Merge branch 'master' of /pub/scm/linux/kernel/git/torvalds/linux-2.6

8 files changed, 51 insertions, 25 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 3ad483bdf505..e9c0c61f2ddd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -179,7 +179,7 @@ config SPLIT_PTLOCK_CPUS
 config COMPACTION
 	bool "Allow for memory compaction"
 	select MIGRATION
-	depends on EXPERIMENTAL && HUGETLB_PAGE && MMU
+	depends on MMU
 	help
 	  Allows the compaction of memory for the allocation of huge pages.
 
diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c
index 177a5169bbde..ff0d9779cec8 100644
--- a/mm/kmemleak-test.c
+++ b/mm/kmemleak-test.c
@@ -75,13 +75,11 @@ static int __init kmemleak_test_init(void)
 	 * after the module is removed.
 	 */
 	for (i = 0; i < 10; i++) {
-		elem = kmalloc(sizeof(*elem), GFP_KERNEL);
-		pr_info("kmemleak: kmalloc(sizeof(*elem)) = %p\n", elem);
+		elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+		pr_info("kmemleak: kzalloc(sizeof(*elem)) = %p\n", elem);
 		if (!elem)
 			return -ENOMEM;
-		memset(elem, 0, sizeof(*elem));
 		INIT_LIST_HEAD(&elem->list);
-
 		list_add_tail(&elem->list, &test_list);
 	}
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index bd9bc214091b..84225f3b7190 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -113,7 +113,9 @@
 #define BYTES_PER_POINTER	sizeof(void *)
 
 /* GFP bitmask for kmemleak internal allocations */
-#define GFP_KMEMLEAK_MASK	(GFP_KERNEL | GFP_ATOMIC)
+#define gfp_kmemleak_mask(gfp)	(((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
+				 __GFP_NORETRY | __GFP_NOMEMALLOC | \
+				 __GFP_NOWARN)
 
 /* scanning area inside a memory block */
 struct kmemleak_scan_area {
@@ -511,9 +513,10 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	struct kmemleak_object *object;
 	struct prio_tree_node *node;
 
-	object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK);
+	object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp));
 	if (!object) {
-		kmemleak_stop("Cannot allocate a kmemleak_object structure\n");
+		pr_warning("Cannot allocate a kmemleak_object structure\n");
+		kmemleak_disable();
 		return NULL;
 	}
 
@@ -734,9 +737,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 		return;
 	}
 
-	area = kmem_cache_alloc(scan_area_cache, gfp & GFP_KMEMLEAK_MASK);
+	area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
 	if (!area) {
-		kmemleak_warn("Cannot allocate a scan area\n");
+		pr_warning("Cannot allocate a scan area\n");
 		goto out;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index db76ef726293..3878cfe399dc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1832,6 +1832,7 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask,
 		if (likely(!ret))
 			return CHARGE_OK;
 
+		res_counter_uncharge(&mem->res, csize);
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
 		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
 	} else
@@ -2144,6 +2145,8 @@ void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail)
 	struct page_cgroup *tail_pc = lookup_page_cgroup(tail);
 	unsigned long flags;
 
+	if (mem_cgroup_disabled())
+		return;
 	/*
 	 * We have no races with charge/uncharge but will have races with
 	 * page state accounting.
@@ -2233,7 +2236,12 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 {
 	int ret = -EINVAL;
 	unsigned long flags;
-
+	/*
+	 * The page is isolated from LRU. So, collapse function
+	 * will not handle this page. But page splitting can happen.
+	 * Do this check under compound_page_lock(). The caller should
+	 * hold it.
+	 */
 	if ((charge_size > PAGE_SIZE) && !PageTransHuge(pc->page))
 		return -EBUSY;
 
@@ -2265,7 +2273,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 	struct cgroup *cg = child->css.cgroup;
 	struct cgroup *pcg = cg->parent;
 	struct mem_cgroup *parent;
-	int charge = PAGE_SIZE;
+	int page_size = PAGE_SIZE;
 	unsigned long flags;
 	int ret;
 
@@ -2278,23 +2286,26 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 		goto out;
 	if (isolate_lru_page(page))
 		goto put;
-	/* The page is isolated from LRU and we have no race with splitting */
-	charge = PAGE_SIZE << compound_order(page);
+
+	if (PageTransHuge(page))
+		page_size = HPAGE_SIZE;
 
 	parent = mem_cgroup_from_cont(pcg);
-	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, charge);
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask,
+				&parent, false, page_size);
 	if (ret || !parent)
 		goto put_back;
 
-	if (charge > PAGE_SIZE)
+	if (page_size > PAGE_SIZE)
 		flags = compound_lock_irqsave(page);
 
-	ret = mem_cgroup_move_account(pc, child, parent, true, charge);
+	ret = mem_cgroup_move_account(pc, child, parent, true, page_size);
 	if (ret)
-		mem_cgroup_cancel_charge(parent, charge);
-put_back:
-	if (charge > PAGE_SIZE)
+		mem_cgroup_cancel_charge(parent, page_size);
+
+	if (page_size > PAGE_SIZE)
 		compound_unlock_irqrestore(page, flags);
+put_back:
 	putback_lru_page(page);
 put:
 	put_page(page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 46fe8cc13d67..9f29a3b7aac2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -888,7 +888,7 @@ out:
  * are movable anymore because to has become empty
  * or no retryable pages exist anymore.
  * Caller should call putback_lru_pages to return pages to the LRU
- * or free list.
+ * or free list only if ret != 0.
  *
  * Return: Number of pages not migrated or error code.
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 90c1439549fd..a873e61e312e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1088,8 +1088,10 @@ static void drain_pages(unsigned int cpu)
 		pset = per_cpu_ptr(zone->pageset, cpu);
 
 		pcp = &pset->pcp;
-		free_pcppages_bulk(zone, pcp->count, pcp);
-		pcp->count = 0;
+		if (pcp->count) {
+			free_pcppages_bulk(zone, pcp->count, pcp);
+			pcp->count = 0;
+		}
 		local_irq_restore(flags);
 	}
 }
@@ -2034,6 +2036,14 @@ restart:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Find the true preferred zone if the allocation is unconstrained by
+	 * cpusets.
+	 */
+	if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
+		first_zones_zonelist(zonelist, high_zoneidx, NULL,
+					&preferred_zone);
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2192,7 +2202,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
 	get_mems_allowed();
 	/* The preferred zone is used for statistics later */
-	first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+	first_zones_zonelist(zonelist, high_zoneidx,
+				nodemask ? : &cpuset_current_mems_allowed,
+				&preferred_zone);
 	if (!preferred_zone) {
 		put_mems_allowed();
 		return NULL;
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0369f5b3ba1b..eb663fb533e0 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -6,6 +6,7 @@
  *  Copyright (C) 2010  Linus Torvalds
  */
 
+#include <linux/pagemap.h>
 #include <asm/tlb.h>
 #include <asm-generic/pgtable.h>
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f5d90dedebba..148c6e630df2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2083,7 +2083,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			struct zone *preferred_zone;
 
 			first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask),
-							NULL, &preferred_zone);
+						&cpuset_current_mems_allowed,
+						&preferred_zone);
 			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10);
 		}
 	}