Linux-libre 4.2.4-gnupck-4.2.4-gnu

4 files changed, 48 insertions, 17 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a8c308708..62c1ec5a9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2974,6 +2974,14 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 
 		/*
+		 * Shared VMAs have their own reserves and do not affect
+		 * MAP_PRIVATE accounting but it is possible that a shared
+		 * VMA is using the same page so check and skip such VMAs.
+		 */
+		if (iter_vma->vm_flags & VM_MAYSHARE)
+			continue;
+
+		/*
 		 * Unmap the page from other VMAs without their own reserves.
 		 * They get marked to be SIGKILLed if they fault in these
 		 * areas. This is because a future no-page fault on this VMA
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index acb93c554..237d46864 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -806,12 +806,14 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 }
 
 /*
+ * Return page count for single (non recursive) @memcg.
+ *
  * Implementation Note: reading percpu statistics for memcg.
  *
  * Both of vmstat[] and percpu_counter has threshold and do periodic
  * synchronization to implement "quick" read. There are trade-off between
  * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
  *
  * But this _read() function is used for user interface now. The user accounts
  * memory usage by memory cgroup and he _always_ requires exact value because
@@ -821,17 +823,24 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
  *
  * If there are kernel internal actions which can make use of some not-exact
  * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
  * implemented.
  */
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
 {
 	long val = 0;
 	int cpu;
 
+	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_possible_cpu(cpu)
 		val += per_cpu(memcg->stat->count[idx], cpu);
+	/*
+	 * Summing races with updates, so val may be negative.  Avoid exposing
+	 * transient negative values.
+	 */
+	if (val < 0)
+		val = 0;
 	return val;
 }
 
@@ -1498,7 +1507,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 				continue;
-			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+			pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
 				K(mem_cgroup_read_stat(iter, i)));
 		}
 
@@ -3119,14 +3128,11 @@ static unsigned long tree_stat(struct mem_cgroup *memcg,
 			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
-	long val = 0;
+	unsigned long val = 0;
 
-	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_mem_cgroup_tree(iter, memcg)
 		val += mem_cgroup_read_stat(iter, idx);
 
-	if (val < 0) /* race ? */
-		val = 0;
 	return val;
 }
 
@@ -3469,7 +3475,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
-		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+		seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
 	}
 
@@ -3494,13 +3500,13 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		long long val = 0;
+		unsigned long long val = 0;
 
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
-		seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+		seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
 	}
 
 	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
diff --git a/mm/migrate.c b/mm/migrate.c
index eb4267107..fcb6204de 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -734,6 +734,15 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	if (PageSwapBacked(page))
 		SetPageSwapBacked(newpage);
 
+	/*
+	 * Indirectly called below, migrate_page_copy() copies PG_dirty and thus
+	 * needs newpage's memcg set to transfer memcg dirty page accounting.
+	 * So perform memcg migration in two steps:
+	 * 1. set newpage->mem_cgroup (here)
+	 * 2. clear page->mem_cgroup (below)
+	 */
+	set_page_memcg(newpage, page_memcg(page));
+
 	mapping = page_mapping(page);
 	if (!mapping)
 		rc = migrate_page(mapping, newpage, page, mode);
@@ -750,9 +759,10 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
 	if (rc != MIGRATEPAGE_SUCCESS) {
+		set_page_memcg(newpage, NULL);
 		newpage->mapping = NULL;
 	} else {
-		mem_cgroup_migrate(page, newpage, false);
+		set_page_memcg(page, NULL);
 		if (page_was_mapped)
 			remove_migration_ptes(page, newpage);
 		page->mapping = NULL;
@@ -1068,7 +1078,7 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
 		put_new_page(new_hpage, private);
 	else
-		put_page(new_hpage);
+		putback_active_hugepage(new_hpage);
 
 	if (result) {
 		if (rc)
diff --git a/mm/slab.c b/mm/slab.c
index bbd0b47dc..ae3602830 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2190,9 +2190,16 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
-	if (size >= kmalloc_size(INDEX_NODE + 1)
-	    && cachep->object_size > cache_line_size()
-	    && ALIGN(size, cachep->align) < PAGE_SIZE) {
+	/*
+	 * To activate debug pagealloc, off-slab management is necessary
+	 * requirement. In early phase of initialization, small sized slab
+	 * doesn't get initialized so it would not be possible. So, we need
+	 * to check size >= 256. It guarantees that all necessary small
+	 * sized slab is initialized in current slab initialization sequence.
+	 */
+	if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+		size >= 256 && cachep->object_size > cache_line_size() &&
+		ALIGN(size, cachep->align) < PAGE_SIZE) {
 		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
 		size = PAGE_SIZE;
 	}