Merge branch 'akpm' (patches from Andrew Morton)

Merge more patches from Andrew Morton: "The rest of MM. Plus one misc cleanup" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (35 commits) mm/Kconfig: add MMU dependency for MIGRATION. kernel: replace strict_strto*() with kstrto*() mm, thp: count thp_fault_fallback anytime thp fault fails thp: consolidate code between handle_mm_fault() and do_huge_pmd_anonymous_page() thp: do_huge_pmd_anonymous_page() cleanup thp: move maybe_pmd_mkwrite() out of mk_huge_pmd() mm: cleanup add_to_page_cache_locked() thp: account anon transparent huge pages into NR_ANON_PAGES truncate: drop 'oldsize' truncate_pagecache() parameter mm: make lru_add_drain_all() selective memcg: document cgroup dirty/writeback memory statistics memcg: add per cgroup writeback pages accounting memcg: check for proper lock held in mem_cgroup_update_page_stat memcg: remove MEMCG_NR_FILE_MAPPED memcg: reduce function dereference memcg: avoid overflow caused by PAGE_ALIGN memcg: rename RESOURCE_MAX to RES_COUNTER_MAX memcg: correct RESOURCE_MAX to ULLONG_MAX mm: memcg: do not trap chargers with full callstack on OOM mm: memcg: rework and document OOM waiting and wakeup ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2013-09-12 18:44:27 -0400
committer: Linus Torvalds <torvalds@linux-foundation.org> 2013-09-12 18:44:27 -0400
commit: ac4de9543aca59f2b763746647577302fbedd57e (patch)
tree: 40407750569ee030de56233c41c9a97f7e89cf67
parent: 26935fb06ee88f1188789807687c03041f3c70d9 (diff)
parent: de32a8177f64bc62e1b19c685dd391af664ab13f (diff)
79 files changed, 973 insertions, 919 deletions
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 2a3330696372..8af4ad121828 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -490,6 +490,8 @@ pgpgin		- # of charging events to the memory cgroup. The charging
 pgpgout         - # of uncharging events to the memory cgroup. The uncharging
                event happens each time a page is unaccounted from the cgroup.
 swap            - # of bytes of swap usage
+writeback       - # of bytes of file/anon cache that are queued for syncing to
+                disk.
 inactive_anon   - # of bytes of anonymous and swap cache memory on inactive
                LRU list.
 active_anon     - # of bytes of anonymous and swap cache memory on active
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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                              (cause > 0 ? FAULT_FLAG_WRITE : 0));
        /* 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 0fd1f0d515ff..d63f3de0cd5b 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -60,8 +60,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address)
        siginfo_t info;
        int fault, ret;
        int write = regs->ecr_cause & ECR_C_PROTV_STORE;  /* ST/EX */
-        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                (write ? FAULT_FLAG_WRITE : 0);
        /*
         * We fault-in kernel-space virtual memory on-demand. The
@@ -89,6 +88,8 @@ void 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);
        vma = find_vma(mm, address);
@@ -117,12 +118,12 @@ 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
@@ -201,10 +202,6 @@ no_context:
        die("Oops", regs, address);
 out_of_memory:
-        if (is_global_init(tsk)) {
-                yield();
-                goto survive;
-        }
        up_read(&mm->mmap_sem);
        if (user_mode(regs)) {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c97f7940cb95..eb8830a4c5ed 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;
-        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                (write ? FAULT_FLAG_WRITE : 0);
        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/mm/fault.c b/arch/arm64/mm/fault.c
index 6c8ba25bf6bb..6d6acf153bff 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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
        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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                 (cause > 0 ? FAULT_FLAG_WRITE : 0);
        /*
         * 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 8fddf46e6c62..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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                (write_access ? FAULT_FLAG_WRITE : 0);
        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;
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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                         (is_write ? FAULT_FLAG_WRITE : 0);
        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/fault.c b/arch/mips/mm/fault.c
index 85df1cd8d446..becc42bb1849 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -42,8 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
        const int field = sizeof(unsigned long) * 2;
        siginfo_t info;
        int fault;
-        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                                 (write ? FAULT_FLAG_WRITE : 0);
 #if 0
        printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -93,6 +92,8 @@ static void __kprobes __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;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -114,6 +115,7 @@ 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)) {
@@ -241,6 +243,8 @@ 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 8a2e6ded9a44..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);
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 4a41f8493ab0..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,
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,
+        fault = handle_mm_fault(mm, vma, address, flags);
-                        flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
        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 2dd69bf4af46..51ab9e7e6c39 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
@@ -288,6 +285,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
        if (user_mode(regs))
                store_update_sp = store_updates_sp(regs);
+        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
@@ -415,6 +415,7 @@ 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 7de4469915f0..fc6679210d83 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 6b18fb0189ae..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;
@@ -167,11 +171,6 @@ no_context:
        */
 out_of_memory:
        up_read(&mm->mmap_sem);
-        if (is_global_init(tsk)) {
-                yield();
-                down_read(&mm->mmap_sem);
-                goto survive;
-        }
        if (!user_mode(regs))
                goto no_context;
        pagefault_out_of_memory();
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;
-        unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                              (write ? FAULT_FLAG_WRITE : 0));
        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/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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                              (write ? FAULT_FLAG_WRITE : 0));
        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 5062ff389e83..2ebec263d685 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -315,7 +315,8 @@ 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
@@ -418,13 +419,14 @@ 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 111d5a9b76f1..4c288f199453 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 |
+        flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                 (write ? FAULT_FLAG_WRITE : 0));
        is_kernel_mode = !user_mode(regs);
@@ -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
@@ -555,11 +557,6 @@ no_context:
 */
 out_of_memory:
        up_read(&mm->mmap_sem);
-        if (is_global_init(tsk)) {
-                yield();
-                down_read(&mm->mmap_sem);
-                goto survive;
-        }
        if (is_kernel_mode)
                goto no_context;
        pagefault_out_of_memory();
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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                 (is_write ? FAULT_FLAG_WRITE : 0);
        *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))
+        if (is_write) {
-                goto out;
+                if (!(vma->vm_flags & VM_WRITE))
+                        goto out;
-        /* Don't require VM_READ|VM_EXEC for write faults! */
+                flags |= FAULT_FLAG_WRITE;
-        if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
+        } else {
-                goto out;
+                /* 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 |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-                                 ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
        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/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae3047..3aaeffcfd67a 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)
 {
-        /*
+        if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
-         * Pagefault was interrupted by SIGKILL. We have no reason to
+                up_read(&current->mm->mmap_sem);
-         * continue pagefault.
+                no_context(regs, error_code, address, 0, 0);
-         */
+                return;
-        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 (!(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)
@@ -1011,9 +1002,7 @@ __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;
-        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                        (write ? FAULT_FLAG_WRITE : 0);
        tsk = current;
        mm = tsk->mm;
@@ -1083,6 +1072,7 @@ __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();
@@ -1109,6 +1099,9 @@ __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
@@ -1187,9 +1180,17 @@ 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))
+         * If we need to retry but a fatal signal is pending, handle the
-                        return;
+         * 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/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/base/node.c b/drivers/base/node.c
index 7616a77ca322..bc9f43bf7e29 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -125,13 +125,7 @@ static ssize_t node_read_meminfo(struct device *dev,
                       nid, K(node_page_state(nid, NR_WRITEBACK)),
                       nid, K(node_page_state(nid, NR_FILE_PAGES)),
                       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-                       nid, K(node_page_state(nid, NR_ANON_PAGES)
-                        + node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-                        HPAGE_PMD_NR),
-#else
                       nid, K(node_page_state(nid, NR_ANON_PAGES)),
-#endif
                       nid, K(node_page_state(nid, NR_SHMEM)),
                       nid, node_page_state(nid, NR_KERNEL_STACK) *
                                THREAD_SIZE / 1024,
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 5f95d1ed9c6d..b9acadafa4a1 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -50,7 +50,7 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size)
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
 }
 static int adfs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 776e3935a758..8669b6ecddee 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -406,7 +406,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                affs_truncate(inode);
        }
 }
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index ad3ea1497cc3..ae2892218335 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -166,7 +166,7 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size)
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
 }
 static int bfs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index ef3bea7bb257..3f0ddfce96e6 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -221,12 +221,10 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
                                    struct btrfs_path *path,
                                    struct inode *inode)
 {
-        loff_t oldsize;
        int ret = 0;
-        oldsize = i_size_read(inode);
        btrfs_i_size_write(inode, 0);
-        truncate_pagecache(inode, oldsize, 0);
+        truncate_pagecache(inode, 0);
        /*
         * We don't need an orphan item because truncating the free space cache
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index db1e43948579..f338c5672d58 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4349,7 +4349,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
                inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
        if (newsize > oldsize) {
-                truncate_pagecache(inode, oldsize, newsize);
+                truncate_pagecache(inode, newsize);
                ret = btrfs_cont_expand(inode, oldsize, newsize);
                if (ret)
                        return ret;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index e3bb6477c83f..f9ff9c173f78 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1856,14 +1856,11 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from)
 static void cifs_setsize(struct inode *inode, loff_t offset)
 {
-        loff_t oldsize;
        spin_lock(&inode->i_lock);
-        oldsize = inode->i_size;
        i_size_write(inode, offset);
        spin_unlock(&inode->i_lock);
-        truncate_pagecache(inode, oldsize, offset);
+        truncate_pagecache(inode, offset);
 }
 static int
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 2ec8eb1ab269..a52a5d23c30b 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -861,7 +861,7 @@ static int exofs_writepage(struct page *page, struct writeback_control *wbc)
 static void _write_failed(struct inode *inode, loff_t to)
 {
        if (to > inode->i_size)
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
 }
 int exofs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0a87bb10998d..c260de6d7b6d 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -58,7 +58,7 @@ static void ext2_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                ext2_truncate_blocks(inode, inode->i_size);
        }
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c79fd7dabe79..0d424d7ac02b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4587,7 +4587,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
        if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
                handle_t *handle;
-                loff_t oldsize = inode->i_size;
                if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
                        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -4650,7 +4649,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
                 * Truncate pagecache after we've waited for commit
                 * in data=journal mode to make pages freeable.
                 */
-                truncate_pagecache(inode, oldsize, inode->i_size);
+                        truncate_pagecache(inode, inode->i_size);
        }
        /*
         * We want to call ext4_truncate() even if attr->ia_size ==
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 11b51bb55b42..0062da21dd8b 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -147,7 +147,7 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                fat_truncate_blocks(inode, inode->i_size);
        }
 }
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 3ac91086f41f..62b43b577bfc 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1678,7 +1678,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
         * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
         */
        if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
-                truncate_pagecache(inode, oldsize, outarg.attr.size);
+                truncate_pagecache(inode, outarg.attr.size);
                invalidate_inode_pages2(inode->i_mapping);
        }
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 84434594e80e..a8ce6dab60a0 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -218,7 +218,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
                bool inval = false;
                if (oldsize != attr->size) {
-                        truncate_pagecache(inode, oldsize, attr->size);
+                        truncate_pagecache(inode, attr->size);
                        inval = true;
                } else if (fc->auto_inval_data) {
                        struct timespec new_mtime = {
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5e2f56fccf6b..62a65fc448dc 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1016,7 +1016,7 @@ static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize
                chunk = oldsize - newsize;
                if (chunk > max_chunk)
                        chunk = max_chunk;
-                truncate_pagecache(inode, oldsize, oldsize - chunk);
+                truncate_pagecache(inode, oldsize - chunk);
                oldsize -= chunk;
                gfs2_trans_end(sdp);
                error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES);
@@ -1067,7 +1067,7 @@ static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
        if (journaled)
                error = gfs2_journaled_truncate(inode, oldsize, newsize);
        else
-                truncate_pagecache(inode, oldsize, newsize);
+                truncate_pagecache(inode, newsize);
        if (error) {
                brelse(dibh);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index f9299d8a64e3..380ab31b5e0f 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -41,7 +41,7 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                hfs_file_truncate(inode);
        }
 }
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 4d2edaea891c..37213d075f3c 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -36,7 +36,7 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                hfsplus_file_truncate(inode);
        }
 }
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 4e9dabcf1f4c..67c1a61e0955 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -138,7 +138,7 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to)
        hpfs_lock(inode->i_sb);
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                hpfs_truncate(inode);
        }
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 730f24e282a6..f4aab719add5 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -306,7 +306,7 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                jfs_truncate(inode);
        }
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index df122496f328..0332109162a5 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -400,7 +400,7 @@ static void minix_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                minix_truncate(inode);
        }
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 87e797640828..eda8879171c4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -541,7 +541,6 @@ EXPORT_SYMBOL_GPL(nfs_setattr);
 */
 static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 {
-        loff_t oldsize;
        int err;
        err = inode_newsize_ok(inode, offset);
@@ -549,11 +548,10 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
                goto out;
        spin_lock(&inode->i_lock);
-        oldsize = inode->i_size;
        i_size_write(inode, offset);
        spin_unlock(&inode->i_lock);
-        truncate_pagecache(inode, oldsize, offset);
+        truncate_pagecache(inode, offset);
 out:
        return err;
 }
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index b1a5277cfd18..7e350c562e0e 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -254,7 +254,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                nilfs_truncate(inode);
        }
 }
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index c5670b8d198c..ea4ba9daeb47 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1768,7 +1768,7 @@ static void ntfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                ntfs_truncate_vfs(inode);
        }
 }
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index e0d9b3e722bd..54d57d6ba68d 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -311,7 +311,7 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                omfs_truncate(inode);
        }
 }
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 5aa847a603c0..59d85d608898 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -132,13 +132,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                K(i.freeswap),
                K(global_page_state(NR_FILE_DIRTY)),
                K(global_page_state(NR_WRITEBACK)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-                K(global_page_state(NR_ANON_PAGES)
-                  + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-                  HPAGE_PMD_NR),
-#else
                K(global_page_state(NR_ANON_PAGES)),
-#endif
                K(global_page_state(NR_FILE_MAPPED)),
                K(global_page_state(NR_SHMEM)),
                K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index c1a591a4725b..66bc316927e8 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -469,7 +469,7 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size) {
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
                sysv_truncate(inode);
        }
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index b6d15d349810..062b7925bca0 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -172,7 +172,7 @@ static void udf_write_failed(struct address_space *mapping, loff_t to)
        loff_t isize = inode->i_size;
        if (to > isize) {
-                truncate_pagecache(inode, to, isize);
+                truncate_pagecache(inode, isize);
                if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
                        down_write(&iinfo->i_data_sem);
                        udf_clear_extent_cache(inode);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index ff24e4449ece..c8ca96086784 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -531,7 +531,7 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to)
        struct inode *inode = mapping->host;
        if (to > inode->i_size)
-                truncate_pagecache(inode, to, inode->i_size);
+                truncate_pagecache(inode, inode->i_size);
 }
 static int ufs_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 977da0ec6604..e51e581454e9 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1582,7 +1582,7 @@ xfs_vm_write_begin(
                unlock_page(page);
                if (pos + len > i_size_read(inode))
-                        truncate_pagecache(inode, pos + len, i_size_read(inode));
+                        truncate_pagecache(inode, i_size_read(inode));
                page_cache_release(page);
                page = NULL;
@@ -1618,7 +1618,7 @@ xfs_vm_write_end(
                loff_t          to = pos + len;
                if (to > isize) {
-                        truncate_pagecache(inode, to, isize);
+                        truncate_pagecache(inode, isize);
                        xfs_vm_kill_delalloc_range(inode, isize, to);
                }
        }
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b60de92e2edc..3935428c57cf 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -96,9 +96,6 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                          pmd_t *dst_pmd, pmd_t *src_pmd,
                          struct vm_area_struct *vma,
                          unsigned long addr, unsigned long end);
-extern int handle_pte_fault(struct mm_struct *mm,
-                            struct vm_area_struct *vma, unsigned long address,
-                            pte_t *pte, pmd_t *pmd, unsigned int flags);
 extern int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c416092e324..60e95872da29 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -30,9 +30,21 @@ struct page;
 struct mm_struct;
 struct kmem_cache;
-/* Stats that can be updated by kernel. */
+/*
-enum mem_cgroup_page_stat_item {
+ * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c,
-        MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */
+ * These two lists should keep in accord with each other.
+ */
+enum mem_cgroup_stat_index {
+        /*
+         * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
+         */
+        MEM_CGROUP_STAT_CACHE,          /* # of pages charged as cache */
+        MEM_CGROUP_STAT_RSS,            /* # of pages charged as anon rss */
+        MEM_CGROUP_STAT_RSS_HUGE,       /* # of pages charged as anon huge */
+        MEM_CGROUP_STAT_FILE_MAPPED,    /* # of pages charged as file rss */
+        MEM_CGROUP_STAT_WRITEBACK,      /* # of pages under writeback */
+        MEM_CGROUP_STAT_SWAP,           /* # of pages, swapped out */
+        MEM_CGROUP_STAT_NSTATS,
 };
 struct mem_cgroup_reclaim_cookie {
@@ -41,6 +53,23 @@ struct mem_cgroup_reclaim_cookie {
        unsigned int generation;
 };
+enum mem_cgroup_filter_t {
+        VISIT,          /* visit current node */
+        SKIP,           /* skip the current node and continue traversal */
+        SKIP_TREE,      /* skip the whole subtree and continue traversal */
+};
+/*
+ * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to
+ * iterate through the hierarchy tree. Each tree element is checked by the
+ * predicate before it is returned by the iterator. If a filter returns
+ * SKIP or SKIP_TREE then the iterator code continues traversal (with the
+ * next node down the hierarchy or the next node that doesn't belong under the
+ * memcg's subtree).
+ */
+typedef enum mem_cgroup_filter_t
+(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root);
 #ifdef CONFIG_MEMCG
 /*
 * All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -108,9 +137,18 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
        struct page *oldpage, struct page *newpage, bool migration_ok);
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
-                                   struct mem_cgroup *,
+                                   struct mem_cgroup *prev,
-                                   struct mem_cgroup_reclaim_cookie *);
+                                   struct mem_cgroup_reclaim_cookie *reclaim,
+                                   mem_cgroup_iter_filter cond);
+static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
+                                   struct mem_cgroup *prev,
+                                   struct mem_cgroup_reclaim_cookie *reclaim)
+{
+        return mem_cgroup_iter_cond(root, prev, reclaim, NULL);
+}
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 /*
@@ -125,6 +163,48 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
                                        struct page *newpage);
+/**
+ * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task
+ * @new: true to enable, false to disable
+ *
+ * Toggle whether a failed memcg charge should invoke the OOM killer
+ * or just return -ENOMEM.  Returns the previous toggle state.
+ *
+ * NOTE: Any path that enables the OOM killer before charging must
+ *       call mem_cgroup_oom_synchronize() afterward to finalize the
+ *       OOM handling and clean up.
+ */
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+        bool old;
+        old = current->memcg_oom.may_oom;
+        current->memcg_oom.may_oom = new;
+        return old;
+}
+static inline void mem_cgroup_enable_oom(void)
+{
+        bool old = mem_cgroup_toggle_oom(true);
+        WARN_ON(old == true);
+}
+static inline void mem_cgroup_disable_oom(void)
+{
+        bool old = mem_cgroup_toggle_oom(false);
+        WARN_ON(old == false);
+}
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+        return p->memcg_oom.in_memcg_oom;
+}
+bool mem_cgroup_oom_synchronize(void);
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -165,24 +245,24 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 }
 void mem_cgroup_update_page_stat(struct page *page,
-                                 enum mem_cgroup_page_stat_item idx,
+                                 enum mem_cgroup_stat_index idx,
                                 int val);
 static inline void mem_cgroup_inc_page_stat(struct page *page,
-                                            enum mem_cgroup_page_stat_item idx)
+                                            enum mem_cgroup_stat_index idx)
 {
        mem_cgroup_update_page_stat(page, idx, 1);
 }
 static inline void mem_cgroup_dec_page_stat(struct page *page,
-                                            enum mem_cgroup_page_stat_item idx)
+                                            enum mem_cgroup_stat_index idx)
 {
        mem_cgroup_update_page_stat(page, idx, -1);
 }
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+enum mem_cgroup_filter_t
-                                                gfp_t gfp_mask,
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-                                                unsigned long *total_scanned);
+                struct mem_cgroup *root);
 void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
@@ -296,6 +376,15 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
                struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 }
+static inline struct mem_cgroup *
+mem_cgroup_iter_cond(struct mem_cgroup *root,
+                struct mem_cgroup *prev,
+                struct mem_cgroup_reclaim_cookie *reclaim,
+                mem_cgroup_iter_filter cond)
+{
+        /* first call must return non-NULL, second return NULL */
+        return (struct mem_cgroup *)(unsigned long)!prev;
+}
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
@@ -348,22 +437,45 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 {
 }
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+        return false;
+}
+static inline void mem_cgroup_enable_oom(void)
+{
+}
+static inline void mem_cgroup_disable_oom(void)
+{
+}
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+        return false;
+}
+static inline bool mem_cgroup_oom_synchronize(void)
+{
+        return false;
+}
 static inline void mem_cgroup_inc_page_stat(struct page *page,
-                                            enum mem_cgroup_page_stat_item idx)
+                                            enum mem_cgroup_stat_index idx)
 {
 }
 static inline void mem_cgroup_dec_page_stat(struct page *page,
-                                            enum mem_cgroup_page_stat_item idx)
+                                            enum mem_cgroup_stat_index idx)
 {
 }
 static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+enum mem_cgroup_filter_t
-                                            gfp_t gfp_mask,
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-                                            unsigned long *total_scanned)
+                struct mem_cgroup *root)
 {
-        return 0;
+        return VISIT;
 }
 static inline void mem_cgroup_split_huge_fixup(struct page *head)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index caf543c7eaa7..8b6e55ee8855 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -176,6 +176,7 @@ 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
@@ -876,11 +877,12 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_NOPAGE 0x0100  /* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED 0x0200  /* ->fault locked the returned page */
 #define VM_FAULT_RETRY  0x0400  /* ->fault blocked, must retry */
+#define VM_FAULT_FALLBACK 0x0800        /* huge page fault failed, fall back to small */
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 #define VM_FAULT_ERROR  (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-                         VM_FAULT_HWPOISON_LARGE)
+                         VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
@@ -984,7 +986,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
        unmap_mapping_range(mapping, holebegin, holelen, 0);
 }
-extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 96a509b6be04..201a69749659 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -54,7 +54,7 @@ struct res_counter {
        struct res_counter *parent;
 };
-#define RESOURCE_MAX (unsigned long long)LLONG_MAX
+#define RES_COUNTER_MAX ULLONG_MAX
 /**
 * Helpers to interact with userspace
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 45f254dddafc..6682da36b293 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1393,6 +1393,13 @@ struct task_struct {
                unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
        } memcg_batch;
        unsigned int memcg_kmem_skip_account;
+        struct memcg_oom_info {
+                unsigned int may_oom:1;
+                unsigned int in_memcg_oom:1;
+                unsigned int oom_locked:1;
+                int wakeups;
+                struct mem_cgroup *wait_on_memcg;
+        } memcg_oom;
 #endif
 #ifdef CONFIG_UPROBES
        struct uprobe_task *utask;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c03c139219c9..46ba0c6c219f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -280,7 +280,7 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
-extern int lru_add_drain_all(void);
+extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_page(struct page *page);
 extern void swap_setup(void);
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 9bd0934f6c33..7a7d2ee96d42 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -74,7 +74,7 @@ static int __init gcov_persist_setup(char *str)
 {
        unsigned long val;
-        if (strict_strtoul(str, 0, &val)) {
+        if (kstrtoul(str, 0, &val)) {
                pr_warning("invalid gcov_persist parameter '%s'\n", str);
                return 0;
        }
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 6ada93c23a9a..9659d38e008f 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -113,7 +113,7 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj,
        unsigned long cnt;
        int ret;
-        if (strict_strtoul(buf, 0, &cnt))
+        if (kstrtoul(buf, 0, &cnt))
                return -EINVAL;
        ret = crash_shrink_memory(cnt);
diff --git a/kernel/params.c b/kernel/params.c
index 501bde4f3bee..81c4e78c8f4c 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -253,13 +253,13 @@ int parse_args(const char *doing,
        EXPORT_SYMBOL(param_ops_##name)
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, strict_strtoul);
+STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, strict_strtol);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, strict_strtoul);
+STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, strict_strtol);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, strict_strtoul);
+STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, strict_strtol);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, strict_strtoul);
+STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
 int param_set_charp(const char *val, const struct kernel_param *kp)
 {
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index ff55247e7049..4aa8a305aede 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -17,8 +17,8 @@
 void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
        spin_lock_init(&counter->lock);
-        counter->limit = RESOURCE_MAX;
+        counter->limit = RES_COUNTER_MAX;
-        counter->soft_limit = RESOURCE_MAX;
+        counter->soft_limit = RES_COUNTER_MAX;
        counter->parent = parent;
 }
@@ -178,23 +178,30 @@ u64 res_counter_read_u64(struct res_counter *counter, int member)
 #endif
 int res_counter_memparse_write_strategy(const char *buf,
-                                        unsigned long long *res)
+                                        unsigned long long *resp)
 {
        char *end;
+        unsigned long long res;
-        /* return RESOURCE_MAX(unlimited) if "-1" is specified */
+        /* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
        if (*buf == '-') {
-                *res = simple_strtoull(buf + 1, &end, 10);
+                res = simple_strtoull(buf + 1, &end, 10);
-                if (*res != 1 || *end != '\0')
+                if (res != 1 || *end != '\0')
                        return -EINVAL;
-                *res = RESOURCE_MAX;
+                *resp = RES_COUNTER_MAX;
                return 0;
        }
-        *res = memparse(buf, &end);
+        res = memparse(buf, &end);
        if (*end != '\0')
                return -EINVAL;
-        *res = PAGE_ALIGN(*res);
+        if (PAGE_ALIGN(res) >= res)
+                res = PAGE_ALIGN(res);
+        else
+                res = RES_COUNTER_MAX;
+        *resp = res;
        return 0;
 }
diff --git a/mm/Kconfig b/mm/Kconfig
index 6cdd27043303..026771a9b097 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -245,7 +245,7 @@ config COMPACTION
 config MIGRATION
        bool "Page migration"
        def_bool y
-        depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA
+        depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
        help
          Allows the migration of the physical location of pages of processes
          while the virtual addresses are not changed. This is useful in
@@ -480,7 +480,7 @@ config FRONTSWAP
 config CMA
        bool "Contiguous Memory Allocator"
-        depends on HAVE_MEMBLOCK
+        depends on HAVE_MEMBLOCK && MMU
        select MIGRATION
        select MEMORY_ISOLATION
        help
diff --git a/mm/filemap.c b/mm/filemap.c
index e607728db4a8..1e6aec4a2d2e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -467,32 +467,34 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
        error = mem_cgroup_cache_charge(page, current->mm,
                                        gfp_mask & GFP_RECLAIM_MASK);
        if (error)
-                goto out;
+                return error;
        error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
-        if (error == 0) {
+        if (error) {
-                page_cache_get(page);
-                page->mapping = mapping;
-                page->index = offset;
-                spin_lock_irq(&mapping->tree_lock);
-                error = radix_tree_insert(&mapping->page_tree, offset, page);
-                if (likely(!error)) {
-                        mapping->nrpages++;
-                        __inc_zone_page_state(page, NR_FILE_PAGES);
-                        spin_unlock_irq(&mapping->tree_lock);
-                        trace_mm_filemap_add_to_page_cache(page);
-                } else {
-                        page->mapping = NULL;
-                        /* Leave page->index set: truncation relies upon it */
-                        spin_unlock_irq(&mapping->tree_lock);
-                        mem_cgroup_uncharge_cache_page(page);
-                        page_cache_release(page);
-                }
-                radix_tree_preload_end();
-        } else
                mem_cgroup_uncharge_cache_page(page);
-out:
+                return error;
+        }
+        page_cache_get(page);
+        page->mapping = mapping;
+        page->index = offset;
+        spin_lock_irq(&mapping->tree_lock);
+        error = radix_tree_insert(&mapping->page_tree, offset, page);
+        radix_tree_preload_end();
+        if (unlikely(error))
+                goto err_insert;
+        mapping->nrpages++;
+        __inc_zone_page_state(page, NR_FILE_PAGES);
+        spin_unlock_irq(&mapping->tree_lock);
+        trace_mm_filemap_add_to_page_cache(page);
+        return 0;
+err_insert:
+        page->mapping = NULL;
+        /* Leave page->index set: truncation relies upon it */
+        spin_unlock_irq(&mapping->tree_lock);
+        mem_cgroup_uncharge_cache_page(page);
+        page_cache_release(page);
        return error;
 }
 EXPORT_SYMBOL(add_to_page_cache_locked);
@@ -1614,6 +1616,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        struct inode *inode = mapping->host;
        pgoff_t offset = vmf->pgoff;
        struct page *page;
+        bool memcg_oom;
        pgoff_t size;
        int ret = 0;
@@ -1622,7 +1625,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                return VM_FAULT_SIGBUS;
        /*
-         * Do we have something in the page cache already?
+         * Do we have something in the page cache already?  Either
+         * way, try readahead, but disable the memcg OOM killer for it
+         * as readahead is optional and no errors are propagated up
+         * the fault stack.  The OOM killer is enabled while trying to
+         * instantiate the faulting page individually below.
         */
        page = find_get_page(mapping, offset);
        if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
@@ -1630,10 +1637,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                 * We found the page, so try async readahead before
                 * waiting for the lock.
                 */
+                memcg_oom = mem_cgroup_toggle_oom(false);
                do_async_mmap_readahead(vma, ra, file, page, offset);
+                mem_cgroup_toggle_oom(memcg_oom);
        } else if (!page) {
                /* No page in the page cache at all */
+                memcg_oom = mem_cgroup_toggle_oom(false);
                do_sync_mmap_readahead(vma, ra, file, offset);
+                mem_cgroup_toggle_oom(memcg_oom);
                count_vm_event(PGMAJFAULT);
                mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
                ret = VM_FAULT_MAJOR;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d66010e0049d..7489884682d8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -695,11 +695,10 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
        return pmd;
 }
-static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma)
+static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 {
        pmd_t entry;
-        entry = mk_pmd(page, vma->vm_page_prot);
+        entry = mk_pmd(page, prot);
-        entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
        entry = pmd_mkhuge(entry);
        return entry;
 }
@@ -732,7 +731,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
                pte_free(mm, pgtable);
        } else {
                pmd_t entry;
-                entry = mk_huge_pmd(page, vma);
+                entry = mk_huge_pmd(page, vma->vm_page_prot);
+                entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
                page_add_new_anon_rmap(page, vma, haddr);
                pgtable_trans_huge_deposit(mm, pmd, pgtable);
                set_pmd_at(mm, haddr, pmd, entry);
@@ -788,77 +788,57 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
        struct page *page;
        unsigned long haddr = address & HPAGE_PMD_MASK;
-        pte_t *pte;
-        if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
+        if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
-                if (unlikely(anon_vma_prepare(vma)))
+                return VM_FAULT_FALLBACK;
-                        return VM_FAULT_OOM;
+        if (unlikely(anon_vma_prepare(vma)))
-                if (unlikely(khugepaged_enter(vma)))
+                return VM_FAULT_OOM;
+        if (unlikely(khugepaged_enter(vma)))
+                return VM_FAULT_OOM;
+        if (!(flags & FAULT_FLAG_WRITE) &&
+                        transparent_hugepage_use_zero_page()) {
+                pgtable_t pgtable;
+                struct page *zero_page;
+                bool set;
+                pgtable = pte_alloc_one(mm, haddr);
+                if (unlikely(!pgtable))
                        return VM_FAULT_OOM;
-                if (!(flags & FAULT_FLAG_WRITE) &&
+                zero_page = get_huge_zero_page();
-                                transparent_hugepage_use_zero_page()) {
+                if (unlikely(!zero_page)) {
-                        pgtable_t pgtable;
+                        pte_free(mm, pgtable);
-                        struct page *zero_page;
-                        bool set;
-                        pgtable = pte_alloc_one(mm, haddr);
-                        if (unlikely(!pgtable))
-                                return VM_FAULT_OOM;
-                        zero_page = get_huge_zero_page();
-                        if (unlikely(!zero_page)) {
-                                pte_free(mm, pgtable);
-                                count_vm_event(THP_FAULT_FALLBACK);
-                                goto out;
-                        }
-                        spin_lock(&mm->page_table_lock);
-                        set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
-                                        zero_page);
-                        spin_unlock(&mm->page_table_lock);
-                        if (!set) {
-                                pte_free(mm, pgtable);
-                                put_huge_zero_page();
-                        }
-                        return 0;
-                }
-                page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-                                          vma, haddr, numa_node_id(), 0);
-                if (unlikely(!page)) {
                        count_vm_event(THP_FAULT_FALLBACK);
-                        goto out;
+                        return VM_FAULT_FALLBACK;
-                }
-                count_vm_event(THP_FAULT_ALLOC);
-                if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
-                        put_page(page);
-                        goto out;
                }
-                if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
+                spin_lock(&mm->page_table_lock);
-                                                          page))) {
+                set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
-                        mem_cgroup_uncharge_page(page);
+                                zero_page);
-                        put_page(page);
+                spin_unlock(&mm->page_table_lock);
-                        goto out;
+                if (!set) {
+                        pte_free(mm, pgtable);
+                        put_huge_zero_page();
                }
                return 0;
        }
-out:
+        page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-        /*
+                        vma, haddr, numa_node_id(), 0);
-         * Use __pte_alloc instead of pte_alloc_map, because we can't
+        if (unlikely(!page)) {
-         * run pte_offset_map on the pmd, if an huge pmd could
+                count_vm_event(THP_FAULT_FALLBACK);
-         * materialize from under us from a different thread.
+                return VM_FAULT_FALLBACK;
-         */
+        }
-        if (unlikely(pmd_none(*pmd)) &&
+        if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
-            unlikely(__pte_alloc(mm, vma, pmd, address)))
+                put_page(page);
-                return VM_FAULT_OOM;
+                count_vm_event(THP_FAULT_FALLBACK);
-        /* if an huge pmd materialized from under us just retry later */
+                return VM_FAULT_FALLBACK;
-        if (unlikely(pmd_trans_huge(*pmd)))
+        }
-                return 0;
+        if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
-        /*
+                mem_cgroup_uncharge_page(page);
-         * A regular pmd is established and it can't morph into a huge pmd
+                put_page(page);
-         * from under us anymore at this point because we hold the mmap_sem
+                count_vm_event(THP_FAULT_FALLBACK);
-         * read mode and khugepaged takes it in write mode. So now it's
+                return VM_FAULT_FALLBACK;
-         * safe to run pte_offset_map().
+        }
-         */
-        pte = pte_offset_map(pmd, address);
+        count_vm_event(THP_FAULT_ALLOC);
-        return handle_pte_fault(mm, vma, address, pte, pmd, flags);
+        return 0;
 }
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -1170,7 +1150,6 @@ alloc:
                new_page = NULL;
        if (unlikely(!new_page)) {
-                count_vm_event(THP_FAULT_FALLBACK);
                if (is_huge_zero_pmd(orig_pmd)) {
                        ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
                                        address, pmd, orig_pmd, haddr);
@@ -1181,9 +1160,9 @@ alloc:
                                split_huge_page(page);
                        put_page(page);
                }
+                count_vm_event(THP_FAULT_FALLBACK);
                goto out;
        }
-        count_vm_event(THP_FAULT_ALLOC);
        if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
                put_page(new_page);
@@ -1191,10 +1170,13 @@ alloc:
                        split_huge_page(page);
                        put_page(page);
                }
+                count_vm_event(THP_FAULT_FALLBACK);
                ret |= VM_FAULT_OOM;
                goto out;
        }
+        count_vm_event(THP_FAULT_ALLOC);
        if (is_huge_zero_pmd(orig_pmd))
                clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
        else
@@ -1215,7 +1197,8 @@ alloc:
                goto out_mn;
        } else {
                pmd_t entry;
-                entry = mk_huge_pmd(new_page, vma);
+                entry = mk_huge_pmd(new_page, vma->vm_page_prot);
+                entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
                pmdp_clear_flush(vma, haddr, pmd);
                page_add_new_anon_rmap(new_page, vma, haddr);
                set_pmd_at(mm, haddr, pmd, entry);
@@ -1666,7 +1649,6 @@ static void __split_huge_page_refcount(struct page *page,
        BUG_ON(atomic_read(&page->_count) <= 0);
        __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);
-        __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
        ClearPageCompound(page);
        compound_unlock(page);
@@ -2364,7 +2346,8 @@ static void collapse_huge_page(struct mm_struct *mm,
        __SetPageUptodate(new_page);
        pgtable = pmd_pgtable(_pmd);
-        _pmd = mk_huge_pmd(new_page, vma);
+        _pmd = mk_huge_pmd(new_page, vma->vm_page_prot);
+        _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
        /*
         * spin_lock() below is not the equivalent of smp_wmb(), so
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c6bd28edd533..d5ff3ce13029 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,7 +39,6 @@
 #include <linux/limits.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -85,26 +84,12 @@ static int really_do_swap_account __initdata = 0;
 #endif
-/*
- * Statistics for memory cgroup.
- */
-enum mem_cgroup_stat_index {
-        /*
-         * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
-         */
-        MEM_CGROUP_STAT_CACHE,          /* # of pages charged as cache */
-        MEM_CGROUP_STAT_RSS,            /* # of pages charged as anon rss */
-        MEM_CGROUP_STAT_RSS_HUGE,       /* # of pages charged as anon huge */
-        MEM_CGROUP_STAT_FILE_MAPPED,    /* # of pages charged as file rss */
-        MEM_CGROUP_STAT_SWAP,           /* # of pages, swapped out */
-        MEM_CGROUP_STAT_NSTATS,
-};
 static const char * const mem_cgroup_stat_names[] = {
        "cache",
        "rss",
        "rss_huge",
        "mapped_file",
+        "writeback",
        "swap",
 };
@@ -175,10 +160,6 @@ struct mem_cgroup_per_zone {
        struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
-        struct rb_node          tree_node;      /* RB tree node */
-        unsigned long long      usage_in_excess;/* Set to the value by which */
-                                                /* the soft limit is exceeded*/
-        bool                    on_tree;
        struct mem_cgroup       *memcg;         /* Back pointer, we cannot */
                                                /* use container_of        */
 };
@@ -187,26 +168,6 @@ struct mem_cgroup_per_node {
        struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
 };
-/*
- * Cgroups above their limits are maintained in a RB-Tree, independent of
- * their hierarchy representation
- */
-struct mem_cgroup_tree_per_zone {
-        struct rb_root rb_root;
-        spinlock_t lock;
-};
-struct mem_cgroup_tree_per_node {
-        struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
-};
-struct mem_cgroup_tree {
-        struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
-};
-static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 struct mem_cgroup_threshold {
        struct eventfd_ctx *eventfd;
        u64 threshold;
@@ -280,6 +241,7 @@ struct mem_cgroup {
        bool            oom_lock;
        atomic_t        under_oom;
+        atomic_t        oom_wakeups;
        int     swappiness;
        /* OOM-Killer disable */
@@ -304,7 +266,7 @@ struct mem_cgroup {
         * Should we move charges of a task when a task is moved into this
         * mem_cgroup ? And what type of charges should we move ?
         */
-        unsigned long   move_charge_at_immigrate;
+        unsigned long move_charge_at_immigrate;
        /*
         * set > 0 if pages under this cgroup are moving to other cgroup.
         */
@@ -341,6 +303,22 @@ struct mem_cgroup {
        atomic_t        numainfo_events;
        atomic_t        numainfo_updating;
 #endif
+        /*
+         * Protects soft_contributed transitions.
+         * See mem_cgroup_update_soft_limit
+         */
+        spinlock_t soft_lock;
+        /*
+         * If true then this group has increased parents' children_in_excess
+         * when it got over the soft limit.
+         * When a group falls bellow the soft limit, parents' children_in_excess
+         * is decreased and soft_contributed changed to false.
+         */
+        bool soft_contributed;
+        /* Number of children that are in soft limit excess */
+        atomic_t children_in_excess;
        struct mem_cgroup_per_node *nodeinfo[0];
        /* WARNING: nodeinfo must be the last member here */
@@ -444,7 +422,6 @@ static bool move_file(void)
 * limit reclaim to prevent infinite loops, if they ever occur.
 */
 #define MEM_CGROUP_MAX_RECLAIM_LOOPS            100
-#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2
 enum charge_type {
        MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
@@ -671,164 +648,6 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
        return mem_cgroup_zoneinfo(memcg, nid, zid);
 }
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_node_zone(int nid, int zid)
-{
-        return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
-}
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_from_page(struct page *page)
-{
-        int nid = page_to_nid(page);
-        int zid = page_zonenum(page);
-        return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
-}
-static void
-__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
-                                struct mem_cgroup_per_zone *mz,
-                                struct mem_cgroup_tree_per_zone *mctz,
-                                unsigned long long new_usage_in_excess)
-{
-        struct rb_node **p = &mctz->rb_root.rb_node;
-        struct rb_node *parent = NULL;
-        struct mem_cgroup_per_zone *mz_node;
-        if (mz->on_tree)
-                return;
-        mz->usage_in_excess = new_usage_in_excess;
-        if (!mz->usage_in_excess)
-                return;
-        while (*p) {
-                parent = *p;
-                mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
-                                        tree_node);
-                if (mz->usage_in_excess < mz_node->usage_in_excess)
-                        p = &(*p)->rb_left;
-                /*
-                 * We can't avoid mem cgroups that are over their soft
-                 * limit by the same amount
-                 */
-                else if (mz->usage_in_excess >= mz_node->usage_in_excess)
-                        p = &(*p)->rb_right;
-        }
-        rb_link_node(&mz->tree_node, parent, p);
-        rb_insert_color(&mz->tree_node, &mctz->rb_root);
-        mz->on_tree = true;
-}
-static void
-__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
-                                struct mem_cgroup_per_zone *mz,
-                                struct mem_cgroup_tree_per_zone *mctz)
-{
-        if (!mz->on_tree)
-                return;
-        rb_erase(&mz->tree_node, &mctz->rb_root);
-        mz->on_tree = false;
-}
-static void
-mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
-                                struct mem_cgroup_per_zone *mz,
-                                struct mem_cgroup_tree_per_zone *mctz)
-{
-        spin_lock(&mctz->lock);
-        __mem_cgroup_remove_exceeded(memcg, mz, mctz);
-        spin_unlock(&mctz->lock);
-}
-static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
-{
-        unsigned long long excess;
-        struct mem_cgroup_per_zone *mz;
-        struct mem_cgroup_tree_per_zone *mctz;
-        int nid = page_to_nid(page);
-        int zid = page_zonenum(page);
-        mctz = soft_limit_tree_from_page(page);
-        /*
-         * Necessary to update all ancestors when hierarchy is used.
-         * because their event counter is not touched.
-         */
-        for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-                mz = mem_cgroup_zoneinfo(memcg, nid, zid);
-                excess = res_counter_soft_limit_excess(&memcg->res);
-                /*
-                 * We have to update the tree if mz is on RB-tree or
-                 * mem is over its softlimit.
-                 */
-                if (excess || mz->on_tree) {
-                        spin_lock(&mctz->lock);
-                        /* if on-tree, remove it */
-                        if (mz->on_tree)
-                                __mem_cgroup_remove_exceeded(memcg, mz, mctz);
-                        /*
-                         * Insert again. mz->usage_in_excess will be updated.
-                         * If excess is 0, no tree ops.
-                         */
-                        __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
-                        spin_unlock(&mctz->lock);
-                }
-        }
-}
-static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
-{
-        int node, zone;
-        struct mem_cgroup_per_zone *mz;
-        struct mem_cgroup_tree_per_zone *mctz;
-        for_each_node(node) {
-                for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-                        mz = mem_cgroup_zoneinfo(memcg, node, zone);
-                        mctz = soft_limit_tree_node_zone(node, zone);
-                        mem_cgroup_remove_exceeded(memcg, mz, mctz);
-                }
-        }
-}
-static struct mem_cgroup_per_zone *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
-{
-        struct rb_node *rightmost = NULL;
-        struct mem_cgroup_per_zone *mz;
-retry:
-        mz = NULL;
-        rightmost = rb_last(&mctz->rb_root);
-        if (!rightmost)
-                goto done;              /* Nothing to reclaim from */
-        mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
-        /*
-         * Remove the node now but someone else can add it back,
-         * we will to add it back at the end of reclaim to its correct
-         * position in the tree.
-         */
-        __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
-        if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
-                !css_tryget(&mz->memcg->css))
-                goto retry;
-done:
-        return mz;
-}
-static struct mem_cgroup_per_zone *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
-{
-        struct mem_cgroup_per_zone *mz;
-        spin_lock(&mctz->lock);
-        mz = __mem_cgroup_largest_soft_limit_node(mctz);
-        spin_unlock(&mctz->lock);
-        return mz;
-}
 /*
 * Implementation Note: reading percpu statistics for memcg.
 *
@@ -1003,6 +822,48 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 }
 /*
+ * Called from rate-limited memcg_check_events when enough
+ * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure
+ * that all the parents up the hierarchy will be notified that this group
+ * is in excess or that it is not in excess anymore. mmecg->soft_contributed
+ * makes the transition a single action whenever the state flips from one to
+ * the other.
+ */
+static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg)
+{
+        unsigned long long excess = res_counter_soft_limit_excess(&memcg->res);
+        struct mem_cgroup *parent = memcg;
+        int delta = 0;
+        spin_lock(&memcg->soft_lock);
+        if (excess) {
+                if (!memcg->soft_contributed) {
+                        delta = 1;
+                        memcg->soft_contributed = true;
+                }
+        } else {
+                if (memcg->soft_contributed) {
+                        delta = -1;
+                        memcg->soft_contributed = false;
+                }
+        }
+        /*
+         * Necessary to update all ancestors when hierarchy is used
+         * because their event counter is not touched.
+         * We track children even outside the hierarchy for the root
+         * cgroup because tree walk starting at root should visit
+         * all cgroups and we want to prevent from pointless tree
+         * walk if no children is below the limit.
+         */
+        while (delta && (parent = parent_mem_cgroup(parent)))
+                atomic_add(delta, &parent->children_in_excess);
+        if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
+                atomic_add(delta, &root_mem_cgroup->children_in_excess);
+        spin_unlock(&memcg->soft_lock);
+}
+/*
 * Check events in order.
 *
 */
@@ -1025,7 +886,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
                mem_cgroup_threshold(memcg);
                if (unlikely(do_softlimit))
-                        mem_cgroup_update_tree(memcg, page);
+                        mem_cgroup_update_soft_limit(memcg);
 #if MAX_NUMNODES > 1
                if (unlikely(do_numainfo))
                        atomic_inc(&memcg->numainfo_events);
@@ -1068,6 +929,15 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
        return memcg;
 }
+static enum mem_cgroup_filter_t
+mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
+                mem_cgroup_iter_filter cond)
+{
+        if (!cond)
+                return VISIT;
+        return cond(memcg, root);
+}
 /*
 * Returns a next (in a pre-order walk) alive memcg (with elevated css
 * ref. count) or NULL if the whole root's subtree has been visited.
@@ -1075,7 +945,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 * helper function to be used by mem_cgroup_iter
 */
 static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-                struct mem_cgroup *last_visited)
+                struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond)
 {
        struct cgroup_subsys_state *prev_css, *next_css;
@@ -1093,11 +963,31 @@ skip_node:
        if (next_css) {
                struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
-                if (css_tryget(&mem->css))
+                switch (mem_cgroup_filter(mem, root, cond)) {
-                        return mem;
+                case SKIP:
-                else {
                        prev_css = next_css;
                        goto skip_node;
+                case SKIP_TREE:
+                        if (mem == root)
+                                return NULL;
+                        /*
+                         * css_rightmost_descendant is not an optimal way to
+                         * skip through a subtree (especially for imbalanced
+                         * trees leaning to right) but that's what we have right
+                         * now. More effective solution would be traversing
+                         * right-up for first non-NULL without calling
+                         * css_next_descendant_pre afterwards.
+                         */
+                        prev_css = css_rightmost_descendant(next_css);
+                        goto skip_node;
+                case VISIT:
+                        if (css_tryget(&mem->css))
+                                return mem;
+                        else {
+                                prev_css = next_css;
+                                goto skip_node;
+                        }
+                        break;
                }
        }
@@ -1161,6 +1051,7 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
 * @root: hierarchy root
 * @prev: previously returned memcg, NULL on first invocation
 * @reclaim: cookie for shared reclaim walks, NULL for full walks
+ * @cond: filter for visited nodes, NULL for no filter
 *
 * Returns references to children of the hierarchy below @root, or
 * @root itself, or %NULL after a full round-trip.
@@ -1173,15 +1064,18 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
 * divide up the memcgs in the hierarchy among all concurrent
 * reclaimers operating on the same zone and priority.
 */
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
+struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
                                   struct mem_cgroup *prev,
-                                   struct mem_cgroup_reclaim_cookie *reclaim)
+                                   struct mem_cgroup_reclaim_cookie *reclaim,
+                                   mem_cgroup_iter_filter cond)
 {
        struct mem_cgroup *memcg = NULL;
        struct mem_cgroup *last_visited = NULL;
-        if (mem_cgroup_disabled())
+        if (mem_cgroup_disabled()) {
-                return NULL;
+                /* first call must return non-NULL, second return NULL */
+                return (struct mem_cgroup *)(unsigned long)!prev;
+        }
        if (!root)
                root = root_mem_cgroup;
@@ -1192,7 +1086,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
        if (!root->use_hierarchy && root != root_mem_cgroup) {
                if (prev)
                        goto out_css_put;
-                return root;
+                if (mem_cgroup_filter(root, root, cond) == VISIT)
+                        return root;
+                return NULL;
        }
        rcu_read_lock();
@@ -1215,7 +1111,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
                        last_visited = mem_cgroup_iter_load(iter, root, &seq);
                }
-                memcg = __mem_cgroup_iter_next(root, last_visited);
+                memcg = __mem_cgroup_iter_next(root, last_visited, cond);
                if (reclaim) {
                        mem_cgroup_iter_update(iter, last_visited, memcg, seq);
@@ -1226,7 +1122,11 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
                                reclaim->generation = iter->generation;
                }
-                if (prev && !memcg)
+                /*
+                 * We have finished the whole tree walk or no group has been
+                 * visited because filter told us to skip the root node.
+                 */
+                if (!memcg && (prev || (cond && !last_visited)))
                        goto out_unlock;
        }
 out_unlock:
@@ -1867,6 +1767,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
        return total;
 }
+#if MAX_NUMNODES > 1
 /**
 * test_mem_cgroup_node_reclaimable
 * @memcg: the target memcg
@@ -1889,7 +1790,6 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
        return false;
 }
-#if MAX_NUMNODES > 1
 /*
 * Always updating the nodemask is not very good - even if we have an empty
@@ -1957,115 +1857,64 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
        return node;
 }
-/*
- * Check all nodes whether it contains reclaimable pages or not.
- * For quick scan, we make use of scan_nodes. This will allow us to skip
- * unused nodes. But scan_nodes is lazily updated and may not cotain
- * enough new information. We need to do double check.
- */
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
-        int nid;
-        /*
-         * quick check...making use of scan_node.
-         * We can skip unused nodes.
-         */
-        if (!nodes_empty(memcg->scan_nodes)) {
-                for (nid = first_node(memcg->scan_nodes);
-                     nid < MAX_NUMNODES;
-                     nid = next_node(nid, memcg->scan_nodes)) {
-                        if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
-                                return true;
-                }
-        }
-        /*
-         * Check rest of nodes.
-         */
-        for_each_node_state(nid, N_MEMORY) {
-                if (node_isset(nid, memcg->scan_nodes))
-                        continue;
-                if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
-                        return true;
-        }
-        return false;
-}
 #else
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
        return 0;
 }
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
-        return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
-}
 #endif
-static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+/*
-                                   struct zone *zone,
+ * A group is eligible for the soft limit reclaim under the given root
-                                   gfp_t gfp_mask,
+ * hierarchy if
-                                   unsigned long *total_scanned)
+ *      a) it is over its soft limit
-{
+ *      b) any parent up the hierarchy is over its soft limit
-        struct mem_cgroup *victim = NULL;
+ *
-        int total = 0;
+ * If the given group doesn't have any children over the limit then it
-        int loop = 0;
+ * doesn't make any sense to iterate its subtree.
-        unsigned long excess;
+ */
-        unsigned long nr_scanned;
+enum mem_cgroup_filter_t
-        struct mem_cgroup_reclaim_cookie reclaim = {
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-                .zone = zone,
+                struct mem_cgroup *root)
-                .priority = 0,
+{
-        };
+        struct mem_cgroup *parent;
-        excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+        if (!memcg)
+                memcg = root_mem_cgroup;
-        while (1) {
+        parent = memcg;
-                victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
-                if (!victim) {
+        if (res_counter_soft_limit_excess(&memcg->res))
-                        loop++;
+                return VISIT;
-                        if (loop >= 2) {
-                                /*
+        /*
-                                 * If we have not been able to reclaim
+         * If any parent up to the root in the hierarchy is over its soft limit
-                                 * anything, it might because there are
+         * then we have to obey and reclaim from this group as well.
-                                 * no reclaimable pages under this hierarchy
+         */
-                                 */
+        while ((parent = parent_mem_cgroup(parent))) {
-                                if (!total)
+                if (res_counter_soft_limit_excess(&parent->res))
-                                        break;
+                        return VISIT;
-                                /*
+                if (parent == root)
-                                 * We want to do more targeted reclaim.
-                                 * excess >> 2 is not to excessive so as to
-                                 * reclaim too much, nor too less that we keep
-                                 * coming back to reclaim from this cgroup
-                                 */
-                                if (total >= (excess >> 2) ||
-                                        (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
-                                        break;
-                        }
-                        continue;
-                }
-                if (!mem_cgroup_reclaimable(victim, false))
-                        continue;
-                total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
-                                                     zone, &nr_scanned);
-                *total_scanned += nr_scanned;
-                if (!res_counter_soft_limit_excess(&root_memcg->res))
                        break;
        }
-        mem_cgroup_iter_break(root_memcg, victim);
-        return total;
+        if (!atomic_read(&memcg->children_in_excess))
+                return SKIP_TREE;
+        return SKIP;
 }
+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) {
                        /*
@@ -2079,33 +1928,33 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
                        iter->oom_lock = true;
        }
-        if (!failed)
+        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
-         * 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) {
-        for_each_mem_cgroup_tree(iter, memcg) {
+                                mem_cgroup_iter_break(memcg, iter);
-                if (iter == failed) {
+                                break;
-                        mem_cgroup_iter_break(memcg, iter);
+                        }
-                        break;
+                        iter->oom_lock = false;
                }
-                iter->oom_lock = false;
        }
-        return false;
+        spin_unlock(&memcg_oom_lock);
+        return !failed;
 }
-/*
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
- * Has to be called with memcg_oom_lock
- */
-static int 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)
@@ -2129,7 +1978,6 @@ 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 {
@@ -2159,6 +2007,7 @@ 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);
 }
@@ -2170,56 +2019,136 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 }
 /*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+ * try to call OOM killer
 */
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
-                                  int order)
 {
-        struct oom_wait_info owait;
+        bool locked;
-        bool locked, need_to_kill;
+        int wakeups;
-        owait.memcg = memcg;
+        if (!current->memcg_oom.may_oom)
-        owait.wait.flags = 0;
+                return;
-        owait.wait.func = memcg_oom_wake_function;
-        owait.wait.private = current;
+        current->memcg_oom.in_memcg_oom = 1;
-        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
+         * As with any blocking lock, a contender needs to start
-         * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
+         * listening for wakeups before attempting the trylock,
-         * under OOM is always welcomed, use TASK_KILLABLE here.
+         * otherwise it can miss the wakeup from the unlock and sleep
+         * indefinitely.  This is just open-coded because our locking
+         * is so particular to memcg hierarchies.
         */
-        prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
+        wakeups = atomic_read(&memcg->oom_wakeups);
-        if (!locked || memcg->oom_kill_disable)
+        mem_cgroup_mark_under_oom(memcg);
-                need_to_kill = false;
+        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) {
-                finish_wait(&memcg_oom_waitq, &owait.wait);
+                mem_cgroup_unmark_under_oom(memcg);
                mem_cgroup_out_of_memory(memcg, mask, order);
+                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);
        } else {
-                schedule();
+                /*
-                finish_wait(&memcg_oom_waitq, &owait.wait);
+                 * A system call can just return -ENOMEM, but if this
+                 * is a page fault and somebody else is handling the
+                 * OOM already, we need to sleep on the OOM waitqueue
+                 * for this memcg until the situation is resolved.
+                 * Which can take some time because it might be
+                 * handled by a userspace task.
+                 *
+                 * However, this is the charge context, which means
+                 * that we may sit on a large call stack and hold
+                 * various filesystem locks, the mmap_sem etc. and we
+                 * don't want the OOM handler to deadlock on them
+                 * while we sit here and wait.  Store the current OOM
+                 * context in the task_struct, then return -ENOMEM.
+                 * At the end of the page fault handler, with the
+                 * stack unwound, pagefault_out_of_memory() will check
+                 * back with us by calling
+                 * mem_cgroup_oom_synchronize(), possibly putting the
+                 * task to sleep.
+                 */
+                current->memcg_oom.oom_locked = locked;
+                current->memcg_oom.wakeups = wakeups;
+                css_get(&memcg->css);
+                current->memcg_oom.wait_on_memcg = memcg;
        }
-        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);
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ *
+ * This has to be called at the end of a page fault if the the memcg
+ * OOM handler was enabled and the fault is returning %VM_FAULT_OOM.
+ *
+ * Memcg supports userspace OOM handling, so 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 put the task to sleep and clean up the
+ * OOM state.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * finalized, %false otherwise.
+ */
+bool mem_cgroup_oom_synchronize(void)
+{
+        struct oom_wait_info owait;
+        struct mem_cgroup *memcg;
-        if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+        /* OOM is global, do not handle */
+        if (!current->memcg_oom.in_memcg_oom)
                return false;
-        /* Give chance to dying process */
-        schedule_timeout_uninterruptible(1);
+        /*
+         * We invoked the OOM killer but there is a chance that a kill
+         * did not free up any charges.  Everybody else might already
+         * be sleeping, so restart the fault and keep the rampage
+         * going until some charges are released.
+         */
+        memcg = current->memcg_oom.wait_on_memcg;
+        if (!memcg)
+                goto out;
+        if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+                goto out_memcg;
+        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);
+        prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
+        /* Only sleep if we didn't miss any wakeups since OOM */
+        if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups)
+                schedule();
+        finish_wait(&memcg_oom_waitq, &owait.wait);
+out_memcg:
+        mem_cgroup_unmark_under_oom(memcg);
+        if (current->memcg_oom.oom_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);
+        }
+        css_put(&memcg->css);
+        current->memcg_oom.wait_on_memcg = NULL;
+out:
+        current->memcg_oom.in_memcg_oom = 0;
        return true;
 }
@@ -2288,7 +2217,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
 }
 void mem_cgroup_update_page_stat(struct page *page,
-                                 enum mem_cgroup_page_stat_item idx, int val)
+                                 enum mem_cgroup_stat_index idx, int val)
 {
        struct mem_cgroup *memcg;
        struct page_cgroup *pc = lookup_page_cgroup(page);
@@ -2297,18 +2226,11 @@ void mem_cgroup_update_page_stat(struct page *page,
        if (mem_cgroup_disabled())
                return;
+        VM_BUG_ON(!rcu_read_lock_held());
        memcg = pc->mem_cgroup;
        if (unlikely(!memcg || !PageCgroupUsed(pc)))
                return;
-        switch (idx) {
-        case MEMCG_NR_FILE_MAPPED:
-                idx = MEM_CGROUP_STAT_FILE_MAPPED;
-                break;
-        default:
-                BUG();
-        }
        this_cpu_add(memcg->stat->count[idx], val);
 }
@@ -2450,7 +2372,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
                        flush_work(&stock->work);
        }
 out:
-        put_online_cpus();
+        put_online_cpus();
 }
 /*
@@ -2532,12 +2454,11 @@ 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;
@@ -2594,14 +2515,10 @@ 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 (invoke_oom)
-        if (!oom_check)
+                mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
-                return CHARGE_NOMEM;
-        /* check OOM */
-        if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
-                return CHARGE_OOM_DIE;
-        return CHARGE_RETRY;
+        return CHARGE_NOMEM;
 }
 /*
@@ -2704,7 +2621,7 @@ again:
        }
        do {
-                bool oom_check;
+                bool invoke_oom = oom && !nr_oom_retries;
                /* If killed, bypass charge */
                if (fatal_signal_pending(current)) {
@@ -2712,14 +2629,8 @@ again:
                        goto bypass;
                }
-                oom_check = false;
+                ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
-                if (oom && !nr_oom_retries) {
+                                           nr_pages, invoke_oom);
-                        oom_check = true;
-                        nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
-                }
-                ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
-                    oom_check);
                switch (ret) {
                case CHARGE_OK:
                        break;
@@ -2732,16 +2643,12 @@ 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);
@@ -2882,7 +2789,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
         * is accessed after testing USED bit. To make pc->mem_cgroup visible
         * before USED bit, we need memory barrier here.
         * See mem_cgroup_add_lru_list(), etc.
-         */
+         */
        smp_wmb();
        SetPageCgroupUsed(pc);
@@ -2905,9 +2812,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
        unlock_page_cgroup(pc);
        /*
-         * "charge_statistics" updated event counter. Then, check it.
+         * "charge_statistics" updated event counter.
-         * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
-         * if they exceeds softlimit.
         */
        memcg_check_events(memcg, page);
 }
@@ -3626,9 +3531,9 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
         * the page allocator. Therefore, the following sequence when backed by
         * the SLUB allocator:
         *
-         *      memcg_stop_kmem_account();
+         *      memcg_stop_kmem_account();
-         *      kmalloc(<large_number>)
+         *      kmalloc(<large_number>)
-         *      memcg_resume_kmem_account();
+         *      memcg_resume_kmem_account();
         *
         * would effectively ignore the fact that we should skip accounting,
         * since it will drive us directly to this function without passing
@@ -3750,6 +3655,20 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline
+void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
+                                        struct mem_cgroup *to,
+                                        unsigned int nr_pages,
+                                        enum mem_cgroup_stat_index idx)
+{
+        /* Update stat data for mem_cgroup */
+        preempt_disable();
+        WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
+        __this_cpu_add(from->stat->count[idx], -nr_pages);
+        __this_cpu_add(to->stat->count[idx], nr_pages);
+        preempt_enable();
+}
 /**
 * mem_cgroup_move_account - move account of the page
 * @page: the page
@@ -3795,13 +3714,14 @@ static int mem_cgroup_move_account(struct page *page,
        move_lock_mem_cgroup(from, &flags);
-        if (!anon && page_mapped(page)) {
+        if (!anon && page_mapped(page))
-                /* Update mapped_file data for mem_cgroup */
+                mem_cgroup_move_account_page_stat(from, to, nr_pages,
-                preempt_disable();
+                        MEM_CGROUP_STAT_FILE_MAPPED);
-                __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-                __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+        if (PageWriteback(page))
-                preempt_enable();
+                mem_cgroup_move_account_page_stat(from, to, nr_pages,
-        }
+                        MEM_CGROUP_STAT_WRITEBACK);
        mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
        /* caller should have done css_get */
@@ -4657,7 +4577,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
                                   MEM_CGROUP_RECLAIM_SHRINK);
                curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
                /* Usage is reduced ? */
-                if (curusage >= oldusage)
+                if (curusage >= oldusage)
                        retry_count--;
                else
                        oldusage = curusage;
@@ -4678,7 +4598,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
        int enlarge = 0;
        /* see mem_cgroup_resize_res_limit */
-        retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+        retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
        oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
        while (retry_count) {
                if (signal_pending(current)) {
@@ -4727,98 +4647,6 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
        return ret;
 }
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
-                                            gfp_t gfp_mask,
-                                            unsigned long *total_scanned)
-{
-        unsigned long nr_reclaimed = 0;
-        struct mem_cgroup_per_zone *mz, *next_mz = NULL;
-        unsigned long reclaimed;
-        int loop = 0;
-        struct mem_cgroup_tree_per_zone *mctz;
-        unsigned long long excess;
-        unsigned long nr_scanned;
-        if (order > 0)
-                return 0;
-        mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
-        /*
-         * This loop can run a while, specially if mem_cgroup's continuously
-         * keep exceeding their soft limit and putting the system under
-         * pressure
-         */
-        do {
-                if (next_mz)
-                        mz = next_mz;
-                else
-                        mz = mem_cgroup_largest_soft_limit_node(mctz);
-                if (!mz)
-                        break;
-                nr_scanned = 0;
-                reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
-                                                    gfp_mask, &nr_scanned);
-                nr_reclaimed += reclaimed;
-                *total_scanned += nr_scanned;
-                spin_lock(&mctz->lock);
-                /*
-                 * If we failed to reclaim anything from this memory cgroup
-                 * it is time to move on to the next cgroup
-                 */
-                next_mz = NULL;
-                if (!reclaimed) {
-                        do {
-                                /*
-                                 * Loop until we find yet another one.
-                                 *
-                                 * By the time we get the soft_limit lock
-                                 * again, someone might have aded the
-                                 * group back on the RB tree. Iterate to
-                                 * make sure we get a different mem.
-                                 * mem_cgroup_largest_soft_limit_node returns
-                                 * NULL if no other cgroup is present on
-                                 * the tree
-                                 */
-                                next_mz =
-                                __mem_cgroup_largest_soft_limit_node(mctz);
-                                if (next_mz == mz)
-                                        css_put(&next_mz->memcg->css);
-                                else /* next_mz == NULL or other memcg */
-                                        break;
-                        } while (1);
-                }
-                __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
-                excess = res_counter_soft_limit_excess(&mz->memcg->res);
-                /*
-                 * One school of thought says that we should not add
-                 * back the node to the tree if reclaim returns 0.
-                 * But our reclaim could return 0, simply because due
-                 * to priority we are exposing a smaller subset of
-                 * memory to reclaim from. Consider this as a longer
-                 * term TODO.
-                 */
-                /* If excess == 0, no tree ops */
-                __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
-                spin_unlock(&mctz->lock);
-                css_put(&mz->memcg->css);
-                loop++;
-                /*
-                 * Could not reclaim anything and there are no more
-                 * mem cgroups to try or we seem to be looping without
-                 * reclaiming anything.
-                 */
-                if (!nr_reclaimed &&
-                        (next_mz == NULL ||
-                        loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
-                        break;
-        } while (!nr_reclaimed);
-        if (next_mz)
-                css_put(&next_mz->memcg->css);
-        return nr_reclaimed;
-}
 /**
 * mem_cgroup_force_empty_list - clears LRU of a group
 * @memcg: group to clear
@@ -4990,18 +4818,12 @@ static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
                                        unsigned int event)
 {
        struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-        int ret;
        if (mem_cgroup_is_root(memcg))
                return -EINVAL;
-        css_get(&memcg->css);
+        return mem_cgroup_force_empty(memcg);
-        ret = mem_cgroup_force_empty(memcg);
-        css_put(&memcg->css);
-        return ret;
 }
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
                                     struct cftype *cft)
 {
@@ -5139,7 +4961,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val)
         */
        mutex_lock(&memcg_create_mutex);
        mutex_lock(&set_limit_mutex);
-        if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
+        if (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) {
                if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) {
                        ret = -EBUSY;
                        goto out;
@@ -5149,7 +4971,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val)
                ret = memcg_update_cache_sizes(memcg);
                if (ret) {
-                        res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+                        res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX);
                        goto out;
                }
                static_key_slow_inc(&memcg_kmem_enabled_key);
@@ -6089,8 +5911,6 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
        for (zone = 0; zone < MAX_NR_ZONES; zone++) {
                mz = &pn->zoneinfo[zone];
                lruvec_init(&mz->lruvec);
-                mz->usage_in_excess = 0;
-                mz->on_tree = false;
                mz->memcg = memcg;
        }
        memcg->nodeinfo[node] = pn;
@@ -6146,7 +5966,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
        int node;
        size_t size = memcg_size();
-        mem_cgroup_remove_from_trees(memcg);
        free_css_id(&mem_cgroup_subsys, &memcg->css);
        for_each_node(node)
@@ -6183,29 +6002,6 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
-static void __init mem_cgroup_soft_limit_tree_init(void)
-{
-        struct mem_cgroup_tree_per_node *rtpn;
-        struct mem_cgroup_tree_per_zone *rtpz;
-        int tmp, node, zone;
-        for_each_node(node) {
-                tmp = node;
-                if (!node_state(node, N_NORMAL_MEMORY))
-                        tmp = -1;
-                rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
-                BUG_ON(!rtpn);
-                soft_limit_tree.rb_tree_per_node[node] = rtpn;
-                for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-                        rtpz = &rtpn->rb_tree_per_zone[zone];
-                        rtpz->rb_root = RB_ROOT;
-                        spin_lock_init(&rtpz->lock);
-                }
-        }
-}
 static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -6235,6 +6031,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
        mutex_init(&memcg->thresholds_lock);
        spin_lock_init(&memcg->move_lock);
        vmpressure_init(&memcg->vmpressure);
+        spin_lock_init(&memcg->soft_lock);
        return &memcg->css;
@@ -6312,6 +6109,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
        mem_cgroup_invalidate_reclaim_iterators(memcg);
        mem_cgroup_reparent_charges(memcg);
+        if (memcg->soft_contributed) {
+                while ((memcg = parent_mem_cgroup(memcg)))
+                        atomic_dec(&memcg->children_in_excess);
+                if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
+                        atomic_dec(&root_mem_cgroup->children_in_excess);
+        }
        mem_cgroup_destroy_all_caches(memcg);
        vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -6986,7 +6790,6 @@ static int __init mem_cgroup_init(void)
 {
        hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
        enable_swap_cgroup();
-        mem_cgroup_soft_limit_tree_init();
        memcg_stock_init();
        return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 2b73dbde2274..ca0003947115 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3695,7 +3695,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
-int handle_pte_fault(struct mm_struct *mm,
+static int handle_pte_fault(struct mm_struct *mm,
                     struct vm_area_struct *vma, unsigned long address,
                     pte_t *pte, pmd_t *pmd, unsigned int flags)
 {
@@ -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,
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-                unsigned long address, unsigned int flags)
+                             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);
@@ -3782,9 +3774,12 @@ retry:
        if (!pmd)
                return VM_FAULT_OOM;
        if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+                int ret = VM_FAULT_FALLBACK;
                if (!vma->vm_ops)
-                        return do_huge_pmd_anonymous_page(mm, vma, address,
+                        ret = do_huge_pmd_anonymous_page(mm, vma, address,
-                                                          pmd, flags);
+                                        pmd, flags);
+                if (!(ret & VM_FAULT_FALLBACK))
+                        return ret;
        } else {
                pmd_t orig_pmd = *pmd;
                int ret;
@@ -3850,6 +3845,37 @@ 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_enable_oom();
+        ret = __handle_mm_fault(mm, vma, address, flags);
+        if (flags & FAULT_FLAG_USER)
+                mem_cgroup_disable_oom();
+        if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)))
+                mem_cgroup_oom_synchronize();
+        return ret;
+}
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
 * Allocate page upper directory.
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 98e75f2ac7bc..314e9d274381 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -678,9 +678,12 @@ out:
 */
 void pagefault_out_of_memory(void)
 {
-        struct zonelist *zonelist = node_zonelist(first_online_node,
+        struct zonelist *zonelist;
-                                                  GFP_KERNEL);
+        if (mem_cgroup_oom_synchronize())
+                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/mm/page-writeback.c b/mm/page-writeback.c
index 6c7b0187be8e..f5236f804aa6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2143,11 +2143,17 @@ EXPORT_SYMBOL(account_page_dirtied);
 /*
 * Helper function for set_page_writeback family.
+ *
+ * The caller must hold mem_cgroup_begin/end_update_page_stat() lock
+ * while calling this function.
+ * See test_set_page_writeback for example.
+ *
 * NOTE: Unlike account_page_dirtied this does not rely on being atomic
 * wrt interrupts.
 */
 void account_page_writeback(struct page *page)
 {
+        mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
        inc_zone_page_state(page, NR_WRITEBACK);
 }
 EXPORT_SYMBOL(account_page_writeback);
@@ -2364,7 +2370,10 @@ int test_clear_page_writeback(struct page *page)
 {
        struct address_space *mapping = page_mapping(page);
        int ret;
+        bool locked;
+        unsigned long memcg_flags;
+        mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
        if (mapping) {
                struct backing_dev_info *bdi = mapping->backing_dev_info;
                unsigned long flags;
@@ -2385,9 +2394,11 @@ int test_clear_page_writeback(struct page *page)
                ret = TestClearPageWriteback(page);
        }
        if (ret) {
+                mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
                dec_zone_page_state(page, NR_WRITEBACK);
                inc_zone_page_state(page, NR_WRITTEN);
        }
+        mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
        return ret;
 }
@@ -2395,7 +2406,10 @@ int test_set_page_writeback(struct page *page)
 {
        struct address_space *mapping = page_mapping(page);
        int ret;
+        bool locked;
+        unsigned long memcg_flags;
+        mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags);
        if (mapping) {
                struct backing_dev_info *bdi = mapping->backing_dev_info;
                unsigned long flags;
@@ -2422,6 +2436,7 @@ int test_set_page_writeback(struct page *page)
        }
        if (!ret)
                account_page_writeback(page);
+        mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags);
        return ret;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 07748e68b729..fd3ee7a54a13 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1052,11 +1052,11 @@ void do_page_add_anon_rmap(struct page *page,
 {
        int first = atomic_inc_and_test(&page->_mapcount);
        if (first) {
-                if (!PageTransHuge(page))
+                if (PageTransHuge(page))
-                        __inc_zone_page_state(page, NR_ANON_PAGES);
-                else
                        __inc_zone_page_state(page,
                                              NR_ANON_TRANSPARENT_HUGEPAGES);
+                __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+                                hpage_nr_pages(page));
        }
        if (unlikely(PageKsm(page)))
                return;
@@ -1085,10 +1085,10 @@ void page_add_new_anon_rmap(struct page *page,
        VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
        SetPageSwapBacked(page);
        atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
-        if (!PageTransHuge(page))
+        if (PageTransHuge(page))
-                __inc_zone_page_state(page, NR_ANON_PAGES);
-        else
                __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+        __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+                        hpage_nr_pages(page));
        __page_set_anon_rmap(page, vma, address, 1);
        if (!mlocked_vma_newpage(vma, page)) {
                SetPageActive(page);
@@ -1111,7 +1111,7 @@ void page_add_file_rmap(struct page *page)
        mem_cgroup_begin_update_page_stat(page, &locked, &flags);
        if (atomic_inc_and_test(&page->_mapcount)) {
                __inc_zone_page_state(page, NR_FILE_MAPPED);
-                mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED);
+                mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
        }
        mem_cgroup_end_update_page_stat(page, &locked, &flags);
 }
@@ -1148,14 +1148,14 @@ void page_remove_rmap(struct page *page)
                goto out;
        if (anon) {
                mem_cgroup_uncharge_page(page);
-                if (!PageTransHuge(page))
+                if (PageTransHuge(page))
-                        __dec_zone_page_state(page, NR_ANON_PAGES);
-                else
                        __dec_zone_page_state(page,
                                              NR_ANON_TRANSPARENT_HUGEPAGES);
+                __mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
+                                -hpage_nr_pages(page));
        } else {
                __dec_zone_page_state(page, NR_FILE_MAPPED);
-                mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED);
+                mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
                mem_cgroup_end_update_page_stat(page, &locked, &flags);
        }
        if (unlikely(PageMlocked(page)))
diff --git a/mm/swap.c b/mm/swap.c
index c899502d3e36..759c3caf44bd 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -432,6 +432,11 @@ static void activate_page_drain(int cpu)
                pagevec_lru_move_fn(pvec, __activate_page, NULL);
 }
+static bool need_activate_page_drain(int cpu)
+{
+        return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+}
 void activate_page(struct page *page)
 {
        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -449,6 +454,11 @@ static inline void activate_page_drain(int cpu)
 {
 }
+static bool need_activate_page_drain(int cpu)
+{
+        return false;
+}
 void activate_page(struct page *page)
 {
        struct zone *zone = page_zone(page);
@@ -701,12 +711,36 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
        lru_add_drain();
 }
-/*
+static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
- * Returns 0 for success
- */
+void lru_add_drain_all(void)
-int lru_add_drain_all(void)
 {
-        return schedule_on_each_cpu(lru_add_drain_per_cpu);
+        static DEFINE_MUTEX(lock);
+        static struct cpumask has_work;
+        int cpu;
+        mutex_lock(&lock);
+        get_online_cpus();
+        cpumask_clear(&has_work);
+        for_each_online_cpu(cpu) {
+                struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
+                if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
+                    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
+                    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
+                    need_activate_page_drain(cpu)) {
+                        INIT_WORK(work, lru_add_drain_per_cpu);
+                        schedule_work_on(cpu, work);
+                        cpumask_set_cpu(cpu, &has_work);
+                }
+        }
+        for_each_cpu(cpu, &has_work)
+                flush_work(&per_cpu(lru_add_drain_work, cpu));
+        put_online_cpus();
+        mutex_unlock(&lock);
 }
 /*
diff --git a/mm/truncate.c b/mm/truncate.c
index e2e8a8a7eb9d..353b683afd6e 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -567,7 +567,6 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
 /**
 * truncate_pagecache - unmap and remove pagecache that has been truncated
 * @inode: inode
- * @oldsize: old file size
 * @newsize: new file size
 *
 * inode's new i_size must already be written before truncate_pagecache
@@ -580,7 +579,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
 * situations such as writepage being called for a page that has already
 * had its underlying blocks deallocated.
 */
-void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize)
+void truncate_pagecache(struct inode *inode, loff_t newsize)
 {
        struct address_space *mapping = inode->i_mapping;
        loff_t holebegin = round_up(newsize, PAGE_SIZE);
@@ -614,12 +613,8 @@ EXPORT_SYMBOL(truncate_pagecache);
 */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
-        loff_t oldsize;
-        oldsize = inode->i_size;
        i_size_write(inode, newsize);
+        truncate_pagecache(inode, newsize);
-        truncate_pagecache(inode, oldsize, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index beb35778c69f..8ed1b775bdc9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -139,11 +139,23 @@ static bool global_reclaim(struct scan_control *sc)
 {
        return !sc->target_mem_cgroup;
 }
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+        struct mem_cgroup *root = sc->target_mem_cgroup;
+        return !mem_cgroup_disabled() &&
+                mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
+}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
        return true;
 }
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+        return false;
+}
 #endif
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -2164,9 +2176,11 @@ static inline bool should_continue_reclaim(struct zone *zone,
        }
 }
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
+static int
+__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 {
        unsigned long nr_reclaimed, nr_scanned;
+        int groups_scanned = 0;
        do {
                struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2174,15 +2188,17 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
                        .zone = zone,
                        .priority = sc->priority,
                };
-                struct mem_cgroup *memcg;
+                struct mem_cgroup *memcg = NULL;
+                mem_cgroup_iter_filter filter = (soft_reclaim) ?
+                        mem_cgroup_soft_reclaim_eligible : NULL;
                nr_reclaimed = sc->nr_reclaimed;
                nr_scanned = sc->nr_scanned;
-                memcg = mem_cgroup_iter(root, NULL, &reclaim);
+                while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
-                do {
                        struct lruvec *lruvec;
+                        groups_scanned++;
                        lruvec = mem_cgroup_zone_lruvec(zone, memcg);
                        shrink_lruvec(lruvec, sc);
@@ -2202,8 +2218,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
                                mem_cgroup_iter_break(root, memcg);
                                break;
                        }
-                        memcg = mem_cgroup_iter(root, memcg, &reclaim);
+                }
-                } while (memcg);
                vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
                           sc->nr_scanned - nr_scanned,
@@ -2211,6 +2226,37 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
        } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
                                         sc->nr_scanned - nr_scanned, sc));
+        return groups_scanned;
+}
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
+{
+        bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
+        unsigned long nr_scanned = sc->nr_scanned;
+        int scanned_groups;
+        scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
+        /*
+         * memcg iterator might race with other reclaimer or start from
+         * a incomplete tree walk so the tree walk in __shrink_zone
+         * might have missed groups that are above the soft limit. Try
+         * another loop to catch up with others. Do it just once to
+         * prevent from reclaim latencies when other reclaimers always
+         * preempt this one.
+         */
+        if (do_soft_reclaim && !scanned_groups)
+                __shrink_zone(zone, sc, do_soft_reclaim);
+        /*
+         * No group is over the soft limit or those that are do not have
+         * pages in the zone we are reclaiming so we have to reclaim everybody
+         */
+        if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
+                __shrink_zone(zone, sc, false);
+                return;
+        }
 }
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2274,8 +2320,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
        struct zoneref *z;
        struct zone *zone;
-        unsigned long nr_soft_reclaimed;
-        unsigned long nr_soft_scanned;
        bool aborted_reclaim = false;
        /*
@@ -2315,18 +2359,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
                                        continue;
                                }
                        }
-                        /*
-                         * This steals pages from memory cgroups over softlimit
-                         * and returns the number of reclaimed pages and
-                         * scanned pages. This works for global memory pressure
-                         * and balancing, not for a memcg's limit.
-                         */
-                        nr_soft_scanned = 0;
-                        nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-                                                sc->order, sc->gfp_mask,
-                                                &nr_soft_scanned);
-                        sc->nr_reclaimed += nr_soft_reclaimed;
-                        sc->nr_scanned += nr_soft_scanned;
                        /* need some check for avoid more shrink_zone() */
                }
@@ -2920,8 +2952,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
        int i;
        int end_zone = 0;       /* Inclusive.  0 = ZONE_DMA */
-        unsigned long nr_soft_reclaimed;
-        unsigned long nr_soft_scanned;
        struct scan_control sc = {
                .gfp_mask = GFP_KERNEL,
                .priority = DEF_PRIORITY,
@@ -3036,15 +3066,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                        sc.nr_scanned = 0;
-                        nr_soft_scanned = 0;
-                        /*
-                         * Call soft limit reclaim before calling shrink_zone.
-                         */
-                        nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-                                                        order, sc.gfp_mask,
-                                                        &nr_soft_scanned);
-                        sc.nr_reclaimed += nr_soft_reclaimed;
                        /*
                         * There should be no need to raise the scanning
                         * priority if enough pages are already being scanned
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 8a57d79b0b16..559d4ae6ebf4 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -87,8 +87,8 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
        if (!cg_proto)
                return -EINVAL;
-        if (val > RESOURCE_MAX)
+        if (val > RES_COUNTER_MAX)
-                val = RESOURCE_MAX;
+                val = RES_COUNTER_MAX;
        tcp = tcp_from_cgproto(cg_proto);
@@ -101,9 +101,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
                tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
                                             net->ipv4.sysctl_tcp_mem[i]);
-        if (val == RESOURCE_MAX)
+        if (val == RES_COUNTER_MAX)
                clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-        else if (val != RESOURCE_MAX) {
+        else if (val != RES_COUNTER_MAX) {
                /*
                 * The active bit needs to be written after the static_key
                 * update. This is what guarantees that the socket activation
@@ -187,7 +187,7 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
        switch (cft->private) {
        case RES_LIMIT:
-                val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
+                val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
                break;
        case RES_USAGE:
                val = tcp_read_usage(memcg);
author	Linus Torvalds <torvalds@linux-foundation.org>	2013-09-12 18:44:27 -0400
committer	Linus Torvalds <torvalds@linux-foundation.org>	2013-09-12 18:44:27 -0400
commit	ac4de9543aca59f2b763746647577302fbedd57e (patch)
tree	40407750569ee030de56233c41c9a97f7e89cf67
parent	26935fb06ee88f1188789807687c03041f3c70d9 (diff)
parent	de32a8177f64bc62e1b19c685dd391af664ab13f (diff)