summaryrefslogtreecommitdiff
path: root/mm/memory_hotplug.c
diff options
context:
space:
mode:
authorHaicheng Li <haicheng.li@linux.intel.com>2010-05-24 14:32:52 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-25 08:07:02 -0700
commit4eaf3f64397c3db3c5785eee508270d62a9fabd9 (patch)
treebfd986a7e974876755ea6fe0de394199c68e2e36 /mm/memory_hotplug.c
parent1f522509c77a5dea8dc384b735314f03908a6415 (diff)
downloadlwn-4eaf3f64397c3db3c5785eee508270d62a9fabd9.tar.gz
lwn-4eaf3f64397c3db3c5785eee508270d62a9fabd9.zip
mem-hotplug: fix potential race while building zonelist for new populated zone
Add global mutex zonelists_mutex to fix the possible race: CPU0 CPU1 CPU2 (1) zone->present_pages += online_pages; (2) build_all_zonelists(); (3) alloc_page(); (4) free_page(); (5) build_all_zonelists(); (6) __build_all_zonelists(); (7) zone->pageset = alloc_percpu(); In step (3,4), zone->pageset still points to boot_pageset, so bad things may happen if 2+ nodes are in this state. Even if only 1 node is accessing the boot_pageset, (3) may still consume too much memory to fail the memory allocations in step (7). Besides, atomic operation ensures alloc_percpu() in step (7) will never fail since there is a new fresh memory block added in step(6). [haicheng.li@linux.intel.com: hold zonelists_mutex when build_all_zonelists] Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Andi Kleen <andi.kleen@intel.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memory_hotplug.c')
-rw-r--r--mm/memory_hotplug.c11
1 files changed, 3 insertions, 8 deletions
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 089cc97aed3c..a4cfcdc00455 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
int nid;
int ret;
struct memory_notify arg;
- /*
- * mutex to protect zone->pageset when it's still shared
- * in onlined_pages()
- */
- static DEFINE_MUTEX(zone_pageset_mutex);
arg.start_pfn = pfn;
arg.nr_pages = nr_pages;
@@ -420,14 +415,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
* This means the page allocator ignores this zone.
* So, zonelist must be updated after online.
*/
- mutex_lock(&zone_pageset_mutex);
+ mutex_lock(&zonelists_mutex);
if (!populated_zone(zone))
need_zonelists_rebuild = 1;
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
online_pages_range);
if (ret) {
- mutex_unlock(&zone_pageset_mutex);
+ mutex_unlock(&zonelists_mutex);
printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
nr_pages, pfn);
memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -441,7 +436,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
else
zone_pcp_update(zone);
- mutex_unlock(&zone_pageset_mutex);
+ mutex_unlock(&zonelists_mutex);
setup_per_zone_wmarks();
calculate_zone_inactive_ratio(zone);
if (onlined_pages) {