1 files changed, 73 insertions, 29 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a13ded1938f0..a712fb9e04ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1161,11 +1161,47 @@ void drain_local_pages(void *arg)
 }
 
 /*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
  */
 void drain_all_pages(void)
 {
-	on_each_cpu(drain_local_pages, NULL, 1);
+	int cpu;
+	struct per_cpu_pageset *pcp;
+	struct zone *zone;
+
+	/*
+	 * Allocate in the BSS so we wont require allocation in
+	 * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+	 */
+	static cpumask_t cpus_with_pcps;
+
+	/*
+	 * We don't care about racing with CPU hotplug event
+	 * as offline notification will cause the notified
+	 * cpu to drain that CPU pcps and on_each_cpu_mask
+	 * disables preemption as part of its processing
+	 */
+	for_each_online_cpu(cpu) {
+		bool has_pcps = false;
+		for_each_populated_zone(zone) {
+			pcp = per_cpu_ptr(zone->pageset, cpu);
+			if (pcp->pcp.count) {
+				has_pcps = true;
+				break;
+			}
+		}
+		if (has_pcps)
+			cpumask_set_cpu(cpu, &cpus_with_pcps);
+		else
+			cpumask_clear_cpu(cpu, &cpus_with_pcps);
+	}
+	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1968,7 +2004,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	out_of_memory(zonelist, gfp_mask, order, nodemask);
+	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
 
 out:
 	clear_zonelist_oom(zonelist, gfp_mask);
@@ -1990,7 +2026,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	if (!order)
 		return NULL;
 
-	if (compaction_deferred(preferred_zone)) {
+	if (compaction_deferred(preferred_zone, order)) {
 		*deferred_compaction = true;
 		return NULL;
 	}
@@ -2012,6 +2048,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		if (page) {
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
+			if (order >= preferred_zone->compact_order_failed)
+				preferred_zone->compact_order_failed = order + 1;
 			count_vm_event(COMPACTSUCCESS);
 			return page;
 		}
@@ -2028,7 +2066,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * defer if the failure was a sync compaction failure.
 		 */
 		if (sync_migration)
-			defer_compaction(preferred_zone);
+			defer_compaction(preferred_zone, order);
 
 		cond_resched();
 	}
@@ -2306,6 +2344,10 @@ rebalance:
 		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
 			if (oom_killer_disabled)
 				goto nopage;
+			/* Coredumps can quickly deplete all memory reserves */
+			if ((current->flags & PF_DUMPCORE) &&
+			    !(gfp_mask & __GFP_NOFAIL))
+				goto nopage;
 			page = __alloc_pages_may_oom(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask, preferred_zone,
@@ -2378,8 +2420,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
-	struct page *page;
+	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
+	unsigned int cpuset_mems_cookie;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2398,15 +2441,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
-	if (!preferred_zone) {
-		put_mems_allowed();
-		return NULL;
-	}
+	if (!preferred_zone)
+		goto out;
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2416,9 +2459,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+	/*
+	 * When updating a task's mems_allowed, it is possible to race with
+	 * parallel threads in such a way that an allocation can fail while
+	 * the mask is being updated. If a page allocation is about to fail,
+	 * check if the cpuset changed during allocation and if so, retry.
+	 */
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2632,13 +2685,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
+	unsigned int cpuset_mems_cookie;
 
 	if (!(flags & SHOW_MEM_FILTER_NODES))
 		goto out;
 
-	get_mems_allowed();
-	ret = !node_isset(nid, cpuset_current_mems_allowed);
-	put_mems_allowed();
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		ret = !node_isset(nid, cpuset_current_mems_allowed);
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -3925,18 +3980,6 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
 	}
 }
 
-int __init add_from_early_node_map(struct range *range, int az,
-				   int nr_range, int nid)
-{
-	unsigned long start_pfn, end_pfn;
-	int i;
-
-	/* need to go over early_node_map to find out good range for node */
-	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL)
-		nr_range = add_range(range, az, nr_range, start_pfn, end_pfn);
-	return nr_range;
-}
-
 /**
  * sparse_memory_present_with_active_regions - Call memory_present for each active range
  * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
@@ -4521,7 +4564,7 @@ static unsigned long __init early_calculate_totalpages(void)
  * memory. When they don't, some nodes will have more kernelcore than
  * others
  */
-static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+static void __init find_zone_movable_pfns_for_nodes(void)
 {
 	int i, nid;
 	unsigned long usable_startpfn;
@@ -4713,7 +4756,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
 	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
-	find_zone_movable_pfns_for_nodes(zone_movable_pfn);
+	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
 	printk("Zone PFN ranges:\n");
@@ -4823,6 +4866,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 	int cpu = (unsigned long)hcpu;
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		lru_add_drain_cpu(cpu);
 		drain_pages(cpu);
 
 		/*