tmpfs: fix spurious ENOSPC when racing with unswap

Testing the shmem_swaplist replacements for igrab() revealed another bug:
writes to /dev/loop0 on a tmpfs file which fills its filesystem were
sometimes failing with "Buffer I/O error"s.

These came from ENOSPC failures of shmem_getpage(), when racing with
swapoff: the same could happen when racing with another shmem_getpage(),
pulling the page in from swap in between our find_lock_page() and our
taking the info->lock (though not in the single-threaded loop case).

This is unacceptable, and surprising that I've not noticed it before:
it dates back many years, but (presumably) was made a lot easier to
reproduce in 2.6.36, which sited a page preallocation in the race window.

Fix it by rechecking the page cache before settling on an ENOSPC error.

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/shmem.c b/mm/shmem.c
index dc17551..9e755c1 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1407,20 +1407,14 @@ repeat:
                if (sbinfo->max_blocks) {
                        if (percpu_counter_compare(&sbinfo->used_blocks,
                                                sbinfo->max_blocks) >= 0 ||
                if (sbinfo->max_blocks) {
                        if (percpu_counter_compare(&sbinfo->used_blocks,
                                                sbinfo->max_blocks) >= 0 ||

-                           shmem_acct_block(info->flags)) {
-                               spin_unlock(&info->lock);
-                               error = -ENOSPC;
-                               goto failed;
-                       }
+                           shmem_acct_block(info->flags))
+                               goto nospace;

                        percpu_counter_inc(&sbinfo->used_blocks);
                        spin_lock(&inode->i_lock);
                        inode->i_blocks += BLOCKS_PER_PAGE;
                        spin_unlock(&inode->i_lock);
                        percpu_counter_inc(&sbinfo->used_blocks);
                        spin_lock(&inode->i_lock);
                        inode->i_blocks += BLOCKS_PER_PAGE;
                        spin_unlock(&inode->i_lock);

-               } else if (shmem_acct_block(info->flags)) {
-                       spin_unlock(&info->lock);
-                       error = -ENOSPC;
-                       goto failed;
-               }
+               } else if (shmem_acct_block(info->flags))
+                       goto nospace;

 
                if (!filepage) {
                        int ret;
 
                if (!filepage) {
                        int ret;


@@ -1500,6 +1494,24 @@ done:
        error = 0;
        goto out;
 
        error = 0;
        goto out;
 

+nospace:
+       /*
+        * Perhaps the page was brought in from swap between find_lock_page
+        * and taking info->lock?  We allow for that at add_to_page_cache_lru,
+        * but must also avoid reporting a spurious ENOSPC while working on a
+        * full tmpfs.  (When filepage has been passed in to shmem_getpage, it
+        * is already in page cache, which prevents this race from occurring.)
+        */
+       if (!filepage) {
+               struct page *page = find_get_page(mapping, idx);
+               if (page) {
+                       spin_unlock(&info->lock);
+                       page_cache_release(page);
+                       goto repeat;
+               }
+       }
+       spin_unlock(&info->lock);
+       error = -ENOSPC;

 failed:
        if (*pagep != filepage) {
                unlock_page(filepage);
 failed:
        if (*pagep != filepage) {
                unlock_page(filepage);