Merge tag 'v3.14.24' into linux-linaro-lsk-v3.14

This is the 3.14.24 stable release

7 files changed, 118 insertions, 12 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 718bfa16a36f..331faa5c0d5e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -199,7 +199,7 @@ retry:
 	preempt_disable();
 	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
 		preempt_enable();
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
 
@@ -231,7 +231,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9b35da28b587..b58d4fbe6c48 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -292,6 +292,9 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
+	/* css_online() has been completed */
+	int initialized;
+
 	/*
 	 * the counter to account for mem+swap usage.
 	 */
@@ -1127,9 +1130,21 @@ skip_node:
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css == &root->css) ||
-		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
-			return mem_cgroup_from_css(next_css);
+		struct mem_cgroup *memcg = mem_cgroup_from_css(next_css);
+
+		if (next_css == &root->css)
+			return memcg;
+
+		if (css_tryget(next_css)) {
+			/*
+			 * Make sure the memcg is initialized:
+			 * mem_cgroup_css_online() orders the the
+			 * initialization against setting the flag.
+			 */
+			if (smp_load_acquire(&memcg->initialized))
+				return memcg;
+			css_put(next_css);
+		}
 
 		prev_css = next_css;
 		goto skip_node;
@@ -6538,6 +6553,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
+	int ret;
 
 	if (css->cgroup->id > MEM_CGROUP_ID_MAX)
 		return -ENOSPC;
@@ -6574,7 +6590,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	}
 	mutex_unlock(&memcg_create_mutex);
 
-	return memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	ret = memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure the memcg is initialized: mem_cgroup_iter()
+	 * orders reading memcg->initialized against its callers
+	 * reading the memcg members.
+	 */
+	smp_store_release(&memcg->initialized, 1);
+
+	return 0;
 }
 
 /*
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3291e82d4352..171c00f2e495 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -406,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ff0f6b13f32f..7b2611a055a7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1957,7 +1957,7 @@ zonelist_scan:
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				continue;
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+			if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0)
 				continue;
 		}
 		/*
@@ -2196,6 +2196,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.
@@ -5662,9 +5670,8 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				      high_wmark_pages(zone) -
-				      low_wmark_pages(zone) -
-				      zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index cfd162882c00..0e9a319d5f8d 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index 8cd4308471c3..a2a54a85f691 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1917,8 +1917,6 @@ void __init setup_per_cpu_areas(void)
 
 	if (pcpu_setup_first_chunk(ai, fc) < 0)
 		panic("Failed to initialize percpu areas.");
-
-	pcpu_free_alloc_info(ai);
 }
 
 #endif	/* CONFIG_SMP */
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683afd6e..ac18edc30649 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 
@@ -613,12 +614,67 @@ EXPORT_SYMBOL(truncate_pagecache);
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
+	loff_t oldsize = inode->i_size;
+
 	i_size_write(inode, newsize);
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
  * @lstart: offset of beginning of hole