summaryrefslogtreecommitdiff
path: root/mm/shmem.c
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2008-02-04 22:28:55 -0800
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-02-05 09:44:16 -0800
commit1b1b32f2c6f6bb32535d2da62075b51c980880eb (patch)
tree686aac685a4c04f085dc17cc1a05910149a04933 /mm/shmem.c
parentb409f9fcf04692c0f603d28c73d2e3dfed27bf54 (diff)
downloadlwn-1b1b32f2c6f6bb32535d2da62075b51c980880eb.tar.gz
lwn-1b1b32f2c6f6bb32535d2da62075b51c980880eb.zip
tmpfs: fix shmem_swaplist races
Intensive swapoff testing shows shmem_unuse spinning on an entry in shmem_swaplist pointing to itself: how does that come about? Days pass... First guess is this: shmem_delete_inode tests list_empty without taking the global mutex (so the swapping case doesn't slow down the common case); but there's an instant in shmem_unuse_inode's list_move_tail when the list entry may appear empty (a rare case, because it's actually moving the head not the the list member). So there's a danger of leaving the inode on the swaplist when it's freed, then reinitialized to point to itself when reused. Fix that by skipping the list_move_tail when it's a no-op, which happens to plug this. But this same spinning then surfaces on another machine. Ah, I'd never suspected it, but shmem_writepage's swaplist manipulation is unsafe: though we still hold page lock, which would hold off inode deletion if the page were in pagecache, it doesn't hold off once it's in swapcache (free_swap_and_cache doesn't wait on locked pages). Hmm: we could put the the inode on swaplist earlier, but then shmem_unuse_inode could never prune unswapped inodes. Fix this with an igrab before dropping info->lock, as in shmem_unuse_inode; though I am a little uneasy about the iput which has to follow - it works, and I see nothing wrong with it, but it is surprising that shmem inode deletion may now occur below shmem_writepage. Revisit this fix later? And while we're looking at these races: the way shmem_unuse tests swapped without holding info->lock looks unsafe, if we've more than one swap area: a racing shmem_writepage on another page of the same inode could be putting it in swapcache, just as we're deciding to remove the inode from swaplist - there's a danger of going on swap without being listed, so a later swapoff would hang, being unable to locate the entry. Move that test and removal down into shmem_unuse_inode, once info->lock is held. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/shmem.c')
-rw-r--r--mm/shmem.c37
1 files changed, 25 insertions, 12 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index 530c5033d028..ee9024483f60 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -833,6 +833,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s
idx = 0;
ptr = info->i_direct;
spin_lock(&info->lock);
+ if (!info->swapped) {
+ list_del_init(&info->swaplist);
+ goto lost2;
+ }
limit = info->next_index;
size = limit;
if (size > SHMEM_NR_DIRECT)
@@ -894,8 +898,15 @@ found:
inode = igrab(&info->vfs_inode);
spin_unlock(&info->lock);
- /* move head to start search for next from here */
- list_move_tail(&shmem_swaplist, &info->swaplist);
+ /*
+ * Move _head_ to start search for next from here.
+ * But be careful: shmem_delete_inode checks list_empty without taking
+ * mutex, and there's an instant in list_move_tail when info->swaplist
+ * would appear empty, if it were the only one on shmem_swaplist. We
+ * could avoid doing it if inode NULL; or use this minor optimization.
+ */
+ if (shmem_swaplist.next != &info->swaplist)
+ list_move_tail(&shmem_swaplist, &info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
error = 1;
@@ -955,10 +966,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(p, next, &shmem_swaplist) {
info = list_entry(p, struct shmem_inode_info, swaplist);
- if (info->swapped)
- found = shmem_unuse_inode(info, entry, page);
- else
- list_del_init(&info->swaplist);
+ found = shmem_unuse_inode(info, entry, page);
cond_resched();
if (found)
goto out;
@@ -1021,18 +1029,23 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
remove_from_page_cache(page);
shmem_swp_set(info, entry, swap.val);
shmem_swp_unmap(entry);
+ if (list_empty(&info->swaplist))
+ inode = igrab(inode);
+ else
+ inode = NULL;
spin_unlock(&info->lock);
- if (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);
- mutex_unlock(&shmem_swaplist_mutex);
- }
swap_duplicate(swap);
BUG_ON(page_mapped(page));
page_cache_release(page); /* pagecache ref */
set_page_dirty(page);
unlock_page(page);
+ 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;
}