Merge commit 'v3.0.8' into android-3.0

5 files changed, 75 insertions, 28 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 666e4e677414..14d0a6a632f6 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -120,10 +120,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 
 		ptep = pte_offset_map(pmd, addr);
 
-		if (!is_swap_pte(*ptep)) {
-			pte_unmap(ptep);
-			goto out;
-		}
+		/*
+		 * Peek to check is_swap_pte() before taking ptlock?  No, we
+		 * can race mremap's move_ptes(), which skips anon_vma lock.
+		 */
 
 		ptl = pte_lockptr(mm, pmd);
 	}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 31f698862420..955fe35d01e0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -892,12 +892,12 @@ int write_cache_pages(struct address_space *mapping,
 			range_whole = 1;
 		cycled = 1; /* ignore range_cyclic tests */
 	}
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
 retry:
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 	done_index = index;
 	while (!done && (index <= end)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a49d67285539..03d8c484d0bc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1631,6 +1631,21 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 	set_bit(i, zlc->fullzones);
 }
 
+/*
+ * clear all zones full, called after direct reclaim makes progress so that
+ * a zone that was recently full is not skipped over for up to a second
+ */
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
+
+	zlc = zonelist->zlcache_ptr;
+	if (!zlc)
+		return;
+
+	bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+}
+
 #else	/* CONFIG_NUMA */
 
 static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
@@ -1647,6 +1662,10 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
 static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 {
 }
+
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+}
 #endif	/* CONFIG_NUMA */
 
 /*
@@ -1679,7 +1698,7 @@ zonelist_scan:
 				continue;
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
-				goto try_next_zone;
+				continue;
 
 		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
@@ -1691,17 +1710,36 @@ zonelist_scan:
 				    classzone_idx, alloc_flags))
 				goto try_this_zone;
 
+			if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+				/*
+				 * we do zlc_setup if there are multiple nodes
+				 * and before considering the first zone allowed
+				 * by the cpuset.
+				 */
+				allowednodes = zlc_setup(zonelist, alloc_flags);
+				zlc_active = 1;
+				did_zlc_setup = 1;
+			}
+
 			if (zone_reclaim_mode == 0)
 				goto this_zone_full;
 
+			/*
+			 * As we may have just activated ZLC, check if the first
+			 * eligible zone has failed zone_reclaim recently.
+			 */
+			if (NUMA_BUILD && zlc_active &&
+				!zlc_zone_worth_trying(zonelist, z, allowednodes))
+				continue;
+
 			ret = zone_reclaim(zone, gfp_mask, order);
 			switch (ret) {
 			case ZONE_RECLAIM_NOSCAN:
 				/* did not scan */
-				goto try_next_zone;
+				continue;
 			case ZONE_RECLAIM_FULL:
 				/* scanned but unreclaimable */
-				goto this_zone_full;
+				continue;
 			default:
 				/* did we reclaim enough */
 				if (!zone_watermark_ok(zone, order, mark,
@@ -1718,16 +1756,6 @@ try_this_zone:
 this_zone_full:
 		if (NUMA_BUILD)
 			zlc_mark_zone_full(zonelist, z);
-try_next_zone:
-		if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
-			/*
-			 * we do zlc_setup after the first zone is tried but only
-			 * if there are multiple nodes make it worthwhile
-			 */
-			allowednodes = zlc_setup(zonelist, alloc_flags);
-			zlc_active = 1;
-			did_zlc_setup = 1;
-		}
 	}
 
 	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
@@ -1969,6 +1997,10 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!(*did_some_progress)))
 		return NULL;
 
+	/* After successful reclaim, reconsider all zones for allocation */
+	if (NUMA_BUILD)
+		zlc_clear_zones_full(zonelist);
+
 retry:
 	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1d34d75366a7..45ece8967e47 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -732,9 +732,10 @@ static void free_unmap_vmap_area_addr(unsigned long addr)
 #define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
 #define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
 #define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
-#define VMAP_BBMAP_BITS		VMAP_MIN(VMAP_BBMAP_BITS_MAX,		\
-					VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
-						VMALLOC_PAGES / NR_CPUS / 16))
+#define VMAP_BBMAP_BITS		\
+		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
+		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
+			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
 
 #define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
 
@@ -2153,6 +2154,14 @@ struct vm_struct *alloc_vm_area(size_t size)
 		return NULL;
 	}
 
+	/*
+	 * If the allocated address space is passed to a hypercall
+	 * before being used then we cannot rely on a page fault to
+	 * trigger an update of the page tables.  So sync all the page
+	 * tables here.
+	 */
+	vmalloc_sync_all();
+
 	return area;
 }
 EXPORT_SYMBOL_GPL(alloc_vm_area);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d036e59d302b..6072d74a16f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1748,6 +1748,7 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	enum lru_list l;
 	int noswap = 0;
 	int force_scan = 0;
+	unsigned long nr_force_scan[2];
 
 
 	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
@@ -1770,6 +1771,8 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		fraction[0] = 0;
 		fraction[1] = 1;
 		denominator = 1;
+		nr_force_scan[0] = 0;
+		nr_force_scan[1] = SWAP_CLUSTER_MAX;
 		goto out;
 	}
 
@@ -1781,6 +1784,8 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 			fraction[0] = 1;
 			fraction[1] = 0;
 			denominator = 1;
+			nr_force_scan[0] = SWAP_CLUSTER_MAX;
+			nr_force_scan[1] = 0;
 			goto out;
 		}
 	}
@@ -1829,6 +1834,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	fraction[0] = ap;
 	fraction[1] = fp;
 	denominator = ap + fp + 1;
+	if (force_scan) {
+		unsigned long scan = SWAP_CLUSTER_MAX;
+		nr_force_scan[0] = div64_u64(scan * ap, denominator);
+		nr_force_scan[1] = div64_u64(scan * fp, denominator);
+	}
 out:
 	for_each_evictable_lru(l) {
 		int file = is_file_lru(l);
@@ -1849,12 +1859,8 @@ out:
 		 * memcg, priority drop can cause big latency. So, it's better
 		 * to scan small amount. See may_noscan above.
 		 */
-		if (!scan && force_scan) {
-			if (file)
-				scan = SWAP_CLUSTER_MAX;
-			else if (!noswap)
-				scan = SWAP_CLUSTER_MAX;
-		}
+		if (!scan && force_scan)
+			scan = nr_force_scan[file];
 		nr[l] = scan;
 	}
 }