summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorCurt Wohlgemuth <curtw@google.com>2011-02-07 12:46:14 -0500
committerTheodore Ts'o <tytso@mit.edu>2011-02-07 12:46:14 -0500
commitd50bdd5aa55127635fd8a5c74bd2abb256bd34e3 (patch)
tree3dbe0f5d06502e144c0398c71e8fe479a855d6f4 /fs/ext4
parentdd68314ccf3fb918c1fb6471817edbc60ece4b52 (diff)
ext4: Fix data corruption with multi-block writepages support
This fixes a corruption problem with the multi-block writepages submittal change for ext4, from commit bd2d0210cf22f2bd0cef72eb97cf94fc7d31d8cc ("ext4: use bio layer instead of buffer layer in mpage_da_submit_io"). (Note that this corruption is not present in 2.6.37 on ext4, because the corruption was detected after the feature was merged in 2.6.37-rc1, and so it was turned off by adding a non-default mount option, mblk_io_submit. With this commit, which hopefully fixes the last of the bugs with this feature, we'll be able to turn on this performance feature by default in 2.6.38, and remove the mblk_io_submit option.) The ext4 code path to bundle multiple pages for writeback in ext4_bio_write_page() had a bug: we should be clearing buffer head dirty flags *before* we submit the bio, not in the completion routine. The patch below was tested on 2.6.37 under KVM with the postgresql script which was submitted by Jon Nelson as documented in commit 1449032be1. Without the patch, I'd hit the corruption problem about 50-70% of the time. With the patch, I executed the script > 100 times with no corruption seen. I also fixed a bug to make sure ext4_end_bio() doesn't dereference the bio after the bio_put() call. Reported-by: Jon Nelson <jnelson@jamponi.net> Reported-by: Matthias Bayer <jackdachef@gmail.com> Signed-off-by: Curt Wohlgemuth <curtw@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@kernel.org
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/page-io.c11
1 files changed, 6 insertions, 5 deletions
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7270dcfca92a..4e9b0a242f4c 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -190,6 +190,7 @@ static void ext4_end_bio(struct bio *bio, int error)
struct inode *inode;
unsigned long flags;
int i;
+ sector_t bi_sector = bio->bi_sector;
BUG_ON(!io_end);
bio->bi_private = NULL;
@@ -207,9 +208,7 @@ static void ext4_end_bio(struct bio *bio, int error)
if (error)
SetPageError(page);
BUG_ON(!head);
- if (head->b_size == PAGE_CACHE_SIZE)
- clear_buffer_dirty(head);
- else {
+ if (head->b_size != PAGE_CACHE_SIZE) {
loff_t offset;
loff_t io_end_offset = io_end->offset + io_end->size;
@@ -221,7 +220,6 @@ static void ext4_end_bio(struct bio *bio, int error)
if (error)
buffer_io_error(bh);
- clear_buffer_dirty(bh);
}
if (buffer_delay(bh))
partial_write = 1;
@@ -257,7 +255,7 @@ static void ext4_end_bio(struct bio *bio, int error)
(unsigned long long) io_end->offset,
(long) io_end->size,
(unsigned long long)
- bio->bi_sector >> (inode->i_blkbits - 9));
+ bi_sector >> (inode->i_blkbits - 9));
}
/* Add the io_end to per-inode completed io list*/
@@ -380,6 +378,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
blocksize = 1 << inode->i_blkbits;
+ BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
set_page_writeback(page);
ClearPageError(page);
@@ -397,12 +396,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
+
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
+ clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*