Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 78 insertions, 57 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c7ea45..6ce2733 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -321,6 +321,7 @@ static void bad_page(struct page *page)
 		current->comm, page_to_pfn(page));
 	dump_page(page);
 
+	print_modules();
 	dump_stack();
 out:
 	/* Leave bad fields for debug, except PageBuddy could make trouble */
@@ -1373,21 +1374,12 @@ failed:
 
 #ifdef CONFIG_FAIL_PAGE_ALLOC
 
-static struct fail_page_alloc_attr {
+static struct {
 	struct fault_attr attr;
 
 	u32 ignore_gfp_highmem;
 	u32 ignore_gfp_wait;
 	u32 min_order;
-
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-
-	struct dentry *ignore_gfp_highmem_file;
-	struct dentry *ignore_gfp_wait_file;
-	struct dentry *min_order_file;
-
-#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
-
 } fail_page_alloc = {
 	.attr = FAULT_ATTR_INITIALIZER,
 	.ignore_gfp_wait = 1,
@@ -1421,36 +1413,27 @@ static int __init fail_page_alloc_debugfs(void)
 {
 	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
 	struct dentry *dir;
-	int err;
-
-	err = init_fault_attr_dentries(&fail_page_alloc.attr,
-				       "fail_page_alloc");
-	if (err)
-		return err;
-	dir = fail_page_alloc.attr.dentries.dir;
-
-	fail_page_alloc.ignore_gfp_wait_file =
-		debugfs_create_bool("ignore-gfp-wait", mode, dir,
-				      &fail_page_alloc.ignore_gfp_wait);
-
-	fail_page_alloc.ignore_gfp_highmem_file =
-		debugfs_create_bool("ignore-gfp-highmem", mode, dir,
-				      &fail_page_alloc.ignore_gfp_highmem);
-	fail_page_alloc.min_order_file =
-		debugfs_create_u32("min-order", mode, dir,
-				   &fail_page_alloc.min_order);
-
-	if (!fail_page_alloc.ignore_gfp_wait_file ||
-            !fail_page_alloc.ignore_gfp_highmem_file ||
-            !fail_page_alloc.min_order_file) {
-		err = -ENOMEM;
-		debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
-		debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
-		debugfs_remove(fail_page_alloc.min_order_file);
-		cleanup_fault_attr_dentries(&fail_page_alloc.attr);
-	}
 
-	return err;
+	dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
+					&fail_page_alloc.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				&fail_page_alloc.ignore_gfp_wait))
+		goto fail;
+	if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+				&fail_page_alloc.ignore_gfp_highmem))
+		goto fail;
+	if (!debugfs_create_u32("min-order", mode, dir,
+				&fail_page_alloc.min_order))
+		goto fail;
+
+	return 0;
+fail:
+	debugfs_remove_recursive(dir);
+
+	return -ENOMEM;
 }
 
 late_initcall(fail_page_alloc_debugfs);
@@ -1619,6 +1602,21 @@ 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)
@@ -1635,6 +1633,10 @@ 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 */
 
 /*
@@ -1667,7 +1669,7 @@ 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)) {
@@ -1679,17 +1681,36 @@ 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,
@@ -1706,16 +1727,6 @@ 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)) {
@@ -1746,7 +1757,6 @@ static DEFINE_RATELIMIT_STATE(nopage_rs,
 
 void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 {
-	va_list args;
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
 
 	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
@@ -1765,14 +1775,21 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 		filter &= ~SHOW_MEM_FILTER_NODES;
 
 	if (fmt) {
-		printk(KERN_WARNING);
+		struct va_format vaf;
+		va_list args;
+
 		va_start(args, fmt);
-		vprintk(fmt, args);
+
+		vaf.fmt = fmt;
+		vaf.va = &args;
+
+		pr_warn("%pV", &vaf);
+
 		va_end(args);
 	}
 
-	pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n",
-		   current->comm, order, gfp_mask);
+	pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
+		current->comm, order, gfp_mask);
 
 	dump_stack();
 	if (!should_suppress_show_mem())
@@ -1957,6 +1974,10 @@ __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,