Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - inotify tweaks

 - some ocfs2 updates (many more are awaiting review)

 - various misc bits

 - kernel/watchdog.c updates

 - Some of mm.  I have a huge number of MM patches this time and quite a
   lot of it is quite difficult and much will be held over to next time.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  selftests: vm: add tests for lock on fault
  mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage
  mm: introduce VM_LOCKONFAULT
  mm: mlock: add new mlock system call
  mm: mlock: refactor mlock, munlock, and munlockall code
  kasan: always taint kernel on report
  mm, slub, kasan: enable user tracking by default with KASAN=y
  kasan: use IS_ALIGNED in memory_is_poisoned_8()
  kasan: Fix a type conversion error
  lib: test_kasan: add some testcases
  kasan: update reference to kasan prototype repo
  kasan: move KASAN_SANITIZE in arch/x86/boot/Makefile
  kasan: various fixes in documentation
  kasan: update log messages
  kasan: accurately determine the type of the bad access
  kasan: update reported bug types for kernel memory accesses
  kasan: update reported bug types for not user nor kernel memory accesses
  mm/kasan: prevent deadlock in kasan reporting
  mm/kasan: don't use kasan shadow pointer in generic functions
  mm/kasan: MODULE_VADDR is not available on all archs
  ...

1 files changed, 116 insertions, 179 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b732edfddb76..bc502e590366 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/lockdep.h>
 #include <linux/file.h>
+#include <linux/tracehook.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -1661,7 +1662,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_oom.may_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -1678,9 +1679,9 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 	 * and when we know whether the fault was overall successful.
 	 */
 	css_get(&memcg->css);
-	current->memcg_oom.memcg = memcg;
-	current->memcg_oom.gfp_mask = mask;
-	current->memcg_oom.order = order;
+	current->memcg_in_oom = memcg;
+	current->memcg_oom_gfp_mask = mask;
+	current->memcg_oom_order = order;
 }
 
 /**
@@ -1702,7 +1703,7 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
  */
 bool mem_cgroup_oom_synchronize(bool handle)
 {
-	struct mem_cgroup *memcg = current->memcg_oom.memcg;
+	struct mem_cgroup *memcg = current->memcg_in_oom;
 	struct oom_wait_info owait;
 	bool locked;
 
@@ -1730,8 +1731,8 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	if (locked && !memcg->oom_kill_disable) {
 		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
-		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
-					 current->memcg_oom.order);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
+					 current->memcg_oom_order);
 	} else {
 		schedule();
 		mem_cgroup_unmark_under_oom(memcg);
@@ -1748,7 +1749,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 		memcg_oom_recover(memcg);
 	}
 cleanup:
-	current->memcg_oom.memcg = NULL;
+	current->memcg_in_oom = NULL;
 	css_put(&memcg->css);
 	return true;
 }
@@ -1972,6 +1973,31 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg, *pos;
+
+	if (likely(!nr_pages))
+		return;
+
+	pos = memcg = get_mem_cgroup_from_mm(current->mm);
+
+	do {
+		if (page_counter_read(&pos->memory) <= pos->high)
+			continue;
+		mem_cgroup_events(pos, MEMCG_HIGH, 1);
+		try_to_free_mem_cgroup_pages(pos, nr_pages, GFP_KERNEL, true);
+	} while ((pos = parent_mem_cgroup(pos)));
+
+	css_put(&memcg->css);
+	current->memcg_nr_pages_over_high = 0;
+}
+
 static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		      unsigned int nr_pages)
 {
@@ -1982,17 +2008,16 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long nr_reclaimed;
 	bool may_swap = true;
 	bool drained = false;
-	int ret = 0;
 
 	if (mem_cgroup_is_root(memcg))
-		goto done;
+		return 0;
 retry:
 	if (consume_stock(memcg, nr_pages))
-		goto done;
+		return 0;
 
 	if (!do_swap_account ||
-	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
-		if (!page_counter_try_charge(&memcg->memory, batch, &counter))
+	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
+		if (page_counter_try_charge(&memcg->memory, batch, &counter))
 			goto done_restock;
 		if (do_swap_account)
 			page_counter_uncharge(&memcg->memsw, batch);
@@ -2016,7 +2041,7 @@ retry:
 	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
 		     fatal_signal_pending(current) ||
 		     current->flags & PF_EXITING))
-		goto bypass;
+		goto force;
 
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
@@ -2062,38 +2087,54 @@ retry:
 		goto retry;
 
 	if (gfp_mask & __GFP_NOFAIL)
-		goto bypass;
+		goto force;
 
 	if (fatal_signal_pending(current))
-		goto bypass;
+		goto force;
 
 	mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1);
 
-	mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages));
+	mem_cgroup_oom(mem_over_limit, gfp_mask,
+		       get_order(nr_pages * PAGE_SIZE));
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
-bypass:
-	return -EINTR;
+force:
+	/*
+	 * The allocation either can't fail or will lead to more memory
+	 * being freed very soon.  Allow memory usage go over the limit
+	 * temporarily by force charging it.
+	 */
+	page_counter_charge(&memcg->memory, nr_pages);
+	if (do_swap_account)
+		page_counter_charge(&memcg->memsw, nr_pages);
+	css_get_many(&memcg->css, nr_pages);
+
+	return 0;
 
 done_restock:
 	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
-	if (!(gfp_mask & __GFP_WAIT))
-		goto done;
+
 	/*
-	 * If the hierarchy is above the normal consumption range,
-	 * make the charging task trim their excess contribution.
+	 * If the hierarchy is above the normal consumption range, schedule
+	 * reclaim on returning to userland.  We can perform reclaim here
+	 * if __GFP_WAIT but let's always punt for simplicity and so that
+	 * GFP_KERNEL can consistently be used during reclaim.  @memcg is
+	 * not recorded as it most likely matches current's and won't
+	 * change in the meantime.  As high limit is checked again before
+	 * reclaim, the cost of mismatch is negligible.
 	 */
 	do {
-		if (page_counter_read(&memcg->memory) <= memcg->high)
-			continue;
-		mem_cgroup_events(memcg, MEMCG_HIGH, 1);
-		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+		if (page_counter_read(&memcg->memory) > memcg->high) {
+			current->memcg_nr_pages_over_high += nr_pages;
+			set_notify_resume(current);
+			break;
+		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
-done:
-	return ret;
+
+	return 0;
 }
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2174,55 +2215,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
-		      unsigned long nr_pages)
-{
-	struct page_counter *counter;
-	int ret = 0;
-
-	ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter);
-	if (ret < 0)
-		return ret;
-
-	ret = try_charge(memcg, gfp, nr_pages);
-	if (ret == -EINTR)  {
-		/*
-		 * try_charge() chose to bypass to root due to OOM kill or
-		 * fatal signal.  Since our only options are to either fail
-		 * the allocation or charge it to this cgroup, do it as a
-		 * temporary condition. But we can't fail. From a kmem/slab
-		 * perspective, the cache has already been selected, by
-		 * mem_cgroup_kmem_get_cache(), so it is too late to change
-		 * our minds.
-		 *
-		 * This condition will only trigger if the task entered
-		 * memcg_charge_kmem in a sane state, but was OOM-killed
-		 * during try_charge() above. Tasks that were already dying
-		 * when the allocation triggers should have been already
-		 * directed to the root cgroup in memcontrol.h
-		 */
-		page_counter_charge(&memcg->memory, nr_pages);
-		if (do_swap_account)
-			page_counter_charge(&memcg->memsw, nr_pages);
-		css_get_many(&memcg->css, nr_pages);
-		ret = 0;
-	} else if (ret)
-		page_counter_uncharge(&memcg->kmem, nr_pages);
-
-	return ret;
-}
-
-void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
-{
-	page_counter_uncharge(&memcg->memory, nr_pages);
-	if (do_swap_account)
-		page_counter_uncharge(&memcg->memsw, nr_pages);
-
-	page_counter_uncharge(&memcg->kmem, nr_pages);
-
-	css_put_many(&memcg->css, nr_pages);
-}
-
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -2384,85 +2376,58 @@ void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 		css_put(&cachep->memcg_params.memcg->css);
 }
 
-/*
- * We need to verify if the allocation against current->mm->owner's memcg is
- * possible for the given order. But the page is not allocated yet, so we'll
- * need a further commit step to do the final arrangements.
- *
- * It is possible for the task to switch cgroups in this mean time, so at
- * commit time, we can't rely on task conversion any longer.  We'll then use
- * the handle argument to return to the caller which cgroup we should commit
- * against. We could also return the memcg directly and avoid the pointer
- * passing, but a boolean return value gives better semantics considering
- * the compiled-out case as well.
- *
- * Returning true means the allocation is possible.
- */
-bool
-__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+			      struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg;
+	unsigned int nr_pages = 1 << order;
+	struct page_counter *counter;
 	int ret;
 
-	*_memcg = NULL;
+	if (!memcg_kmem_is_active(memcg))
+		return 0;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
+	if (!page_counter_try_charge(&memcg->kmem, nr_pages, &counter))
+		return -ENOMEM;
 
-	if (!memcg_kmem_is_active(memcg)) {
-		css_put(&memcg->css);
-		return true;
+	ret = try_charge(memcg, gfp, nr_pages);
+	if (ret) {
+		page_counter_uncharge(&memcg->kmem, nr_pages);
+		return ret;
 	}
 
-	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
-	if (!ret)
-		*_memcg = memcg;
+	page->mem_cgroup = memcg;
 
-	css_put(&memcg->css);
-	return (ret == 0);
+	return 0;
 }
 
-void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      int order)
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
-	VM_BUG_ON(mem_cgroup_is_root(memcg));
+	struct mem_cgroup *memcg;
+	int ret;
 
-	/* The page allocation failed. Revert */
-	if (!page) {
-		memcg_uncharge_kmem(memcg, 1 << order);
-		return;
-	}
-	page->mem_cgroup = memcg;
+	memcg = get_mem_cgroup_from_mm(current->mm);
+	ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+	css_put(&memcg->css);
+	return ret;
 }
 
-void __memcg_kmem_uncharge_pages(struct page *page, int order)
+void __memcg_kmem_uncharge(struct page *page, int order)
 {
 	struct mem_cgroup *memcg = page->mem_cgroup;
+	unsigned int nr_pages = 1 << order;
 
 	if (!memcg)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 
-	memcg_uncharge_kmem(memcg, 1 << order);
-	page->mem_cgroup = NULL;
-}
-
-struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
-{
-	struct mem_cgroup *memcg = NULL;
-	struct kmem_cache *cachep;
-	struct page *page;
-
-	page = virt_to_head_page(ptr);
-	if (PageSlab(page)) {
-		cachep = page->slab_cache;
-		if (!is_root_cache(cachep))
-			memcg = cachep->memcg_params.memcg;
-	} else
-		/* page allocated by alloc_kmem_pages */
-		memcg = page->mem_cgroup;
+	page_counter_uncharge(&memcg->kmem, nr_pages);
+	page_counter_uncharge(&memcg->memory, nr_pages);
+	if (do_swap_account)
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	return memcg;
+	page->mem_cgroup = NULL;
+	css_put_many(&memcg->css, nr_pages);
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
@@ -2836,9 +2801,9 @@ static unsigned long tree_stat(struct mem_cgroup *memcg,
 	return val;
 }
 
-static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
+static inline unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 {
-	u64 val;
+	unsigned long val;
 
 	if (mem_cgroup_is_root(memcg)) {
 		val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE);
@@ -2851,7 +2816,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 		else
 			val = page_counter_read(&memcg->memsw);
 	}
-	return val << PAGE_SHIFT;
+	return val;
 }
 
 enum {
@@ -2885,9 +2850,9 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	switch (MEMFILE_ATTR(cft->private)) {
 	case RES_USAGE:
 		if (counter == &memcg->memory)
-			return mem_cgroup_usage(memcg, false);
+			return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
 		if (counter == &memcg->memsw)
-			return mem_cgroup_usage(memcg, true);
+			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
 		return (u64)page_counter_read(counter) * PAGE_SIZE;
 	case RES_LIMIT:
 		return (u64)counter->limit * PAGE_SIZE;
@@ -3387,7 +3352,6 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 	ret = page_counter_memparse(args, "-1", &threshold);
 	if (ret)
 		return ret;
-	threshold <<= PAGE_SHIFT;
 
 	mutex_lock(&memcg->thresholds_lock);
 
@@ -4406,22 +4370,10 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		mc.precharge += count;
 		return ret;
 	}
-	if (ret == -EINTR) {
-		cancel_charge(root_mem_cgroup, count);
-		return ret;
-	}
 
 	/* Try charges one by one with reclaim */
 	while (count--) {
 		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
-		/*
-		 * In case of failure, any residual charges against
-		 * mc.to will be dropped by mem_cgroup_clear_mc()
-		 * later on.  However, cancel any charges that are
-		 * bypassed to root right away or they'll be lost.
-		 */
-		if (ret == -EINTR)
-			cancel_charge(root_mem_cgroup, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -4576,9 +4528,8 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	/*
-	 * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup
-	 * of its source page while we change it: page migration takes
-	 * both pages off the LRU, but page cache replacement doesn't.
+	 * Prevent mem_cgroup_replace_page() from looking at
+	 * page->mem_cgroup of its source page while we change it.
 	 */
 	if (!trylock_page(page))
 		goto out;
@@ -5085,7 +5036,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 static u64 memory_current_read(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	return mem_cgroup_usage(mem_cgroup_from_css(css), false);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE;
 }
 
 static int memory_low_show(struct seq_file *m, void *v)
@@ -5197,6 +5150,7 @@ static int memory_events_show(struct seq_file *m, void *v)
 static struct cftype memory_files[] = {
 	{
 		.name = "current",
+		.flags = CFTYPE_NOT_ON_ROOT,
 		.read_u64 = memory_current_read,
 	},
 	{
@@ -5340,11 +5294,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	ret = try_charge(memcg, gfp_mask, nr_pages);
 
 	css_put(&memcg->css);
-
-	if (ret == -EINTR) {
-		memcg = root_mem_cgroup;
-		ret = 0;
-	}
 out:
 	*memcgp = memcg;
 	return ret;
@@ -5559,7 +5508,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 }
 
 /**
- * mem_cgroup_migrate - migrate a charge to another page
+ * mem_cgroup_replace_page - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
  * @lrucare: either or both pages might be on the LRU already
@@ -5568,16 +5517,13 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  *
  * Both pages must be locked, @newpage->mapping must be set up.
  */
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
-			bool lrucare)
+void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 {
 	struct mem_cgroup *memcg;
 	int isolated;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
 	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
-	VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage);
-	VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage);
 	VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
 	VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage),
 		       newpage);
@@ -5589,25 +5535,16 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 	if (newpage->mem_cgroup)
 		return;
 
-	/*
-	 * Swapcache readahead pages can get migrated before being
-	 * charged, and migration from compaction can happen to an
-	 * uncharged page when the PFN walker finds a page that
-	 * reclaim just put back on the LRU but has not released yet.
-	 */
+	/* Swapcache readahead pages can get replaced before being charged */
 	memcg = oldpage->mem_cgroup;
 	if (!memcg)
 		return;
 
-	if (lrucare)
-		lock_page_lru(oldpage, &isolated);
-
+	lock_page_lru(oldpage, &isolated);
 	oldpage->mem_cgroup = NULL;
+	unlock_page_lru(oldpage, isolated);
 
-	if (lrucare)
-		unlock_page_lru(oldpage, isolated);
-
-	commit_charge(newpage, memcg, lrucare);
+	commit_charge(newpage, memcg, true);
 }
 
 /*