[PATCH] fix race in __block_prepare_write

Fix a race where __block_prepare_write can leak out an in-flight read
against a bh if get_block returns an error.  This can lead to the page
becoming unlocked while the buffer is locked and the read still in flight.
__mpage_writepage BUGs on this condition.

BUG sighted on a 2-way Itanium2 system with 16K PAGE_SIZE running

	fsstress -v -d $DIR/tmp -n 1000 -p 1000 -l 2

where $DIR is a new ext2 filesystem with 4K blocks that is quite
small (causing get_block to fail often with -ENOSPC).

Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/fs/buffer.c b/fs/buffer.c
index 6ed5949..af7c51d 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1953,7 +1953,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page,
                if (!buffer_mapped(bh)) {
                        err = get_block(inode, block, bh, 1);
                        if (err)
-                               goto out;
+                               break;
                        if (buffer_new(bh)) {
                                clear_buffer_new(bh);
                                unmap_underlying_metadata(bh->b_bdev,
@@ -1995,10 +1995,12 @@ static int __block_prepare_write(struct inode *inode, struct page *page,
        while(wait_bh > wait) {
                wait_on_buffer(*--wait_bh);
                if (!buffer_uptodate(*wait_bh))
-                       return -EIO;
+                       err = -EIO;
        }
-       return 0;
-out:
+       if (!err)
+               return err;
+
+       /* Error case: */
        /*
         * Zero out any newly allocated blocks to avoid exposing stale
         * data.  If BH_New is set, we know that the block was newly