+ if (!sock_tag_entry) {
+ pr_err("qtaguid: ctrl_tag(%s): "
+ "socket tag alloc failed\n",
+ input);
+ spin_unlock_bh(&sock_tag_list_lock);
+ res = -ENOMEM;
+ goto err_tag_unref_put;
+ }
+ sock_tag_entry->sk = el_socket->sk;
+ sock_tag_entry->socket = el_socket;
+ sock_tag_entry->pid = current->tgid;
+ sock_tag_entry->tag = combine_atag_with_uid(acct_tag,
+ uid);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ pqd_entry = proc_qtu_data_tree_search(
+ &proc_qtu_data_tree, current->tgid);
+ /*
+ * TODO: remove if, and start failing.
+ * At first, we want to catch user-space code that is not
+ * opening the /dev/xt_qtaguid.
+ */
+ if (IS_ERR_OR_NULL(pqd_entry))
+ pr_warn_once(
+ "qtaguid: %s(): "
+ "User space forgot to open /dev/xt_qtaguid? "
+ "pid=%u tgid=%u uid=%u\n", __func__,
+ current->pid, current->tgid,
+ current_fsuid());
+ else
+ list_add(&sock_tag_entry->list,
+ &pqd_entry->sock_tag_list);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+
+ sock_tag_tree_insert(sock_tag_entry, &sock_tag_tree);
+ atomic64_inc(&qtu_events.sockets_tagged);
+ }
+ spin_unlock_bh(&sock_tag_list_lock);
+ /* We keep the ref to the socket (file) until it is untagged */
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done st@%p ...->f_count=%ld\n",
+ input, sock_tag_entry,
+ atomic_long_read(&el_socket->file->f_count));
+ return 0;
+
+err_tag_unref_put:
+ BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+ tag_ref_entry->num_sock_tags--;
+ free_tag_ref_from_utd_entry(tag_ref_entry, uid_tag_data_entry);
+err_put:
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done. ...->f_count=%ld\n",
+ input, atomic_long_read(&el_socket->file->f_count) - 1);
+ /* Release the sock_fd that was grabbed by sockfd_lookup(). */
+ sockfd_put(el_socket);
+ return res;
+
+err:
+ CT_DEBUG("qtaguid: ctrl_tag(%s): done.\n", input);
+ return res;
+}
+
+static int ctrl_cmd_untag(const char *input)
+{
+ char cmd;
+ int sock_fd = 0;
+ struct socket *el_socket;
+ int res, argc;
+ struct sock_tag *sock_tag_entry;
+ struct tag_ref *tag_ref_entry;
+ struct uid_tag_data *utd_entry;
+ struct proc_qtu_data *pqd_entry;
+
+ argc = sscanf(input, "%c %d", &cmd, &sock_fd);
+ CT_DEBUG("qtaguid: ctrl_untag(%s): argc=%d cmd=%c sock_fd=%d\n",
+ input, argc, cmd, sock_fd);
+ if (argc < 2) {
+ res = -EINVAL;
+ goto err;
+ }
+ el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */
+ if (!el_socket) {
+ pr_info("qtaguid: ctrl_untag(%s): failed to lookup"
+ " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+ input, sock_fd, res, current->pid, current->tgid,
+ current_fsuid());
+ goto err;
+ }
+ CT_DEBUG("qtaguid: ctrl_untag(%s): socket->...->f_count=%ld ->sk=%p\n",
+ input, atomic_long_read(&el_socket->file->f_count),
+ el_socket->sk);
+ spin_lock_bh(&sock_tag_list_lock);
+ sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+ if (!sock_tag_entry) {
+ spin_unlock_bh(&sock_tag_list_lock);
+ res = -EINVAL;
+ goto err_put;
+ }
+ /*
+ * The socket already belongs to the current process
+ * so it can do whatever it wants to it.
+ */
+ rb_erase(&sock_tag_entry->sock_node, &sock_tag_tree);
+
+ tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag, &utd_entry);
+ BUG_ON(!tag_ref_entry);
+ BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+ pqd_entry = proc_qtu_data_tree_search(
+ &proc_qtu_data_tree, current->tgid);
+ /*
+ * TODO: remove if, and start failing.
+ * At first, we want to catch user-space code that is not
+ * opening the /dev/xt_qtaguid.
+ */
+ if (IS_ERR_OR_NULL(pqd_entry))
+ pr_warn_once("qtaguid: %s(): "
+ "User space forgot to open /dev/xt_qtaguid? "
+ "pid=%u tgid=%u uid=%u\n", __func__,
+ current->pid, current->tgid, current_fsuid());
+ else
+ list_del(&sock_tag_entry->list);
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ /*
+ * We don't free tag_ref from the utd_entry here,
+ * only during a cmd_delete().
+ */
+ tag_ref_entry->num_sock_tags--;
+ spin_unlock_bh(&sock_tag_list_lock);
+ /*
+ * Release the sock_fd that was grabbed at tag time,
+ * and once more for the sockfd_lookup() here.
+ */
+ sockfd_put(sock_tag_entry->socket);
+ CT_DEBUG("qtaguid: ctrl_untag(%s): done. st@%p ...->f_count=%ld\n",
+ input, sock_tag_entry,
+ atomic_long_read(&el_socket->file->f_count) - 1);
+ sockfd_put(el_socket);
+
+ kfree(sock_tag_entry);
+ atomic64_inc(&qtu_events.sockets_untagged);
+
+ return 0;
+
+err_put:
+ CT_DEBUG("qtaguid: ctrl_untag(%s): done. socket->...->f_count=%ld\n",
+ input, atomic_long_read(&el_socket->file->f_count) - 1);
+ /* Release the sock_fd that was grabbed by sockfd_lookup(). */
+ sockfd_put(el_socket);
+ return res;
+
+err:
+ CT_DEBUG("qtaguid: ctrl_untag(%s): done.\n", input);
+ return res;
+}
+
+static ssize_t qtaguid_ctrl_parse(const char *input, size_t count)
+{
+ char cmd;
+ ssize_t res;
+
+ CT_DEBUG("qtaguid: ctrl(%s): pid=%u tgid=%u uid=%u\n",
+ input, current->pid, current->tgid, current_fsuid());
+
+ cmd = input[0];
+ /* Collect params for commands */
+ switch (cmd) {
+ case 'd':
+ res = ctrl_cmd_delete(input);
+ break;
+
+ case 's':
+ res = ctrl_cmd_counter_set(input);
+ break;
+
+ case 't':
+ res = ctrl_cmd_tag(input);
+ break;
+
+ case 'u':
+ res = ctrl_cmd_untag(input);
+ break;
+
+ default:
+ res = -EINVAL;
+ goto err;
+ }
+ if (!res)
+ res = count;
+err:
+ CT_DEBUG("qtaguid: ctrl(%s): res=%zd\n", input, res);
+ return res;
+}
+
+#define MAX_QTAGUID_CTRL_INPUT_LEN 255
+static ssize_t qtaguid_ctrl_proc_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *offp)
+{
+ char input_buf[MAX_QTAGUID_CTRL_INPUT_LEN];
+
+ if (unlikely(module_passive))
+ return count;
+
+ if (count >= MAX_QTAGUID_CTRL_INPUT_LEN)
+ return -EINVAL;
+
+ if (copy_from_user(input_buf, buffer, count))
+ return -EFAULT;
+
+ input_buf[count] = '\0';
+ return qtaguid_ctrl_parse(input_buf, count);
+}
+
+struct proc_print_info {
+ struct iface_stat *iface_entry;
+ int item_index;
+ tag_t tag; /* tag found by reading to tag_pos */
+ off_t tag_pos;
+ int tag_item_index;
+};
+
+static void pp_stats_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "idx iface acct_tag_hex uid_tag_int cnt_set "
+ "rx_bytes rx_packets "
+ "tx_bytes tx_packets "
+ "rx_tcp_bytes rx_tcp_packets "
+ "rx_udp_bytes rx_udp_packets "
+ "rx_other_bytes rx_other_packets "
+ "tx_tcp_bytes tx_tcp_packets "
+ "tx_udp_bytes tx_udp_packets "
+ "tx_other_bytes tx_other_packets\n");
+}
+
+static int pp_stats_line(struct seq_file *m, struct tag_stat *ts_entry,
+ int cnt_set)
+{
+ int ret;
+ struct data_counters *cnts;
+ tag_t tag = ts_entry->tn.tag;
+ uid_t stat_uid = get_uid_from_tag(tag);
+ struct proc_print_info *ppi = m->private;
+ /* Detailed tags are not available to everybody */
+ if (get_atag_from_tag(tag) && !can_read_other_uid_stats(stat_uid)) {
+ CT_DEBUG("qtaguid: stats line: "
+ "%s 0x%llx %u: insufficient priv "
+ "from pid=%u tgid=%u uid=%u stats.gid=%u\n",
+ ppi->iface_entry->ifname,
+ get_atag_from_tag(tag), stat_uid,
+ current->pid, current->tgid, current_fsuid(),
+ xt_qtaguid_stats_file->gid);
+ return 0;
+ }
+ ppi->item_index++;
+ cnts = &ts_entry->counters;
+ ret = seq_printf(m, "%d %s 0x%llx %u %u "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu "
+ "%llu %llu\n",
+ ppi->item_index,
+ ppi->iface_entry->ifname,
+ get_atag_from_tag(tag),
+ stat_uid,
+ cnt_set,
+ dc_sum_bytes(cnts, cnt_set, IFS_RX),
+ dc_sum_packets(cnts, cnt_set, IFS_RX),
+ dc_sum_bytes(cnts, cnt_set, IFS_TX),
+ dc_sum_packets(cnts, cnt_set, IFS_TX),
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+ cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+ return ret ?: 1;
+}
+
+static bool pp_sets(struct seq_file *m, struct tag_stat *ts_entry)
+{
+ int ret;
+ int counter_set;
+ for (counter_set = 0; counter_set < IFS_MAX_COUNTER_SETS;
+ counter_set++) {
+ ret = pp_stats_line(m, ts_entry, counter_set);
+ if (ret < 0)
+ return false;
+ }
+ return true;
+}
+
+static int qtaguid_stats_proc_iface_stat_ptr_valid(struct iface_stat *ptr)
+{
+ struct iface_stat *iface_entry;
+
+ if (!ptr)
+ return false;
+
+ list_for_each_entry(iface_entry, &iface_stat_list, list)
+ if (iface_entry == ptr)
+ return true;
+ return false;
+}
+
+static void qtaguid_stats_proc_next_iface_entry(struct proc_print_info *ppi)
+{
+ spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ list_for_each_entry_continue(ppi->iface_entry, &iface_stat_list, list) {
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ return;
+ }
+ ppi->iface_entry = NULL;
+}
+
+static void *qtaguid_stats_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct proc_print_info *ppi = m->private;
+ struct tag_stat *ts_entry;
+ struct rb_node *node;
+
+ if (!v) {
+ pr_err("qtaguid: %s(): unexpected v: NULL\n", __func__);
+ return NULL;
+ }
+
+ (*pos)++;
+
+ if (!ppi->iface_entry || unlikely(module_passive))
+ return NULL;
+
+ if (v == SEQ_START_TOKEN)
+ node = rb_first(&ppi->iface_entry->tag_stat_tree);
+ else
+ node = rb_next(&((struct tag_stat *)v)->tn.node);
+
+ while (!node) {
+ qtaguid_stats_proc_next_iface_entry(ppi);
+ if (!ppi->iface_entry)
+ return NULL;
+ node = rb_first(&ppi->iface_entry->tag_stat_tree);
+ }
+
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ ppi->tag = ts_entry->tn.tag;
+ ppi->tag_pos = *pos;
+ ppi->tag_item_index = ppi->item_index;
+ return ts_entry;
+}
+
+static void *qtaguid_stats_proc_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_print_info *ppi = m->private;
+ struct tag_stat *ts_entry = NULL;
+
+ spin_lock_bh(&iface_stat_list_lock);
+
+ if (*pos == 0) {
+ ppi->item_index = 1;
+ ppi->tag_pos = 0;
+ if (list_empty(&iface_stat_list)) {
+ ppi->iface_entry = NULL;
+ } else {
+ ppi->iface_entry = list_first_entry(&iface_stat_list,
+ struct iface_stat,
+ list);
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ }
+ return SEQ_START_TOKEN;
+ }
+ if (!qtaguid_stats_proc_iface_stat_ptr_valid(ppi->iface_entry)) {
+ if (ppi->iface_entry) {
+ pr_err("qtaguid: %s(): iface_entry %p not found\n",
+ __func__, ppi->iface_entry);
+ ppi->iface_entry = NULL;
+ }
+ return NULL;
+ }
+
+ spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+
+ if (!ppi->tag_pos) {
+ /* seq_read skipped first next call */
+ ts_entry = SEQ_START_TOKEN;
+ } else {
+ ts_entry = tag_stat_tree_search(
+ &ppi->iface_entry->tag_stat_tree, ppi->tag);
+ if (!ts_entry) {
+ pr_info("qtaguid: %s(): tag_stat.tag 0x%llx not found. Abort.\n",
+ __func__, ppi->tag);
+ return NULL;
+ }
+ }
+
+ if (*pos == ppi->tag_pos) { /* normal resume */
+ ppi->item_index = ppi->tag_item_index;
+ } else {
+ /* seq_read skipped a next call */
+ *pos = ppi->tag_pos;
+ ts_entry = qtaguid_stats_proc_next(m, ts_entry, pos);
+ }
+
+ return ts_entry;
+}
+
+static void qtaguid_stats_proc_stop(struct seq_file *m, void *v)
+{
+ struct proc_print_info *ppi = m->private;
+ if (ppi->iface_entry)
+ spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+ spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/*
+ * Procfs reader to get all tag stats using style "1)" as described in
+ * fs/proc/generic.c
+ * Groups all protocols tx/rx bytes.
+ */
+static int qtaguid_stats_proc_show(struct seq_file *m, void *v)
+{
+ struct tag_stat *ts_entry = v;
+
+ if (v == SEQ_START_TOKEN)
+ pp_stats_header(m);
+ else
+ pp_sets(m, ts_entry);
+
+ return 0;
+}
+
+/*------------------------------------------*/
+static int qtudev_open(struct inode *inode, struct file *file)
+{
+ struct uid_tag_data *utd_entry;
+ struct proc_qtu_data *pqd_entry;
+ struct proc_qtu_data *new_pqd_entry;
+ int res;
+ bool utd_entry_found;
+
+ if (unlikely(qtu_proc_handling_passive))
+ return 0;
+
+ DR_DEBUG("qtaguid: qtudev_open(): pid=%u tgid=%u uid=%u\n",
+ current->pid, current->tgid, current_fsuid());
+
+ spin_lock_bh(&uid_tag_data_tree_lock);
+
+ /* Look for existing uid data, or alloc one. */
+ utd_entry = get_uid_data(current_fsuid(), &utd_entry_found);
+ if (IS_ERR_OR_NULL(utd_entry)) {
+ res = PTR_ERR(utd_entry);
+ goto err_unlock;
+ }
+
+ /* Look for existing PID based proc_data */
+ pqd_entry = proc_qtu_data_tree_search(&proc_qtu_data_tree,
+ current->tgid);
+ if (pqd_entry) {
+ pr_err("qtaguid: qtudev_open(): %u/%u %u "
+ "%s already opened\n",
+ current->pid, current->tgid, current_fsuid(),
+ QTU_DEV_NAME);
+ res = -EBUSY;
+ goto err_unlock_free_utd;
+ }
+
+ new_pqd_entry = kzalloc(sizeof(*new_pqd_entry), GFP_ATOMIC);
+ if (!new_pqd_entry) {
+ pr_err("qtaguid: qtudev_open(): %u/%u %u: "
+ "proc data alloc failed\n",
+ current->pid, current->tgid, current_fsuid());
+ res = -ENOMEM;
+ goto err_unlock_free_utd;
+ }
+ new_pqd_entry->pid = current->tgid;
+ INIT_LIST_HEAD(&new_pqd_entry->sock_tag_list);
+ new_pqd_entry->parent_tag_data = utd_entry;
+ utd_entry->num_pqd++;
+
+ proc_qtu_data_tree_insert(new_pqd_entry,
+ &proc_qtu_data_tree);
+
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ DR_DEBUG("qtaguid: tracking data for uid=%u in pqd=%p\n",
+ current_fsuid(), new_pqd_entry);
+ file->private_data = new_pqd_entry;
+ return 0;
+
+err_unlock_free_utd:
+ if (!utd_entry_found) {
+ rb_erase(&utd_entry->node, &uid_tag_data_tree);
+ kfree(utd_entry);
+ }
+err_unlock:
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ return res;
+}
+
+static int qtudev_release(struct inode *inode, struct file *file)
+{
+ struct proc_qtu_data *pqd_entry = file->private_data;
+ struct uid_tag_data *utd_entry = pqd_entry->parent_tag_data;
+ struct sock_tag *st_entry;
+ struct rb_root st_to_free_tree = RB_ROOT;
+ struct list_head *entry, *next;
+ struct tag_ref *tr;
+
+ if (unlikely(qtu_proc_handling_passive))
+ return 0;
+
+ /*
+ * Do not trust the current->pid, it might just be a kworker cleaning
+ * up after a dead proc.
+ */
+ DR_DEBUG("qtaguid: qtudev_release(): "
+ "pid=%u tgid=%u uid=%u "
+ "pqd_entry=%p->pid=%u utd_entry=%p->active_tags=%d\n",
+ current->pid, current->tgid, pqd_entry->parent_tag_data->uid,
+ pqd_entry, pqd_entry->pid, utd_entry,
+ utd_entry->num_active_tags);
+
+ spin_lock_bh(&sock_tag_list_lock);
+ spin_lock_bh(&uid_tag_data_tree_lock);
+
+ list_for_each_safe(entry, next, &pqd_entry->sock_tag_list) {
+ st_entry = list_entry(entry, struct sock_tag, list);
+ DR_DEBUG("qtaguid: %s(): "
+ "erase sock_tag=%p->sk=%p pid=%u tgid=%u uid=%u\n",
+ __func__,
+ st_entry, st_entry->sk,
+ current->pid, current->tgid,
+ pqd_entry->parent_tag_data->uid);
+
+ utd_entry = uid_tag_data_tree_search(
+ &uid_tag_data_tree,
+ get_uid_from_tag(st_entry->tag));
+ BUG_ON(IS_ERR_OR_NULL(utd_entry));
+ DR_DEBUG("qtaguid: %s(): "
+ "looking for tag=0x%llx in utd_entry=%p\n", __func__,
+ st_entry->tag, utd_entry);
+ tr = tag_ref_tree_search(&utd_entry->tag_ref_tree,
+ st_entry->tag);
+ BUG_ON(!tr);
+ BUG_ON(tr->num_sock_tags <= 0);
+ tr->num_sock_tags--;
+ free_tag_ref_from_utd_entry(tr, utd_entry);
+
+ rb_erase(&st_entry->sock_node, &sock_tag_tree);
+ list_del(&st_entry->list);
+ /* Can't sockfd_put() within spinlock, do it later. */
+ sock_tag_tree_insert(st_entry, &st_to_free_tree);
+
+ /*
+ * Try to free the utd_entry if no other proc_qtu_data is
+ * using it (num_pqd is 0) and it doesn't have active tags
+ * (num_active_tags is 0).
+ */
+ put_utd_entry(utd_entry);
+ }
+
+ rb_erase(&pqd_entry->node, &proc_qtu_data_tree);
+ BUG_ON(pqd_entry->parent_tag_data->num_pqd < 1);
+ pqd_entry->parent_tag_data->num_pqd--;
+ put_utd_entry(pqd_entry->parent_tag_data);
+ kfree(pqd_entry);
+ file->private_data = NULL;
+
+ spin_unlock_bh(&uid_tag_data_tree_lock);
+ spin_unlock_bh(&sock_tag_list_lock);
+
+
+ sock_tag_tree_erase(&st_to_free_tree);
+
+ prdebug_full_state(0, "%s(): pid=%u tgid=%u", __func__,
+ current->pid, current->tgid);
+ return 0;
+}
+
+/*------------------------------------------*/
+static const struct file_operations qtudev_fops = {
+ .owner = THIS_MODULE,
+ .open = qtudev_open,
+ .release = qtudev_release,
+};
+
+static struct miscdevice qtu_device = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = QTU_DEV_NAME,
+ .fops = &qtudev_fops,
+ /* How sad it doesn't allow for defaults: .mode = S_IRUGO | S_IWUSR */
+};
+
+static const struct seq_operations proc_qtaguid_ctrl_seqops = {
+ .start = qtaguid_ctrl_proc_start,
+ .next = qtaguid_ctrl_proc_next,
+ .stop = qtaguid_ctrl_proc_stop,
+ .show = qtaguid_ctrl_proc_show,
+};
+
+static int proc_qtaguid_ctrl_open(struct inode *inode, struct file *file)
+{
+ return seq_open_private(file, &proc_qtaguid_ctrl_seqops,
+ sizeof(struct proc_ctrl_print_info));
+}
+
+static const struct file_operations proc_qtaguid_ctrl_fops = {
+ .open = proc_qtaguid_ctrl_open,
+ .read = seq_read,
+ .write = qtaguid_ctrl_proc_write,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct seq_operations proc_qtaguid_stats_seqops = {
+ .start = qtaguid_stats_proc_start,
+ .next = qtaguid_stats_proc_next,
+ .stop = qtaguid_stats_proc_stop,
+ .show = qtaguid_stats_proc_show,
+};
+
+static int proc_qtaguid_stats_open(struct inode *inode, struct file *file)
+{
+ return seq_open_private(file, &proc_qtaguid_stats_seqops,
+ sizeof(struct proc_print_info));
+}
+
+static const struct file_operations proc_qtaguid_stats_fops = {
+ .open = proc_qtaguid_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+/*------------------------------------------*/
+static int __init qtaguid_proc_register(struct proc_dir_entry **res_procdir)
+{
+ int ret;
+ *res_procdir = proc_mkdir(module_procdirname, init_net.proc_net);
+ if (!*res_procdir) {
+ pr_err("qtaguid: failed to create proc/.../xt_qtaguid\n");
+ ret = -ENOMEM;
+ goto no_dir;
+ }
+
+ xt_qtaguid_ctrl_file = proc_create_data("ctrl", proc_ctrl_perms,
+ *res_procdir,
+ &proc_qtaguid_ctrl_fops,
+ NULL);
+ if (!xt_qtaguid_ctrl_file) {
+ pr_err("qtaguid: failed to create xt_qtaguid/ctrl "
+ " file\n");
+ ret = -ENOMEM;
+ goto no_ctrl_entry;
+ }
+
+ xt_qtaguid_stats_file = proc_create_data("stats", proc_stats_perms,
+ *res_procdir,
+ &proc_qtaguid_stats_fops,
+ NULL);
+ if (!xt_qtaguid_stats_file) {
+ pr_err("qtaguid: failed to create xt_qtaguid/stats "
+ "file\n");
+ ret = -ENOMEM;
+ goto no_stats_entry;
+ }
+ /*
+ * TODO: add support counter hacking
+ * xt_qtaguid_stats_file->write_proc = qtaguid_stats_proc_write;
+ */
+ return 0;
+
+no_stats_entry:
+ remove_proc_entry("ctrl", *res_procdir);
+no_ctrl_entry:
+ remove_proc_entry("xt_qtaguid", NULL);
+no_dir:
+ return ret;
+}
+
+static struct xt_match qtaguid_mt_reg __read_mostly = {
+ /*
+ * This module masquerades as the "owner" module so that iptables
+ * tools can deal with it.
+ */
+ .name = "owner",
+ .revision = 1,
+ .family = NFPROTO_UNSPEC,
+ .match = qtaguid_mt,
+ .matchsize = sizeof(struct xt_qtaguid_match_info),
+ .me = THIS_MODULE,
+};
+
+static int __init qtaguid_mt_init(void)
+{
+ if (qtaguid_proc_register(&xt_qtaguid_procdir)
+ || iface_stat_init(xt_qtaguid_procdir)
+ || xt_register_match(&qtaguid_mt_reg)
+ || misc_register(&qtu_device))
+ return -1;
+ return 0;
+}
+
+/*
+ * TODO: allow unloading of the module.
+ * For now stats are permanent.
+ * Kconfig forces'y/n' and never an 'm'.
+ */
+
+module_init(qtaguid_mt_init);
+MODULE_AUTHOR("jpa <jpa@google.com>");
+MODULE_DESCRIPTION("Xtables: socket owner+tag matching and associated stats");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_owner");
+MODULE_ALIAS("ip6t_owner");
+MODULE_ALIAS("ipt_qtaguid");
+MODULE_ALIAS("ip6t_qtaguid");
diff --git a/net/netfilter/xt_qtaguid_internal.h b/net/netfilter/xt_qtaguid_internal.h
new file mode 100644
index 0000000..6dc14a9
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_internal.h
@@ -0,0 +1,352 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __XT_QTAGUID_INTERNAL_H__
+#define __XT_QTAGUID_INTERNAL_H__
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock_types.h>
+#include <linux/workqueue.h>
+
+/* Iface handling */
+#define IDEBUG_MASK (1<<0)
+/* Iptable Matching. Per packet. */
+#define MDEBUG_MASK (1<<1)
+/* Red-black tree handling. Per packet. */
+#define RDEBUG_MASK (1<<2)
+/* procfs ctrl/stats handling */
+#define CDEBUG_MASK (1<<3)
+/* dev and resource tracking */
+#define DDEBUG_MASK (1<<4)
+
+/* E.g (IDEBUG_MASK | CDEBUG_MASK | DDEBUG_MASK) */
+#define DEFAULT_DEBUG_MASK 0
+
+/*
+ * (Un)Define these *DEBUG to compile out/in the pr_debug calls.
+ * All undef: text size ~ 0x3030; all def: ~ 0x4404.
+ */
+#define IDEBUG
+#define MDEBUG
+#define RDEBUG
+#define CDEBUG
+#define DDEBUG
+
+#define MSK_DEBUG(mask, ...) do { \
+ if (unlikely(qtaguid_debug_mask & (mask))) \
+ pr_debug(__VA_ARGS__); \
+ } while (0)
+#ifdef IDEBUG
+#define IF_DEBUG(...) MSK_DEBUG(IDEBUG_MASK, __VA_ARGS__)
+#else
+#define IF_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef MDEBUG
+#define MT_DEBUG(...) MSK_DEBUG(MDEBUG_MASK, __VA_ARGS__)
+#else
+#define MT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef RDEBUG
+#define RB_DEBUG(...) MSK_DEBUG(RDEBUG_MASK, __VA_ARGS__)
+#else
+#define RB_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef CDEBUG
+#define CT_DEBUG(...) MSK_DEBUG(CDEBUG_MASK, __VA_ARGS__)
+#else
+#define CT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef DDEBUG
+#define DR_DEBUG(...) MSK_DEBUG(DDEBUG_MASK, __VA_ARGS__)
+#else
+#define DR_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+
+extern uint qtaguid_debug_mask;
+
+/*---------------------------------------------------------------------------*/
+/*
+ * Tags:
+ *
+ * They represent what the data usage counters will be tracked against.
+ * By default a tag is just based on the UID.
+ * The UID is used as the base for policing, and can not be ignored.
+ * So a tag will always at least represent a UID (uid_tag).
+ *
+ * A tag can be augmented with an "accounting tag" which is associated
+ * with a UID.
+ * User space can set the acct_tag portion of the tag which is then used
+ * with sockets: all data belonging to that socket will be counted against the
+ * tag. The policing is then based on the tag's uid_tag portion,
+ * and stats are collected for the acct_tag portion separately.
+ *
+ * There could be
+ * a: {acct_tag=1, uid_tag=10003}
+ * b: {acct_tag=2, uid_tag=10003}
+ * c: {acct_tag=3, uid_tag=10003}
+ * d: {acct_tag=0, uid_tag=10003}
+ * a, b, and c represent tags associated with specific sockets.
+ * d is for the totals for that uid, including all untagged traffic.
+ * Typically d is used with policing/quota rules.
+ *
+ * We want tag_t big enough to distinguish uid_t and acct_tag.
+ * It might become a struct if needed.
+ * Nothing should be using it as an int.
+ */
+typedef uint64_t tag_t; /* Only used via accessors */
+
+#define TAG_UID_MASK 0xFFFFFFFFULL
+#define TAG_ACCT_MASK (~0xFFFFFFFFULL)
+
+static inline int tag_compare(tag_t t1, tag_t t2)
+{
+ return t1 < t2 ? -1 : t1 == t2 ? 0 : 1;
+}
+
+static inline tag_t combine_atag_with_uid(tag_t acct_tag, uid_t uid)
+{
+ return acct_tag | uid;
+}
+static inline tag_t make_tag_from_uid(uid_t uid)
+{
+ return uid;
+}
+static inline uid_t get_uid_from_tag(tag_t tag)
+{
+ return tag & TAG_UID_MASK;
+}
+static inline tag_t get_utag_from_tag(tag_t tag)
+{
+ return tag & TAG_UID_MASK;
+}
+static inline tag_t get_atag_from_tag(tag_t tag)
+{
+ return tag & TAG_ACCT_MASK;
+}
+
+static inline bool valid_atag(tag_t tag)
+{
+ return !(tag & TAG_UID_MASK);
+}
+static inline tag_t make_atag_from_value(uint32_t value)
+{
+ return (uint64_t)value << 32;
+}
+/*---------------------------------------------------------------------------*/
+
+/*
+ * Maximum number of socket tags that a UID is allowed to have active.
+ * Multiple processes belonging to the same UID contribute towards this limit.
+ * Special UIDs that can impersonate a UID also contribute (e.g. download
+ * manager, ...)
+ */
+#define DEFAULT_MAX_SOCK_TAGS 1024
+
+/*
+ * For now we only track 2 sets of counters.
+ * The default set is 0.
+ * Userspace can activate another set for a given uid being tracked.
+ */
+#define IFS_MAX_COUNTER_SETS 2
+
+enum ifs_tx_rx {
+ IFS_TX,
+ IFS_RX,
+ IFS_MAX_DIRECTIONS
+};
+
+/* For now, TCP, UDP, the rest */
+enum ifs_proto {
+ IFS_TCP,
+ IFS_UDP,
+ IFS_PROTO_OTHER,
+ IFS_MAX_PROTOS
+};
+
+struct byte_packet_counters {
+ uint64_t bytes;
+ uint64_t packets;
+};
+
+struct data_counters {
+ struct byte_packet_counters bpc[IFS_MAX_COUNTER_SETS][IFS_MAX_DIRECTIONS][IFS_MAX_PROTOS];
+};
+
+static inline uint64_t dc_sum_bytes(struct data_counters *counters,
+ int set,
+ enum ifs_tx_rx direction)
+{
+ return counters->bpc[set][direction][IFS_TCP].bytes
+ + counters->bpc[set][direction][IFS_UDP].bytes
+ + counters->bpc[set][direction][IFS_PROTO_OTHER].bytes;
+}
+
+static inline uint64_t dc_sum_packets(struct data_counters *counters,
+ int set,
+ enum ifs_tx_rx direction)
+{
+ return counters->bpc[set][direction][IFS_TCP].packets
+ + counters->bpc[set][direction][IFS_UDP].packets
+ + counters->bpc[set][direction][IFS_PROTO_OTHER].packets;
+}
+
+
+/* Generic X based nodes used as a base for rb_tree ops */
+struct tag_node {
+ struct rb_node node;
+ tag_t tag;
+};
+
+struct tag_stat {
+ struct tag_node tn;
+ struct data_counters counters;
+ /*
+ * If this tag is acct_tag based, we need to count against the
+ * matching parent uid_tag.
+ */
+ struct data_counters *parent_counters;
+};
+
+struct iface_stat {
+ struct list_head list; /* in iface_stat_list */
+ char *ifname;
+ bool active;
+ /* net_dev is only valid for active iface_stat */
+ struct net_device *net_dev;
+
+ struct byte_packet_counters totals_via_dev[IFS_MAX_DIRECTIONS];
+ struct data_counters totals_via_skb;
+ /*
+ * We keep the last_known, because some devices reset their counters
+ * just before NETDEV_UP, while some will reset just before
+ * NETDEV_REGISTER (which is more normal).
+ * So now, if the device didn't do a NETDEV_UNREGISTER and we see
+ * its current dev stats smaller that what was previously known, we
+ * assume an UNREGISTER and just use the last_known.
+ */
+ struct byte_packet_counters last_known[IFS_MAX_DIRECTIONS];
+ /* last_known is usable when last_known_valid is true */
+ bool last_known_valid;
+
+ struct proc_dir_entry *proc_ptr;
+
+ struct rb_root tag_stat_tree;
+ spinlock_t tag_stat_list_lock;
+};
+
+/* This is needed to create proc_dir_entries from atomic context. */
+struct iface_stat_work {
+ struct work_struct iface_work;
+ struct iface_stat *iface_entry;
+};
+
+/*
+ * Track tag that this socket is transferring data for, and not necessarily
+ * the uid that owns the socket.
+ * This is the tag against which tag_stat.counters will be billed.
+ * These structs need to be looked up by sock and pid.
+ */
+struct sock_tag {
+ struct rb_node sock_node;
+ struct sock *sk; /* Only used as a number, never dereferenced */
+ /* The socket is needed for sockfd_put() */
+ struct socket *socket;
+ /* Used to associate with a given pid */
+ struct list_head list; /* in proc_qtu_data.sock_tag_list */
+ pid_t pid;
+
+ tag_t tag;
+};
+
+struct qtaguid_event_counts {
+ /* Various successful events */
+ atomic64_t sockets_tagged;
+ atomic64_t sockets_untagged;
+ atomic64_t counter_set_changes;
+ atomic64_t delete_cmds;
+ atomic64_t iface_events; /* Number of NETDEV_* events handled */
+
+ atomic64_t match_calls; /* Number of times iptables called mt */
+ /* Number of times iptables called mt from pre or post routing hooks */
+ atomic64_t match_calls_prepost;
+ /*
+ * match_found_sk_*: numbers related to the netfilter matching
+ * function finding a sock for the sk_buff.
+ * Total skbs processed is sum(match_found*).
+ */
+ atomic64_t match_found_sk; /* An sk was already in the sk_buff. */
+ /* The connection tracker had or didn't have the sk. */
+ atomic64_t match_found_sk_in_ct;
+ atomic64_t match_found_no_sk_in_ct;
+ /*
+ * No sk could be found. No apparent owner. Could happen with
+ * unsolicited traffic.
+ */
+ atomic64_t match_no_sk;
+ /*
+ * The file ptr in the sk_socket wasn't there.
+ * This might happen for traffic while the socket is being closed.
+ */
+ atomic64_t match_no_sk_file;
+};
+
+/* Track the set active_set for the given tag. */
+struct tag_counter_set {
+ struct tag_node tn;
+ int active_set;
+};
+
+/*----------------------------------------------*/
+/*
+ * The qtu uid data is used to track resources that are created directly or
+ * indirectly by processes (uid tracked).
+ * It is shared by the processes with the same uid.
+ * Some of the resource will be counted to prevent further rogue allocations,
+ * some will need freeing once the owner process (uid) exits.
+ */
+struct uid_tag_data {
+ struct rb_node node;
+ uid_t uid;
+
+ /*
+ * For the uid, how many accounting tags have been set.
+ */
+ int num_active_tags;
+ /* Track the number of proc_qtu_data that reference it */
+ int num_pqd;
+ struct rb_root tag_ref_tree;
+ /* No tag_node_tree_lock; use uid_tag_data_tree_lock */
+};
+
+struct tag_ref {
+ struct tag_node tn;
+
+ /*
+ * This tracks the number of active sockets that have a tag on them
+ * which matches this tag_ref.tn.tag.
+ * A tag ref can live on after the sockets are untagged.
+ * A tag ref can only be removed during a tag delete command.
+ */
+ int num_sock_tags;
+};
+
+struct proc_qtu_data {
+ struct rb_node node;
+ pid_t pid;
+
+ struct uid_tag_data *parent_tag_data;
+
+ /* Tracks the sock_tags that need freeing upon this proc's death */
+ struct list_head sock_tag_list;
+ /* No spinlock_t sock_tag_list_lock; use the global one. */
+};
+
+/*----------------------------------------------*/
+#endif /* ifndef __XT_QTAGUID_INTERNAL_H__ */
diff --git a/net/netfilter/xt_qtaguid_print.c b/net/netfilter/xt_qtaguid_print.c
new file mode 100644
index 0000000..f6a00a3
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.c
@@ -0,0 +1,566 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Most of the functions in this file just waste time if DEBUG is not defined.
+ * The matching xt_qtaguid_print.h will static inline empty funcs if the needed
+ * debug flags ore not defined.
+ * Those funcs that fail to allocate memory will panic as there is no need to
+ * hobble allong just pretending to do the requested work.
+ */
+
+#define DEBUG
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/net.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+
+
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+
+#ifdef DDEBUG
+
+static void _bug_on_err_or_null(void *ptr)
+{
+ if (IS_ERR_OR_NULL(ptr)) {
+ pr_err("qtaguid: kmalloc failed\n");
+ BUG();
+ }
+}
+
+char *pp_tag_t(tag_t *tag)
+{
+ char *res;
+
+ if (!tag)
+ res = kasprintf(GFP_ATOMIC, "tag_t@null{}");
+ else
+ res = kasprintf(GFP_ATOMIC,
+ "tag_t@%p{tag=0x%llx, uid=%u}",
+ tag, *tag, get_uid_from_tag(*tag));
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+ char *res;
+
+ if (!dc)
+ res = kasprintf(GFP_ATOMIC, "data_counters@null{}");
+ else if (showValues)
+ res = kasprintf(
+ GFP_ATOMIC, "data_counters@%p{"
+ "set0{"
+ "rx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}, "
+ "tx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}}, "
+ "set1{"
+ "rx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}, "
+ "tx{"
+ "tcp{b=%llu, p=%llu}, "
+ "udp{b=%llu, p=%llu},"
+ "other{b=%llu, p=%llu}}}}",
+ dc,
+ dc->bpc[0][IFS_RX][IFS_TCP].bytes,
+ dc->bpc[0][IFS_RX][IFS_TCP].packets,
+ dc->bpc[0][IFS_RX][IFS_UDP].bytes,
+ dc->bpc[0][IFS_RX][IFS_UDP].packets,
+ dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].packets,
+ dc->bpc[0][IFS_TX][IFS_TCP].bytes,
+ dc->bpc[0][IFS_TX][IFS_TCP].packets,
+ dc->bpc[0][IFS_TX][IFS_UDP].bytes,
+ dc->bpc[0][IFS_TX][IFS_UDP].packets,
+ dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].packets,
+ dc->bpc[1][IFS_RX][IFS_TCP].bytes,
+ dc->bpc[1][IFS_RX][IFS_TCP].packets,
+ dc->bpc[1][IFS_RX][IFS_UDP].bytes,
+ dc->bpc[1][IFS_RX][IFS_UDP].packets,
+ dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].packets,
+ dc->bpc[1][IFS_TX][IFS_TCP].bytes,
+ dc->bpc[1][IFS_TX][IFS_TCP].packets,
+ dc->bpc[1][IFS_TX][IFS_UDP].bytes,
+ dc->bpc[1][IFS_TX][IFS_UDP].packets,
+ dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].bytes,
+ dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].packets);
+ else
+ res = kasprintf(GFP_ATOMIC, "data_counters@%p{...}", dc);
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_tag_node(struct tag_node *tn)
+{
+ char *tag_str;
+ char *res;
+
+ if (!tn) {
+ res = kasprintf(GFP_ATOMIC, "tag_node@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tag_str = pp_tag_t(&tn->tag);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_node@%p{tag=%s}",
+ tn, tag_str);
+ _bug_on_err_or_null(res);
+ kfree(tag_str);
+ return res;
+}
+
+char *pp_tag_ref(struct tag_ref *tr)
+{
+ char *tn_str;
+ char *res;
+
+ if (!tr) {
+ res = kasprintf(GFP_ATOMIC, "tag_ref@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tn_str = pp_tag_node(&tr->tn);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_ref@%p{%s, num_sock_tags=%d}",
+ tr, tn_str, tr->num_sock_tags);
+ _bug_on_err_or_null(res);
+ kfree(tn_str);
+ return res;
+}
+
+char *pp_tag_stat(struct tag_stat *ts)
+{
+ char *tn_str;
+ char *counters_str;
+ char *parent_counters_str;
+ char *res;
+
+ if (!ts) {
+ res = kasprintf(GFP_ATOMIC, "tag_stat@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tn_str = pp_tag_node(&ts->tn);
+ counters_str = pp_data_counters(&ts->counters, true);
+ parent_counters_str = pp_data_counters(ts->parent_counters, false);
+ res = kasprintf(GFP_ATOMIC,
+ "tag_stat@%p{%s, counters=%s, parent_counters=%s}",
+ ts, tn_str, counters_str, parent_counters_str);
+ _bug_on_err_or_null(res);
+ kfree(tn_str);
+ kfree(counters_str);
+ kfree(parent_counters_str);
+ return res;
+}
+
+char *pp_iface_stat(struct iface_stat *is)
+{
+ char *res;
+ if (!is) {
+ res = kasprintf(GFP_ATOMIC, "iface_stat@null{}");
+ } else {
+ struct data_counters *cnts = &is->totals_via_skb;
+ res = kasprintf(GFP_ATOMIC, "iface_stat@%p{"
+ "list=list_head{...}, "
+ "ifname=%s, "
+ "total_dev={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "total_skb={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "last_known_valid=%d, "
+ "last_known={rx={bytes=%llu, "
+ "packets=%llu}, "
+ "tx={bytes=%llu, "
+ "packets=%llu}}, "
+ "active=%d, "
+ "net_dev=%p, "
+ "proc_ptr=%p, "
+ "tag_stat_tree=rb_root{...}}",
+ is,
+ is->ifname,
+ is->totals_via_dev[IFS_RX].bytes,
+ is->totals_via_dev[IFS_RX].packets,
+ is->totals_via_dev[IFS_TX].bytes,
+ is->totals_via_dev[IFS_TX].packets,
+ dc_sum_bytes(cnts, 0, IFS_RX),
+ dc_sum_packets(cnts, 0, IFS_RX),
+ dc_sum_bytes(cnts, 0, IFS_TX),
+ dc_sum_packets(cnts, 0, IFS_TX),
+ is->last_known_valid,
+ is->last_known[IFS_RX].bytes,
+ is->last_known[IFS_RX].packets,
+ is->last_known[IFS_TX].bytes,
+ is->last_known[IFS_TX].packets,
+ is->active,
+ is->net_dev,
+ is->proc_ptr);
+ }
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_sock_tag(struct sock_tag *st)
+{
+ char *tag_str;
+ char *res;
+
+ if (!st) {
+ res = kasprintf(GFP_ATOMIC, "sock_tag@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ tag_str = pp_tag_t(&st->tag);
+ res = kasprintf(GFP_ATOMIC, "sock_tag@%p{"
+ "sock_node=rb_node{...}, "
+ "sk=%p socket=%p (f_count=%lu), list=list_head{...}, "
+ "pid=%u, tag=%s}",
+ st, st->sk, st->socket, atomic_long_read(
+ &st->socket->file->f_count),
+ st->pid, tag_str);
+ _bug_on_err_or_null(res);
+ kfree(tag_str);
+ return res;
+}
+
+char *pp_uid_tag_data(struct uid_tag_data *utd)
+{
+ char *res;
+
+ if (!utd)
+ res = kasprintf(GFP_ATOMIC, "uid_tag_data@null{}");
+ else
+ res = kasprintf(GFP_ATOMIC, "uid_tag_data@%p{"
+ "uid=%u, num_active_acct_tags=%d, "
+ "num_pqd=%d, "
+ "tag_node_tree=rb_root{...}, "
+ "proc_qtu_data_tree=rb_root{...}}",
+ utd, utd->uid,
+ utd->num_active_tags, utd->num_pqd);
+ _bug_on_err_or_null(res);
+ return res;
+}
+
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+ char *parent_tag_data_str;
+ char *res;
+
+ if (!pqd) {
+ res = kasprintf(GFP_ATOMIC, "proc_qtu_data@null{}");
+ _bug_on_err_or_null(res);
+ return res;
+ }
+ parent_tag_data_str = pp_uid_tag_data(pqd->parent_tag_data);
+ res = kasprintf(GFP_ATOMIC, "proc_qtu_data@%p{"
+ "node=rb_node{...}, pid=%u, "
+ "parent_tag_data=%s, "
+ "sock_tag_list=list_head{...}}",
+ pqd, pqd->pid, parent_tag_data_str
+ );
+ _bug_on_err_or_null(res);
+ kfree(parent_tag_data_str);
+ return res;
+}
+
+/*------------------------------------------*/
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree)
+{
+ struct rb_node *node;
+ struct sock_tag *sock_tag_entry;
+ char *str;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(sock_tag_tree)) {
+ str = "sock_tag_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "sock_tag_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(sock_tag_tree);
+ node;
+ node = rb_next(node)) {
+ sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+ str = pp_sock_tag(sock_tag_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list)
+{
+ struct sock_tag *sock_tag_entry;
+ char *str;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (list_empty(sock_tag_list)) {
+ str = "sock_tag_list=list_head{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "sock_tag_list=list_head{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ list_for_each_entry(sock_tag_entry, sock_tag_list, list) {
+ str = pp_sock_tag(sock_tag_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct proc_qtu_data *proc_qtu_data_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(proc_qtu_data_tree)) {
+ str = "proc_qtu_data_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "proc_qtu_data_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(proc_qtu_data_tree);
+ node;
+ node = rb_next(node)) {
+ proc_qtu_data_entry = rb_entry(node,
+ struct proc_qtu_data,
+ node);
+ str = pp_proc_qtu_data(proc_qtu_data_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ indent_level++;
+ prdebug_sock_tag_list(indent_level,
+ &proc_qtu_data_entry->sock_tag_list);
+ indent_level--;
+
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct tag_ref *tag_ref_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(tag_ref_tree)) {
+ str = "tag_ref_tree{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "tag_ref_tree{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(tag_ref_tree);
+ node;
+ node = rb_next(node)) {
+ tag_ref_entry = rb_entry(node,
+ struct tag_ref,
+ tn.node);
+ str = pp_tag_ref(tag_ref_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct uid_tag_data *uid_tag_data_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(uid_tag_data_tree)) {
+ str = "uid_tag_data_tree=rb_root{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "uid_tag_data_tree=rb_root{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(uid_tag_data_tree);
+ node;
+ node = rb_next(node)) {
+ uid_tag_data_entry = rb_entry(node, struct uid_tag_data,
+ node);
+ str = pp_uid_tag_data(uid_tag_data_entry);
+ pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+ kfree(str);
+ if (!RB_EMPTY_ROOT(&uid_tag_data_entry->tag_ref_tree)) {
+ indent_level++;
+ prdebug_tag_ref_tree(indent_level,
+ &uid_tag_data_entry->tag_ref_tree);
+ indent_level--;
+ }
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree)
+{
+ char *str;
+ struct rb_node *node;
+ struct tag_stat *ts_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (RB_EMPTY_ROOT(tag_stat_tree)) {
+ str = "tag_stat_tree{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "tag_stat_tree{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ for (node = rb_first(tag_stat_tree);
+ node;
+ node = rb_next(node)) {
+ ts_entry = rb_entry(node, struct tag_stat, tn.node);
+ str = pp_tag_stat(ts_entry);
+ pr_debug("%*d: %s\n", indent_level*2, indent_level,
+ str);
+ kfree(str);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list)
+{
+ char *str;
+ struct iface_stat *iface_entry;
+
+ if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+ return;
+
+ if (list_empty(iface_stat_list)) {
+ str = "iface_stat_list=list_head{}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ return;
+ }
+
+ str = "iface_stat_list=list_head{";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ indent_level++;
+ list_for_each_entry(iface_entry, iface_stat_list, list) {
+ str = pp_iface_stat(iface_entry);
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+ kfree(str);
+
+ spin_lock_bh(&iface_entry->tag_stat_list_lock);
+ if (!RB_EMPTY_ROOT(&iface_entry->tag_stat_tree)) {
+ indent_level++;
+ prdebug_tag_stat_tree(indent_level,
+ &iface_entry->tag_stat_tree);
+ indent_level--;
+ }
+ spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+ }
+ indent_level--;
+ str = "}";
+ pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+#endif /* ifdef DDEBUG */
+/*------------------------------------------*/
+static const char * const netdev_event_strings[] = {
+ "netdev_unknown",
+ "NETDEV_UP",
+ "NETDEV_DOWN",
+ "NETDEV_REBOOT",
+ "NETDEV_CHANGE",
+ "NETDEV_REGISTER",
+ "NETDEV_UNREGISTER",
+ "NETDEV_CHANGEMTU",
+ "NETDEV_CHANGEADDR",
+ "NETDEV_GOING_DOWN",
+ "NETDEV_CHANGENAME",
+ "NETDEV_FEAT_CHANGE",
+ "NETDEV_BONDING_FAILOVER",
+ "NETDEV_PRE_UP",
+ "NETDEV_PRE_TYPE_CHANGE",
+ "NETDEV_POST_TYPE_CHANGE",
+ "NETDEV_POST_INIT",
+ "NETDEV_UNREGISTER_BATCH",
+ "NETDEV_RELEASE",
+ "NETDEV_NOTIFY_PEERS",
+ "NETDEV_JOIN",
+};
+
+const char *netdev_evt_str(int netdev_event)
+{
+ if (netdev_event < 0
+ || netdev_event >= ARRAY_SIZE(netdev_event_strings))
+ return "bad event num";
+ return netdev_event_strings[netdev_event];
+}
diff --git a/net/netfilter/xt_qtaguid_print.h b/net/netfilter/xt_qtaguid_print.h
new file mode 100644
index 0000000..b63871a
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.h
@@ -0,0 +1,120 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __XT_QTAGUID_PRINT_H__
+#define __XT_QTAGUID_PRINT_H__
+
+#include "xt_qtaguid_internal.h"
+
+#ifdef DDEBUG
+
+char *pp_tag_t(tag_t *tag);
+char *pp_data_counters(struct data_counters *dc, bool showValues);
+char *pp_tag_node(struct tag_node *tn);
+char *pp_tag_ref(struct tag_ref *tr);
+char *pp_tag_stat(struct tag_stat *ts);
+char *pp_iface_stat(struct iface_stat *is);
+char *pp_sock_tag(struct sock_tag *st);
+char *pp_uid_tag_data(struct uid_tag_data *qtd);
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd);
+
+/*------------------------------------------*/
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list);
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree);
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree);
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree);
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree);
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree);
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list);
+
+#else
+
+/*------------------------------------------*/
+static inline char *pp_tag_t(tag_t *tag)
+{
+ return NULL;
+}
+static inline char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+ return NULL;
+}
+static inline char *pp_tag_node(struct tag_node *tn)
+{
+ return NULL;
+}
+static inline char *pp_tag_ref(struct tag_ref *tr)
+{
+ return NULL;
+}
+static inline char *pp_tag_stat(struct tag_stat *ts)
+{
+ return NULL;
+}
+static inline char *pp_iface_stat(struct iface_stat *is)
+{
+ return NULL;
+}
+static inline char *pp_sock_tag(struct sock_tag *st)
+{
+ return NULL;
+}
+static inline char *pp_uid_tag_data(struct uid_tag_data *qtd)
+{
+ return NULL;
+}
+static inline char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+ return NULL;
+}
+
+/*------------------------------------------*/
+static inline
+void prdebug_sock_tag_list(int indent_level,
+ struct list_head *sock_tag_list)
+{
+}
+static inline
+void prdebug_sock_tag_tree(int indent_level,
+ struct rb_root *sock_tag_tree)
+{
+}
+static inline
+void prdebug_proc_qtu_data_tree(int indent_level,
+ struct rb_root *proc_qtu_data_tree)
+{
+}
+static inline
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+}
+static inline
+void prdebug_uid_tag_data_tree(int indent_level,
+ struct rb_root *uid_tag_data_tree)
+{
+}
+static inline
+void prdebug_tag_stat_tree(int indent_level,
+ struct rb_root *tag_stat_tree)
+{
+}
+static inline
+void prdebug_iface_stat_list(int indent_level,
+ struct list_head *iface_stat_list)
+{
+}
+#endif
+/*------------------------------------------*/
+const char *netdev_evt_str(int netdev_event);
+#endif /* ifndef __XT_QTAGUID_PRINT_H__ */
diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c
new file mode 100644
index 0000000..4328562
--- /dev/null
+++ b/net/netfilter/xt_quota2.c
@@ -0,0 +1,385 @@
+/*
+ * xt_quota2 - enhanced xt_quota that can count upwards and in packets
+ * as a minimal accounting match.
+ * by Jan Engelhardt <jengelh@medozas.de>, 2008
+ *
+ * Originally based on xt_quota.c:
+ * netfilter module to enforce network quotas
+ * Sam Johnston <samj@samj.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License; either
+ * version 2 of the License, as published by the Free Software Foundation.
+ */
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_quota2.h>
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+#include <linux/netfilter_ipv4/ipt_ULOG.h>
+#endif
+
+/**
+ * @lock: lock to protect quota writers from each other
+ */
+struct xt_quota_counter {
+ u_int64_t quota;
+ spinlock_t lock;
+ struct list_head list;
+ atomic_t ref;
+ char name[sizeof(((struct xt_quota_mtinfo2 *)NULL)->name)];
+ struct proc_dir_entry *procfs_entry;
+};
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+/* Harald's favorite number +1 :D From ipt_ULOG.C */
+static int qlog_nl_event = 112;
+module_param_named(event_num, qlog_nl_event, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(event_num,
+ "Event number for NETLINK_NFLOG message. 0 disables log."
+ "111 is what ipt_ULOG uses.");
+static struct sock *nflognl;
+#endif
+
+static LIST_HEAD(counter_list);
+static DEFINE_SPINLOCK(counter_list_lock);
+
+static struct proc_dir_entry *proc_xt_quota;
+static unsigned int quota_list_perms = S_IRUGO | S_IWUSR;
+static unsigned int quota_list_uid = 0;
+static unsigned int quota_list_gid = 0;
+module_param_named(perms, quota_list_perms, uint, S_IRUGO | S_IWUSR);
+module_param_named(uid, quota_list_uid, uint, S_IRUGO | S_IWUSR);
+module_param_named(gid, quota_list_gid, uint, S_IRUGO | S_IWUSR);
+
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+static void quota2_log(unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const char *prefix)
+{
+ ulog_packet_msg_t *pm;
+ struct sk_buff *log_skb;
+ size_t size;
+ struct nlmsghdr *nlh;
+
+ if (!qlog_nl_event)
+ return;
+
+ size = NLMSG_SPACE(sizeof(*pm));
+ size = max(size, (size_t)NLMSG_GOODSIZE);
+ log_skb = alloc_skb(size, GFP_ATOMIC);
+ if (!log_skb) {
+ pr_err("xt_quota2: cannot alloc skb for logging\n");
+ return;
+ }
+
+ nlh = nlmsg_put(log_skb, /*pid*/0, /*seq*/0, qlog_nl_event,
+ sizeof(*pm), 0);
+ if (!nlh) {
+ pr_err("xt_quota2: nlmsg_put failed\n");
+ kfree_skb(log_skb);
+ return;
+ }
+ pm = nlmsg_data(nlh);
+ if (skb->tstamp.tv64 == 0)
+ __net_timestamp((struct sk_buff *)skb);
+ pm->data_len = 0;
+ pm->hook = hooknum;
+ if (prefix != NULL)
+ strlcpy(pm->prefix, prefix, sizeof(pm->prefix));
+ else
+ *(pm->prefix) = '\0';
+ if (in)
+ strlcpy(pm->indev_name, in->name, sizeof(pm->indev_name));
+ else
+ pm->indev_name[0] = '\0';
+
+ if (out)
+ strlcpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
+ else
+ pm->outdev_name[0] = '\0';
+
+ NETLINK_CB(log_skb).dst_group = 1;
+ pr_debug("throwing 1 packets to netlink group 1\n");
+ netlink_broadcast(nflognl, log_skb, 0, 1, GFP_ATOMIC);
+}
+#else
+static void quota2_log(unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const char *prefix)
+{
+}
+#endif /* if+else CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG */
+
+static ssize_t quota_proc_read(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+ char tmp[24];
+ size_t tmp_size;
+
+ spin_lock_bh(&e->lock);
+ tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", e->quota);
+ spin_unlock_bh(&e->lock);
+ return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t quota_proc_write(struct file *file, const char __user *input,
+ size_t size, loff_t *ppos)
+{
+ struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+ char buf[sizeof("18446744073709551616")];
+
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+ if (copy_from_user(buf, input, size) != 0)
+ return -EFAULT;
+ buf[sizeof(buf)-1] = '\0';
+
+ spin_lock_bh(&e->lock);
+ e->quota = simple_strtoull(buf, NULL, 0);
+ spin_unlock_bh(&e->lock);
+ return size;
+}
+
+static const struct file_operations q2_counter_fops = {
+ .read = quota_proc_read,
+ .write = quota_proc_write,
+ .llseek = default_llseek,
+};
+
+static struct xt_quota_counter *
+q2_new_counter(const struct xt_quota_mtinfo2 *q, bool anon)
+{
+ struct xt_quota_counter *e;
+ unsigned int size;
+
+ /* Do not need all the procfs things for anonymous counters. */
+ size = anon ? offsetof(typeof(*e), list) : sizeof(*e);
+ e = kmalloc(size, GFP_KERNEL);
+ if (e == NULL)
+ return NULL;
+
+ e->quota = q->quota;
+ spin_lock_init(&e->lock);
+ if (!anon) {
+ INIT_LIST_HEAD(&e->list);
+ atomic_set(&e->ref, 1);
+ strlcpy(e->name, q->name, sizeof(e->name));
+ }
+ return e;
+}
+
+/**
+ * q2_get_counter - get ref to counter or create new
+ * @name: name of counter
+ */
+static struct xt_quota_counter *
+q2_get_counter(const struct xt_quota_mtinfo2 *q)
+{
+ struct proc_dir_entry *p;
+ struct xt_quota_counter *e = NULL;
+ struct xt_quota_counter *new_e;
+
+ if (*q->name == '\0')
+ return q2_new_counter(q, true);
+
+ /* No need to hold a lock while getting a new counter */
+ new_e = q2_new_counter(q, false);
+ if (new_e == NULL)
+ goto out;
+
+ spin_lock_bh(&counter_list_lock);
+ list_for_each_entry(e, &counter_list, list)
+ if (strcmp(e->name, q->name) == 0) {
+ atomic_inc(&e->ref);
+ spin_unlock_bh(&counter_list_lock);
+ kfree(new_e);
+ pr_debug("xt_quota2: old counter name=%s", e->name);
+ return e;
+ }
+ e = new_e;
+ pr_debug("xt_quota2: new_counter name=%s", e->name);
+ list_add_tail(&e->list, &counter_list);
+ /* The entry having a refcount of 1 is not directly destructible.
+ * This func has not yet returned the new entry, thus iptables
+ * has not references for destroying this entry.
+ * For another rule to try to destroy it, it would 1st need for this
+ * func* to be re-invoked, acquire a new ref for the same named quota.
+ * Nobody will access the e->procfs_entry either.
+ * So release the lock. */
+ spin_unlock_bh(&counter_list_lock);
+
+ /* create_proc_entry() is not spin_lock happy */
+ p = e->procfs_entry = proc_create_data(e->name, quota_list_perms,
+ proc_xt_quota, &q2_counter_fops, e);
+
+ if (IS_ERR_OR_NULL(p)) {
+ spin_lock_bh(&counter_list_lock);
+ list_del(&e->list);
+ spin_unlock_bh(&counter_list_lock);
+ goto out;
+ }
+ proc_set_user(p, quota_list_uid, quota_list_gid);
+ return e;
+
+ out:
+ kfree(e);
+ return NULL;
+}
+
+static int quota_mt2_check(const struct xt_mtchk_param *par)
+{
+ struct xt_quota_mtinfo2 *q = par->matchinfo;
+
+ pr_debug("xt_quota2: check() flags=0x%04x", q->flags);
+
+ if (q->flags & ~XT_QUOTA_MASK)
+ return -EINVAL;
+
+ q->name[sizeof(q->name)-1] = '\0';
+ if (*q->name == '.' || strchr(q->name, '/') != NULL) {
+ printk(KERN_ERR "xt_quota.3: illegal name\n");
+ return -EINVAL;
+ }
+
+ q->master = q2_get_counter(q);
+ if (q->master == NULL) {
+ printk(KERN_ERR "xt_quota.3: memory alloc failure\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void quota_mt2_destroy(const struct xt_mtdtor_param *par)
+{
+ struct xt_quota_mtinfo2 *q = par->matchinfo;
+ struct xt_quota_counter *e = q->master;
+
+ if (*q->name == '\0') {
+ kfree(e);
+ return;
+ }
+
+ spin_lock_bh(&counter_list_lock);
+ if (!atomic_dec_and_test(&e->ref)) {
+ spin_unlock_bh(&counter_list_lock);
+ return;
+ }
+
+ list_del(&e->list);
+ remove_proc_entry(e->name, proc_xt_quota);
+ spin_unlock_bh(&counter_list_lock);
+ kfree(e);
+}
+
+static bool
+quota_mt2(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ struct xt_quota_mtinfo2 *q = (void *)par->matchinfo;
+ struct xt_quota_counter *e = q->master;
+ bool ret = q->flags & XT_QUOTA_INVERT;
+
+ spin_lock_bh(&e->lock);
+ if (q->flags & XT_QUOTA_GROW) {
+ /*
+ * While no_change is pointless in "grow" mode, we will
+ * implement it here simply to have a consistent behavior.
+ */
+ if (!(q->flags & XT_QUOTA_NO_CHANGE)) {
+ e->quota += (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+ }
+ ret = true;
+ } else {
+ if (e->quota >= skb->len) {
+ if (!(q->flags & XT_QUOTA_NO_CHANGE))
+ e->quota -= (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+ ret = !ret;
+ } else {
+ /* We are transitioning, log that fact. */
+ if (e->quota) {
+ quota2_log(par->hooknum,
+ skb,
+ par->in,
+ par->out,
+ q->name);
+ }
+ /* we do not allow even small packets from now on */
+ e->quota = 0;
+ }
+ }
+ spin_unlock_bh(&e->lock);
+ return ret;
+}
+
+static struct xt_match quota_mt2_reg[] __read_mostly = {
+ {
+ .name = "quota2",
+ .revision = 3,
+ .family = NFPROTO_IPV4,
+ .checkentry = quota_mt2_check,
+ .match = quota_mt2,
+ .destroy = quota_mt2_destroy,
+ .matchsize = sizeof(struct xt_quota_mtinfo2),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "quota2",
+ .revision = 3,
+ .family = NFPROTO_IPV6,
+ .checkentry = quota_mt2_check,
+ .match = quota_mt2,
+ .destroy = quota_mt2_destroy,
+ .matchsize = sizeof(struct xt_quota_mtinfo2),
+ .me = THIS_MODULE,
+ },
+};
+
+static int __init quota_mt2_init(void)
+{
+ int ret;
+ pr_debug("xt_quota2: init()");
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+ nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, NULL);
+ if (!nflognl)
+ return -ENOMEM;
+#endif
+
+ proc_xt_quota = proc_mkdir("xt_quota", init_net.proc_net);
+ if (proc_xt_quota == NULL)
+ return -EACCES;
+
+ ret = xt_register_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+ if (ret < 0)
+ remove_proc_entry("xt_quota", init_net.proc_net);
+ pr_debug("xt_quota2: init() %d", ret);
+ return ret;
+}
+
+static void __exit quota_mt2_exit(void)
+{
+ xt_unregister_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+ remove_proc_entry("xt_quota", init_net.proc_net);
+}
+
+module_init(quota_mt2_init);
+module_exit(quota_mt2_exit);
+MODULE_DESCRIPTION("Xtables: countdown quota match; up counter");
+MODULE_AUTHOR("Sam Johnston <samj@samj.net>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_quota2");
+MODULE_ALIAS("ip6t_quota2");
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 63b2bdb..030f33c 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -35,7 +35,7 @@
#include <net/netfilter/nf_conntrack.h>
#endif
-static void
+void
xt_socket_put_sk(struct sock *sk)
{
if (sk->sk_state == TCP_TIME_WAIT)
@@ -43,6 +43,7 @@
else
sock_put(sk);
}
+EXPORT_SYMBOL(xt_socket_put_sk);
static int
extract_icmp4_fields(const struct sk_buff *skb,
@@ -101,9 +102,8 @@
return 0;
}
-static bool
-socket_match(const struct sk_buff *skb, struct xt_action_param *par,
- const struct xt_socket_mtinfo1 *info)
+struct sock*
+xt_socket_get4_sk(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct iphdr *iph = ip_hdr(skb);
struct udphdr _hdr, *hp = NULL;
@@ -120,7 +120,7 @@
hp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(_hdr), &_hdr);
if (hp == NULL)
- return false;
+ return NULL;
protocol = iph->protocol;
saddr = iph->saddr;
@@ -131,9 +131,9 @@
} else if (iph->protocol == IPPROTO_ICMP) {
if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
&sport, &dport))
- return false;
+ return NULL;
} else {
- return false;
+ return NULL;
}
#ifdef XT_SOCKET_HAVE_CONNTRACK
@@ -157,6 +157,23 @@
sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
+
+ pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
+ protocol, &saddr, ntohs(sport),
+ &daddr, ntohs(dport),
+ &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
+
+ return sk;
+}
+EXPORT_SYMBOL(xt_socket_get4_sk);
+
+static bool
+socket_match(const struct sk_buff *skb, struct xt_action_param *par,
+ const struct xt_socket_mtinfo1 *info)
+{
+ struct sock *sk;
+
+ sk = xt_socket_get4_sk(skb, par);
if (sk != NULL) {
bool wildcard;
bool transparent = true;
@@ -179,11 +196,6 @@
sk = NULL;
}
- pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
- protocol, &saddr, ntohs(sport),
- &daddr, ntohs(dport),
- &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
return (sk != NULL);
}
@@ -255,8 +267,8 @@
return 0;
}
-static bool
-socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
+struct sock*
+xt_socket_get6_sk(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
struct udphdr _hdr, *hp = NULL;
@@ -264,7 +276,6 @@
struct in6_addr *daddr = NULL, *saddr = NULL;
__be16 uninitialized_var(dport), uninitialized_var(sport);
int thoff = 0, uninitialized_var(tproto);
- const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
@@ -276,7 +287,7 @@
hp = skb_header_pointer(skb, thoff,
sizeof(_hdr), &_hdr);
if (hp == NULL)
- return false;
+ return NULL;
saddr = &iph->saddr;
sport = hp->source;
@@ -286,13 +297,30 @@
} else if (tproto == IPPROTO_ICMPV6) {
if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
&sport, &dport))
- return false;
+ return NULL;
} else {
- return false;
+ return NULL;
}
sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
+ pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
+ "(orig %pI6:%hu) sock %p\n",
+ tproto, saddr, ntohs(sport),
+ daddr, ntohs(dport),
+ &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
+ return sk;
+}
+EXPORT_SYMBOL(xt_socket_get6_sk);
+
+static bool
+socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ struct sock *sk;
+ const struct xt_socket_mtinfo1 *info;
+
+ info = (struct xt_socket_mtinfo1 *) par->matchinfo;
+ sk = xt_socket_get6_sk(skb, par);
if (sk != NULL) {
bool wildcard;
bool transparent = true;
@@ -315,12 +343,6 @@
sk = NULL;
}
- pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
- "(orig %pI6:%hu) sock %p\n",
- tproto, saddr, ntohs(sport),
- daddr, ntohs(dport),
- &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
return (sk != NULL);
}
#endif
diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig
index 78efe89..8e12c8a 100644
--- a/net/rfkill/Kconfig
+++ b/net/rfkill/Kconfig
@@ -10,6 +10,11 @@
To compile this driver as a module, choose M here: the
module will be called rfkill.
+config RFKILL_PM
+ bool "Power off on suspend"
+ depends on RFKILL && PM
+ default y
+
# LED trigger support
config RFKILL_LEDS
bool
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 6563cc0..352cb55 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -792,6 +792,7 @@
}
EXPORT_SYMBOL(rfkill_pause_polling);
+#ifdef CONFIG_RFKILL_PM
void rfkill_resume_polling(struct rfkill *rfkill)
{
BUG_ON(!rfkill);
@@ -826,14 +827,17 @@
return 0;
}
+#endif
static struct class rfkill_class = {
.name = "rfkill",
.dev_release = rfkill_release,
.dev_attrs = rfkill_dev_attrs,
.dev_uevent = rfkill_dev_uevent,
+#ifdef CONFIG_RFKILL_PM
.suspend = rfkill_suspend,
.resume = rfkill_resume,
+#endif
};
bool rfkill_blocked(struct rfkill *rfkill)
diff --git a/net/socket.c b/net/socket.c
index e91e8ed..cc5fe7b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1764,6 +1764,8 @@
if (len > INT_MAX)
len = INT_MAX;
+ if (unlikely(!access_ok(VERIFY_READ, buff, len)))
+ return -EFAULT;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
@@ -1823,6 +1825,8 @@
if (size > INT_MAX)
size = INT_MAX;
+ if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size)))
+ return -EFAULT;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 5356b12..77d251e 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -254,7 +254,7 @@
{
if (fatal_signal_pending(current))
return -ERESTARTSYS;
- freezable_schedule();
+ freezable_schedule_unsafe();
return 0;
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8f118c7..7617fbf 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -114,6 +114,7 @@
#include <linux/mount.h>
#include <net/checksum.h>
#include <linux/security.h>
+#include <linux/freezer.h>
struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
EXPORT_SYMBOL_GPL(unix_socket_table);
@@ -1714,7 +1715,12 @@
goto out_unlock;
}
- if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+ /* other == sk && unix_peer(other) != sk if
+ * - unix_peer(sk) == NULL, destination address bound to sk
+ * - unix_peer(sk) == sk by time of get but disconnected before lock
+ */
+ if (other != sk &&
+ unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
if (timeo) {
timeo = unix_wait_for_peer(other, timeo);
@@ -2055,7 +2061,7 @@
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
unix_state_unlock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = freezable_schedule_timeout(timeo);
unix_state_lock(sk);
if (sock_flag(sk, SOCK_DEAD))
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 16d08b3..4c602d1 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -166,3 +166,14 @@
from lib80211.
If unsure, say N.
+
+config CFG80211_ALLOW_RECONNECT
+ bool "Allow reconnect while already connected"
+ depends on CFG80211
+ default n
+ help
+ cfg80211 stack doesn't allow to connect if you are already
+ connected. This option allows to make a connection in this case.
+
+ Select this option ONLY for wlan drivers that are specifically
+ built for such purposes.
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 64fcbae..0fc9d75 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -305,6 +305,59 @@
rtnl_unlock();
}
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev)
+{
+ struct cfg80211_iface_destroy *item;
+
+ ASSERT_RTNL();
+
+ spin_lock_irq(&rdev->destroy_list_lock);
+ while ((item = list_first_entry_or_null(&rdev->destroy_list,
+ struct cfg80211_iface_destroy,
+ list))) {
+ struct wireless_dev *wdev, *tmp;
+ u32 nlportid = item->nlportid;
+
+ list_del(&item->list);
+ kfree(item);
+ spin_unlock_irq(&rdev->destroy_list_lock);
+
+ list_for_each_entry_safe(wdev, tmp, &rdev->wdev_list, list) {
+ if (nlportid == wdev->owner_nlportid)
+ rdev_del_virtual_intf(rdev, wdev);
+ }
+
+ spin_lock_irq(&rdev->destroy_list_lock);
+ }
+ spin_unlock_irq(&rdev->destroy_list_lock);
+}
+
+static void cfg80211_destroy_iface_wk(struct work_struct *work)
+{
+ struct cfg80211_registered_device *rdev;
+
+ rdev = container_of(work, struct cfg80211_registered_device,
+ destroy_work);
+
+ rtnl_lock();
+ cfg80211_destroy_ifaces(rdev);
+ rtnl_unlock();
+}
+
+static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
+{
+ struct cfg80211_registered_device *rdev;
+
+ rdev = container_of(work, struct cfg80211_registered_device,
+ sched_scan_stop_wk);
+
+ rtnl_lock();
+
+ __cfg80211_stop_sched_scan(rdev, false);
+
+ rtnl_unlock();
+}
+
/* exported functions */
struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
@@ -368,6 +421,11 @@
rdev->wiphy.dev.class = &ieee80211_class;
rdev->wiphy.dev.platform_data = rdev;
+ INIT_LIST_HEAD(&rdev->destroy_list);
+ spin_lock_init(&rdev->destroy_list_lock);
+ INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
+ INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
+
#ifdef CONFIG_CFG80211_DEFAULT_PS
rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
#endif
@@ -736,6 +794,8 @@
cancel_work_sync(&rdev->conn_work);
flush_work(&rdev->event_work);
cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
+ flush_work(&rdev->destroy_work);
+ flush_work(&rdev->sched_scan_stop_wk);
if (rdev->wowlan && rdev->ops->set_wakeup)
rdev_set_wakeup(rdev, false);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index fd35dae..2a7cd12 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -77,9 +77,7 @@
struct mutex sched_scan_mtx;
-#ifdef CONFIG_NL80211_TESTMODE
- struct genl_info *testmode_info;
-#endif
+ struct genl_info *cur_cmd_info;
struct work_struct conn_work;
struct work_struct event_work;
@@ -91,6 +89,12 @@
/* netlink port which started critical protocol (0 means not started) */
u32 crit_proto_nlportid;
+ spinlock_t destroy_list_lock;
+ struct list_head destroy_list;
+ struct work_struct destroy_work;
+
+ struct work_struct sched_scan_stop_wk;
+
/* must be last because of the way we do wiphy_priv(),
* and it should at least be aligned to NETDEV_ALIGN */
struct wiphy wiphy __aligned(NETDEV_ALIGN);
@@ -262,6 +266,13 @@
u32 nlportid;
};
+struct cfg80211_iface_destroy {
+ struct list_head list;
+ u32 nlportid;
+};
+
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev);
+
/* free object */
extern void cfg80211_dev_free(struct cfg80211_registered_device *rdev);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index dd3dbed..df9a997 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -378,6 +378,13 @@
[NL80211_ATTR_MDID] = { .type = NLA_U16 },
[NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY,
.len = IEEE80211_MAX_DATA_LEN },
+ [NL80211_ATTR_PEER_AID] = { .type = NLA_U16 },
+ [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
+ [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
+ [NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+ [NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
+ [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
+ [NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
};
/* policy for the key attributes */
@@ -1520,6 +1527,39 @@
dev->wiphy.max_acl_mac_addrs))
goto nla_put_failure;
+ if (dev->wiphy.n_vendor_commands) {
+ const struct nl80211_vendor_cmd_info *info;
+ struct nlattr *nested;
+
+ nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
+ if (!nested)
+ goto nla_put_failure;
+
+ for (i = 0; i < dev->wiphy.n_vendor_commands; i++) {
+ info = &dev->wiphy.vendor_commands[i].info;
+ if (nla_put(msg, i + 1, sizeof(*info), info))
+ goto nla_put_failure;
+ }
+ nla_nest_end(msg, nested);
+ }
+
+ if (dev->wiphy.n_vendor_events) {
+ const struct nl80211_vendor_cmd_info *info;
+ struct nlattr *nested;
+
+ nested = nla_nest_start(msg,
+ NL80211_ATTR_VENDOR_EVENTS);
+ if (!nested)
+ goto nla_put_failure;
+
+ for (i = 0; i < dev->wiphy.n_vendor_events; i++) {
+ info = &dev->wiphy.vendor_events[i];
+ if (nla_put(msg, i + 1, sizeof(*info), info))
+ goto nla_put_failure;
+ }
+ nla_nest_end(msg, nested);
+ }
+
/*
* Any information below this point is only available to
* applications that can deal with it being split. This
@@ -2420,6 +2460,9 @@
enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED;
u32 flags;
+ /* to avoid failing a new interface creation due to pending removal */
+ cfg80211_destroy_ifaces(rdev);
+
memset(¶ms, 0, sizeof(params));
if (!info->attrs[NL80211_ATTR_IFNAME])
@@ -2464,6 +2507,9 @@
return PTR_ERR(wdev);
}
+ if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+ wdev->owner_nlportid = info->snd_portid;
+
switch (type) {
case NL80211_IFTYPE_MESH_POINT:
if (!info->attrs[NL80211_ATTR_MESH_ID])
@@ -2638,8 +2684,8 @@
hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
NL80211_CMD_NEW_KEY);
- if (IS_ERR(hdr))
- return PTR_ERR(hdr);
+ if (!hdr)
+ goto nla_put_failure;
cookie.msg = msg;
cookie.idx = key_idx;
@@ -5285,6 +5331,7 @@
enum ieee80211_band band;
size_t ie_len;
struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1];
+ s32 default_match_rssi = NL80211_SCAN_RSSI_THOLD_OFF;
if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
!rdev->ops->sched_scan_start)
@@ -5323,11 +5370,40 @@
if (n_ssids > wiphy->max_sched_scan_ssids)
return -EINVAL;
- if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH])
+ /*
+ * First, count the number of 'real' matchsets. Due to an issue with
+ * the old implementation, matchsets containing only the RSSI attribute
+ * (NL80211_SCHED_SCAN_MATCH_ATTR_RSSI) are considered as the 'default'
+ * RSSI for all matchsets, rather than their own matchset for reporting
+ * all APs with a strong RSSI. This is needed to be compatible with
+ * older userspace that treated a matchset with only the RSSI as the
+ * global RSSI for all other matchsets - if there are other matchsets.
+ */
+ if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) {
nla_for_each_nested(attr,
info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
- tmp)
- n_match_sets++;
+ tmp) {
+ struct nlattr *rssi;
+
+ err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+ nla_data(attr), nla_len(attr),
+ nl80211_match_policy);
+ if (err)
+ return err;
+ /* add other standalone attributes here */
+ if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]) {
+ n_match_sets++;
+ continue;
+ }
+ rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
+ if (rssi)
+ default_match_rssi = nla_get_s32(rssi);
+ }
+ }
+
+ /* However, if there's no other matchset, add the RSSI one */
+ if (!n_match_sets && default_match_rssi != NL80211_SCAN_RSSI_THOLD_OFF)
+ n_match_sets = 1;
if (n_match_sets > wiphy->max_match_sets)
return -EINVAL;
@@ -5455,6 +5531,15 @@
nl80211_match_policy);
ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID];
if (ssid) {
+ if (WARN_ON(i >= n_match_sets)) {
+ /* this indicates a programming error,
+ * the loop above should have verified
+ * things properly
+ */
+ err = -EINVAL;
+ goto out_free;
+ }
+
if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) {
err = -EINVAL;
goto out_free;
@@ -5463,17 +5548,32 @@
nla_data(ssid), nla_len(ssid));
request->match_sets[i].ssid.ssid_len =
nla_len(ssid);
+ /* special attribute - old implemenation w/a */
+ request->match_sets[i].rssi_thold =
+ default_match_rssi;
+ rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
+ if (rssi)
+ request->match_sets[i].rssi_thold =
+ nla_get_s32(rssi);
}
- rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
- if (rssi)
- request->rssi_thold = nla_get_u32(rssi);
- else
- request->rssi_thold =
- NL80211_SCAN_RSSI_THOLD_OFF;
i++;
}
+
+ /* there was no other matchset, so the RSSI one is alone */
+ if (i == 0)
+ request->match_sets[0].rssi_thold = default_match_rssi;
+
+ request->min_rssi_thold = INT_MAX;
+ for (i = 0; i < n_match_sets; i++)
+ request->min_rssi_thold =
+ min(request->match_sets[i].rssi_thold,
+ request->min_rssi_thold);
+ } else {
+ request->min_rssi_thold = NL80211_SCAN_RSSI_THOLD_OFF;
}
+ request->rssi_thold = request->min_rssi_thold;
+
if (info->attrs[NL80211_ATTR_IE]) {
request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
memcpy((void *)request->ie,
@@ -5500,6 +5600,9 @@
err = rdev_sched_scan_start(rdev, dev, request);
if (!err) {
+ if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+ request->owner_nlportid = info->snd_portid;
+
rdev->sched_scan_req = request;
nl80211_send_sched_scan(rdev, dev,
NL80211_CMD_START_SCHED_SCAN);
@@ -6402,12 +6505,62 @@
return err;
}
+static struct sk_buff *
+__cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
+ int approxlen, u32 portid, u32 seq,
+ enum nl80211_commands cmd,
+ enum nl80211_attrs attr,
+ const struct nl80211_vendor_cmd_info *info,
+ gfp_t gfp)
+{
+ struct sk_buff *skb;
+ void *hdr;
+ struct nlattr *data;
+
+ skb = nlmsg_new(approxlen + 100, gfp);
+ if (!skb)
+ return NULL;
+
+ hdr = nl80211hdr_put(skb, portid, seq, 0, cmd);
+ if (!hdr) {
+ kfree_skb(skb);
+ return NULL;
+ }
+
+ if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
+ goto nla_put_failure;
+
+ if (info) {
+ if (nla_put_u32(skb, NL80211_ATTR_VENDOR_ID,
+ info->vendor_id))
+ goto nla_put_failure;
+ if (nla_put_u32(skb, NL80211_ATTR_VENDOR_SUBCMD,
+ info->subcmd))
+ goto nla_put_failure;
+ }
+
+ data = nla_nest_start(skb, attr);
+
+ ((void **)skb->cb)[0] = rdev;
+ ((void **)skb->cb)[1] = hdr;
+ ((void **)skb->cb)[2] = data;
+
+ return skb;
+
+ nla_put_failure:
+ kfree_skb(skb);
+ return NULL;
+}
#ifdef CONFIG_NL80211_TESTMODE
static struct genl_multicast_group nl80211_testmode_mcgrp = {
.name = "testmode",
};
+static struct genl_multicast_group nl80211_vendor_mcgrp = {
+ .name = "vendor",
+};
+
static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info)
{
struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -6418,11 +6571,11 @@
err = -EOPNOTSUPP;
if (rdev->ops->testmode_cmd) {
- rdev->testmode_info = info;
+ rdev->cur_cmd_info = info;
err = rdev_testmode_cmd(rdev,
nla_data(info->attrs[NL80211_ATTR_TESTDATA]),
nla_len(info->attrs[NL80211_ATTR_TESTDATA]));
- rdev->testmode_info = NULL;
+ rdev->cur_cmd_info = NULL;
}
return err;
@@ -6491,6 +6644,9 @@
NL80211_CMD_TESTMODE);
struct nlattr *tmdata;
+ if (!hdr)
+ break;
+
if (nla_put_u32(skb, NL80211_ATTR_WIPHY, phy_idx)) {
genlmsg_cancel(skb, hdr);
break;
@@ -6523,84 +6679,37 @@
return err;
}
-static struct sk_buff *
-__cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev,
- int approxlen, u32 portid, u32 seq, gfp_t gfp)
-{
- struct sk_buff *skb;
- void *hdr;
- struct nlattr *data;
-
- skb = nlmsg_new(approxlen + 100, gfp);
- if (!skb)
- return NULL;
-
- hdr = nl80211hdr_put(skb, portid, seq, 0, NL80211_CMD_TESTMODE);
- if (!hdr) {
- kfree_skb(skb);
- return NULL;
- }
-
- if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
- goto nla_put_failure;
- data = nla_nest_start(skb, NL80211_ATTR_TESTDATA);
-
- ((void **)skb->cb)[0] = rdev;
- ((void **)skb->cb)[1] = hdr;
- ((void **)skb->cb)[2] = data;
-
- return skb;
-
- nla_put_failure:
- kfree_skb(skb);
- return NULL;
-}
-
-struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
- int approxlen)
+struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+ enum nl80211_commands cmd,
+ enum nl80211_attrs attr,
+ int vendor_event_idx,
+ int approxlen, gfp_t gfp)
{
struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+ const struct nl80211_vendor_cmd_info *info;
- if (WARN_ON(!rdev->testmode_info))
+ switch (cmd) {
+ case NL80211_CMD_TESTMODE:
+ if (WARN_ON(vendor_event_idx != -1))
+ return NULL;
+ info = NULL;
+ break;
+ case NL80211_CMD_VENDOR:
+ if (WARN_ON(vendor_event_idx < 0 ||
+ vendor_event_idx >= wiphy->n_vendor_events))
+ return NULL;
+ info = &wiphy->vendor_events[vendor_event_idx];
+ break;
+ default:
+ WARN_ON(1);
return NULL;
-
- return __cfg80211_testmode_alloc_skb(rdev, approxlen,
- rdev->testmode_info->snd_portid,
- rdev->testmode_info->snd_seq,
- GFP_KERNEL);
-}
-EXPORT_SYMBOL(cfg80211_testmode_alloc_reply_skb);
-
-int cfg80211_testmode_reply(struct sk_buff *skb)
-{
- struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
- void *hdr = ((void **)skb->cb)[1];
- struct nlattr *data = ((void **)skb->cb)[2];
-
- /* clear CB data for netlink core to own from now on */
- memset(skb->cb, 0, sizeof(skb->cb));
-
- if (WARN_ON(!rdev->testmode_info)) {
- kfree_skb(skb);
- return -EINVAL;
}
-
- nla_nest_end(skb, data);
- genlmsg_end(skb, hdr);
- return genlmsg_reply(skb, rdev->testmode_info);
+ return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0,
+ cmd, attr, info, gfp);
}
-EXPORT_SYMBOL(cfg80211_testmode_reply);
+EXPORT_SYMBOL(__cfg80211_alloc_event_skb);
-struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
- int approxlen, gfp_t gfp)
-{
- struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
-
- return __cfg80211_testmode_alloc_skb(rdev, approxlen, 0, 0, gfp);
-}
-EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb);
-
-void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
+void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp)
{
struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
void *hdr = ((void **)skb->cb)[1];
@@ -6611,10 +6720,15 @@
nla_nest_end(skb, data);
genlmsg_end(skb, hdr);
- genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
- nl80211_testmode_mcgrp.id, gfp);
+
+ if (data->nla_type == NL80211_ATTR_VENDOR_DATA)
+ genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
+ nl80211_vendor_mcgrp.id, gfp);
+ else
+ genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
+ nl80211_testmode_mcgrp.id, gfp);
}
-EXPORT_SYMBOL(cfg80211_testmode_event);
+EXPORT_SYMBOL(__cfg80211_send_event_skb);
#endif
static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
@@ -6935,9 +7049,8 @@
hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
NL80211_CMD_REMAIN_ON_CHANNEL);
-
- if (IS_ERR(hdr)) {
- err = PTR_ERR(hdr);
+ if (!hdr) {
+ err = -ENOBUFS;
goto free_msg;
}
@@ -7224,9 +7337,8 @@
hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
NL80211_CMD_FRAME);
-
- if (IS_ERR(hdr)) {
- err = PTR_ERR(hdr);
+ if (!hdr) {
+ err = -ENOBUFS;
goto free_msg;
}
}
@@ -8087,9 +8199,8 @@
hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
NL80211_CMD_PROBE_CLIENT);
-
- if (IS_ERR(hdr)) {
- err = PTR_ERR(hdr);
+ if (!hdr) {
+ err = -ENOBUFS;
goto free_msg;
}
@@ -8306,6 +8417,111 @@
return 0;
}
+static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg80211_registered_device *rdev = info->user_ptr[0];
+ struct wireless_dev *wdev =
+ __cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs);
+ int i, err;
+ u32 vid, subcmd;
+
+ if (!rdev || !rdev->wiphy.vendor_commands)
+ return -EOPNOTSUPP;
+
+ if (IS_ERR(wdev)) {
+ err = PTR_ERR(wdev);
+ if (err != -EINVAL)
+ return err;
+ wdev = NULL;
+ } else if (wdev->wiphy != &rdev->wiphy) {
+ return -EINVAL;
+ }
+
+ if (!info->attrs[NL80211_ATTR_VENDOR_ID] ||
+ !info->attrs[NL80211_ATTR_VENDOR_SUBCMD])
+ return -EINVAL;
+
+ vid = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_ID]);
+ subcmd = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_SUBCMD]);
+ for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) {
+ const struct wiphy_vendor_command *vcmd;
+ void *data = NULL;
+ int len = 0;
+
+ vcmd = &rdev->wiphy.vendor_commands[i];
+
+ if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
+ continue;
+
+ if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
+ WIPHY_VENDOR_CMD_NEED_NETDEV)) {
+ if (!wdev)
+ return -EINVAL;
+ if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
+ !wdev->netdev)
+ return -EINVAL;
+
+ if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
+ if (!wdev->netdev ||
+ !netif_running(wdev->netdev))
+ return -ENETDOWN;
+ }
+ } else {
+ wdev = NULL;
+ }
+
+ if (info->attrs[NL80211_ATTR_VENDOR_DATA]) {
+ data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+ len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+ }
+
+ rdev->cur_cmd_info = info;
+ err = rdev->wiphy.vendor_commands[i].doit(&rdev->wiphy, wdev,
+ data, len);
+ rdev->cur_cmd_info = NULL;
+ return err;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
+ enum nl80211_commands cmd,
+ enum nl80211_attrs attr,
+ int approxlen)
+{
+ struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+
+ if (WARN_ON(!rdev->cur_cmd_info))
+ return NULL;
+
+ return __cfg80211_alloc_vendor_skb(rdev, approxlen,
+ 0,
+ 0,
+ cmd, attr, NULL, GFP_KERNEL);
+}
+EXPORT_SYMBOL(__cfg80211_alloc_reply_skb);
+
+int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
+{
+ struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
+ void *hdr = ((void **)skb->cb)[1];
+ struct nlattr *data = ((void **)skb->cb)[2];
+
+ /* clear CB data for netlink core to own from now on */
+ memset(skb->cb, 0, sizeof(skb->cb));
+
+ if (WARN_ON(!rdev->cur_cmd_info)) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ nla_nest_end(skb, data);
+ genlmsg_end(skb, hdr);
+ return genlmsg_reply(skb, rdev->cur_cmd_info);
+}
+EXPORT_SYMBOL(cfg80211_vendor_cmd_reply);
+
#define NL80211_FLAG_NEED_WIPHY 0x01
#define NL80211_FLAG_NEED_NETDEV 0x02
#define NL80211_FLAG_NEED_RTNL 0x04
@@ -9010,7 +9226,15 @@
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
NL80211_FLAG_NEED_RTNL,
- }
+ },
+ {
+ .cmd = NL80211_CMD_VENDOR,
+ .doit = nl80211_vendor_cmd,
+ .policy = nl80211_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL80211_FLAG_NEED_WIPHY |
+ NL80211_FLAG_NEED_RTNL,
+ },
};
static struct genl_multicast_group nl80211_mlme_mcgrp = {
@@ -10691,9 +10915,22 @@
rcu_read_lock();
list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
- list_for_each_entry_rcu(wdev, &rdev->wdev_list, list)
+ bool schedule_destroy_work = false;
+ bool schedule_scan_stop = false;
+ struct cfg80211_sched_scan_request *sched_scan_req =
+ rcu_dereference(rdev->sched_scan_req);
+
+ if (sched_scan_req && notify->portid &&
+ sched_scan_req->owner_nlportid == notify->portid)
+ schedule_scan_stop = true;
+
+ list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
cfg80211_mlme_unregister_socket(wdev, notify->portid);
+ if (wdev->owner_nlportid == notify->portid)
+ schedule_destroy_work = true;
+ }
+
spin_lock_bh(&rdev->beacon_registrations_lock);
list_for_each_entry_safe(reg, tmp, &rdev->beacon_registrations,
list) {
@@ -10704,6 +10941,25 @@
}
}
spin_unlock_bh(&rdev->beacon_registrations_lock);
+
+ if (schedule_destroy_work) {
+ struct cfg80211_iface_destroy *destroy;
+
+ destroy = kzalloc(sizeof(*destroy), GFP_ATOMIC);
+ if (destroy) {
+ destroy->nlportid = notify->portid;
+ spin_lock(&rdev->destroy_list_lock);
+ list_add(&destroy->list, &rdev->destroy_list);
+ spin_unlock(&rdev->destroy_list_lock);
+ schedule_work(&rdev->destroy_work);
+ }
+ } else if (schedule_scan_stop) {
+ sched_scan_req->owner_nlportid = 0;
+
+ if (rdev->ops->sched_scan_stop &&
+ rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+ schedule_work(&rdev->sched_scan_stop_wk);
+ }
}
rcu_read_unlock();
@@ -10829,6 +11085,10 @@
err = genl_register_mc_group(&nl80211_fam, &nl80211_testmode_mcgrp);
if (err)
goto err_out;
+
+ err = genl_register_mc_group(&nl80211_fam, &nl80211_vendor_mcgrp);
+ if (err)
+ goto err_out;
#endif
err = netlink_register_notifier(&nl80211_netlink_notifier);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 81019ee..ab406d0 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -55,7 +55,7 @@
* also linked into the probe response struct.
*/
-#define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ)
+#define IEEE80211_SCAN_RESULT_EXPIRE (7 * HZ)
static void bss_free(struct cfg80211_internal_bss *bss)
{
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 3ed35c3..e2f74e6 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -707,8 +707,10 @@
wdev->iftype != NL80211_IFTYPE_P2P_CLIENT))
return;
+#ifndef CONFIG_CFG80211_ALLOW_RECONNECT
if (wdev->sme_state != CFG80211_SME_CONNECTED)
return;
+#endif
if (wdev->current_bss) {
cfg80211_unhold_bss(wdev->current_bss);
@@ -785,10 +787,14 @@
ASSERT_WDEV_LOCK(wdev);
+#ifndef CONFIG_CFG80211_ALLOW_RECONNECT
if (wdev->sme_state != CFG80211_SME_IDLE)
return -EALREADY;
if (WARN_ON(wdev->connect_keys)) {
+#else
+ if (wdev->connect_keys) {
+#endif
kfree(wdev->connect_keys);
wdev->connect_keys = NULL;
}
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f97869f..ef2142a 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -273,6 +273,12 @@
dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
+# cat
+# ---------------------------------------------------------------------------
+# Concatentate multiple files together
+quiet_cmd_cat = CAT $@
+cmd_cat = (cat $(filter-out FORCE,$^) > $@) || (rm -f $@; false)
+
# Bzip2
# ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index ecbb447..8900c5c5 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -24,7 +24,7 @@
INSTALL_MOD_DIR ?= extra
ext-mod-dir = $(INSTALL_MOD_DIR)$(subst $(patsubst %/,%,$(KBUILD_EXTMOD)),,$(@D))
-modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
+modinst_dir ?= $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
$(modules):
$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 43eda40..35e0f16 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -1083,7 +1083,7 @@
csym->flags &= ~(SYMBOL_VALID);
}
-static void set_all_choice_values(struct symbol *csym)
+void set_all_choice_values(struct symbol *csym)
{
struct property *prop;
struct symbol *sym;
@@ -1100,7 +1100,7 @@
}
csym->flags |= SYMBOL_DEF_USER;
/* clear VALID to get value calculated */
- csym->flags &= ~(SYMBOL_VALID);
+ csym->flags &= ~(SYMBOL_VALID | SYMBOL_NEED_SET_CHOICE_VALUES);
}
void conf_set_all_new_symbols(enum conf_def_mode mode)
@@ -1202,6 +1202,14 @@
* selected in a choice block and we set it to yes,
* and the rest to no.
*/
+ if (mode != def_random) {
+ for_all_symbols(i, csym) {
+ if ((sym_is_choice(csym) && !sym_has_value(csym)) ||
+ sym_is_choice_value(csym))
+ csym->flags |= SYMBOL_NEED_SET_CHOICE_VALUES;
+ }
+ }
+
for_all_symbols(i, csym) {
if (sym_has_value(csym) || !sym_is_choice(csym))
continue;
@@ -1209,7 +1217,5 @@
sym_calc_value(csym);
if (mode == def_random)
randomize_choice_values(csym);
- else
- set_all_choice_values(csym);
}
}
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index cdd4860..df198a5 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -106,6 +106,9 @@
#define SYMBOL_DEF3 0x40000 /* symbol.def[S_DEF_3] is valid */
#define SYMBOL_DEF4 0x80000 /* symbol.def[S_DEF_4] is valid */
+/* choice values need to be set before calculating this symbol value */
+#define SYMBOL_NEED_SET_CHOICE_VALUES 0x100000
+
#define SYMBOL_MAXLENGTH 256
#define SYMBOL_HASHSIZE 9973
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index f8aee5f..0c8d419 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -87,6 +87,7 @@
void sym_set_change_count(int count);
void sym_add_change_count(int count);
void conf_set_all_new_symbols(enum conf_def_mode mode);
+void set_all_choice_values(struct symbol *csym);
struct conf_printer {
void (*print_symbol)(FILE *, struct symbol *, const char *, void *);
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index ecc5aa5..ab8f4c8 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -300,6 +300,14 @@
if (sym->flags & SYMBOL_VALID)
return;
+
+ if (sym_is_choice_value(sym) &&
+ sym->flags & SYMBOL_NEED_SET_CHOICE_VALUES) {
+ sym->flags &= ~SYMBOL_NEED_SET_CHOICE_VALUES;
+ prop = sym_get_choice_prop(sym);
+ sym_calc_value(prop_get_symbol(prop));
+ }
+
sym->flags |= SYMBOL_VALID;
oldval = sym->curr;
@@ -425,6 +433,9 @@
if (sym->flags & SYMBOL_AUTO)
sym->flags &= ~SYMBOL_WRITE;
+
+ if (sym->flags & SYMBOL_NEED_SET_CHOICE_VALUES)
+ set_all_choice_values(sym);
}
void sym_clear_all_valid(void)
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index e66d4d2..5e74595 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -174,6 +174,9 @@
DEVID_FIELD(x86_cpu_id, model);
DEVID_FIELD(x86_cpu_id, vendor);
+ DEVID(cpu_feature);
+ DEVID_FIELD(cpu_feature, feature);
+
DEVID(mei_cl_device_id);
DEVID_FIELD(mei_cl_device_id, name);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 4319a38..09632f0 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1133,6 +1133,16 @@
}
ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);
+/* LOOKS like cpu:type:*:feature:*FEAT* */
+static int do_cpu_entry(const char *filename, void *symval, char *alias)
+{
+ DEF_FIELD(symval, cpu_feature, feature);
+
+ sprintf(alias, "cpu:type:*:feature:*%04X*", feature);
+ return 1;
+}
+ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);
+
/* Looks like: mei:S */
static int do_mei_entry(const char *filename, void *symval,
char *alias)
diff --git a/security/Kconfig b/security/Kconfig
index e9c6ac7..e371824 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -18,6 +18,15 @@
If you are unsure how to answer this question, answer N.
+config SECURITY_PERF_EVENTS_RESTRICT
+ bool "Restrict unprivileged use of performance events"
+ depends on PERF_EVENTS
+ help
+ If you say Y here, the kernel.perf_event_paranoid sysctl
+ will be set to 3 by default, and no unprivileged use of the
+ perf_event_open syscall will be permitted unless it is
+ changed.
+
config SECURITY
bool "Enable different security models"
depends on SYSFS
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 859abda..9aaa4e7 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -629,7 +629,7 @@
* There is no exception for unconfined as change_hat is not
* available.
*/
- if (current->no_new_privs)
+ if (task_no_new_privs(current))
return -EPERM;
/* released below */
@@ -780,7 +780,7 @@
* no_new_privs is set because this aways results in a reduction
* of permissions.
*/
- if (current->no_new_privs && !unconfined(profile)) {
+ if (task_no_new_privs(current) && !unconfined(profile)) {
put_cred(cred);
return -EPERM;
}
diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h
index 40aedd9..4a8cbfe 100644
--- a/security/apparmor/include/apparmor.h
+++ b/security/apparmor/include/apparmor.h
@@ -65,7 +65,6 @@
char *aa_split_fqname(char *args, char **ns_name);
void aa_info_message(const char *str);
void *kvmalloc(size_t size);
-void kvfree(void *buffer);
/**
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
index 7430298..ce8d9a8 100644
--- a/security/apparmor/lib.c
+++ b/security/apparmor/lib.c
@@ -103,35 +103,3 @@
}
return buffer;
}
-
-/**
- * do_vfree - workqueue routine for freeing vmalloced memory
- * @work: data to be freed
- *
- * The work_struct is overlaid to the data being freed, as at the point
- * the work is scheduled the data is no longer valid, be its freeing
- * needs to be delayed until safe.
- */
-static void do_vfree(struct work_struct *work)
-{
- vfree(work);
-}
-
-/**
- * kvfree - free an allocation do by kvmalloc
- * @buffer: buffer to free (MAYBE_NULL)
- *
- * Free a buffer allocated by kvmalloc
- */
-void kvfree(void *buffer)
-{
- if (is_vmalloc_addr(buffer)) {
- /* Data is no longer valid so just use the allocated space
- * as the work_struct
- */
- struct work_struct *work = (struct work_struct *) buffer;
- INIT_WORK(work, do_vfree);
- schedule_work(work);
- } else
- kfree(buffer);
-}
diff --git a/security/capability.c b/security/capability.c
index 1728d4e..6e4fc77 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -12,6 +12,26 @@
#include <linux/security.h>
+static int cap_binder_set_context_mgr(struct task_struct *mgr)
+{
+ return 0;
+}
+
+static int cap_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+ return 0;
+}
+
+static int cap_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+ return 0;
+}
+
+static int cap_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+ return 0;
+}
+
static int cap_syslog(int type)
{
return 0;
@@ -903,6 +923,10 @@
void __init security_fixup_ops(struct security_operations *ops)
{
+ set_to_cap_if_null(ops, binder_set_context_mgr);
+ set_to_cap_if_null(ops, binder_transaction);
+ set_to_cap_if_null(ops, binder_transfer_binder);
+ set_to_cap_if_null(ops, binder_transfer_file);
set_to_cap_if_null(ops, ptrace_access_check);
set_to_cap_if_null(ops, ptrace_traceme);
set_to_cap_if_null(ops, capget);
diff --git a/security/commoncap.c b/security/commoncap.c
index 4fd7bf2..f2ad12e 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -31,6 +31,10 @@
#include <linux/binfmts.h>
#include <linux/personality.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+#endif
+
/*
* If a non-root user executes a setuid-root binary in
* !secure(SECURE_NOROOT) mode, then we raise capabilities.
@@ -78,6 +82,13 @@
{
struct user_namespace *ns = targ_ns;
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+ if (cap == CAP_NET_RAW && in_egroup_p(AID_NET_RAW))
+ return 0;
+ if (cap == CAP_NET_ADMIN && in_egroup_p(AID_NET_ADMIN))
+ return 0;
+#endif
+
/* See if cred has the capability in the target user namespace
* by examining the target user namespace and all of the target
* user namespace's parents.
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 8d8d97d..8f6b8e8 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -245,6 +245,21 @@
}
break;
}
+ case LSM_AUDIT_DATA_IOCTL_OP: {
+ struct inode *inode;
+
+ audit_log_d_path(ab, " path=", &a->u.op->path);
+
+ inode = a->u.op->path.dentry->d_inode;
+ if (inode) {
+ audit_log_format(ab, " dev=");
+ audit_log_untrustedstring(ab, inode->i_sb->s_id);
+ audit_log_format(ab, " ino=%lu", inode->i_ino);
+ }
+
+ audit_log_format(ab, " ioctlcmd=%hx", a->u.op->cmd);
+ break;
+ }
case LSM_AUDIT_DATA_DENTRY: {
struct inode *inode;
diff --git a/security/security.c b/security/security.c
index a3dce87..d6ab2d2 100644
--- a/security/security.c
+++ b/security/security.c
@@ -134,6 +134,26 @@
/* Security operations */
+int security_binder_set_context_mgr(struct task_struct *mgr)
+{
+ return security_ops->binder_set_context_mgr(mgr);
+}
+
+int security_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+ return security_ops->binder_transaction(from, to);
+}
+
+int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+ return security_ops->binder_transfer_binder(from, to);
+}
+
+int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+ return security_ops->binder_transfer_file(from, to, file);
+}
+
int security_ptrace_access_check(struct task_struct *child, unsigned int mode)
{
#ifdef CONFIG_SECURITY_YAMA_STACKED
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index dad36a6..386aafb 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -22,6 +22,7 @@
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/percpu.h>
+#include <linux/list.h>
#include <net/sock.h>
#include <linux/un.h>
#include <net/af_unix.h>
@@ -48,6 +49,7 @@
u32 tsid;
u16 tclass;
struct av_decision avd;
+ struct avc_xperms_node *xp_node;
};
struct avc_node {
@@ -56,6 +58,16 @@
struct rcu_head rhead;
};
+struct avc_xperms_decision_node {
+ struct extended_perms_decision xpd;
+ struct list_head xpd_list; /* list of extended_perms_decision */
+};
+
+struct avc_xperms_node {
+ struct extended_perms xp;
+ struct list_head xpd_head; /* list head of extended_perms_decision */
+};
+
struct avc_cache {
struct hlist_head slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */
spinlock_t slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */
@@ -80,6 +92,9 @@
static struct avc_cache avc_cache;
static struct avc_callback_node *avc_callbacks;
static struct kmem_cache *avc_node_cachep;
+static struct kmem_cache *avc_xperms_data_cachep;
+static struct kmem_cache *avc_xperms_decision_cachep;
+static struct kmem_cache *avc_xperms_cachep;
static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass)
{
@@ -170,7 +185,17 @@
atomic_set(&avc_cache.lru_hint, 0);
avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node),
- 0, SLAB_PANIC, NULL);
+ 0, SLAB_PANIC, NULL);
+ avc_xperms_cachep = kmem_cache_create("avc_xperms_node",
+ sizeof(struct avc_xperms_node),
+ 0, SLAB_PANIC, NULL);
+ avc_xperms_decision_cachep = kmem_cache_create(
+ "avc_xperms_decision_node",
+ sizeof(struct avc_xperms_decision_node),
+ 0, SLAB_PANIC, NULL);
+ avc_xperms_data_cachep = kmem_cache_create("avc_xperms_data",
+ sizeof(struct extended_perms_data),
+ 0, SLAB_PANIC, NULL);
audit_log(current->audit_context, GFP_KERNEL, AUDIT_KERNEL, "AVC INITIALIZED\n");
}
@@ -205,9 +230,261 @@
slots_used, AVC_CACHE_SLOTS, max_chain_len);
}
+/*
+ * using a linked list for extended_perms_decision lookup because the list is
+ * always small. i.e. less than 5, typically 1
+ */
+static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver,
+ struct avc_xperms_node *xp_node)
+{
+ struct avc_xperms_decision_node *xpd_node;
+
+ list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) {
+ if (xpd_node->xpd.driver == driver)
+ return &xpd_node->xpd;
+ }
+ return NULL;
+}
+
+static inline unsigned int
+avc_xperms_has_perm(struct extended_perms_decision *xpd,
+ u8 perm, u8 which)
+{
+ unsigned int rc = 0;
+
+ if ((which == XPERMS_ALLOWED) &&
+ (xpd->used & XPERMS_ALLOWED))
+ rc = security_xperm_test(xpd->allowed->p, perm);
+ else if ((which == XPERMS_AUDITALLOW) &&
+ (xpd->used & XPERMS_AUDITALLOW))
+ rc = security_xperm_test(xpd->auditallow->p, perm);
+ else if ((which == XPERMS_DONTAUDIT) &&
+ (xpd->used & XPERMS_DONTAUDIT))
+ rc = security_xperm_test(xpd->dontaudit->p, perm);
+ return rc;
+}
+
+static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node,
+ u8 driver, u8 perm)
+{
+ struct extended_perms_decision *xpd;
+ security_xperm_set(xp_node->xp.drivers.p, driver);
+ xpd = avc_xperms_decision_lookup(driver, xp_node);
+ if (xpd && xpd->allowed)
+ security_xperm_set(xpd->allowed->p, perm);
+}
+
+static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node)
+{
+ struct extended_perms_decision *xpd;
+
+ xpd = &xpd_node->xpd;
+ if (xpd->allowed)
+ kmem_cache_free(avc_xperms_data_cachep, xpd->allowed);
+ if (xpd->auditallow)
+ kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow);
+ if (xpd->dontaudit)
+ kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit);
+ kmem_cache_free(avc_xperms_decision_cachep, xpd_node);
+}
+
+static void avc_xperms_free(struct avc_xperms_node *xp_node)
+{
+ struct avc_xperms_decision_node *xpd_node, *tmp;
+
+ if (!xp_node)
+ return;
+
+ list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) {
+ list_del(&xpd_node->xpd_list);
+ avc_xperms_decision_free(xpd_node);
+ }
+ kmem_cache_free(avc_xperms_cachep, xp_node);
+}
+
+static void avc_copy_xperms_decision(struct extended_perms_decision *dest,
+ struct extended_perms_decision *src)
+{
+ dest->driver = src->driver;
+ dest->used = src->used;
+ if (dest->used & XPERMS_ALLOWED)
+ memcpy(dest->allowed->p, src->allowed->p,
+ sizeof(src->allowed->p));
+ if (dest->used & XPERMS_AUDITALLOW)
+ memcpy(dest->auditallow->p, src->auditallow->p,
+ sizeof(src->auditallow->p));
+ if (dest->used & XPERMS_DONTAUDIT)
+ memcpy(dest->dontaudit->p, src->dontaudit->p,
+ sizeof(src->dontaudit->p));
+}
+
+/*
+ * similar to avc_copy_xperms_decision, but only copy decision
+ * information relevant to this perm
+ */
+static inline void avc_quick_copy_xperms_decision(u8 perm,
+ struct extended_perms_decision *dest,
+ struct extended_perms_decision *src)
+{
+ /*
+ * compute index of the u32 of the 256 bits (8 u32s) that contain this
+ * command permission
+ */
+ u8 i = perm >> 5;
+
+ dest->used = src->used;
+ if (dest->used & XPERMS_ALLOWED)
+ dest->allowed->p[i] = src->allowed->p[i];
+ if (dest->used & XPERMS_AUDITALLOW)
+ dest->auditallow->p[i] = src->auditallow->p[i];
+ if (dest->used & XPERMS_DONTAUDIT)
+ dest->dontaudit->p[i] = src->dontaudit->p[i];
+}
+
+static struct avc_xperms_decision_node
+ *avc_xperms_decision_alloc(u8 which)
+{
+ struct avc_xperms_decision_node *xpd_node;
+ struct extended_perms_decision *xpd;
+
+ xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep,
+ GFP_ATOMIC | __GFP_NOMEMALLOC);
+ if (!xpd_node)
+ return NULL;
+
+ xpd = &xpd_node->xpd;
+ if (which & XPERMS_ALLOWED) {
+ xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep,
+ GFP_ATOMIC | __GFP_NOMEMALLOC);
+ if (!xpd->allowed)
+ goto error;
+ }
+ if (which & XPERMS_AUDITALLOW) {
+ xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep,
+ GFP_ATOMIC | __GFP_NOMEMALLOC);
+ if (!xpd->auditallow)
+ goto error;
+ }
+ if (which & XPERMS_DONTAUDIT) {
+ xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep,
+ GFP_ATOMIC | __GFP_NOMEMALLOC);
+ if (!xpd->dontaudit)
+ goto error;
+ }
+ return xpd_node;
+error:
+ avc_xperms_decision_free(xpd_node);
+ return NULL;
+}
+
+static int avc_add_xperms_decision(struct avc_node *node,
+ struct extended_perms_decision *src)
+{
+ struct avc_xperms_decision_node *dest_xpd;
+
+ node->ae.xp_node->xp.len++;
+ dest_xpd = avc_xperms_decision_alloc(src->used);
+ if (!dest_xpd)
+ return -ENOMEM;
+ avc_copy_xperms_decision(&dest_xpd->xpd, src);
+ list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head);
+ return 0;
+}
+
+static struct avc_xperms_node *avc_xperms_alloc(void)
+{
+ struct avc_xperms_node *xp_node;
+
+ xp_node = kmem_cache_zalloc(avc_xperms_cachep,
+ GFP_ATOMIC|__GFP_NOMEMALLOC);
+ if (!xp_node)
+ return xp_node;
+ INIT_LIST_HEAD(&xp_node->xpd_head);
+ return xp_node;
+}
+
+static int avc_xperms_populate(struct avc_node *node,
+ struct avc_xperms_node *src)
+{
+ struct avc_xperms_node *dest;
+ struct avc_xperms_decision_node *dest_xpd;
+ struct avc_xperms_decision_node *src_xpd;
+
+ if (src->xp.len == 0)
+ return 0;
+ dest = avc_xperms_alloc();
+ if (!dest)
+ return -ENOMEM;
+
+ memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p));
+ dest->xp.len = src->xp.len;
+
+ /* for each source xpd allocate a destination xpd and copy */
+ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) {
+ dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used);
+ if (!dest_xpd)
+ goto error;
+ avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd);
+ list_add(&dest_xpd->xpd_list, &dest->xpd_head);
+ }
+ node->ae.xp_node = dest;
+ return 0;
+error:
+ avc_xperms_free(dest);
+ return -ENOMEM;
+
+}
+
+static inline u32 avc_xperms_audit_required(u32 requested,
+ struct av_decision *avd,
+ struct extended_perms_decision *xpd,
+ u8 perm,
+ int result,
+ u32 *deniedp)
+{
+ u32 denied, audited;
+
+ denied = requested & ~avd->allowed;
+ if (unlikely(denied)) {
+ audited = denied & avd->auditdeny;
+ if (audited && xpd) {
+ if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT))
+ audited &= ~requested;
+ }
+ } else if (result) {
+ audited = denied = requested;
+ } else {
+ audited = requested & avd->auditallow;
+ if (audited && xpd) {
+ if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW))
+ audited &= ~requested;
+ }
+ }
+
+ *deniedp = denied;
+ return audited;
+}
+
+static inline int avc_xperms_audit(u32 ssid, u32 tsid, u16 tclass,
+ u32 requested, struct av_decision *avd,
+ struct extended_perms_decision *xpd,
+ u8 perm, int result,
+ struct common_audit_data *ad)
+{
+ u32 audited, denied;
+
+ audited = avc_xperms_audit_required(
+ requested, avd, xpd, perm, result, &denied);
+ if (likely(!audited))
+ return 0;
+ return slow_avc_audit(ssid, tsid, tclass, requested,
+ audited, denied, result, ad, 0);
+}
+
static void avc_node_free(struct rcu_head *rhead)
{
struct avc_node *node = container_of(rhead, struct avc_node, rhead);
+ avc_xperms_free(node->ae.xp_node);
kmem_cache_free(avc_node_cachep, node);
avc_cache_stats_incr(frees);
}
@@ -221,6 +498,7 @@
static void avc_node_kill(struct avc_node *node)
{
+ avc_xperms_free(node->ae.xp_node);
kmem_cache_free(avc_node_cachep, node);
avc_cache_stats_incr(frees);
atomic_dec(&avc_cache.active_nodes);
@@ -367,6 +645,7 @@
* @tsid: target security identifier
* @tclass: target security class
* @avd: resulting av decision
+ * @xp_node: resulting extended permissions
*
* Insert an AVC entry for the SID pair
* (@ssid, @tsid) and class @tclass.
@@ -378,7 +657,9 @@
* the access vectors into a cache entry, returns
* avc_node inserted. Otherwise, this function returns NULL.
*/
-static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
+static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass,
+ struct av_decision *avd,
+ struct avc_xperms_node *xp_node)
{
struct avc_node *pos, *node = NULL;
int hvalue;
@@ -391,10 +672,15 @@
if (node) {
struct hlist_head *head;
spinlock_t *lock;
+ int rc = 0;
hvalue = avc_hash(ssid, tsid, tclass);
avc_node_populate(node, ssid, tsid, tclass, avd);
-
+ rc = avc_xperms_populate(node, xp_node);
+ if (rc) {
+ kmem_cache_free(avc_node_cachep, node);
+ return NULL;
+ }
head = &avc_cache.slots[hvalue];
lock = &avc_cache.slots_lock[hvalue];
@@ -444,11 +730,15 @@
avc_dump_query(ab, ad->selinux_audit_data->ssid,
ad->selinux_audit_data->tsid,
ad->selinux_audit_data->tclass);
+ if (ad->selinux_audit_data->denied) {
+ audit_log_format(ab, " permissive=%u",
+ ad->selinux_audit_data->result ? 0 : 1);
+ }
}
/* This is the slow part of avc audit with big stack footprint */
noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
- u32 requested, u32 audited, u32 denied,
+ u32 requested, u32 audited, u32 denied, int result,
struct common_audit_data *a,
unsigned flags)
{
@@ -477,6 +767,7 @@
sad.tsid = tsid;
sad.audited = audited;
sad.denied = denied;
+ sad.result = result;
a->selinux_audit_data = &sad;
@@ -523,14 +814,17 @@
* @perms : Permission mask bits
* @ssid,@tsid,@tclass : identifier of an AVC entry
* @seqno : sequence number when decision was made
+ * @xpd: extended_perms_decision to be added to the node
*
* if a valid AVC entry doesn't exist,this function returns -ENOENT.
* if kmalloc() called internal returns NULL, this function returns -ENOMEM.
* otherwise, this function updates the AVC entry. The original AVC-entry object
* will release later by RCU.
*/
-static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
- u32 seqno)
+static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid,
+ u32 tsid, u16 tclass, u32 seqno,
+ struct extended_perms_decision *xpd,
+ u32 flags)
{
int hvalue, rc = 0;
unsigned long flag;
@@ -574,9 +868,19 @@
avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);
+ if (orig->ae.xp_node) {
+ rc = avc_xperms_populate(node, orig->ae.xp_node);
+ if (rc) {
+ kmem_cache_free(avc_node_cachep, node);
+ goto out_unlock;
+ }
+ }
+
switch (event) {
case AVC_CALLBACK_GRANT:
node->ae.avd.allowed |= perms;
+ if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS))
+ avc_xperms_allow_perm(node->ae.xp_node, driver, xperm);
break;
case AVC_CALLBACK_TRY_REVOKE:
case AVC_CALLBACK_REVOKE:
@@ -594,6 +898,9 @@
case AVC_CALLBACK_AUDITDENY_DISABLE:
node->ae.avd.auditdeny &= ~perms;
break;
+ case AVC_CALLBACK_ADD_XPERMS:
+ avc_add_xperms_decision(node, xpd);
+ break;
}
avc_node_replace(node, orig);
out_unlock:
@@ -665,18 +972,20 @@
* results in a bigger stack frame.
*/
static noinline struct avc_node *avc_compute_av(u32 ssid, u32 tsid,
- u16 tclass, struct av_decision *avd)
+ u16 tclass, struct av_decision *avd,
+ struct avc_xperms_node *xp_node)
{
rcu_read_unlock();
- security_compute_av(ssid, tsid, tclass, avd);
+ INIT_LIST_HEAD(&xp_node->xpd_head);
+ security_compute_av(ssid, tsid, tclass, avd, &xp_node->xp);
rcu_read_lock();
- return avc_insert(ssid, tsid, tclass, avd);
+ return avc_insert(ssid, tsid, tclass, avd, xp_node);
}
static noinline int avc_denied(u32 ssid, u32 tsid,
- u16 tclass, u32 requested,
- unsigned flags,
- struct av_decision *avd)
+ u16 tclass, u32 requested,
+ u8 driver, u8 xperm, unsigned flags,
+ struct av_decision *avd)
{
if (flags & AVC_STRICT)
return -EACCES;
@@ -684,11 +993,91 @@
if (selinux_enforcing && !(avd->flags & AVD_FLAGS_PERMISSIVE))
return -EACCES;
- avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
- tsid, tclass, avd->seqno);
+ avc_update_node(AVC_CALLBACK_GRANT, requested, driver, xperm, ssid,
+ tsid, tclass, avd->seqno, NULL, flags);
return 0;
}
+/*
+ * The avc extended permissions logic adds an additional 256 bits of
+ * permissions to an avc node when extended permissions for that node are
+ * specified in the avtab. If the additional 256 permissions is not adequate,
+ * as-is the case with ioctls, then multiple may be chained together and the
+ * driver field is used to specify which set contains the permission.
+ */
+int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+ u8 driver, u8 xperm, struct common_audit_data *ad)
+{
+ struct avc_node *node;
+ struct av_decision avd;
+ u32 denied;
+ struct extended_perms_decision local_xpd;
+ struct extended_perms_decision *xpd = NULL;
+ struct extended_perms_data allowed;
+ struct extended_perms_data auditallow;
+ struct extended_perms_data dontaudit;
+ struct avc_xperms_node local_xp_node;
+ struct avc_xperms_node *xp_node;
+ int rc = 0, rc2;
+
+ xp_node = &local_xp_node;
+ BUG_ON(!requested);
+
+ rcu_read_lock();
+
+ node = avc_lookup(ssid, tsid, tclass);
+ if (unlikely(!node)) {
+ node = avc_compute_av(ssid, tsid, tclass, &avd, xp_node);
+ } else {
+ memcpy(&avd, &node->ae.avd, sizeof(avd));
+ xp_node = node->ae.xp_node;
+ }
+ /* if extended permissions are not defined, only consider av_decision */
+ if (!xp_node || !xp_node->xp.len)
+ goto decision;
+
+ local_xpd.allowed = &allowed;
+ local_xpd.auditallow = &auditallow;
+ local_xpd.dontaudit = &dontaudit;
+
+ xpd = avc_xperms_decision_lookup(driver, xp_node);
+ if (unlikely(!xpd)) {
+ /*
+ * Compute the extended_perms_decision only if the driver
+ * is flagged
+ */
+ if (!security_xperm_test(xp_node->xp.drivers.p, driver)) {
+ avd.allowed &= ~requested;
+ goto decision;
+ }
+ rcu_read_unlock();
+ security_compute_xperms_decision(ssid, tsid, tclass, driver,
+ &local_xpd);
+ rcu_read_lock();
+ avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver, xperm,
+ ssid, tsid, tclass, avd.seqno, &local_xpd, 0);
+ } else {
+ avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd);
+ }
+ xpd = &local_xpd;
+
+ if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED))
+ avd.allowed &= ~requested;
+
+decision:
+ denied = requested & ~(avd.allowed);
+ if (unlikely(denied))
+ rc = avc_denied(ssid, tsid, tclass, requested, driver, xperm,
+ AVC_EXTENDED_PERMS, &avd);
+
+ rcu_read_unlock();
+
+ rc2 = avc_xperms_audit(ssid, tsid, tclass, requested,
+ &avd, xpd, xperm, rc, ad);
+ if (rc2)
+ return rc2;
+ return rc;
+}
/**
* avc_has_perm_noaudit - Check permissions but perform no auditing.
@@ -716,6 +1105,7 @@
struct av_decision *avd)
{
struct avc_node *node;
+ struct avc_xperms_node xp_node;
int rc = 0;
u32 denied;
@@ -724,16 +1114,14 @@
rcu_read_lock();
node = avc_lookup(ssid, tsid, tclass);
- if (unlikely(!node)) {
- node = avc_compute_av(ssid, tsid, tclass, avd);
- } else {
+ if (unlikely(!node))
+ node = avc_compute_av(ssid, tsid, tclass, avd, &xp_node);
+ else
memcpy(avd, &node->ae.avd, sizeof(*avd));
- avd = &node->ae.avd;
- }
denied = requested & ~(avd->allowed);
if (unlikely(denied))
- rc = avc_denied(ssid, tsid, tclass, requested, flags, avd);
+ rc = avc_denied(ssid, tsid, tclass, requested, 0, 0, flags, avd);
rcu_read_unlock();
return rc;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index fdd6e4f..24c8c19 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -147,6 +147,17 @@
return (atomic_read(&selinux_secmark_refcount) > 0);
}
+static int selinux_netcache_avc_callback(u32 event)
+{
+ if (event == AVC_CALLBACK_RESET) {
+ sel_netif_flush();
+ sel_netnode_flush();
+ sel_netport_flush();
+ synchronize_net();
+ }
+ return 0;
+}
+
/*
* initialise the security for the init task
*/
@@ -419,8 +430,11 @@
sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
sbsec->flags &= ~SE_SBLABELSUPP;
- /* Special handling for sysfs. Is genfs but also has setxattr handler*/
- if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
+ /* Special handling. Is genfs but also has in-core setxattr handler*/
+ if (!strcmp(sb->s_type->name, "sysfs") ||
+ !strcmp(sb->s_type->name, "pstore") ||
+ !strcmp(sb->s_type->name, "debugfs") ||
+ !strcmp(sb->s_type->name, "rootfs"))
sbsec->flags |= SE_SBLABELSUPP;
/* Initialize the root inode. */
@@ -685,7 +699,12 @@
}
if (strcmp(sb->s_type->name, "proc") == 0)
- sbsec->flags |= SE_SBPROC;
+ sbsec->flags |= SE_SBPROC | SE_SBGENFS;
+
+ if (!strcmp(sb->s_type->name, "debugfs") ||
+ !strcmp(sb->s_type->name, "sysfs") ||
+ !strcmp(sb->s_type->name, "pstore"))
+ sbsec->flags |= SE_SBGENFS;
/* Determine the labeling behavior to use for this filesystem type. */
rc = security_fs_use((sbsec->flags & SE_SBPROC) ? "proc" : sb->s_type->name, &sbsec->behavior, &sbsec->sid);
@@ -1170,12 +1189,13 @@
return SECCLASS_SOCKET;
}
-#ifdef CONFIG_PROC_FS
-static int selinux_proc_get_sid(struct dentry *dentry,
- u16 tclass,
- u32 *sid)
+static int selinux_genfs_get_sid(struct dentry *dentry,
+ u16 tclass,
+ u16 flags,
+ u32 *sid)
{
int rc;
+ struct super_block *sb = dentry->d_inode->i_sb;
char *buffer, *path;
buffer = (char *)__get_free_page(GFP_KERNEL);
@@ -1186,26 +1206,20 @@
if (IS_ERR(path))
rc = PTR_ERR(path);
else {
- /* each process gets a /proc/PID/ entry. Strip off the
- * PID part to get a valid selinux labeling.
- * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
- while (path[1] >= '0' && path[1] <= '9') {
- path[1] = '/';
- path++;
+ if (flags & SE_SBPROC) {
+ /* each process gets a /proc/PID/ entry. Strip off the
+ * PID part to get a valid selinux labeling.
+ * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
+ while (path[1] >= '0' && path[1] <= '9') {
+ path[1] = '/';
+ path++;
+ }
}
- rc = security_genfs_sid("proc", path, tclass, sid);
+ rc = security_genfs_sid(sb->s_type->name, path, tclass, sid);
}
free_page((unsigned long)buffer);
return rc;
}
-#else
-static int selinux_proc_get_sid(struct dentry *dentry,
- u16 tclass,
- u32 *sid)
-{
- return -EINVAL;
-}
-#endif
/* The inode's security attributes must be initialized before first use. */
static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry)
@@ -1360,7 +1374,7 @@
/* Default to the fs superblock SID. */
isec->sid = sbsec->sid;
- if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
+ if ((sbsec->flags & SE_SBGENFS) && !S_ISLNK(inode->i_mode)) {
/* We must have a dentry to determine the label on
* procfs inodes */
if (opt_dentry)
@@ -1383,7 +1397,8 @@
if (!dentry)
goto out_unlock;
isec->sclass = inode_mode_to_security_class(inode->i_mode);
- rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+ rc = selinux_genfs_get_sid(dentry, isec->sclass,
+ sbsec->flags, &sid);
dput(dentry);
if (rc)
goto out_unlock;
@@ -1856,6 +1871,65 @@
/* Hook functions begin here. */
+static int selinux_binder_set_context_mgr(struct task_struct *mgr)
+{
+ u32 mysid = current_sid();
+ u32 mgrsid = task_sid(mgr);
+
+ return avc_has_perm(mysid, mgrsid, SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL);
+}
+
+static int selinux_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+ u32 mysid = current_sid();
+ u32 fromsid = task_sid(from);
+ u32 tosid = task_sid(to);
+ int rc;
+
+ if (mysid != fromsid) {
+ rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL);
+ if (rc)
+ return rc;
+ }
+
+ return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL);
+}
+
+static int selinux_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+ u32 fromsid = task_sid(from);
+ u32 tosid = task_sid(to);
+ return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__TRANSFER, NULL);
+}
+
+static int selinux_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+ u32 sid = task_sid(to);
+ struct file_security_struct *fsec = file->f_security;
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode_security_struct *isec = inode->i_security;
+ struct common_audit_data ad;
+ int rc;
+
+ ad.type = LSM_AUDIT_DATA_PATH;
+ ad.u.path = file->f_path;
+
+ if (sid != fsec->sid) {
+ rc = avc_has_perm(sid, fsec->sid,
+ SECCLASS_FD,
+ FD__USE,
+ &ad);
+ if (rc)
+ return rc;
+ }
+
+ if (unlikely(IS_PRIVATE(inode)))
+ return 0;
+
+ return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file),
+ &ad);
+}
+
static int selinux_ptrace_access_check(struct task_struct *child,
unsigned int mode)
{
@@ -2672,6 +2746,7 @@
static noinline int audit_inode_permission(struct inode *inode,
u32 perms, u32 audited, u32 denied,
+ int result,
unsigned flags)
{
struct common_audit_data ad;
@@ -2682,7 +2757,7 @@
ad.u.inode = inode;
rc = slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms,
- audited, denied, &ad, flags);
+ audited, denied, result, &ad, flags);
if (rc)
return rc;
return 0;
@@ -2724,7 +2799,7 @@
if (likely(!audited))
return rc;
- rc2 = audit_inode_permission(inode, perms, audited, denied, flags);
+ rc2 = audit_inode_permission(inode, perms, audited, denied, rc, flags);
if (rc2)
return rc2;
return rc;
@@ -2748,7 +2823,8 @@
ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET))
return dentry_has_perm(cred, dentry, FILE__SETATTR);
- if (selinux_policycap_openperm && (ia_valid & ATTR_SIZE))
+ if (selinux_policycap_openperm && (ia_valid & ATTR_SIZE)
+ && !(ia_valid & ATTR_FILE))
av |= FILE__OPEN;
return dentry_has_perm(cred, dentry, av);
@@ -3035,6 +3111,46 @@
file_free_security(file);
}
+/*
+ * Check whether a task has the ioctl permission and cmd
+ * operation to an inode.
+ */
+int ioctl_has_perm(const struct cred *cred, struct file *file,
+ u32 requested, u16 cmd)
+{
+ struct common_audit_data ad;
+ struct file_security_struct *fsec = file->f_security;
+ struct inode *inode = file_inode(file);
+ struct inode_security_struct *isec = inode->i_security;
+ struct lsm_ioctlop_audit ioctl;
+ u32 ssid = cred_sid(cred);
+ int rc;
+ u8 driver = cmd >> 8;
+ u8 xperm = cmd & 0xff;
+
+ ad.type = LSM_AUDIT_DATA_IOCTL_OP;
+ ad.u.op = &ioctl;
+ ad.u.op->cmd = cmd;
+ ad.u.op->path = file->f_path;
+
+ if (ssid != fsec->sid) {
+ rc = avc_has_perm(ssid, fsec->sid,
+ SECCLASS_FD,
+ FD__USE,
+ &ad);
+ if (rc)
+ goto out;
+ }
+
+ if (unlikely(IS_PRIVATE(inode)))
+ return 0;
+
+ rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass,
+ requested, driver, xperm, &ad);
+out:
+ return rc;
+}
+
static int selinux_file_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
@@ -3077,7 +3193,7 @@
* to the file's ioctl() function.
*/
default:
- error = file_has_perm(cred, file, FILE__IOCTL);
+ error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd);
}
return error;
}
@@ -3121,24 +3237,20 @@
static int selinux_mmap_addr(unsigned long addr)
{
- int rc = 0;
- u32 sid = current_sid();
-
- /*
- * notice that we are intentionally putting the SELinux check before
- * the secondary cap_file_mmap check. This is such a likely attempt
- * at bad behaviour/exploit that we always want to get the AVC, even
- * if DAC would have also denied the operation.
- */
- if (addr < CONFIG_LSM_MMAP_MIN_ADDR) {
- rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT,
- MEMPROTECT__MMAP_ZERO, NULL);
- if (rc)
- return rc;
- }
+ int rc;
/* do DAC check on address space usage */
- return cap_mmap_addr(addr);
+ rc = cap_mmap_addr(addr);
+ if (rc)
+ return rc;
+
+ if (addr < CONFIG_LSM_MMAP_MIN_ADDR) {
+ u32 sid = current_sid();
+ rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT,
+ MEMPROTECT__MMAP_ZERO, NULL);
+ }
+
+ return rc;
}
static int selinux_mmap_file(struct file *file, unsigned long reqprot,
@@ -3423,6 +3535,38 @@
SYSTEM__MODULE_REQUEST, &ad);
}
+static int selinux_kernel_module_from_file(struct file *file)
+{
+ struct common_audit_data ad;
+ struct inode_security_struct *isec;
+ struct file_security_struct *fsec;
+ struct inode *inode;
+ u32 sid = current_sid();
+ int rc;
+
+ /* init_module */
+ if (file == NULL)
+ return avc_has_perm(sid, sid, SECCLASS_SYSTEM,
+ SYSTEM__MODULE_LOAD, NULL);
+
+ /* finit_module */
+ ad.type = LSM_AUDIT_DATA_PATH;
+ ad.u.path = file->f_path;
+
+ inode = file_inode(file);
+ isec = inode->i_security;
+ fsec = file->f_security;
+
+ if (sid != fsec->sid) {
+ rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad);
+ if (rc)
+ return rc;
+ }
+
+ return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM,
+ SYSTEM__MODULE_LOAD, &ad);
+}
+
static int selinux_task_setpgid(struct task_struct *p, pid_t pgid)
{
return current_has_perm(p, PROCESS__SETPGID);
@@ -4153,15 +4297,15 @@
&ad);
}
-static int selinux_inet_sys_rcv_skb(int ifindex, char *addrp, u16 family,
- u32 peer_sid,
+static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex,
+ char *addrp, u16 family, u32 peer_sid,
struct common_audit_data *ad)
{
int err;
u32 if_sid;
u32 node_sid;
- err = sel_netif_sid(ifindex, &if_sid);
+ err = sel_netif_sid(ns, ifindex, &if_sid);
if (err)
return err;
err = avc_has_perm(peer_sid, if_sid,
@@ -4254,8 +4398,8 @@
err = selinux_skb_peerlbl_sid(skb, family, &peer_sid);
if (err)
return err;
- err = selinux_inet_sys_rcv_skb(skb->skb_iif, addrp, family,
- peer_sid, &ad);
+ err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif,
+ addrp, family, peer_sid, &ad);
if (err) {
selinux_netlbl_err(skb, err, 0);
return err;
@@ -4598,7 +4742,8 @@
#ifdef CONFIG_NETFILTER
-static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
+static unsigned int selinux_ip_forward(struct sk_buff *skb,
+ const struct net_device *indev,
u16 family)
{
int err;
@@ -4624,14 +4769,14 @@
ad.type = LSM_AUDIT_DATA_NET;
ad.u.net = &net;
- ad.u.net->netif = ifindex;
+ ad.u.net->netif = indev->ifindex;
ad.u.net->family = family;
if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0)
return NF_DROP;
if (peerlbl_active) {
- err = selinux_inet_sys_rcv_skb(ifindex, addrp, family,
- peer_sid, &ad);
+ err = selinux_inet_sys_rcv_skb(dev_net(indev), indev->ifindex,
+ addrp, family, peer_sid, &ad);
if (err) {
selinux_netlbl_err(skb, err, 1);
return NF_DROP;
@@ -4660,7 +4805,7 @@
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return selinux_ip_forward(skb, in->ifindex, PF_INET);
+ return selinux_ip_forward(skb, in, PF_INET);
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -4670,7 +4815,7 @@
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return selinux_ip_forward(skb, in->ifindex, PF_INET6);
+ return selinux_ip_forward(skb, in, PF_INET6);
}
#endif /* IPV6 */
@@ -4758,11 +4903,13 @@
return NF_ACCEPT;
}
-static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
+static unsigned int selinux_ip_postroute(struct sk_buff *skb,
+ const struct net_device *outdev,
u16 family)
{
u32 secmark_perm;
u32 peer_sid;
+ int ifindex = outdev->ifindex;
struct sock *sk;
struct common_audit_data ad;
struct lsm_network_audit net = {0,};
@@ -4875,7 +5022,7 @@
u32 if_sid;
u32 node_sid;
- if (sel_netif_sid(ifindex, &if_sid))
+ if (sel_netif_sid(dev_net(outdev), ifindex, &if_sid))
return NF_DROP;
if (avc_has_perm(peer_sid, if_sid,
SECCLASS_NETIF, NETIF__EGRESS, &ad))
@@ -4897,7 +5044,7 @@
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return selinux_ip_postroute(skb, out->ifindex, PF_INET);
+ return selinux_ip_postroute(skb, out, PF_INET);
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -4907,7 +5054,7 @@
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return selinux_ip_postroute(skb, out->ifindex, PF_INET6);
+ return selinux_ip_postroute(skb, out, PF_INET6);
}
#endif /* IPV6 */
@@ -5656,6 +5803,11 @@
static struct security_operations selinux_ops = {
.name = "selinux",
+ .binder_set_context_mgr = selinux_binder_set_context_mgr,
+ .binder_transaction = selinux_binder_transaction,
+ .binder_transfer_binder = selinux_binder_transfer_binder,
+ .binder_transfer_file = selinux_binder_transfer_file,
+
.ptrace_access_check = selinux_ptrace_access_check,
.ptrace_traceme = selinux_ptrace_traceme,
.capget = selinux_capget,
@@ -5736,6 +5888,7 @@
.kernel_act_as = selinux_kernel_act_as,
.kernel_create_files_as = selinux_kernel_create_files_as,
.kernel_module_request = selinux_kernel_module_request,
+ .kernel_module_from_file = selinux_kernel_module_from_file,
.task_setpgid = selinux_task_setpgid,
.task_getpgid = selinux_task_getpgid,
.task_getsid = selinux_task_getsid,
@@ -5882,6 +6035,9 @@
if (register_security(&selinux_ops))
panic("SELinux: Unable to register with kernel.\n");
+ if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET))
+ panic("SELinux: Unable to register AVC netcache callback\n");
+
if (selinux_enforcing)
printk(KERN_DEBUG "SELinux: Starting in enforcing mode\n");
else
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 92d0ab5..6d65f77 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -102,7 +102,7 @@
}
int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
- u32 requested, u32 audited, u32 denied,
+ u32 requested, u32 audited, u32 denied, int result,
struct common_audit_data *a,
unsigned flags);
@@ -137,11 +137,12 @@
if (likely(!audited))
return 0;
return slow_avc_audit(ssid, tsid, tclass,
- requested, audited, denied,
+ requested, audited, denied, result,
a, flags);
}
#define AVC_STRICT 1 /* Ignore permissive mode. */
+#define AVC_EXTENDED_PERMS 2 /* update extended permissions */
int avc_has_perm_noaudit(u32 ssid, u32 tsid,
u16 tclass, u32 requested,
unsigned flags,
@@ -159,6 +160,9 @@
return avc_has_perm_flags(ssid, tsid, tclass, requested, auditdata, 0);
}
+int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+ u8 driver, u8 perm, struct common_audit_data *ad);
+
u32 avc_policy_seqno(void);
#define AVC_CALLBACK_GRANT 1
@@ -169,6 +173,7 @@
#define AVC_CALLBACK_AUDITALLOW_DISABLE 32
#define AVC_CALLBACK_AUDITDENY_ENABLE 64
#define AVC_CALLBACK_AUDITDENY_DISABLE 128
+#define AVC_CALLBACK_ADD_XPERMS 256
int avc_add_callback(int (*callback)(u32 event), u32 events);
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 14d04e6..3e53322 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -32,7 +32,7 @@
"setsockcreate", NULL } },
{ "system",
{ "ipc_info", "syslog_read", "syslog_mod",
- "syslog_console", "module_request", NULL } },
+ "syslog_console", "module_request", "module_load", NULL } },
{ "capability",
{ "chown", "dac_override", "dac_read_search",
"fowner", "fsetid", "kill", "setgid", "setuid", "setpcap",
@@ -151,5 +151,6 @@
{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
{ "tun_socket",
{ COMMON_SOCK_PERMS, "attach_queue", NULL } },
+ { "binder", { "impersonate", "call", "set_context_mgr", "transfer", NULL } },
{ NULL }
};
diff --git a/security/selinux/include/netif.h b/security/selinux/include/netif.h
index 43d5072..c721454 100644
--- a/security/selinux/include/netif.h
+++ b/security/selinux/include/netif.h
@@ -17,7 +17,11 @@
#ifndef _SELINUX_NETIF_H_
#define _SELINUX_NETIF_H_
-int sel_netif_sid(int ifindex, u32 *sid);
+#include <net/net_namespace.h>
+
+void sel_netif_flush(void);
+
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid);
#endif /* _SELINUX_NETIF_H_ */
diff --git a/security/selinux/include/netnode.h b/security/selinux/include/netnode.h
index df7a5ed..937668d 100644
--- a/security/selinux/include/netnode.h
+++ b/security/selinux/include/netnode.h
@@ -27,6 +27,8 @@
#ifndef _SELINUX_NETNODE_H
#define _SELINUX_NETNODE_H
+void sel_netnode_flush(void);
+
int sel_netnode_sid(void *addr, u16 family, u32 *sid);
#endif
diff --git a/security/selinux/include/netport.h b/security/selinux/include/netport.h
index 4d965b8..d1ce896 100644
--- a/security/selinux/include/netport.h
+++ b/security/selinux/include/netport.h
@@ -26,6 +26,8 @@
#ifndef _SELINUX_NETPORT_H
#define _SELINUX_NETPORT_H
+void sel_netport_flush(void);
+
int sel_netport_sid(u8 protocol, u16 pnum, u32 *sid);
#endif
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 6fd9dd2..2a3be7a 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -24,6 +24,7 @@
#include <linux/binfmts.h>
#include <linux/in.h>
#include <linux/spinlock.h>
+#include <net/net_namespace.h>
#include "flask.h"
#include "avc.h"
@@ -78,6 +79,7 @@
};
struct netif_security_struct {
+ struct net *ns; /* network namespace */
int ifindex; /* device index */
u32 sid; /* SID for this interface */
};
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 6d38851..c290ec3 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -33,13 +33,15 @@
#define POLICYDB_VERSION_ROLETRANS 26
#define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS 27
#define POLICYDB_VERSION_DEFAULT_TYPE 28
+#define POLICYDB_VERSION_CONSTRAINT_NAMES 29
+#define POLICYDB_VERSION_XPERMS_IOCTL 30
/* Range of policy versions we understand*/
#define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE
#ifdef CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX
#define POLICYDB_VERSION_MAX CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX_VALUE
#else
-#define POLICYDB_VERSION_MAX POLICYDB_VERSION_DEFAULT_TYPE
+#define POLICYDB_VERSION_MAX POLICYDB_VERSION_XPERMS_IOCTL
#endif
/* Mask for just the mount related flags */
@@ -53,6 +55,7 @@
#define SE_SBINITIALIZED 0x10
#define SE_SBPROC 0x20
#define SE_SBLABELSUPP 0x40
+#define SE_SBGENFS 0x80
#define CONTEXT_STR "context="
#define FSCONTEXT_STR "fscontext="
@@ -102,11 +105,38 @@
u32 flags;
};
+#define XPERMS_ALLOWED 1
+#define XPERMS_AUDITALLOW 2
+#define XPERMS_DONTAUDIT 4
+
+#define security_xperm_set(perms, x) (perms[x >> 5] |= 1 << (x & 0x1f))
+#define security_xperm_test(perms, x) (1 & (perms[x >> 5] >> (x & 0x1f)))
+struct extended_perms_data {
+ u32 p[8];
+};
+
+struct extended_perms_decision {
+ u8 used;
+ u8 driver;
+ struct extended_perms_data *allowed;
+ struct extended_perms_data *auditallow;
+ struct extended_perms_data *dontaudit;
+};
+
+struct extended_perms {
+ u16 len; /* length associated decision chain */
+ struct extended_perms_data drivers; /* flag drivers that are used */
+};
+
/* definitions of av_decision.flags */
#define AVD_FLAGS_PERMISSIVE 0x0001
void security_compute_av(u32 ssid, u32 tsid,
- u16 tclass, struct av_decision *avd);
+ u16 tclass, struct av_decision *avd,
+ struct extended_perms *xperms);
+
+void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass,
+ u8 driver, struct extended_perms_decision *xpermd);
void security_compute_av_user(u32 ssid, u32 tsid,
u16 tclass, struct av_decision *avd);
diff --git a/security/selinux/netif.c b/security/selinux/netif.c
index 47a49d1..548651a 100644
--- a/security/selinux/netif.c
+++ b/security/selinux/netif.c
@@ -45,6 +45,7 @@
/**
* sel_netif_hashfn - Hashing function for the interface table
+ * @ns: the network namespace
* @ifindex: the network interface
*
* Description:
@@ -52,13 +53,14 @@
* bucket number for the given interface.
*
*/
-static inline u32 sel_netif_hashfn(int ifindex)
+static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex)
{
- return (ifindex & (SEL_NETIF_HASH_SIZE - 1));
+ return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1));
}
/**
* sel_netif_find - Search for an interface record
+ * @ns: the network namespace
* @ifindex: the network interface
*
* Description:
@@ -66,15 +68,15 @@
* If an entry can not be found in the table return NULL.
*
*/
-static inline struct sel_netif *sel_netif_find(int ifindex)
+static inline struct sel_netif *sel_netif_find(const struct net *ns,
+ int ifindex)
{
- int idx = sel_netif_hashfn(ifindex);
+ int idx = sel_netif_hashfn(ns, ifindex);
struct sel_netif *netif;
list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list)
- /* all of the devices should normally fit in the hash, so we
- * optimize for that case */
- if (likely(netif->nsec.ifindex == ifindex))
+ if (net_eq(netif->nsec.ns, ns) &&
+ netif->nsec.ifindex == ifindex)
return netif;
return NULL;
@@ -96,7 +98,7 @@
if (sel_netif_total >= SEL_NETIF_HASH_MAX)
return -ENOSPC;
- idx = sel_netif_hashfn(netif->nsec.ifindex);
+ idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex);
list_add_rcu(&netif->list, &sel_netif_hash[idx]);
sel_netif_total++;
@@ -120,6 +122,7 @@
/**
* sel_netif_sid_slow - Lookup the SID of a network interface using the policy
+ * @ns: the network namespace
* @ifindex: the network interface
* @sid: interface SID
*
@@ -130,7 +133,7 @@
* failure.
*
*/
-static int sel_netif_sid_slow(int ifindex, u32 *sid)
+static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid)
{
int ret;
struct sel_netif *netif;
@@ -140,7 +143,7 @@
/* NOTE: we always use init's network namespace since we don't
* currently support containers */
- dev = dev_get_by_index(&init_net, ifindex);
+ dev = dev_get_by_index(ns, ifindex);
if (unlikely(dev == NULL)) {
printk(KERN_WARNING
"SELinux: failure in sel_netif_sid_slow(),"
@@ -149,7 +152,7 @@
}
spin_lock_bh(&sel_netif_lock);
- netif = sel_netif_find(ifindex);
+ netif = sel_netif_find(ns, ifindex);
if (netif != NULL) {
*sid = netif->nsec.sid;
ret = 0;
@@ -163,6 +166,7 @@
ret = security_netif_sid(dev->name, &new->nsec.sid);
if (ret != 0)
goto out;
+ new->nsec.ns = ns;
new->nsec.ifindex = ifindex;
ret = sel_netif_insert(new);
if (ret != 0)
@@ -184,6 +188,7 @@
/**
* sel_netif_sid - Lookup the SID of a network interface
+ * @ns: the network namespace
* @ifindex: the network interface
* @sid: interface SID
*
@@ -195,12 +200,12 @@
* on failure.
*
*/
-int sel_netif_sid(int ifindex, u32 *sid)
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid)
{
struct sel_netif *netif;
rcu_read_lock();
- netif = sel_netif_find(ifindex);
+ netif = sel_netif_find(ns, ifindex);
if (likely(netif != NULL)) {
*sid = netif->nsec.sid;
rcu_read_unlock();
@@ -208,11 +213,12 @@
}
rcu_read_unlock();
- return sel_netif_sid_slow(ifindex, sid);
+ return sel_netif_sid_slow(ns, ifindex, sid);
}
/**
* sel_netif_kill - Remove an entry from the network interface table
+ * @ns: the network namespace
* @ifindex: the network interface
*
* Description:
@@ -220,13 +226,13 @@
* table if it exists.
*
*/
-static void sel_netif_kill(int ifindex)
+static void sel_netif_kill(const struct net *ns, int ifindex)
{
struct sel_netif *netif;
rcu_read_lock();
spin_lock_bh(&sel_netif_lock);
- netif = sel_netif_find(ifindex);
+ netif = sel_netif_find(ns, ifindex);
if (netif)
sel_netif_destroy(netif);
spin_unlock_bh(&sel_netif_lock);
@@ -240,7 +246,7 @@
* Remove all entries from the network interface table.
*
*/
-static void sel_netif_flush(void)
+void sel_netif_flush(void)
{
int idx;
struct sel_netif *netif;
@@ -252,25 +258,13 @@
spin_unlock_bh(&sel_netif_lock);
}
-static int sel_netif_avc_callback(u32 event)
-{
- if (event == AVC_CALLBACK_RESET) {
- sel_netif_flush();
- synchronize_net();
- }
- return 0;
-}
-
static int sel_netif_netdev_notifier_handler(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
- if (dev_net(dev) != &init_net)
- return NOTIFY_DONE;
-
if (event == NETDEV_DOWN)
- sel_netif_kill(dev->ifindex);
+ sel_netif_kill(dev_net(dev), dev->ifindex);
return NOTIFY_DONE;
}
@@ -291,10 +285,6 @@
register_netdevice_notifier(&sel_netif_netdev_notifier);
- err = avc_add_callback(sel_netif_avc_callback, AVC_CALLBACK_RESET);
- if (err)
- panic("avc_add_callback() failed, error %d\n", err);
-
return err;
}
diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index c5454c0..bb8de9d 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -281,7 +281,7 @@
* Remove all entries from the network address table.
*
*/
-static void sel_netnode_flush(void)
+void sel_netnode_flush(void)
{
unsigned int idx;
struct sel_netnode *node, *node_tmp;
@@ -298,15 +298,6 @@
spin_unlock_bh(&sel_netnode_lock);
}
-static int sel_netnode_avc_callback(u32 event)
-{
- if (event == AVC_CALLBACK_RESET) {
- sel_netnode_flush();
- synchronize_net();
- }
- return 0;
-}
-
static __init int sel_netnode_init(void)
{
int iter;
@@ -320,10 +311,6 @@
sel_netnode_hash[iter].size = 0;
}
- ret = avc_add_callback(sel_netnode_avc_callback, AVC_CALLBACK_RESET);
- if (ret != 0)
- panic("avc_add_callback() failed, error %d\n", ret);
-
return ret;
}
diff --git a/security/selinux/netport.c b/security/selinux/netport.c
index d353797..73ac678 100644
--- a/security/selinux/netport.c
+++ b/security/selinux/netport.c
@@ -217,7 +217,7 @@
* Remove all entries from the network address table.
*
*/
-static void sel_netport_flush(void)
+void sel_netport_flush(void)
{
unsigned int idx;
struct sel_netport *port, *port_tmp;
@@ -234,15 +234,6 @@
spin_unlock_bh(&sel_netport_lock);
}
-static int sel_netport_avc_callback(u32 event)
-{
- if (event == AVC_CALLBACK_RESET) {
- sel_netport_flush();
- synchronize_net();
- }
- return 0;
-}
-
static __init int sel_netport_init(void)
{
int iter;
@@ -256,10 +247,6 @@
sel_netport_hash[iter].size = 0;
}
- ret = avc_add_callback(sel_netport_avc_callback, AVC_CALLBACK_RESET);
- if (ret != 0)
- panic("avc_add_callback() failed, error %d\n", ret);
-
return ret;
}
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 855e464..dd28eb2 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -17,6 +17,7 @@
#include <linux/inet_diag.h>
#include <linux/xfrm.h>
#include <linux/audit.h>
+#include <linux/sock_diag.h>
#include "flask.h"
#include "av_permissions.h"
@@ -76,8 +77,10 @@
static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
{
- { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
- { DCCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+ { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+ { DCCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+ { SOCK_DIAG_BY_FAMILY, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+ { SOCK_DESTROY_BACKPORT, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
};
static struct nlmsg_perm nlmsg_xfrm_perms[] =
@@ -98,6 +101,13 @@
{ XFRM_MSG_FLUSHPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
{ XFRM_MSG_NEWAE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
{ XFRM_MSG_GETAE, NETLINK_XFRM_SOCKET__NLMSG_READ },
+ { XFRM_MSG_REPORT, NETLINK_XFRM_SOCKET__NLMSG_READ },
+ { XFRM_MSG_MIGRATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+ { XFRM_MSG_NEWSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+ { XFRM_MSG_GETSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+ { XFRM_MSG_NEWSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+ { XFRM_MSG_GETSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+ { XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ },
};
static struct nlmsg_perm nlmsg_audit_perms[] =
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index a3dd9fa..640c16b 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -24,6 +24,7 @@
#include "policydb.h"
static struct kmem_cache *avtab_node_cachep;
+static struct kmem_cache *avtab_xperms_cachep;
static inline int avtab_hash(struct avtab_key *keyp, u16 mask)
{
@@ -37,11 +38,24 @@
struct avtab_key *key, struct avtab_datum *datum)
{
struct avtab_node *newnode;
+ struct avtab_extended_perms *xperms;
newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
if (newnode == NULL)
return NULL;
newnode->key = *key;
- newnode->datum = *datum;
+
+ if (key->specified & AVTAB_XPERMS) {
+ xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL);
+ if (xperms == NULL) {
+ kmem_cache_free(avtab_node_cachep, newnode);
+ return NULL;
+ }
+ *xperms = *(datum->u.xperms);
+ newnode->datum.u.xperms = xperms;
+ } else {
+ newnode->datum.u.data = datum->u.data;
+ }
+
if (prev) {
newnode->next = prev->next;
prev->next = newnode;
@@ -70,8 +84,12 @@
if (key->source_type == cur->key.source_type &&
key->target_type == cur->key.target_type &&
key->target_class == cur->key.target_class &&
- (specified & cur->key.specified))
+ (specified & cur->key.specified)) {
+ /* extended perms may not be unique */
+ if (specified & AVTAB_XPERMS)
+ break;
return -EEXIST;
+ }
if (key->source_type < cur->key.source_type)
break;
if (key->source_type == cur->key.source_type &&
@@ -232,6 +250,9 @@
while (cur) {
temp = cur;
cur = cur->next;
+ if (temp->key.specified & AVTAB_XPERMS)
+ kmem_cache_free(avtab_xperms_cachep,
+ temp->datum.u.xperms);
kmem_cache_free(avtab_node_cachep, temp);
}
h->htable[i] = NULL;
@@ -314,13 +335,42 @@
chain2_len_sum);
}
+/*
+ * extended permissions compatibility. Make ToT Android kernels compatible
+ * with Android M releases
+ */
+#define AVTAB_OPTYPE_ALLOWED 0x1000
+#define AVTAB_OPTYPE_AUDITALLOW 0x2000
+#define AVTAB_OPTYPE_DONTAUDIT 0x4000
+#define AVTAB_OPTYPE (AVTAB_OPTYPE_ALLOWED | \
+ AVTAB_OPTYPE_AUDITALLOW | \
+ AVTAB_OPTYPE_DONTAUDIT)
+#define AVTAB_XPERMS_OPTYPE 4
+
+#define avtab_xperms_to_optype(x) (x << AVTAB_XPERMS_OPTYPE)
+#define avtab_optype_to_xperms(x) (x >> AVTAB_XPERMS_OPTYPE)
+
+static unsigned int avtab_android_m_compat;
+
+static void avtab_android_m_compat_set(void)
+{
+ if (!avtab_android_m_compat) {
+ pr_info("SELinux: Android master kernel running Android"
+ " M policy in compatibility mode.\n");
+ avtab_android_m_compat = 1;
+ }
+}
+
static uint16_t spec_order[] = {
AVTAB_ALLOWED,
AVTAB_AUDITDENY,
AVTAB_AUDITALLOW,
AVTAB_TRANSITION,
AVTAB_CHANGE,
- AVTAB_MEMBER
+ AVTAB_MEMBER,
+ AVTAB_XPERMS_ALLOWED,
+ AVTAB_XPERMS_AUDITALLOW,
+ AVTAB_XPERMS_DONTAUDIT
};
int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
@@ -330,10 +380,12 @@
{
__le16 buf16[4];
u16 enabled;
- __le32 buf32[7];
u32 items, items2, val, vers = pol->policyvers;
struct avtab_key key;
struct avtab_datum datum;
+ struct avtab_extended_perms xperms;
+ __le32 buf32[ARRAY_SIZE(xperms.perms.p)];
+ unsigned int android_m_compat_optype = 0;
int i, rc;
unsigned set;
@@ -390,11 +442,15 @@
printk(KERN_ERR "SELinux: avtab: entry has both access vectors and types\n");
return -EINVAL;
}
+ if (val & AVTAB_XPERMS) {
+ printk(KERN_ERR "SELinux: avtab: entry has extended permissions\n");
+ return -EINVAL;
+ }
for (i = 0; i < ARRAY_SIZE(spec_order); i++) {
if (val & spec_order[i]) {
key.specified = spec_order[i] | enabled;
- datum.data = le32_to_cpu(buf32[items++]);
+ datum.u.data = le32_to_cpu(buf32[items++]);
rc = insertf(a, &key, &datum, p);
if (rc)
return rc;
@@ -420,6 +476,13 @@
key.target_class = le16_to_cpu(buf16[items++]);
key.specified = le16_to_cpu(buf16[items++]);
+ if ((key.specified & AVTAB_OPTYPE) &&
+ (vers == POLICYDB_VERSION_XPERMS_IOCTL)) {
+ key.specified = avtab_optype_to_xperms(key.specified);
+ android_m_compat_optype = 1;
+ avtab_android_m_compat_set();
+ }
+
if (!policydb_type_isvalid(pol, key.source_type) ||
!policydb_type_isvalid(pol, key.target_type) ||
!policydb_class_isvalid(pol, key.target_class)) {
@@ -437,14 +500,54 @@
return -EINVAL;
}
- rc = next_entry(buf32, fp, sizeof(u32));
- if (rc) {
- printk(KERN_ERR "SELinux: avtab: truncated entry\n");
- return rc;
+ if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) &&
+ (key.specified & AVTAB_XPERMS)) {
+ printk(KERN_ERR "SELinux: avtab: policy version %u does not "
+ "support extended permissions rules and one "
+ "was specified\n", vers);
+ return -EINVAL;
+ } else if (key.specified & AVTAB_XPERMS) {
+ memset(&xperms, 0, sizeof(struct avtab_extended_perms));
+ rc = next_entry(&xperms.specified, fp, sizeof(u8));
+ if (rc) {
+ printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+ return rc;
+ }
+ if (avtab_android_m_compat ||
+ ((xperms.specified != AVTAB_XPERMS_IOCTLFUNCTION) &&
+ (xperms.specified != AVTAB_XPERMS_IOCTLDRIVER) &&
+ (vers == POLICYDB_VERSION_XPERMS_IOCTL))) {
+ xperms.driver = xperms.specified;
+ if (android_m_compat_optype)
+ xperms.specified = AVTAB_XPERMS_IOCTLDRIVER;
+ else
+ xperms.specified = AVTAB_XPERMS_IOCTLFUNCTION;
+ avtab_android_m_compat_set();
+ } else {
+ rc = next_entry(&xperms.driver, fp, sizeof(u8));
+ if (rc) {
+ printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+ return rc;
+ }
+ }
+ rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(xperms.perms.p));
+ if (rc) {
+ printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+ return rc;
+ }
+ for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++)
+ xperms.perms.p[i] = le32_to_cpu(buf32[i]);
+ datum.u.xperms = &xperms;
+ } else {
+ rc = next_entry(buf32, fp, sizeof(u32));
+ if (rc) {
+ printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+ return rc;
+ }
+ datum.u.data = le32_to_cpu(*buf32);
}
- datum.data = le32_to_cpu(*buf32);
if ((key.specified & AVTAB_TYPE) &&
- !policydb_type_isvalid(pol, datum.data)) {
+ !policydb_type_isvalid(pol, datum.u.data)) {
printk(KERN_ERR "SELinux: avtab: invalid type\n");
return -EINVAL;
}
@@ -504,18 +607,40 @@
int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
{
__le16 buf16[4];
- __le32 buf32[1];
+ __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)];
int rc;
+ unsigned int i;
buf16[0] = cpu_to_le16(cur->key.source_type);
buf16[1] = cpu_to_le16(cur->key.target_type);
buf16[2] = cpu_to_le16(cur->key.target_class);
- buf16[3] = cpu_to_le16(cur->key.specified);
+ if (avtab_android_m_compat && (cur->key.specified & AVTAB_XPERMS) &&
+ (cur->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER))
+ buf16[3] = cpu_to_le16(avtab_xperms_to_optype(cur->key.specified));
+ else
+ buf16[3] = cpu_to_le16(cur->key.specified);
rc = put_entry(buf16, sizeof(u16), 4, fp);
if (rc)
return rc;
- buf32[0] = cpu_to_le32(cur->datum.data);
- rc = put_entry(buf32, sizeof(u32), 1, fp);
+
+ if (cur->key.specified & AVTAB_XPERMS) {
+ if (avtab_android_m_compat == 0) {
+ rc = put_entry(&cur->datum.u.xperms->specified,
+ sizeof(u8), 1, fp);
+ if (rc)
+ return rc;
+ }
+ rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp);
+ if (rc)
+ return rc;
+ for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++)
+ buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]);
+ rc = put_entry(buf32, sizeof(u32),
+ ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp);
+ } else {
+ buf32[0] = cpu_to_le32(cur->datum.u.data);
+ rc = put_entry(buf32, sizeof(u32), 1, fp);
+ }
if (rc)
return rc;
return 0;
@@ -548,9 +673,13 @@
avtab_node_cachep = kmem_cache_create("avtab_node",
sizeof(struct avtab_node),
0, SLAB_PANIC, NULL);
+ avtab_xperms_cachep = kmem_cache_create("avtab_extended_perms",
+ sizeof(struct avtab_extended_perms),
+ 0, SLAB_PANIC, NULL);
}
void avtab_cache_destroy(void)
{
kmem_cache_destroy(avtab_node_cachep);
+ kmem_cache_destroy(avtab_xperms_cachep);
}
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index 63ce2f9..8133523 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -23,6 +23,8 @@
#ifndef _SS_AVTAB_H_
#define _SS_AVTAB_H_
+#include "security.h"
+
struct avtab_key {
u16 source_type; /* source type */
u16 target_type; /* target type */
@@ -35,13 +37,43 @@
#define AVTAB_MEMBER 0x0020
#define AVTAB_CHANGE 0x0040
#define AVTAB_TYPE (AVTAB_TRANSITION | AVTAB_MEMBER | AVTAB_CHANGE)
+/* extended permissions */
+#define AVTAB_XPERMS_ALLOWED 0x0100
+#define AVTAB_XPERMS_AUDITALLOW 0x0200
+#define AVTAB_XPERMS_DONTAUDIT 0x0400
+#define AVTAB_XPERMS (AVTAB_XPERMS_ALLOWED | \
+ AVTAB_XPERMS_AUDITALLOW | \
+ AVTAB_XPERMS_DONTAUDIT)
#define AVTAB_ENABLED_OLD 0x80000000 /* reserved for used in cond_avtab */
#define AVTAB_ENABLED 0x8000 /* reserved for used in cond_avtab */
u16 specified; /* what field is specified */
};
+/*
+ * For operations that require more than the 32 permissions provided by the avc
+ * extended permissions may be used to provide 256 bits of permissions.
+ */
+struct avtab_extended_perms {
+/* These are not flags. All 256 values may be used */
+#define AVTAB_XPERMS_IOCTLFUNCTION 0x01
+#define AVTAB_XPERMS_IOCTLDRIVER 0x02
+ /* extension of the avtab_key specified */
+ u8 specified; /* ioctl, netfilter, ... */
+ /*
+ * if 256 bits is not adequate as is often the case with ioctls, then
+ * multiple extended perms may be used and the driver field
+ * specifies which permissions are included.
+ */
+ u8 driver;
+ /* 256 bits of permissions */
+ struct extended_perms_data perms;
+};
+
struct avtab_datum {
- u32 data; /* access vector or type value */
+ union {
+ u32 data; /* access vector or type value */
+ struct avtab_extended_perms *xperms;
+ } u;
};
struct avtab_node {
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 377d148..ba7dd93 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -15,6 +15,7 @@
#include "security.h"
#include "conditional.h"
+#include "services.h"
/*
* cond_evaluate_expr evaluates a conditional expr
@@ -617,10 +618,28 @@
return 0;
}
+
+void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key,
+ struct extended_perms_decision *xpermd)
+{
+ struct avtab_node *node;
+
+ if (!ctab || !key || !xpermd)
+ return;
+
+ for (node = avtab_search_node(ctab, key); node;
+ node = avtab_search_node_next(node, key->specified)) {
+ if (node->key.specified & AVTAB_ENABLED)
+ services_compute_xperms_decision(xpermd, node);
+ }
+ return;
+
+}
/* Determine whether additional permissions are granted by the conditional
* av table, and if so, add them to the result
*/
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd)
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+ struct av_decision *avd, struct extended_perms *xperms)
{
struct avtab_node *node;
@@ -631,7 +650,7 @@
node = avtab_search_node_next(node, key->specified)) {
if ((u16)(AVTAB_ALLOWED|AVTAB_ENABLED) ==
(node->key.specified & (AVTAB_ALLOWED|AVTAB_ENABLED)))
- avd->allowed |= node->datum.data;
+ avd->allowed |= node->datum.u.data;
if ((u16)(AVTAB_AUDITDENY|AVTAB_ENABLED) ==
(node->key.specified & (AVTAB_AUDITDENY|AVTAB_ENABLED)))
/* Since a '0' in an auditdeny mask represents a
@@ -639,10 +658,13 @@
* the '&' operand to ensure that all '0's in the mask
* are retained (much unlike the allow and auditallow cases).
*/
- avd->auditdeny &= node->datum.data;
+ avd->auditdeny &= node->datum.u.data;
if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) ==
(node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED)))
- avd->auditallow |= node->datum.data;
+ avd->auditallow |= node->datum.u.data;
+ if (xperms && (node->key.specified & AVTAB_ENABLED) &&
+ (node->key.specified & AVTAB_XPERMS))
+ services_compute_xperms_drivers(xperms, node);
}
return;
}
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
index 4d1f874..ddb43e7 100644
--- a/security/selinux/ss/conditional.h
+++ b/security/selinux/ss/conditional.h
@@ -73,8 +73,10 @@
int cond_write_bool(void *key, void *datum, void *ptr);
int cond_write_list(struct policydb *p, struct cond_node *list, void *fp);
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd);
-
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+ struct av_decision *avd, struct extended_perms *xperms);
+void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key,
+ struct extended_perms_decision *xpermd);
int evaluate_cond_node(struct policydb *p, struct cond_node *node);
#endif /* _CONDITIONAL_H_ */
diff --git a/security/selinux/ss/constraint.h b/security/selinux/ss/constraint.h
index 149dda7..96fd947 100644
--- a/security/selinux/ss/constraint.h
+++ b/security/selinux/ss/constraint.h
@@ -48,6 +48,7 @@
u32 op; /* operator */
struct ebitmap names; /* names */
+ struct type_set *type_names;
struct constraint_expr *next; /* next expression */
};
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index bcdca73..ca2c6f4 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -143,6 +143,16 @@
.sym_num = SYM_NUM,
.ocon_num = OCON_NUM,
},
+ {
+ .version = POLICYDB_VERSION_CONSTRAINT_NAMES,
+ .sym_num = SYM_NUM,
+ .ocon_num = OCON_NUM,
+ },
+ {
+ .version = POLICYDB_VERSION_XPERMS_IOCTL,
+ .sym_num = SYM_NUM,
+ .ocon_num = OCON_NUM,
+ },
};
static struct policydb_compat_info *policydb_lookup_compat(int version)
@@ -613,6 +623,19 @@
return 0;
}
+static void constraint_expr_destroy(struct constraint_expr *expr)
+{
+ if (expr) {
+ ebitmap_destroy(&expr->names);
+ if (expr->type_names) {
+ ebitmap_destroy(&expr->type_names->types);
+ ebitmap_destroy(&expr->type_names->negset);
+ kfree(expr->type_names);
+ }
+ kfree(expr);
+ }
+}
+
static int cls_destroy(void *key, void *datum, void *p)
{
struct class_datum *cladatum;
@@ -628,10 +651,9 @@
while (constraint) {
e = constraint->expr;
while (e) {
- ebitmap_destroy(&e->names);
etmp = e;
e = e->next;
- kfree(etmp);
+ constraint_expr_destroy(etmp);
}
ctemp = constraint;
constraint = constraint->next;
@@ -642,16 +664,14 @@
while (constraint) {
e = constraint->expr;
while (e) {
- ebitmap_destroy(&e->names);
etmp = e;
e = e->next;
- kfree(etmp);
+ constraint_expr_destroy(etmp);
}
ctemp = constraint;
constraint = constraint->next;
kfree(ctemp);
}
-
kfree(cladatum->comkey);
}
kfree(datum);
@@ -1156,8 +1176,34 @@
return rc;
}
-static int read_cons_helper(struct constraint_node **nodep, int ncons,
- int allowxtarget, void *fp)
+static void type_set_init(struct type_set *t)
+{
+ ebitmap_init(&t->types);
+ ebitmap_init(&t->negset);
+}
+
+static int type_set_read(struct type_set *t, void *fp)
+{
+ __le32 buf[1];
+ int rc;
+
+ if (ebitmap_read(&t->types, fp))
+ return -EINVAL;
+ if (ebitmap_read(&t->negset, fp))
+ return -EINVAL;
+
+ rc = next_entry(buf, fp, sizeof(u32));
+ if (rc < 0)
+ return -EINVAL;
+ t->flags = le32_to_cpu(buf[0]);
+
+ return 0;
+}
+
+
+static int read_cons_helper(struct policydb *p,
+ struct constraint_node **nodep,
+ int ncons, int allowxtarget, void *fp)
{
struct constraint_node *c, *lc;
struct constraint_expr *e, *le;
@@ -1225,6 +1271,18 @@
rc = ebitmap_read(&e->names, fp);
if (rc)
return rc;
+ if (p->policyvers >=
+ POLICYDB_VERSION_CONSTRAINT_NAMES) {
+ e->type_names = kzalloc(sizeof
+ (*e->type_names),
+ GFP_KERNEL);
+ if (!e->type_names)
+ return -ENOMEM;
+ type_set_init(e->type_names);
+ rc = type_set_read(e->type_names, fp);
+ if (rc)
+ return rc;
+ }
break;
default:
return -EINVAL;
@@ -1301,7 +1359,7 @@
goto bad;
}
- rc = read_cons_helper(&cladatum->constraints, ncons, 0, fp);
+ rc = read_cons_helper(p, &cladatum->constraints, ncons, 0, fp);
if (rc)
goto bad;
@@ -1311,7 +1369,8 @@
if (rc)
goto bad;
ncons = le32_to_cpu(buf[0]);
- rc = read_cons_helper(&cladatum->validatetrans, ncons, 1, fp);
+ rc = read_cons_helper(p, &cladatum->validatetrans,
+ ncons, 1, fp);
if (rc)
goto bad;
}
@@ -2762,6 +2821,24 @@
return 0;
}
+static int type_set_write(struct type_set *t, void *fp)
+{
+ int rc;
+ __le32 buf[1];
+
+ if (ebitmap_write(&t->types, fp))
+ return -EINVAL;
+ if (ebitmap_write(&t->negset, fp))
+ return -EINVAL;
+
+ buf[0] = cpu_to_le32(t->flags);
+ rc = put_entry(buf, sizeof(u32), 1, fp);
+ if (rc)
+ return -EINVAL;
+
+ return 0;
+}
+
static int write_cons_helper(struct policydb *p, struct constraint_node *node,
void *fp)
{
@@ -2793,6 +2870,12 @@
rc = ebitmap_write(&e->names, fp);
if (rc)
return rc;
+ if (p->policyvers >=
+ POLICYDB_VERSION_CONSTRAINT_NAMES) {
+ rc = type_set_write(e->type_names, fp);
+ if (rc)
+ return rc;
+ }
break;
default:
break;
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
index da63747..725d594 100644
--- a/security/selinux/ss/policydb.h
+++ b/security/selinux/ss/policydb.h
@@ -154,6 +154,17 @@
struct cond_node;
/*
+ * type set preserves data needed to determine constraint info from
+ * policy source. This is not used by the kernel policy but allows
+ * utilities such as audit2allow to determine constraint denials.
+ */
+struct type_set {
+ struct ebitmap types;
+ struct ebitmap negset;
+ u32 flags;
+};
+
+/*
* The configuration data includes security contexts for
* initial SIDs, unlabeled file systems, TCP and UDP port numbers,
* network interfaces, and nodes. This structure stores the
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 18caa16..cf905cd 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -92,9 +92,10 @@
u32 *scontext_len);
static void context_struct_compute_av(struct context *scontext,
- struct context *tcontext,
- u16 tclass,
- struct av_decision *avd);
+ struct context *tcontext,
+ u16 tclass,
+ struct av_decision *avd,
+ struct extended_perms *xperms);
struct selinux_mapping {
u16 value; /* policy value */
@@ -564,7 +565,8 @@
context_struct_compute_av(&lo_scontext,
tcontext,
tclass,
- &lo_avd);
+ &lo_avd,
+ NULL);
if ((lo_avd.allowed & avd->allowed) == avd->allowed)
return; /* no masked permission */
masked = ~lo_avd.allowed & avd->allowed;
@@ -579,7 +581,8 @@
context_struct_compute_av(scontext,
&lo_tcontext,
tclass,
- &lo_avd);
+ &lo_avd,
+ NULL);
if ((lo_avd.allowed & avd->allowed) == avd->allowed)
return; /* no masked permission */
masked = ~lo_avd.allowed & avd->allowed;
@@ -595,7 +598,8 @@
context_struct_compute_av(&lo_scontext,
&lo_tcontext,
tclass,
- &lo_avd);
+ &lo_avd,
+ NULL);
if ((lo_avd.allowed & avd->allowed) == avd->allowed)
return; /* no masked permission */
masked = ~lo_avd.allowed & avd->allowed;
@@ -612,13 +616,39 @@
}
/*
- * Compute access vectors based on a context structure pair for
- * the permissions in a particular class.
+ * flag which drivers have permissions
+ * only looking for ioctl based extended permssions
+ */
+void services_compute_xperms_drivers(
+ struct extended_perms *xperms,
+ struct avtab_node *node)
+{
+ unsigned int i;
+
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) {
+ /* if one or more driver has all permissions allowed */
+ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++)
+ xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i];
+ } else if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) {
+ /* if allowing permissions within a driver */
+ security_xperm_set(xperms->drivers.p,
+ node->datum.u.xperms->driver);
+ }
+
+ /* If no ioctl commands are allowed, ignore auditallow and auditdeny */
+ if (node->key.specified & AVTAB_XPERMS_ALLOWED)
+ xperms->len = 1;
+}
+
+/*
+ * Compute access vectors and extended permissions based on a context
+ * structure pair for the permissions in a particular class.
*/
static void context_struct_compute_av(struct context *scontext,
- struct context *tcontext,
- u16 tclass,
- struct av_decision *avd)
+ struct context *tcontext,
+ u16 tclass,
+ struct av_decision *avd,
+ struct extended_perms *xperms)
{
struct constraint_node *constraint;
struct role_allow *ra;
@@ -632,6 +662,10 @@
avd->allowed = 0;
avd->auditallow = 0;
avd->auditdeny = 0xffffffff;
+ if (xperms) {
+ memset(&xperms->drivers, 0, sizeof(xperms->drivers));
+ xperms->len = 0;
+ }
if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
if (printk_ratelimit())
@@ -646,7 +680,7 @@
* this permission check, then use it.
*/
avkey.target_class = tclass;
- avkey.specified = AVTAB_AV;
+ avkey.specified = AVTAB_AV | AVTAB_XPERMS;
sattr = flex_array_get(policydb.type_attr_map_array, scontext->type - 1);
BUG_ON(!sattr);
tattr = flex_array_get(policydb.type_attr_map_array, tcontext->type - 1);
@@ -659,15 +693,18 @@
node;
node = avtab_search_node_next(node, avkey.specified)) {
if (node->key.specified == AVTAB_ALLOWED)
- avd->allowed |= node->datum.data;
+ avd->allowed |= node->datum.u.data;
else if (node->key.specified == AVTAB_AUDITALLOW)
- avd->auditallow |= node->datum.data;
+ avd->auditallow |= node->datum.u.data;
else if (node->key.specified == AVTAB_AUDITDENY)
- avd->auditdeny &= node->datum.data;
+ avd->auditdeny &= node->datum.u.data;
+ else if (xperms && (node->key.specified & AVTAB_XPERMS))
+ services_compute_xperms_drivers(xperms, node);
}
/* Check conditional av table for additional permissions */
- cond_compute_av(&policydb.te_cond_avtab, &avkey, avd);
+ cond_compute_av(&policydb.te_cond_avtab, &avkey,
+ avd, xperms);
}
}
@@ -898,6 +935,139 @@
avd->flags = 0;
}
+void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
+ struct avtab_node *node)
+{
+ unsigned int i;
+
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) {
+ if (xpermd->driver != node->datum.u.xperms->driver)
+ return;
+ } else if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) {
+ if (!security_xperm_test(node->datum.u.xperms->perms.p,
+ xpermd->driver))
+ return;
+ } else {
+ BUG();
+ }
+
+ if (node->key.specified == AVTAB_XPERMS_ALLOWED) {
+ xpermd->used |= XPERMS_ALLOWED;
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) {
+ memset(xpermd->allowed->p, 0xff,
+ sizeof(xpermd->allowed->p));
+ }
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) {
+ for (i = 0; i < ARRAY_SIZE(xpermd->allowed->p); i++)
+ xpermd->allowed->p[i] |=
+ node->datum.u.xperms->perms.p[i];
+ }
+ } else if (node->key.specified == AVTAB_XPERMS_AUDITALLOW) {
+ xpermd->used |= XPERMS_AUDITALLOW;
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) {
+ memset(xpermd->auditallow->p, 0xff,
+ sizeof(xpermd->auditallow->p));
+ }
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) {
+ for (i = 0; i < ARRAY_SIZE(xpermd->auditallow->p); i++)
+ xpermd->auditallow->p[i] |=
+ node->datum.u.xperms->perms.p[i];
+ }
+ } else if (node->key.specified == AVTAB_XPERMS_DONTAUDIT) {
+ xpermd->used |= XPERMS_DONTAUDIT;
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) {
+ memset(xpermd->dontaudit->p, 0xff,
+ sizeof(xpermd->dontaudit->p));
+ }
+ if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) {
+ for (i = 0; i < ARRAY_SIZE(xpermd->dontaudit->p); i++)
+ xpermd->dontaudit->p[i] |=
+ node->datum.u.xperms->perms.p[i];
+ }
+ } else {
+ BUG();
+ }
+}
+
+void security_compute_xperms_decision(u32 ssid,
+ u32 tsid,
+ u16 orig_tclass,
+ u8 driver,
+ struct extended_perms_decision *xpermd)
+{
+ u16 tclass;
+ struct context *scontext, *tcontext;
+ struct avtab_key avkey;
+ struct avtab_node *node;
+ struct ebitmap *sattr, *tattr;
+ struct ebitmap_node *snode, *tnode;
+ unsigned int i, j;
+
+ xpermd->driver = driver;
+ xpermd->used = 0;
+ memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p));
+ memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p));
+ memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p));
+
+ read_lock(&policy_rwlock);
+ if (!ss_initialized)
+ goto allow;
+
+ scontext = sidtab_search(&sidtab, ssid);
+ if (!scontext) {
+ printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n",
+ __func__, ssid);
+ goto out;
+ }
+
+ tcontext = sidtab_search(&sidtab, tsid);
+ if (!tcontext) {
+ printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n",
+ __func__, tsid);
+ goto out;
+ }
+
+ tclass = unmap_class(orig_tclass);
+ if (unlikely(orig_tclass && !tclass)) {
+ if (policydb.allow_unknown)
+ goto allow;
+ goto out;
+ }
+
+
+ if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
+ pr_warn_ratelimited("SELinux: Invalid class %hu\n", tclass);
+ goto out;
+ }
+
+ avkey.target_class = tclass;
+ avkey.specified = AVTAB_XPERMS;
+ sattr = flex_array_get(policydb.type_attr_map_array,
+ scontext->type - 1);
+ BUG_ON(!sattr);
+ tattr = flex_array_get(policydb.type_attr_map_array,
+ tcontext->type - 1);
+ BUG_ON(!tattr);
+ ebitmap_for_each_positive_bit(sattr, snode, i) {
+ ebitmap_for_each_positive_bit(tattr, tnode, j) {
+ avkey.source_type = i + 1;
+ avkey.target_type = j + 1;
+ for (node = avtab_search_node(&policydb.te_avtab, &avkey);
+ node;
+ node = avtab_search_node_next(node, avkey.specified))
+ services_compute_xperms_decision(xpermd, node);
+
+ cond_compute_xperms(&policydb.te_cond_avtab,
+ &avkey, xpermd);
+ }
+ }
+out:
+ read_unlock(&policy_rwlock);
+ return;
+allow:
+ memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p));
+ goto out;
+}
/**
* security_compute_av - Compute access vector decisions.
@@ -905,6 +1075,7 @@
* @tsid: target security identifier
* @tclass: target security class
* @avd: access vector decisions
+ * @xperms: extended permissions
*
* Compute a set of access vector decisions based on the
* SID pair (@ssid, @tsid) for the permissions in @tclass.
@@ -912,13 +1083,15 @@
void security_compute_av(u32 ssid,
u32 tsid,
u16 orig_tclass,
- struct av_decision *avd)
+ struct av_decision *avd,
+ struct extended_perms *xperms)
{
u16 tclass;
struct context *scontext = NULL, *tcontext = NULL;
read_lock(&policy_rwlock);
avd_init(avd);
+ xperms->len = 0;
if (!ss_initialized)
goto allow;
@@ -946,7 +1119,7 @@
goto allow;
goto out;
}
- context_struct_compute_av(scontext, tcontext, tclass, avd);
+ context_struct_compute_av(scontext, tcontext, tclass, avd, xperms);
map_decision(orig_tclass, avd, policydb.allow_unknown);
out:
read_unlock(&policy_rwlock);
@@ -992,7 +1165,7 @@
goto out;
}
- context_struct_compute_av(scontext, tcontext, tclass, avd);
+ context_struct_compute_av(scontext, tcontext, tclass, avd, NULL);
out:
read_unlock(&policy_rwlock);
return;
@@ -1512,7 +1685,7 @@
if (avdatum) {
/* Use the type from the type transition/member/change rule. */
- newcontext.type = avdatum->data;
+ newcontext.type = avdatum->u.data;
}
/* if we have a objname this is a file trans check so check those rules */
diff --git a/security/selinux/ss/services.h b/security/selinux/ss/services.h
index e8d907e..6abcd87 100644
--- a/security/selinux/ss/services.h
+++ b/security/selinux/ss/services.h
@@ -11,5 +11,11 @@
extern struct policydb policydb;
+void services_compute_xperms_drivers(struct extended_perms *xperms,
+ struct avtab_node *node);
+
+void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
+ struct avtab_node *node);
+
#endif /* _SS_SERVICES_H_ */
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 572f951..58366de 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -489,7 +489,7 @@
{
/* first let's check the buffer parameter's */
if (params->buffer.fragment_size == 0 ||
- params->buffer.fragments > SIZE_MAX / params->buffer.fragment_size)
+ params->buffer.fragments > INT_MAX / params->buffer.fragment_size)
return -EINVAL;
/* now codec parameters */
@@ -499,9 +499,6 @@
if (params->codec.ch_in == 0 || params->codec.ch_out == 0)
return -EINVAL;
- if (!(params->codec.sample_rate & SNDRV_PCM_RATE_8000_192000))
- return -EINVAL;
-
return 0;
}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d56bbea..a862361 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2103,9 +2103,13 @@
{
unsigned int ret;
- ret = codec->read(codec, reg);
- dev_dbg(codec->dev, "read %x => %x\n", reg, ret);
- trace_snd_soc_reg_read(codec, reg, ret);
+ if (codec->read) {
+ ret = codec->read(codec, reg);
+ dev_dbg(codec->dev, "read %x => %x\n", reg, ret);
+ trace_snd_soc_reg_read(codec, reg, ret);
+ }
+ else
+ ret = -EIO;
return ret;
}
@@ -2114,9 +2118,13 @@
unsigned int snd_soc_write(struct snd_soc_codec *codec,
unsigned int reg, unsigned int val)
{
- dev_dbg(codec->dev, "write %x = %x\n", reg, val);
- trace_snd_soc_reg_write(codec, reg, val);
- return codec->write(codec, reg, val);
+ if (codec->write) {
+ dev_dbg(codec->dev, "write %x = %x\n", reg, val);
+ trace_snd_soc_reg_write(codec, reg, val);
+ return codec->write(codec, reg, val);
+ }
+ else
+ return -EIO;
}
EXPORT_SYMBOL_GPL(snd_soc_write);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 63b6f8c..54494df 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1515,12 +1515,15 @@
case EPERM:
case EACCES:
return scnprintf(msg, size,
- "You may not have permission to collect %sstats.\n"
- "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
- " -1 - Not paranoid at all\n"
- " 0 - Disallow raw tracepoint access for unpriv\n"
- " 1 - Disallow cpu events for unpriv\n"
- " 2 - Disallow kernel profiling for unpriv",
+ "You may not have permission to collect %sstats.\n\n"
+ "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+ "which controls use of the performance events system by\n"
+ "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+ "The default value is 1:\n\n"
+ " -1: Allow use of (almost) all events by all users\n"
+ ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+ ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+ ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
target->system_wide ? "system-wide " : "");
case ENOENT:
return scnprintf(msg, size, "The %s event is not supported.",
