Merge branch 'akpm' (Andrew's patch-bomb)

Merge first batch of patches from Andrew Morton:
 "A few misc things and all the MM queue"

* emailed from Andrew Morton <akpm@linux-foundation.org>: (92 commits)
  memcg: avoid THP split in task migration
  thp: add HPAGE_PMD_* definitions for !CONFIG_TRANSPARENT_HUGEPAGE
  memcg: clean up existing move charge code
  mm/memcontrol.c: remove unnecessary 'break' in mem_cgroup_read()
  mm/memcontrol.c: remove redundant BUG_ON() in mem_cgroup_usage_unregister_event()
  mm/memcontrol.c: s/stealed/stolen/
  memcg: fix performance of mem_cgroup_begin_update_page_stat()
  memcg: remove PCG_FILE_MAPPED
  memcg: use new logic for page stat accounting
  memcg: remove PCG_MOVE_LOCK flag from page_cgroup
  memcg: simplify move_account() check
  memcg: remove EXPORT_SYMBOL(mem_cgroup_update_page_stat)
  memcg: kill dead prev_priority stubs
  memcg: remove PCG_CACHE page_cgroup flag
  memcg: let css_get_next() rely upon rcu_read_lock()
  cgroup: revert ss_id_lock to spinlock
  idr: make idr_get_next() good for rcu_read_lock()
  memcg: remove unnecessary thp check in page stat accounting
  memcg: remove redundant returns
  memcg: enum lru_list lru
  ...

Documentation/filesystems/proc.txt

@@ -290,7 +290,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
   rsslim        current limit in bytes on the rss
   start_code    address above which program text can run
   end_code      address below which program text can run
-  start_stack   address of the start of the stack
+  start_stack   address of the start of the main process stack
   esp           current value of ESP
   eip           current value of EIP
   pending       bitmap of pending signals
@@ -325,7 +325,7 @@ address           perms offset  dev   inode      pathname
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
@@ -357,11 +357,39 @@ is not associated with a file:
 
  [heap]                   = the heap of the program
  [stack]                  = the stack of the main process
+ [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
 
  or if empty, the mapping is anonymous.
 
+The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
+of the individual tasks of a process. In this file you will see a mapping marked
+as [stack] if that task sees it as a stack. This is a key difference from the
+content of /proc/PID/maps, where you will see all mappings that are being used
+as stack by all of those tasks. Hence, for the example above, the task-level
+map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
+
+08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
+08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
+0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
+a7cb1000-a7cb2000 ---p 00000000 00:00 0
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
+a7eb2000-a7eb3000 ---p 00000000 00:00 0
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
+a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
+a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
+a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
+a800b000-a800e000 rw-p 00000000 00:00 0
+a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
+a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
+a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
+a8024000-a8027000 rw-p 00000000 00:00 0
+a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
+a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
+a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
+aff35000-aff4a000 rw-p 00000000 00:00 0
+ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 
 The /proc/PID/smaps is an extension based on maps, showing the memory
 consumption for each of the process's mappings. For each of mappings there

Documentation/kernel-parameters.txt

@@ -2635,6 +2635,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			to facilitate early boot debugging.
 			See also Documentation/trace/events.txt
 
+	transparent_hugepage=
+			[KNL]
+			Format: [always|madvise|never]
+			Can be used to control the default behavior of the system
+			with respect to transparent hugepages.
+			See Documentation/vm/transhuge.txt for more details.
+
 	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
 			[x86] reliable: mark tsc clocksource as reliable, this

Documentation/vm/page-types.c

@@ -98,6 +98,7 @@
 #define KPF_HWPOISON		19
 #define KPF_NOPAGE		20
 #define KPF_KSM			21
+#define KPF_THP			22
 
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
@@ -147,6 +148,7 @@ static const char *page_flag_names[] = {
 	[KPF_HWPOISON]		= "X:hwpoison",
 	[KPF_NOPAGE]		= "n:nopage",
 	[KPF_KSM]		= "x:ksm",
+	[KPF_THP]		= "t:thp",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",

Documentation/vm/pagemap.txt

@@ -60,6 +60,7 @@ There are three components to pagemap:
     19. HWPOISON
     20. NOPAGE
     21. KSM
+    22. THP
 
 Short descriptions to the page flags:
 
@@ -97,6 +98,9 @@ Short descriptions to the page flags:
 21. KSM
     identical memory pages dynamically shared between one or more processes
 
+22. THP
+    contiguous pages which construct transparent hugepages
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data

arch/sparc/kernel/signal32.c

@@ -776,7 +776,6 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka,
 				  siginfo_t *info,
 				  sigset_t *oldset, struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int err;
 
 	if (ka->sa.sa_flags & SA_SIGINFO)
@@ -787,11 +786,7 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka,
 	if (err)
 		return err;
 
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NOMASK))
-		sigaddset(&blocked, signr);
-	set_current_blocked(&blocked);
-
+	block_sigmask(ka, signr);
 	tracehook_signal_handler(signr, info, ka, regs, 0);
 
 	return 0;

arch/sparc/kernel/signal_32.c

@@ -465,7 +465,6 @@ static inline int
 handle_signal(unsigned long signr, struct k_sigaction *ka,
 	      siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int err;
 
 	if (ka->sa.sa_flags & SA_SIGINFO)
@@ -476,11 +475,7 @@ handle_signal(unsigned long signr, struct k_sigaction *ka,
 	if (err)
 		return err;
 
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NOMASK))
-		sigaddset(&blocked, signr);
-	set_current_blocked(&blocked);
-
+	block_sigmask(ka, signr);
 	tracehook_signal_handler(signr, info, ka, regs, 0);
 
 	return 0;

arch/sparc/kernel/signal_64.c

@@ -479,18 +479,14 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka,
 				siginfo_t *info,
 				sigset_t *oldset, struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int err;
 
 	err = setup_rt_frame(ka, regs, signr, oldset,
 			     (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL);
 	if (err)
 		return err;
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NOMASK))
-		sigaddset(&blocked, signr);
-	set_current_blocked(&blocked);
 
+	block_sigmask(ka, signr);
 	tracehook_signal_handler(signr, info, ka, regs, 0);
 
 	return 0;

arch/x86/kernel/sys_x86_64.c

@@ -195,7 +195,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0;
+	unsigned long addr = addr0, start_addr;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
@@ -223,25 +223,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		mm->free_area_cache = mm->mmap_base;
 	}
 
+try_again:
 	/* either no address requested or can't fit in requested address hole */
-	addr = mm->free_area_cache;
-
-	/* make sure it can fit in the remaining address space */
-	if (addr > len) {
-		unsigned long tmp_addr = align_addr(addr - len, filp,
-						    ALIGN_TOPDOWN);
-
-		vma = find_vma(mm, tmp_addr);
-		if (!vma || tmp_addr + len <= vma->vm_start)
-			/* remember the address as a hint for next time */
-			return mm->free_area_cache = tmp_addr;
-	}
-
-	if (mm->mmap_base < len)
-		goto bottomup;
+	start_addr = addr = mm->free_area_cache;
 
-	addr = mm->mmap_base-len;
+	if (addr < len)
+		goto fail;
 
+	addr -= len;
 	do {
 		addr = align_addr(addr, filp, ALIGN_TOPDOWN);
 
@@ -263,6 +252,17 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = vma->vm_start-len;
 	} while (len < vma->vm_start);
 
+fail:
+	/*
+	 * if hint left us with no space for the requested
+	 * mapping then try again:
+	 */
+	if (start_addr != mm->mmap_base) {
+		mm->free_area_cache = mm->mmap_base;
+		mm->cached_hole_size = 0;
+		goto try_again;
+	}
+
 bottomup:
 	/*
 	 * A failed mmap() very likely causes application failure,

arch/x86/kernel/vm86_32.c

@@ -172,6 +172,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	spinlock_t *ptl;
 	int i;
 
+	down_write(&mm->mmap_sem);
 	pgd = pgd_offset(mm, 0xA0000);
 	if (pgd_none_or_clear_bad(pgd))
 		goto out;
@@ -190,6 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	}
 	pte_unmap_unlock(pte, ptl);
 out:
+	up_write(&mm->mmap_sem);
 	flush_tlb();
 }
 

arch/x86/mm/hugetlbpage.c

@@ -308,10 +308,11 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 {
 	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma, *prev_vma;
-	unsigned long base = mm->mmap_base, addr = addr0;
+	struct vm_area_struct *vma;
+	unsigned long base = mm->mmap_base;
+	unsigned long addr = addr0;
 	unsigned long largest_hole = mm->cached_hole_size;
-	int first_time = 1;
+	unsigned long start_addr;
 
 	/* don't allow allocations above current base */
 	if (mm->free_area_cache > base)
@@ -322,6 +323,8 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		mm->free_area_cache  = base;
 	}
 try_again:
+	start_addr = mm->free_area_cache;
+
 	/* make sure it can fit in the remaining address space */
 	if (mm->free_area_cache < len)
 		goto fail;
@@ -337,22 +340,14 @@ try_again:
 		if (!vma)
 			return addr;
 
-		/*
-		 * new region fits between prev_vma->vm_end and
-		 * vma->vm_start, use it:
-		 */
-		prev_vma = vma->vm_prev;
-		if (addr + len <= vma->vm_start &&
-		            (!prev_vma || (addr >= prev_vma->vm_end))) {
+		if (addr + len <= vma->vm_start) {
 			/* remember the address as a hint for next time */
 		        mm->cached_hole_size = largest_hole;
 		        return (mm->free_area_cache = addr);
-		} else {
+		} else if (mm->free_area_cache == vma->vm_end) {
 			/* pull free_area_cache down to the first hole */
-		        if (mm->free_area_cache == vma->vm_end) {
-				mm->free_area_cache = vma->vm_start;
-				mm->cached_hole_size = largest_hole;
-			}
+			mm->free_area_cache = vma->vm_start;
+			mm->cached_hole_size = largest_hole;
 		}
 
 		/* remember the largest hole we saw so far */
@@ -368,10 +363,9 @@ fail:
 	 * if hint left us with no space for the requested
 	 * mapping then try again:
 	 */
-	if (first_time) {
+	if (start_addr != base) {
 		mm->free_area_cache = base;
 		largest_hole = 0;
-		first_time = 0;
 		goto try_again;
 	}
 	/*

arch/x86/mm/numa_emulation.c

@@ -60,7 +60,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	eb->nid = nid;
 
 	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = pb->nid;
+		emu_nid_to_phys[nid] = nid;
 
 	pb->start += size;
 	if (pb->start >= pb->end) {

arch/xtensa/kernel/signal.c

@@ -260,10 +260,7 @@ asmlinkage long xtensa_rt_sigreturn(long a0, long a1, long a2, long a3,
 		goto badframe;
 
 	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&set);
 
 	if (restore_sigcontext(regs, frame))
 		goto badframe;
@@ -336,8 +333,8 @@ gen_return_code(unsigned char *codemem)
 }
 
 
-static void setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-			sigset_t *set, struct pt_regs *regs)
+static int setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+		       sigset_t *set, struct pt_regs *regs)
 {
 	struct rt_sigframe *frame;
 	int err = 0;
@@ -422,12 +419,11 @@ static void setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		current->comm, current->pid, signal, frame, regs->pc);
 #endif
 
-	return;
+	return 0;
 
 give_sigsegv:
-	if (sig == SIGSEGV)
-		ka->sa.sa_handler = SIG_DFL;
-	force_sig(SIGSEGV, current);
+	force_sigsegv(sig, current);
+	return -EFAULT;
 }
 
 /*
@@ -449,11 +445,8 @@ asmlinkage long xtensa_rt_sigsuspend(sigset_t __user *unewset,
 		return -EFAULT;
 
 	sigdelsetmask(&newset, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
 	saveset = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	regs->areg[2] = -EINTR;
 	while (1) {
@@ -536,17 +529,11 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 
 		/* Whee!  Actually deliver the signal.  */
 		/* Set up the stack frame */
-		setup_frame(signr, &ka, &info, oldset, regs);
-
-		if (ka.sa.sa_flags & SA_ONESHOT)
-			ka.sa.sa_handler = SIG_DFL;
+		ret = setup_frame(signr, &ka, &info, oldset, regs);
+		if (ret)
+			return ret;
 
-		spin_lock_irq(&current->sighand->siglock);
-		sigorsets(&current->blocked, &current->blocked, &ka.sa.sa_mask);
-		if (!(ka.sa.sa_flags & SA_NODEFER))
-			sigaddset(&current->blocked, signr);
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
+		block_sigmask(&ka, signr);
 		if (current->ptrace & PT_SINGLESTEP)
 			task_pt_regs(current)->icountlevel = 1;
 

drivers/idle/intel_idle.c

@@ -507,8 +507,7 @@ int intel_idle_cpu_init(int cpu)
 		int num_substates;
 
 		if (cstate > max_cstate) {
-			printk(PREFIX "max_cstate %d reached\n",
-			       max_cstate);
+			printk(PREFIX "max_cstate %d reached\n", max_cstate);
 			break;
 		}
 
@@ -524,8 +523,9 @@ int intel_idle_cpu_init(int cpu)
 		dev->states_usage[dev->state_count].driver_data =
 			(void *)get_driver_data(cstate);
 
-			dev->state_count += 1;
-		}
+		dev->state_count += 1;
+	}
+
 	dev->cpu = cpu;
 
 	if (cpuidle_register_device(dev)) {

drivers/tty/sysrq.c

@@ -346,7 +346,7 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(node_zonelist(0, GFP_KERNEL), GFP_KERNEL, 0, NULL);
+	out_of_memory(node_zonelist(0, GFP_KERNEL), GFP_KERNEL, 0, NULL, true);
 }
 
 static DECLARE_WORK(moom_work, moom_callback);

fs/exec.c

@@ -822,7 +822,7 @@ static int exec_mmap(struct mm_struct *mm)
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
-	sync_mm_rss(tsk, old_mm);
+	sync_mm_rss(old_mm);
 	mm_release(tsk, old_mm);
 
 	if (old_mm) {

fs/hugetlbfs/inode.c

@@ -41,6 +41,25 @@ const struct file_operations hugetlbfs_file_operations;
 static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
+struct hugetlbfs_config {
+	uid_t   uid;
+	gid_t   gid;
+	umode_t mode;
+	long	nr_blocks;
+	long	nr_inodes;
+	struct hstate *hstate;
+};
+
+struct hugetlbfs_inode_info {
+	struct shared_policy policy;
+	struct inode vfs_inode;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
 static struct backing_dev_info hugetlbfs_backing_dev_info = {
 	.name		= "hugetlbfs",
 	.ra_pages	= 0,	/* No readahead */
@@ -154,10 +173,12 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 			return addr;
 	}
 
-	start_addr = mm->free_area_cache;
-
-	if (len <= mm->cached_hole_size)
+	if (len > mm->cached_hole_size)
+		start_addr = mm->free_area_cache;
+	else {
 		start_addr = TASK_UNMAPPED_BASE;
+		mm->cached_hole_size = 0;
+	}
 
 full_search:
 	addr = ALIGN(start_addr, huge_page_size(h));
@@ -171,13 +192,18 @@ full_search:
 			 */
 			if (start_addr != TASK_UNMAPPED_BASE) {
 				start_addr = TASK_UNMAPPED_BASE;
+				mm->cached_hole_size = 0;
 				goto full_search;
 			}
 			return -ENOMEM;
 		}
 
-		if (!vma || addr + len <= vma->vm_start)
+		if (!vma || addr + len <= vma->vm_start) {
+			mm->free_area_cache = addr + len;
 			return addr;
+		}
+		if (addr + mm->cached_hole_size < vma->vm_start)
+			mm->cached_hole_size = vma->vm_start - addr;
 		addr = ALIGN(vma->vm_end, huge_page_size(h));
 	}
 }
@@ -238,17 +264,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 	loff_t isize;
 	ssize_t retval = 0;
 
-	mutex_lock(&inode->i_mutex);
-
 	/* validate length */
 	if (len == 0)
 		goto out;
 
-	isize = i_size_read(inode);
-	if (!isize)
-		goto out;
-
-	end_index = (isize - 1) >> huge_page_shift(h);
 	for (;;) {
 		struct page *page;
 		unsigned long nr, ret;
@@ -256,18 +275,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = huge_page_size(h);
+		isize = i_size_read(inode);
+		if (!isize)
+			goto out;
+		end_index = (isize - 1) >> huge_page_shift(h);
 		if (index >= end_index) {
 			if (index > end_index)
 				goto out;
 			nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
-			if (nr <= offset) {
+			if (nr <= offset)
 				goto out;
-			}
 		}
 		nr = nr - offset;
 
 		/* Find the page */
-		page = find_get_page(mapping, index);
+		page = find_lock_page(mapping, index);
 		if (unlikely(page == NULL)) {
 			/*
 			 * We have a HOLE, zero out the user-buffer for the
@@ -279,17 +301,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 			else
 				ra = 0;
 		} else {
+			unlock_page(page);
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
 			ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
 			ret = ra;
+			page_cache_release(page);
 		}
 		if (ra < 0) {
 			if (retval == 0)
 				retval = ra;
-			if (page)
-				page_cache_release(page);
 			goto out;
 		}
 
@@ -299,16 +322,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
 		index += offset >> huge_page_shift(h);
 		offset &= ~huge_page_mask(h);
 
-		if (page)
-			page_cache_release(page);
-
 		/* short read or no more work */
 		if ((ret != nr) || (len == 0))
 			break;
 	}
 out:
 	*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
-	mutex_unlock(&inode->i_mutex);
 	return retval;
 }
 
@@ -607,9 +626,15 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		spin_lock(&sbinfo->stat_lock);
 		/* If no limits set, just report 0 for max/free/used
 		 * blocks, like simple_statfs() */
-		if (sbinfo->max_blocks >= 0) {
-			buf->f_blocks = sbinfo->max_blocks;
-			buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+		if (sbinfo->spool) {
+			long free_pages;
+
+			spin_lock(&sbinfo->spool->lock);
+			buf->f_blocks = sbinfo->spool->max_hpages;
+			free_pages = sbinfo->spool->max_hpages
+				- sbinfo->spool->used_hpages;
+			buf->f_bavail = buf->f_bfree = free_pages;
+			spin_unlock(&sbinfo->spool->lock);
 			buf->f_files = sbinfo->max_inodes;
 			buf->f_ffree = sbinfo->free_inodes;
 		}
@@ -625,6 +650,10 @@ static void hugetlbfs_put_super(struct super_block *sb)
 
 	if (sbi) {
 		sb->s_fs_info = NULL;
+
+		if (sbi->spool)
+			hugepage_put_subpool(sbi->spool);
+
 		kfree(sbi);
 	}
 }
@@ -853,10 +882,14 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_fs_info = sbinfo;
 	sbinfo->hstate = config.hstate;
 	spin_lock_init(&sbinfo->stat_lock);
-	sbinfo->max_blocks = config.nr_blocks;
-	sbinfo->free_blocks = config.nr_blocks;
 	sbinfo->max_inodes = config.nr_inodes;
 	sbinfo->free_inodes = config.nr_inodes;
+	sbinfo->spool = NULL;
+	if (config.nr_blocks != -1) {
+		sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+		if (!sbinfo->spool)
+			goto out_free;
+	}
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize = huge_page_size(config.hstate);
 	sb->s_blocksize_bits = huge_page_shift(config.hstate);
@@ -868,38 +901,12 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_free;
 	return 0;
 out_free:
+	if (sbinfo->spool)
+		kfree(sbinfo->spool);
 	kfree(sbinfo);
 	return -ENOMEM;
 }
 
-int hugetlb_get_quota(struct address_space *mapping, long delta)
-{
-	int ret = 0;
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
-	if (sbinfo->free_blocks > -1) {
-		spin_lock(&sbinfo->stat_lock);
-		if (sbinfo->free_blocks - delta >= 0)
-			sbinfo->free_blocks -= delta;
-		else
-			ret = -ENOMEM;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-
-	return ret;
-}
-
-void hugetlb_put_quota(struct address_space *mapping, long delta)
-{
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
-	if (sbinfo->free_blocks > -1) {
-		spin_lock(&sbinfo->stat_lock);
-		sbinfo->free_blocks += delta;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-}
-
 static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
@@ -919,8 +926,8 @@ static int can_do_hugetlb_shm(void)
 	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size,
-				vm_flags_t acctflag,
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+				size_t size, vm_flags_t acctflag,
 				struct user_struct **user, int creat_flags)
 {
 	int error = -ENOMEM;
@@ -929,6 +936,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	struct path path;
 	struct dentry *root;
 	struct qstr quick_string;
+	struct hstate *hstate;
+	unsigned long num_pages;
 
 	*user = NULL;
 	if (!hugetlbfs_vfsmount)
@@ -937,7 +946,11 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
 		*user = current_user();
 		if (user_shm_lock(size, *user)) {
-			printk_once(KERN_WARNING "Using mlock ulimits for SHM_HUGETLB is deprecated\n");
+			task_lock(current);
+			printk_once(KERN_WARNING
+				"%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+				current->comm, current->pid);
+			task_unlock(current);
 		} else {
 			*user = NULL;
 			return ERR_PTR(-EPERM);
@@ -958,10 +971,12 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	if (!inode)
 		goto out_dentry;
 
+	hstate = hstate_inode(inode);
+	size += addr & ~huge_page_mask(hstate);
+	num_pages = ALIGN(size, huge_page_size(hstate)) >>
+			huge_page_shift(hstate);
 	error = -ENOMEM;
-	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
+	if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
 		goto out_inode;
 
 	d_instantiate(path.dentry, inode);
@@ -997,6 +1012,7 @@ static int __init init_hugetlbfs_fs(void)
 	if (error)
 		return error;
 
+	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
 					0, 0, init_once);
@@ -1015,10 +1031,10 @@ static int __init init_hugetlbfs_fs(void)
 	}
 
 	error = PTR_ERR(vfsmount);
+	unregister_filesystem(&hugetlbfs_fs_type);
 
  out:
-	if (error)
-		kmem_cache_destroy(hugetlbfs_inode_cachep);
+	kmem_cache_destroy(hugetlbfs_inode_cachep);
  out2:
 	bdi_destroy(&hugetlbfs_backing_dev_info);
 	return error;

fs/namei.c

@@ -1455,9 +1455,15 @@ done:
 }
 EXPORT_SYMBOL(full_name_hash);
 
+#ifdef CONFIG_64BIT
 #define ONEBYTES	0x0101010101010101ul
 #define SLASHBYTES	0x2f2f2f2f2f2f2f2ful
 #define HIGHBITS	0x8080808080808080ul
+#else
+#define ONEBYTES	0x01010101ul
+#define SLASHBYTES	0x2f2f2f2ful
+#define HIGHBITS	0x80808080ul
+#endif
 
 /* Return the high bit set in the first byte that is a zero */
 static inline unsigned long has_zero(unsigned long a)

fs/proc/base.c

@@ -2989,9 +2989,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
 	ONE("statm",      S_IRUGO, proc_pid_statm),
-	REG("maps",       S_IRUGO, proc_maps_operations),
+	REG("maps",       S_IRUGO, proc_pid_maps_operations),
 #ifdef CONFIG_NUMA
-	REG("numa_maps",  S_IRUGO, proc_numa_maps_operations),
+	REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
 #endif
 	REG("mem",        S_IRUSR|S_IWUSR, proc_mem_operations),
 	LNK("cwd",        proc_cwd_link),
@@ -3002,7 +3002,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("mountstats", S_IRUSR, proc_mountstats_operations),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
-	REG("smaps",      S_IRUGO, proc_smaps_operations),
+	REG("smaps",      S_IRUGO, proc_pid_smaps_operations),
 	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
@@ -3348,9 +3348,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	INF("cmdline",   S_IRUGO, proc_pid_cmdline),
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
-	REG("maps",      S_IRUGO, proc_maps_operations),
+	REG("maps",      S_IRUGO, proc_tid_maps_operations),
 #ifdef CONFIG_NUMA
-	REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+	REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
 #endif
 	REG("mem",       S_IRUSR|S_IWUSR, proc_mem_operations),
 	LNK("cwd",       proc_cwd_link),
@@ -3360,7 +3360,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
-	REG("smaps",     S_IRUGO, proc_smaps_operations),
+	REG("smaps",     S_IRUGO, proc_tid_smaps_operations),
 	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY

fs/proc/internal.h

@@ -53,9 +53,12 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
-extern const struct file_operations proc_maps_operations;
-extern const struct file_operations proc_numa_maps_operations;
-extern const struct file_operations proc_smaps_operations;
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_tid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;

fs/proc/page.c

@@ -115,6 +115,8 @@ u64 stable_page_flags(struct page *page)
 		u |= 1 << KPF_COMPOUND_TAIL;
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
+	else if (PageTransCompound(page))
+		u |= 1 << KPF_THP;
 
 	/*
 	 * Caveats on high order pages: page->_count will only be set

fs/proc/task_mmu.c

@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
+	struct proc_maps_private *priv = m->private;
+	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
 	unsigned long start, end;
 	dev_t dev = 0;
 	int len;
+	const char *name = NULL;
 
 	if (file) {
 		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	if (file) {
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "\n");
-	} else {
-		const char *name = arch_vma_name(vma);
-		if (!name) {
-			if (mm) {
-				if (vma->vm_start <= mm->brk &&
-						vma->vm_end >= mm->start_brk) {
-					name = "[heap]";
-				} else if (vma->vm_start <= mm->start_stack &&
-					   vma->vm_end >= mm->start_stack) {
-					name = "[stack]";
-				}
+		goto done;
+	}
+
+	name = arch_vma_name(vma);
+	if (!name) {
+		pid_t tid;
+
+		if (!mm) {
+			name = "[vdso]";
+			goto done;
+		}
+
+		if (vma->vm_start <= mm->brk &&
+		    vma->vm_end >= mm->start_brk) {
+			name = "[heap]";
+			goto done;
+		}
+
+		tid = vm_is_stack(task, vma, is_pid);
+
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack)) {
+				name = "[stack]";
 			} else {
-				name = "[vdso]";
+				/* Thread stack in /proc/PID/maps */
+				pad_len_spaces(m, len);
+				seq_printf(m, "[stack:%d]", tid);
 			}
 		}
-		if (name) {
-			pad_len_spaces(m, len);
-			seq_puts(m, name);
-		}
+	}
+
+done:
+	if (name) {
+		pad_len_spaces(m, len);
+		seq_puts(m, name);
 	}
 	seq_putc(m, '\n');
 }
 
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+	return show_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_maps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_maps_op);
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -394,21 +448,15 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma, pmd);
-		} else {
-			smaps_pte_entry(*(pte_t *)pmd, addr,
-					HPAGE_PMD_SIZE, walk);
-			spin_unlock(&walk->mm->page_table_lock);
-			mss->anonymous_thp += HPAGE_PMD_SIZE;
-			return 0;
-		}
-	} else {
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
 		spin_unlock(&walk->mm->page_table_lock);
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+		return 0;
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	/*
 	 * The mmap_sem held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
@@ -422,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-static int show_smap(struct seq_file *m, void *v)
+static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;
@@ -440,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
-	show_map_vma(m, vma);
+	show_map_vma(m, vma, is_pid);
 
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
@@ -479,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+	return show_smap(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_smaps_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_smap
+	.show	= show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_smap
 };
 
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
-const struct file_operations proc_smaps_operations = {
-	.open		= smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+	.open		= pid_smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
@@ -507,6 +584,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -598,11 +677,18 @@ const struct file_operations proc_clear_refs_operations = {
 	.llseek		= noop_llseek,
 };
 
+typedef struct {
+	u64 pme;
+} pagemap_entry_t;
+
 struct pagemapread {
 	int pos, len;
-	u64 *buffer;
+	pagemap_entry_t *buffer;
 };
 
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
+#define PAGEMAP_WALK_MASK	(PMD_MASK)
+
 #define PM_ENTRY_BYTES      sizeof(u64)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
@@ -620,10 +706,15 @@ struct pagemapread {
 #define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
 #define PM_END_OF_BUFFER    1
 
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+	return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
 			  struct pagemapread *pm)
 {
-	pm->buffer[pm->pos++] = pfn;
+	pm->buffer[pm->pos++] = *pme;
 	if (pm->pos >= pm->len)
 		return PM_END_OF_BUFFER;
 	return 0;
@@ -635,8 +726,10 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
 	}
@@ -649,17 +742,35 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
-static u64 pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
 {
-	u64 pme = 0;
 	if (is_swap_pte(pte))
-		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+		*pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
 	else if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte))
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte))
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+					pmd_t pmd, int offset)
+{
+	/*
+	 * Currently pmd for thp is always present because thp can not be
+	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pmd_present(pmd))
+		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+						pmd_t pmd, int offset)
+{
+}
+#endif
 
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
@@ -668,13 +779,30 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
-	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
+	spin_lock(&walk->mm->page_table_lock);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		for (; addr != end; addr += PAGE_SIZE) {
+			unsigned long offset;
+
+			offset = (addr & ~PAGEMAP_WALK_MASK) >>
+					PAGE_SHIFT;
+			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+		}
+		spin_unlock(&walk->mm->page_table_lock);
+		return err;
+	}
+
 	for (; addr != end; addr += PAGE_SIZE) {
-		u64 pfn = PM_NOT_PRESENT;
 
 		/* check to see if we've left 'vma' behind
 		 * and need a new, higher one */
@@ -686,11 +814,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pfn = pte_to_pagemap_entry(*pte);
+			pte_to_pagemap_entry(&pme, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
-		err = add_to_pagemap(addr, pfn, pm);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -701,13 +829,12 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+					pte_t pte, int offset)
 {
-	u64 pme = 0;
 	if (pte_present(pte))
-		pme = PM_PFRAME(pte_pfn(pte) + offset)
-			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
-	return pme;
+		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
+				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -717,12 +844,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 {
 	struct pagemapread *pm = walk->private;
 	int err = 0;
-	u64 pfn;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		pfn = huge_pte_to_pagemap_entry(*pte, offset);
-		err = add_to_pagemap(addr, pfn, pm);
+		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
 	}
@@ -757,8 +884,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
  */
-#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
-#define PAGEMAP_WALK_MASK	(PMD_MASK)
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
@@ -941,26 +1066,21 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *pte;
 
 	md = walk->private;
-	spin_lock(&walk->mm->page_table_lock);
-	if (pmd_trans_huge(*pmd)) {
-		if (pmd_trans_splitting(*pmd)) {
-			spin_unlock(&walk->mm->page_table_lock);
-			wait_split_huge_page(md->vma->anon_vma, pmd);
-		} else {
-			pte_t huge_pte = *(pte_t *)pmd;
-			struct page *page;
-
-			page = can_gather_numa_stats(huge_pte, md->vma, addr);
-			if (page)
-				gather_stats(page, md, pte_dirty(huge_pte),
-						HPAGE_PMD_SIZE/PAGE_SIZE);
-			spin_unlock(&walk->mm->page_table_lock);
-			return 0;
-		}
-	} else {
+
+	if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+		pte_t huge_pte = *(pte_t *)pmd;
+		struct page *page;
+
+		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		if (page)
+			gather_stats(page, md, pte_dirty(huge_pte),
+				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(&walk->mm->page_table_lock);
+		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1002,7 +1122,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 {
 	struct numa_maps_private *numa_priv = m->private;
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1039,9 +1159,19 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_path(m, &file->f_path, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
-	} else if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
-		seq_printf(m, " stack");
+	} else {
+		pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+		if (tid != 0) {
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, " stack");
+			else
+				seq_printf(m, " stack:%d", tid);
+		}
 	}
 
 	if (is_vm_hugetlb_page(vma))
@@ -1084,21 +1214,39 @@ out:
 	return 0;
 }
 
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+	return show_numa_map(m, v, 0);
+}
+
 static const struct seq_operations proc_pid_numa_maps_op = {
-        .start  = m_start,
-        .next   = m_next,
-        .stop   = m_stop,
-        .show   = show_numa_map,
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_pid_numa_map,
+};
+
+static const struct seq_operations proc_tid_numa_maps_op = {
+	.start  = m_start,
+	.next   = m_next,
+	.stop   = m_stop,
+	.show   = show_tid_numa_map,
 };
 
-static int numa_maps_open(struct inode *inode, struct file *file)
+static int numa_maps_open(struct inode *inode, struct file *file,
+			  const struct seq_operations *ops)
 {
 	struct numa_maps_private *priv;
 	int ret = -ENOMEM;
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (priv) {
 		priv->proc_maps.pid = proc_pid(inode);
-		ret = seq_open(file, &proc_pid_numa_maps_op);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -1109,8 +1257,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_numa_maps_operations = {
-	.open		= numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+	.open		= pid_numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,

fs/proc/task_nommu.c

@@ -134,9 +134,11 @@ static void pad_len_spaces(struct seq_file *m, int len)
 /*
  * display a single VMA to a sequenced file
  */
-static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+			  int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct proc_maps_private *priv = m->private;
 	unsigned long ino = 0;
 	struct file *file;
 	dev_t dev = 0;
@@ -168,10 +170,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "");
 	} else if (mm) {
-		if (vma->vm_start <= mm->start_stack &&
-			vma->vm_end >= mm->start_stack) {
+		pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+
+		if (tid != 0) {
 			pad_len_spaces(m, len);
-			seq_puts(m, "[stack]");
+			/*
+			 * Thread stack in /proc/PID/task/TID/maps or
+			 * the main process stack.
+			 */
+			if (!is_pid || (vma->vm_start <= mm->start_stack &&
+			    vma->vm_end >= mm->start_stack))
+				seq_printf(m, "[stack]");
+			else
+				seq_printf(m, "[stack:%d]", tid);
 		}
 	}
 
@@ -182,11 +193,22 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 /*
  * display mapping lines for a particular process's /proc/pid/maps
  */
-static int show_map(struct seq_file *m, void *_p)
+static int show_map(struct seq_file *m, void *_p, int is_pid)
 {
 	struct rb_node *p = _p;
 
-	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+	return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
+			      is_pid);
+}
+
+static int show_pid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *_p)
+{
+	return show_map(m, _p, 0);
 }
 
 static void *m_start(struct seq_file *m, loff_t *pos)
@@ -240,10 +262,18 @@ static const struct seq_operations proc_pid_maps_ops = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
-	.show	= show_map
+	.show	= show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_ops = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_tid_map
 };
 
-static int maps_open(struct inode *inode, struct file *file)
+static int maps_open(struct inode *inode, struct file *file,
+		     const struct seq_operations *ops)
 {
 	struct proc_maps_private *priv;
 	int ret = -ENOMEM;
@@ -251,7 +281,7 @@ static int maps_open(struct inode *inode, struct file *file)
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (priv) {
 		priv->pid = proc_pid(inode);
-		ret = seq_open(file, &proc_pid_maps_ops);
+		ret = seq_open(file, ops);
 		if (!ret) {
 			struct seq_file *m = file->private_data;
 			m->private = priv;
@@ -262,8 +292,25 @@ static int maps_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_tid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,

fs/seq_file.c

@@ -140,9 +140,21 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 
 	mutex_lock(&m->lock);
 
+	/*
+	 * seq_file->op->..m_start/m_stop/m_next may do special actions
+	 * or optimisations based on the file->f_version, so we want to
+	 * pass the file->f_version to those methods.
+	 *
+	 * seq_file->version is just copy of f_version, and seq_file
+	 * methods can treat it simply as file version.
+	 * It is copied in first and copied out after all operations.
+	 * It is convenient to have it as  part of structure to avoid the
+	 * need of passing another argument to all the seq_file methods.
+	 */
+	m->version = file->f_version;
+
 	/* Don't assume *ppos is where we left it */
 	if (unlikely(*ppos != m->read_pos)) {
-		m->read_pos = *ppos;
 		while ((err = traverse(m, *ppos)) == -EAGAIN)
 			;
 		if (err) {
@@ -152,21 +164,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 			m->index = 0;
 			m->count = 0;
 			goto Done;
+		} else {
+			m->read_pos = *ppos;
 		}
 	}
 
-	/*
-	 * seq_file->op->..m_start/m_stop/m_next may do special actions
-	 * or optimisations based on the file->f_version, so we want to
-	 * pass the file->f_version to those methods.
-	 *
-	 * seq_file->version is just copy of f_version, and seq_file
-	 * methods can treat it simply as file version.
-	 * It is copied in first and copied out after all operations.
-	 * It is convenient to have it as  part of structure to avoid the
-	 * need of passing another argument to all the seq_file methods.
-	 */
-	m->version = file->f_version;
 	/* grab buffer if we didn't have one */
 	if (!m->buf) {
 		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);

include/asm-generic/pgtable.h

@@ -425,6 +425,8 @@ extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 				unsigned long size);
 #endif
 
+#ifdef CONFIG_MMU
+
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_trans_huge(pmd_t pmd)
 {
@@ -441,7 +443,66 @@ static inline int pmd_write(pmd_t pmd)
 	return 0;
 }
 #endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * This function is meant to be used by sites walking pagetables with
+ * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
+ * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
+ * into a null pmd and the transhuge page fault can convert a null pmd
+ * into an hugepmd or into a regular pmd (if the hugepage allocation
+ * fails). While holding the mmap_sem in read mode the pmd becomes
+ * stable and stops changing under us only if it's not null and not a
+ * transhuge pmd. When those races occurs and this function makes a
+ * difference vs the standard pmd_none_or_clear_bad, the result is
+ * undefined so behaving like if the pmd was none is safe (because it
+ * can return none anyway). The compiler level barrier() is critically
+ * important to compute the two checks atomically on the same pmdval.
+ */
+static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
+{
+	/* depend on compiler for an atomic pmd read */
+	pmd_t pmdval = *pmd;
+	/*
+	 * The barrier will stabilize the pmdval in a register or on
+	 * the stack so that it will stop changing under the code.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+	if (pmd_none(pmdval))
+		return 1;
+	if (unlikely(pmd_bad(pmdval))) {
+		if (!pmd_trans_huge(pmdval))
+			pmd_clear_bad(pmd);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * This is a noop if Transparent Hugepage Support is not built into
+ * the kernel. Otherwise it is equivalent to
+ * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
+ * places that already verified the pmd is not none and they want to
+ * walk ptes while holding the mmap sem in read mode (write mode don't
+ * need this). If THP is not enabled, the pmd can't go away under the
+ * code even if MADV_DONTNEED runs, but if THP is enabled we need to
+ * run a pmd_trans_unstable before walking the ptes after
+ * split_huge_page_pmd returns (because it may have run when the pmd
+ * become null, but then a page fault can map in a THP and not a
+ * regular page).
+ */
+static inline int pmd_trans_unstable(pmd_t *pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return pmd_none_or_trans_huge_or_clear_bad(pmd);
+#else
+	return 0;
 #endif
+}
+
+#endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
 

include/linux/cgroup.h

@@ -498,7 +498,7 @@ struct cgroup_subsys {
 	struct list_head sibling;
 	/* used when use_id == true */
 	struct idr idr;
-	rwlock_t id_lock;
+	spinlock_t id_lock;
 
 	/* should be defined only by modular subsystems */
 	struct module *module;

include/linux/compaction.h

@@ -23,6 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			bool sync);
+extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
 /* Do not skip compaction more than 64 times */
@@ -33,20 +34,26 @@ extern unsigned long compaction_suitable(struct zone *zone, int order);
  * allocation success. 1 << compact_defer_limit compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
-static inline void defer_compaction(struct zone *zone)
+static inline void defer_compaction(struct zone *zone, int order)
 {
 	zone->compact_considered = 0;
 	zone->compact_defer_shift++;
 
+	if (order < zone->compact_order_failed)
+		zone->compact_order_failed = order;
+
 	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
 		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
 }
 
 /* Returns true if compaction should be skipped this time */
-static inline bool compaction_deferred(struct zone *zone)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
 	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
 
+	if (order < zone->compact_order_failed)
+		return false;
+
 	/* Avoid possible overflow */
 	if (++zone->compact_considered > defer_limit)
 		zone->compact_considered = defer_limit;
@@ -62,16 +69,21 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	return COMPACT_CONTINUE;
 }
 
+static inline int compact_pgdat(pg_data_t *pgdat, int order)
+{
+	return COMPACT_CONTINUE;
+}
+
 static inline unsigned long compaction_suitable(struct zone *zone, int order)
 {
 	return COMPACT_SKIPPED;
 }
 
-static inline void defer_compaction(struct zone *zone)
+static inline void defer_compaction(struct zone *zone, int order)
 {
 }
 
-static inline bool compaction_deferred(struct zone *zone)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
 	return 1;
 }

include/linux/cpuset.h

@@ -89,42 +89,33 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * reading current mems_allowed and mempolicy in the fastpath must protected
- * by get_mems_allowed()
+ * get_mems_allowed is required when making decisions involving mems_allowed
+ * such as during page allocation. mems_allowed can be updated in parallel
+ * and depending on the new value an operation can fail potentially causing
+ * process failure. A retry loop with get_mems_allowed and put_mems_allowed
+ * prevents these artificial failures.
  */
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
-	current->mems_allowed_change_disable++;
-
-	/*
-	 * ensure that reading mems_allowed and mempolicy happens after the
-	 * update of ->mems_allowed_change_disable.
-	 *
-	 * the write-side task finds ->mems_allowed_change_disable is not 0,
-	 * and knows the read-side task is reading mems_allowed or mempolicy,
-	 * so it will clear old bits lazily.
-	 */
-	smp_mb();
+	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
-static inline void put_mems_allowed(void)
+/*
+ * If this returns false, the operation that took place after get_mems_allowed
+ * may have failed. It is up to the caller to retry the operation if
+ * appropriate.
+ */
+static inline bool put_mems_allowed(unsigned int seq)
 {
-	/*
-	 * ensure that reading mems_allowed and mempolicy before reducing
-	 * mems_allowed_change_disable.
-	 *
-	 * the write-side task will know that the read-side task is still
-	 * reading mems_allowed or mempolicy, don't clears old bits in the
-	 * nodemask.
-	 */
-	smp_mb();
-	--ACCESS_ONCE(current->mems_allowed_change_disable);
+	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
 {
 	task_lock(current);
+	write_seqcount_begin(&current->mems_allowed_seq);
 	current->mems_allowed = nodemask;
+	write_seqcount_end(&current->mems_allowed_seq);
 	task_unlock(current);
 }
 
@@ -234,12 +225,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
+	return 0;
 }
 
-static inline void put_mems_allowed(void)
+static inline bool put_mems_allowed(unsigned int seq)
 {
+	return true;
 }
 
 #endif /* !CONFIG_CPUSETS */

include/linux/huge_mm.h

@@ -51,6 +51,9 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag);
 
+#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT HPAGE_SHIFT
 #define HPAGE_PMD_MASK HPAGE_MASK
@@ -102,8 +105,6 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
 	} while (0)
-#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
-#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 #if HPAGE_PMD_ORDER > MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -113,6 +114,18 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
+extern int __pmd_trans_huge_lock(pmd_t *pmd,
+				 struct vm_area_struct *vma);
+/* mmap_sem must be held on entry */
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	if (pmd_trans_huge(*pmd))
+		return __pmd_trans_huge_lock(pmd, vma);
+	else
+		return 0;
+}
 static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 unsigned long start,
 					 unsigned long end,
@@ -146,9 +159,9 @@ static inline struct page *compound_trans_head(struct page *page)
 	return page;
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
-#define HPAGE_PMD_SHIFT ({ BUG(); 0; })
-#define HPAGE_PMD_MASK ({ BUG(); 0; })
-#define HPAGE_PMD_SIZE ({ BUG(); 0; })
+#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
+#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
+#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
 
 #define hpage_nr_pages(x) 1
 
@@ -176,6 +189,11 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */

include/linux/hugetlb.h

@@ -14,6 +14,15 @@ struct user_struct;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+struct hugepage_subpool {
+	spinlock_t lock;
+	long count;
+	long max_hpages, used_hpages;
+};
+
+struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
+void hugepage_put_subpool(struct hugepage_subpool *spool);
+
 int PageHuge(struct page *page);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
@@ -128,35 +137,14 @@ enum {
 };
 
 #ifdef CONFIG_HUGETLBFS
-struct hugetlbfs_config {
-	uid_t   uid;
-	gid_t   gid;
-	umode_t mode;
-	long	nr_blocks;
-	long	nr_inodes;
-	struct hstate *hstate;
-};
-
 struct hugetlbfs_sb_info {
-	long	max_blocks;   /* blocks allowed */
-	long	free_blocks;  /* blocks free */
 	long	max_inodes;   /* inodes allowed */
 	long	free_inodes;  /* inodes free */
 	spinlock_t	stat_lock;
 	struct hstate *hstate;
+	struct hugepage_subpool *spool;
 };
 
-
-struct hugetlbfs_inode_info {
-	struct shared_policy policy;
-	struct inode vfs_inode;
-};
-
-static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
-{
-	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
-}
-
 static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -164,10 +152,9 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+				size_t size, vm_flags_t acct,
 				struct user_struct **user, int creat_flags);
-int hugetlb_get_quota(struct address_space *mapping, long delta);
-void hugetlb_put_quota(struct address_space *mapping, long delta);
 
 static inline int is_file_hugepages(struct file *file)
 {
@@ -179,15 +166,11 @@ static inline int is_file_hugepages(struct file *file)
 	return 0;
 }
 
-static inline void set_file_hugepages(struct file *file)
-{
-	file->f_op = &hugetlbfs_file_operations;
-}
 #else /* !CONFIG_HUGETLBFS */
 
 #define is_file_hugepages(file)			0
-#define set_file_hugepages(file)		BUG()
-static inline struct file *hugetlb_file_setup(const char *name, size_t size,
+static inline struct file *
+hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
 		vm_flags_t acctflag, struct user_struct **user, int creat_flags)
 {
 	return ERR_PTR(-ENOSYS);

include/linux/init_task.h

@@ -29,6 +29,13 @@ extern struct fs_struct init_fs;
 #define INIT_GROUP_RWSEM(sig)
 #endif
 
+#ifdef CONFIG_CPUSETS
+#define INIT_CPUSET_SEQ							\
+	.mems_allowed_seq = SEQCNT_ZERO,
+#else
+#define INIT_CPUSET_SEQ
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
@@ -192,6 +199,7 @@ extern struct cred init_cred;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_CPUSET_SEQ							\
 }
 
 

include/linux/kernel-page-flags.h

@@ -30,6 +30,7 @@
 #define KPF_NOPAGE		20
 
 #define KPF_KSM			21
+#define KPF_THP			22
 
 /* kernel hacking assistances
  * WARNING: subject to change, never rely on them!

include/linux/memcontrol.h

@@ -77,7 +77,8 @@ extern void mem_cgroup_uncharge_end(void);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
 
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
@@ -140,6 +141,34 @@ static inline bool mem_cgroup_disabled(void)
 	return false;
 }
 
+void __mem_cgroup_begin_update_page_stat(struct page *page, bool *locked,
+					 unsigned long *flags);
+
+extern atomic_t memcg_moving;
+
+static inline void mem_cgroup_begin_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+	if (mem_cgroup_disabled())
+		return;
+	rcu_read_lock();
+	*locked = false;
+	if (atomic_read(&memcg_moving))
+		__mem_cgroup_begin_update_page_stat(page, locked, flags);
+}
+
+void __mem_cgroup_end_update_page_stat(struct page *page,
+				unsigned long *flags);
+static inline void mem_cgroup_end_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (*locked)
+		__mem_cgroup_end_update_page_stat(page, flags);
+	rcu_read_unlock();
+}
+
 void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_page_stat_item idx,
 				 int val);
@@ -298,21 +327,6 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
 {
 }
 
-static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *memcg)
-{
-	return 0;
-}
-
-static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *memcg,
-						int priority)
-{
-}
-
-static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *memcg,
-						int priority)
-{
-}
-
 static inline bool mem_cgroup_disabled(void)
 {
 	return true;
@@ -355,6 +369,16 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
+static inline void mem_cgroup_begin_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+}
+
+static inline void mem_cgroup_end_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_page_stat_item idx)
 {
@@ -391,7 +415,7 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
 				struct page *newpage)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_CONT */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
 
 #if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
 static inline bool

include/linux/migrate.h

@@ -8,7 +8,6 @@
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
 #ifdef CONFIG_MIGRATION
-#define PAGE_MIGRATION 1
 
 extern void putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
@@ -32,7 +31,6 @@ extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
 #else
-#define PAGE_MIGRATION 0
 
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,

include/linux/mm.h

@@ -1040,6 +1040,9 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
+extern pid_t
+vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group);
+
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len);
@@ -1058,19 +1061,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 /*
  * per-process(per-mm_struct) statistics.
  */
-static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
-{
-	atomic_long_set(&mm->rss_stat.count[member], value);
-}
-
-#if defined(SPLIT_RSS_COUNTING)
-unsigned long get_mm_counter(struct mm_struct *mm, int member);
-#else
 static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 {
-	return atomic_long_read(&mm->rss_stat.count[member]);
-}
+	long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+#ifdef SPLIT_RSS_COUNTING
+	/*
+	 * counter is updated in asynchronous manner and may go to minus.
+	 * But it's never be expected number for users.
+	 */
+	if (val < 0)
+		val = 0;
 #endif
+	return (unsigned long)val;
+}
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
@@ -1127,9 +1131,9 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 }
 
 #if defined(SPLIT_RSS_COUNTING)
-void sync_mm_rss(struct task_struct *task, struct mm_struct *mm);
+void sync_mm_rss(struct mm_struct *mm);
 #else
-static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
+static inline void sync_mm_rss(struct mm_struct *mm)
 {
 }
 #endif
@@ -1291,8 +1295,6 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 extern unsigned long find_min_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
-int add_from_early_node_map(struct range *range, int az,
-				   int nr_range, int nid);
 extern void sparse_memory_present_with_active_regions(int nid);
 
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */

include/linux/mmzone.h

@@ -365,6 +365,7 @@ struct zone {
 	 */
 	unsigned int		compact_considered;
 	unsigned int		compact_defer_shift;
+	int			compact_order_failed;
 #endif
 
 	ZONE_PADDING(_pad1_)

include/linux/oom.h

@@ -49,7 +49,7 @@ extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *mask);
+		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);
 extern int unregister_oom_notifier(struct notifier_block *nb);
 

include/linux/page-flags.h

@@ -414,11 +414,26 @@ static inline int PageTransHuge(struct page *page)
 	return PageHead(page);
 }
 
+/*
+ * PageTransCompound returns true for both transparent huge pages
+ * and hugetlbfs pages, so it should only be called when it's known
+ * that hugetlbfs pages aren't involved.
+ */
 static inline int PageTransCompound(struct page *page)
 {
 	return PageCompound(page);
 }
 
+/*
+ * PageTransTail returns true for both transparent huge pages
+ * and hugetlbfs pages, so it should only be called when it's known
+ * that hugetlbfs pages aren't involved.
+ */
+static inline int PageTransTail(struct page *page)
+{
+	return PageTail(page);
+}
+
 #else
 
 static inline int PageTransHuge(struct page *page)
@@ -430,6 +445,11 @@ static inline int PageTransCompound(struct page *page)
 {
 	return 0;
 }
+
+static inline int PageTransTail(struct page *page)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_MMU

include/linux/page_cgroup.h

@@ -4,12 +4,8 @@
 enum {
 	/* flags for mem_cgroup */
 	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-	PCG_CACHE, /* charged as cache */
 	PCG_USED, /* this object is in use. */
 	PCG_MIGRATION, /* under page migration */
-	/* flags for mem_cgroup and file and I/O status */
-	PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */
-	PCG_FILE_MAPPED, /* page is accounted as "mapped" */
 	__NR_PCG_FLAGS,
 };
 
@@ -64,19 +60,10 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
 static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
 	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
 
-/* Cache flag is set only once (at allocation) */
-TESTPCGFLAG(Cache, CACHE)
-CLEARPCGFLAG(Cache, CACHE)
-SETPCGFLAG(Cache, CACHE)
-
 TESTPCGFLAG(Used, USED)
 CLEARPCGFLAG(Used, USED)
 SETPCGFLAG(Used, USED)
 
-SETPCGFLAG(FileMapped, FILE_MAPPED)
-CLEARPCGFLAG(FileMapped, FILE_MAPPED)
-TESTPCGFLAG(FileMapped, FILE_MAPPED)
-
 SETPCGFLAG(Migration, MIGRATION)
 CLEARPCGFLAG(Migration, MIGRATION)
 TESTPCGFLAG(Migration, MIGRATION)
@@ -85,7 +72,7 @@ static inline void lock_page_cgroup(struct page_cgroup *pc)
 {
 	/*
 	 * Don't take this lock in IRQ context.
-	 * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
+	 * This lock is for pc->mem_cgroup, USED, MIGRATION
 	 */
 	bit_spin_lock(PCG_LOCK, &pc->flags);
 }
@@ -95,24 +82,6 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-static inline void move_lock_page_cgroup(struct page_cgroup *pc,
-	unsigned long *flags)
-{
-	/*
-	 * We know updates to pc->flags of page cache's stats are from both of
-	 * usual context or IRQ context. Disable IRQ to avoid deadlock.
-	 */
-	local_irq_save(*flags);
-	bit_spin_lock(PCG_MOVE_LOCK, &pc->flags);
-}
-
-static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
-	unsigned long *flags)
-{
-	bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags);
-	local_irq_restore(*flags);
-}
-
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct page_cgroup;
 

include/linux/rmap.h

@@ -122,7 +122,6 @@ void unlink_anon_vmas(struct vm_area_struct *);
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
 void anon_vma_moveto_tail(struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
-void __anon_vma_link(struct vm_area_struct *);
 
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)

include/linux/sched.h

@@ -1514,7 +1514,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
-	int mems_allowed_change_disable;
+	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
 	int cpuset_mem_spread_rotor;
 	int cpuset_slab_spread_rotor;
 #endif

include/linux/swap.h

@@ -223,6 +223,7 @@ extern void lru_add_page_tail(struct zone* zone,
 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 rotate_reclaimable_page(struct page *page);
 extern void deactivate_page(struct page *page);
@@ -329,7 +330,6 @@ extern long total_swap_pages;
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
 extern swp_entry_t get_swap_page_of_type(int);
-extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);

ipc/shm.c

@@ -482,7 +482,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		/* hugetlb_file_setup applies strict accounting */
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
-		file = hugetlb_file_setup(name, size, acctflag,
+		file = hugetlb_file_setup(name, 0, size, acctflag,
 					&shp->mlock_user, HUGETLB_SHMFS_INODE);
 	} else {
 		/*

kernel/cgroup.c

@@ -4881,9 +4881,9 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 
 	rcu_assign_pointer(id->css, NULL);
 	rcu_assign_pointer(css->id, NULL);
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, id->id);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 	kfree_rcu(id, rcu_head);
 }
 EXPORT_SYMBOL_GPL(free_css_id);
@@ -4909,10 +4909,10 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 		error = -ENOMEM;
 		goto err_out;
 	}
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	/* Don't use 0. allocates an ID of 1-65535 */
 	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 
 	/* Returns error when there are no free spaces for new ID.*/
 	if (error) {
@@ -4927,9 +4927,9 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 	return newid;
 remove_idr:
 	error = -ENOSPC;
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, myid);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 err_out:
 	kfree(newid);
 	return ERR_PTR(error);
@@ -4941,7 +4941,7 @@ static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
 {
 	struct css_id *newid;
 
-	rwlock_init(&ss->id_lock);
+	spin_lock_init(&ss->id_lock);
 	idr_init(&ss->idr);
 
 	newid = get_new_cssid(ss, 0);
@@ -5029,6 +5029,8 @@ css_get_next(struct cgroup_subsys *ss, int id,
 		return NULL;
 
 	BUG_ON(!ss->use_id);
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 	/* fill start point for scan */
 	tmpid = id;
 	while (1) {
@@ -5036,10 +5038,7 @@ css_get_next(struct cgroup_subsys *ss, int id,
 		 * scan next entry from bitmap(tree), tmpid is updated after
 		 * idr_get_next().
 		 */
-		read_lock(&ss->id_lock);
 		tmp = idr_get_next(&ss->idr, &tmpid);
-		read_unlock(&ss->id_lock);
-
 		if (!tmp)
 			break;
 		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {

kernel/cpuset.c

@@ -964,7 +964,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 {
 	bool need_loop;
 
-repeat:
 	/*
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
@@ -983,45 +982,19 @@ repeat:
 	 */
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
-	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
-	/*
-	 * ensure checking ->mems_allowed_change_disable after setting all new
-	 * allowed nodes.
-	 *
-	 * the read-side task can see an nodemask with new allowed nodes and
-	 * old allowed nodes. and if it allocates page when cpuset clears newly
-	 * disallowed ones continuous, it can see the new allowed bits.
-	 *
-	 * And if setting all new allowed nodes is after the checking, setting
-	 * all new allowed nodes and clearing newly disallowed ones will be done
-	 * continuous, and the read-side task may find no node to alloc page.
-	 */
-	smp_mb();
+	if (need_loop)
+		write_seqcount_begin(&tsk->mems_allowed_seq);
 
-	/*
-	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.
-	 */
-	while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
-		task_unlock(tsk);
-		if (!task_curr(tsk))
-			yield();
-		goto repeat;
-	}
-
-	/*
-	 * ensure checking ->mems_allowed_change_disable before clearing all new
-	 * disallowed nodes.
-	 *
-	 * if clearing newly disallowed bits before the checking, the read-side
-	 * task may find no node to alloc page.
-	 */
-	smp_mb();
+	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
+
+	if (need_loop)
+		write_seqcount_end(&tsk->mems_allowed_seq);
+
 	task_unlock(tsk);
 }
 

kernel/exit.c

@@ -935,7 +935,7 @@ void do_exit(long code)
 	acct_update_integrals(tsk);
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
-		sync_mm_rss(tsk, tsk->mm);
+		sync_mm_rss(tsk->mm);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);

kernel/fork.c

@@ -512,6 +512,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	return NULL;
 }
 
+static void check_mm(struct mm_struct *mm)
+{
+	int i;
+
+	for (i = 0; i < NR_MM_COUNTERS; i++) {
+		long x = atomic_long_read(&mm->rss_stat.count[i]);
+
+		if (unlikely(x))
+			printk(KERN_ALERT "BUG: Bad rss-counter state "
+					  "mm:%p idx:%d val:%ld\n", mm, i, x);
+	}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
+}
+
 /*
  * Allocate and initialize an mm_struct.
  */
@@ -539,9 +556,7 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON(mm->pmd_huge_pte);
-#endif
+	check_mm(mm);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -1223,6 +1238,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
 	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
+	seqcount_init(&p->mems_allowed_seq);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;

lib/idr.c

@@ -595,8 +595,10 @@ EXPORT_SYMBOL(idr_for_each);
  * Returns pointer to registered object with id, which is next number to
  * given id. After being looked up, *@nextidp will be updated for the next
  * iteration.
+ *
+ * This function can be called under rcu_read_lock(), given that the leaf
+ * pointers lifetimes are correctly managed.
  */
-
 void *idr_get_next(struct idr *idp, int *nextidp)
 {
 	struct idr_layer *p, *pa[MAX_LEVEL];
@@ -605,11 +607,11 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 	int n, max;
 
 	/* find first ent */
-	n = idp->layers * IDR_BITS;
-	max = 1 << n;
 	p = rcu_dereference_raw(idp->top);
 	if (!p)
 		return NULL;
+	n = (p->layer + 1) * IDR_BITS;
+	max = 1 << n;
 
 	while (id < max) {
 		while (n > 0 && p) {

mm/bootmem.c

@@ -766,14 +766,13 @@ void * __init alloc_bootmem_section(unsigned long size,
 				    unsigned long section_nr)
 {
 	bootmem_data_t *bdata;
-	unsigned long pfn, goal, limit;
+	unsigned long pfn, goal;
 
 	pfn = section_nr_to_pfn(section_nr);
 	goal = pfn << PAGE_SHIFT;
-	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
 	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
 
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
+	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
 }
 #endif
 

mm/compaction.c

@@ -35,7 +35,7 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
 
-	unsigned int order;		/* order a direct compactor needs */
+	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
 };
@@ -675,49 +675,71 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 
 
 /* Compact all zones within a node */
-static int compact_node(int nid)
+static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 {
 	int zoneid;
-	pg_data_t *pgdat;
 	struct zone *zone;
 
-	if (nid < 0 || nid >= nr_node_ids || !node_online(nid))
-		return -EINVAL;
-	pgdat = NODE_DATA(nid);
-
-	/* Flush pending updates to the LRU lists */
-	lru_add_drain_all();
-
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
-		struct compact_control cc = {
-			.nr_freepages = 0,
-			.nr_migratepages = 0,
-			.order = -1,
-			.sync = true,
-		};
 
 		zone = &pgdat->node_zones[zoneid];
 		if (!populated_zone(zone))
 			continue;
 
-		cc.zone = zone;
-		INIT_LIST_HEAD(&cc.freepages);
-		INIT_LIST_HEAD(&cc.migratepages);
-
-		compact_zone(zone, &cc);
+		cc->nr_freepages = 0;
+		cc->nr_migratepages = 0;
+		cc->zone = zone;
+		INIT_LIST_HEAD(&cc->freepages);
+		INIT_LIST_HEAD(&cc->migratepages);
+
+		if (cc->order == -1 || !compaction_deferred(zone, cc->order))
+			compact_zone(zone, cc);
+
+		if (cc->order > 0) {
+			int ok = zone_watermark_ok(zone, cc->order,
+						low_wmark_pages(zone), 0, 0);
+			if (ok && cc->order > zone->compact_order_failed)
+				zone->compact_order_failed = cc->order + 1;
+			/* Currently async compaction is never deferred. */
+			else if (!ok && cc->sync)
+				defer_compaction(zone, cc->order);
+		}
 
-		VM_BUG_ON(!list_empty(&cc.freepages));
-		VM_BUG_ON(!list_empty(&cc.migratepages));
+		VM_BUG_ON(!list_empty(&cc->freepages));
+		VM_BUG_ON(!list_empty(&cc->migratepages));
 	}
 
 	return 0;
 }
 
+int compact_pgdat(pg_data_t *pgdat, int order)
+{
+	struct compact_control cc = {
+		.order = order,
+		.sync = false,
+	};
+
+	return __compact_pgdat(pgdat, &cc);
+}
+
+static int compact_node(int nid)
+{
+	struct compact_control cc = {
+		.order = -1,
+		.sync = true,
+	};
+
+	return __compact_pgdat(NODE_DATA(nid), &cc);
+}
+
 /* Compact all nodes in the system */
 static int compact_nodes(void)
 {
 	int nid;
 
+	/* Flush pending updates to the LRU lists */
+	lru_add_drain_all();
+
 	for_each_online_node(nid)
 		compact_node(nid);
 
@@ -750,7 +772,14 @@ ssize_t sysfs_compact_node(struct device *dev,
 			struct device_attribute *attr,
 			const char *buf, size_t count)
 {
-	compact_node(dev->id);
+	int nid = dev->id;
+
+	if (nid >= 0 && nid < nr_node_ids && node_online(nid)) {
+		/* Flush pending updates to the LRU lists */
+		lru_add_drain_all();
+
+		compact_node(nid);
+	}
 
 	return count;
 }

mm/filemap.c

@@ -101,9 +101,8 @@
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- *  (code doesn't rely on that order, so you could switch it around)
- *  ->tasklist_lock             (memory_failure, collect_procs_ao)
- *    ->i_mmap_mutex
+ * ->i_mmap_mutex
+ *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
 /*
@@ -500,10 +499,13 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	struct page *page;
 
 	if (cpuset_do_page_mem_spread()) {
-		get_mems_allowed();
-		n = cpuset_mem_spread_node();
-		page = alloc_pages_exact_node(n, gfp, 0);
-		put_mems_allowed();
+		unsigned int cpuset_mems_cookie;
+		do {
+			cpuset_mems_cookie = get_mems_allowed();
+			n = cpuset_mem_spread_node();
+			page = alloc_pages_exact_node(n, gfp, 0);
+		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+
 		return page;
 	}
 	return alloc_pages(gfp, 0);
@@ -2341,7 +2343,9 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 	struct page *page;
 	gfp_t gfp_notmask = 0;
 
-	gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE;
+	gfp_mask = mapping_gfp_mask(mapping);
+	if (mapping_cap_account_dirty(mapping))
+		gfp_mask |= __GFP_WRITE;
 	if (flags & AOP_FLAG_NOFS)
 		gfp_notmask = __GFP_FS;
 repeat:

mm/huge_memory.c

@@ -1031,32 +1031,23 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 {
 	int ret = 0;
 
-	spin_lock(&tlb->mm->page_table_lock);
-	if (likely(pmd_trans_huge(*pmd))) {
-		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&tlb->mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma,
-					     pmd);
-		} else {
-			struct page *page;
-			pgtable_t pgtable;
-			pgtable = get_pmd_huge_pte(tlb->mm);
-			page = pmd_page(*pmd);
-			pmd_clear(pmd);
-			tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
-			page_remove_rmap(page);
-			VM_BUG_ON(page_mapcount(page) < 0);
-			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
-			VM_BUG_ON(!PageHead(page));
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
-			tlb_remove_page(tlb, page);
-			pte_free(tlb->mm, pgtable);
-			ret = 1;
-		}
-	} else
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		struct page *page;
+		pgtable_t pgtable;
+		pgtable = get_pmd_huge_pte(tlb->mm);
+		page = pmd_page(*pmd);
+		pmd_clear(pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		page_remove_rmap(page);
+		VM_BUG_ON(page_mapcount(page) < 0);
+		add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+		VM_BUG_ON(!PageHead(page));
+		tlb->mm->nr_ptes--;
 		spin_unlock(&tlb->mm->page_table_lock);
-
+		tlb_remove_page(tlb, page);
+		pte_free(tlb->mm, pgtable);
+		ret = 1;
+	}
 	return ret;
 }
 
@@ -1066,21 +1057,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	int ret = 0;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
-	if (likely(pmd_trans_huge(*pmd))) {
-		ret = !pmd_trans_splitting(*pmd);
-		spin_unlock(&vma->vm_mm->page_table_lock);
-		if (unlikely(!ret))
-			wait_split_huge_page(vma->anon_vma, pmd);
-		else {
-			/*
-			 * All logical pages in the range are present
-			 * if backed by a huge page.
-			 */
-			memset(vec, 1, (end - addr) >> PAGE_SHIFT);
-		}
-	} else
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		/*
+		 * All logical pages in the range are present
+		 * if backed by a huge page.
+		 */
 		spin_unlock(&vma->vm_mm->page_table_lock);
+		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
+		ret = 1;
+	}
 
 	return ret;
 }
@@ -1110,20 +1095,11 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		goto out;
 	}
 
-	spin_lock(&mm->page_table_lock);
-	if (likely(pmd_trans_huge(*old_pmd))) {
-		if (pmd_trans_splitting(*old_pmd)) {
-			spin_unlock(&mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma, old_pmd);
-			ret = -1;
-		} else {
-			pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
-			VM_BUG_ON(!pmd_none(*new_pmd));
-			set_pmd_at(mm, new_addr, new_pmd, pmd);
-			spin_unlock(&mm->page_table_lock);
-			ret = 1;
-		}
-	} else {
+	ret = __pmd_trans_huge_lock(old_pmd, vma);
+	if (ret == 1) {
+		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
+		VM_BUG_ON(!pmd_none(*new_pmd));
+		set_pmd_at(mm, new_addr, new_pmd, pmd);
 		spin_unlock(&mm->page_table_lock);
 	}
 out:
@@ -1136,24 +1112,41 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	struct mm_struct *mm = vma->vm_mm;
 	int ret = 0;
 
-	spin_lock(&mm->page_table_lock);
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		pmd_t entry;
+		entry = pmdp_get_and_clear(mm, addr, pmd);
+		entry = pmd_modify(entry, newprot);
+		set_pmd_at(mm, addr, pmd, entry);
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+/*
+ * Returns 1 if a given pmd maps a stable (not under splitting) thp.
+ * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
+ *
+ * Note that if it returns 1, this routine returns without unlocking page
+ * table locks. So callers must unlock them.
+ */
+int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
+{
+	spin_lock(&vma->vm_mm->page_table_lock);
 	if (likely(pmd_trans_huge(*pmd))) {
 		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(&vma->vm_mm->page_table_lock);
 			wait_split_huge_page(vma->anon_vma, pmd);
+			return -1;
 		} else {
-			pmd_t entry;
-
-			entry = pmdp_get_and_clear(mm, addr, pmd);
-			entry = pmd_modify(entry, newprot);
-			set_pmd_at(mm, addr, pmd, entry);
-			spin_unlock(&vma->vm_mm->page_table_lock);
-			ret = 1;
+			/* Thp mapped by 'pmd' is stable, so we can
+			 * handle it as it is. */
+			return 1;
 		}
-	} else
-		spin_unlock(&vma->vm_mm->page_table_lock);
-
-	return ret;
+	}
+	spin_unlock(&vma->vm_mm->page_table_lock);
+	return 0;
 }
 
 pmd_t *page_check_address_pmd(struct page *page,

mm/hugetlb.c

@@ -53,6 +53,84 @@ static unsigned long __initdata default_hstate_size;
  */
 static DEFINE_SPINLOCK(hugetlb_lock);
 
+static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
+{
+	bool free = (spool->count == 0) && (spool->used_hpages == 0);
+
+	spin_unlock(&spool->lock);
+
+	/* If no pages are used, and no other handles to the subpool
+	 * remain, free the subpool the subpool remain */
+	if (free)
+		kfree(spool);
+}
+
+struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
+{
+	struct hugepage_subpool *spool;
+
+	spool = kmalloc(sizeof(*spool), GFP_KERNEL);
+	if (!spool)
+		return NULL;
+
+	spin_lock_init(&spool->lock);
+	spool->count = 1;
+	spool->max_hpages = nr_blocks;
+	spool->used_hpages = 0;
+
+	return spool;
+}
+
+void hugepage_put_subpool(struct hugepage_subpool *spool)
+{
+	spin_lock(&spool->lock);
+	BUG_ON(!spool->count);
+	spool->count--;
+	unlock_or_release_subpool(spool);
+}
+
+static int hugepage_subpool_get_pages(struct hugepage_subpool *spool,
+				      long delta)
+{
+	int ret = 0;
+
+	if (!spool)
+		return 0;
+
+	spin_lock(&spool->lock);
+	if ((spool->used_hpages + delta) <= spool->max_hpages) {
+		spool->used_hpages += delta;
+	} else {
+		ret = -ENOMEM;
+	}
+	spin_unlock(&spool->lock);
+
+	return ret;
+}
+
+static void hugepage_subpool_put_pages(struct hugepage_subpool *spool,
+				       long delta)
+{
+	if (!spool)
+		return;
+
+	spin_lock(&spool->lock);
+	spool->used_hpages -= delta;
+	/* If hugetlbfs_put_super couldn't free spool due to
+	* an outstanding quota reference, free it now. */
+	unlock_or_release_subpool(spool);
+}
+
+static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
+{
+	return HUGETLBFS_SB(inode->i_sb)->spool;
+}
+
+static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
+{
+	return subpool_inode(vma->vm_file->f_dentry->d_inode);
+}
+
 /*
  * Region tracking -- allows tracking of reservations and instantiated pages
  *                    across the pages in a mapping.
@@ -454,14 +532,16 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
-	struct page *page = NULL;
+	struct page *page;
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
+	unsigned int cpuset_mems_cookie;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol, &nodemask);
 	/*
@@ -488,10 +568,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			}
 		}
 	}
-err:
+
 	mpol_cond_put(mpol);
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
+
+err:
+	mpol_cond_put(mpol);
+	return NULL;
 }
 
 static void update_and_free_page(struct hstate *h, struct page *page)
@@ -533,9 +618,9 @@ static void free_huge_page(struct page *page)
 	 */
 	struct hstate *h = page_hstate(page);
 	int nid = page_to_nid(page);
-	struct address_space *mapping;
+	struct hugepage_subpool *spool =
+		(struct hugepage_subpool *)page_private(page);
 
-	mapping = (struct address_space *) page_private(page);
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
@@ -551,8 +636,7 @@ static void free_huge_page(struct page *page)
 		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
-	if (mapping)
-		hugetlb_put_quota(mapping, 1);
+	hugepage_subpool_put_pages(spool, 1);
 }
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
@@ -852,6 +936,7 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 	struct page *page, *tmp;
 	int ret, i;
 	int needed, allocated;
+	bool alloc_ok = true;
 
 	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
 	if (needed <= 0) {
@@ -867,17 +952,13 @@ retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
-		if (!page)
-			/*
-			 * We were not able to allocate enough pages to
-			 * satisfy the entire reservation so we free what
-			 * we've allocated so far.
-			 */
-			goto free;
-
+		if (!page) {
+			alloc_ok = false;
+			break;
+		}
 		list_add(&page->lru, &surplus_list);
 	}
-	allocated += needed;
+	allocated += i;
 
 	/*
 	 * After retaking hugetlb_lock, we need to recalculate 'needed'
@@ -886,9 +967,16 @@ retry:
 	spin_lock(&hugetlb_lock);
 	needed = (h->resv_huge_pages + delta) -
 			(h->free_huge_pages + allocated);
-	if (needed > 0)
-		goto retry;
-
+	if (needed > 0) {
+		if (alloc_ok)
+			goto retry;
+		/*
+		 * We were not able to allocate enough pages to
+		 * satisfy the entire reservation so we free what
+		 * we've allocated so far.
+		 */
+		goto free;
+	}
 	/*
 	 * The surplus_list now contains _at_least_ the number of extra pages
 	 * needed to accommodate the reservation.  Add the appropriate number
@@ -914,10 +1002,10 @@ retry:
 		VM_BUG_ON(page_count(page));
 		enqueue_huge_page(h, page);
 	}
+free:
 	spin_unlock(&hugetlb_lock);
 
 	/* Free unnecessary surplus pages to the buddy allocator */
-free:
 	if (!list_empty(&surplus_list)) {
 		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 			list_del(&page->lru);
@@ -966,11 +1054,12 @@ static void return_unused_surplus_pages(struct hstate *h,
 /*
  * Determine if the huge page at addr within the vma has an associated
  * reservation.  Where it does not we will need to logically increase
- * reservation and actually increase quota before an allocation can occur.
- * Where any new reservation would be required the reservation change is
- * prepared, but not committed.  Once the page has been quota'd allocated
- * an instantiated the change should be committed via vma_commit_reservation.
- * No action is required on failure.
+ * reservation and actually increase subpool usage before an allocation
+ * can occur.  Where any new reservation would be required the
+ * reservation change is prepared, but not committed.  Once the page
+ * has been allocated from the subpool and instantiated the change should
+ * be committed via vma_commit_reservation.  No action is required on
+ * failure.
  */
 static long vma_needs_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
@@ -1019,24 +1108,24 @@ static void vma_commit_reservation(struct hstate *h,
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {
+	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	struct inode *inode = mapping->host;
 	long chg;
 
 	/*
-	 * Processes that did not create the mapping will have no reserves and
-	 * will not have accounted against quota. Check that the quota can be
-	 * made before satisfying the allocation
-	 * MAP_NORESERVE mappings may also need pages and quota allocated
-	 * if no reserve mapping overlaps.
+	 * Processes that did not create the mapping will have no
+	 * reserves and will not have accounted against subpool
+	 * limit. Check that the subpool limit can be made before
+	 * satisfying the allocation MAP_NORESERVE mappings may also
+	 * need pages and subpool limit allocated allocated if no reserve
+	 * mapping overlaps.
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
 		return ERR_PTR(-VM_FAULT_OOM);
 	if (chg)
-		if (hugetlb_get_quota(inode->i_mapping, chg))
+		if (hugepage_subpool_get_pages(spool, chg))
 			return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
@@ -1046,12 +1135,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	if (!page) {
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
-			hugetlb_put_quota(inode->i_mapping, chg);
+			hugepage_subpool_put_pages(spool, chg);
 			return ERR_PTR(-VM_FAULT_SIGBUS);
 		}
 	}
 
-	set_page_private(page, (unsigned long) mapping);
+	set_page_private(page, (unsigned long)spool);
 
 	vma_commit_reservation(h, vma, addr);
 
@@ -2072,6 +2161,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct resv_map *reservations = vma_resv_map(vma);
+	struct hugepage_subpool *spool = subpool_vma(vma);
 	unsigned long reserve;
 	unsigned long start;
 	unsigned long end;
@@ -2087,7 +2177,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
-			hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
+			hugepage_subpool_put_pages(spool, reserve);
 		}
 	}
 }
@@ -2276,6 +2366,10 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		if (pte_dirty(pte))
 			set_page_dirty(page);
 		list_add(&page->lru, &page_list);
+
+		/* Bail out after unmapping reference page if supplied */
+		if (ref_page)
+			break;
 	}
 	flush_tlb_range(vma, start, end);
 	spin_unlock(&mm->page_table_lock);
@@ -2316,7 +2410,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	address = address & huge_page_mask(h);
 	pgoff = vma_hugecache_offset(h, vma, address);
-	mapping = (struct address_space *)page_private(page);
+	mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
 
 	/*
 	 * Take the mapping lock for the duration of the table walk. As
@@ -2869,11 +2963,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 {
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
+	struct hugepage_subpool *spool = subpool_inode(inode);
 
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
-	 * and filesystem quota without using reserves
+	 * without using reserves
 	 */
 	if (vm_flags & VM_NORESERVE)
 		return 0;
@@ -2900,17 +2995,17 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (chg < 0)
 		return chg;
 
-	/* There must be enough filesystem quota for the mapping */
-	if (hugetlb_get_quota(inode->i_mapping, chg))
+	/* There must be enough pages in the subpool for the mapping */
+	if (hugepage_subpool_get_pages(spool, chg))
 		return -ENOSPC;
 
 	/*
 	 * Check enough hugepages are available for the reservation.
-	 * Hand back the quota if there are not
+	 * Hand the pages back to the subpool if there are not
 	 */
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
-		hugetlb_put_quota(inode->i_mapping, chg);
+		hugepage_subpool_put_pages(spool, chg);
 		return ret;
 	}
 
@@ -2934,12 +3029,13 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
 	struct hstate *h = hstate_inode(inode);
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+	struct hugepage_subpool *spool = subpool_inode(inode);
 
 	spin_lock(&inode->i_lock);
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
 
-	hugetlb_put_quota(inode->i_mapping, (chg - freed));
+	hugepage_subpool_put_pages(spool, (chg - freed));
 	hugetlb_acct_memory(h, -(chg - freed));
 }
 

mm/ksm.c

@@ -374,6 +374,20 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 	return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
 }
 
+static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
+		unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	if (ksm_test_exit(mm))
+		return NULL;
+	vma = find_vma(mm, addr);
+	if (!vma || vma->vm_start > addr)
+		return NULL;
+	if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
+		return NULL;
+	return vma;
+}
+
 static void break_cow(struct rmap_item *rmap_item)
 {
 	struct mm_struct *mm = rmap_item->mm;
@@ -387,15 +401,9 @@ static void break_cow(struct rmap_item *rmap_item)
 	put_anon_vma(rmap_item->anon_vma);
 
 	down_read(&mm->mmap_sem);
-	if (ksm_test_exit(mm))
-		goto out;
-	vma = find_vma(mm, addr);
-	if (!vma || vma->vm_start > addr)
-		goto out;
-	if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
-		goto out;
-	break_ksm(vma, addr);
-out:
+	vma = find_mergeable_vma(mm, addr);
+	if (vma)
+		break_ksm(vma, addr);
 	up_read(&mm->mmap_sem);
 }
 
@@ -421,12 +429,8 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 	struct page *page;
 
 	down_read(&mm->mmap_sem);
-	if (ksm_test_exit(mm))
-		goto out;
-	vma = find_vma(mm, addr);
-	if (!vma || vma->vm_start > addr)
-		goto out;
-	if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
+	vma = find_mergeable_vma(mm, addr);
+	if (!vma)
 		goto out;
 
 	page = follow_page(vma, addr, FOLL_GET);

mm/memcontrol.c

@@ -89,7 +89,6 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
 	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
 	MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
-	MEM_CGROUP_ON_MOVE,	/* someone is moving account between groups */
 	MEM_CGROUP_STAT_NSTATS,
 };
 
@@ -135,7 +134,7 @@ struct mem_cgroup_reclaim_iter {
  */
 struct mem_cgroup_per_zone {
 	struct lruvec		lruvec;
-	unsigned long		count[NR_LRU_LISTS];
+	unsigned long		lru_size[NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
@@ -144,11 +143,9 @@ struct mem_cgroup_per_zone {
 	unsigned long long	usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
-	struct mem_cgroup	*mem;		/* Back pointer, we cannot */
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
-/* Macro for accessing counter */
-#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
 
 struct mem_cgroup_per_node {
 	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
@@ -299,6 +296,12 @@ struct mem_cgroup {
 	 * mem_cgroup ? And what type of charges should we move ?
 	 */
 	unsigned long 	move_charge_at_immigrate;
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t	moving_account;
+	/* taken only while moving_account > 0 */
+	spinlock_t	move_lock;
 	/*
 	 * percpu counter.
 	 */
@@ -612,9 +615,9 @@ retry:
 	 * we will to add it back at the end of reclaim to its correct
 	 * position in the tree.
 	 */
-	__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
-	if (!res_counter_soft_limit_excess(&mz->mem->res) ||
-		!css_tryget(&mz->mem->css))
+	__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;
@@ -692,15 +695,19 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
-					 bool file, int nr_pages)
+					 bool anon, int nr_pages)
 {
 	preempt_disable();
 
-	if (file)
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
+	/*
+	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
+	 * counted as CACHE even if it's on ANON LRU.
+	 */
+	if (anon)
+		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
 				nr_pages);
 	else
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
+		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 
 	/* pagein of a big page is an event. So, ignore page size */
@@ -721,14 +728,14 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
 			unsigned int lru_mask)
 {
 	struct mem_cgroup_per_zone *mz;
-	enum lru_list l;
+	enum lru_list lru;
 	unsigned long ret = 0;
 
 	mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
-	for_each_lru(l) {
-		if (BIT(l) & lru_mask)
-			ret += MEM_CGROUP_ZSTAT(mz, l);
+	for_each_lru(lru) {
+		if (BIT(lru) & lru_mask)
+			ret += mz->lru_size[lru];
 	}
 	return ret;
 }
@@ -1077,7 +1084,7 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
 
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* compound_order() is stabilized through lru_lock */
-	MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
+	mz->lru_size[lru] += 1 << compound_order(page);
 	return &mz->lruvec;
 }
 
@@ -1105,8 +1112,8 @@ void mem_cgroup_lru_del_list(struct page *page, enum lru_list lru)
 	VM_BUG_ON(!memcg);
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* huge page split is done under lru_lock. so, we have no races. */
-	VM_BUG_ON(MEM_CGROUP_ZSTAT(mz, lru) < (1 << compound_order(page)));
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page);
+	VM_BUG_ON(mz->lru_size[lru] < (1 << compound_order(page)));
+	mz->lru_size[lru] -= 1 << compound_order(page);
 }
 
 void mem_cgroup_lru_del(struct page *page)
@@ -1285,40 +1292,48 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 	return memcg->swappiness;
 }
 
-static void mem_cgroup_start_move(struct mem_cgroup *memcg)
-{
-	int cpu;
+/*
+ * memcg->moving_account is used for checking possibility that some thread is
+ * calling move_account(). When a thread on CPU-A starts moving pages under
+ * a memcg, other threads should check memcg->moving_account under
+ * rcu_read_lock(), like this:
+ *
+ *         CPU-A                                    CPU-B
+ *                                              rcu_read_lock()
+ *         memcg->moving_account+1              if (memcg->mocing_account)
+ *                                                   take heavy locks.
+ *         synchronize_rcu()                    update something.
+ *                                              rcu_read_unlock()
+ *         start move here.
+ */
 
-	get_online_cpus();
-	spin_lock(&memcg->pcp_counter_lock);
-	for_each_online_cpu(cpu)
-		per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
-	memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
-	spin_unlock(&memcg->pcp_counter_lock);
-	put_online_cpus();
+/* for quick checking without looking up memcg */
+atomic_t memcg_moving __read_mostly;
 
+static void mem_cgroup_start_move(struct mem_cgroup *memcg)
+{
+	atomic_inc(&memcg_moving);
+	atomic_inc(&memcg->moving_account);
 	synchronize_rcu();
 }
 
 static void mem_cgroup_end_move(struct mem_cgroup *memcg)
 {
-	int cpu;
-
-	if (!memcg)
-		return;
-	get_online_cpus();
-	spin_lock(&memcg->pcp_counter_lock);
-	for_each_online_cpu(cpu)
-		per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
-	memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
-	spin_unlock(&memcg->pcp_counter_lock);
-	put_online_cpus();
+	/*
+	 * Now, mem_cgroup_clear_mc() may call this function with NULL.
+	 * We check NULL in callee rather than caller.
+	 */
+	if (memcg) {
+		atomic_dec(&memcg_moving);
+		atomic_dec(&memcg->moving_account);
+	}
 }
+
 /*
  * 2 routines for checking "mem" is under move_account() or not.
  *
- * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used
- *			  for avoiding race in accounting. If true,
+ * mem_cgroup_stolen() -  checking whether a cgroup is mc.from or not. This
+ *			  is used for avoiding races in accounting.  If true,
  *			  pc->mem_cgroup may be overwritten.
  *
  * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
@@ -1326,10 +1341,10 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg)
  *			  waiting at hith-memory prressure caused by "move".
  */
 
-static bool mem_cgroup_stealed(struct mem_cgroup *memcg)
+static bool mem_cgroup_stolen(struct mem_cgroup *memcg)
 {
 	VM_BUG_ON(!rcu_read_lock_held());
-	return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+	return atomic_read(&memcg->moving_account) > 0;
 }
 
 static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
@@ -1370,6 +1385,24 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
 	return false;
 }
 
+/*
+ * Take this lock when
+ * - a code tries to modify page's memcg while it's USED.
+ * - a code tries to modify page state accounting in a memcg.
+ * see mem_cgroup_stolen(), too.
+ */
+static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
+				  unsigned long *flags)
+{
+	spin_lock_irqsave(&memcg->move_lock, *flags);
+}
+
+static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
+				unsigned long *flags)
+{
+	spin_unlock_irqrestore(&memcg->move_lock, *flags);
+}
+
 /**
  * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
  * @memcg: The memory cgroup that went over limit
@@ -1393,7 +1426,6 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	if (!memcg || !p)
 		return;
 
-
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1772,22 +1804,22 @@ static DEFINE_SPINLOCK(memcg_oom_lock);
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
 
 struct oom_wait_info {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *memcg;
 	wait_queue_t	wait;
 };
 
 static int memcg_oom_wake_function(wait_queue_t *wait,
 	unsigned mode, int sync, void *arg)
 {
-	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg,
-			  *oom_wait_memcg;
+	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
+	struct mem_cgroup *oom_wait_memcg;
 	struct oom_wait_info *oom_wait_info;
 
 	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
-	oom_wait_memcg = oom_wait_info->mem;
+	oom_wait_memcg = oom_wait_info->memcg;
 
 	/*
-	 * Both of oom_wait_info->mem and wake_mem are stable under us.
+	 * Both of oom_wait_info->memcg and wake_memcg are stable under us.
 	 * Then we can use css_is_ancestor without taking care of RCU.
 	 */
 	if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
@@ -1811,12 +1843,12 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 /*
  * try to call OOM killer. returns false if we should exit memory-reclaim loop.
  */
-bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
+bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
 	struct oom_wait_info owait;
 	bool locked, need_to_kill;
 
-	owait.mem = memcg;
+	owait.memcg = memcg;
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
@@ -1841,7 +1873,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
 
 	if (need_to_kill) {
 		finish_wait(&memcg_oom_waitq, &owait.wait);
-		mem_cgroup_out_of_memory(memcg, mask);
+		mem_cgroup_out_of_memory(memcg, mask, order);
 	} else {
 		schedule();
 		finish_wait(&memcg_oom_waitq, &owait.wait);
@@ -1881,41 +1913,66 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
  * by flags.
  *
  * Considering "move", this is an only case we see a race. To make the race
- * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
- * possibility of race condition. If there is, we take a lock.
+ * small, we check mm->moving_account and detect there are possibility of race
+ * If there is, we take a lock.
  */
 
+void __mem_cgroup_begin_update_page_stat(struct page *page,
+				bool *locked, unsigned long *flags)
+{
+	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
+
+	pc = lookup_page_cgroup(page);
+again:
+	memcg = pc->mem_cgroup;
+	if (unlikely(!memcg || !PageCgroupUsed(pc)))
+		return;
+	/*
+	 * If this memory cgroup is not under account moving, we don't
+	 * need to take move_lock_page_cgroup(). Because we already hold
+	 * rcu_read_lock(), any calls to move_account will be delayed until
+	 * rcu_read_unlock() if mem_cgroup_stolen() == true.
+	 */
+	if (!mem_cgroup_stolen(memcg))
+		return;
+
+	move_lock_mem_cgroup(memcg, flags);
+	if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
+		move_unlock_mem_cgroup(memcg, flags);
+		goto again;
+	}
+	*locked = true;
+}
+
+void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
+{
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+
+	/*
+	 * It's guaranteed that pc->mem_cgroup never changes while
+	 * lock is held because a routine modifies pc->mem_cgroup
+	 * should take move_lock_page_cgroup().
+	 */
+	move_unlock_mem_cgroup(pc->mem_cgroup, flags);
+}
+
 void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_page_stat_item idx, int val)
 {
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc = lookup_page_cgroup(page);
-	bool need_unlock = false;
 	unsigned long uninitialized_var(flags);
 
 	if (mem_cgroup_disabled())
 		return;
 
-	rcu_read_lock();
 	memcg = pc->mem_cgroup;
 	if (unlikely(!memcg || !PageCgroupUsed(pc)))
-		goto out;
-	/* pc->mem_cgroup is unstable ? */
-	if (unlikely(mem_cgroup_stealed(memcg)) || PageTransHuge(page)) {
-		/* take a lock against to access pc->mem_cgroup */
-		move_lock_page_cgroup(pc, &flags);
-		need_unlock = true;
-		memcg = pc->mem_cgroup;
-		if (!memcg || !PageCgroupUsed(pc))
-			goto out;
-	}
+		return;
 
 	switch (idx) {
 	case MEMCG_NR_FILE_MAPPED:
-		if (val > 0)
-			SetPageCgroupFileMapped(pc);
-		else if (!page_mapped(page))
-			ClearPageCgroupFileMapped(pc);
 		idx = MEM_CGROUP_STAT_FILE_MAPPED;
 		break;
 	default:
@@ -1923,14 +1980,7 @@ void mem_cgroup_update_page_stat(struct page *page,
 	}
 
 	this_cpu_add(memcg->stat->count[idx], val);
-
-out:
-	if (unlikely(need_unlock))
-		move_unlock_page_cgroup(pc, &flags);
-	rcu_read_unlock();
-	return;
 }
-EXPORT_SYMBOL(mem_cgroup_update_page_stat);
 
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
@@ -2101,17 +2151,6 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
 		per_cpu(memcg->stat->events[i], cpu) = 0;
 		memcg->nocpu_base.events[i] += x;
 	}
-	/* need to clear ON_MOVE value, works as a kind of lock. */
-	per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
-	spin_unlock(&memcg->pcp_counter_lock);
-}
-
-static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu)
-{
-	int idx = MEM_CGROUP_ON_MOVE;
-
-	spin_lock(&memcg->pcp_counter_lock);
-	per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx];
 	spin_unlock(&memcg->pcp_counter_lock);
 }
 
@@ -2123,11 +2162,8 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	struct memcg_stock_pcp *stock;
 	struct mem_cgroup *iter;
 
-	if ((action == CPU_ONLINE)) {
-		for_each_mem_cgroup(iter)
-			synchronize_mem_cgroup_on_move(iter, cpu);
+	if (action == CPU_ONLINE)
 		return NOTIFY_OK;
-	}
 
 	if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
@@ -2212,7 +2248,7 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	if (!oom_check)
 		return CHARGE_NOMEM;
 	/* check OOM */
-	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask))
+	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
 		return CHARGE_OOM_DIE;
 
 	return CHARGE_RETRY;
@@ -2446,6 +2482,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 {
 	struct zone *uninitialized_var(zone);
 	bool was_on_lru = false;
+	bool anon;
 
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
@@ -2481,19 +2518,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * See mem_cgroup_add_lru_list(), etc.
  	 */
 	smp_wmb();
-	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_CACHE:
-	case MEM_CGROUP_CHARGE_TYPE_SHMEM:
-		SetPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
-		ClearPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	default:
-		break;
-	}
+	SetPageCgroupUsed(pc);
 
 	if (lrucare) {
 		if (was_on_lru) {
@@ -2504,7 +2529,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+		anon = true;
+	else
+		anon = false;
+
+	mem_cgroup_charge_statistics(memcg, anon, nr_pages);
 	unlock_page_cgroup(pc);
 
 	/*
@@ -2517,8 +2547,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
-			(1 << PCG_MIGRATION))
+#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION))
 /*
  * Because tail pages are not marked as "used", set it. We're under
  * zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -2569,6 +2598,7 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
+	bool anon = PageAnon(page);
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON(PageLRU(page));
@@ -2588,23 +2618,23 @@ static int mem_cgroup_move_account(struct page *page,
 	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
 		goto unlock;
 
-	move_lock_page_cgroup(pc, &flags);
+	move_lock_mem_cgroup(from, &flags);
 
-	if (PageCgroupFileMapped(pc)) {
+	if (!anon && page_mapped(page)) {
 		/* Update mapped_file data for mem_cgroup */
 		preempt_disable();
 		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(from, anon, -nr_pages);
 	if (uncharge)
 		/* This is not "cancel", but cancel_charge does all we need. */
 		__mem_cgroup_cancel_charge(from, nr_pages);
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages);
+	mem_cgroup_charge_statistics(to, anon, nr_pages);
 	/*
 	 * We charges against "to" which may not have any tasks. Then, "to"
 	 * can be under rmdir(). But in current implementation, caller of
@@ -2612,7 +2642,7 @@ static int mem_cgroup_move_account(struct page *page,
 	 * guaranteed that "to" is never removed. So, we don't check rmdir
 	 * status here.
 	 */
-	move_unlock_page_cgroup(pc, &flags);
+	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
 	unlock_page_cgroup(pc);
@@ -2914,7 +2944,6 @@ direct_uncharge:
 		res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE);
 	if (unlikely(batch->memcg != memcg))
 		memcg_oom_recover(memcg);
-	return;
 }
 
 /*
@@ -2926,6 +2955,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
+	bool anon;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -2951,8 +2981,17 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	if (!PageCgroupUsed(pc))
 		goto unlock_out;
 
+	anon = PageAnon(page);
+
 	switch (ctype) {
 	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+		/*
+		 * Generally PageAnon tells if it's the anon statistics to be
+		 * updated; but sometimes e.g. mem_cgroup_uncharge_page() is
+		 * used before page reached the stage of being marked PageAnon.
+		 */
+		anon = true;
+		/* fallthrough */
 	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		/* See mem_cgroup_prepare_migration() */
 		if (page_mapped(page) || PageCgroupMigration(pc))
@@ -2969,7 +3008,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		break;
 	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
 
 	ClearPageCgroupUsed(pc);
 	/*
@@ -3276,6 +3315,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 {
 	struct page *used, *unused;
 	struct page_cgroup *pc;
+	bool anon;
 
 	if (!memcg)
 		return;
@@ -3297,8 +3337,10 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	lock_page_cgroup(pc);
 	ClearPageCgroupMigration(pc);
 	unlock_page_cgroup(pc);
-
-	__mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE);
+	anon = PageAnon(used);
+	__mem_cgroup_uncharge_common(unused,
+		anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
+		     : MEM_CGROUP_CHARGE_TYPE_CACHE);
 
 	/*
 	 * If a page is a file cache, radix-tree replacement is very atomic
@@ -3308,7 +3350,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 * and USED bit check in mem_cgroup_uncharge_page() will do enough
 	 * check. (see prepare_charge() also)
 	 */
-	if (PageAnon(used))
+	if (anon)
 		mem_cgroup_uncharge_page(used);
 	/*
 	 * At migration, we may charge account against cgroup which has no
@@ -3338,7 +3380,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	/* fix accounting on old pages */
 	lock_page_cgroup(pc);
 	memcg = pc->mem_cgroup;
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -1);
+	mem_cgroup_charge_statistics(memcg, false, -1);
 	ClearPageCgroupUsed(pc);
 	unlock_page_cgroup(pc);
 
@@ -3549,7 +3591,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 
 		nr_scanned = 0;
-		reclaimed = mem_cgroup_soft_reclaim(mz->mem, zone,
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
@@ -3576,13 +3618,13 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 				next_mz =
 				__mem_cgroup_largest_soft_limit_node(mctz);
 				if (next_mz == mz)
-					css_put(&next_mz->mem->css);
+					css_put(&next_mz->memcg->css);
 				else /* next_mz == NULL or other memcg */
 					break;
 			} while (1);
 		}
-		__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
-		excess = res_counter_soft_limit_excess(&mz->mem->res);
+		__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.
@@ -3592,9 +3634,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 		 * term TODO.
 		 */
 		/* If excess == 0, no tree ops */
-		__mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess);
+		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
 		spin_unlock(&mctz->lock);
-		css_put(&mz->mem->css);
+		css_put(&mz->memcg->css);
 		loop++;
 		/*
 		 * Could not reclaim anything and there are no more
@@ -3607,7 +3649,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 	} while (!nr_reclaimed);
 	if (next_mz)
-		css_put(&next_mz->mem->css);
+		css_put(&next_mz->memcg->css);
 	return nr_reclaimed;
 }
 
@@ -3629,7 +3671,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 	mz = mem_cgroup_zoneinfo(memcg, node, zid);
 	list = &mz->lruvec.lists[lru];
 
-	loop = MEM_CGROUP_ZSTAT(mz, lru);
+	loop = mz->lru_size[lru];
 	/* give some margin against EBUSY etc...*/
 	loop += 256;
 	busy = NULL;
@@ -3703,10 +3745,10 @@ move_account:
 		mem_cgroup_start_move(memcg);
 		for_each_node_state(node, N_HIGH_MEMORY) {
 			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
-				enum lru_list l;
-				for_each_lru(l) {
+				enum lru_list lru;
+				for_each_lru(lru) {
 					ret = mem_cgroup_force_empty_list(memcg,
-							node, zid, l);
+							node, zid, lru);
 					if (ret)
 						break;
 				}
@@ -3860,7 +3902,6 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 		break;
 	default:
 		BUG();
-		break;
 	}
 	return val;
 }
@@ -3939,7 +3980,6 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
 out:
 	*mem_limit = min_limit;
 	*memsw_limit = min_memsw_limit;
-	return;
 }
 
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
@@ -4098,38 +4138,38 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
 	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
 	unsigned long node_nr;
 	struct cgroup *cont = m->private;
-	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	total_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL);
+	total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
 	seq_printf(m, "total=%lu", total_nr);
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, LRU_ALL);
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	file_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_FILE);
+	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
 	seq_printf(m, "file=%lu", file_nr);
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_FILE);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	anon_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_ANON);
+	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
 	seq_printf(m, "anon=%lu", anon_nr);
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_ANON);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	unevictable_nr = mem_cgroup_nr_lru_pages(mem_cont, BIT(LRU_UNEVICTABLE));
+	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
 	seq_printf(m, "unevictable=%lu", unevictable_nr);
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				BIT(LRU_UNEVICTABLE));
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
@@ -4141,12 +4181,12 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct cgroup_map_cb *cb)
 {
-	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	struct mcs_total_stat mystat;
 	int i;
 
 	memset(&mystat, 0, sizeof(mystat));
-	mem_cgroup_get_local_stat(mem_cont, &mystat);
+	mem_cgroup_get_local_stat(memcg, &mystat);
 
 
 	for (i = 0; i < NR_MCS_STAT; i++) {
@@ -4158,14 +4198,14 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	/* Hierarchical information */
 	{
 		unsigned long long limit, memsw_limit;
-		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
+		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
 		cb->fill(cb, "hierarchical_memory_limit", limit);
 		if (do_swap_account)
 			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
 	}
 
 	memset(&mystat, 0, sizeof(mystat));
-	mem_cgroup_get_total_stat(mem_cont, &mystat);
+	mem_cgroup_get_total_stat(memcg, &mystat);
 	for (i = 0; i < NR_MCS_STAT; i++) {
 		if (i == MCS_SWAP && !do_swap_account)
 			continue;
@@ -4181,7 +4221,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 
 		for_each_online_node(nid)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
+				mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
 				recent_rotated[0] +=
 					mz->reclaim_stat.recent_rotated[0];
@@ -4426,12 +4466,6 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	else
 		BUG();
 
-	/*
-	 * Something went wrong if we trying to unregister a threshold
-	 * if we don't have thresholds
-	 */
-	BUG_ON(!thresholds);
-
 	if (!thresholds->primary)
 		goto unlock;
 
@@ -4736,7 +4770,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup_per_zone *mz;
-	enum lru_list l;
+	enum lru_list lru;
 	int zone, tmp = node;
 	/*
 	 * This routine is called against possible nodes.
@@ -4754,11 +4788,11 @@ 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];
-		for_each_lru(l)
-			INIT_LIST_HEAD(&mz->lruvec.lists[l]);
+		for_each_lru(lru)
+			INIT_LIST_HEAD(&mz->lruvec.lists[lru]);
 		mz->usage_in_excess = 0;
 		mz->on_tree = false;
-		mz->mem = memcg;
+		mz->memcg = memcg;
 	}
 	memcg->info.nodeinfo[node] = pn;
 	return 0;
@@ -4771,29 +4805,29 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *memcg;
 	int size = sizeof(struct mem_cgroup);
 
 	/* Can be very big if MAX_NUMNODES is very big */
 	if (size < PAGE_SIZE)
-		mem = kzalloc(size, GFP_KERNEL);
+		memcg = kzalloc(size, GFP_KERNEL);
 	else
-		mem = vzalloc(size);
+		memcg = vzalloc(size);
 
-	if (!mem)
+	if (!memcg)
 		return NULL;
 
-	mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
-	if (!mem->stat)
+	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
+	if (!memcg->stat)
 		goto out_free;
-	spin_lock_init(&mem->pcp_counter_lock);
-	return mem;
+	spin_lock_init(&memcg->pcp_counter_lock);
+	return memcg;
 
 out_free:
 	if (size < PAGE_SIZE)
-		kfree(mem);
+		kfree(memcg);
 	else
-		vfree(mem);
+		vfree(memcg);
 	return NULL;
 }
 
@@ -4981,6 +5015,7 @@ mem_cgroup_create(struct cgroup *cont)
 	atomic_set(&memcg->refcnt, 1);
 	memcg->move_charge_at_immigrate = 0;
 	mutex_init(&memcg->thresholds_lock);
+	spin_lock_init(&memcg->move_lock);
 	return &memcg->css;
 free_out:
 	__mem_cgroup_free(memcg);
@@ -5075,7 +5110,7 @@ one_by_one:
 }
 
 /**
- * is_target_pte_for_mc - check a pte whether it is valid for move charge
+ * get_mctgt_type - get target type of moving charge
  * @vma: the vma the pte to be checked belongs
  * @addr: the address corresponding to the pte to be checked
  * @ptent: the pte to be checked
@@ -5098,7 +5133,7 @@ union mc_target {
 };
 
 enum mc_target_type {
-	MC_TARGET_NONE,	/* not used */
+	MC_TARGET_NONE = 0,
 	MC_TARGET_PAGE,
 	MC_TARGET_SWAP,
 };
@@ -5179,12 +5214,12 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	return page;
 }
 
-static int is_target_pte_for_mc(struct vm_area_struct *vma,
+static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		unsigned long addr, pte_t ptent, union mc_target *target)
 {
 	struct page *page = NULL;
 	struct page_cgroup *pc;
-	int ret = 0;
+	enum mc_target_type ret = MC_TARGET_NONE;
 	swp_entry_t ent = { .val = 0 };
 
 	if (pte_present(ptent))
@@ -5195,7 +5230,7 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
 		page = mc_handle_file_pte(vma, addr, ptent, &ent);
 
 	if (!page && !ent.val)
-		return 0;
+		return ret;
 	if (page) {
 		pc = lookup_page_cgroup(page);
 		/*
@@ -5221,6 +5256,41 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
 	return ret;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * We don't consider swapping or file mapped pages because THP does not
+ * support them for now.
+ * Caller should make sure that pmd_trans_huge(pmd) is true.
+ */
+static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	struct page *page = NULL;
+	struct page_cgroup *pc;
+	enum mc_target_type ret = MC_TARGET_NONE;
+
+	page = pmd_page(pmd);
+	VM_BUG_ON(!page || !PageHead(page));
+	if (!move_anon())
+		return ret;
+	pc = lookup_page_cgroup(page);
+	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+		ret = MC_TARGET_PAGE;
+		if (target) {
+			get_page(page);
+			target->page = page;
+		}
+	}
+	return ret;
+}
+#else
+static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	return MC_TARGET_NONE;
+}
+#endif
+
 static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 					unsigned long addr, unsigned long end,
 					struct mm_walk *walk)
@@ -5229,11 +5299,16 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
+			mc.precharge += HPAGE_PMD_NR;
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return 0;
+	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
-		if (is_target_pte_for_mc(vma, addr, *pte, NULL))
+		if (get_mctgt_type(vma, addr, *pte, NULL))
 			mc.precharge++;	/* increment precharge temporarily */
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
@@ -5388,23 +5463,55 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	struct vm_area_struct *vma = walk->private;
 	pte_t *pte;
 	spinlock_t *ptl;
+	enum mc_target_type target_type;
+	union mc_target target;
+	struct page *page;
+	struct page_cgroup *pc;
+
+	/*
+	 * We don't take compound_lock() here but no race with splitting thp
+	 * happens because:
+	 *  - if pmd_trans_huge_lock() returns 1, the relevant thp is not
+	 *    under splitting, which means there's no concurrent thp split,
+	 *  - if another thread runs into split_huge_page() just after we
+	 *    entered this if-block, the thread must wait for page table lock
+	 *    to be unlocked in __split_huge_page_splitting(), where the main
+	 *    part of thp split is not executed yet.
+	 */
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (!mc.precharge) {
+			spin_unlock(&vma->vm_mm->page_table_lock);
+			return 0;
+		}
+		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
+		if (target_type == MC_TARGET_PAGE) {
+			page = target.page;
+			if (!isolate_lru_page(page)) {
+				pc = lookup_page_cgroup(page);
+				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
+							     pc, mc.from, mc.to,
+							     false)) {
+					mc.precharge -= HPAGE_PMD_NR;
+					mc.moved_charge += HPAGE_PMD_NR;
+				}
+				putback_lru_page(page);
+			}
+			put_page(page);
+		}
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return 0;
+	}
 
-	split_huge_page_pmd(walk->mm, pmd);
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
 		pte_t ptent = *(pte++);
-		union mc_target target;
-		int type;
-		struct page *page;
-		struct page_cgroup *pc;
 		swp_entry_t ent;
 
 		if (!mc.precharge)
 			break;
 
-		type = is_target_pte_for_mc(vma, addr, ptent, &target);
-		switch (type) {
+		switch (get_mctgt_type(vma, addr, ptent, &target)) {
 		case MC_TARGET_PAGE:
 			page = target.page;
 			if (isolate_lru_page(page))
@@ -5417,7 +5524,7 @@ retry:
 				mc.moved_charge++;
 			}
 			putback_lru_page(page);
-put:			/* is_target_pte_for_mc() gets the page */
+put:			/* get_mctgt_type() gets the page */
 			put_page(page);
 			break;
 		case MC_TARGET_SWAP:

mm/memory-failure.c

@@ -1063,7 +1063,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	if (!PageHuge(p) && !PageTransCompound(p)) {
+	if (!PageHuge(p) && !PageTransTail(p)) {
 		if (!PageLRU(p))
 			shake_page(p, 0);
 		if (!PageLRU(p)) {

mm/memory.c

@@ -125,17 +125,17 @@ core_initcall(init_zero_pfn);
 
 #if defined(SPLIT_RSS_COUNTING)
 
-static void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm)
+void sync_mm_rss(struct mm_struct *mm)
 {
 	int i;
 
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
-		if (task->rss_stat.count[i]) {
-			add_mm_counter(mm, i, task->rss_stat.count[i]);
-			task->rss_stat.count[i] = 0;
+		if (current->rss_stat.count[i]) {
+			add_mm_counter(mm, i, current->rss_stat.count[i]);
+			current->rss_stat.count[i] = 0;
 		}
 	}
-	task->rss_stat.events = 0;
+	current->rss_stat.events = 0;
 }
 
 static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
@@ -157,30 +157,7 @@ static void check_sync_rss_stat(struct task_struct *task)
 	if (unlikely(task != current))
 		return;
 	if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
-		__sync_task_rss_stat(task, task->mm);
-}
-
-unsigned long get_mm_counter(struct mm_struct *mm, int member)
-{
-	long val = 0;
-
-	/*
-	 * Don't use task->mm here...for avoiding to use task_get_mm()..
-	 * The caller must guarantee task->mm is not invalid.
-	 */
-	val = atomic_long_read(&mm->rss_stat.count[member]);
-	/*
-	 * counter is updated in asynchronous manner and may go to minus.
-	 * But it's never be expected number for users.
-	 */
-	if (val < 0)
-		return 0;
-	return (unsigned long)val;
-}
-
-void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
-{
-	__sync_task_rss_stat(task, mm);
+		sync_mm_rss(task->mm);
 }
 #else /* SPLIT_RSS_COUNTING */
 
@@ -661,7 +638,7 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
 	int i;
 
 	if (current->mm == mm)
-		sync_mm_rss(current, mm);
+		sync_mm_rss(mm);
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		if (rss[i])
 			add_mm_counter(mm, i, rss[i]);
@@ -1247,16 +1224,24 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	do {
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
-			if (next-addr != HPAGE_PMD_SIZE) {
+			if (next - addr != HPAGE_PMD_SIZE) {
 				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
 				split_huge_page_pmd(vma->vm_mm, pmd);
 			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
-				continue;
+				goto next;
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
+		/*
+		 * Here there can be other concurrent MADV_DONTNEED or
+		 * trans huge page faults running, and if the pmd is
+		 * none or trans huge it can change under us. This is
+		 * because MADV_DONTNEED holds the mmap_sem in read
+		 * mode.
+		 */
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+			goto next;
 		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+next:
 		cond_resched();
 	} while (pmd++, addr = next, addr != end);
 

mm/mempolicy.c

@@ -512,7 +512,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	do {
 		next = pmd_addr_end(addr, end);
 		split_huge_page_pmd(vma->vm_mm, pmd);
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			continue;
 		if (check_pte_range(vma, pmd, addr, next, nodes,
 				    flags, private))
@@ -1323,12 +1323,9 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 		err = -ESRCH;
 		goto out;
 	}
-	mm = get_task_mm(task);
-	rcu_read_unlock();
+	get_task_struct(task);
 
 	err = -EINVAL;
-	if (!mm)
-		goto out;
 
 	/*
 	 * Check if this process has the right to modify the specified
@@ -1336,14 +1333,13 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	rcu_read_lock();
 	tcred = __task_cred(task);
 	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
 	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
 	    !capable(CAP_SYS_NICE)) {
 		rcu_read_unlock();
 		err = -EPERM;
-		goto out;
+		goto out_put;
 	}
 	rcu_read_unlock();
 
@@ -1351,26 +1347,36 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 	/* Is the user allowed to access the target nodes? */
 	if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) {
 		err = -EPERM;
-		goto out;
+		goto out_put;
 	}
 
 	if (!nodes_subset(*new, node_states[N_HIGH_MEMORY])) {
 		err = -EINVAL;
-		goto out;
+		goto out_put;
 	}
 
 	err = security_task_movememory(task);
 	if (err)
-		goto out;
+		goto out_put;
 
-	err = do_migrate_pages(mm, old, new,
-		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
-out:
+	mm = get_task_mm(task);
+	put_task_struct(task);
 	if (mm)
-		mmput(mm);
+		err = do_migrate_pages(mm, old, new,
+			capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
+	else
+		err = -EINVAL;
+
+	mmput(mm);
+out:
 	NODEMASK_SCRATCH_FREE(scratch);
 
 	return err;
+
+out_put:
+	put_task_struct(task);
+	goto out;
+
 }
 
 
@@ -1844,18 +1850,24 @@ struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, int node)
 {
-	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+	struct mempolicy *pol;
 	struct zonelist *zl;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+	pol = get_vma_policy(current, vma, addr);
+	cpuset_mems_cookie = get_mems_allowed();
 
-	get_mems_allowed();
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
+
 		return page;
 	}
 	zl = policy_zonelist(gfp, pol, node);
@@ -1866,7 +1878,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		struct page *page =  __alloc_pages_nodemask(gfp, order,
 						zl, policy_nodemask(gfp, pol));
 		__mpol_put(pol);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
 		return page;
 	}
 	/*
@@ -1874,7 +1887,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	 */
 	page = __alloc_pages_nodemask(gfp, order, zl,
 				      policy_nodemask(gfp, pol));
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
 }
 
@@ -1901,11 +1915,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/*
 	 * No reference counting needed for current->mempolicy
 	 * nor system default_policy
@@ -1916,7 +1933,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		page = __alloc_pages_nodemask(gfp, order,
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);

mm/migrate.c

@@ -1174,20 +1174,17 @@ set_status:
  * Migrate an array of page address onto an array of nodes and fill
  * the corresponding array of status.
  */
-static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
+static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			 unsigned long nr_pages,
 			 const void __user * __user *pages,
 			 const int __user *nodes,
 			 int __user *status, int flags)
 {
 	struct page_to_node *pm;
-	nodemask_t task_nodes;
 	unsigned long chunk_nr_pages;
 	unsigned long chunk_start;
 	int err;
 
-	task_nodes = cpuset_mems_allowed(task);
-
 	err = -ENOMEM;
 	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
 	if (!pm)
@@ -1349,6 +1346,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 	struct task_struct *task;
 	struct mm_struct *mm;
 	int err;
+	nodemask_t task_nodes;
 
 	/* Check flags */
 	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
@@ -1364,11 +1362,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 		rcu_read_unlock();
 		return -ESRCH;
 	}
-	mm = get_task_mm(task);
-	rcu_read_unlock();
-
-	if (!mm)
-		return -EINVAL;
+	get_task_struct(task);
 
 	/*
 	 * Check if this process has the right to modify the specified
@@ -1376,7 +1370,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	rcu_read_lock();
 	tcred = __task_cred(task);
 	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
 	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
@@ -1391,16 +1384,25 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
  	if (err)
 		goto out;
 
-	if (nodes) {
-		err = do_pages_move(mm, task, nr_pages, pages, nodes, status,
-				    flags);
-	} else {
-		err = do_pages_stat(mm, nr_pages, pages, status);
-	}
+	task_nodes = cpuset_mems_allowed(task);
+	mm = get_task_mm(task);
+	put_task_struct(task);
+
+	if (mm) {
+		if (nodes)
+			err = do_pages_move(mm, task_nodes, nr_pages, pages,
+					    nodes, status, flags);
+		else
+			err = do_pages_stat(mm, nr_pages, pages, status);
+	} else
+		err = -EINVAL;
 
-out:
 	mmput(mm);
 	return err;
+
+out:
+	put_task_struct(task);
+	return err;
 }
 
 /*

mm/mincore.c

@@ -164,7 +164,7 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 			}
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else
 			mincore_pte_range(vma, pmd, addr, next, vec);

mm/mmap.c

@@ -451,9 +451,8 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * Helper for vma_adjust in the split_vma insert case:
- * insert vm structure into list and rbtree and anon_vma,
- * but it has already been inserted into prio_tree earlier.
+ * Helper for vma_adjust() in the split_vma insert case: insert a vma into the
+ * mm's list and rbtree.  It has already been inserted into the prio_tree.
  */
 static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 {
@@ -1112,9 +1111,9 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		 * A dummy user value is used because we are not locking
 		 * memory so no accounting is necessary
 		 */
-		len = ALIGN(len, huge_page_size(&default_hstate));
-		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
-						&user, HUGETLB_ANONHUGE_INODE);
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
+						VM_NORESERVE, &user,
+						HUGETLB_ANONHUGE_INODE);
 		if (IS_ERR(file))
 			return PTR_ERR(file);
 	}
@@ -1439,10 +1438,8 @@ void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
 	/*
 	 * Is this a new hole at the lowest possible address?
 	 */
-	if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) {
+	if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache)
 		mm->free_area_cache = addr;
-		mm->cached_hole_size = ~0UL;
-	}
 }
 
 /*
@@ -1457,7 +1454,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0;
+	unsigned long addr = addr0, start_addr;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
@@ -1481,22 +1478,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
  		mm->free_area_cache = mm->mmap_base;
  	}
 
+try_again:
 	/* either no address requested or can't fit in requested address hole */
-	addr = mm->free_area_cache;
-
-	/* make sure it can fit in the remaining address space */
-	if (addr > len) {
-		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start)
-			/* remember the address as a hint for next time */
-			return (mm->free_area_cache = addr-len);
-	}
-
-	if (mm->mmap_base < len)
-		goto bottomup;
+	start_addr = addr = mm->free_area_cache;
 
-	addr = mm->mmap_base-len;
+	if (addr < len)
+		goto fail;
 
+	addr -= len;
 	do {
 		/*
 		 * Lookup failure means no vma is above this address,
@@ -1516,7 +1505,21 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = vma->vm_start-len;
 	} while (len < vma->vm_start);
 
-bottomup:
+fail:
+	/*
+	 * if hint left us with no space for the requested
+	 * mapping then try again:
+	 *
+	 * Note: this is different with the case of bottomup
+	 * which does the fully line-search, but we use find_vma
+	 * here that causes some holes skipped.
+	 */
+	if (start_addr != mm->mmap_base) {
+		mm->free_area_cache = mm->mmap_base;
+		mm->cached_hole_size = 0;
+		goto try_again;
+	}
+
 	/*
 	 * A failed mmap() very likely causes application failure,
 	 * so fall back to the bottom-up function here. This scenario

mm/mmu_context.c

@@ -53,7 +53,7 @@ void unuse_mm(struct mm_struct *mm)
 	struct task_struct *tsk = current;
 
 	task_lock(tsk);
-	sync_mm_rss(tsk, mm);
+	sync_mm_rss(mm);
 	tsk->mm = NULL;
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);

mm/mprotect.c

@@ -60,7 +60,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 
 			ptep_modify_prot_commit(mm, addr, pte, ptent);
-		} else if (PAGE_MIGRATION && !pte_file(oldpte)) {
+		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
 			if (is_write_migration_entry(entry)) {

mm/oom_kill.c

@@ -34,6 +34,7 @@
 #include <linux/ptrace.h>
 #include <linux/freezer.h>
 #include <linux/ftrace.h>
+#include <linux/ratelimit.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -309,7 +310,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
  */
 static struct task_struct *select_bad_process(unsigned int *ppoints,
 		unsigned long totalpages, struct mem_cgroup *memcg,
-		const nodemask_t *nodemask)
+		const nodemask_t *nodemask, bool force_kill)
 {
 	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
@@ -335,7 +336,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
 			if (unlikely(frozen(p)))
 				__thaw_task(p);
-			return ERR_PTR(-1UL);
+			if (!force_kill)
+				return ERR_PTR(-1UL);
 		}
 		if (!p->mm)
 			continue;
@@ -353,7 +355,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			if (p == current) {
 				chosen = p;
 				*ppoints = 1000;
-			} else {
+			} else if (!force_kill) {
 				/*
 				 * If this task is not being ptraced on exit,
 				 * then wait for it to finish before killing
@@ -434,66 +436,18 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
-static int oom_kill_task(struct task_struct *p)
-{
-	struct task_struct *q;
-	struct mm_struct *mm;
-
-	p = find_lock_task_mm(p);
-	if (!p)
-		return 1;
-
-	/* mm cannot be safely dereferenced after task_unlock(p) */
-	mm = p->mm;
-
-	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
-		task_pid_nr(p), p->comm, K(p->mm->total_vm),
-		K(get_mm_counter(p->mm, MM_ANONPAGES)),
-		K(get_mm_counter(p->mm, MM_FILEPAGES)));
-	task_unlock(p);
-
-	/*
-	 * Kill all user processes sharing p->mm in other thread groups, if any.
-	 * They don't get access to memory reserves or a higher scheduler
-	 * priority, though, to avoid depletion of all memory or task
-	 * starvation.  This prevents mm->mmap_sem livelock when an oom killed
-	 * task cannot exit because it requires the semaphore and its contended
-	 * by another thread trying to allocate memory itself.  That thread will
-	 * now get access to memory reserves since it has a pending fatal
-	 * signal.
-	 */
-	for_each_process(q)
-		if (q->mm == mm && !same_thread_group(q, p) &&
-		    !(q->flags & PF_KTHREAD)) {
-			if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
-				continue;
-
-			task_lock(q);	/* Protect ->comm from prctl() */
-			pr_err("Kill process %d (%s) sharing same memory\n",
-				task_pid_nr(q), q->comm);
-			task_unlock(q);
-			force_sig(SIGKILL, q);
-		}
-
-	set_tsk_thread_flag(p, TIF_MEMDIE);
-	force_sig(SIGKILL, p);
-
-	return 0;
-}
-#undef K
-
-static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-			    unsigned int points, unsigned long totalpages,
-			    struct mem_cgroup *memcg, nodemask_t *nodemask,
-			    const char *message)
+static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+			     unsigned int points, unsigned long totalpages,
+			     struct mem_cgroup *memcg, nodemask_t *nodemask,
+			     const char *message)
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
 	struct task_struct *t = p;
+	struct mm_struct *mm;
 	unsigned int victim_points = 0;
-
-	if (printk_ratelimit())
-		dump_header(p, gfp_mask, order, memcg, nodemask);
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -501,9 +455,12 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 */
 	if (p->flags & PF_EXITING) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
-		return 0;
+		return;
 	}
 
+	if (__ratelimit(&oom_rs))
+		dump_header(p, gfp_mask, order, memcg, nodemask);
+
 	task_lock(p);
 	pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n",
 		message, task_pid_nr(p), p->comm, points);
@@ -533,8 +490,44 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 		}
 	} while_each_thread(p, t);
 
-	return oom_kill_task(victim);
+	victim = find_lock_task_mm(victim);
+	if (!victim)
+		return;
+
+	/* mm cannot safely be dereferenced after task_unlock(victim) */
+	mm = victim->mm;
+	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
+		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
+		K(get_mm_counter(victim->mm, MM_ANONPAGES)),
+		K(get_mm_counter(victim->mm, MM_FILEPAGES)));
+	task_unlock(victim);
+
+	/*
+	 * Kill all user processes sharing victim->mm in other thread groups, if
+	 * any.  They don't get access to memory reserves, though, to avoid
+	 * depletion of all memory.  This prevents mm->mmap_sem livelock when an
+	 * oom killed thread cannot exit because it requires the semaphore and
+	 * its contended by another thread trying to allocate memory itself.
+	 * That thread will now get access to memory reserves since it has a
+	 * pending fatal signal.
+	 */
+	for_each_process(p)
+		if (p->mm == mm && !same_thread_group(p, victim) &&
+		    !(p->flags & PF_KTHREAD)) {
+			if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+				continue;
+
+			task_lock(p);	/* Protect ->comm from prctl() */
+			pr_err("Kill process %d (%s) sharing same memory\n",
+				task_pid_nr(p), p->comm);
+			task_unlock(p);
+			force_sig(SIGKILL, p);
+		}
+
+	set_tsk_thread_flag(victim, TIF_MEMDIE);
+	force_sig(SIGKILL, victim);
 }
+#undef K
 
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
@@ -561,7 +554,8 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 }
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask)
+void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+			      int order)
 {
 	unsigned long limit;
 	unsigned int points = 0;
@@ -577,18 +571,13 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask)
 		return;
 	}
 
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
+	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
 	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT;
 	read_lock(&tasklist_lock);
-retry:
-	p = select_bad_process(&points, limit, memcg, NULL);
-	if (!p || PTR_ERR(p) == -1UL)
-		goto out;
-
-	if (oom_kill_process(p, gfp_mask, 0, points, limit, memcg, NULL,
-				"Memory cgroup out of memory"))
-		goto retry;
-out:
+	p = select_bad_process(&points, limit, memcg, NULL, false);
+	if (p && PTR_ERR(p) != -1UL)
+		oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL,
+				 "Memory cgroup out of memory");
 	read_unlock(&tasklist_lock);
 }
 #endif
@@ -700,6 +689,7 @@ static void clear_system_oom(void)
  * @gfp_mask: memory allocation flags
  * @order: amount of memory being requested as a power of 2
  * @nodemask: nodemask passed to page allocator
+ * @force_kill: true if a task must be killed, even if others are exiting
  *
  * If we run out of memory, we have the choice between either
  * killing a random task (bad), letting the system crash (worse)
@@ -707,7 +697,7 @@ static void clear_system_oom(void)
  * don't have to be perfect here, we just have to be good.
  */
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *nodemask)
+		int order, nodemask_t *nodemask, bool force_kill)
 {
 	const nodemask_t *mpol_mask;
 	struct task_struct *p;
@@ -745,33 +735,25 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	if (sysctl_oom_kill_allocating_task &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
 	    current->mm) {
-		/*
-		 * oom_kill_process() needs tasklist_lock held.  If it returns
-		 * non-zero, current could not be killed so we must fallback to
-		 * the tasklist scan.
-		 */
-		if (!oom_kill_process(current, gfp_mask, order, 0, totalpages,
-				NULL, nodemask,
-				"Out of memory (oom_kill_allocating_task)"))
-			goto out;
-	}
-
-retry:
-	p = select_bad_process(&points, totalpages, NULL, mpol_mask);
-	if (PTR_ERR(p) == -1UL)
+		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
+				 nodemask,
+				 "Out of memory (oom_kill_allocating_task)");
 		goto out;
+	}
 
+	p = select_bad_process(&points, totalpages, NULL, mpol_mask,
+			       force_kill);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
 		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
-
-	if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
-				nodemask, "Out of memory"))
-		goto retry;
-	killed = 1;
+	if (PTR_ERR(p) != -1UL) {
+		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
+				 nodemask, "Out of memory");
+		killed = 1;
+	}
 out:
 	read_unlock(&tasklist_lock);
 
@@ -792,7 +774,7 @@ out:
 void pagefault_out_of_memory(void)
 {
 	if (try_set_system_oom()) {
-		out_of_memory(NULL, 0, 0, NULL);
+		out_of_memory(NULL, 0, 0, NULL, false);
 		clear_system_oom();
 	}
 	if (!test_thread_flag(TIF_MEMDIE))

mm/page-writeback.c

@@ -1472,6 +1472,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
 
         for ( ; ; ) {
 		global_dirty_limits(&background_thresh, &dirty_thresh);
+		dirty_thresh = hard_dirty_limit(dirty_thresh);
 
                 /*
                  * Boost the allowable dirty threshold a bit for page

mm/page_alloc.c

@@ -1968,7 +1968,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	out_of_memory(zonelist, gfp_mask, order, nodemask);
+	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
 
 out:
 	clear_zonelist_oom(zonelist, gfp_mask);
@@ -1990,7 +1990,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	if (!order)
 		return NULL;
 
-	if (compaction_deferred(preferred_zone)) {
+	if (compaction_deferred(preferred_zone, order)) {
 		*deferred_compaction = true;
 		return NULL;
 	}
@@ -2012,6 +2012,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		if (page) {
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
+			if (order >= preferred_zone->compact_order_failed)
+				preferred_zone->compact_order_failed = order + 1;
 			count_vm_event(COMPACTSUCCESS);
 			return page;
 		}
@@ -2028,7 +2030,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * defer if the failure was a sync compaction failure.
 		 */
 		if (sync_migration)
-			defer_compaction(preferred_zone);
+			defer_compaction(preferred_zone, order);
 
 		cond_resched();
 	}
@@ -2378,8 +2380,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
-	struct page *page;
+	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
+	unsigned int cpuset_mems_cookie;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2398,15 +2401,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
-	if (!preferred_zone) {
-		put_mems_allowed();
-		return NULL;
-	}
+	if (!preferred_zone)
+		goto out;
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2416,9 +2419,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+	/*
+	 * When updating a task's mems_allowed, it is possible to race with
+	 * parallel threads in such a way that an allocation can fail while
+	 * the mask is being updated. If a page allocation is about to fail,
+	 * check if the cpuset changed during allocation and if so, retry.
+	 */
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2632,13 +2645,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
+	unsigned int cpuset_mems_cookie;
 
 	if (!(flags & SHOW_MEM_FILTER_NODES))
 		goto out;
 
-	get_mems_allowed();
-	ret = !node_isset(nid, cpuset_current_mems_allowed);
-	put_mems_allowed();
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		ret = !node_isset(nid, cpuset_current_mems_allowed);
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -3925,18 +3940,6 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
 	}
 }
 
-int __init add_from_early_node_map(struct range *range, int az,
-				   int nr_range, int nid)
-{
-	unsigned long start_pfn, end_pfn;
-	int i;
-
-	/* need to go over early_node_map to find out good range for node */
-	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL)
-		nr_range = add_range(range, az, nr_range, start_pfn, end_pfn);
-	return nr_range;
-}
-
 /**
  * sparse_memory_present_with_active_regions - Call memory_present for each active range
  * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
@@ -4521,7 +4524,7 @@ static unsigned long __init early_calculate_totalpages(void)
  * memory. When they don't, some nodes will have more kernelcore than
  * others
  */
-static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+static void __init find_zone_movable_pfns_for_nodes(void)
 {
 	int i, nid;
 	unsigned long usable_startpfn;
@@ -4713,7 +4716,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
 	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
-	find_zone_movable_pfns_for_nodes(zone_movable_pfn);
+	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
 	printk("Zone PFN ranges:\n");
@@ -4823,6 +4826,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 	int cpu = (unsigned long)hcpu;
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		lru_add_drain_cpu(cpu);
 		drain_pages(cpu);
 
 		/*

mm/pagewalk.c

@@ -59,7 +59,7 @@ again:
 			continue;
 
 		split_huge_page_pmd(walk->mm, pmd);
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			goto again;
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)

mm/pgtable-generic.c

@@ -70,10 +70,11 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 			   unsigned long address, pmd_t *pmdp)
 {
 	int young;
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+#else
 	BUG();
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	young = pmdp_test_and_clear_young(vma, address, pmdp);
 	if (young)
 		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);

mm/rmap.c

@@ -120,6 +120,21 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
 	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
 }
 
+static void anon_vma_chain_link(struct vm_area_struct *vma,
+				struct anon_vma_chain *avc,
+				struct anon_vma *anon_vma)
+{
+	avc->vma = vma;
+	avc->anon_vma = anon_vma;
+	list_add(&avc->same_vma, &vma->anon_vma_chain);
+
+	/*
+	 * It's critical to add new vmas to the tail of the anon_vma,
+	 * see comment in huge_memory.c:__split_huge_page().
+	 */
+	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+}
+
 /**
  * anon_vma_prepare - attach an anon_vma to a memory region
  * @vma: the memory region in question
@@ -175,10 +190,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 		spin_lock(&mm->page_table_lock);
 		if (likely(!vma->anon_vma)) {
 			vma->anon_vma = anon_vma;
-			avc->anon_vma = anon_vma;
-			avc->vma = vma;
-			list_add(&avc->same_vma, &vma->anon_vma_chain);
-			list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+			anon_vma_chain_link(vma, avc, anon_vma);
 			allocated = NULL;
 			avc = NULL;
 		}
@@ -224,21 +236,6 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
 		mutex_unlock(&root->mutex);
 }
 
-static void anon_vma_chain_link(struct vm_area_struct *vma,
-				struct anon_vma_chain *avc,
-				struct anon_vma *anon_vma)
-{
-	avc->vma = vma;
-	avc->anon_vma = anon_vma;
-	list_add(&avc->same_vma, &vma->anon_vma_chain);
-
-	/*
-	 * It's critical to add new vmas to the tail of the anon_vma,
-	 * see comment in huge_memory.c:__split_huge_page().
-	 */
-	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
-}
-
 /*
  * Attach the anon_vmas from src to dst.
  * Returns 0 on success, -ENOMEM on failure.
@@ -1151,10 +1148,15 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
+	bool locked;
+	unsigned long flags;
+
+	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_end_update_page_stat(page, &locked, &flags);
 }
 
 /**
@@ -1165,9 +1167,21 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
+	bool anon = PageAnon(page);
+	bool locked;
+	unsigned long flags;
+
+	/*
+	 * The anon case has no mem_cgroup page_stat to update; but may
+	 * uncharge_page() below, where the lock ordering can deadlock if
+	 * we hold the lock against page_stat move: so avoid it on anon.
+	 */
+	if (!anon)
+		mem_cgroup_begin_update_page_stat(page, &locked, &flags);
+
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
-		return;
+		goto out;
 
 	/*
 	 * Now that the last pte has gone, s390 must transfer dirty
@@ -1176,7 +1190,7 @@ void page_remove_rmap(struct page *page)
 	 * not if it's in swapcache - there might be another pte slot
 	 * containing the swap entry, but page not yet written to swap.
 	 */
-	if ((!PageAnon(page) || PageSwapCache(page)) &&
+	if ((!anon || PageSwapCache(page)) &&
 	    page_test_and_clear_dirty(page_to_pfn(page), 1))
 		set_page_dirty(page);
 	/*
@@ -1184,8 +1198,8 @@ void page_remove_rmap(struct page *page)
 	 * and not charged by memcg for now.
 	 */
 	if (unlikely(PageHuge(page)))
-		return;
-	if (PageAnon(page)) {
+		goto out;
+	if (anon) {
 		mem_cgroup_uncharge_page(page);
 		if (!PageTransHuge(page))
 			__dec_zone_page_state(page, NR_ANON_PAGES);
@@ -1205,6 +1219,9 @@ void page_remove_rmap(struct page *page)
 	 * Leaving it set also helps swapoff to reinstate ptes
 	 * faster for those pages still in swapcache.
 	 */
+out:
+	if (!anon)
+		mem_cgroup_end_update_page_stat(page, &locked, &flags);
 }
 
 /*
@@ -1282,7 +1299,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			}
 			dec_mm_counter(mm, MM_ANONPAGES);
 			inc_mm_counter(mm, MM_SWAPENTS);
-		} else if (PAGE_MIGRATION) {
+		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			/*
 			 * Store the pfn of the page in a special migration
 			 * pte. do_swap_page() will wait until the migration
@@ -1293,7 +1310,8 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
 		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 		BUG_ON(pte_file(*pte));
-	} else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
+	} else if (IS_ENABLED(CONFIG_MIGRATION) &&
+		   (TTU_ACTION(flags) == TTU_MIGRATION)) {
 		/* Establish migration entry for a file page */
 		swp_entry_t entry;
 		entry = make_migration_entry(page, pte_write(pteval));
@@ -1499,7 +1517,7 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 		 * locking requirements of exec(), migration skips
 		 * temporary VMAs until after exec() completes.
 		 */
-		if (PAGE_MIGRATION && (flags & TTU_MIGRATION) &&
+		if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
 				is_vma_temporary_stack(vma))
 			continue;
 

mm/shmem.c

@@ -1178,6 +1178,12 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
 
+#ifdef CONFIG_TMPFS_XATTR
+static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
+#else
+#define shmem_initxattrs NULL
+#endif
+
 static int
 shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
@@ -1490,7 +1496,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 	if (inode) {
 		error = security_inode_init_security(inode, dir,
 						     &dentry->d_name,
-						     NULL, NULL);
+						     shmem_initxattrs, NULL);
 		if (error) {
 			if (error != -EOPNOTSUPP) {
 				iput(inode);
@@ -1630,7 +1636,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 		return -ENOSPC;
 
 	error = security_inode_init_security(inode, dir, &dentry->d_name,
-					     NULL, NULL);
+					     shmem_initxattrs, NULL);
 	if (error) {
 		if (error != -EOPNOTSUPP) {
 			iput(inode);
@@ -1704,6 +1710,66 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co
  * filesystem level, though.
  */
 
+/*
+ * Allocate new xattr and copy in the value; but leave the name to callers.
+ */
+static struct shmem_xattr *shmem_xattr_alloc(const void *value, size_t size)
+{
+	struct shmem_xattr *new_xattr;
+	size_t len;
+
+	/* wrap around? */
+	len = sizeof(*new_xattr) + size;
+	if (len <= sizeof(*new_xattr))
+		return NULL;
+
+	new_xattr = kmalloc(len, GFP_KERNEL);
+	if (!new_xattr)
+		return NULL;
+
+	new_xattr->size = size;
+	memcpy(new_xattr->value, value, size);
+	return new_xattr;
+}
+
+/*
+ * Callback for security_inode_init_security() for acquiring xattrs.
+ */
+static int shmem_initxattrs(struct inode *inode,
+			    const struct xattr *xattr_array,
+			    void *fs_info)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	const struct xattr *xattr;
+	struct shmem_xattr *new_xattr;
+	size_t len;
+
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		new_xattr = shmem_xattr_alloc(xattr->value, xattr->value_len);
+		if (!new_xattr)
+			return -ENOMEM;
+
+		len = strlen(xattr->name) + 1;
+		new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len,
+					  GFP_KERNEL);
+		if (!new_xattr->name) {
+			kfree(new_xattr);
+			return -ENOMEM;
+		}
+
+		memcpy(new_xattr->name, XATTR_SECURITY_PREFIX,
+		       XATTR_SECURITY_PREFIX_LEN);
+		memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN,
+		       xattr->name, len);
+
+		spin_lock(&info->lock);
+		list_add(&new_xattr->list, &info->xattr_list);
+		spin_unlock(&info->lock);
+	}
+
+	return 0;
+}
+
 static int shmem_xattr_get(struct dentry *dentry, const char *name,
 			   void *buffer, size_t size)
 {
@@ -1731,24 +1797,17 @@ static int shmem_xattr_get(struct dentry *dentry, const char *name,
 	return ret;
 }
 
-static int shmem_xattr_set(struct dentry *dentry, const char *name,
+static int shmem_xattr_set(struct inode *inode, const char *name,
 			   const void *value, size_t size, int flags)
 {
-	struct inode *inode = dentry->d_inode;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_xattr *xattr;
 	struct shmem_xattr *new_xattr = NULL;
-	size_t len;
 	int err = 0;
 
 	/* value == NULL means remove */
 	if (value) {
-		/* wrap around? */
-		len = sizeof(*new_xattr) + size;
-		if (len <= sizeof(*new_xattr))
-			return -ENOMEM;
-
-		new_xattr = kmalloc(len, GFP_KERNEL);
+		new_xattr = shmem_xattr_alloc(value, size);
 		if (!new_xattr)
 			return -ENOMEM;
 
@@ -1757,9 +1816,6 @@ static int shmem_xattr_set(struct dentry *dentry, const char *name,
 			kfree(new_xattr);
 			return -ENOMEM;
 		}
-
-		new_xattr->size = size;
-		memcpy(new_xattr->value, value, size);
 	}
 
 	spin_lock(&info->lock);
@@ -1858,7 +1914,7 @@ static int shmem_setxattr(struct dentry *dentry, const char *name,
 	if (size == 0)
 		value = "";  /* empty EA, do not remove */
 
-	return shmem_xattr_set(dentry, name, value, size, flags);
+	return shmem_xattr_set(dentry->d_inode, name, value, size, flags);
 
 }
 
@@ -1878,7 +1934,7 @@ static int shmem_removexattr(struct dentry *dentry, const char *name)
 	if (err)
 		return err;
 
-	return shmem_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE);
+	return shmem_xattr_set(dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
 }
 
 static bool xattr_is_trusted(const char *name)

mm/slab.c

@@ -3284,12 +3284,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_mem_id();
-	get_mems_allowed();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
-	put_mems_allowed();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3312,14 +3310,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
+	unsigned int cpuset_mems_cookie;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+
 retry:
 	/*
 	 * Look through allowed nodes for objects available
@@ -3372,7 +3373,9 @@ retry:
 			}
 		}
 	}
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+		goto retry_cpuset;
 	return obj;
 }
 

mm/slub.c

@@ -1581,6 +1581,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags,
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *object;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between
@@ -1604,23 +1605,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags,
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		struct kmem_cache_node *n;
-
-		n = get_node(s, zone_to_nid(zone));
-
-		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-				n->nr_partial > s->min_partial) {
-			object = get_partial_node(s, n, c);
-			if (object) {
-				put_mems_allowed();
-				return object;
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+			struct kmem_cache_node *n;
+
+			n = get_node(s, zone_to_nid(zone));
+
+			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+					n->nr_partial > s->min_partial) {
+				object = get_partial_node(s, n, c);
+				if (object) {
+					/*
+					 * Return the object even if
+					 * put_mems_allowed indicated that
+					 * the cpuset mems_allowed was
+					 * updated in parallel. It's a
+					 * harmless race between the alloc
+					 * and the cpuset update.
+					 */
+					put_mems_allowed(cpuset_mems_cookie);
+					return object;
+				}
 			}
 		}
-	}
-	put_mems_allowed();
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 #endif
 	return NULL;
 }

mm/sparse.c

@@ -353,29 +353,21 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
 
 	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
 								 usemap_count);
-	if (usemap) {
-		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
-			if (!present_section_nr(pnum))
-				continue;
-			usemap_map[pnum] = usemap;
-			usemap += size;
+	if (!usemap) {
+		usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
+		if (!usemap) {
+			printk(KERN_WARNING "%s: allocation failed\n", __func__);
+			return;
 		}
-		return;
 	}
 
-	usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
-	if (usemap) {
-		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
-			if (!present_section_nr(pnum))
-				continue;
-			usemap_map[pnum] = usemap;
-			usemap += size;
-			check_usemap_section_nr(nodeid, usemap_map[pnum]);
-		}
-		return;
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		if (!present_section_nr(pnum))
+			continue;
+		usemap_map[pnum] = usemap;
+		usemap += size;
+		check_usemap_section_nr(nodeid, usemap_map[pnum]);
 	}
-
-	printk(KERN_WARNING "%s: allocation failed\n", __func__);
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP

mm/swap.c

@@ -496,7 +496,7 @@ static void lru_deactivate_fn(struct page *page, void *arg)
  * Either "cpu" is the current CPU, and preemption has already been
  * disabled; or "cpu" is being hot-unplugged, and is already dead.
  */
-static void drain_cpu_pagevecs(int cpu)
+void lru_add_drain_cpu(int cpu)
 {
 	struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
 	struct pagevec *pvec;
@@ -553,7 +553,7 @@ void deactivate_page(struct page *page)
 
 void lru_add_drain(void)
 {
-	drain_cpu_pagevecs(get_cpu());
+	lru_add_drain_cpu(get_cpu());
 	put_cpu();
 }
 

mm/swap_state.c

@@ -372,25 +372,23 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	int nr_pages;
 	struct page *page;
-	unsigned long offset;
-	unsigned long end_offset;
+	unsigned long offset = swp_offset(entry);
+	unsigned long start_offset, end_offset;
+	unsigned long mask = (1UL << page_cluster) - 1;
 
-	/*
-	 * Get starting offset for readaround, and number of pages to read.
-	 * Adjust starting address by readbehind (for NUMA interleave case)?
-	 * No, it's very unlikely that swap layout would follow vma layout,
-	 * more likely that neighbouring swap pages came from the same node:
-	 * so use the same "addr" to choose the same node for each swap read.
-	 */
-	nr_pages = valid_swaphandles(entry, &offset);
-	for (end_offset = offset + nr_pages; offset < end_offset; offset++) {
+	/* Read a page_cluster sized and aligned cluster around offset. */
+	start_offset = offset & ~mask;
+	end_offset = offset | mask;
+	if (!start_offset)	/* First page is swap header. */
+		start_offset++;
+
+	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
 						gfp_mask, vma, addr);
 		if (!page)
-			break;
+			continue;
 		page_cache_release(page);
 	}
 	lru_add_drain();	/* Push any new pages onto the LRU now */

mm/swapfile.c

@@ -932,9 +932,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (unlikely(pmd_trans_huge(*pmd)))
-			continue;
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
 		if (ret)
@@ -2107,7 +2105,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			p->flags |= SWP_SOLIDSTATE;
 			p->cluster_next = 1 + (random32() % p->highest_bit);
 		}
-		if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD))
+		if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0)
 			p->flags |= SWP_DISCARDABLE;
 	}
 
@@ -2291,58 +2289,6 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
-/*
- * swap_lock prevents swap_map being freed. Don't grab an extra
- * reference on the swaphandle, it doesn't matter if it becomes unused.
- */
-int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
-{
-	struct swap_info_struct *si;
-	int our_page_cluster = page_cluster;
-	pgoff_t target, toff;
-	pgoff_t base, end;
-	int nr_pages = 0;
-
-	if (!our_page_cluster)	/* no readahead */
-		return 0;
-
-	si = swap_info[swp_type(entry)];
-	target = swp_offset(entry);
-	base = (target >> our_page_cluster) << our_page_cluster;
-	end = base + (1 << our_page_cluster);
-	if (!base)		/* first page is swap header */
-		base++;
-
-	spin_lock(&swap_lock);
-	if (end > si->max)	/* don't go beyond end of map */
-		end = si->max;
-
-	/* Count contiguous allocated slots above our target */
-	for (toff = target; ++toff < end; nr_pages++) {
-		/* Don't read in free or bad pages */
-		if (!si->swap_map[toff])
-			break;
-		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
-			break;
-	}
-	/* Count contiguous allocated slots below our target */
-	for (toff = target; --toff >= base; nr_pages++) {
-		/* Don't read in free or bad pages */
-		if (!si->swap_map[toff])
-			break;
-		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
-			break;
-	}
-	spin_unlock(&swap_lock);
-
-	/*
-	 * Indicate starting offset, and return number of pages to get:
-	 * if only 1, say 0, since there's then no readahead to be done.
-	 */
-	*offset = ++toff;
-	return nr_pages? ++nr_pages: 0;
-}
-
 /*
  * add_swap_count_continuation - called when a swap count is duplicated
  * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's

mm/util.c

@@ -239,6 +239,47 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		next->vm_prev = vma;
 }
 
+/* Check if the vma is being used as a stack by this task */
+static int vm_is_stack_for_task(struct task_struct *t,
+				struct vm_area_struct *vma)
+{
+	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
+}
+
+/*
+ * Check if the vma is being used as a stack.
+ * If is_group is non-zero, check in the entire thread group or else
+ * just check in the current task. Returns the pid of the task that
+ * the vma is stack for.
+ */
+pid_t vm_is_stack(struct task_struct *task,
+		  struct vm_area_struct *vma, int in_group)
+{
+	pid_t ret = 0;
+
+	if (vm_is_stack_for_task(task, vma))
+		return task->pid;
+
+	if (in_group) {
+		struct task_struct *t;
+		rcu_read_lock();
+		if (!pid_alive(task))
+			goto done;
+
+		t = task;
+		do {
+			if (vm_is_stack_for_task(t, vma)) {
+				ret = t->pid;
+				goto done;
+			}
+		} while_each_thread(task, t);
+done:
+		rcu_read_unlock();
+	}
+
+	return ret;
+}
+
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {

mm/vmscan.c

@@ -1138,7 +1138,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
  * @mz:		The mem_cgroup_zone to pull pages from.
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
- * @order:	The caller's attempted allocation order
+ * @sc:		The scan_control struct for this reclaim session
  * @mode:	One of the LRU isolation modes
  * @active:	True [1] if isolating active pages
  * @file:	True [1] if isolating file [!anon] pages
@@ -1147,8 +1147,8 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct mem_cgroup_zone *mz, struct list_head *dst,
-		unsigned long *nr_scanned, int order, isolate_mode_t mode,
-		int active, int file)
+		unsigned long *nr_scanned, struct scan_control *sc,
+		isolate_mode_t mode, int active, int file)
 {
 	struct lruvec *lruvec;
 	struct list_head *src;
@@ -1194,7 +1194,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			BUG();
 		}
 
-		if (!order)
+		if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM))
 			continue;
 
 		/*
@@ -1208,8 +1208,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 */
 		zone_id = page_zone_id(page);
 		page_pfn = page_to_pfn(page);
-		pfn = page_pfn & ~((1 << order) - 1);
-		end_pfn = pfn + (1 << order);
+		pfn = page_pfn & ~((1 << sc->order) - 1);
+		end_pfn = pfn + (1 << sc->order);
 		for (; pfn < end_pfn; pfn++) {
 			struct page *cursor_page;
 
@@ -1275,7 +1275,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 	*nr_scanned = scan;
 
-	trace_mm_vmscan_lru_isolate(order,
+	trace_mm_vmscan_lru_isolate(sc->order,
 			nr_to_scan, scan,
 			nr_taken,
 			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
@@ -1413,7 +1413,6 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 		       unsigned long *nr_anon,
 		       unsigned long *nr_file)
 {
-	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 	struct zone *zone = mz->zone;
 	unsigned int count[NR_LRU_LISTS] = { 0, };
 	unsigned long nr_active = 0;
@@ -1434,6 +1433,7 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 		count[lru] += numpages;
 	}
 
+	preempt_disable();
 	__count_vm_events(PGDEACTIVATE, nr_active);
 
 	__mod_zone_page_state(zone, NR_ACTIVE_FILE,
@@ -1448,8 +1448,9 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 	*nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
 	*nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
 
-	reclaim_stat->recent_scanned[0] += *nr_anon;
-	reclaim_stat->recent_scanned[1] += *nr_file;
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file);
+	preempt_enable();
 }
 
 /*
@@ -1509,8 +1510,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	unsigned long nr_file;
 	unsigned long nr_dirty = 0;
 	unsigned long nr_writeback = 0;
-	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
+	isolate_mode_t isolate_mode = ISOLATE_INACTIVE;
 	struct zone *zone = mz->zone;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1522,20 +1524,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 
 	set_reclaim_mode(priority, sc, false);
 	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		reclaim_mode |= ISOLATE_ACTIVE;
+		isolate_mode |= ISOLATE_ACTIVE;
 
 	lru_add_drain();
 
 	if (!sc->may_unmap)
-		reclaim_mode |= ISOLATE_UNMAPPED;
+		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
-		reclaim_mode |= ISOLATE_CLEAN;
+		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&zone->lru_lock);
 
-	nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list,
-				     &nr_scanned, sc->order,
-				     reclaim_mode, 0, file);
+	nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list, &nr_scanned,
+				     sc, isolate_mode, 0, file);
 	if (global_reclaim(sc)) {
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
@@ -1545,19 +1546,13 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 			__count_zone_vm_events(PGSCAN_DIRECT, zone,
 					       nr_scanned);
 	}
+	spin_unlock_irq(&zone->lru_lock);
 
-	if (nr_taken == 0) {
-		spin_unlock_irq(&zone->lru_lock);
+	if (nr_taken == 0)
 		return 0;
-	}
 
 	update_isolated_counts(mz, &page_list, &nr_anon, &nr_file);
 
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
-
-	spin_unlock_irq(&zone->lru_lock);
-
 	nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
 						&nr_dirty, &nr_writeback);
 
@@ -1570,6 +1565,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 
 	spin_lock_irq(&zone->lru_lock);
 
+	reclaim_stat->recent_scanned[0] += nr_anon;
+	reclaim_stat->recent_scanned[1] += nr_file;
+
 	if (current_is_kswapd())
 		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
 	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
@@ -1643,18 +1641,6 @@ static void move_active_pages_to_lru(struct zone *zone,
 	unsigned long pgmoved = 0;
 	struct page *page;
 
-	if (buffer_heads_over_limit) {
-		spin_unlock_irq(&zone->lru_lock);
-		list_for_each_entry(page, list, lru) {
-			if (page_has_private(page) && trylock_page(page)) {
-				if (page_has_private(page))
-					try_to_release_page(page, 0);
-				unlock_page(page);
-			}
-		}
-		spin_lock_irq(&zone->lru_lock);
-	}
-
 	while (!list_empty(list)) {
 		struct lruvec *lruvec;
 
@@ -1699,21 +1685,22 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz);
 	unsigned long nr_rotated = 0;
-	isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
+	isolate_mode_t isolate_mode = ISOLATE_ACTIVE;
 	struct zone *zone = mz->zone;
 
 	lru_add_drain();
 
+	reset_reclaim_mode(sc);
+
 	if (!sc->may_unmap)
-		reclaim_mode |= ISOLATE_UNMAPPED;
+		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
-		reclaim_mode |= ISOLATE_CLEAN;
+		isolate_mode |= ISOLATE_CLEAN;
 
 	spin_lock_irq(&zone->lru_lock);
 
-	nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold,
-				     &nr_scanned, sc->order,
-				     reclaim_mode, 1, file);
+	nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold, &nr_scanned, sc,
+				     isolate_mode, 1, file);
 	if (global_reclaim(sc))
 		zone->pages_scanned += nr_scanned;
 
@@ -1737,6 +1724,14 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			continue;
 		}
 
+		if (unlikely(buffer_heads_over_limit)) {
+			if (page_has_private(page) && trylock_page(page)) {
+				if (page_has_private(page))
+					try_to_release_page(page, 0);
+				unlock_page(page);
+			}
+		}
+
 		if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
@@ -2112,7 +2107,12 @@ restart:
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim)
+			nr_to_reclaim = 0;
+		else
+			nr_to_reclaim -= nr_reclaimed;
+
+		if (!nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 	blk_finish_plug(&plug);
@@ -2195,7 +2195,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	 * If compaction is deferred, reclaim up to a point where
 	 * compaction will have a chance of success when re-enabled
 	 */
-	if (compaction_deferred(zone))
+	if (compaction_deferred(zone, sc->order))
 		return watermark_ok;
 
 	/* If compaction is not ready to start, keep reclaiming */
@@ -2235,6 +2235,14 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
+	/*
+	 * If the number of buffer_heads in the machine exceeds the maximum
+	 * allowed level, force direct reclaim to scan the highmem zone as
+	 * highmem pages could be pinning lowmem pages storing buffer_heads
+	 */
+	if (buffer_heads_over_limit)
+		sc->gfp_mask |= __GFP_HIGHMEM;
+
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		if (!populated_zone(zone))
@@ -2255,8 +2263,8 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 				 * Even though compaction is invoked for any
 				 * non-zero order, only frequent costly order
 				 * reclamation is disruptive enough to become a
-				 * noticable problem, like transparent huge page
-				 * allocations.
+				 * noticeable problem, like transparent huge
+				 * page allocations.
 				 */
 				if (compaction_ready(zone, sc)) {
 					aborted_reclaim = true;
@@ -2337,7 +2345,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	unsigned long writeback_threshold;
 	bool aborted_reclaim;
 
-	get_mems_allowed();
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
@@ -2401,7 +2408,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 out:
 	delayacct_freepages_end();
-	put_mems_allowed();
 
 	if (sc->nr_reclaimed)
 		return sc->nr_reclaimed;
@@ -2724,6 +2730,17 @@ loop_again:
 			 */
 			age_active_anon(zone, &sc, priority);
 
+			/*
+			 * If the number of buffer_heads in the machine
+			 * exceeds the maximum allowed level and this node
+			 * has a highmem zone, force kswapd to reclaim from
+			 * it to relieve lowmem pressure.
+			 */
+			if (buffer_heads_over_limit && is_highmem_idx(i)) {
+				end_zone = i;
+				break;
+			}
+
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
@@ -2753,7 +2770,7 @@ loop_again:
 		 */
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
-			int nr_slab;
+			int nr_slab, testorder;
 			unsigned long balance_gap;
 
 			if (!populated_zone(zone))
@@ -2786,7 +2803,21 @@ loop_again:
 				(zone->present_pages +
 					KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
 				KSWAPD_ZONE_BALANCE_GAP_RATIO);
-			if (!zone_watermark_ok_safe(zone, order,
+			/*
+			 * Kswapd reclaims only single pages with compaction
+			 * enabled. Trying too hard to reclaim until contiguous
+			 * free pages have become available can hurt performance
+			 * by evicting too much useful data from memory.
+			 * Do not reclaim more than needed for compaction.
+			 */
+			testorder = order;
+			if (COMPACTION_BUILD && order &&
+					compaction_suitable(zone, order) !=
+						COMPACT_SKIPPED)
+				testorder = 0;
+
+			if ((buffer_heads_over_limit && is_highmem_idx(i)) ||
+				    !zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone) + balance_gap,
 					end_zone, 0)) {
 				shrink_zone(priority, zone, &sc);
@@ -2815,7 +2846,7 @@ loop_again:
 				continue;
 			}
 
-			if (!zone_watermark_ok_safe(zone, order,
+			if (!zone_watermark_ok_safe(zone, testorder,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
 				/*
@@ -2903,6 +2934,8 @@ out:
 	 * and it is potentially going to sleep here.
 	 */
 	if (order) {
+		int zones_need_compaction = 1;
+
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
@@ -2912,6 +2945,10 @@ out:
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
+			/* Would compaction fail due to lack of free memory? */
+			if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
+				goto loop_again;
+
 			/* Confirm the zone is balanced for order-0 */
 			if (!zone_watermark_ok(zone, 0,
 					high_wmark_pages(zone), 0, 0)) {
@@ -2919,11 +2956,17 @@ out:
 				goto loop_again;
 			}
 
+			/* Check if the memory needs to be defragmented. */
+			if (zone_watermark_ok(zone, order,
+				    low_wmark_pages(zone), *classzone_idx, 0))
+				zones_need_compaction = 0;
+
 			/* If balanced, clear the congested flag */
 			zone_clear_flag(zone, ZONE_CONGESTED);
-			if (i <= *classzone_idx)
-				balanced += zone->present_pages;
 		}
+
+		if (zones_need_compaction)
+			compact_pgdat(pgdat, order);
 	}
 
 	/*