summaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorJiri Kosina <jkosina@suse.cz>2011-04-26 10:22:15 +0200
committerJiri Kosina <jkosina@suse.cz>2011-04-26 10:22:59 +0200
commit07f9479a40cc778bc1462ada11f95b01360ae4ff (patch)
tree0676cf38df3844004bb3ebfd99dfa67a4a8998f5 /mm/page_alloc.c
parent9d5e6bdb3013acfb311ab407eeca0b6a6a3dedbf (diff)
parentcd2e49e90f1cae7726c9a2c54488d881d7f1cd1c (diff)
downloadlinux-3.10-07f9479a40cc778bc1462ada11f95b01360ae4ff.tar.gz
linux-3.10-07f9479a40cc778bc1462ada11f95b01360ae4ff.tar.bz2
linux-3.10-07f9479a40cc778bc1462ada11f95b01360ae4ff.zip
Merge branch 'master' into for-next
Fast-forwarded to current state of Linus' tree as there are patches to be applied for files that didn't exist on the old branch.
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c95
1 files changed, 81 insertions, 14 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48c9737ad49..df9fc3385fb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -53,6 +53,7 @@
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <linux/ftrace_event.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -565,7 +566,8 @@ static inline int free_pages_check(struct page *page)
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE) |
+ (mem_cgroup_bad_page_check(page)))) {
bad_page(page);
return 1;
}
@@ -614,6 +616,10 @@ static void free_pcppages_bulk(struct zone *zone, int count,
list = &pcp->lists[migratetype];
} while (list_empty(list));
+ /* This is the only non-empty list. Free them all. */
+ if (batch_free == MIGRATE_PCPTYPES)
+ batch_free = to_free;
+
do {
page = list_entry(list->prev, struct page, lru);
/* must delete as __free_one_page list manipulates */
@@ -750,7 +756,8 @@ static inline int check_new_page(struct page *page)
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP) |
+ (mem_cgroup_bad_page_check(page)))) {
bad_page(page);
return 1;
}
@@ -863,9 +870,8 @@ static int move_freepages(struct zone *zone,
}
order = page_order(page);
- list_del(&page->lru);
- list_add(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
+ list_move(&page->lru,
+ &zone->free_area[order].free_list[migratetype]);
page += 1 << order;
pages_moved += 1 << order;
}
@@ -936,7 +942,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
* If breaking a large block of pages, move all free
* pages to the preferred allocation list. If falling
* back for a reclaimable kernel allocation, be more
- * agressive about taking ownership of free pages
+ * aggressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
start_migratetype == MIGRATE_RECLAIMABLE ||
@@ -1333,7 +1339,7 @@ again:
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
- zone_statistics(preferred_zone, zone);
+ zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
VM_BUG_ON(bad_range(zone, page));
@@ -1714,6 +1720,20 @@ try_next_zone:
return page;
}
+/*
+ * Large machines with many possible nodes should not always dump per-node
+ * meminfo in irq context.
+ */
+static inline bool should_suppress_show_mem(void)
+{
+ bool ret = false;
+
+#if NODES_SHIFT > 8
+ ret = in_interrupt();
+#endif
+ return ret;
+}
+
static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
unsigned long pages_reclaimed)
@@ -2085,7 +2105,7 @@ rebalance:
sync_migration);
if (page)
goto got_pg;
- sync_migration = true;
+ sync_migration = !(gfp_mask & __GFP_NO_KSWAPD);
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
@@ -2157,11 +2177,25 @@ rebalance:
nopage:
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
- printk(KERN_WARNING "%s: page allocation failure."
- " order:%d, mode:0x%x\n",
+ unsigned int filter = SHOW_MEM_FILTER_NODES;
+
+ /*
+ * This documents exceptions given to allocations in certain
+ * contexts that are allowed to allocate outside current's set
+ * of allowed nodes.
+ */
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
+ if (test_thread_flag(TIF_MEMDIE) ||
+ (current->flags & (PF_MEMALLOC | PF_EXITING)))
+ filter &= ~SHOW_MEM_FILTER_NODES;
+ if (in_interrupt() || !wait)
+ filter &= ~SHOW_MEM_FILTER_NODES;
+
+ pr_warning("%s: page allocation failure. order:%d, mode:0x%x\n",
current->comm, order, gfp_mask);
dump_stack();
- show_mem();
+ if (!should_suppress_show_mem())
+ show_mem(filter);
}
return page;
got_pg:
@@ -2411,19 +2445,42 @@ void si_meminfo_node(struct sysinfo *val, int nid)
}
#endif
+/*
+ * Determine whether the zone's node should be displayed or not, depending on
+ * whether SHOW_MEM_FILTER_NODES was passed to __show_free_areas().
+ */
+static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
+{
+ bool ret = false;
+
+ if (!(flags & SHOW_MEM_FILTER_NODES))
+ goto out;
+
+ get_mems_allowed();
+ ret = !node_isset(zone->zone_pgdat->node_id,
+ cpuset_current_mems_allowed);
+ put_mems_allowed();
+out:
+ return ret;
+}
+
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* Show free area list (used inside shift_scroll-lock stuff)
* We also calculate the percentage fragmentation. We do this by counting the
* memory on each free list with the exception of the first item on the list.
+ * Suppresses nodes that are not allowed by current's cpuset if
+ * SHOW_MEM_FILTER_NODES is passed.
*/
-void show_free_areas(void)
+void __show_free_areas(unsigned int filter)
{
int cpu;
struct zone *zone;
for_each_populated_zone(zone) {
+ if (skip_free_areas_zone(filter, zone))
+ continue;
show_node(zone);
printk("%s per-cpu:\n", zone->name);
@@ -2465,6 +2522,8 @@ void show_free_areas(void)
for_each_populated_zone(zone) {
int i;
+ if (skip_free_areas_zone(filter, zone))
+ continue;
show_node(zone);
printk("%s"
" free:%lukB"
@@ -2532,6 +2591,8 @@ void show_free_areas(void)
for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ if (skip_free_areas_zone(filter, zone))
+ continue;
show_node(zone);
printk("%s: ", zone->name);
@@ -2551,6 +2612,11 @@ void show_free_areas(void)
show_swap_cache_info();
}
+void show_free_areas(void)
+{
+ __show_free_areas(0);
+}
+
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
@@ -3110,7 +3176,7 @@ static __init_refok int __build_all_zonelists(void *data)
* Called with zonelists_mutex held always
* unless system_state == SYSTEM_BOOTING.
*/
-void build_all_zonelists(void *data)
+void __ref build_all_zonelists(void *data)
{
set_zonelist_order();
@@ -3860,7 +3926,7 @@ static void __init find_usable_zone_for_movable(void)
/*
* The zone ranges provided by the architecture do not include ZONE_MOVABLE
- * because it is sized independant of architecture. Unlike the other zones,
+ * because it is sized independent of architecture. Unlike the other zones,
* the starting point for ZONE_MOVABLE is not fixed. It may be different
* in each node depending on the size of each node and how evenly kernelcore
* is distributed. This helper function adjusts the zone ranges
@@ -5621,4 +5687,5 @@ void dump_page(struct page *page)
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
dump_page_flags(page->flags);
+ mem_cgroup_print_bad_page(page);
}