The patch titled
memcg: make resize limit hold mutex
has been removed from the -mm tree. Its filename was
memcg-memswap-controller-core-make-resize-limit-hold-mutex.patch
This patch was dropped because it was folded into memcg-memswap-controller-core.patch
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memcg: make resize limit hold mutex
From: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
mem_cgroup_resize_memsw_limit() try to hold memsw.lock while holding
res.lock, so below message is showed when trying to write
memory.memsw.limit_in_bytes file.
[ INFO: possible recursive locking detected ]
2.6.28-rc4-mm1-mmotm-2008-11-14-20-50-ef4e17ef #1
bash/4406 is trying to acquire lock:
(&counter->lock){....}, at: [<c0498408>] mem_cgroup_resize_memsw_limit+0x8d/0x113
but task is already holding lock:
(&counter->lock){....}, at: [<c04983d6>] mem_cgroup_resize_memsw_limit+0x5b/0x113
other info that might help us debug this:
1 lock held by bash/4406:
#0: (&counter->lock){....}, at: [<c04983d6>] mem_cgroup_resize_memsw_limit+0x5b/0x113
stack backtrace:
Pid: 4406, comm: bash Not tainted 2.6.28-rc4-mm1-mmotm-2008-11-14-20-50-ef4e17ef #1
Call Trace:
[<c066e60f>] ? printk+0xf/0x18
[<c044d0c0>] __lock_acquire+0xc67/0x1353
[<c044d793>] ? __lock_acquire+0x133a/0x1353
[<c044d81c>] lock_acquire+0x70/0x97
[<c0498408>] ? mem_cgroup_resize_memsw_limit+0x8d/0x113
[<c0671519>] _spin_lock_irqsave+0x3a/0x6d
[<c0498408>] ? mem_cgroup_resize_memsw_limit+0x8d/0x113
[<c0498408>] mem_cgroup_resize_memsw_limit+0x8d/0x113
[<c0518a6c>] ? memparse+0x14/0x66
[<c0498594>] mem_cgroup_write+0x4a/0x50
[<c045e063>] cgroup_file_write+0x181/0x1c6
[<c0449e43>] ? lock_release_holdtime+0x1a/0x168
[<c04ec725>] ? security_file_permission+0xf/0x11
[<c049b5f0>] ? rw_verify_area+0x76/0x97
[<c045dee2>] ? cgroup_file_write+0x0/0x1c6
[<c049bce6>] vfs_write+0x8a/0x12e
[<c049be23>] sys_write+0x3b/0x60
[<c0403867>] sysenter_do_call+0x12/0x3f
This patch define a new mutex and make both mem_cgroup_resize_limit and
mem_cgroup_memsw_resize_limit hold it to remove spin_lock_irqsave.
Signed-off-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Hugh Dickins <hugh@xxxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 46 +++++++++++++++++++++++++++++-----------------
1 file changed, 29 insertions(+), 17 deletions(-)
diff -puN mm/memcontrol.c~memcg-memswap-controller-core-make-resize-limit-hold-mutex mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-memswap-controller-core-make-resize-limit-hold-mutex
+++ a/mm/memcontrol.c
@@ -27,6 +27,7 @@
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
+#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
@@ -1189,32 +1190,43 @@ int mem_cgroup_shrink_usage(struct mm_st
return 0;
}
+static DEFINE_MUTEX(set_limit_mutex);
+
static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
- unsigned long long val)
+ unsigned long long val)
{
int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
int progress;
+ u64 memswlimit;
int ret = 0;
- if (do_swap_account) {
- if (val > memcg->memsw.limit)
- return -EINVAL;
- }
-
- while (res_counter_set_limit(&memcg->res, val)) {
+ while (retry_count) {
if (signal_pending(current)) {
ret = -EINTR;
break;
}
- if (!retry_count) {
- ret = -EBUSY;
+ /*
+ * Rather than hide all in some function, I do this in
+ * open coded manner. You see what this really does.
+ * We have to guarantee mem->res.limit < mem->memsw.limit.
+ */
+ mutex_lock(&set_limit_mutex);
+ memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+ if (memswlimit < val) {
+ ret = -EINVAL;
+ mutex_unlock(&set_limit_mutex);
break;
}
+ ret = res_counter_set_limit(&memcg->res, val);
+ mutex_unlock(&set_limit_mutex);
+
+ if (!ret)
+ break;
+
progress = try_to_free_mem_cgroup_pages(memcg,
GFP_HIGHUSER_MOVABLE, false);
- if (!progress)
- retry_count--;
+ if (!progress) retry_count--;
}
return ret;
}
@@ -1223,7 +1235,6 @@ int mem_cgroup_resize_memsw_limit(struct
unsigned long long val)
{
int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
- unsigned long flags;
u64 memlimit, oldusage, curusage;
int ret;
@@ -1240,19 +1251,20 @@ int mem_cgroup_resize_memsw_limit(struct
* open coded manner. You see what this really does.
* We have to guarantee mem->res.limit < mem->memsw.limit.
*/
- spin_lock_irqsave(&memcg->res.lock, flags);
- memlimit = memcg->res.limit;
+ mutex_lock(&set_limit_mutex);
+ memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
if (memlimit > val) {
- spin_unlock_irqrestore(&memcg->res.lock, flags);
ret = -EINVAL;
+ mutex_unlock(&set_limit_mutex);
break;
}
ret = res_counter_set_limit(&memcg->memsw, val);
- oldusage = memcg->memsw.usage;
- spin_unlock_irqrestore(&memcg->res.lock, flags);
+ mutex_unlock(&set_limit_mutex);
if (!ret)
break;
+
+ oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
try_to_free_mem_cgroup_pages(memcg, GFP_HIGHUSER_MOVABLE, true);
curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
if (curusage >= oldusage)
_
Patches currently in -mm which might be from nishimura@xxxxxxxxxxxxxxxxx are
cgroups-make-cgroup-config-a-submenu.patch
memcg-introduce-charge-commit-cancel-style-of-functions.patch
memcg-fix-gfp_mask-of-callers-of-charge.patch
memcg-simple-migration-handling.patch
memcg-do-not-recalculate-section-unnecessarily-in-init_section_page_cgroup.patch
memcg-move-all-acccounts-to-parent-at-rmdir.patch
memcg-handle-swap-caches.patch
memcg-memswap-controller-kconfig.patch
memcg-swap-cgroup-for-remembering-usage.patch
memcg-memswap-controller-core.patch
memcg-memswap-controller-core-make-resize-limit-hold-mutex.patch
memcg-memswap-controller-core-swapcache-fixes.patch
memory-cgroup-hierarchical-reclaim-v4-fix-for-hierarchical-reclaim.patch
memcg-avoid-unnecessary-system-wide-oom-killer.patch
memcg-avoid-unnecessary-system-wide-oom-killer-fix.patch
memcg-fix-reclaim-result-checks.patch
memcg-revert-gfp-mask-fix.patch
memcg-check-group-leader-fix.patch
memcg-memoryswap-controller-fix-limit-check.patch
memcg-swapout-refcnt-fix.patch
memcg-hierarchy-avoid-unnecessary-reclaim.patch
inactive_anon_is_low-move-to-vmscan.patch
mm-introduce-zone_reclaim-struct.patch
mm-add-zone-nr_pages-helper-function.patch
mm-make-get_scan_ratio-safe-for-memcg.patch
memcg-add-null-check-to-page_cgroup_zoneinfo.patch
memcg-add-inactive_anon_is_low.patch
memcg-add-mem_cgroup_zone_nr_pages.patch
memcg-add-zone_reclaim_stat.patch
memcg-remove-mem_cgroup_cal_reclaim.patch
memcg-show-reclaim-stat.patch
memcg-rename-scan-global-lru.patch
memcg-protect-prev_priority.patch
memcg-swappiness.patch
memcg-explain-details-and-test-document.patch
memcg-dont-trigger-oom-at-page-migration.patch
memcg-remove-mem_cgroup_try_charge.patch
memcg-avoid-dead-lock-caused-by-race-between-oom-and-cpuset_attach.patch
memcg-change-try_to_free_pages-to-hierarchical_reclaim.patch
memcg-fix-swap-accounting-leak-v3.patch
memcg-fix-swap-accounting-leak-doc-fix.patch
memcg-fix-double-free-and-make-refcnt-sane.patch
memcg-use-css_tryget-in-memcg.patch
memcg-use-css_tryget-in-memcg-fix.patch
memcg-fix-lru-accounting-for-swapcache-v2.patch
memcg-fix-shmems-swap-accounting.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
