Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify updates

 - ocfs2 updates

 - all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (127 commits)
  console: don't prefer first registered if DT specifies stdout-path
  cred: simpler, 1D supplementary groups
  CREDITS: update Pavel's information, add GPG key, remove snail mail address
  mailmap: add Johan Hovold
  .gitattributes: set git diff driver for C source code files
  uprobes: remove function declarations from arch/{mips,s390}
  spelling.txt: "modeled" is spelt correctly
  nmi_backtrace: generate one-line reports for idle cpus
  arch/tile: adopt the new nmi_backtrace framework
  nmi_backtrace: do a local dump_stack() instead of a self-NMI
  nmi_backtrace: add more trigger_*_cpu_backtrace() methods
  min/max: remove sparse warnings when they're nested
  Documentation/filesystems/proc.txt: add more description for maps/smaps
  mm, proc: fix region lost in /proc/self/smaps
  proc: fix timerslack_ns CAP_SYS_NICE check when adjusting self
  proc: add LSM hook checks to /proc/<tid>/timerslack_ns
  proc: relax /proc/<tid>/timerslack_ns capability requirements
  meminfo: break apart a very long seq_printf with #ifdefs
  seq/proc: modify seq_put_decimal_[u]ll to take a const char *, not char
  proc: faster /proc/*/status
  ...

7 files changed, 58 insertions, 66 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 1e1d913914c0..9d68c45ebbe3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -511,7 +511,7 @@ static void exit_mm(struct task_struct *tsk)
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
-		exit_oom_victim(tsk);
+		exit_oom_victim();
 }
 
 static struct task_struct *find_alive_thread(struct task_struct *p)
diff --git a/kernel/fork.c b/kernel/fork.c
index 9a05bd93f8e7..6d42242485cb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -359,6 +359,12 @@ static inline void free_signal_struct(struct signal_struct *sig)
 {
 	taskstats_tgid_free(sig);
 	sched_autogroup_exit(sig);
+	/*
+	 * __mmdrop is not safe to call from softirq context on x86 due to
+	 * pgd_dtor so postpone it to the async context
+	 */
+	if (sig->oom_mm)
+		mmdrop_async(sig->oom_mm);
 	kmem_cache_free(signal_cachep, sig);
 }
 
@@ -848,6 +854,7 @@ static inline void __mmput(struct mm_struct *mm)
 	ksm_exit(mm);
 	khugepaged_exit(mm); /* must run before exit_mmap */
 	exit_mmap(mm);
+	mm_put_huge_zero_page(mm);
 	set_mm_exe_file(mm, NULL);
 	if (!list_empty(&mm->mmlist)) {
 		spin_lock(&mmlist_lock);
@@ -856,6 +863,7 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
+	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
diff --git a/kernel/groups.c b/kernel/groups.c
index 74d431d25251..2fcadd66a8fd 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -7,55 +7,31 @@
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/user_namespace.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 
 struct group_info *groups_alloc(int gidsetsize)
 {
-	struct group_info *group_info;
-	int nblocks;
-	int i;
-
-	nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
-	/* Make sure we always allocate at least one indirect block pointer */
-	nblocks = nblocks ? : 1;
-	group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
-	if (!group_info)
+	struct group_info *gi;
+	unsigned int len;
+
+	len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
+	gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
+	if (!gi)
+		gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL);
+	if (!gi)
 		return NULL;
-	group_info->ngroups = gidsetsize;
-	group_info->nblocks = nblocks;
-	atomic_set(&group_info->usage, 1);
-
-	if (gidsetsize <= NGROUPS_SMALL)
-		group_info->blocks[0] = group_info->small_block;
-	else {
-		for (i = 0; i < nblocks; i++) {
-			kgid_t *b;
-			b = (void *)__get_free_page(GFP_USER);
-			if (!b)
-				goto out_undo_partial_alloc;
-			group_info->blocks[i] = b;
-		}
-	}
-	return group_info;
 
-out_undo_partial_alloc:
-	while (--i >= 0) {
-		free_page((unsigned long)group_info->blocks[i]);
-	}
-	kfree(group_info);
-	return NULL;
+	atomic_set(&gi->usage, 1);
+	gi->ngroups = gidsetsize;
+	return gi;
 }
 
 EXPORT_SYMBOL(groups_alloc);
 
 void groups_free(struct group_info *group_info)
 {
-	if (group_info->blocks[0] != group_info->small_block) {
-		int i;
-		for (i = 0; i < group_info->nblocks; i++)
-			free_page((unsigned long)group_info->blocks[i]);
-	}
-	kfree(group_info);
+	kvfree(group_info);
 }
 
 EXPORT_SYMBOL(groups_free);
@@ -70,7 +46,7 @@ static int groups_to_user(gid_t __user *grouplist,
 
 	for (i = 0; i < count; i++) {
 		gid_t gid;
-		gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i));
+		gid = from_kgid_munged(user_ns, group_info->gid[i]);
 		if (put_user(gid, grouplist+i))
 			return -EFAULT;
 	}
@@ -95,7 +71,7 @@ static int groups_from_user(struct group_info *group_info,
 		if (!gid_valid(kgid))
 			return -EINVAL;
 
-		GROUP_AT(group_info, i) = kgid;
+		group_info->gid[i] = kgid;
 	}
 	return 0;
 }
@@ -115,15 +91,14 @@ static void groups_sort(struct group_info *group_info)
 		for (base = 0; base < max; base++) {
 			int left = base;
 			int right = left + stride;
-			kgid_t tmp = GROUP_AT(group_info, right);
+			kgid_t tmp = group_info->gid[right];
 
-			while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) {
-				GROUP_AT(group_info, right) =
-				    GROUP_AT(group_info, left);
+			while (left >= 0 && gid_gt(group_info->gid[left], tmp)) {
+				group_info->gid[right] = group_info->gid[left];
 				right = left;
 				left -= stride;
 			}
-			GROUP_AT(group_info, right) = tmp;
+			group_info->gid[right] = tmp;
 		}
 		stride /= 3;
 	}
@@ -141,9 +116,9 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
 	right = group_info->ngroups;
 	while (left < right) {
 		unsigned int mid = (left+right)/2;
-		if (gid_gt(grp, GROUP_AT(group_info, mid)))
+		if (gid_gt(grp, group_info->gid[mid]))
 			left = mid + 1;
-		else if (gid_lt(grp, GROUP_AT(group_info, mid)))
+		else if (gid_lt(grp, group_info->gid[mid]))
 			right = mid;
 		else
 			return 1;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 8f27d5a8adf6..2fba066e125f 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -144,23 +144,12 @@ int freeze_processes(void)
 	/*
 	 * Now that the whole userspace is frozen we need to disbale
 	 * the OOM killer to disallow any further interference with
-	 * killable tasks.
+	 * killable tasks. There is no guarantee oom victims will
+	 * ever reach a point they go away we have to wait with a timeout.
 	 */
-	if (!error && !oom_killer_disable())
+	if (!error && !oom_killer_disable(msecs_to_jiffies(freeze_timeout_msecs)))
 		error = -EBUSY;
 
-	/*
-	 * There is a hard to fix race between oom_reaper kernel thread
-	 * and oom_killer_disable. oom_reaper calls exit_oom_victim
-	 * before the victim reaches exit_mm so try to freeze all the tasks
-	 * again and catch such a left over task.
-	 */
-	if (!error) {
-		pr_info("Double checking all user space processes after OOM killer disable... ");
-		error = try_to_freeze_tasks(true);
-		pr_cont("\n");
-	}
-
 	if (error)
 		thaw_processes();
 	return error;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index eea6dbc2d8cf..8019cc0d3a73 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -253,6 +253,17 @@ static int preferred_console = -1;
 int console_set_on_cmdline;
 EXPORT_SYMBOL(console_set_on_cmdline);
 
+#ifdef CONFIG_OF
+static bool of_specified_console;
+
+void console_set_by_of(void)
+{
+	of_specified_console = true;
+}
+#else
+# define of_specified_console false
+#endif
+
 /* Flag: console code may call schedule() */
 static int console_may_schedule;
 
@@ -2647,7 +2658,7 @@ void register_console(struct console *newcon)
 	 *	didn't select a console we take the first one
 	 *	that registers here.
 	 */
-	if (preferred_console < 0) {
+	if (preferred_console < 0 && !of_specified_console) {
 		if (newcon->index < 0)
 			newcon->index = 0;
 		if (newcon->setup == NULL ||
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 9fb873cfc75c..1d8718d5300d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -16,6 +16,9 @@
 
 #include "sched.h"
 
+/* Linker adds these: start and end of __cpuidle functions */
+extern char __cpuidle_text_start[], __cpuidle_text_end[];
+
 /**
  * sched_idle_set_state - Record idle state for the current CPU.
  * @idle_state: State to record.
@@ -53,7 +56,7 @@ static int __init cpu_idle_nopoll_setup(char *__unused)
 __setup("hlt", cpu_idle_nopoll_setup);
 #endif
 
-static inline int cpu_idle_poll(void)
+static noinline int __cpuidle cpu_idle_poll(void)
 {
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
@@ -84,7 +87,7 @@ void __weak arch_cpu_idle(void)
  *
  * To use when the cpuidle framework cannot be used.
  */
-void default_idle_call(void)
+void __cpuidle default_idle_call(void)
 {
 	if (current_clr_polling_and_test()) {
 		local_irq_enable();
@@ -271,6 +274,12 @@ static void cpu_idle_loop(void)
 	}
 }
 
+bool cpu_in_idle(unsigned long pc)
+{
+	return pc >= (unsigned long)__cpuidle_text_start &&
+		pc < (unsigned long)__cpuidle_text_end;
+}
+
 void cpu_startup_entry(enum cpuhp_state state)
 {
 	/*
diff --git a/kernel/uid16.c b/kernel/uid16.c
index d58cc4d8f0d1..cc40793464e3 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -117,7 +117,7 @@ static int groups16_to_user(old_gid_t __user *grouplist,
 	kgid_t kgid;
 
 	for (i = 0; i < group_info->ngroups; i++) {
-		kgid = GROUP_AT(group_info, i);
+		kgid = group_info->gid[i];
 		group = high2lowgid(from_kgid_munged(user_ns, kgid));
 		if (put_user(group, grouplist+i))
 			return -EFAULT;
@@ -142,7 +142,7 @@ static int groups16_from_user(struct group_info *group_info,
 		if (!gid_valid(kgid))
 			return -EINVAL;
 
-		GROUP_AT(group_info, i) = kgid;
+		group_info->gid[i] = kgid;
 	}
 
 	return 0;