summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
authorAndrey Savochkin <saw@sw.ru>2006-12-06 20:37:36 -0800
committerLinus Torvalds <torvalds@woody.osdl.org>2006-12-07 08:39:37 -0800
commitb46be05004abb419e303e66e143eed9f8a6e9f3f (patch)
tree51893650757b48b02d18f5e6ab619d5300dc08ca /fs/ext4
parente92a4d595b464c4aae64be39ca61a9ffe9c8b278 (diff)
downloadlinux-b46be05004abb419e303e66e143eed9f8a6e9f3f.tar.gz
linux-b46be05004abb419e303e66e143eed9f8a6e9f3f.tar.bz2
linux-b46be05004abb419e303e66e143eed9f8a6e9f3f.zip
[PATCH] retries in ext4_prepare_write() violate ordering requirements
In journal=ordered or journal=data mode retry in ext4_prepare_write() breaks the requirements of journaling of data with respect to metadata. The fix is to call commit_write to commit allocated zero blocks before retry. Signed-off-by: Kirill Korotaev <dev@openvz.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Ken Chen <kenneth.w.chen@intel.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/inode.c85
1 files changed, 75 insertions, 10 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0a60ec5a16db..1d85d4ec9598 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1147,37 +1147,102 @@ static int do_journal_get_write_access(handle_t *handle,
return ext4_journal_get_write_access(handle, bh);
}
+/*
+ * The idea of this helper function is following:
+ * if prepare_write has allocated some blocks, but not all of them, the
+ * transaction must include the content of the newly allocated blocks.
+ * This content is expected to be set to zeroes by block_prepare_write().
+ * 2006/10/14 SAW
+ */
+static int ext4_prepare_failure(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ struct address_space *mapping;
+ struct buffer_head *bh, *head, *next;
+ unsigned block_start, block_end;
+ unsigned blocksize;
+ int ret;
+ handle_t *handle = ext4_journal_current_handle();
+
+ mapping = page->mapping;
+ if (ext4_should_writeback_data(mapping->host)) {
+ /* optimization: no constraints about data */
+skip:
+ return ext4_journal_stop(handle);
+ }
+
+ head = page_buffers(page);
+ blocksize = head->b_size;
+ for ( bh = head, block_start = 0;
+ bh != head || !block_start;
+ block_start = block_end, bh = next)
+ {
+ next = bh->b_this_page;
+ block_end = block_start + blocksize;
+ if (block_end <= from)
+ continue;
+ if (block_start >= to) {
+ block_start = to;
+ break;
+ }
+ if (!buffer_mapped(bh))
+ /* prepare_write failed on this bh */
+ break;
+ if (ext4_should_journal_data(mapping->host)) {
+ ret = do_journal_get_write_access(handle, bh);
+ if (ret) {
+ ext4_journal_stop(handle);
+ return ret;
+ }
+ }
+ /*
+ * block_start here becomes the first block where the current iteration
+ * of prepare_write failed.
+ */
+ }
+ if (block_start <= from)
+ goto skip;
+
+ /* commit allocated and zeroed buffers */
+ return mapping->a_ops->commit_write(file, page, from, block_start);
+}
+
static int ext4_prepare_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
- int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+ int ret, ret2;
+ int needed_blocks = ext4_writepage_trans_blocks(inode);
handle_t *handle;
int retries = 0;
retry:
handle = ext4_journal_start(inode, needed_blocks);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
ret = nobh_prepare_write(page, from, to, ext4_get_block);
else
ret = block_prepare_write(page, from, to, ext4_get_block);
if (ret)
- goto prepare_write_failed;
+ goto failure;
if (ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, do_journal_get_write_access);
+ if (ret)
+ /* fatal error, just put the handle and return */
+ journal_stop(handle);
}
-prepare_write_failed:
- if (ret)
- ext4_journal_stop(handle);
+ return ret;
+
+failure:
+ ret2 = ext4_prepare_failure(file, page, from, to);
+ if (ret2 < 0)
+ return ret2;
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
-out:
+ /* retry number exceeded, or other error like -EDQUOT */
return ret;
}