Merge branch 'android-3.18-zram' into android-3.18
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 a6148ea..2e69e83 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -141,3 +141,28 @@
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/blockdev/zram.txt b/Documentation/blockdev/zram.txt
index 7fcf9c6..48a183e 100644
--- a/Documentation/blockdev/zram.txt
+++ b/Documentation/blockdev/zram.txt
@@ -98,20 +98,79 @@
mount /dev/zram1 /tmp
7) Stats:
- Per-device statistics are exported as various nodes under
- /sys/block/zram<id>/
- disksize
- num_reads
- num_writes
- failed_reads
- failed_writes
- invalid_io
- notify_free
- zero_pages
- orig_data_size
- compr_data_size
- mem_used_total
- mem_used_max
+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
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 c721042..c236e00 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10475,6 +10475,7 @@
S: Maintained
F: mm/zsmalloc.c
F: include/linux/zsmalloc.h
+F: Documentation/vm/zsmalloc.txt
ZSWAP COMPRESSED SWAP CACHING
M: Seth Jennings <sjennings@variantweb.net>
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index f1ff39a..54d946a 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -325,12 +325,14 @@
* 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.
+ * 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)
@@ -342,12 +344,12 @@
comp->backend = backend;
if (max_strm > 1)
- zcomp_strm_multi_create(comp, max_strm);
+ error = zcomp_strm_multi_create(comp, max_strm);
else
- zcomp_strm_single_create(comp);
- if (!comp->stream) {
+ error = zcomp_strm_single_create(comp);
+ if (error) {
kfree(comp);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(error);
}
return comp;
}
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 3920ee4..d1832d78 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -43,20 +43,30 @@
/* 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, \
+static ssize_t 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 DEVICE_ATTR_RO(name);
-static inline int init_done(struct zram *zram)
+static inline bool init_done(struct zram *zram)
{
- return zram->meta != NULL;
+ return zram->disksize;
}
static inline struct zram *dev_to_zram(struct device *dev)
@@ -64,6 +74,27 @@
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)
{
@@ -90,6 +121,7 @@
{
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);
}
@@ -100,6 +132,7 @@
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;
@@ -129,6 +162,7 @@
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);
@@ -160,6 +194,7 @@
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);
@@ -287,19 +322,18 @@
/*
* Check if request is within bounds and aligned on zram logical blocks.
*/
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
+static inline int valid_io_request(struct zram *zram,
+ sector_t start, unsigned int size)
{
- u64 start, end, bound;
+ u64 end, bound;
/* unaligned request */
- if (unlikely(bio->bi_iter.bi_sector &
- (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+ if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
return 0;
- if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+ if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
return 0;
- start = bio->bi_iter.bi_sector;
- end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+ end = start + (size >> SECTOR_SHIFT);
bound = zram->disksize >> SECTOR_SHIFT;
/* out of range range */
if (unlikely(start >= bound || end > bound || start > end))
@@ -309,42 +343,67 @@
return 1;
}
-static void zram_meta_free(struct zram_meta *meta)
+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(u64 disksize)
+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)
- goto out;
+ 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 free_meta;
+ goto out_error;
}
- meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+ 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 free_table;
+ goto out_error;
}
return meta;
-free_table:
+out_error:
vfree(meta->table);
-free_meta:
kfree(meta);
- meta = NULL;
-out:
- return 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)
@@ -453,7 +512,7 @@
}
static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset, struct bio *bio)
+ u32 index, int offset)
{
int ret;
struct page *page;
@@ -505,7 +564,7 @@
static inline void update_used_max(struct zram *zram,
const unsigned long pages)
{
- int old_max, cur_max;
+ unsigned long old_max, cur_max;
old_max = atomic_long_read(&zram->stats.max_used_pages);
@@ -645,14 +704,13 @@
}
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, struct bio *bio)
+ int offset, int rw)
{
int ret;
- int rw = bio_data_dir(bio);
if (rw == READ) {
atomic64_inc(&zram->stats.num_reads);
- ret = zram_bvec_read(zram, bvec, index, offset, bio);
+ ret = zram_bvec_read(zram, bvec, index, offset);
} else {
atomic64_inc(&zram->stats.num_writes);
ret = zram_bvec_write(zram, bvec, index, offset);
@@ -707,10 +765,11 @@
}
}
-static void zram_reset_device(struct zram *zram, bool reset_capacity)
+static void zram_reset_device(struct zram *zram)
{
- size_t index;
struct zram_meta *meta;
+ struct zcomp *comp;
+ u64 disksize;
down_write(&zram->init_lock);
@@ -722,36 +781,32 @@
}
meta = zram->meta;
- /* 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;
+ 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);
- zs_free(meta->mem_pool, handle);
- }
-
- zcomp_destroy(zram->comp);
- zram->max_comp_streams = 1;
-
- zram_meta_free(zram->meta);
- zram->meta = NULL;
/* Reset stats */
memset(&zram->stats, 0, sizeof(zram->stats));
-
zram->disksize = 0;
- if (reset_capacity)
- set_capacity(zram->disk, 0);
+ zram->max_comp_streams = 1;
+
+ set_capacity(zram->disk, 0);
+ part_stat_set_all(&zram->disk->part0, 0);
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.
- */
- if (reset_capacity)
- revalidate_disk(zram->disk);
+ /* 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,
@@ -768,7 +823,7 @@
return -EINVAL;
disksize = PAGE_ALIGN(disksize);
- meta = zram_meta_alloc(disksize);
+ meta = zram_meta_alloc(zram->disk->first_minor, disksize);
if (!meta)
return -ENOMEM;
@@ -787,6 +842,8 @@
goto out_destroy_comp;
}
+ init_waitqueue_head(&zram->io_done);
+ atomic_set(&zram->refcount, 1);
zram->meta = meta;
zram->comp = comp;
zram->disksize = disksize;
@@ -806,7 +863,7 @@
up_write(&zram->init_lock);
zcomp_destroy(comp);
out_free_meta:
- zram_meta_free(meta);
+ zram_meta_free(meta, disksize);
return err;
}
@@ -824,8 +881,9 @@
if (!bdev)
return -ENOMEM;
+ mutex_lock(&bdev->bd_mutex);
/* Do not reset an active device! */
- if (bdev->bd_holders) {
+ if (bdev->bd_openers) {
ret = -EBUSY;
goto out;
}
@@ -841,19 +899,23 @@
/* 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);
- zram_reset_device(zram, true);
return len;
out:
+ mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
return ret;
}
static void __zram_make_request(struct zram *zram, struct bio *bio)
{
- int offset;
+ int offset, rw;
u32 index;
struct bio_vec bvec;
struct bvec_iter iter;
@@ -868,6 +930,7 @@
return;
}
+ rw = bio_data_dir(bio);
bio_for_each_segment(bvec, bio, iter) {
int max_transfer_size = PAGE_SIZE - offset;
@@ -882,15 +945,15 @@
bv.bv_len = max_transfer_size;
bv.bv_offset = bvec.bv_offset;
- if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
+ 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, bio) < 0)
+ if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
goto out;
} else
- if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0)
+ if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0)
goto out;
update_position(&index, &offset, &bvec);
@@ -911,22 +974,21 @@
{
struct zram *zram = queue->queuedata;
- down_read(&zram->init_lock);
- if (unlikely(!init_done(zram)))
+ if (unlikely(!zram_meta_get(zram)))
goto error;
- if (!valid_io_request(zram, bio)) {
+ if (!valid_io_request(zram, bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size)) {
atomic64_inc(&zram->stats.invalid_io);
- goto error;
+ goto put_zram;
}
__zram_make_request(zram, bio);
- up_read(&zram->init_lock);
-
+ zram_meta_put(zram);
return;
-
+put_zram:
+ zram_meta_put(zram);
error:
- up_read(&zram->init_lock);
bio_io_error(bio);
}
@@ -945,26 +1007,114 @@
atomic64_inc(&zram->stats.notify_free);
}
+static int zram_rw_page(struct block_device *bdev, sector_t sector,
+ struct page *page, int rw)
+{
+ int offset, err = -EIO;
+ u32 index;
+ struct zram *zram;
+ struct bio_vec bv;
+
+ zram = bdev->bd_disk->private_data;
+ if (unlikely(!zram_meta_get(zram)))
+ goto out;
+
+ if (!valid_io_request(zram, sector, PAGE_SIZE)) {
+ atomic64_inc(&zram->stats.invalid_io);
+ err = -EINVAL;
+ goto put_zram;
+ }
+
+ index = sector >> SECTORS_PER_PAGE_SHIFT;
+ offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+
+ bv.bv_page = page;
+ bv.bv_len = PAGE_SIZE;
+ bv.bv_offset = 0;
+
+ err = zram_bvec_rw(zram, &bv, index, offset, rw);
+put_zram:
+ zram_meta_put(zram);
+out:
+ /*
+ * If I/O fails, just return error(ie, non-zero) without
+ * calling page_endio.
+ * It causes resubmit the I/O with bio request by upper functions
+ * of rw_page(e.g., swap_readpage, __swap_writepage) and
+ * bio->bi_end_io does things to handle the error
+ * (e.g., SetPageError, set_page_dirty and extra works).
+ */
+ if (err == 0)
+ page_endio(page, rw, 0);
+ return err;
+}
+
static const struct block_device_operations zram_devops = {
.swap_slot_free_notify = zram_slot_free_notify,
+ .rw_page = zram_rw_page,
.owner = THIS_MODULE
};
-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 DEVICE_ATTR_WO(compact);
+static DEVICE_ATTR_RW(disksize);
+static DEVICE_ATTR_RO(initstate);
+static DEVICE_ATTR_WO(reset);
+static DEVICE_ATTR_RO(orig_data_size);
+static DEVICE_ATTR_RO(mem_used_total);
+static DEVICE_ATTR_RW(mem_limit);
+static DEVICE_ATTR_RW(mem_used_max);
+static DEVICE_ATTR_RW(max_comp_streams);
+static DEVICE_ATTR_RW(comp_algorithm);
+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_RO(io_stat);
+static DEVICE_ATTR_RO(mm_stat);
ZRAM_ATTR_RO(num_reads);
ZRAM_ATTR_RO(num_writes);
ZRAM_ATTR_RO(failed_reads);
@@ -982,6 +1132,7 @@
&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,
@@ -992,6 +1143,8 @@
&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,
};
@@ -1001,32 +1154,34 @@
static int create_device(struct zram *zram, int device_id)
{
+ struct request_queue *queue;
int ret = -ENOMEM;
init_rwsem(&zram->init_lock);
- zram->queue = blk_alloc_queue(GFP_KERNEL);
- if (!zram->queue) {
+ 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(zram->queue, zram_make_request);
- zram->queue->queuedata = zram;
+ 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 = zram->queue;
+ zram->disk->queue = queue;
+ zram->disk->queue->queuedata = zram;
zram->disk->private_data = zram;
snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
@@ -1077,20 +1232,35 @@
del_gendisk(zram->disk);
put_disk(zram->disk);
out_free_queue:
- blk_cleanup_queue(zram->queue);
+ blk_cleanup_queue(queue);
out:
return ret;
}
-static void destroy_device(struct zram *zram)
+static void destroy_devices(unsigned int nr)
{
- sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
+ struct zram *zram;
+ unsigned int i;
- del_gendisk(zram->disk);
- put_disk(zram->disk);
+ 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);
- blk_cleanup_queue(zram->queue);
+ 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)
@@ -1100,64 +1270,39 @@
if (num_devices > max_num_devices) {
pr_warn("Invalid value for num_devices: %u\n",
num_devices);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_warn("Unable to get major number\n");
- ret = -EBUSY;
- goto out;
+ return -EBUSY;
}
/* 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;
+ 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 free_devices;
+ goto out_error;
}
- pr_info("Created %u device(s) ...\n", num_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:
+out_error:
+ destroy_devices(dev_id);
return ret;
}
static void __exit zram_exit(void)
{
- int i;
- struct zram *zram;
-
- for (i = 0; i < num_devices; i++) {
- zram = &zram_devices[i];
-
- destroy_device(zram);
- /*
- * Shouldn't access zram->disk after destroy_device
- * because destroy_device already released zram->disk.
- */
- zram_reset_device(zram, false);
- }
-
- unregister_blkdev(zram_major, "zram");
-
- kfree(zram_devices);
- pr_debug("Cleanup done!\n");
+ destroy_devices(num_devices);
}
module_init(zram_init);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index c6ee271..570c598 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -66,8 +66,8 @@
/* Flags for zram pages (table[page_no].value) */
enum zram_pageflags {
/* Page consists entirely of zeros */
- ZRAM_ZERO = ZRAM_FLAG_SHIFT + 1,
- ZRAM_ACCESS, /* page in now accessed */
+ ZRAM_ZERO = ZRAM_FLAG_SHIFT,
+ ZRAM_ACCESS, /* page is now accessed */
__NR_ZRAM_PAGEFLAGS,
};
@@ -84,6 +84,7 @@
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 */
@@ -100,24 +101,25 @@
struct zram {
struct zram_meta *meta;
- struct request_queue *queue;
- struct gendisk *disk;
struct zcomp *comp;
-
- /* Prevent concurrent execution of device init, reset and R/W request */
+ 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 */
- int max_comp_streams;
- struct zram_stats stats;
- /*
- * the number of pages zram can consume for storing compressed data
- */
- unsigned long limit_pages;
-
char compressor[10];
};
#endif
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index f14bd75..56529b3 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -36,7 +36,8 @@
ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
};
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+struct zpool *zpool_create_pool(char *type, char *name,
+ gfp_t gfp, struct zpool_ops *ops);
char *zpool_get_type(struct zpool *pool);
@@ -80,7 +81,7 @@
atomic_t refcount;
struct list_head list;
- void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+ 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,
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 05c2147..1338190 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -36,7 +36,7 @@
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);
@@ -47,5 +47,6 @@
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
unsigned long zs_get_total_pages(struct zs_pool *pool);
+unsigned long zs_compact(struct zs_pool *pool);
#endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 1d1ae6b..95c5728 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -601,6 +601,16 @@
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.
+
config GENERIC_EARLY_IOREMAP
bool
diff --git a/mm/zbud.c b/mm/zbud.c
index ecf1dbe..2010b6e 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -130,7 +130,8 @@
.evict = zbud_zpool_evict
};
-static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zbud_zpool_create(char *name, gfp_t gfp,
+ struct zpool_ops *zpool_ops)
{
return zbud_create_pool(gfp, &zbud_zpool_ops);
}
diff --git a/mm/zpool.c b/mm/zpool.c
index 739cdf0..bacdab6 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -129,6 +129,7 @@
/**
* 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.
*
@@ -140,7 +141,8 @@
*
* Returns: New zpool on success, NULL on failure.
*/
-struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
+struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+ struct zpool_ops *ops)
{
struct zpool_driver *driver;
struct zpool *zpool;
@@ -168,7 +170,7 @@
zpool->type = driver->type;
zpool->driver = driver;
- zpool->pool = driver->create(gfp, ops);
+ zpool->pool = driver->create(name, gfp, ops);
zpool->ops = ops;
if (!zpool->pool) {
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 839a48c..a8b5e74 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -12,35 +12,6 @@
*/
/*
- * 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().
- *
* Following is how we use various fields and flags of underlying
* struct page(s) to form a zspage.
*
@@ -57,6 +28,8 @@
*
* 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.
@@ -78,6 +51,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/highmem.h>
@@ -91,6 +65,7 @@
#include <linux/hardirq.h>
#include <linux/spinlock.h>
#include <linux/types.h>
+#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
@@ -109,6 +84,8 @@
#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.
@@ -132,13 +109,33 @@
#endif
#endif
#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
-#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
+
+/*
+ * 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
/*
@@ -155,8 +152,6 @@
* (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
@@ -170,6 +165,29 @@
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
@@ -196,6 +214,12 @@
/* 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;
@@ -209,15 +233,31 @@
* 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;
+ 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 {
- struct size_class size_class[ZS_SIZE_CLASSES];
+ 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
};
/*
@@ -237,15 +277,45 @@
#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(gfp_t gfp, struct zpool_ops *zpool_ops)
+static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops)
{
- return zs_create_pool(gfp);
+ return zs_create_pool(name, gfp);
}
static void zs_zpool_destroy(void *pool)
@@ -316,6 +386,11 @@
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);
@@ -366,9 +441,182 @@
idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
ZS_SIZE_CLASS_DELTA);
- return idx;
+ 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
@@ -389,7 +637,7 @@
fg = ZS_EMPTY;
else if (inuse == max_objects)
fg = ZS_FULL;
- else if (inuse <= max_objects / fullness_threshold_frac)
+ else if (inuse <= 3 * max_objects / fullness_threshold_frac)
fg = ZS_ALMOST_EMPTY;
else
fg = ZS_ALMOST_FULL;
@@ -418,6 +666,8 @@
list_add_tail(&page->lru, &(*head)->lru);
*head = page;
+ zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
+ CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
}
/*
@@ -443,6 +693,8 @@
struct page, lru);
list_del_init(&page->lru);
+ zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ?
+ CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
}
/*
@@ -454,11 +706,10 @@
* page from the freelist of the old fullness group to that of the new
* fullness group.
*/
-static enum fullness_group fix_fullness_group(struct zs_pool *pool,
+static enum fullness_group fix_fullness_group(struct size_class *class,
struct page *page)
{
int class_idx;
- struct size_class *class;
enum fullness_group currfg, newfg;
BUG_ON(!is_first_page(page));
@@ -468,7 +719,6 @@
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);
@@ -482,7 +732,8 @@
* 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
+ * 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
@@ -541,35 +792,50 @@
/*
* 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.
+ * We use the least bit of handle for tagging.
*/
-static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
+static void *location_to_obj(struct page *page, unsigned long obj_idx)
{
- unsigned long handle;
+ unsigned long obj;
if (!page) {
BUG_ON(obj_idx);
return NULL;
}
- handle = page_to_pfn(page) << OBJ_INDEX_BITS;
- handle |= ((obj_idx + 1) & OBJ_INDEX_MASK);
+ obj = page_to_pfn(page) << OBJ_INDEX_BITS;
+ obj |= ((obj_idx) & OBJ_INDEX_MASK);
+ obj <<= OBJ_TAG_BITS;
- return (void *)handle;
+ 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
- * obj_location_to_handle().
+ * location_to_obj().
*/
-static void obj_handle_to_location(unsigned long handle, struct page **page,
+static void obj_to_location(unsigned long obj, struct page **page,
unsigned long *obj_idx)
{
- *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
- *obj_idx = (handle & OBJ_INDEX_MASK) - 1;
+ 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,
@@ -583,6 +849,25 @@
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);
@@ -629,6 +914,7 @@
struct page *next_page;
struct link_free *link;
unsigned int i = 1;
+ void *vaddr;
/*
* page->index stores offset of first object starting
@@ -639,11 +925,11 @@
if (page != first_page)
page->index = off;
- link = (struct link_free *)kmap_atomic(page) +
- off / sizeof(*link);
+ vaddr = kmap_atomic(page);
+ link = (struct link_free *)vaddr + off / sizeof(*link);
while ((off += class->size) < PAGE_SIZE) {
- link->next = obj_location_to_handle(page, i++);
+ link->next = location_to_obj(page, i++);
link += class->size / sizeof(*link);
}
@@ -653,8 +939,8 @@
* page (if present)
*/
next_page = get_next_page(page);
- link->next = obj_location_to_handle(next_page, 0);
- kunmap_atomic(link);
+ link->next = location_to_obj(next_page, 0);
+ kunmap_atomic(vaddr);
page = next_page;
off %= PAGE_SIZE;
}
@@ -707,7 +993,7 @@
init_zspage(first_page, class);
- first_page->freelist = obj_location_to_handle(first_page, 0);
+ 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;
@@ -784,7 +1070,7 @@
*/
if (area->vm_buf)
return 0;
- area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
+ area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL);
if (!area->vm_buf)
return -ENOMEM;
return 0;
@@ -792,8 +1078,7 @@
static inline void __zs_cpu_down(struct mapping_area *area)
{
- if (area->vm_buf)
- free_page((unsigned long)area->vm_buf);
+ kfree(area->vm_buf);
area->vm_buf = NULL;
}
@@ -830,12 +1115,19 @@
{
int sizes[2];
void *addr;
- char *buf = area->vm_buf;
+ 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];
@@ -881,14 +1173,27 @@
.notifier_call = zs_cpu_notifier
};
-static void zs_exit(void)
+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;
-#ifdef CONFIG_ZPOOL
- zpool_unregister_driver(&zs_zpool_driver);
-#endif
-
cpu_notifier_register_begin();
for_each_online_cpu(cpu)
@@ -898,194 +1203,41 @@
cpu_notifier_register_done();
}
-static int zs_init(void)
+static void init_zs_size_classes(void)
{
- int cpu, ret;
+ int nr;
- cpu_notifier_register_begin();
+ 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;
- __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)) {
- cpu_notifier_register_done();
- goto fail;
- }
- }
-
- cpu_notifier_register_done();
-
-#ifdef CONFIG_ZPOOL
- zpool_register_driver(&zs_zpool_driver);
-#endif
-
- return 0;
-fail:
- zs_exit();
- return notifier_to_errno(ret);
+ zs_size_classes = nr;
}
-/**
- * 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)
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
{
- int i, ovhd_size;
- struct zs_pool *pool;
+ if (prev->pages_per_zspage != pages_per_zspage)
+ return false;
- ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
- pool = kzalloc(ovhd_size, GFP_KERNEL);
- if (!pool)
- return NULL;
+ if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+ != get_maxobj_per_zspage(size, pages_per_zspage))
+ return false;
- 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;
+ return true;
}
-EXPORT_SYMBOL_GPL(zs_create_pool);
-void zs_destroy_pool(struct zs_pool *pool)
+static bool zspage_full(struct page *page)
{
- int i;
+ BUG_ON(!is_first_page(page));
- 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);
+ return page->inuse == page->objects;
}
-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 zs_get_total_pages(struct zs_pool *pool)
{
- 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);
- atomic_long_add(class->pages_per_zspage,
- &pool->pages_allocated);
- spin_lock(&class->lock);
- }
-
- 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;
+ return atomic_long_read(&pool->pages_allocated);
}
-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);
- spin_unlock(&class->lock);
-
- if (fullness == ZS_EMPTY) {
- atomic_long_sub(class->pages_per_zspage,
- &pool->pages_allocated);
- free_zspage(first_page);
- }
-}
-EXPORT_SYMBOL_GPL(zs_free);
+EXPORT_SYMBOL_GPL(zs_get_total_pages);
/**
* zs_map_object - get address of allocated object from handle.
@@ -1105,13 +1257,14 @@
enum zs_mapmode mm)
{
struct page *page;
- unsigned long obj_idx, off;
+ 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);
@@ -1122,9 +1275,13 @@
*/
BUG_ON(in_interrupt());
- obj_handle_to_location(handle, &page, &obj_idx);
+ /* 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];
+ class = pool->size_class[class_idx];
off = obj_idx_to_offset(page, obj_idx, class->size);
area = &get_cpu_var(zs_map_area);
@@ -1132,7 +1289,8 @@
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;
+ ret = area->vm_addr + off;
+ goto out;
}
/* this object spans two pages */
@@ -1140,14 +1298,19 @@
pages[1] = get_next_page(page);
BUG_ON(!pages[1]);
- return __zs_map_object(area, pages, off, class->size);
+ 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_idx, off;
+ unsigned long obj, obj_idx, off;
unsigned int class_idx;
enum fullness_group fg;
@@ -1156,9 +1319,10 @@
BUG_ON(!handle);
- obj_handle_to_location(handle, &page, &obj_idx);
+ 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];
+ class = pool->size_class[class_idx];
off = obj_idx_to_offset(page, obj_idx, class->size);
area = this_cpu_ptr(&zs_map_area);
@@ -1174,14 +1338,607 @@
__zs_unmap_object(area, pages, off, class->size);
}
put_cpu_var(zs_map_area);
+ unpin_tag(handle);
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
-unsigned long zs_get_total_pages(struct zs_pool *pool)
+static unsigned long obj_malloc(struct page *first_page,
+ struct size_class *class, unsigned long handle)
{
- return atomic_long_read(&pool->pages_allocated);
+ 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;
}
-EXPORT_SYMBOL_GPL(zs_get_total_pages);
+
+
+/**
+ * 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);
diff --git a/mm/zswap.c b/mm/zswap.c
index ea064c1..e2f8c7e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -907,11 +907,12 @@
pr_info("loading zswap\n");
- zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, &zswap_zpool_ops);
+ zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
+ &zswap_zpool_ops);
if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
pr_info("%s zpool not available\n", zswap_zpool_type);
zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
- zswap_pool = zpool_create_pool(zswap_zpool_type, gfp,
+ zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
&zswap_zpool_ops);
}
if (!zswap_pool) {
