gfs2: fix O_SYNC write handling

In gfs2_file_write_iter, for direct writes, the error checking in the buffered
write fallback case is incomplete.  This can cause inode write errors to go
undetected.  Fix and clean up gfs2_file_write_iter along the way.

Based on a proposed fix by Christoph Hellwig <hch@lst.de>.

Fixes: 967bcc91b0 ("gfs2: iomap direct I/O support")
Cc: stable@vger.kernel.org # v4.19+
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
This commit is contained in:
Andreas Gruenbacher 2020-01-14 17:12:18 +01:00
parent 4c0e8dda60
commit 6e5e41e2dc
1 changed files with 21 additions and 30 deletions

View File

@ -847,7 +847,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct gfs2_inode *ip = GFS2_I(inode);
ssize_t written = 0, ret;
ssize_t ret;
ret = gfs2_rsqa_alloc(ip);
if (ret)
@ -879,55 +879,46 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (iocb->ki_flags & IOCB_DIRECT) {
struct address_space *mapping = file->f_mapping;
loff_t pos, endbyte;
ssize_t buffered;
ssize_t buffered, ret2;
written = gfs2_file_direct_write(iocb, from);
if (written < 0 || !iov_iter_count(from))
ret = gfs2_file_direct_write(iocb, from);
if (ret < 0 || !iov_iter_count(from))
goto out_unlock;
iocb->ki_flags |= IOCB_DSYNC;
current->backing_dev_info = inode_to_bdi(inode);
ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
current->backing_dev_info = NULL;
if (unlikely(ret < 0))
if (unlikely(buffered <= 0))
goto out_unlock;
buffered = ret;
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
* semantics. If the writeback or invalidate fails, only report
* the direct I/O range as we don't know if the buffered pages
* made it to disk.
*/
pos = iocb->ki_pos;
endbyte = pos + buffered - 1;
ret = filemap_write_and_wait_range(mapping, pos, endbyte);
if (!ret) {
iocb->ki_pos += buffered;
written += buffered;
invalidate_mapping_pages(mapping,
pos >> PAGE_SHIFT,
endbyte >> PAGE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
* the number of bytes which were direct-written
*/
}
iocb->ki_pos += buffered;
ret2 = generic_write_sync(iocb, buffered);
invalidate_mapping_pages(mapping,
(iocb->ki_pos - buffered) >> PAGE_SHIFT,
(iocb->ki_pos - 1) >> PAGE_SHIFT);
if (!ret || ret2 > 0)
ret += ret2;
} else {
current->backing_dev_info = inode_to_bdi(inode);
ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
current->backing_dev_info = NULL;
if (likely(ret > 0))
if (likely(ret > 0)) {
iocb->ki_pos += ret;
ret = generic_write_sync(iocb, ret);
}
}
out_unlock:
inode_unlock(inode);
if (likely(ret > 0)) {
/* Handle various SYNC-type writes */
ret = generic_write_sync(iocb, ret);
}
return written ? written : ret;
return ret;
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,