| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <084beda24a5c03fc81a6100ccdc6f78af7b13cf3.1382603434.git.vdavydov@parallels.com>
Date: Thu, 24 Oct 2013 16:04:54 +0400
From: Vladimir Davydov <vdavydov@...allels.com>
To: <akpm@...ux-foundation.org>
CC: <glommer@...nvz.org>, <khorenko@...allels.com>, <devel@...nvz.org>,
<linux-mm@...ck.org>, <cgroups@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, Dave Chinner <dchinner@...hat.com>,
Mel Gorman <mgorman@...e.de>, Rik van Riel <riel@...hat.com>,
Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...e.cz>, Hugh Dickins <hughd@...gle.com>,
Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Subject: [PATCH v11 03/15] vmscan: also shrink slab in memcg pressure
From: Glauber Costa <glommer@...nvz.org>
Without the surrounding infrastructure, this patch is a bit of a hammer:
it will basically shrink objects from all memcgs under memcg pressure.
At least, however, we will keep the scan limited to the shrinkers marked
as per-memcg.
Future patches will implement the in-shrinker logic to filter objects
based on its memcg association.
Signed-off-by: Glauber Costa <glommer@...nvz.org>
Cc: Dave Chinner <dchinner@...hat.com>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Rik van Riel <riel@...hat.com>
Cc: Johannes Weiner <hannes@...xchg.org>
Cc: Michal Hocko <mhocko@...e.cz>
Cc: Hugh Dickins <hughd@...gle.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
---
include/linux/memcontrol.h | 17 +++++++++++++++
include/linux/shrinker.h | 6 +++++-
mm/memcontrol.c | 16 +++++++++++++-
mm/vmscan.c | 50 +++++++++++++++++++++++++++++++++++++++-----
4 files changed, 82 insertions(+), 7 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b3e7a66..d16ba51 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -231,6 +231,9 @@ void mem_cgroup_split_huge_fixup(struct page *head);
bool mem_cgroup_bad_page_check(struct page *page);
void mem_cgroup_print_bad_page(struct page *page);
#endif
+
+unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone);
#else /* CONFIG_MEMCG */
struct mem_cgroup;
@@ -427,6 +430,12 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
struct page *newpage)
{
}
+
+static inline unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
+{
+ return 0;
+}
#endif /* CONFIG_MEMCG */
#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
@@ -479,6 +488,8 @@ static inline bool memcg_kmem_enabled(void)
return static_key_false(&memcg_kmem_enabled_key);
}
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+
/*
* In general, we'll do everything in our power to not incur in any overhead
* for non-memcg users for the kmem functions. Not even a function call, if we
@@ -612,6 +623,12 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
return __memcg_kmem_get_cache(cachep, gfp);
}
#else
+
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 68c0970..7d462b1 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -22,6 +22,9 @@ struct shrink_control {
nodemask_t nodes_to_scan;
/* current node being shrunk (for NUMA aware shrinkers) */
int nid;
+
+ /* reclaim from this memcg only (if not NULL) */
+ struct mem_cgroup *target_mem_cgroup;
};
#define SHRINK_STOP (~0UL)
@@ -63,7 +66,8 @@ struct shrinker {
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
/* Flags */
-#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_MEMCG_AWARE (1 << 1)
extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0a5cc30..41c216a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -356,7 +356,7 @@ static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
-static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
@@ -938,6 +938,20 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
return ret;
}
+unsigned long
+memcg_zone_reclaimable_pages(struct mem_cgroup *memcg, struct zone *zone)
+{
+ int nid = zone_to_nid(zone);
+ int zid = zone_idx(zone);
+ unsigned long val;
+
+ val = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, LRU_ALL_FILE);
+ if (do_swap_account)
+ val += mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ LRU_ALL_ANON);
+ return val;
+}
+
static unsigned long
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eea668d..652dfa3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -140,11 +140,41 @@ static bool global_reclaim(struct scan_control *sc)
{
return !sc->target_mem_cgroup;
}
+
+/*
+ * kmem reclaim should usually not be triggered when we are doing targetted
+ * reclaim. It is only valid when global reclaim is triggered, or when the
+ * underlying memcg has kmem objects.
+ */
+static bool has_kmem_reclaim(struct scan_control *sc)
+{
+ return !sc->target_mem_cgroup ||
+ memcg_kmem_is_active(sc->target_mem_cgroup);
+}
+
+static unsigned long
+zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
+{
+ if (global_reclaim(sc))
+ return zone_reclaimable_pages(zone);
+ return memcg_zone_reclaimable_pages(sc->target_mem_cgroup, zone);
+}
#else
static bool global_reclaim(struct scan_control *sc)
{
return true;
}
+
+static bool has_kmem_reclaim(struct scan_control *sc)
+{
+ return true;
+}
+
+static unsigned long
+zone_nr_reclaimable_pages(struct scan_control *sc, struct zone *zone)
+{
+ return zone_reclaimable_pages(zone);
+}
#endif
unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -352,6 +382,15 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
}
list_for_each_entry(shrinker, &shrinker_list, list) {
+ /*
+ * If we don't have a target mem cgroup, we scan them all.
+ * Otherwise we will limit our scan to shrinkers marked as
+ * memcg aware
+ */
+ if (shrinkctl->target_mem_cgroup &&
+ !(shrinker->flags & SHRINKER_MEMCG_AWARE))
+ continue;
+
for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
if (!node_online(shrinkctl->nid))
continue;
@@ -2399,11 +2438,11 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
/*
* Don't shrink slabs when reclaiming memory from over limit
- * cgroups but do shrink slab at least once when aborting
- * reclaim for compaction to avoid unevenly scanning file/anon
- * LRU pages over slab pages.
+ * cgroups unless we know they have kmem objects. But do shrink
+ * slab at least once when aborting reclaim for compaction to
+ * avoid unevenly scanning file/anon LRU pages over slab pages.
*/
- if (global_reclaim(sc)) {
+ if (has_kmem_reclaim(sc)) {
unsigned long lru_pages = 0;
nodes_clear(shrink->nodes_to_scan);
@@ -2412,7 +2451,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- lru_pages += zone_reclaimable_pages(zone);
+ lru_pages += zone_nr_reclaimable_pages(sc, zone);
node_set(zone_to_nid(zone),
shrink->nodes_to_scan);
}
@@ -2669,6 +2708,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
+ .target_mem_cgroup = memcg,
};
/*
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists