From e767e0561d7fd2333df1921f1ab4176211f9036b Mon Sep 17 00:00:00 2001
From: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Date: Thu, 28 May 2009 14:34:28 -0700
Subject: memcg: fix deadlock between lock_page_cgroup and mapping tree_lock
mapping->tree_lock can be acquired from interrupt context. Then,
following dead lock can occur.
Assume "A" as a page.
CPU0:
lock_page_cgroup(A)
interrupted
-> take mapping->tree_lock.
CPU1:
take mapping->tree_lock
-> lock_page_cgroup(A)
This patch tries to fix above deadlock by moving memcg's hook to out of
mapping->tree_lock. charge/uncharge of pagecache/swapcache is protected
by page lock, not tree_lock.
After this patch, lock_page_cgroup() is not called under mapping->tree_lock.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/memcontrol.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
(limited to 'mm/memcontrol.c')
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 01c2d8f1468..4a747a27a22 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1488,8 +1488,9 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}
+#ifdef CONFIG_SWAP
/*
- * called from __delete_from_swap_cache() and drop "page" account.
+ * called after __delete_from_swap_cache() and drop "page" account.
* memcg information is recorded to swap_cgroup of "ent"
*/
void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
@@ -1506,6 +1507,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
if (memcg)
css_put(&memcg->css);
}
+#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/*
--
cgit v1.2.3-70-g09d2
From 46f7e602fb32e02145ef14f8c0ca6d399f0a96b9 Mon Sep 17 00:00:00 2001
From: Nikanth Karthikesan <knikanth@suse.de>
Date: Thu, 28 May 2009 14:34:41 -0700
Subject: memcg: fix build warning and avoid checking for mem != null again and
again
Fix build warning, "mem_cgroup_is_obsolete defined but not used" when
CONFIG_DEBUG_VM is not set. Also avoid checking for !mem again and again.
Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/memcontrol.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
(limited to 'mm/memcontrol.c')
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4a747a27a22..78eb8552818 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -314,14 +314,6 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
return mem;
}
-static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
-{
- if (!mem)
- return true;
- return css_is_removed(&mem->css);
-}
-
-
/*
* Call callback function against all cgroup under hierarchy tree.
*/
@@ -932,7 +924,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
if (unlikely(!mem))
return 0;
- VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem));
+ VM_BUG_ON(css_is_removed(&mem->css));
while (1) {
int ret;
--
cgit v1.2.3-70-g09d2
From 56e49d218890f49b0057710a4b6fef31f5ffbfec Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Tue, 16 Jun 2009 15:32:28 -0700
Subject: vmscan: evict use-once pages first
When the file LRU lists are dominated by streaming IO pages, evict those
pages first, before considering evicting other pages.
This should be safe from deadlocks or performance problems
because only three things can happen to an inactive file page:
1) referenced twice and promoted to the active list
2) evicted by the pageout code
3) under IO, after which it will get evicted or promoted
The pages freed in this way can either be reused for streaming IO, or
allocated for something else. If the pages are used for streaming IO,
this pageout pattern continues. Otherwise, we will fall back to the
normal pageout pattern.
Signed-off-by: Rik van Riel <riel@redhat.com>
Reported-by: Elladan <elladan@eskimo.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/memcontrol.h | 7 +++++++
mm/memcontrol.c | 11 +++++++++++
mm/vmscan.c | 38 +++++++++++++++++++++++++++++++++++++-
3 files changed, 55 insertions(+), 1 deletion(-)
(limited to 'mm/memcontrol.c')
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 25b9ca93d23..45add35dda1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -94,6 +94,7 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
int priority);
int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
struct zone *zone,
enum lru_list lru);
@@ -239,6 +240,12 @@ mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
return 1;
}
+static inline int
+mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+{
+ return 1;
+}
+
static inline unsigned long
mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone,
enum lru_list lru)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 78eb8552818..70db6e0a5ee 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -570,6 +570,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
return 0;
}
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+{
+ unsigned long active;
+ unsigned long inactive;
+
+ inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE);
+ active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE);
+
+ return (active > inactive);
+}
+
unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
struct zone *zone,
enum lru_list lru)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5245d05164..9673437a545 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1351,12 +1351,48 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
return low;
}
+static int inactive_file_is_low_global(struct zone *zone)
+{
+ unsigned long active, inactive;
+
+ active = zone_page_state(zone, NR_ACTIVE_FILE);
+ inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+ return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc: scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+ int low;
+
+ if (scanning_global_lru(sc))
+ low = inactive_file_is_low_global(zone);
+ else
+ low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+ return low;
+}
+
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct zone *zone, struct scan_control *sc, int priority)
{
int file = is_file_lru(lru);
- if (lru == LRU_ACTIVE_FILE) {
+ if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
--
cgit v1.2.3-70-g09d2