1 files changed, 38 insertions, 19 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8d088371196a..3974fd81d27c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -42,13 +42,13 @@
  * MCD - HACK: Find somewhere to initialize this EARLY, or make this
  * initializer cleaner
  */
-nodemask_t node_online_map = { { [0] = 1UL } };
+nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
 EXPORT_SYMBOL(node_online_map);
-nodemask_t node_possible_map = NODE_MASK_ALL;
+nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
 EXPORT_SYMBOL(node_possible_map);
-struct pglist_data *pgdat_list;
-unsigned long totalram_pages;
-unsigned long totalhigh_pages;
+struct pglist_data *pgdat_list __read_mostly;
+unsigned long totalram_pages __read_mostly;
+unsigned long totalhigh_pages __read_mostly;
 long nr_swap_pages;
 
 /*
@@ -68,7 +68,7 @@ EXPORT_SYMBOL(nr_swap_pages);
  * Used by page_zone() to look up the address of the struct zone whose
  * id is encoded in the upper bits of page->flags
  */
-struct zone *zone_table[1 << ZONETABLE_SHIFT];
+struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
 EXPORT_SYMBOL(zone_table);
 
 static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
@@ -329,7 +329,7 @@ static inline void free_pages_check(const char *function, struct page *page)
 			1 << PG_writeback )))
 		bad_page(function, page);
 	if (PageDirty(page))
-		ClearPageDirty(page);
+		__ClearPageDirty(page);
 }
 
 /*
@@ -806,11 +806,14 @@ __alloc_pages(unsigned int __nocast gfp_mask, unsigned int order,
 	classzone_idx = zone_idx(zones[0]);
 
 restart:
-	/* Go through the zonelist once, looking for a zone with enough free */
+	/*
+	 * Go through the zonelist once, looking for a zone with enough free.
+	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+	 */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
 		int do_reclaim = should_reclaim_zone(z, gfp_mask);
 
-		if (!cpuset_zone_allowed(z))
+		if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
 			continue;
 
 		/*
@@ -845,6 +848,7 @@ zone_reclaim_retry:
 	 *
 	 * This is the last chance, in general, before the goto nopage.
 	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
 		if (!zone_watermark_ok(z, order, z->pages_min,
@@ -852,7 +856,7 @@ zone_reclaim_retry:
 				       gfp_mask & __GFP_HIGH))
 			continue;
 
-		if (wait && !cpuset_zone_allowed(z))
+		if (wait && !cpuset_zone_allowed(z, gfp_mask))
 			continue;
 
 		page = buffered_rmqueue(z, order, gfp_mask);
@@ -867,7 +871,7 @@ zone_reclaim_retry:
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 			/* go through the zonelist yet again, ignoring mins */
 			for (i = 0; (z = zones[i]) != NULL; i++) {
-				if (!cpuset_zone_allowed(z))
+				if (!cpuset_zone_allowed(z, gfp_mask))
 					continue;
 				page = buffered_rmqueue(z, order, gfp_mask);
 				if (page)
@@ -903,7 +907,7 @@ rebalance:
 					       gfp_mask & __GFP_HIGH))
 				continue;
 
-			if (!cpuset_zone_allowed(z))
+			if (!cpuset_zone_allowed(z, gfp_mask))
 				continue;
 
 			page = buffered_rmqueue(z, order, gfp_mask);
@@ -922,7 +926,7 @@ rebalance:
 					       classzone_idx, 0, 0))
 				continue;
 
-			if (!cpuset_zone_allowed(z))
+			if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
 				continue;
 
 			page = buffered_rmqueue(z, order, gfp_mask);
@@ -1130,19 +1134,20 @@ EXPORT_SYMBOL(nr_pagecache);
 DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
 #endif
 
-void __get_page_state(struct page_state *ret, int nr)
+void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 {
 	int cpu = 0;
 
 	memset(ret, 0, sizeof(*ret));
+	cpus_and(*cpumask, *cpumask, cpu_online_map);
 
-	cpu = first_cpu(cpu_online_map);
+	cpu = first_cpu(*cpumask);
 	while (cpu < NR_CPUS) {
 		unsigned long *in, *out, off;
 
 		in = (unsigned long *)&per_cpu(page_states, cpu);
 
-		cpu = next_cpu(cpu, cpu_online_map);
+		cpu = next_cpu(cpu, *cpumask);
 
 		if (cpu < NR_CPUS)
 			prefetch(&per_cpu(page_states, cpu));
@@ -1153,19 +1158,33 @@ void __get_page_state(struct page_state *ret, int nr)
 	}
 }
 
+void get_page_state_node(struct page_state *ret, int node)
+{
+	int nr;
+	cpumask_t mask = node_to_cpumask(node);
+
+	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+	nr /= sizeof(unsigned long);
+
+	__get_page_state(ret, nr+1, &mask);
+}
+
 void get_page_state(struct page_state *ret)
 {
 	int nr;
+	cpumask_t mask = CPU_MASK_ALL;
 
 	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
 	nr /= sizeof(unsigned long);
 
-	__get_page_state(ret, nr + 1);
+	__get_page_state(ret, nr + 1, &mask);
 }
 
 void get_full_page_state(struct page_state *ret)
 {
-	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
+	cpumask_t mask = CPU_MASK_ALL;
+
+	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
 }
 
 unsigned long __read_page_state(unsigned long offset)
@@ -1909,7 +1928,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
 		zone->nr_scan_inactive = 0;
 		zone->nr_active = 0;
 		zone->nr_inactive = 0;
-		atomic_set(&zone->reclaim_in_progress, -1);
+		atomic_set(&zone->reclaim_in_progress, 0);
 		if (!size)
 			continue;