diff options
authorHugh Dickins <hughd@google.com>2011-05-11 15:13:36 -0700
committerGreg Kroah-Hartman <gregkh@suse.de>2011-05-21 15:13:23 -0700
commita621088213d3272950a85875afc25cc87b01b560 (patch)
parent6e8a1b8955ad234e6e52d8f3725ce03cbc7940ab (diff)
tmpfs: fix race between umount and writepage
commit b1dea800ac39599301d4bb8dcf2b1d29c2558211 upstream. Konstanin Khlebnikov reports that a dangerous race between umount and shmem_writepage can be reproduced by this script: for i in {1..300} ; do mkdir $i while true ; do mount -t tmpfs none $i dd if=/dev/zero of=$i/test bs=1M count=$(($RANDOM % 100)) umount $i done & done on a 6xCPU node with 8Gb RAM: kernel very unstable after this accident. =) Kernel log: VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds. Have a nice day... WARNING: at lib/list_debug.c:53 __list_del_entry+0x8d/0x98() list_del corruption. prev->next should be ffff880222fdaac8, but was (null) Pid: 11222, comm: mount.tmpfs Not tainted 2.6.39-rc2+ #4 Call Trace: warn_slowpath_common+0x80/0x98 warn_slowpath_fmt+0x41/0x43 __list_del_entry+0x8d/0x98 evict+0x50/0x113 iput+0x138/0x141 ... BUG: unable to handle kernel paging request at ffffffffffffffff IP: shmem_free_blocks+0x18/0x4c Pid: 10422, comm: dd Tainted: G W 2.6.39-rc2+ #4 Call Trace: shmem_recalc_inode+0x61/0x66 shmem_writepage+0xba/0x1dc pageout+0x13c/0x24c shrink_page_list+0x28e/0x4be shrink_inactive_list+0x21f/0x382 ... shmem_writepage() calls igrab() on the inode for the page which came from page reclaim, to add it later into shmem_swaplist for swapoff operation. This igrab() can race with super-block deactivating process: shrink_inactive_list() deactivate_super() pageout() tmpfs_fs_type->kill_sb() shmem_writepage() kill_litter_super() generic_shutdown_super() evict_inodes() igrab() atomic_read(&inode->i_count) skip-inode iput() if (!list_empty(&sb->s_inodes)) printk("VFS: Busy inodes after... This igrap-iput pair was added in commit 1b1b32f2c6f6 "tmpfs: fix shmem_swaplist races" based on incorrect assumptions: igrab() protects the inode from concurrent eviction by deletion, but it does nothing to protect it from concurrent unmounting, which goes ahead despite the raised i_count. So this use of igrab() was wrong all along, but the race made much worse in 2.6.37 when commit 63997e98a3be "split invalidate_inodes()" replaced two attempts at invalidate_inodes() by a single evict_inodes(). Konstantin posted a plausible patch, raising sb->s_active too: I'm unsure whether it was correct or not; but burnt once by igrab(), I am sure that we don't want to rely more deeply upon externals here. Fix it by adding the inode to shmem_swaplist earlier, while the page lock on page in page cache still secures the inode against eviction, without artifically raising i_count. It was originally added later because shmem_unuse_inode() is liable to remove an inode from the list while it's unswapped; but we can guard against that by taking spinlock before dropping mutex. Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Hugh Dickins <hughd@google.com> Tested-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
1 files changed, 20 insertions, 11 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index 8ac1684d790..bd376ba6fd3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1037,6 +1037,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
struct address_space *mapping;
unsigned long index;
struct inode *inode;
+ bool unlock_mutex = false;
mapping = page->mapping;
@@ -1062,7 +1063,26 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
swap.val = 0;
+ /*
+ * Add inode to shmem_unuse()'s list of swapped-out inodes,
+ * if it's not already there. Do it now because we cannot take
+ * mutex while holding spinlock, and must do so before the page
+ * is moved to swap cache, when its pagelock no longer protects
+ * the inode from eviction. But don't unlock the mutex until
+ * we've taken the spinlock, because shmem_unuse_inode() will
+ * prune a !swapped inode from the swaplist under both locks.
+ */
+ if (swap.val && list_empty(&info->swaplist)) {
+ mutex_lock(&shmem_swaplist_mutex);
+ /* move instead of add in case we're racing */
+ list_move_tail(&info->swaplist, &shmem_swaplist);
+ unlock_mutex = true;
+ }
+ if (unlock_mutex)
+ mutex_unlock(&shmem_swaplist_mutex);
if (index >= info->next_index) {
BUG_ON(!(info->flags & SHMEM_TRUNCATE));
goto unlock;
@@ -1082,22 +1102,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
shmem_swp_set(info, entry, swap.val);
- if (list_empty(&info->swaplist))
- inode = igrab(inode);
- else
- inode = NULL;
page_cache_release(page); /* pagecache ref */
swap_writepage(page, wbc);
- if (inode) {
- mutex_lock(&shmem_swaplist_mutex);
- /* move instead of add in case we're racing */
- list_move_tail(&info->swaplist, &shmem_swaplist);
- mutex_unlock(&shmem_swaplist_mutex);
- iput(inode);
- }
return 0;