Re: Linux 3.10.61

From: Greg KH
Date: Fri Nov 21 2014 - 15:13:13 EST


diff --git a/Makefile b/Makefile
index 9d4f30d0d201..0d5ba80786b8 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 3
PATCHLEVEL = 10
-SUBLEVEL = 60
+SUBLEVEL = 61
EXTRAVERSION =
NAME = TOSSUG Baby Fish

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132dd3507..98838a05ba6d 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
@@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
if (address >= TASK_SIZE)
goto vmalloc_fault;
#endif
-
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -142,6 +142,7 @@ retry:
} else {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
}

/* If for any reason at all we couldn't handle the fault,
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 331a0846628e..50533b750a99 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -59,8 +59,7 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
struct mm_struct *mm = tsk->mm;
siginfo_t info;
int fault, ret;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

/*
* We fault-in kernel-space virtual memory on-demand. The
@@ -88,6 +87,8 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -115,12 +116,12 @@ good_area:
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}

-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -200,14 +201,12 @@ no_context:
die("Oops", regs, address, cause_code);

out_of_memory:
- if (is_global_init(tsk)) {
- yield();
- goto survive;
- }
up_read(&mm->mmap_sem);

- if (user_mode(regs))
- do_group_exit(SIGKILL); /* This will never return */
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return;
+ }

goto no_context;

diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 7af5c6c3653a..b274bde24905 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -2,6 +2,8 @@
#define _ASMARM_BUG_H

#include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>

#ifdef CONFIG_BUG

@@ -12,10 +14,10 @@
*/
#ifdef CONFIG_THUMB2_KERNEL
#define BUG_INSTR_VALUE 0xde02
-#define BUG_INSTR_TYPE ".hword "
+#define BUG_INSTR(__value) __inst_thumb16(__value)
#else
#define BUG_INSTR_VALUE 0xe7f001f2
-#define BUG_INSTR_TYPE ".word "
+#define BUG_INSTR(__value) __inst_arm(__value)
#endif


@@ -33,7 +35,7 @@

#define __BUG(__file, __line, __value) \
do { \
- asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \
+ asm volatile("1:\t" BUG_INSTR(__value) "\n" \
".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
"2:\t.asciz " #__file "\n" \
".popsection\n" \
@@ -48,7 +50,7 @@ do { \

#define __BUG(__file, __line, __value) \
do { \
- asm volatile(BUG_INSTR_TYPE #__value); \
+ asm volatile(BUG_INSTR(__value) "\n"); \
unreachable(); \
} while (0)
#endif /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index 18a76282970e..380c20fb9c85 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <asm/system_info.h>
+#include <asm/opcodes.h>

#include "kprobes.h"

@@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)

if (handler) {
/* We can emulate the instruction in (possibly) modified form */
- asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+ asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) |
+ (rn << 16) | reglist);
asi->insn_handler = handler;
return INSN_GOOD;
}
@@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
#ifdef CONFIG_THUMB2_KERNEL
if (thumb) {
u16 *thumb_insn = (u16 *)asi->insn;
- thumb_insn[1] = 0x4770; /* Thumb bx lr */
- thumb_insn[2] = 0x4770; /* Thumb bx lr */
+ /* Thumb bx lr */
+ thumb_insn[1] = __opcode_to_mem_thumb16(0x4770);
+ thumb_insn[2] = __opcode_to_mem_thumb16(0x4770);
return insn;
}
- asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+ asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */
#else
- asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+ asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */
#endif
/* Make an ARM instruction unconditional */
if (insn < 0xe0000000)
@@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
if (thumb) {
u16 *ip = (u16 *)asi->insn;
if (is_wide_instruction(insn))
- *ip++ = insn >> 16;
- *ip++ = insn;
+ *ip++ = __opcode_to_mem_thumb16(insn >> 16);
+ *ip++ = __opcode_to_mem_thumb16(insn);
return;
}
#endif
- asi->insn[0] = insn;
+ asi->insn[0] = __opcode_to_mem_arm(insn);
}

/*
diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c
index 6123daf397a7..b82e798983c4 100644
--- a/arch/arm/kernel/kprobes-thumb.c
+++ b/arch/arm/kernel/kprobes-thumb.c
@@ -163,9 +163,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi);

/* Fixup modified instruction to have halfwords in correct order...*/
- insn = asi->insn[0];
- ((u16 *)asi->insn)[0] = insn >> 16;
- ((u16 *)asi->insn)[1] = insn & 0xffff;
+ insn = __mem_to_opcode_arm(asi->insn[0]);
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16);
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff);

return ret;
}
@@ -1153,7 +1153,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi)
{
insn &= ~0x00ff;
insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
- ((u16 *)asi->insn)[0] = insn;
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn);
asi->insn_handler = t16_emulate_hiregs;
return INSN_GOOD;
}
@@ -1182,8 +1182,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi)
* and call it with R9=SP and LR in the register list represented
* by R8.
*/
- ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */
- ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */
+ /* 1st half STMDB R9!,{} */
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929);
+ /* 2nd half (register list) */
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
asi->insn_handler = t16_emulate_push;
return INSN_GOOD;
}
@@ -1232,8 +1234,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi)
* and call it with R9=SP and PC in the register list represented
* by R8.
*/
- ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */
- ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */
+ /* 1st half LDMIA R9!,{} */
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9);
+ /* 2nd half (register list) */
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc
: t16_emulate_pop_nopc;
return INSN_GOOD;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 170e9f34003f..1c6ece51781c 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -26,6 +26,7 @@
#include <linux/stop_machine.h>
#include <linux/stringify.h>
#include <asm/traps.h>
+#include <asm/opcodes.h>
#include <asm/cacheflush.h>

#include "kprobes.h"
@@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
#ifdef CONFIG_THUMB2_KERNEL
thumb = true;
addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
- insn = ((u16 *)addr)[0];
+ insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
if (is_wide_instruction(insn)) {
- insn <<= 16;
- insn |= ((u16 *)addr)[1];
+ u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
+ insn = __opcode_thumb32_compose(insn, inst2);
decode_insn = thumb32_kprobe_decode_insn;
} else
decode_insn = thumb16_kprobe_decode_insn;
@@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
thumb = false;
if (addr & 0x3)
return -EINVAL;
- insn = *p->addr;
+ insn = __mem_to_opcode_arm(*p->addr);
decode_insn = arm_kprobe_decode_insn;
#endif

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d6a0fdb6c2ee..a2a2804b1bc2 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -347,15 +347,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs,
int is_valid_bugaddr(unsigned long pc)
{
#ifdef CONFIG_THUMB2_KERNEL
- unsigned short bkpt;
+ u16 bkpt;
+ u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE);
#else
- unsigned long bkpt;
+ u32 bkpt;
+ u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
#endif

if (probe_kernel_address((unsigned *)pc, bkpt))
return 0;

- return bkpt == BUG_INSTR_VALUE;
+ return bkpt == insn;
}

#endif
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c21082d664ed..c6926eae4fe0 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -778,6 +778,7 @@ config NEED_KUSER_HELPERS

config KUSER_HELPERS
bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+ depends on MMU
default y
help
Warning: disabling this option may break user programs.
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5dbf13f954f6..160da6d65546 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- int write = fsr & FSR_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

if (notify_page_fault(regs, fsr))
return 0;
@@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (fsr & FSR_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -349,6 +352,13 @@ retry:
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;

+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -359,13 +369,6 @@ retry:
return 0;
}

- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 6e0ed93d51fe..c17967fdf5f6 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -46,7 +46,7 @@ USER(9f, strh wzr, [x0], #2 )
sub x1, x1, #2
4: adds x1, x1, #1
b.mi 5f
- strb wzr, [x0]
+USER(9f, strb wzr, [x0] )
5: mov x0, #0
ret
ENDPROC(__clear_user)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f51d669c8ebd..b5d458769b65 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

- if (esr & ESR_LNX_EXEC) {
- vm_flags = VM_EXEC;
- } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
- vm_flags = VM_WRITE;
- mm_flags |= FAULT_FLAG_WRITE;
- }
-
tsk = current;
mm = tsk->mm;

@@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ mm_flags |= FAULT_FLAG_USER;
+
+ if (esr & ESR_LNX_EXEC) {
+ vm_flags = VM_EXEC;
+ } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+ vm_flags = VM_WRITE;
+ mm_flags |= FAULT_FLAG_WRITE;
+ }
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -288,6 +291,13 @@ retry:
VM_FAULT_BADACCESS))))
return 0;

+ /*
+ * If we are in kernel mode at this point, we have no context to
+ * handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -298,13 +308,6 @@ retry:
return 0;
}

- /*
- * If we are in kernel mode at this point, we have no context to
- * handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to successfully fix up
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index b2f2d2d66849..0eca93327195 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)

local_irq_enable();

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);

@@ -228,9 +230,9 @@ no_context:
*/
out_of_memory:
up_read(&mm->mmap_sem);
- pagefault_out_of_memory();
if (!user_mode(regs))
goto no_context;
+ pagefault_out_of_memory();
return;

do_sigbus:
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab6c696..1790f22e71a2 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
struct vm_area_struct * vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

D(printk(KERN_DEBUG
"Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -155,6 +156,7 @@ retry:
} else if (writeaccess == 1) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2cfb67..9a66372fc7c7 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
struct vm_area_struct *vma;
struct mm_struct *mm;
unsigned long _pme, lrai, lrad, fixup;
+ unsigned long flags = 0;
siginfo_t info;
pgd_t *pge;
pud_t *pue;
pte_t *pte;
- int write;
int fault;

#if 0
@@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(__frame))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);

vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (esr0 & ESR0_ATXC) {
default:
/* handle write to write protected page */
@@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write = 1;
+ flags |= FAULT_FLAG_WRITE;
break;

/* handle read from protected page */
@@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, ear0, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276dbec7d..8704c9320032 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
int si_code = SEGV_MAPERR;
int fault;
const struct exception_table_entry *fixup;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

/*
* If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)

local_irq_enable();

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -96,6 +97,7 @@ good_area:
case FLT_STORE:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
break;
}

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341f978e..7225dad87094 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));

- flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
/* mmap_sem is performance critical.... */
prefetchw(&mm->mmap_sem);

@@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
if (notify_page_fault(regs, TRAP_BRKPT))
return;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (mask & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);

diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c1d091..e9c6a8014bd6 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
struct mm_struct *mm;
struct vm_area_struct * vma;
unsigned long page, addr;
- int write;
+ unsigned long flags = 0;
int fault;
siginfo_t info;

@@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
if (in_atomic() || !mm)
goto bad_area_nosemaphore;

+ if (error_code & ACE_USERMODE)
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
default: /* 3: write, present */
/* fall through */
case ACE_WRITE: /* write, not present */
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write++;
+ flags |= FAULT_FLAG_WRITE;
break;
case ACE_PROTECTION: /* read, present */
case 0: /* read, not present */
@@ -194,7 +196,7 @@ good_area:
*/
addr = (address & PAGE_MASK);
set_thread_fault_code(error_code);
- fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, addr, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727806bf..eb1d61f68725 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);

diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2c75bf7357c5..332680e5ebf2 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
struct vm_area_struct *vma, *prev_vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write_access ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

tsk = current;

@@ -109,6 +108,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);

@@ -121,6 +122,7 @@ good_area:
if (write_access) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
@@ -224,8 +226,10 @@ do_sigbus:
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return 1;
+ }

no_context:
/* Are we prepared to handle this kernel fault? */
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739d17a1..fa4cf52aa7a6 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
int code = SEGV_MAPERR;
int is_write = error_code & ESR_S;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

regs->ear = address;
regs->esr = error_code;
@@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
die("Weird page fault", regs, SIGSEGV);
}

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -199,6 +201,7 @@ good_area:
if (unlikely(is_write)) {
if (unlikely(!(vma->vm_flags & VM_WRITE)))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 5495101d32c8..c2ec87e5d1cc 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -608,6 +608,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
r4k_blast_scache();
else
blast_scache_range(addr, addr + size);
+ preempt_enable();
__sync();
return;
}
@@ -649,6 +650,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
*/
blast_inv_scache_range(addr, addr + size);
}
+ preempt_enable();
__sync();
return;
}
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 0fead53d1c26..0214a43b9911 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -41,8 +41,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
const int field = sizeof(unsigned long) * 2;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

#if 0
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -92,6 +91,8 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
if (in_atomic() || !mm)
goto bad_area_nosemaphore;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -113,6 +114,7 @@ good_area:
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (cpu_has_rixi) {
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
@@ -240,6 +242,8 @@ out_of_memory:
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
pagefault_out_of_memory();
return;

diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index d48a84fd7fae..3516cbdf1ee9 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
if (in_atomic() || !mm)
goto no_context;

+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);

@@ -345,9 +347,10 @@ no_context:
*/
out_of_memory:
up_read(&mm->mmap_sem);
- printk(KERN_ALERT "VM: killing process %s\n", tsk->comm);
- if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
- do_exit(SIGKILL);
+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
+ pagefault_out_of_memory();
+ return;
+ }
goto no_context;

do_sigbus:
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e2bfafce66c5..0703acf7d327 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
if (user_mode(regs)) {
/* Exception was in userspace: reenable interrupts */
local_irq_enable();
+ flags |= FAULT_FLAG_USER;
} else {
/* If exception was in a syscall, then IRQ's may have
* been enabled or disabled. If they were enabled,
@@ -267,10 +268,10 @@ out_of_memory:
__asm__ __volatile__("l.nop 1");

up_read(&mm->mmap_sem);
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;

do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index 0a3eada1863b..f395cde7b593 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -36,23 +36,16 @@ struct shmid64_ds {
unsigned int __unused2;
};

-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
struct shminfo64 {
- unsigned int shmmax;
- unsigned int shmmin;
- unsigned int shmmni;
- unsigned int shmseg;
- unsigned int shmall;
- unsigned int __unused1;
- unsigned int __unused2;
- unsigned int __unused3;
- unsigned int __unused4;
+ unsigned long shmmax;
+ unsigned long shmmin;
+ unsigned long shmmni;
+ unsigned long shmseg;
+ unsigned long shmall;
+ unsigned long __unused1;
+ unsigned long __unused2;
+ unsigned long __unused3;
+ unsigned long __unused4;
};

#endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 10a0c2aad8cf..b24732d1bdbf 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -286,11 +286,11 @@
ENTRY_COMP(msgsnd)
ENTRY_COMP(msgrcv)
ENTRY_SAME(msgget) /* 190 */
- ENTRY_SAME(msgctl)
- ENTRY_SAME(shmat)
+ ENTRY_COMP(msgctl)
+ ENTRY_COMP(shmat)
ENTRY_SAME(shmdt)
ENTRY_SAME(shmget)
- ENTRY_SAME(shmctl) /* 195 */
+ ENTRY_COMP(shmctl) /* 195 */
ENTRY_SAME(ni_syscall) /* streams1 */
ENTRY_SAME(ni_syscall) /* streams2 */
ENTRY_SAME(lstat64)
@@ -323,7 +323,7 @@
ENTRY_SAME(epoll_ctl) /* 225 */
ENTRY_SAME(epoll_wait)
ENTRY_SAME(remap_file_pages)
- ENTRY_SAME(semtimedop)
+ ENTRY_COMP(semtimedop)
ENTRY_COMP(mq_open)
ENTRY_SAME(mq_unlink) /* 230 */
ENTRY_COMP(mq_timedsend)
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a3480e8e..d10d27a720c0 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -180,6 +180,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (acc_type & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
vma = find_vma_prev(mm, address, &prev_vma);
@@ -203,8 +207,7 @@ good_area:
* fault.
*/

- fault = handle_mm_fault(mm, vma, address,
- flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+ fault = handle_mm_fault(mm, vma, address, flags);

if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779e1409..d9196c9f93d9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
is_write = error_code & ESR_DST;
#endif /* CONFIG_4xx || CONFIG_BOOKE */

- if (is_write)
- flags |= FAULT_FLAG_WRITE;
-
#ifdef CONFIG_PPC_ICSWX
/*
* we need to do this early because this "data storage
@@ -280,6 +277,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,

perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -408,6 +408,7 @@ good_area:
} else if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 047c3e4c59a2..416facec4a33 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem);
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 47b600e4b2c5..52238983527d 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
+ unsigned long flags = 0;
siginfo_t info;
int fault;

@@ -75,6 +76,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
if (in_atomic() || !mm)
goto bad_area_nosemaphore;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
@@ -95,18 +99,18 @@ good_area:
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
goto bad_area;
}

-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, write);
+ fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
@@ -167,15 +171,10 @@ no_context:
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;

do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28affa9..541dc6101508 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -400,9 +400,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
struct mm_struct *mm;
struct vm_area_struct * vma;
int fault;
- int write = error_code & FAULT_CODE_WRITE;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

tsk = current;
mm = tsk->mm;
@@ -476,6 +474,11 @@ good_area:

set_thread_fault_code(error_code);

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (error_code & FAULT_CODE_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 905832aa9e9e..a0ed182ae73c 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -21,7 +21,7 @@

extern int __atomic_add_return(int, atomic_t *);
extern int atomic_cmpxchg(atomic_t *, int, int);
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+extern int atomic_xchg(atomic_t *, int);
extern int __atomic_add_unless(atomic_t *, int, int);
extern void atomic_set(atomic_t *, int);

diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a02e3c2..ae0f9a7a314d 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -11,22 +11,14 @@
#ifndef __ARCH_SPARC_CMPXCHG__
#define __ARCH_SPARC_CMPXCHG__

-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
- __asm__ __volatile__("swap [%2], %0"
- : "=&r" (val)
- : "0" (val), "r" (m)
- : "memory");
- return val;
-}
-
+extern unsigned long __xchg_u32(volatile u32 *m, u32 new);
extern void __xchg_called_with_bad_pointer(void);

static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
{
switch (size) {
case 4:
- return xchg_u32(ptr, x);
+ return __xchg_u32(ptr, x);
}
__xchg_called_with_bad_pointer();
return x;
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa838861..55841c184e6d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -118,12 +118,18 @@ struct vio_disk_attr_info {
u8 vdisk_type;
#define VD_DISK_TYPE_SLICE 0x01 /* Slice in block device */
#define VD_DISK_TYPE_DISK 0x02 /* Entire block device */
- u16 resv1;
+ u8 vdisk_mtype; /* v1.1 */
+#define VD_MEDIA_TYPE_FIXED 0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD 0x02 /* CD Device */
+#define VD_MEDIA_TYPE_DVD 0x03 /* DVD Device */
+ u8 resv1;
u32 vdisk_block_size;
u64 operations;
- u64 vdisk_size;
+ u64 vdisk_size; /* v1.1 */
u64 max_xfer_size;
- u64 resv2[2];
+ u32 phys_block_size; /* v1.2 */
+ u32 resv2;
+ u64 resv3[1];
};

struct vio_disk_desc {
@@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr,
unsigned int ring_size)
{
return (dr->pending -
- ((dr->prod - dr->cons) & (ring_size - 1)));
+ ((dr->prod - dr->cons) & (ring_size - 1)) - 1);
}

#define VIO_MAX_TYPE_LEN 32
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 8f76f23dac38..f9c6813c132d 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
{
unsigned long csr_reg, csr, csr_error_bits;
irqreturn_t ret = IRQ_NONE;
- u16 stat;
+ u32 stat;

csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
csr = upa_readq(csr_reg);
@@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
pbm->name);
ret = IRQ_HANDLED;
}
- pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat);
+ pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
if (stat & (PCI_STATUS_PARITY |
PCI_STATUS_SIG_TARGET_ABORT |
PCI_STATUS_REC_TARGET_ABORT |
@@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
PCI_STATUS_SIG_SYSTEM_ERROR)) {
printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
pbm->name, stat);
- pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff);
+ pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
ret = IRQ_HANDLED;
}
return ret;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8565ecd7d48a..173964d5e948 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -821,13 +821,17 @@ void arch_send_call_function_single_ipi(int cpu)
void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
{
clear_softint(1 << irq);
+ irq_enter();
generic_smp_call_function_interrupt();
+ irq_exit();
}

void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
{
clear_softint(1 << irq);
+ irq_enter();
generic_smp_call_function_single_interrupt();
+ irq_exit();
}

static void tsb_sync(void *info)
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 1d32b54089aa..8f2f94d53434 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v)
}
EXPORT_SYMBOL(__atomic_add_return);

+int atomic_xchg(atomic_t *v, int new)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(ATOMIC_HASH(v), flags);
+ ret = v->counter;
+ v->counter = new;
+ spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
+ return ret;
+}
+EXPORT_SYMBOL(atomic_xchg);
+
int atomic_cmpxchg(atomic_t *v, int old, int new)
{
int ret;
@@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
return (unsigned long)prev;
}
EXPORT_SYMBOL(__cmpxchg_u32);
+
+unsigned long __xchg_u32(volatile u32 *ptr, u32 new)
+{
+ unsigned long flags;
+ u32 prev;
+
+ spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
+ prev = *ptr;
+ *ptr = new;
+ spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
+
+ return (unsigned long)prev;
+}
+EXPORT_SYMBOL(__xchg_u32);
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda205a2..59dbd4645725 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
unsigned long g2;
int from_user = !(regs->psr & PSR_PS);
int fault, code;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

if (text_fault)
address = regs->pc;
@@ -235,6 +234,11 @@ good_area:
goto bad_area;
}

+ if (from_user)
+ flags |= FAULT_FLAG_USER;
+ if (write)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write)
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
+ unsigned int flags = FAULT_FLAG_USER;
int code;

code = SEGV_MAPERR;
@@ -402,11 +407,12 @@ good_area:
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+ switch (handle_mm_fault(mm, vma, address, flags)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index ea83f82464da..3841a081beb3 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -323,7 +323,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
bad_kernel_pc(regs, address);
return;
}
- }
+ } else
+ flags |= FAULT_FLAG_USER;

/*
* If we're in an interrupt or have no user
@@ -426,13 +427,14 @@ good_area:
vma->vm_file != NULL)
set_thread_fault_code(fault_code |
FAULT_CODE_BLKCOMMIT);
+
+ flags |= FAULT_FLAG_WRITE;
} else {
/* Allow reads even for write-only mappings */
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}

- flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
fault = handle_mm_fault(mm, vma, address, flags);

if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 3d2b81c163a6..3ff289f422e6 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -280,8 +280,7 @@ static int handle_page_fault(struct pt_regs *regs,
if (!is_page_fault)
write = 1;

- flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

is_kernel_mode = (EX1_PL(regs->ex1) != USER_PL);

@@ -365,6 +364,9 @@ static int handle_page_fault(struct pt_regs *regs,
goto bad_area_nosemaphore;
}

+ if (!is_kernel_mode)
+ flags |= FAULT_FLAG_USER;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
@@ -425,12 +427,12 @@ good_area:
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!is_page_fault || !(vma->vm_flags & VM_READ))
goto bad_area;
}

- survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -568,15 +570,10 @@ no_context:
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
- pr_alert("VM: killing process %s\n", tsk->comm);
- if (!is_kernel_mode)
- do_group_exit(SIGKILL);
- goto no_context;
+ if (is_kernel_mode)
+ goto no_context;
+ pagefault_out_of_memory();
+ return 0;

do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 089f3987e273..5c3aef74237f 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
pmd_t *pmd;
pte_t *pte;
int err = -EFAULT;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

*code_out = SEGV_MAPERR;

@@ -42,6 +41,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
if (in_atomic())
goto out_nosemaphore;

+ if (is_user)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -58,12 +59,15 @@ retry:

good_area:
*code_out = SEGV_ACCERR;
- if (is_write && !(vma->vm_flags & VM_WRITE))
- goto out;
-
- /* Don't require VM_READ|VM_EXEC for write faults! */
- if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
- goto out;
+ if (is_write) {
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out;
+ flags |= FAULT_FLAG_WRITE;
+ } else {
+ /* Don't require VM_READ|VM_EXEC for write faults! */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto out;
+ }

do {
int fault;
@@ -124,6 +128,8 @@ out_of_memory:
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!is_user)
+ goto out_nosemaphore;
pagefault_out_of_memory();
return 0;
}
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index f9b5c10bccee..0dc922dba915 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

tsk = current;
mm = tsk->mm;
@@ -222,6 +221,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (in_atomic() || !mm)
goto no_context;

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (!(fsr ^ 0x12))
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -278,6 +282,13 @@ retry:
(VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;

+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -288,13 +299,6 @@ retry:
return 0;
}

- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b45ac6affa9c..6d6bb6f4fd43 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2172,6 +2172,9 @@ __init int intel_pmu_init(void)
case 62: /* IvyBridge EP */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ /* dTLB-load-misses on IVB is different than SNB */
+ hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));

diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 29a8120e6fe8..baa61e7370b7 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1475,15 +1475,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
force_sig_info(SIGTRAP, &info, tsk);
}

-
-#ifdef CONFIG_X86_32
-# define IS_IA32 1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32 is_compat_task()
-#else
-# define IS_IA32 0
-#endif
-
/*
* We must return the syscall number to actually look up in the table.
* This can be -1L to skip running any syscall at all.
@@ -1521,7 +1512,7 @@ long syscall_trace_enter(struct pt_regs *regs)
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->orig_ax);

- if (IS_IA32)
+ if (is_ia32_task())
audit_syscall_entry(AUDIT_ARCH_I386,
regs->orig_ax,
regs->bx, regs->cx,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 684f46dc87de..adfc30d9f9f4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4834,7 +4834,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)

++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
- if (!is_guest_mode(vcpu)) {
+ if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c1e9e4cbbd76..d8b1ff68dbb9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}

-static noinline int
+static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
unsigned long address, unsigned int fault)
{
- /*
- * Pagefault was interrupted by SIGKILL. We have no reason to
- * continue pagefault.
- */
- if (fatal_signal_pending(current)) {
- if (!(fault & VM_FAULT_RETRY))
- up_read(&current->mm->mmap_sem);
- if (!(error_code & PF_USER))
- no_context(regs, error_code, address, 0, 0);
- return 1;
+ if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+ up_read(&current->mm->mmap_sem);
+ no_context(regs, error_code, address, 0, 0);
+ return;
}
- if (!(fault & VM_FAULT_ERROR))
- return 0;

if (fault & VM_FAULT_OOM) {
/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
up_read(&current->mm->mmap_sem);
no_context(regs, error_code, address,
SIGSEGV, SEGV_MAPERR);
- return 1;
+ return;
}

up_read(&current->mm->mmap_sem);
@@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
else
BUG();
}
- return 1;
}

static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1017,9 +1008,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
unsigned long address;
struct mm_struct *mm;
int fault;
- int write = error_code & PF_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

tsk = current;
mm = tsk->mm;
@@ -1089,6 +1078,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
if (user_mode_vm(regs)) {
local_irq_enable();
error_code |= PF_USER;
+ flags |= FAULT_FLAG_USER;
} else {
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
@@ -1113,6 +1103,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
return;
}

+ if (error_code & PF_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in
@@ -1191,9 +1184,17 @@ good_area:
*/
fault = handle_mm_fault(mm, vma, address, flags);

- if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
- if (mm_fault_error(regs, error_code, address, fault))
- return;
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}

/*
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fec6990..513effd48060 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1)
#define __NR_pivot_root 175
__SYSCALL(175, sys_pivot_root, 2)
#define __NR_umount 176
-__SYSCALL(176, sys_umount, 2)
+__SYSCALL(176, sys_oldumount, 1)
+#define __ARCH_WANT_SYS_OLDUMOUNT
#define __NR_swapoff 177
__SYSCALL(177, sys_swapoff, 1)
#define __NR_sync 178
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8db170f..70fa7bc42b4a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@ void do_page_fault(struct pt_regs *regs)
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif

+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c3f09505f795..64150a9ffff3 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,6 +61,7 @@ enum board_ids {
/* board IDs by feature in alphabetical order */
board_ahci,
board_ahci_ign_iferr,
+ board_ahci_nomsi,
board_ahci_noncq,
board_ahci_nosntf,
board_ahci_yes_fbs,
@@ -120,6 +121,13 @@ static const struct ata_port_info ahci_port_info[] = {
.udma_mask = ATA_UDMA6,
.port_ops = &ahci_ops,
},
+ [board_ahci_nomsi] = {
+ AHCI_HFLAGS (AHCI_HFLAG_NO_MSI),
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_ops,
+ },
[board_ahci_noncq] = {
AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ),
.flags = AHCI_FLAG_COMMON,
@@ -312,6 +320,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
{ PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */

/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -474,10 +487,10 @@ static const struct pci_device_id ahci_pci_tbl[] = {
{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */

/*
- * Samsung SSDs found on some macbooks. NCQ times out.
- * https://bugzilla.kernel.org/show_bug.cgi?id=60731
+ * Samsung SSDs found on some macbooks. NCQ times out if MSI is
+ * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731
*/
- { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq },
+ { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi },

/* Enmotus */
{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb6963d..0ebadf93b6c5 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/genhd.h>
+#include <linux/cdrom.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
@@ -22,8 +23,8 @@

#define DRV_MODULE_NAME "sunvdc"
#define PFX DRV_MODULE_NAME ": "
-#define DRV_MODULE_VERSION "1.0"
-#define DRV_MODULE_RELDATE "June 25, 2007"
+#define DRV_MODULE_VERSION "1.1"
+#define DRV_MODULE_RELDATE "February 13, 2013"

static char version[] =
DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_VERSION);

-#define VDC_TX_RING_SIZE 256
+#define VDC_TX_RING_SIZE 512

#define WAITING_FOR_LINK_UP 0x01
#define WAITING_FOR_TX_SPACE 0x02
@@ -65,11 +66,9 @@ struct vdc_port {
u64 operations;
u32 vdisk_size;
u8 vdisk_type;
+ u8 vdisk_mtype;

char disk_name[32];
-
- struct vio_disk_geom geom;
- struct vio_disk_vtoc label;
};

static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
@@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)

/* Ordered from largest major to lowest */
static struct vio_version vdc_versions[] = {
+ { .major = 1, .minor = 1 },
{ .major = 1, .minor = 0 },
};

+static inline int vdc_version_supported(struct vdc_port *port,
+ u16 major, u16 minor)
+{
+ return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
#define VDCBLK_NAME "vdisk"
static int vdc_major;
#define PARTITION_SHIFT 3
@@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct gendisk *disk = bdev->bd_disk;
- struct vdc_port *port = disk->private_data;
+ sector_t nsect = get_capacity(disk);
+ sector_t cylinders = nsect;

- geo->heads = (u8) port->geom.num_hd;
- geo->sectors = (u8) port->geom.num_sec;
- geo->cylinders = port->geom.num_cyl;
+ geo->heads = 0xff;
+ geo->sectors = 0x3f;
+ sector_div(cylinders, geo->heads * geo->sectors);
+ geo->cylinders = cylinders;
+ if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+ geo->cylinders = 0xffff;

return 0;
}

+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned command, unsigned long argument)
+{
+ int i;
+ struct gendisk *disk;
+
+ switch (command) {
+ case CDROMMULTISESSION:
+ pr_debug(PFX "Multisession CDs not supported\n");
+ for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+ if (put_user(0, (char __user *)(argument + i)))
+ return -EFAULT;
+ return 0;
+
+ case CDROM_GET_CAPABILITY:
+ disk = bdev->bd_disk;
+
+ if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+ return 0;
+ return -EINVAL;
+
+ default:
+ pr_debug(PFX "ioctl %08x not supported\n", command);
+ return -EINVAL;
+ }
+}
+
static const struct block_device_operations vdc_fops = {
.owner = THIS_MODULE,
.getgeo = vdc_getgeo,
+ .ioctl = vdc_ioctl,
};

static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
struct vio_disk_attr_info *pkt = arg;

viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
- "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+ "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
pkt->tag.stype, pkt->operations,
- pkt->vdisk_size, pkt->vdisk_type,
+ pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
pkt->xfer_mode, pkt->vdisk_block_size,
pkt->max_xfer_size);

@@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
}

port->operations = pkt->operations;
- port->vdisk_size = pkt->vdisk_size;
port->vdisk_type = pkt->vdisk_type;
+ if (vdc_version_supported(port, 1, 1)) {
+ port->vdisk_size = pkt->vdisk_size;
+ port->vdisk_mtype = pkt->vdisk_mtype;
+ }
if (pkt->max_xfer_size < port->max_xfer_size)
port->max_xfer_size = pkt->max_xfer_size;
port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,

__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);

- if (blk_queue_stopped(port->disk->queue))
+ /* restart blk queue when ring is half emptied */
+ if (blk_queue_stopped(port->disk->queue) &&
+ vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
blk_start_queue(port->disk->queue);
}

@@ -388,12 +435,6 @@ static int __send_request(struct request *req)
for (i = 0; i < nsg; i++)
len += sg[i].length;

- if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
- blk_stop_queue(port->disk->queue);
- err = -ENOMEM;
- goto out;
- }
-
desc = vio_dring_cur(dr);

err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +474,32 @@ static int __send_request(struct request *req)
port->req_id++;
dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
}
-out:

return err;
}

-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
{
- while (1) {
- struct request *req = blk_fetch_request(q);
+ struct request *req;

- if (!req)
- break;
+ while ((req = blk_peek_request(rq)) != NULL) {
+ struct vdc_port *port;
+ struct vio_dring_state *dr;

- if (__send_request(req) < 0)
- __blk_end_request_all(req, -EIO);
+ port = req->rq_disk->private_data;
+ dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+ if (unlikely(vdc_tx_dring_avail(dr) < 1))
+ goto wait;
+
+ blk_start_request(req);
+
+ if (__send_request(req) < 0) {
+ blk_requeue_request(rq, req);
+wait:
+ /* Avoid pointless unplugs. */
+ blk_stop_queue(rq);
+ break;
+ }
}
}

@@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port)
if (comp.err)
return comp.err;

- err = generic_request(port, VD_OP_GET_VTOC,
- &port->label, sizeof(port->label));
- if (err < 0) {
- printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err);
- return err;
- }
-
- err = generic_request(port, VD_OP_GET_DISKGEOM,
- &port->geom, sizeof(port->geom));
- if (err < 0) {
- printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
- "error %d\n", err);
- return err;
+ if (vdc_version_supported(port, 1, 1)) {
+ /* vdisk_size should be set during the handshake, if it wasn't
+ * then the underlying disk is reserved by another system
+ */
+ if (port->vdisk_size == -1)
+ return -ENODEV;
+ } else {
+ struct vio_disk_geom geom;
+
+ err = generic_request(port, VD_OP_GET_DISKGEOM,
+ &geom, sizeof(geom));
+ if (err < 0) {
+ printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+ "error %d\n", err);
+ return err;
+ }
+ port->vdisk_size = ((u64)geom.num_cyl *
+ (u64)geom.num_hd *
+ (u64)geom.num_sec);
}

- port->vdisk_size = ((u64)port->geom.num_cyl *
- (u64)port->geom.num_hd *
- (u64)port->geom.num_sec);
-
q = blk_init_queue(do_vdc_request, &port->vio.lock);
if (!q) {
printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port)

port->disk = g;

+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(q, PAGE_SIZE);
+
blk_queue_max_segments(q, port->ring_cookies);
blk_queue_max_hw_sectors(q, port->max_xfer_size);
g->major = vdc_major;
@@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port)

set_capacity(g, port->vdisk_size);

- printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+ if (vdc_version_supported(port, 1, 1)) {
+ switch (port->vdisk_mtype) {
+ case VD_MEDIA_TYPE_CD:
+ pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_DVD:
+ pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_FIXED:
+ pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+ break;
+ }
+ }
+
+ pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
g->disk_name,
- port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+ port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+ port->vio.ver.major, port->vio.ver.minor);

add_disk(g);

@@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
else
snprintf(port->disk_name, sizeof(port->disk_name),
VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+ port->vdisk_size = -1;

err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index ac1b43a04285..4f73c727a97a 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client,
_IOC_SIZE(cmd) > sizeof(buffer))
return -ENOTTY;

- if (_IOC_DIR(cmd) == _IOC_READ)
- memset(&buffer, 0, _IOC_SIZE(cmd));
+ memset(&buffer, 0, sizeof(buffer));

if (_IOC_DIR(cmd) & _IOC_WRITE)
if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd)))
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e62a9ce3e4dc..ead08a49bec0 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2379,6 +2379,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
}
} else {
tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 7c5d72a6a26a..19e070f16e6b 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -873,7 +873,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse)
{
struct alps_data *priv = psmouse->private;

- if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */
+ /*
+ * Check if we are dealing with a bare PS/2 packet, presumably from
+ * a device connected to the external PS/2 port. Because bare PS/2
+ * protocol does not have enough constant bits to self-synchronize
+ * properly we only do this if the device is fully synchronized.
+ */
+ if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) {
if (psmouse->pktcnt == 3) {
alps_report_bare_ps2_packet(psmouse, psmouse->packet,
true);
@@ -1816,6 +1822,9 @@ int alps_init(struct psmouse *psmouse)
/* We are having trouble resyncing ALPS touchpads so disable it for now */
psmouse->resync_time = 0;

+ /* Allow 2 invalid packets without resetting device */
+ psmouse->resetafter = psmouse->pktsize * 2;
+
return 0;

init_fail:
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 2dea49c4279e..84cddccc0249 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -785,8 +785,7 @@ struct dm_raid_superblock {
__le32 layout;
__le32 stripe_sectors;

- __u8 pad[452]; /* Round struct to 512 bytes. */
- /* Always set to 0 when writing. */
+ /* Remainder of a logical block is zero-filled when writing (see super_sync()). */
} __packed;

static int read_disk_sb(struct md_rdev *rdev, int size)
@@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
test_bit(Faulty, &(rs->dev[i].rdev.flags)))
failed_devices |= (1ULL << i);

- memset(sb, 0, sizeof(*sb));
+ memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));

sb->magic = cpu_to_le32(DM_RAID_MAGIC);
sb->features = cpu_to_le32(0); /* No features yet */
@@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
uint64_t events_sb, events_refsb;

rdev->sb_start = 0;
- rdev->sb_size = sizeof(*sb);
+ rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
+ if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
+ DMERR("superblock size of a logical block is no longer valid");
+ return -EINVAL;
+ }

ret = read_disk_sb(rdev, rdev->sb_size);
if (ret)
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 37d367bb9aa8..bf2b80d5c470 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -42,6 +42,12 @@ struct btree_node {
} __packed;


+/*
+ * Locks a block using the btree node validator.
+ */
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+ struct dm_block **result);
+
void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
struct dm_btree_value_type *vt);

diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index cf9fd676ae44..1b5e13ec7f96 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = {

/*----------------------------------------------------------------*/

-static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
struct dm_block **result)
{
return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 35865425e4b4..0a7592e88811 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -812,22 +812,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_highest_key);
* FIXME: We shouldn't use a recursive algorithm when we have limited stack
* space. Also this only works for single level trees.
*/
-static int walk_node(struct ro_spine *s, dm_block_t block,
+static int walk_node(struct dm_btree_info *info, dm_block_t block,
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
int r;
unsigned i, nr;
+ struct dm_block *node;
struct btree_node *n;
uint64_t keys;

- r = ro_step(s, block);
- n = ro_node(s);
+ r = bn_read_lock(info, block, &node);
+ if (r)
+ return r;
+
+ n = dm_block_data(node);

nr = le32_to_cpu(n->header.nr_entries);
for (i = 0; i < nr; i++) {
if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) {
- r = walk_node(s, value64(n, i), fn, context);
+ r = walk_node(info, value64(n, i), fn, context);
if (r)
goto out;
} else {
@@ -839,7 +843,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block,
}

out:
- ro_pop(s);
+ dm_tm_unlock(info->tm, node);
return r;
}

@@ -847,15 +851,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root,
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
- int r;
- struct ro_spine spine;
-
BUG_ON(info->levels > 1);
-
- init_ro_spine(&spine, info);
- r = walk_node(&spine, root, fn, context);
- exit_ro_spine(&spine);
-
- return r;
+ return walk_node(info, root, fn, context);
}
EXPORT_SYMBOL_GPL(dm_btree_walk);
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 5c45c9d0712d..9c29552aedec 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc
0x00, 0x00, 0x00, 0x00,
0x00, 0x00 };

+ if (cmd->msg_len > sizeof(b) - 4)
+ return -EINVAL;
+
memcpy(&b[4], cmd->msg, cmd->msg_len);

state->config->send_command(fe, 0x72,
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 99cc0b07a713..0513ea0906dd 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev)

dev_dbg(dev, "Device probe\n");

- strncpy(id.name, dev_name(dev), MEI_CL_NAME_SIZE);
+ strlcpy(id.name, dev_name(dev), sizeof(id.name));

return driver->probe(device, &id);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4e6877a032a8..bd8800c85525 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -191,6 +191,39 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
}

+static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
+ struct mlx4_en_tx_ring *ring, int index,
+ u8 owner)
+{
+ __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
+ struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
+ struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
+ void *end = ring->buf + ring->buf_size;
+ __be32 *ptr = (__be32 *)tx_desc;
+ int i;
+
+ /* Optimize the common case when there are no wraparounds */
+ if (likely((void *)tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
+ /* Stamp the freed descriptor */
+ for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+ i += STAMP_STRIDE) {
+ *ptr = stamp;
+ ptr += STAMP_DWORDS;
+ }
+ } else {
+ /* Stamp the freed descriptor */
+ for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+ i += STAMP_STRIDE) {
+ *ptr = stamp;
+ ptr += STAMP_DWORDS;
+ if ((void *)ptr >= end) {
+ ptr = ring->buf;
+ stamp ^= cpu_to_be32(0x80000000);
+ }
+ }
+ }
+}
+

static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
@@ -205,8 +238,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
void *end = ring->buf + ring->buf_size;
int frags = skb_shinfo(skb)->nr_frags;
int i;
- __be32 *ptr = (__be32 *)tx_desc;
- __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
struct skb_shared_hwtstamps hwts;

if (timestamp) {
@@ -232,12 +263,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
skb_frag_size(frag), PCI_DMA_TODEVICE);
}
}
- /* Stamp the freed descriptor */
- for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
- *ptr = stamp;
- ptr += STAMP_DWORDS;
- }
-
} else {
if (!tx_info->inl) {
if ((void *) data >= end) {
@@ -263,16 +288,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
++data;
}
}
- /* Stamp the freed descriptor */
- for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
- *ptr = stamp;
- ptr += STAMP_DWORDS;
- if ((void *) ptr >= end) {
- ptr = ring->buf;
- stamp ^= cpu_to_be32(0x80000000);
- }
- }
-
}
dev_kfree_skb_any(skb);
return tx_info->nr_txbb;
@@ -318,8 +333,9 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
struct mlx4_cqe *cqe;
u16 index;
- u16 new_index, ring_index;
+ u16 new_index, ring_index, stamp_index;
u32 txbbs_skipped = 0;
+ u32 txbbs_stamp = 0;
u32 cons_index = mcq->cons_index;
int size = cq->size;
u32 size_mask = ring->size_mask;
@@ -335,6 +351,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
index = cons_index & size_mask;
cqe = &buf[(index << factor) + factor];
ring_index = ring->cons & size_mask;
+ stamp_index = ring_index;

/* Process all completed CQEs */
while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
@@ -359,6 +376,12 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
priv, ring, ring_index,
!!((ring->cons + txbbs_skipped) &
ring->size), timestamp);
+
+ mlx4_en_stamp_wqe(priv, ring, stamp_index,
+ !!((ring->cons + txbbs_stamp) &
+ ring->size));
+ stamp_index = ring_index;
+ txbbs_stamp = txbbs_skipped;
packets++;
bytes += ring->tx_info[ring_index].nr_bytes;
} while (ring_index != new_index);
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 398faff8be7a..ade8bdfc03af 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
spin_lock_irqsave(&port->vio.lock, flags);

dr = &port->vio.drings[VIO_DRIVER_TX_RING];
- if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+ if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
if (!netif_queue_stopped(dev)) {
netif_stop_queue(dev);

@@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
dev->stats.tx_bytes += skb->len;

dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
- if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+ if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
netif_stop_queue(dev);
if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
netif_wake_queue(dev);
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 9e56eb479a4f..2d255ba911d5 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -625,6 +625,8 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
if (skb->ip_summed == CHECKSUM_PARTIAL) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
vnet_hdr->csum_start = skb_checksum_start_offset(skb);
+ if (vlan_tx_tag_present(skb))
+ vnet_hdr->csum_start += VLAN_HLEN;
vnet_hdr->csum_offset = skb->csum_offset;
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 72d2ecce0b8d..d8df1d9b0de3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -489,6 +489,7 @@ enum iwl_trans_state {
* Set during transport allocation.
* @hw_id_str: a string with info about HW ID. Set during transport allocation.
* @pm_support: set to true in start_hw if link pm is supported
+ * @ltr_enabled: set to true if the LTR is enabled
* @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
* The user should use iwl_trans_{alloc,free}_tx_cmd.
* @dev_cmd_headroom: room needed for the transport's private use before the
@@ -513,6 +514,7 @@ struct iwl_trans {
u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;

bool pm_support;
+ bool ltr_enabled;

/* The following fields are internal only */
struct kmem_cache *dev_cmd_pool;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
index 81fe45f46be7..ac38ecf13c18 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
@@ -67,7 +67,40 @@
/* Power Management Commands, Responses, Notifications */

/**
- * enum iwl_scan_flags - masks for power table command flags
+ * enum iwl_ltr_config_flags - masks for LTR config command flags
+ * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status
+ * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow
+ * memory access
+ * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR
+ * reg change
+ * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from
+ * D0 to D3
+ * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register
+ * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register
+ * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD
+ */
+enum iwl_ltr_config_flags {
+ LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0),
+ LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1),
+ LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2),
+ LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3),
+ LTR_CFG_FLAG_SW_SET_SHORT = BIT(4),
+ LTR_CFG_FLAG_SW_SET_LONG = BIT(5),
+ LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6),
+};
+
+/**
+ * struct iwl_ltr_config_cmd - configures the LTR
+ * @flags: See %enum iwl_ltr_config_flags
+ */
+struct iwl_ltr_config_cmd {
+ __le32 flags;
+ __le32 static_long;
+ __le32 static_short;
+} __packed;
+
+/**
+ * enum iwl_power_flags - masks for power table command flags
* @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off
* receiver and transmitter. '0' - does not allow.
* @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index c6384555aab4..4b6730db42a5 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -138,6 +138,7 @@ enum {

/* Power */
POWER_TABLE_CMD = 0x77,
+ LTR_CONFIG = 0xee,

/* Scanning */
SCAN_REQUEST_CMD = 0x80,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index e18c92dd60ec..d250d451fd01 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -443,6 +443,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
if (ret)
goto error;

+ if (mvm->trans->ltr_enabled) {
+ struct iwl_ltr_config_cmd cmd = {
+ .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE),
+ };
+
+ WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
+ sizeof(cmd), &cmd));
+ }
+
IWL_DEBUG_INFO(mvm, "RT uCode started.\n");

return 0;
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index 388c8a914960..649d301cfa2a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -293,6 +293,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = {
CMD(BT_PROFILE_NOTIFICATION),
CMD(BT_CONFIG),
CMD(MCAST_FILTER_CMD),
+ CMD(LTR_CONFIG),
};
#undef CMD

diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index ff04135d37af..6a5eb2b29418 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -116,11 +116,13 @@ static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)

/* PCI registers */
#define PCI_CFG_RETRY_TIMEOUT 0x041
+#define PCI_EXP_DEVCTL2_LTR_EN 0x0400

static void iwl_pcie_apm_config(struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
u16 lctl;
+ u16 cap;

/*
* HW bug W/A for instability in PCIe bus L0S->L1 transition.
@@ -131,16 +133,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans)
* power savings, even without L1.
*/
pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
- if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
- /* L1-ASPM enabled; disable(!) L0S */
+ if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
- dev_info(trans->dev, "L1 Enabled; Disabling L0S\n");
- } else {
- /* L1-ASPM disabled; enable(!) L0S */
+ else
iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
- dev_info(trans->dev, "L1 Disabled; Enabling L0S\n");
- }
trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
+
+ pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
+ trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN;
+ dev_info(trans->dev, "L1 %sabled - LTR %sabled\n",
+ (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis",
+ trans->ltr_enabled ? "En" : "Dis");
}

/*
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index fa9a2171cc13..b264d8fe1908 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context)
const struct key_entry *key;
int reported_key;
u16 *buffer_entry = (u16 *)obj->buffer.pointer;
+ int buffer_size = obj->buffer.length/2;

- if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
+ if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) {
pr_info("Received unknown WMI event (0x%x)\n",
buffer_entry[1]);
kfree(obj);
return;
}

- if (dell_new_hk_type || buffer_entry[1] == 0x0)
+ if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0))
reported_key = (int)buffer_entry[2];
- else
+ else if (buffer_size >= 2)
reported_key = (int)buffer_entry[1] & 0xffff;
+ else {
+ pr_info("Received unknown WMI event\n");
+ kfree(obj);
+ return;
+ }

key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
reported_key);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 287667c20c6a..62ed744bbe06 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -1206,8 +1206,8 @@ static void complete_scsi_command(struct CommandList *cp)
scsi_set_resid(cmd, ei->ResidualCnt);

if (ei->CommandStatus == 0) {
- cmd->scsi_done(cmd);
cmd_free(h, cp);
+ cmd->scsi_done(cmd);
return;
}

@@ -1380,8 +1380,8 @@ static void complete_scsi_command(struct CommandList *cp)
dev_warn(&h->pdev->dev, "cp %p returned unknown status %x\n",
cp, ei->CommandStatus);
}
- cmd->scsi_done(cmd);
cmd_free(h, cp);
+ cmd->scsi_done(cmd);
}

static void hpsa_pci_unmap(struct pci_dev *pdev,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f43de1e56420..3668b1b23b5a 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1689,8 +1689,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost)
* is no point trying to lock the door of an off-line device.
*/
shost_for_each_device(sdev, shost) {
- if (scsi_device_online(sdev) && sdev->locked)
+ if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) {
scsi_eh_lock_door(sdev);
+ sdev->was_reset = 0;
+ }
}

/*
diff --git a/fs/ioprio.c b/fs/ioprio.c
index e50170ca7c33..31666c92b46a 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -157,14 +157,16 @@ out:

int ioprio_best(unsigned short aprio, unsigned short bprio)
{
- unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
- unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+ unsigned short aclass;
+ unsigned short bclass;

- if (aclass == IOPRIO_CLASS_NONE)
- aclass = IOPRIO_CLASS_BE;
- if (bclass == IOPRIO_CLASS_NONE)
- bclass = IOPRIO_CLASS_BE;
+ if (!ioprio_valid(aprio))
+ aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+ if (!ioprio_valid(bprio))
+ bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);

+ aclass = IOPRIO_PRIO_CLASS(aprio);
+ bclass = IOPRIO_PRIO_CLASS(bprio);
if (aclass == bclass)
return min(aprio, bprio);
if (aclass > bclass)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 4b49a8c6ccad..ef0c394b7bf5 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -108,6 +108,8 @@ again:
continue;
if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
continue;
+ if (!nfs4_valid_open_stateid(state))
+ continue;
if (!nfs4_stateid_match(&state->stateid, stateid))
continue;
get_nfs_open_context(ctx);
@@ -175,7 +177,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
{
int res = 0;

- res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+ if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ res = nfs4_proc_delegreturn(inode,
+ delegation->cred,
+ &delegation->stateid,
+ issync);
nfs_free_delegation(delegation);
return res;
}
@@ -361,11 +367,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
{
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
struct nfs_inode *nfsi = NFS_I(inode);
- int err;
+ int err = 0;

if (delegation == NULL)
return 0;
do {
+ if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ break;
err = nfs_delegation_claim_opens(inode, &delegation->stateid);
if (!issync || err != -EAGAIN)
break;
@@ -586,10 +594,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
rcu_read_unlock();
}

+static void nfs_revoke_delegation(struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+ rcu_read_lock();
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation != NULL) {
+ set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+ nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+ }
+ rcu_read_unlock();
+}
+
void nfs_remove_bad_delegation(struct inode *inode)
{
struct nfs_delegation *delegation;

+ nfs_revoke_delegation(inode);
delegation = nfs_inode_detach_delegation(inode);
if (delegation) {
nfs_inode_find_state_and_recover(inode, &delegation->stateid);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9a79c7a99d6d..e02b090ab9da 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
NFS_DELEGATION_RETURN_IF_CLOSED,
NFS_DELEGATION_REFERENCED,
NFS_DELEGATION_RETURNING,
+ NFS_DELEGATION_REVOKED,
};

int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0bd7a55a5f07..725e87538c98 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -180,6 +180,7 @@ static void nfs_direct_req_free(struct kref *kref)
{
struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);

+ nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
if (dreq->l_ctx != NULL)
nfs_put_lock_context(dreq->l_ctx);
if (dreq->ctx != NULL)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index cd4b9073dd20..e9be01b2cc5a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -519,7 +519,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
- int err;
+ int err = 0;

/* Flush out writes to the server in order to update c/mtime. */
if (S_ISREG(inode->i_mode)) {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 69fc437be661..78787948f69d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1416,7 +1416,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
nfs_inode_find_state_and_recover(state->inode,
stateid);
nfs4_schedule_stateid_recovery(server, state);
- return 0;
+ return -EAGAIN;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -1845,6 +1845,28 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
return ret;
}

+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+ nfs_remove_bad_delegation(state->inode);
+ write_seqlock(&state->seqlock);
+ nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+ write_sequnlock(&state->seqlock);
+ clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+ if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+ nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+ /* NFSv4.0 doesn't allow for delegation recovery on open expire */
+ nfs40_clear_delegation_stateid(state);
+ return nfs4_open_expired(sp, state);
+}
+
#if defined(CONFIG_NFS_V4_1)
static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
{
@@ -6974,7 +6996,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
.state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
- .recover_open = nfs4_open_expired,
+ .recover_open = nfs40_open_expired,
.recover_lock = nfs4_lock_expired,
.establish_clid = nfs4_init_clientid,
.get_clid_cred = nfs4_get_setclientid_cred,
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7279b94c01da..91aa89e1aaa0 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -285,7 +285,7 @@ extern struct clocksource* clocksource_get_next(void);
extern void clocksource_change_rating(struct clocksource *cs, int rating);
extern void clocksource_suspend(void);
extern void clocksource_resume(void);
-extern struct clocksource * __init __weak clocksource_default_clock(void);
+extern struct clocksource * __init clocksource_default_clock(void);
extern void clocksource_mark_unstable(struct clocksource *cs);

extern void
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index c6e091bf39a5..bdfc95bddde9 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -283,7 +283,7 @@ struct kgdb_io {

extern struct kgdb_arch arch_kgdb_ops;

-extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs);
+extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);

#ifdef CONFIG_SERIAL_KGDB_NMI
extern int kgdb_register_nmi_console(void);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d6183f06d8c1..a3b4812f494f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -124,6 +124,25 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
extern void mem_cgroup_replace_page_cache(struct page *oldpage,
struct page *newpage);

+static inline void mem_cgroup_oom_enable(void)
+{
+ WARN_ON(current->memcg_oom.may_oom);
+ current->memcg_oom.may_oom = 1;
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+ WARN_ON(!current->memcg_oom.may_oom);
+ current->memcg_oom.may_oom = 0;
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return p->memcg_oom.memcg;
+}
+
+bool mem_cgroup_oom_synchronize(bool wait);
+
#ifdef CONFIG_MEMCG_SWAP
extern int do_swap_account;
#endif
@@ -347,6 +366,24 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
{
}

+static inline void mem_cgroup_oom_enable(void)
+{
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(bool wait)
+{
+ return false;
+}
+
static inline void mem_cgroup_inc_page_stat(struct page *page,
enum mem_cgroup_page_stat_item idx)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7da14357aa76..d4cdac903468 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -167,6 +167,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */
#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */
#define FAULT_FLAG_TRIED 0x40 /* second try */
+#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */

/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 104b62f23ee0..54e351aa4d2e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1184,11 +1184,22 @@ struct nfs41_free_stateid_res {
unsigned int status;
};

+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+ kfree(cinfo->buckets);
+}
+
#else

struct pnfs_ds_commit_info {
};

+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+}
+
#endif /* CONFIG_NFS_V4_1 */

struct nfs_page;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f87e9a8d364f..00c1d4f45072 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1411,6 +1411,12 @@ struct task_struct {
unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
} memcg_batch;
unsigned int memcg_kmem_skip_account;
+ struct memcg_oom_info {
+ struct mem_cgroup *memcg;
+ gfp_t gfp_mask;
+ int order;
+ unsigned int may_oom:1;
+ } memcg_oom;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
atomic_t ptrace_bp_refcnt;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index cd89510eab2a..845ab6decc45 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -540,6 +540,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat
asoc->pmtu_pending = 0;
}

+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+ return !list_empty(&chunk->list);
+}
+
/* Walk through a list of TLV parameters. Don't trust the
* individual parameter lengths and instead depend on
* the chunk length to indicate when to stop. Make sure
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2a82d1384706..c4c9458f37cd 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -255,9 +255,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *,
int, __be16);
struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
- struct sctp_paramhdr *param_hdr, void *chunk_end,
- struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+ struct sctp_chunk *chunk, bool addr_param_needed,
+ struct sctp_paramhdr **errp);
struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
struct sctp_chunk *asconf);
int sctp_process_asconf_ack(struct sctp_association *asoc,
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index 5dda450eb55b..2ec9fbcd06f9 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -6,6 +6,8 @@

#define XT_BPF_MAX_NUM_INSTR 64

+struct sk_filter;
+
struct xt_bpf_info {
__u16 bpf_program_num_elem;
struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index b0e99deb6d05..a0f0ab2ac2a8 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
- size_t lenp_bef = *lenp;
int oldval;
int rc;

@@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,

rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);

- if (write && !rc && lenp_bef == *lenp) {
+ if (write && !rc) {
int newval = *((int *)(ipc_table.data));
/*
* The file "auto_msgmni" has correctly been set.
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307dc9453..00c4459f76df 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
chunk->owners[i].index = i;
}
fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+ chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0b4733447151..3f63ea6464ca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -39,6 +39,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
#include <linux/cgroup.h>
+#include <linux/compat.h>

#include "internal.h"

@@ -3490,6 +3491,25 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return 0;
}

+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ switch (_IOC_NR(cmd)) {
+ case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+ /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+ if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+ cmd &= ~IOCSIZE_MASK;
+ cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+ }
+ break;
+ }
+ return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
int perf_event_task_enable(void)
{
struct perf_event *event;
@@ -3961,7 +3981,7 @@ static const struct file_operations perf_fops = {
.read = perf_read,
.poll = perf_poll,
.unlocked_ioctl = perf_ioctl,
- .compat_ioctl = perf_ioctl,
+ .compat_ioctl = perf_compat_ioctl,
.mmap = perf_mmap,
.fasync = perf_fasync,
};
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f45e21ab9cea..eaa3accb01e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -302,6 +302,7 @@ struct mem_cgroup {

bool oom_lock;
atomic_t under_oom;
+ atomic_t oom_wakeups;

atomic_t refcnt;

@@ -2075,15 +2076,18 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
return total;
}

+static DEFINE_SPINLOCK(memcg_oom_lock);
+
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
- * Has to be called with memcg_oom_lock
*/
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter, *failed = NULL;

+ spin_lock(&memcg_oom_lock);
+
for_each_mem_cgroup_tree(iter, memcg) {
if (iter->oom_lock) {
/*
@@ -2097,33 +2101,33 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
iter->oom_lock = true;
}

- if (!failed)
- return true;
-
- /*
- * OK, we failed to lock the whole subtree so we have to clean up
- * what we set up to the failing subtree
- */
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter == failed) {
- mem_cgroup_iter_break(memcg, iter);
- break;
+ if (failed) {
+ /*
+ * OK, we failed to lock the whole subtree so we have
+ * to clean up what we set up to the failing subtree
+ */
+ for_each_mem_cgroup_tree(iter, memcg) {
+ if (iter == failed) {
+ mem_cgroup_iter_break(memcg, iter);
+ break;
+ }
+ iter->oom_lock = false;
}
- iter->oom_lock = false;
}
- return false;
+
+ spin_unlock(&memcg_oom_lock);
+
+ return !failed;
}

-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;

+ spin_lock(&memcg_oom_lock);
for_each_mem_cgroup_tree(iter, memcg)
iter->oom_lock = false;
- return 0;
+ spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
@@ -2147,7 +2151,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
atomic_add_unless(&iter->under_oom, -1, 0);
}

-static DEFINE_SPINLOCK(memcg_oom_lock);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);

struct oom_wait_info {
@@ -2177,6 +2180,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait,

static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
+ atomic_inc(&memcg->oom_wakeups);
/* for filtering, pass "memcg" as argument. */
__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
@@ -2187,57 +2191,97 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
memcg_wakeup_oom(memcg);
}

-/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+{
+ if (!current->memcg_oom.may_oom)
+ return;
+ /*
+ * We are in the middle of the charge context here, so we
+ * don't want to block when potentially sitting on a callstack
+ * that holds all kinds of filesystem and mm locks.
+ *
+ * Also, the caller may handle a failed allocation gracefully
+ * (like optional page cache readahead) and so an OOM killer
+ * invocation might not even be necessary.
+ *
+ * That's why we don't do anything here except remember the
+ * OOM context and then deal with it at the end of the page
+ * fault when the stack is unwound, the locks are released,
+ * and when we know whether the fault was overall successful.
+ */
+ css_get(&memcg->css);
+ current->memcg_oom.memcg = memcg;
+ current->memcg_oom.gfp_mask = mask;
+ current->memcg_oom.order = order;
+}
+
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ * @handle: actually kill/wait or just clean up the OOM state
+ *
+ * This has to be called at the end of a page fault if the memcg OOM
+ * handler was enabled.
+ *
+ * Memcg supports userspace OOM handling where failed allocations must
+ * sleep on a waitqueue until the userspace task resolves the
+ * situation. Sleeping directly in the charge context with all kinds
+ * of locks held is not a good idea, instead we remember an OOM state
+ * in the task and mem_cgroup_oom_synchronize() has to be called at
+ * the end of the page fault to complete the OOM handling.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * completed, %false otherwise.
*/
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
- int order)
+bool mem_cgroup_oom_synchronize(bool handle)
{
+ struct mem_cgroup *memcg = current->memcg_oom.memcg;
struct oom_wait_info owait;
- bool locked, need_to_kill;
+ bool locked;
+
+ /* OOM is global, do not handle */
+ if (!memcg)
+ return false;
+
+ if (!handle)
+ goto cleanup;

owait.memcg = memcg;
owait.wait.flags = 0;
owait.wait.func = memcg_oom_wake_function;
owait.wait.private = current;
INIT_LIST_HEAD(&owait.wait.task_list);
- need_to_kill = true;
- mem_cgroup_mark_under_oom(memcg);

- /* At first, try to OOM lock hierarchy under memcg.*/
- spin_lock(&memcg_oom_lock);
- locked = mem_cgroup_oom_lock(memcg);
- /*
- * Even if signal_pending(), we can't quit charge() loop without
- * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
- * under OOM is always welcomed, use TASK_KILLABLE here.
- */
prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- if (!locked || memcg->oom_kill_disable)
- need_to_kill = false;
+ mem_cgroup_mark_under_oom(memcg);
+
+ locked = mem_cgroup_oom_trylock(memcg);
+
if (locked)
mem_cgroup_oom_notify(memcg);
- spin_unlock(&memcg_oom_lock);

- if (need_to_kill) {
+ if (locked && !memcg->oom_kill_disable) {
+ mem_cgroup_unmark_under_oom(memcg);
finish_wait(&memcg_oom_waitq, &owait.wait);
- mem_cgroup_out_of_memory(memcg, mask, order);
+ mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+ current->memcg_oom.order);
} else {
schedule();
+ mem_cgroup_unmark_under_oom(memcg);
finish_wait(&memcg_oom_waitq, &owait.wait);
}
- spin_lock(&memcg_oom_lock);
- if (locked)
- mem_cgroup_oom_unlock(memcg);
- memcg_wakeup_oom(memcg);
- spin_unlock(&memcg_oom_lock);

- mem_cgroup_unmark_under_oom(memcg);
-
- if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
- return false;
- /* Give chance to dying process */
- schedule_timeout_uninterruptible(1);
+ if (locked) {
+ mem_cgroup_oom_unlock(memcg);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
+ }
+cleanup:
+ current->memcg_oom.memcg = NULL;
+ css_put(&memcg->css);
return true;
}

@@ -2550,12 +2594,11 @@ enum {
CHARGE_RETRY, /* need to retry but retry is not bad */
CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
- CHARGE_OOM_DIE, /* the current is killed because of OOM */
};

static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages, unsigned int min_pages,
- bool oom_check)
+ bool invoke_oom)
{
unsigned long csize = nr_pages * PAGE_SIZE;
struct mem_cgroup *mem_over_limit;
@@ -2612,14 +2655,10 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
if (mem_cgroup_wait_acct_move(mem_over_limit))
return CHARGE_RETRY;

- /* If we don't need to call oom-killer at el, return immediately */
- if (!oom_check)
- return CHARGE_NOMEM;
- /* check OOM */
- if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
- return CHARGE_OOM_DIE;
+ if (invoke_oom)
+ mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));

- return CHARGE_RETRY;
+ return CHARGE_NOMEM;
}

/*
@@ -2663,6 +2702,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
|| fatal_signal_pending(current)))
goto bypass;

+ if (unlikely(task_in_memcg_oom(current)))
+ goto bypass;
+
/*
* We always charge the cgroup the mm_struct belongs to.
* The mm_struct's mem_cgroup changes on task migration if the
@@ -2722,7 +2764,7 @@ again:
}

do {
- bool oom_check;
+ bool invoke_oom = oom && !nr_oom_retries;

/* If killed, bypass charge */
if (fatal_signal_pending(current)) {
@@ -2730,14 +2772,8 @@ again:
goto bypass;
}

- oom_check = false;
- if (oom && !nr_oom_retries) {
- oom_check = true;
- nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- }
-
- ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
- oom_check);
+ ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+ nr_pages, invoke_oom);
switch (ret) {
case CHARGE_OK:
break;
@@ -2750,16 +2786,12 @@ again:
css_put(&memcg->css);
goto nomem;
case CHARGE_NOMEM: /* OOM routine works */
- if (!oom) {
+ if (!oom || invoke_oom) {
css_put(&memcg->css);
goto nomem;
}
- /* If oom, we never return -ENOMEM */
nr_oom_retries--;
break;
- case CHARGE_OOM_DIE: /* Killed by OOM Killer */
- css_put(&memcg->css);
- goto bypass;
}
} while (ret != CHARGE_OK);

diff --git a/mm/memory.c b/mm/memory.c
index ebe0f285c0e7..0984f398d746 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3754,22 +3754,14 @@ unlock:
/*
* By the time we get here, we already hold the mm semaphore
*/
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;

- __set_current_state(TASK_RUNNING);
-
- count_vm_event(PGFAULT);
- mem_cgroup_count_vm_event(mm, PGFAULT);
-
- /* do counter updates before entering really critical section. */
- check_sync_rss_stat(current);
-
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, flags);

@@ -3850,6 +3842,43 @@ retry:
return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}

+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
+{
+ int ret;
+
+ __set_current_state(TASK_RUNNING);
+
+ count_vm_event(PGFAULT);
+ mem_cgroup_count_vm_event(mm, PGFAULT);
+
+ /* do counter updates before entering really critical section. */
+ check_sync_rss_stat(current);
+
+ /*
+ * Enable the memcg OOM handling for faults triggered in user
+ * space. Kernel faults are handled more gracefully.
+ */
+ if (flags & FAULT_FLAG_USER)
+ mem_cgroup_oom_enable();
+
+ ret = __handle_mm_fault(mm, vma, address, flags);
+
+ if (flags & FAULT_FLAG_USER) {
+ mem_cgroup_oom_disable();
+ /*
+ * The task may have entered a memcg OOM situation but
+ * if the allocation error was handled gracefully (no
+ * VM_FAULT_OOM), there is no need to kill anything.
+ * Just clean up the OOM state peacefully.
+ */
+ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+ mem_cgroup_oom_synchronize(false);
+ }
+
+ return ret;
+}
+
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f104c7e9f61e..4d87d7c4ed2e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -702,9 +702,12 @@ out:
*/
void pagefault_out_of_memory(void)
{
- struct zonelist *zonelist = node_zonelist(first_online_node,
- GFP_KERNEL);
+ struct zonelist *zonelist;

+ if (mem_cgroup_oom_synchronize(true))
+ return;
+
+ zonelist = node_zonelist(first_online_node, GFP_KERNEL);
if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
out_of_memory(NULL, 0, 0, NULL, false);
clear_zonelist_oom(zonelist, GFP_KERNEL);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e696833a31b5..11ab6628027a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -429,6 +429,16 @@ extern netdev_features_t br_features_recompute(struct net_bridge *br,
extern int br_handle_frame_finish(struct sk_buff *skb);
extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb);

+static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
+{
+ return rcu_dereference(dev->rx_handler) == br_handle_frame;
+}
+
+static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev)
+{
+ return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL;
+}
+
/* br_ioctl.c */
extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg);
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 8660ea3be705..bdb459d21ad8 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0)
goto err;

- p = br_port_get_rcu(dev);
+ p = br_port_get_check_rcu(dev);
if (!p)
goto err;

diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 6e7a236525b6..06f19b9e159a 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)

static const u8 *aes_iv = (u8 *)CEPH_AES_IV;

+/*
+ * Should be used for buffers allocated with ceph_kvmalloc().
+ * Currently these are encrypt out-buffer (ceph_buffer) and decrypt
+ * in-buffer (msg front).
+ *
+ * Dispose of @sgt with teardown_sgtable().
+ *
+ * @prealloc_sg is to avoid memory allocation inside sg_alloc_table()
+ * in cases where a single sg is sufficient. No attempt to reduce the
+ * number of sgs by squeezing physically contiguous pages together is
+ * made though, for simplicity.
+ */
+static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg,
+ const void *buf, unsigned int buf_len)
+{
+ struct scatterlist *sg;
+ const bool is_vmalloc = is_vmalloc_addr(buf);
+ unsigned int off = offset_in_page(buf);
+ unsigned int chunk_cnt = 1;
+ unsigned int chunk_len = PAGE_ALIGN(off + buf_len);
+ int i;
+ int ret;
+
+ if (buf_len == 0) {
+ memset(sgt, 0, sizeof(*sgt));
+ return -EINVAL;
+ }
+
+ if (is_vmalloc) {
+ chunk_cnt = chunk_len >> PAGE_SHIFT;
+ chunk_len = PAGE_SIZE;
+ }
+
+ if (chunk_cnt > 1) {
+ ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS);
+ if (ret)
+ return ret;
+ } else {
+ WARN_ON(chunk_cnt != 1);
+ sg_init_table(prealloc_sg, 1);
+ sgt->sgl = prealloc_sg;
+ sgt->nents = sgt->orig_nents = 1;
+ }
+
+ for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) {
+ struct page *page;
+ unsigned int len = min(chunk_len - off, buf_len);
+
+ if (is_vmalloc)
+ page = vmalloc_to_page(buf);
+ else
+ page = virt_to_page(buf);
+
+ sg_set_page(sg, page, len, off);
+
+ off = 0;
+ buf += len;
+ buf_len -= len;
+ }
+ WARN_ON(buf_len != 0);
+
+ return 0;
+}
+
+static void teardown_sgtable(struct sg_table *sgt)
+{
+ if (sgt->orig_nents > 1)
+ sg_free_table(sgt);
+}
+
static int ceph_aes_encrypt(const void *key, int key_len,
void *dst, size_t *dst_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[2], sg_out[1];
+ struct scatterlist sg_in[2], prealloc_sg;
+ struct sg_table sg_out;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
int ret;
@@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len,

*dst_len = src_len + zero_padding;

- crypto_blkcipher_setkey((void *)tfm, key, key_len);
sg_init_table(sg_in, 2);
sg_set_buf(&sg_in[0], src, src_len);
sg_set_buf(&sg_in[1], pad, zero_padding);
- sg_init_table(sg_out, 1);
- sg_set_buf(sg_out, dst, *dst_len);
+ ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+ if (ret)
+ goto out_tfm;
+
+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
+
/*
print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
key, key_len, 1);
@@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len,
print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
pad, zero_padding, 1);
*/
- ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+ ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
src_len + zero_padding);
- crypto_free_blkcipher(tfm);
- if (ret < 0)
+ if (ret < 0) {
pr_err("ceph_aes_crypt failed %d\n", ret);
+ goto out_sg;
+ }
/*
print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_out);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}

static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
@@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
const void *src1, size_t src1_len,
const void *src2, size_t src2_len)
{
- struct scatterlist sg_in[3], sg_out[1];
+ struct scatterlist sg_in[3], prealloc_sg;
+ struct sg_table sg_out;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
int ret;
@@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,

*dst_len = src1_len + src2_len + zero_padding;

- crypto_blkcipher_setkey((void *)tfm, key, key_len);
sg_init_table(sg_in, 3);
sg_set_buf(&sg_in[0], src1, src1_len);
sg_set_buf(&sg_in[1], src2, src2_len);
sg_set_buf(&sg_in[2], pad, zero_padding);
- sg_init_table(sg_out, 1);
- sg_set_buf(sg_out, dst, *dst_len);
+ ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+ if (ret)
+ goto out_tfm;
+
+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
+
/*
print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
key, key_len, 1);
@@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
pad, zero_padding, 1);
*/
- ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+ ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
src1_len + src2_len + zero_padding);
- crypto_free_blkcipher(tfm);
- if (ret < 0)
+ if (ret < 0) {
pr_err("ceph_aes_crypt2 failed %d\n", ret);
+ goto out_sg;
+ }
/*
print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_out);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}

static int ceph_aes_decrypt(const void *key, int key_len,
void *dst, size_t *dst_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[1], sg_out[2];
+ struct sg_table sg_in;
+ struct scatterlist sg_out[2], prealloc_sg;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm };
char pad[16];
@@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len,
if (IS_ERR(tfm))
return PTR_ERR(tfm);

- crypto_blkcipher_setkey((void *)tfm, key, key_len);
- sg_init_table(sg_in, 1);
sg_init_table(sg_out, 2);
- sg_set_buf(sg_in, src, src_len);
sg_set_buf(&sg_out[0], dst, *dst_len);
sg_set_buf(&sg_out[1], pad, sizeof(pad));
+ ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+ if (ret)
+ goto out_tfm;

+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);

/*
@@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len,
print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
src, src_len, 1);
*/
-
- ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
- crypto_free_blkcipher(tfm);
+ ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
if (ret < 0) {
pr_err("ceph_aes_decrypt failed %d\n", ret);
- return ret;
+ goto out_sg;
}

if (src_len <= *dst_len)
@@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len,
print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_in);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}

static int ceph_aes_decrypt2(const void *key, int key_len,
@@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
void *dst2, size_t *dst2_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[1], sg_out[3];
+ struct sg_table sg_in;
+ struct scatterlist sg_out[3], prealloc_sg;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm };
char pad[16];
@@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
if (IS_ERR(tfm))
return PTR_ERR(tfm);

- sg_init_table(sg_in, 1);
- sg_set_buf(sg_in, src, src_len);
sg_init_table(sg_out, 3);
sg_set_buf(&sg_out[0], dst1, *dst1_len);
sg_set_buf(&sg_out[1], dst2, *dst2_len);
sg_set_buf(&sg_out[2], pad, sizeof(pad));
+ ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+ if (ret)
+ goto out_tfm;

crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);

/*
@@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
src, src_len, 1);
*/
-
- ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
- crypto_free_blkcipher(tfm);
+ ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
if (ret < 0) {
pr_err("ceph_aes_decrypt failed %d\n", ret);
- return ret;
+ goto out_sg;
}

if (src_len <= *dst1_len)
@@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
dst2, *dst2_len, 1);
*/

- return 0;
+out_sg:
+ teardown_sgtable(&sg_in);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}


diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 250a73e77f57..6c20f4731f1a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
else
dev->flags &= ~IFF_POINTOPOINT;

- dev->iflink = p->link;
-
/* Precalculate GRE options length */
if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
if (t->parms.o_flags&GRE_CSUM)
@@ -1267,6 +1265,8 @@ static int ip6gre_tunnel_init(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;

+ dev->iflink = tunnel->parms.link;
+
return 0;
}

@@ -1282,7 +1282,6 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev)
dev_hold(dev);
}

-
static struct inet6_protocol ip6gre_protocol __read_mostly = {
.handler = ip6gre_rcv,
.err_handler = ip6gre_err,
@@ -1458,6 +1457,8 @@ static int ip6gre_tap_init(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;

+ dev->iflink = tunnel->parms.link;
+
return 0;
}

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0ecdf596f2f..14f46af17704 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -265,9 +265,6 @@ static int ip6_tnl_create2(struct net_device *dev)
int err;

t = netdev_priv(dev);
- err = ip6_tnl_dev_init(dev);
- if (err < 0)
- goto out;

err = register_netdevice(dev);
if (err < 0)
@@ -1433,6 +1430,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)


static const struct net_device_ops ip6_tnl_netdev_ops = {
+ .ndo_init = ip6_tnl_dev_init,
.ndo_uninit = ip6_tnl_dev_uninit,
.ndo_start_xmit = ip6_tnl_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
@@ -1514,16 +1512,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- int err = ip6_tnl_dev_init_gen(dev);
-
- if (err)
- return err;

t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);

- ip6_tnl_link_config(t);
-
rcu_assign_pointer(ip6n->tnls_wc[0], t);
return 0;
}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index fae73b0ef14b..85bc6d498b46 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1585,11 +1585,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
sc = le16_to_cpu(hdr->seq_ctrl);
frag = sc & IEEE80211_SCTL_FRAG;

- if (likely((!ieee80211_has_morefrags(fc) && frag == 0) ||
- is_multicast_ether_addr(hdr->addr1))) {
- /* not fragmented */
+ if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+ goto out;
+
+ if (is_multicast_ether_addr(hdr->addr1)) {
+ rx->local->dot11MulticastReceivedFrameCount++;
goto out;
}
+
I802_DEBUG_INC(rx->local->rx_handlers_fragments);

if (skb_linearize(rx->skb))
@@ -1682,10 +1685,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
out:
if (rx->sta)
rx->sta->rx_packets++;
- if (is_multicast_ether_addr(hdr->addr1))
- rx->local->dot11MulticastReceivedFrameCount++;
- else
- ieee80211_led_rx(rx->local);
+ ieee80211_led_rx(rx->local);
return RX_CONTINUE;
}

diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 038eee5c8f85..2bb801e3ee8c 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -487,6 +487,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
return i->status & IPS_NAT_MASK ? 1 : 0;
}

+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+ struct nf_conn_nat *nat = nfct_nat(ct);
+
+ if (nf_nat_proto_remove(ct, data))
+ return 1;
+
+ if (!nat || !nat->ct)
+ return 0;
+
+ /* This netns is being destroyed, and conntrack has nat null binding.
+ * Remove it from bysource hash, as the table will be freed soon.
+ *
+ * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+ * will delete entry from already-freed table.
+ */
+ if (!del_timer(&ct->timeout))
+ return 1;
+
+ spin_lock_bh(&nf_nat_lock);
+ hlist_del_rcu(&nat->bysource);
+ ct->status &= ~IPS_NAT_DONE_MASK;
+ nat->ct = NULL;
+ spin_unlock_bh(&nf_nat_lock);
+
+ add_timer(&ct->timeout);
+
+ /* don't delete conntrack. Although that would make things a lot
+ * simpler, we'd end up flushing all conntracks on nat rmmod.
+ */
+ return 0;
+}
+
static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
{
struct nf_nat_proto_clean clean = {
@@ -749,7 +782,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
{
struct nf_nat_proto_clean clean = {};

- nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
+ nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
synchronize_rcu();
nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
}
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 962e9792e317..216261dd32ae 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -45,7 +45,8 @@
#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 100 /* every second */
#define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */
-#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */
+/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN)

#define PRINTR(x, args...) do { if (net_ratelimit()) \
printk(x, ## args); } while (0);
@@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode,

case NFULNL_COPY_PACKET:
inst->copy_mode = mode;
+ if (range == 0)
+ range = NFULNL_COPY_RANGE_MAX;
inst->copy_range = min_t(unsigned int,
range, NFULNL_COPY_RANGE_MAX);
break;
@@ -345,26 +348,25 @@ nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size)
return skb;
}

-static int
+static void
__nfulnl_send(struct nfulnl_instance *inst)
{
- int status = -1;
-
if (inst->qlen > 1) {
struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0,
NLMSG_DONE,
sizeof(struct nfgenmsg),
0);
- if (!nlh)
+ if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n",
+ inst->skb->len, skb_tailroom(inst->skb))) {
+ kfree_skb(inst->skb);
goto out;
+ }
}
- status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
- MSG_DONTWAIT);
-
+ nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
+ MSG_DONTWAIT);
+out:
inst->qlen = 0;
inst->skb = NULL;
-out:
- return status;
}

static void
@@ -647,7 +649,8 @@ nfulnl_log_packet(struct net *net,
+ nla_total_size(sizeof(u_int32_t)) /* gid */
+ nla_total_size(plen) /* prefix */
+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
- + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp));
+ + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
+ + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */

if (in && skb_mac_header_was_set(skb)) {
size += nla_total_size(skb->dev->hard_header_len)
@@ -676,8 +679,7 @@ nfulnl_log_packet(struct net *net,
break;

case NFULNL_COPY_PACKET:
- if (inst->copy_range == 0
- || inst->copy_range > skb->len)
+ if (inst->copy_range > skb->len)
data_len = skb->len;
else
data_len = inst->copy_range;
@@ -690,8 +692,7 @@ nfulnl_log_packet(struct net *net,
goto unlock_and_release;
}

- if (inst->skb &&
- size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) {
+ if (inst->skb && size > skb_tailroom(inst->skb)) {
/* either the queue len is too high or we don't have
* enough room in the skb left. flush to userspace. */
__nfulnl_flush(inst);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 62e86d98bc36..ca4a1a1b8e69 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1659,6 +1659,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
* ack chunk whose serial number matches that of the request.
*/
list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) {
+ if (sctp_chunk_pending(ack))
+ continue;
if (ack->subh.addip_hdr->serial == serial) {
sctp_chunk_hold(ack);
return ack;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 7a19117254db..bc2fae7e67be 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -874,8 +874,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
list_add(&cur_key->key_list, sh_keys);

cur_key->key = key;
- sctp_auth_key_hold(key);
-
return 0;
nomem:
if (!replace)
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 3221d073448c..49c58eadbfa2 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -147,18 +147,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
} else {
/* Nothing to do. Next chunk in the packet, please. */
ch = (sctp_chunkhdr_t *) chunk->chunk_end;
-
/* Force chunk->skb->data to chunk->chunk_end. */
- skb_pull(chunk->skb,
- chunk->chunk_end - chunk->skb->data);
-
- /* Verify that we have at least chunk headers
- * worth of buffer left.
- */
- if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
- sctp_chunk_free(chunk);
- chunk = queue->in_progress = NULL;
- }
+ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data);
+ /* We are guaranteed to pull a SCTP header. */
}
}

@@ -194,24 +185,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
chunk->subh.v = NULL; /* Subheader is no longer valid. */

- if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
+ if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) <
+ skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
- /* RFC 2960, Section 6.10 Bundling
- *
- * Partial chunks MUST NOT be placed in an SCTP packet.
- * If the receiver detects a partial chunk, it MUST drop
- * the chunk.
- *
- * Since the end of the chunk is past the end of our buffer
- * (which contains the whole packet, we can freely discard
- * the whole packet.
- */
- sctp_chunk_free(chunk);
- chunk = queue->in_progress = NULL;
-
- return NULL;
+ /* Discard inside state machine. */
+ chunk->pdiscard = 1;
+ chunk->chunk_end = skb_tail_pointer(chunk->skb);
} else {
/* We are at the end of the packet, so mark the chunk
* in case we need to send a SACK.
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 87e244be899a..29fc16f3633f 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2596,6 +2596,9 @@ do_addr_param:
addr_param = param.v + sizeof(sctp_addip_param_t);

af = sctp_get_af_specific(param_type2af(param.p->type));
+ if (af == NULL)
+ break;
+
af->from_addr_param(&addr, addr_param,
htons(asoc->peer.port), 0);

@@ -3094,50 +3097,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
return SCTP_ERROR_NO_ERROR;
}

-/* Verify the ASCONF packet before we process it. */
-int sctp_verify_asconf(const struct sctp_association *asoc,
- struct sctp_paramhdr *param_hdr, void *chunk_end,
- struct sctp_paramhdr **errp) {
- sctp_addip_param_t *asconf_param;
+/* Verify the ASCONF packet before we process it. */
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+ struct sctp_chunk *chunk, bool addr_param_needed,
+ struct sctp_paramhdr **errp)
+{
+ sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr;
union sctp_params param;
- int length, plen;
+ bool addr_param_seen = false;

- param.v = (sctp_paramhdr_t *) param_hdr;
- while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
- length = ntohs(param.p->length);
- *errp = param.p;
-
- if (param.v > chunk_end - length ||
- length < sizeof(sctp_paramhdr_t))
- return 0;
+ sctp_walk_params(param, addip, addip_hdr.params) {
+ size_t length = ntohs(param.p->length);

+ *errp = param.p;
switch (param.p->type) {
+ case SCTP_PARAM_ERR_CAUSE:
+ break;
+ case SCTP_PARAM_IPV4_ADDRESS:
+ if (length != sizeof(sctp_ipv4addr_param_t))
+ return false;
+ addr_param_seen = true;
+ break;
+ case SCTP_PARAM_IPV6_ADDRESS:
+ if (length != sizeof(sctp_ipv6addr_param_t))
+ return false;
+ addr_param_seen = true;
+ break;
case SCTP_PARAM_ADD_IP:
case SCTP_PARAM_DEL_IP:
case SCTP_PARAM_SET_PRIMARY:
- asconf_param = (sctp_addip_param_t *)param.v;
- plen = ntohs(asconf_param->param_hdr.length);
- if (plen < sizeof(sctp_addip_param_t) +
- sizeof(sctp_paramhdr_t))
- return 0;
+ /* In ASCONF chunks, these need to be first. */
+ if (addr_param_needed && !addr_param_seen)
+ return false;
+ length = ntohs(param.addip->param_hdr.length);
+ if (length < sizeof(sctp_addip_param_t) +
+ sizeof(sctp_paramhdr_t))
+ return false;
break;
case SCTP_PARAM_SUCCESS_REPORT:
case SCTP_PARAM_ADAPTATION_LAYER_IND:
if (length != sizeof(sctp_addip_param_t))
- return 0;
-
+ return false;
break;
default:
- break;
+ /* This is unkown to us, reject! */
+ return false;
}
-
- param.v += WORD_ROUND(length);
}

- if (param.v != chunk_end)
- return 0;
+ /* Remaining sanity checks. */
+ if (addr_param_needed && !addr_param_seen)
+ return false;
+ if (!addr_param_needed && addr_param_seen)
+ return false;
+ if (param.v != chunk->chunk_end)
+ return false;

- return 1;
+ return true;
}

/* Process an incoming ASCONF chunk with the next expected serial no. and
@@ -3146,16 +3162,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc,
struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
struct sctp_chunk *asconf)
{
+ sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr;
+ bool all_param_pass = true;
+ union sctp_params param;
sctp_addiphdr_t *hdr;
union sctp_addr_param *addr_param;
sctp_addip_param_t *asconf_param;
struct sctp_chunk *asconf_ack;
-
__be16 err_code;
int length = 0;
int chunk_len;
__u32 serial;
- int all_param_pass = 1;

chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
hdr = (sctp_addiphdr_t *)asconf->skb->data;
@@ -3183,9 +3200,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
goto done;

/* Process the TLVs contained within the ASCONF chunk. */
- while (chunk_len > 0) {
+ sctp_walk_params(param, addip, addip_hdr.params) {
+ /* Skip preceeding address parameters. */
+ if (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+ param.p->type == SCTP_PARAM_IPV6_ADDRESS)
+ continue;
+
err_code = sctp_process_asconf_param(asoc, asconf,
- asconf_param);
+ param.addip);
/* ADDIP 4.1 A7)
* If an error response is received for a TLV parameter,
* all TLVs with no response before the failed TLV are
@@ -3193,28 +3215,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
* the failed response are considered unsuccessful unless
* a specific success indication is present for the parameter.
*/
- if (SCTP_ERROR_NO_ERROR != err_code)
- all_param_pass = 0;
-
+ if (err_code != SCTP_ERROR_NO_ERROR)
+ all_param_pass = false;
if (!all_param_pass)
- sctp_add_asconf_response(asconf_ack,
- asconf_param->crr_id, err_code,
- asconf_param);
+ sctp_add_asconf_response(asconf_ack, param.addip->crr_id,
+ err_code, param.addip);

/* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add
* an IP address sends an 'Out of Resource' in its response, it
* MUST also fail any subsequent add or delete requests bundled
* in the ASCONF.
*/
- if (SCTP_ERROR_RSRC_LOW == err_code)
+ if (err_code == SCTP_ERROR_RSRC_LOW)
goto done;
-
- /* Move to the next ASCONF param. */
- length = ntohs(asconf_param->param_hdr.length);
- asconf_param = (void *)asconf_param + length;
- chunk_len -= length;
}
-
done:
asoc->peer.addip_serial++;

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index edc204b05c82..c52763a26297 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -177,6 +177,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk,
{
__u16 chunk_length = ntohs(chunk->chunk_hdr->length);

+ /* Previously already marked? */
+ if (unlikely(chunk->pdiscard))
+ return 0;
if (unlikely(chunk_length < required_length))
return 0;

@@ -3593,9 +3596,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
struct sctp_chunk *asconf_ack = NULL;
struct sctp_paramhdr *err_param = NULL;
sctp_addiphdr_t *hdr;
- union sctp_addr_param *addr_param;
__u32 serial;
- int length;

if (!sctp_vtag_verify(chunk, asoc)) {
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
@@ -3620,17 +3621,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
hdr = (sctp_addiphdr_t *)chunk->skb->data;
serial = ntohl(hdr->serial);

- addr_param = (union sctp_addr_param *)hdr->params;
- length = ntohs(addr_param->p.length);
- if (length < sizeof(sctp_paramhdr_t))
- return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
- (void *)addr_param, commands);
-
/* Verify the ASCONF chunk before processing it. */
- if (!sctp_verify_asconf(asoc,
- (sctp_paramhdr_t *)((void *)addr_param + length),
- (void *)chunk->chunk_end,
- &err_param))
+ if (!sctp_verify_asconf(asoc, chunk, true, &err_param))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)err_param, commands);

@@ -3748,10 +3740,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
rcvd_serial = ntohl(addip_hdr->serial);

/* Verify the ASCONF-ACK chunk before processing it. */
- if (!sctp_verify_asconf(asoc,
- (sctp_paramhdr_t *)addip_hdr->params,
- (void *)asconf_ack->chunk_end,
- &err_param))
+ if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)err_param, commands);

diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index ebe91440a068..c89a5bf5c00e 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -799,6 +799,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl,
return changed;
}

+static void kctl_private_value_free(struct snd_kcontrol *kctl)
+{
+ kfree((void *)kctl->private_value);
+}
+
static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
int validx, int bUnitID)
{
@@ -833,6 +838,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
return -ENOMEM;
}

+ kctl->private_free = kctl_private_value_free;
err = snd_ctl_add(mixer->chip->card, kctl);
if (err < 0)
return err;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/