Merge remote-tracking branch 'common/android-3.10' into android-x86_64-fugu-3.10
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..bd43704 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@
ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg
index f288006..9303376 100644
--- a/android/configs/android-base.cfg
+++ b/android/configs/android-base.cfg
@@ -42,6 +42,7 @@
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
diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg
index 960b9de..4dd3b45 100644
--- a/android/configs/android-recommended.cfg
+++ b/android/configs/android-recommended.cfg
@@ -109,6 +109,10 @@
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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c5926f2..e159dcd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -998,10 +998,27 @@
default y
depends on X86_32
---help---
- This option is required by programs like DOSEMU to run 16-bit legacy
- code on X86 processors. It also may be needed by software like
- XFree86 to initialize some video cards via BIOS. Disabling this
- option saves about 6k.
+ This option is required by programs like DOSEMU to run
+ 16-bit real mode legacy code on x86 processors. It also may
+ be needed by software like XFree86 to initialize some video
+ cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+ bool "Enable support for 16-bit segments" if EXPERT
+ default y
+ ---help---
+ This option is required by programs like Wine to run 16-bit
+ protected mode legacy code on x86 processors. Disabling
+ this option saves about 300 bytes on i386, or around 6K text
+ plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+ def_bool y
+ depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+ def_bool y
+ depends on X86_16BIT && X86_64
config TOSHIBA
tristate "Toshiba Laptop support"
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 0000000..99efebb
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf8..0a8b519 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@
#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */
-#define INTERRUPT_RETURN iretq
+#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
sysretq;
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ef17af0..4376b45 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -18,7 +18,6 @@
#define THREAD_SIZE_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define STACKFAULT_STACK 0
#define DOUBLEFAULT_STACK 1
#define NMI_STACK 0
#define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6c896fb..970f309 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
#define IRQ_STACK_ORDER 2
#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */
#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d88344..b1609f2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@
#define MODULES_VADDR _AC(0xffffffffa0000000, UL)
#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
#define EARLY_DYNAMIC_PAGE_TABLES 64
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index cafa665..e993660 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -62,6 +62,8 @@
#ifndef _SETUP
+#include <asm/espfix.h>
+
/*
* This is set up by the setup-routine at boot-time
*/
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 78d81cf..c5975ec 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -27,6 +27,7 @@
obj-y += syscall_$(BITS).o
obj-$(CONFIG_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207..66e274a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@
[ DEBUG_STACK-1 ] = "#DB",
[ NMI_STACK-1 ] = "NMI",
[ DOUBLEFAULT_STACK-1 ] = "#DF",
- [ STACKFAULT_STACK-1 ] = "#SS",
[ MCE_STACK-1 ] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8f3e2de..e758e2f 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -530,6 +530,7 @@
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
# are returning to the kernel.
@@ -540,6 +541,7 @@
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
CFI_REMEMBER_STATE
je ldt_ss # returning to user-space with LDT SS
+#endif
restore_nocheck:
RESTORE_REGS 4 # skip orig_eax/error_code
irq_return:
@@ -552,13 +554,9 @@
.previous
_ASM_EXTABLE(irq_return,iret_exc)
+#ifdef CONFIG_X86_ESPFIX32
CFI_RESTORE_STATE
ldt_ss:
- larl PT_OLDSS(%esp), %eax
- jnz restore_nocheck
- testl $0x00400000, %eax # returning to 32bit stack?
- jnz restore_nocheck # allright, normal return
-
#ifdef CONFIG_PARAVIRT
/*
* The kernel can't run on a non-flat stack if paravirt mode
@@ -600,6 +598,7 @@
lss (%esp), %esp /* switch to espfix segment */
CFI_ADJUST_CFA_OFFSET -8
jmp restore_nocheck
+#endif
CFI_ENDPROC
ENDPROC(system_call)
@@ -707,6 +706,7 @@
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
*/
+#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -716,8 +716,10 @@
pushl_cfi %eax
lss (%esp), %esp /* switch to the normal stack segment */
CFI_ADJUST_CFA_OFFSET -8
+#endif
.endm
.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
movl %ss, %eax
/* see if on espfix stack */
cmpw $__ESPFIX_SS, %ax
@@ -728,6 +730,7 @@
/* switch to normal stack */
FIXUP_ESPFIX_STACK
27:
+#endif
.endm
/*
@@ -1335,11 +1338,13 @@
ENTRY(nmi)
RING0_INT_FRAME
ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
pushl_cfi %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
popl_cfi %eax
je nmi_espfix_stack
+#endif
cmpl $ia32_sysenter_target,(%esp)
je nmi_stack_fixup
pushl_cfi %eax
@@ -1379,6 +1384,7 @@
FIX_STACK 24, nmi_stack_correct, 1
jmp nmi_stack_correct
+#ifdef CONFIG_X86_ESPFIX32
nmi_espfix_stack:
/* We have a RING0_INT_FRAME here.
*
@@ -1400,6 +1406,7 @@
lss 12+4(%esp), %esp # back to espfix stack
CFI_ADJUST_CFA_OFFSET -24
jmp irq_return
+#endif
CFI_ENDPROC
END(nmi)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7272089..50e5e59 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
#include <asm/asm.h>
#include <asm/context_tracking.h>
#include <asm/smap.h>
+#include <asm/pgtable_types.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -1056,12 +1057,46 @@
irq_return:
INTERRUPT_RETURN
- _ASM_EXTABLE(irq_return, bad_iret)
-#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4,(SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
+#endif
+
+.global native_irq_return_iret
+native_irq_return_iret:
iretq
- _ASM_EXTABLE(native_iret, bad_iret)
+ _ASM_EXTABLE(native_irq_return_iret, bad_iret)
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq_cfi %rax
+ pushq_cfi %rdi
+ SWAPGS
+ movq PER_CPU_VAR(espfix_waddr),%rdi
+ movq %rax,(0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp),%rax /* RIP */
+ movq %rax,(1*8)(%rdi)
+ movq (3*8)(%rsp),%rax /* CS */
+ movq %rax,(2*8)(%rdi)
+ movq (4*8)(%rsp),%rax /* RFLAGS */
+ movq %rax,(3*8)(%rdi)
+ movq (6*8)(%rsp),%rax /* SS */
+ movq %rax,(5*8)(%rdi)
+ movq (5*8)(%rsp),%rax /* RSP */
+ movq %rax,(4*8)(%rdi)
+ andl $0xffff0000,%eax
+ popq_cfi %rdi
+ orq PER_CPU_VAR(espfix_stack),%rax
+ SWAPGS
+ movq %rax,%rsp
+ popq_cfi %rax
+ jmp native_irq_return_iret
#endif
.section .fixup,"ax"
@@ -1127,9 +1162,9 @@
call preempt_schedule_irq
jmp exit_intr
#endif
-
CFI_ENDPROC
END(common_interrupt)
+
/*
* End of kprobes section
*/
@@ -1468,7 +1503,7 @@
paranoidzeroentry_ist debug do_debug DEBUG_STACK
paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
#ifdef CONFIG_XEN
zeroentry xen_debug do_debug
zeroentry xen_int3 do_int3
@@ -1585,7 +1620,7 @@
*/
error_kernelspace:
incl %ebx
- leaq irq_return(%rip),%rcx
+ leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
je error_swapgs
movl %ecx,%eax /* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 0000000..94d857f
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ * Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer. This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart. When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace. The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables. The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE (8*8UL)
+#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+ __aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+ unsigned long page, slot;
+ unsigned long addr;
+
+ page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+ slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+ addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+ addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+ addr += ESPFIX_BASE_ADDR;
+ return addr;
+}
+
+#define PTE_STRIDE (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+ unsigned long rand;
+
+ /*
+ * This is run before the entropy pools are initialized,
+ * but this is hopefully better than nothing.
+ */
+ if (!arch_get_random_long(&rand)) {
+ /* The constant is an arbitrary large prime */
+ rdtscll(rand);
+ rand *= 0xc345c6b72fd16123UL;
+ }
+
+ slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+ page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+ & (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+ pgd_t *pgd_p;
+ pteval_t ptemask;
+
+ ptemask = __supported_pte_mask;
+
+ /* Install the espfix pud into the kernel page directory */
+ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+ pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+ /* Randomize the locations */
+ init_espfix_random();
+
+ /* The rest is the same as for any other processor */
+ init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+ unsigned int cpu, page;
+ unsigned long addr;
+ pud_t pud, *pud_p;
+ pmd_t pmd, *pmd_p;
+ pte_t pte, *pte_p;
+ int n;
+ void *stack_page;
+ pteval_t ptemask;
+
+ /* We only have to do this once... */
+ if (likely(this_cpu_read(espfix_stack)))
+ return; /* Already initialized */
+
+ cpu = smp_processor_id();
+ addr = espfix_base_addr(cpu);
+ page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+ /* Did another CPU already set this up? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (likely(stack_page))
+ goto done;
+
+ mutex_lock(&espfix_init_mutex);
+
+ /* Did we race on the lock? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (stack_page)
+ goto unlock_done;
+
+ ptemask = __supported_pte_mask;
+
+ pud_p = &espfix_pud_page[pud_index(addr)];
+ pud = *pud_p;
+ if (!pud_present(pud)) {
+ pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+ set_pud(&pud_p[n], pud);
+ }
+
+ pmd_p = pmd_offset(&pud, addr);
+ pmd = *pmd_p;
+ if (!pmd_present(pmd)) {
+ pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+ pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+ set_pmd(&pmd_p[n], pmd);
+ }
+
+ pte_p = pte_offset_kernel(&pmd, addr);
+ stack_page = (void *)__get_free_page(GFP_KERNEL);
+ pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+ for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+ set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+ /* Job is done for this CPU and any CPU which shares this page */
+ ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+ mutex_unlock(&espfix_init_mutex);
+done:
+ this_cpu_write(espfix_stack, addr);
+ this_cpu_write(espfix_waddr, (unsigned long)stack_page
+ + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc9873..c37886d 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,11 @@
}
}
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
fill_ldt(&ldt, &ldt_info);
if (oldmode)
ldt.avl = 0;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34..a1da673 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@
DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, iret);
PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2192c1c..4ffe6bb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -265,6 +265,13 @@
check_tsc_sync_target();
/*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap();
+#endif
+
+ /*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09..e7650bd 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,21 @@
return -ESRCH;
}
+static bool tls_desc_okay(const struct user_desc *info)
+{
+ if (LDT_empty(info))
+ return true;
+
+ /*
+ * espfix is required for 16-bit data segments, but espfix
+ * only works for LDT segments.
+ */
+ if (!info->seg_32bit)
+ return false;
+
+ return true;
+}
+
static void set_tls_desc(struct task_struct *p, int idx,
const struct user_desc *info, int n)
{
@@ -66,6 +81,9 @@
if (copy_from_user(&info, u_info, sizeof(info)))
return -EFAULT;
+ if (!tls_desc_okay(&info))
+ return -EINVAL;
+
if (idx == -1)
idx = info.entry_number;
@@ -192,6 +210,7 @@
{
struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
const struct user_desc *info;
+ int i;
if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +224,10 @@
else
info = infobuf;
+ for (i = 0; i < count / sizeof(struct user_desc); i++)
+ if (!tls_desc_okay(info + i))
+ return -EINVAL;
+
set_tls_desc(target,
GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 5ca57b9..8a75efd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -220,33 +220,41 @@
coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-#ifdef CONFIG_X86_32
DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-#endif
DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
BUS_ADRALN, 0)
#ifdef CONFIG_X86_64
/* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
- enum ctx_state prev_state;
-
- prev_state = exception_enter();
- if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
- preempt_conditional_sti(regs);
- do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
- }
- exception_exit(prev_state);
-}
-
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
+#ifdef CONFIG_X86_ESPFIX64
+ extern unsigned char native_irq_return_iret[];
+
+ /*
+ * If IRET takes a non-IST fault on the espfix64 stack, then we
+ * end up promoting it to a doublefault. In that case, modify
+ * the stack to make it look like we just entered the #GP
+ * handler from user space, similar to bad_iret.
+ */
+ if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ regs->cs == __KERNEL_CS &&
+ regs->ip == (unsigned long)native_irq_return_iret)
+ {
+ struct pt_regs *normal_regs = task_pt_regs(current);
+
+ /* Fake a #GP(0) from userspace. */
+ memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+ normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
+ regs->ip = (unsigned long)general_protection;
+ regs->sp = (unsigned long)&normal_regs->orig_ax;
+ return;
+ }
+#endif
+
exception_enter();
/* Return not checked because double check cannot be ignored */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -778,7 +786,7 @@
set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
set_intr_gate(X86_TRAP_TS, &invalid_TSS);
set_intr_gate(X86_TRAP_NP, &segment_not_present);
- set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+ set_intr_gate(X86_TRAP_SS, stack_segment);
set_intr_gate(X86_TRAP_GP, &general_protection);
set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
set_intr_gate(X86_TRAP_MF, &coprocessor_error);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a..e04e677 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@
unsigned long start_address;
unsigned long current_address;
const struct addr_marker *marker;
+ unsigned long lines;
};
struct addr_marker {
unsigned long start_address;
const char *name;
+ unsigned long max_lines;
};
/* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
+ ESPFIX_START_NR,
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
@@ -67,6 +70,7 @@
{ PAGE_OFFSET, "Low Kernel Mapping" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMEMMAP_START, "Vmemmap" },
+ { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
@@ -163,7 +167,7 @@
pgprot_t new_prot, int level)
{
pgprotval_t prot, cur;
- static const char units[] = "KMGTPE";
+ static const char units[] = "BKMGTPE";
/*
* If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@
st->current_prot = new_prot;
st->level = level;
st->marker = address_markers;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
} else if (prot != cur || level != st->level ||
st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@
/*
* Now print the actual finished series
*/
- seq_printf(m, "0x%0*lx-0x%0*lx ",
- width, st->start_address,
- width, st->current_address);
+ if (!st->marker->max_lines ||
+ st->lines < st->marker->max_lines) {
+ seq_printf(m, "0x%0*lx-0x%0*lx ",
+ width, st->start_address,
+ width, st->current_address);
- delta = (st->current_address - st->start_address) >> 10;
- while (!(delta & 1023) && unit[1]) {
- delta >>= 10;
- unit++;
+ delta = (st->current_address - st->start_address);
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ seq_printf(m, "%9lu%c ", delta, *unit);
+ printk_prot(m, st->current_prot, st->level);
}
- seq_printf(m, "%9lu%c ", delta, *unit);
- printk_prot(m, st->current_prot, st->level);
+ st->lines++;
/*
* We print markers for special areas of address space,
@@ -206,7 +215,15 @@
* This helps in the interpretation.
*/
if (st->current_address >= st->marker[1].start_address) {
+ if (st->marker->max_lines &&
+ st->lines > st->marker->max_lines) {
+ unsigned long nskip =
+ st->lines - st->marker->max_lines;
+ seq_printf(m, "... %lu entr%s skipped ... \n",
+ nskip, nskip == 1 ? "y" : "ies");
+ }
st->marker++;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6d2d41a..a293092 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -17,10 +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/percpu.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>
@@ -44,6 +45,7 @@
unsigned int idx_out;
sector_t cc_sector;
atomic_t cc_pending;
+ struct ablkcipher_request *req;
};
/*
@@ -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;
@@ -105,15 +108,7 @@
enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
/*
- * Duplicated per-CPU state for cipher.
- */
-struct crypt_cpu {
- struct ablkcipher_request *req;
-};
-
-/*
- * The fields in here must be read only after initialization,
- * changing state should be in crypt_cpu.
+ * The fields in here must be read only after initialization.
*/
struct crypt_config {
struct dm_dev *dev;
@@ -123,14 +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;
@@ -143,12 +142,6 @@
sector_t iv_offset;
unsigned int iv_size;
- /*
- * Duplicated per cpu state. Access through
- * per_cpu_ptr() only.
- */
- struct crypt_cpu __percpu *cpu;
-
/* ESSIV: struct crypto_cipher *essiv_tfm */
void *iv_private;
struct crypto_ablkcipher **tfms;
@@ -169,6 +162,8 @@
*/
unsigned int dmreq_start;
+ unsigned int per_bio_data_size;
+
unsigned long flags;
unsigned int key_size;
unsigned int key_parts;
@@ -176,19 +171,11 @@
};
#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);
static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
-static struct crypt_cpu *this_crypt_config(struct crypt_config *cc)
-{
- return this_cpu_ptr(cc->cpu);
-}
-
/*
* Use this to access cipher attributes that are the same for each CPU.
*/
@@ -738,16 +725,24 @@
static void crypt_alloc_req(struct crypt_config *cc,
struct convert_context *ctx)
{
- struct crypt_cpu *this_cc = this_crypt_config(cc);
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
- if (!this_cc->req)
- this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO);
+ if (!ctx->req)
+ ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
- ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]);
- ablkcipher_request_set_callback(this_cc->req,
+ ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+ ablkcipher_request_set_callback(ctx->req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- kcryptd_async_done, dmreq_of_req(cc, this_cc->req));
+ 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);
}
/*
@@ -756,7 +751,6 @@
static int crypt_convert(struct crypt_config *cc,
struct convert_context *ctx)
{
- struct crypt_cpu *this_cc = this_crypt_config(cc);
int r;
atomic_set(&ctx->cc_pending, 1);
@@ -768,7 +762,7 @@
atomic_inc(&ctx->cc_pending);
- r = crypt_convert_block(cc, ctx, this_cc->req);
+ r = crypt_convert_block(cc, ctx, ctx->req);
switch (r) {
/* async */
@@ -777,7 +771,7 @@
INIT_COMPLETION(ctx->restart);
/* fall through*/
case -EINPROGRESS:
- this_cc->req = NULL;
+ ctx->req = NULL;
ctx->cc_sector++;
continue;
@@ -798,57 +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;
}
@@ -865,20 +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)
@@ -889,27 +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;
- mempool_free(io, cc->io_pool);
+ if (io->ctx.req)
+ 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);
}
/*
@@ -991,37 +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);
@@ -1035,20 +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;
@@ -1058,81 +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);
}
@@ -1180,7 +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;
@@ -1326,26 +1338,20 @@
static void crypt_dtr(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
- struct crypt_cpu *cpu_cc;
- int cpu;
ti->private = NULL;
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)
destroy_workqueue(cc->crypt_queue);
- if (cc->cpu)
- for_each_possible_cpu(cpu) {
- cpu_cc = per_cpu_ptr(cc->cpu, cpu);
- if (cpu_cc->req)
- mempool_free(cpu_cc->req, cc->req_pool);
- }
-
crypt_free_tfms(cc);
if (cc->bs)
@@ -1355,8 +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);
@@ -1364,9 +1368,6 @@
if (cc->dev)
dm_put_device(ti, cc->dev);
- if (cc->cpu)
- free_percpu(cc->cpu);
-
kzfree(cc->cipher);
kzfree(cc->cipher_string);
@@ -1421,13 +1422,6 @@
if (tmp)
DMWARN("Ignoring unexpected additional cipher options");
- cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)),
- __alignof__(struct crypt_cpu));
- if (!cc->cpu) {
- ti->error = "Cannot allocate per cpu state";
- goto bad_mem;
- }
-
/*
* For compatibility with the original dm-crypt mapping format, if
* only the cipher name is supplied, use cbc-plain.
@@ -1543,6 +1537,7 @@
unsigned int key_size, opt_params;
unsigned long long tmpll;
int ret;
+ size_t iv_size_padding;
struct dm_arg_set as;
const char *opt_string;
char dummy;
@@ -1570,27 +1565,37 @@
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, crypto_tfm_ctx_alignment());
- cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
- ~(crypto_tfm_ctx_alignment() - 1);
+ cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+ if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+ /* Allocate the padding exactly */
+ iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+ & crypto_ablkcipher_alignmask(any_tfm(cc));
+ } else {
+ /*
+ * If the cipher requires greater alignment than kmalloc
+ * alignment, we don't know the exact position of the
+ * initialization vector. We must assume worst case.
+ */
+ 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) + cc->iv_size);
+ sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
if (!cc->req_pool) {
ti->error = "Cannot allocate crypt request mempool";
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;
@@ -1602,6 +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";
@@ -1664,6 +1671,18 @@
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;
@@ -1691,11 +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);
@@ -1841,15 +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;
}
@@ -1857,7 +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/init/main.c b/init/main.c
index e83ac04..2132ffd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -606,6 +606,10 @@
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
+#ifdef CONFIG_X86_ESPFIX64
+ /* Should be run before the first non-init thread is created */
+ init_espfix_bsp();
+#endif
thread_info_cache_init();
cred_init();
fork_init(totalram_pages);
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 6618fb4..ba7dd93 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -643,7 +643,7 @@
{
struct avtab_node *node;
- if (!ctab || !key || !avd || !xperms)
+ if (!ctab || !key || !avd)
return;
for (node = avtab_search_node(ctab, key); node;
@@ -662,7 +662,7 @@
if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) ==
(node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED)))
avd->auditallow |= node->datum.u.data;
- if ((node->key.specified & AVTAB_ENABLED) &&
+ if (xperms && (node->key.specified & AVTAB_ENABLED) &&
(node->key.specified & AVTAB_XPERMS))
services_compute_xperms_drivers(xperms, node);
}