summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2017-09-06 16:20:37 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-06 17:27:26 -0700
commitb93e0f329e24f3615aa551fd9b99a75fb7c9195f (patch)
tree3b6e1cade48a38d71456258f634ce868fa7dd20d /mm/page_alloc.c
parent11cd8638c37f6c400cc472cc52b6eccb505aba6e (diff)
downloadlinux-stable-b93e0f329e24f3615aa551fd9b99a75fb7c9195f.tar.gz
linux-stable-b93e0f329e24f3615aa551fd9b99a75fb7c9195f.tar.bz2
linux-stable-b93e0f329e24f3615aa551fd9b99a75fb7c9195f.zip
mm, memory_hotplug: get rid of zonelists_mutex
zonelists_mutex was introduced by commit 4eaf3f64397c ("mem-hotplug: fix potential race while building zonelist for new populated zone") to protect zonelist building from races. This is no longer needed though because both memory online and offline are fully serialized. New users have grown since then. Notably setup_per_zone_wmarks wants to prevent from races between memory hotplug, khugepaged setup and manual min_free_kbytes update via sysctl (see cfd3da1e49bb ("mm: Serialize access to min_free_kbytes"). Let's add a private lock for that purpose. This will not prevent from seeing halfway through memory hotplug operation but that shouldn't be a big deal becuse memory hotplug will update watermarks explicitly so we will eventually get a full picture. The lock just makes sure we won't race when updating watermarks leading to weird results. Also __build_all_zonelists manipulates global data so add a private lock for it as well. This doesn't seem to be necessary today but it is more robust to have a lock there. While we are at it make sure we document that memory online/offline depends on a full serialization either via mem_hotplug_begin() or device_lock. Link: http://lkml.kernel.org/r/20170721143915.14161-9-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Haicheng Li <haicheng.li@linux.intel.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c18
1 files changed, 9 insertions, 9 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3086d0fd945..0bea94af0423 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5131,17 +5131,14 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
-/*
- * Global mutex to protect against size modification of zonelists
- * as well as to serialize pageset setup for the new populated zone.
- */
-DEFINE_MUTEX(zonelists_mutex);
-
static void __build_all_zonelists(void *data)
{
int nid;
int __maybe_unused cpu;
pg_data_t *self = data;
+ static DEFINE_SPINLOCK(lock);
+
+ spin_lock(&lock);
#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
@@ -5173,6 +5170,8 @@ static void __build_all_zonelists(void *data)
set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
}
+
+ spin_unlock(&lock);
}
static noinline void __init
@@ -5203,7 +5202,6 @@ build_all_zonelists_init(void)
}
/*
- * Called with zonelists_mutex held always
* unless system_state == SYSTEM_BOOTING.
*
* __ref due to call of __init annotated helper build_all_zonelists_init
@@ -6939,9 +6937,11 @@ static void __setup_per_zone_wmarks(void)
*/
void setup_per_zone_wmarks(void)
{
- mutex_lock(&zonelists_mutex);
+ static DEFINE_SPINLOCK(lock);
+
+ spin_lock(&lock);
__setup_per_zone_wmarks();
- mutex_unlock(&zonelists_mutex);
+ spin_unlock(&lock);
}
/*