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 <[email protected]>: (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 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		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 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 	 * 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;