* [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 1:45 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 1:45 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-mm, LKML, Minchan Kim, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
When racing between putback_lru_page and shmem_unlock happens,
progrom execution order is as follows, but clear_bit in processor #1
could be reordered right before spin_unlock of processor #1.
Then, the page would be stranded on the unevictable list.
spin_lock
SetPageLRU
spin_unlock
clear_bit(AS_UNEVICTABLE)
spin_lock
if PageLRU()
if !test_bit(AS_UNEVICTABLE)
move evictable list
smp_mb
if !test_bit(AS_UNEVICTABLE)
move evictable list
spin_unlock
But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
so this problem never happens. But it's a unexpected side effect and we should
solve this problem properly.
This patch adds a barrier after mapping_clear_unevictable.
side-note: I didn't meet this problem but just found during review.
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
---
mm/shmem.c | 1 +
mm/vmscan.c | 11 ++++++-----
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 2d35772..22cb349 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
+ smp_mb__after_clear_bit();
scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23256e8..4480f67 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -634,13 +634,14 @@ redo:
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
/*
- * When racing with an mlock clearing (page is
- * unlocked), make sure that if the other thread does
- * not observe our setting of PG_lru and fails
- * isolation, we see PG_mlocked cleared below and move
+ * When racing with an mlock or AS_UNEVICTABLE clearing
+ * (page is unlocked) make sure that if the other thread
+ * does not observe our setting of PG_lru and fails
+ * isolation/check_move_unevictable_page,
+ * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
* the page back to the evictable list.
*
- * The other side is TestClearPageMlocked().
+ * The other side is TestClearPageMlocked() or shmem_lock().
*/
smp_mb();
}
--
1.7.4.1
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 1:45 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 1:45 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-mm, LKML, Minchan Kim, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
When racing between putback_lru_page and shmem_unlock happens,
progrom execution order is as follows, but clear_bit in processor #1
could be reordered right before spin_unlock of processor #1.
Then, the page would be stranded on the unevictable list.
spin_lock
SetPageLRU
spin_unlock
clear_bit(AS_UNEVICTABLE)
spin_lock
if PageLRU()
if !test_bit(AS_UNEVICTABLE)
move evictable list
smp_mb
if !test_bit(AS_UNEVICTABLE)
move evictable list
spin_unlock
But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
so this problem never happens. But it's a unexpected side effect and we should
solve this problem properly.
This patch adds a barrier after mapping_clear_unevictable.
side-note: I didn't meet this problem but just found during review.
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
---
mm/shmem.c | 1 +
mm/vmscan.c | 11 ++++++-----
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 2d35772..22cb349 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
+ smp_mb__after_clear_bit();
scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23256e8..4480f67 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -634,13 +634,14 @@ redo:
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
/*
- * When racing with an mlock clearing (page is
- * unlocked), make sure that if the other thread does
- * not observe our setting of PG_lru and fails
- * isolation, we see PG_mlocked cleared below and move
+ * When racing with an mlock or AS_UNEVICTABLE clearing
+ * (page is unlocked) make sure that if the other thread
+ * does not observe our setting of PG_lru and fails
+ * isolation/check_move_unevictable_page,
+ * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
* the page back to the evictable list.
*
- * The other side is TestClearPageMlocked().
+ * The other side is TestClearPageMlocked() or shmem_lock().
*/
smp_mb();
}
--
1.7.4.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 1:45 ` Minchan Kim
@ 2011-09-28 2:21 ` KOSAKI Motohiro
-1 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-28 2:21 UTC (permalink / raw)
To: minchan.kim
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
(2011/09/28 10:45), Minchan Kim wrote:
> When racing between putback_lru_page and shmem_unlock happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
Do we still need this after Hannes removes scan_mapping_unevictable_pages?
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 2:21 ` KOSAKI Motohiro
0 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-28 2:21 UTC (permalink / raw)
To: minchan.kim
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
(2011/09/28 10:45), Minchan Kim wrote:
> When racing between putback_lru_page and shmem_unlock happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
Do we still need this after Hannes removes scan_mapping_unevictable_pages?
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 2:21 ` KOSAKI Motohiro
@ 2011-09-28 2:25 ` Minchan Kim
-1 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 2:25 UTC (permalink / raw)
To: KOSAKI Motohiro
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
On Wed, Sep 28, 2011 at 11:21:58AM +0900, KOSAKI Motohiro wrote:
> (2011/09/28 10:45), Minchan Kim wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
> >
> > spin_lock
> > SetPageLRU
> > spin_unlock
> > clear_bit(AS_UNEVICTABLE)
> > spin_lock
> > if PageLRU()
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > smp_mb
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > spin_unlock
> >
> > But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> > it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> > so this problem never happens. But it's a unexpected side effect and we should
> > solve this problem properly.
>
> Do we still need this after Hannes removes scan_mapping_unevictable_pages?
Hi KOSAKI,
What Hannes removes is scan_zone_unevictable_pages not scan_mapping_unevictable_pages.
--
Kinds regards,
Minchan Kim
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 2:25 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 2:25 UTC (permalink / raw)
To: KOSAKI Motohiro
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
On Wed, Sep 28, 2011 at 11:21:58AM +0900, KOSAKI Motohiro wrote:
> (2011/09/28 10:45), Minchan Kim wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
> >
> > spin_lock
> > SetPageLRU
> > spin_unlock
> > clear_bit(AS_UNEVICTABLE)
> > spin_lock
> > if PageLRU()
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > smp_mb
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > spin_unlock
> >
> > But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> > it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> > so this problem never happens. But it's a unexpected side effect and we should
> > solve this problem properly.
>
> Do we still need this after Hannes removes scan_mapping_unevictable_pages?
Hi KOSAKI,
What Hannes removes is scan_zone_unevictable_pages not scan_mapping_unevictable_pages.
--
Kinds regards,
Minchan Kim
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 2:25 ` Minchan Kim
@ 2011-09-28 2:48 ` KOSAKI Motohiro
-1 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-28 2:48 UTC (permalink / raw)
To: minchan.kim
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
(2011/09/28 11:25), Minchan Kim wrote:
> On Wed, Sep 28, 2011 at 11:21:58AM +0900, KOSAKI Motohiro wrote:
>> (2011/09/28 10:45), Minchan Kim wrote:
>>> When racing between putback_lru_page and shmem_unlock happens,
>>> progrom execution order is as follows, but clear_bit in processor #1
>>> could be reordered right before spin_unlock of processor #1.
>>> Then, the page would be stranded on the unevictable list.
>>>
>>> spin_lock
>>> SetPageLRU
>>> spin_unlock
>>> clear_bit(AS_UNEVICTABLE)
>>> spin_lock
>>> if PageLRU()
>>> if !test_bit(AS_UNEVICTABLE)
>>> move evictable list
>>> smp_mb
>>> if !test_bit(AS_UNEVICTABLE)
>>> move evictable list
>>> spin_unlock
>>>
>>> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
>>> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
>>> so this problem never happens. But it's a unexpected side effect and we should
>>> solve this problem properly.
>>
>> Do we still need this after Hannes removes scan_mapping_unevictable_pages?
>
> Hi KOSAKI,
>
> What Hannes removes is scan_zone_unevictable_pages not scan_mapping_unevictable_pages.
>
Oops, you are right.
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 2:48 ` KOSAKI Motohiro
0 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-28 2:48 UTC (permalink / raw)
To: minchan.kim
Cc: akpm, linux-mm, linux-kernel, jweiner, mel, riel, lee.schermerhorn
(2011/09/28 11:25), Minchan Kim wrote:
> On Wed, Sep 28, 2011 at 11:21:58AM +0900, KOSAKI Motohiro wrote:
>> (2011/09/28 10:45), Minchan Kim wrote:
>>> When racing between putback_lru_page and shmem_unlock happens,
>>> progrom execution order is as follows, but clear_bit in processor #1
>>> could be reordered right before spin_unlock of processor #1.
>>> Then, the page would be stranded on the unevictable list.
>>>
>>> spin_lock
>>> SetPageLRU
>>> spin_unlock
>>> clear_bit(AS_UNEVICTABLE)
>>> spin_lock
>>> if PageLRU()
>>> if !test_bit(AS_UNEVICTABLE)
>>> move evictable list
>>> smp_mb
>>> if !test_bit(AS_UNEVICTABLE)
>>> move evictable list
>>> spin_unlock
>>>
>>> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
>>> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
>>> so this problem never happens. But it's a unexpected side effect and we should
>>> solve this problem properly.
>>
>> Do we still need this after Hannes removes scan_mapping_unevictable_pages?
>
> Hi KOSAKI,
>
> What Hannes removes is scan_zone_unevictable_pages not scan_mapping_unevictable_pages.
>
Oops, you are right.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 1:45 ` Minchan Kim
@ 2011-09-28 8:14 ` Johannes Weiner
-1 siblings, 0 replies; 22+ messages in thread
From: Johannes Weiner @ 2011-09-28 8:14 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, KOSAKI Motohiro, Mel Gorman,
Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 10:45:30AM +0900, Minchan Kim wrote:
> When racing between putback_lru_page and shmem_unlock happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
>
> Cc: Johannes Weiner <jweiner@redhat.com>
> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> Cc: Mel Gorman <mel@csn.ul.ie>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
> ---
> mm/shmem.c | 1 +
> mm/vmscan.c | 11 ++++++-----
> 2 files changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 2d35772..22cb349 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
> user_shm_unlock(inode->i_size, user);
> info->flags &= ~VM_LOCKED;
> mapping_clear_unevictable(file->f_mapping);
> + smp_mb__after_clear_bit();
> scan_mapping_unevictable_pages(file->f_mapping);
I always get nervous when I see undocumented barriers. Maybe add a
teensy tiny comment here?
/*
* Ensure that a racing putback_lru_page() can see
* the pages of this mapping are evictable when we
* skip them due to !PageLRU during the scan.
*/
Or something like that. Otherwise, nice catch :-)
Acked-by: Johannes Weiner <jweiner@redhat.com>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 8:14 ` Johannes Weiner
0 siblings, 0 replies; 22+ messages in thread
From: Johannes Weiner @ 2011-09-28 8:14 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, KOSAKI Motohiro, Mel Gorman,
Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 10:45:30AM +0900, Minchan Kim wrote:
> When racing between putback_lru_page and shmem_unlock happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
>
> Cc: Johannes Weiner <jweiner@redhat.com>
> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> Cc: Mel Gorman <mel@csn.ul.ie>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
> ---
> mm/shmem.c | 1 +
> mm/vmscan.c | 11 ++++++-----
> 2 files changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 2d35772..22cb349 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
> user_shm_unlock(inode->i_size, user);
> info->flags &= ~VM_LOCKED;
> mapping_clear_unevictable(file->f_mapping);
> + smp_mb__after_clear_bit();
> scan_mapping_unevictable_pages(file->f_mapping);
I always get nervous when I see undocumented barriers. Maybe add a
teensy tiny comment here?
/*
* Ensure that a racing putback_lru_page() can see
* the pages of this mapping are evictable when we
* skip them due to !PageLRU during the scan.
*/
Or something like that. Otherwise, nice catch :-)
Acked-by: Johannes Weiner <jweiner@redhat.com>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 1:45 ` Minchan Kim
@ 2011-09-28 15:04 ` Lin Ming
-1 siblings, 0 replies; 22+ messages in thread
From: Lin Ming @ 2011-09-28 15:04 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> When racing between putback_lru_page and shmem_unlock happens,
s/shmem_unlock/shmem_lock/
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 15:04 ` Lin Ming
0 siblings, 0 replies; 22+ messages in thread
From: Lin Ming @ 2011-09-28 15:04 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> When racing between putback_lru_page and shmem_unlock happens,
s/shmem_unlock/shmem_lock/
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 8:14 ` Johannes Weiner
@ 2011-09-28 18:03 ` Minchan Kim
-1 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 18:03 UTC (permalink / raw)
To: Johannes Weiner
Cc: Andrew Morton, linux-mm, LKML, KOSAKI Motohiro, Mel Gorman,
Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 10:14:52AM +0200, Johannes Weiner wrote:
> On Wed, Sep 28, 2011 at 10:45:30AM +0900, Minchan Kim wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
> >
> > spin_lock
> > SetPageLRU
> > spin_unlock
> > clear_bit(AS_UNEVICTABLE)
> > spin_lock
> > if PageLRU()
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > smp_mb
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > spin_unlock
> >
> > But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> > it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> > so this problem never happens. But it's a unexpected side effect and we should
> > solve this problem properly.
> >
> > This patch adds a barrier after mapping_clear_unevictable.
> >
> > side-note: I didn't meet this problem but just found during review.
> >
> > Cc: Johannes Weiner <jweiner@redhat.com>
> > Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> > Cc: Mel Gorman <mel@csn.ul.ie>
> > Cc: Rik van Riel <riel@redhat.com>
> > Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> > Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
> > ---
> > mm/shmem.c | 1 +
> > mm/vmscan.c | 11 ++++++-----
> > 2 files changed, 7 insertions(+), 5 deletions(-)
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 2d35772..22cb349 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
> > user_shm_unlock(inode->i_size, user);
> > info->flags &= ~VM_LOCKED;
> > mapping_clear_unevictable(file->f_mapping);
> > + smp_mb__after_clear_bit();
> > scan_mapping_unevictable_pages(file->f_mapping);
>
> I always get nervous when I see undocumented barriers. Maybe add a
> teensy tiny comment here?
Agree. I will try it.
>
> /*
> * Ensure that a racing putback_lru_page() can see
> * the pages of this mapping are evictable when we
> * skip them due to !PageLRU during the scan.
> */
>
> Or something like that. Otherwise, nice catch :-)
>
> Acked-by: Johannes Weiner <jweiner@redhat.com>
Thanks!
--
Kind regards,
Minchan Kim
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 18:03 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 18:03 UTC (permalink / raw)
To: Johannes Weiner
Cc: Andrew Morton, linux-mm, LKML, KOSAKI Motohiro, Mel Gorman,
Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 10:14:52AM +0200, Johannes Weiner wrote:
> On Wed, Sep 28, 2011 at 10:45:30AM +0900, Minchan Kim wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
> >
> > spin_lock
> > SetPageLRU
> > spin_unlock
> > clear_bit(AS_UNEVICTABLE)
> > spin_lock
> > if PageLRU()
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > smp_mb
> > if !test_bit(AS_UNEVICTABLE)
> > move evictable list
> > spin_unlock
> >
> > But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> > it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> > so this problem never happens. But it's a unexpected side effect and we should
> > solve this problem properly.
> >
> > This patch adds a barrier after mapping_clear_unevictable.
> >
> > side-note: I didn't meet this problem but just found during review.
> >
> > Cc: Johannes Weiner <jweiner@redhat.com>
> > Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> > Cc: Mel Gorman <mel@csn.ul.ie>
> > Cc: Rik van Riel <riel@redhat.com>
> > Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> > Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
> > ---
> > mm/shmem.c | 1 +
> > mm/vmscan.c | 11 ++++++-----
> > 2 files changed, 7 insertions(+), 5 deletions(-)
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 2d35772..22cb349 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -1068,6 +1068,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
> > user_shm_unlock(inode->i_size, user);
> > info->flags &= ~VM_LOCKED;
> > mapping_clear_unevictable(file->f_mapping);
> > + smp_mb__after_clear_bit();
> > scan_mapping_unevictable_pages(file->f_mapping);
>
> I always get nervous when I see undocumented barriers. Maybe add a
> teensy tiny comment here?
Agree. I will try it.
>
> /*
> * Ensure that a racing putback_lru_page() can see
> * the pages of this mapping are evictable when we
> * skip them due to !PageLRU during the scan.
> */
>
> Or something like that. Otherwise, nice catch :-)
>
> Acked-by: Johannes Weiner <jweiner@redhat.com>
Thanks!
--
Kind regards,
Minchan Kim
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 15:04 ` Lin Ming
@ 2011-09-28 18:05 ` Minchan Kim
-1 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 18:05 UTC (permalink / raw)
To: Lin Ming
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 11:04:05PM +0800, Lin Ming wrote:
> On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
>
> s/shmem_unlock/shmem_lock/
I did it intentionally for represent shmem_lock with user = 1, lock = 0.
If you think it makes others confusing, I will change in next version.
Thanks.
>
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
--
Kind regards,
Minchan Kim
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-28 18:05 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-28 18:05 UTC (permalink / raw)
To: Lin Ming
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Wed, Sep 28, 2011 at 11:04:05PM +0800, Lin Ming wrote:
> On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> > When racing between putback_lru_page and shmem_unlock happens,
>
> s/shmem_unlock/shmem_lock/
I did it intentionally for represent shmem_lock with user = 1, lock = 0.
If you think it makes others confusing, I will change in next version.
Thanks.
>
> > progrom execution order is as follows, but clear_bit in processor #1
> > could be reordered right before spin_unlock of processor #1.
> > Then, the page would be stranded on the unevictable list.
--
Kind regards,
Minchan Kim
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 18:05 ` Minchan Kim
@ 2011-09-29 1:02 ` Lin Ming
-1 siblings, 0 replies; 22+ messages in thread
From: Lin Ming @ 2011-09-29 1:02 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Thu, Sep 29, 2011 at 2:05 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> On Wed, Sep 28, 2011 at 11:04:05PM +0800, Lin Ming wrote:
>> On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
>> > When racing between putback_lru_page and shmem_unlock happens,
>>
>> s/shmem_unlock/shmem_lock/
>
> I did it intentionally for represent shmem_lock with user = 1, lock = 0.
> If you think it makes others confusing, I will change in next version.
> Thanks.
I was confused. Now I understand.
>
>>
>> > progrom execution order is as follows, but clear_bit in processor #1
>> > could be reordered right before spin_unlock of processor #1.
>> > Then, the page would be stranded on the unevictable list.
>
> --
> Kind regards,
> Minchan Kim
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-29 1:02 ` Lin Ming
0 siblings, 0 replies; 22+ messages in thread
From: Lin Ming @ 2011-09-29 1:02 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
On Thu, Sep 29, 2011 at 2:05 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
> On Wed, Sep 28, 2011 at 11:04:05PM +0800, Lin Ming wrote:
>> On Wed, Sep 28, 2011 at 9:45 AM, Minchan Kim <minchan.kim@gmail.com> wrote:
>> > When racing between putback_lru_page and shmem_unlock happens,
>>
>> s/shmem_unlock/shmem_lock/
>
> I did it intentionally for represent shmem_lock with user = 1, lock = 0.
> If you think it makes others confusing, I will change in next version.
> Thanks.
I was confused. Now I understand.
>
>>
>> > progrom execution order is as follows, but clear_bit in processor #1
>> > could be reordered right before spin_unlock of processor #1.
>> > Then, the page would be stranded on the unevictable list.
>
> --
> Kind regards,
> Minchan Kim
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH v2] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-28 8:14 ` Johannes Weiner
@ 2011-09-29 9:54 ` Minchan Kim
-1 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-29 9:54 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-mm, LKML, Johannes Weiner, Minchan Kim, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
When racing between putback_lru_page and shmem_lock with lock=0 happens,
progrom execution order is as follows, but clear_bit in processor #1
could be reordered right before spin_unlock of processor #1.
Then, the page would be stranded on the unevictable list.
spin_lock
SetPageLRU
spin_unlock
clear_bit(AS_UNEVICTABLE)
spin_lock
if PageLRU()
if !test_bit(AS_UNEVICTABLE)
move evictable list
smp_mb
if !test_bit(AS_UNEVICTABLE)
move evictable list
spin_unlock
But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
so this problem never happens. But it's a unexpected side effect and we should
solve this problem properly.
This patch adds a barrier after mapping_clear_unevictable.
side-note: I didn't meet this problem but just found during review.
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
---
mm/shmem.c | 6 ++++++
mm/vmscan.c | 11 ++++++-----
2 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 2d35772..fa4fa6c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1068,6 +1068,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
+ /*
+ * Ensure that a racing putback_lru_page() can see
+ * the pages of this mapping are evictable when we
+ * skip them due to !PageLRU during the scan.
+ */
+ smp_mb__after_clear_bit();
scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23256e8..4480f67 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -634,13 +634,14 @@ redo:
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
/*
- * When racing with an mlock clearing (page is
- * unlocked), make sure that if the other thread does
- * not observe our setting of PG_lru and fails
- * isolation, we see PG_mlocked cleared below and move
+ * When racing with an mlock or AS_UNEVICTABLE clearing
+ * (page is unlocked) make sure that if the other thread
+ * does not observe our setting of PG_lru and fails
+ * isolation/check_move_unevictable_page,
+ * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
* the page back to the evictable list.
*
- * The other side is TestClearPageMlocked().
+ * The other side is TestClearPageMlocked() or shmem_lock().
*/
smp_mb();
}
--
1.7.4.1
^ permalink raw reply related [flat|nested] 22+ messages in thread
* [PATCH v2] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-29 9:54 ` Minchan Kim
0 siblings, 0 replies; 22+ messages in thread
From: Minchan Kim @ 2011-09-29 9:54 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-mm, LKML, Johannes Weiner, Minchan Kim, KOSAKI Motohiro,
Mel Gorman, Rik van Riel, Lee Schermerhorn
When racing between putback_lru_page and shmem_lock with lock=0 happens,
progrom execution order is as follows, but clear_bit in processor #1
could be reordered right before spin_unlock of processor #1.
Then, the page would be stranded on the unevictable list.
spin_lock
SetPageLRU
spin_unlock
clear_bit(AS_UNEVICTABLE)
spin_lock
if PageLRU()
if !test_bit(AS_UNEVICTABLE)
move evictable list
smp_mb
if !test_bit(AS_UNEVICTABLE)
move evictable list
spin_unlock
But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
so this problem never happens. But it's a unexpected side effect and we should
solve this problem properly.
This patch adds a barrier after mapping_clear_unevictable.
side-note: I didn't meet this problem but just found during review.
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
---
mm/shmem.c | 6 ++++++
mm/vmscan.c | 11 ++++++-----
2 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 2d35772..fa4fa6c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1068,6 +1068,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
+ /*
+ * Ensure that a racing putback_lru_page() can see
+ * the pages of this mapping are evictable when we
+ * skip them due to !PageLRU during the scan.
+ */
+ smp_mb__after_clear_bit();
scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 23256e8..4480f67 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -634,13 +634,14 @@ redo:
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
/*
- * When racing with an mlock clearing (page is
- * unlocked), make sure that if the other thread does
- * not observe our setting of PG_lru and fails
- * isolation, we see PG_mlocked cleared below and move
+ * When racing with an mlock or AS_UNEVICTABLE clearing
+ * (page is unlocked) make sure that if the other thread
+ * does not observe our setting of PG_lru and fails
+ * isolation/check_move_unevictable_page,
+ * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
* the page back to the evictable list.
*
- * The other side is TestClearPageMlocked().
+ * The other side is TestClearPageMlocked() or shmem_lock().
*/
smp_mb();
}
--
1.7.4.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 22+ messages in thread
* Re: [PATCH v2] vmscan: add barrier to prevent evictable page in unevictable list
2011-09-29 9:54 ` Minchan Kim
@ 2011-09-29 12:50 ` KOSAKI Motohiro
-1 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-29 12:50 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, Mel Gorman,
Rik van Riel, Lee Schermerhorn
2011/9/29 Minchan Kim <minchan.kim@gmail.com>:
> When racing between putback_lru_page and shmem_lock with lock=0 happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
>
> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> Cc: Mel Gorman <mel@csn.ul.ie>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> Acked-by: Johannes Weiner <jweiner@redhat.com>
> Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH v2] vmscan: add barrier to prevent evictable page in unevictable list
@ 2011-09-29 12:50 ` KOSAKI Motohiro
0 siblings, 0 replies; 22+ messages in thread
From: KOSAKI Motohiro @ 2011-09-29 12:50 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton, linux-mm, LKML, Johannes Weiner, Mel Gorman,
Rik van Riel, Lee Schermerhorn
2011/9/29 Minchan Kim <minchan.kim@gmail.com>:
> When racing between putback_lru_page and shmem_lock with lock=0 happens,
> progrom execution order is as follows, but clear_bit in processor #1
> could be reordered right before spin_unlock of processor #1.
> Then, the page would be stranded on the unevictable list.
>
> spin_lock
> SetPageLRU
> spin_unlock
> clear_bit(AS_UNEVICTABLE)
> spin_lock
> if PageLRU()
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> smp_mb
> if !test_bit(AS_UNEVICTABLE)
> move evictable list
> spin_unlock
>
> But, pagevec_lookup in scan_mapping_unevictable_pages has rcu_read_[un]lock so
> it could protect reordering before reaching test_bit(AS_UNEVICTABLE) on processor #1
> so this problem never happens. But it's a unexpected side effect and we should
> solve this problem properly.
>
> This patch adds a barrier after mapping_clear_unevictable.
>
> side-note: I didn't meet this problem but just found during review.
>
> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> Cc: Mel Gorman <mel@csn.ul.ie>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
> Acked-by: Johannes Weiner <jweiner@redhat.com>
> Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 22+ messages in thread
end of thread, other threads:[~2011-09-29 12:50 UTC | newest]
Thread overview: 22+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-09-28 1:45 [PATCH] vmscan: add barrier to prevent evictable page in unevictable list Minchan Kim
2011-09-28 1:45 ` Minchan Kim
2011-09-28 2:21 ` KOSAKI Motohiro
2011-09-28 2:21 ` KOSAKI Motohiro
2011-09-28 2:25 ` Minchan Kim
2011-09-28 2:25 ` Minchan Kim
2011-09-28 2:48 ` KOSAKI Motohiro
2011-09-28 2:48 ` KOSAKI Motohiro
2011-09-28 8:14 ` Johannes Weiner
2011-09-28 8:14 ` Johannes Weiner
2011-09-28 18:03 ` Minchan Kim
2011-09-28 18:03 ` Minchan Kim
2011-09-29 9:54 ` [PATCH v2] " Minchan Kim
2011-09-29 9:54 ` Minchan Kim
2011-09-29 12:50 ` KOSAKI Motohiro
2011-09-29 12:50 ` KOSAKI Motohiro
2011-09-28 15:04 ` [PATCH] " Lin Ming
2011-09-28 15:04 ` Lin Ming
2011-09-28 18:05 ` Minchan Kim
2011-09-28 18:05 ` Minchan Kim
2011-09-29 1:02 ` Lin Ming
2011-09-29 1:02 ` Lin Ming
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.