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;
+	start_addr = 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;
-
-	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);
+		ret = setup_frame(signr, &ka, &info, oldset, regs);
+		if (ret)
+			return ret;
 
-		if (ka.sa.sa_flags & SA_ONESHOT)
-			ka.sa.sa_handler = SIG_DFL;
-
-		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