vfs: Fix lock inversion in drop_pagecache_sb()
Jan Kara
reviewerPATCH 1/1 vfs: Fix lock inversion in drop_pagecache_sb()
Fix longstanding lock inversion in drop_pagecache_sb by dropping inode_lock before calling __invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...
--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)
fs/drop_caches.c +7 -1
@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ; +__iget (inode); +spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true); +iput (toput_inode); + toput_inode = inode; +spin_lock (&inode_lock); }spin_unlock (&inode_lock); +iput (toput_inode); }void drop_pagecache (void )
Signature · 1 line
1.5.2.4
Quoted 19 lines · On Tue, 25 Mar 2008 19:12:27 +0100 Jan Kara <[email protected]> wrote:
Fix longstanding lock inversion in
drop_pagecache_sbby droppinginode_lockbefore calling__invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...Signed-off-by Jan Kara <[email protected]>CC Fengguang Wu <[email protected]>CC David Chinner <[email protected]>--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)fs/drop_caches.c +0
-0
fs/drop_caches.c int sysctl_drop_caches; · line 22
Quoted 10 lines
fs/drop_caches.c +1
-1@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ;
OT: it might be worth having an `if (mapping->nrpages==0) continue' here.
fs/drop_caches.c int sysctl_drop_caches; · line 34
Quoted 12 lines
fs/drop_caches.c +6
-0+__iget (inode); +spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true); +iput (toput_inode); + toput_inode = inode; +spin_lock (&inode_lock); }spin_unlock (&inode_lock); +iput (toput_inode); }void drop_pagecache (void )
hrm. So we have a random ref on an inode without holding inode_lock. If we race with invalidate_list() we end up with an inode stuck on s_inodes and "Self-destruct in 5 seconds. Have a nice day...", don't we?
Quoted 46 lines · Andrew Morton
Quoted 19 lines · On Tue, 25 Mar 2008 19:12:27 +0100 Jan Kara <[email protected]> wrote:
Fix longstanding lock inversion in
drop_pagecache_sbby droppinginode_lockbefore calling__invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...Signed-off-by Jan Kara <[email protected]>CC Fengguang Wu <[email protected]>CC David Chinner <[email protected]>--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)fs/drop_caches.c +0
-0fs/drop_caches.c int sysctl_drop_caches; · line 22
Quoted 10 lines
fs/drop_caches.c +1
-1@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ;OT: it might be worth having an `if (mapping->nrpages==0) continue' here.
Quoted 11 lines
fs/drop_caches.c +6
-0+__iget (inode); +spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true); +iput (toput_inode); + toput_inode = inode; +spin_lock (&inode_lock); }spin_unlock (&inode_lock); +iput (toput_inode); }
Quoted 5 lines
fs/drop_caches.c int sysctl_drop_caches; · line 34
Quoted 1 line
fs/drop_caches.c +0
-0void drop_pagecache (void )hrm. So we have a random ref on an inode without holding
inode_lock. If we race withinvalidate_list()we end up with an inode stuck ons_inodesand "Self-destruct in 5 seconds. Have a nice day...", don't we?
Calling drop_pagecache_sb() without having a reference to 'sb'? Surely not...
Trond
Quoted 28 lines · Andrew Morton
Quoted 25 lines · On Tue, 25 Mar 2008 19:12:27 +0100 Jan Kara <[email protected]> wrote:
Fix longstanding lock inversion in
drop_pagecache_sbby droppinginode_lockbefore calling__invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...Signed-off-by Jan Kara <[email protected]>CC Fengguang Wu <[email protected]>CC David Chinner <[email protected]>--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)fs/drop_caches.c +1
-1@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;
Quoted 6 lines
fs/drop_caches.c int sysctl_drop_caches; · line 22
Quoted 4 lines
fs/drop_caches.c +0
-0spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ;OT: it might be worth having an `if (mapping->nrpages==0) continue' here.
Good catch!
There are 25k opened inodes in my desktop, merely 10% of them has cached pages:
% cat /proc/sys/fs/inode-state
25395 129 0 0 0 0 0
# wc -l /proc/filecache
2542 /proc/filecache
+ if (!inode->i_mapping || !inode->i_mapping->nrpages)
+ continue;
Jan Kara
reviewerQuoted 28 lines · Andrew Morton
Quoted 25 lines · On Tue, 25 Mar 2008 19:12:27 +0100 Jan Kara <[email protected]> wrote:
Fix longstanding lock inversion in
drop_pagecache_sbby droppinginode_lockbefore calling__invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...Signed-off-by Jan Kara <[email protected]>CC Fengguang Wu <[email protected]>CC David Chinner <[email protected]>--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)fs/drop_caches.c +1
-1@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;
Quoted 6 lines
fs/drop_caches.c int sysctl_drop_caches; · line 22
Quoted 4 lines
fs/drop_caches.c +0
-0spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ;OT: it might be worth having an `if (mapping->nrpages==0) continue' here.
Good idea. I'll send a patch in a minute.
Quoted 11 lines
Quoted 11 lines
fs/drop_caches.c +6
-0+__iget (inode); +spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true); +iput (toput_inode); + toput_inode = inode; +spin_lock (&inode_lock); }spin_unlock (&inode_lock); +iput (toput_inode); }
Quoted 5 lines
fs/drop_caches.c int sysctl_drop_caches; · line 34
Quoted 1 line
fs/drop_caches.c +0
-0void drop_pagecache (void )hrm. So we have a random ref on an inode without holding
inode_lock. If we race withinvalidate_list()we end up with an inode stuck ons_inodesand "Self-destruct in 5 seconds. Have a nice day...", don't we?
We hold s_umount for reading so we should be safe against someone trying
to do umount. We could possibly race with invalidate_list() called from check_disk_change() but removing media without unmounting is a bad behavior anyway. So I think we are fine.
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR
Jan Kara
reviewerPATCH 1/1 vfs: Skip inodes without pages to free in drop_pagecache_sb()
In reply to Andrew Morton--- fs/drop_caches.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
fs/drop_caches.c +2 -0
@@ -20,6 +20,8 @@ static void drop_pagecache_sb(struct super_block *sb)list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ; +if (inode->i_mapping->nrpages ==0 ) +continue ;__iget (inode);spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true);
Signature · 1 line
1.5.2.4
Quoted 5 lines · Jan Kara
Fix longstanding lock inversion in
drop_pagecache_sbby droppinginode_lockbefore calling__invalidate_mapping_pages(). We just have to make sure inode won't go away from under us by keeping reference to it and putting the reference only after we have safely resumed the scan of the inode list. A bit tricky but not too bad...
It's a handy trick to iterate through the list_head :-) I have practiced this in my filecache code, and it works nice.
Fengguang
Quoted 38 lines
Signed-off-by Jan Kara <[email protected]>CC Fengguang Wu <[email protected]>CC David Chinner <[email protected]>--- fs/drop_caches.c | 8 +++++++- 1 files changed, 7 insertions(+), 1 deletions(-)fs/drop_caches.c +7
-1@@ -14,15 +14,21 @@ int sysctl_drop_caches;static void drop_pagecache_sb (struct super_block *sb) { -struct inode *inode; +struct inode *inode, *toput_inode =NULL ;spin_lock (&inode_lock);list_for_each_entry (inode, &sb->s_inodes, i_sb_list) {if (inode->i_state & (I_FREEING |I_WILL_FREE ))continue ; +__iget (inode); +spin_unlock (&inode_lock);__invalidate_mapping_pages (inode->i_mapping,0 ,-1 , true); +iput (toput_inode); + toput_inode = inode; +spin_lock (&inode_lock); }spin_unlock (&inode_lock); +iput (toput_inode); }void drop_pagecache (void )Signature · 1 line
1.5.2.4