From: Omar Sandoval <osandov@osandov.com>
To: linux-btrfs@vger.kernel.org
Cc: kernel-team@fb.com, Christoph Hellwig <hch@lst.de>
Subject: [PATCH 02/15] btrfs: fix double __endio_write_update_ordered in direct I/O
Date: Mon, 9 Mar 2020 14:32:28 -0700 [thread overview]
Message-ID: <b4b45179cc951dde98feea48723572683daf7fb3.1583789410.git.osandov@fb.com> (raw)
In-Reply-To: <cover.1583789410.git.osandov@fb.com>
From: Omar Sandoval <osandov@fb.com>
In btrfs_submit_direct(), if we fail to allocate the btrfs_dio_private,
we complete the ordered extent range. However, we don't mark that the
range doesn't need to be cleaned up from btrfs_direct_IO() until later.
Therefore, if we fail to allocate the btrfs_dio_private, we complete the
ordered extent range twice. We could fix this by updating
unsubmitted_oe_range earlier, but it's simpler to always clean up via
the bio once the btrfs_dio_private is allocated and leave it for
btrfs_direct_IO() before that.
Fixes: f28a49287817 ("Btrfs: fix leaking of ordered extents after direct IO write error")
Signed-off-by: Omar Sandoval <osandov@fb.com>
---
fs/btrfs/inode.c | 92 ++++++++++++++----------------------------------
1 file changed, 26 insertions(+), 66 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d48a2010f24a..8e986056be3c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7912,7 +7912,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
return ret;
}
-static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
+static void btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
{
struct inode *inode = dip->inode;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -7932,7 +7932,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio),
start_sector << 9, submit_len, &geom);
if (ret)
- return -EIO;
+ goto out_err;
if (geom.len >= submit_len) {
bio = orig_bio;
@@ -7995,7 +7995,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
submit:
status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
if (!status)
- return 0;
+ return;
if (bio != orig_bio)
bio_put(bio);
@@ -8009,9 +8009,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
*/
if (atomic_dec_and_test(&dip->pending_bios))
bio_io_error(dip->orig_bio);
-
- /* bio_end_io() will handle error, so we needn't return it */
- return 0;
}
static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
@@ -8021,14 +8018,24 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
struct bio *bio = NULL;
struct btrfs_io_bio *io_bio;
bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
- int ret = 0;
bio = btrfs_bio_clone(dio_bio);
dip = kzalloc(sizeof(*dip), GFP_NOFS);
if (!dip) {
- ret = -ENOMEM;
- goto free_ordered;
+ if (!write) {
+ unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+ file_offset + dio_bio->bi_iter.bi_size - 1);
+ }
+
+ dio_bio->bi_status = BLK_STS_RESOURCE;
+ /*
+ * Releases and cleans up our dio_bio, no need to bio_put() nor
+ * bio_endio()/bio_io_error() against dio_bio.
+ */
+ dio_end_io(dio_bio);
+ bio_put(bio);
+ return;
}
dip->private = dio_bio->bi_private;
@@ -8044,72 +8051,25 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
io_bio->logical = file_offset;
if (write) {
- bio->bi_end_io = btrfs_endio_direct_write;
- } else {
- bio->bi_end_io = btrfs_endio_direct_read;
- dip->subio_endio = btrfs_subio_endio_read;
- }
-
- /*
- * Reset the range for unsubmitted ordered extents (to a 0 length range)
- * even if we fail to submit a bio, because in such case we do the
- * corresponding error handling below and it must not be done a second
- * time by btrfs_direct_IO().
- */
- if (write) {
+ /*
+ * At this point, the btrfs_dio_private is responsible for
+ * cleaning up the ordered extents whether or not we submit any
+ * bios.
+ */
struct btrfs_dio_data *dio_data = current->journal_info;
dio_data->unsubmitted_oe_range_end = dip->logical_offset +
dip->bytes;
dio_data->unsubmitted_oe_range_start =
dio_data->unsubmitted_oe_range_end;
- }
-
- ret = btrfs_submit_direct_hook(dip);
- if (!ret)
- return;
-
- btrfs_io_bio_free_csum(io_bio);
-free_ordered:
- /*
- * If we arrived here it means either we failed to submit the dip
- * or we either failed to clone the dio_bio or failed to allocate the
- * dip. If we cloned the dio_bio and allocated the dip, we can just
- * call bio_endio against our io_bio so that we get proper resource
- * cleanup if we fail to submit the dip, otherwise, we must do the
- * same as btrfs_endio_direct_[write|read] because we can't call these
- * callbacks - they require an allocated dip and a clone of dio_bio.
- */
- if (bio && dip) {
- bio_io_error(bio);
- /*
- * The end io callbacks free our dip, do the final put on bio
- * and all the cleanup and final put for dio_bio (through
- * dio_end_io()).
- */
- dip = NULL;
- bio = NULL;
+ bio->bi_end_io = btrfs_endio_direct_write;
} else {
- if (write)
- __endio_write_update_ordered(inode,
- file_offset,
- dio_bio->bi_iter.bi_size,
- false);
- else
- unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
- file_offset + dio_bio->bi_iter.bi_size - 1);
-
- dio_bio->bi_status = BLK_STS_IOERR;
- /*
- * Releases and cleans up our dio_bio, no need to bio_put()
- * nor bio_endio()/bio_io_error() against dio_bio.
- */
- dio_end_io(dio_bio);
+ bio->bi_end_io = btrfs_endio_direct_read;
+ dip->subio_endio = btrfs_subio_endio_read;
}
- if (bio)
- bio_put(bio);
- kfree(dip);
+
+ btrfs_submit_direct_hook(dip);
}
static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
--
2.25.1
next prev parent reply other threads:[~2020-03-09 21:33 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-09 21:32 [PATCH 00/15] btrfs: read repair/direct I/O improvements Omar Sandoval
2020-03-09 21:32 ` [PATCH 01/15] btrfs: fix error handling when submitting direct I/O bio Omar Sandoval
2020-03-11 17:54 ` Josef Bacik
2020-03-17 13:46 ` Nikolay Borisov
2020-03-09 21:32 ` Omar Sandoval [this message]
2020-03-10 16:30 ` [PATCH 02/15] btrfs: fix double __endio_write_update_ordered in direct I/O Christoph Hellwig
2020-03-11 9:03 ` Omar Sandoval
2020-03-17 14:04 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 03/15] btrfs: look at full bi_io_vec for repair decision Omar Sandoval
2020-03-10 16:33 ` Christoph Hellwig
2020-03-11 9:07 ` Omar Sandoval
2020-03-16 10:48 ` Christoph Hellwig
2020-03-17 14:38 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 04/15] btrfs: don't do repair validation for checksum errors Omar Sandoval
2020-03-11 17:55 ` Josef Bacik
2020-03-09 21:32 ` [PATCH 05/15] btrfs: clarify btrfs_lookup_bio_sums documentation Omar Sandoval
2020-03-11 17:56 ` Josef Bacik
2020-03-11 18:23 ` Omar Sandoval
2020-03-11 18:34 ` Josef Bacik
2020-03-17 14:38 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 06/15] btrfs: rename __readpage_endio_check to check_data_csum Omar Sandoval
2020-03-10 14:46 ` Johannes Thumshirn
2020-03-11 17:57 ` Josef Bacik
2020-03-17 14:39 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 07/15] btrfs: make btrfs_check_repairable() static Omar Sandoval
2020-03-10 14:53 ` Johannes Thumshirn
2020-03-11 17:58 ` Josef Bacik
2020-03-17 14:52 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 08/15] btrfs: move btrfs_dio_private to inode.c Omar Sandoval
2020-03-10 14:56 ` Johannes Thumshirn
2020-03-11 8:48 ` Omar Sandoval
2020-03-17 14:53 ` Nikolay Borisov
2020-03-19 16:16 ` David Sterba
2020-03-09 21:32 ` [PATCH 09/15] btrfs: kill btrfs_dio_private->private Omar Sandoval
2020-03-11 17:59 ` Josef Bacik
2020-03-17 14:54 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 10/15] btrfs: convert btrfs_dio_private->pending_bios to refcount_t Omar Sandoval
2020-03-11 18:00 ` Josef Bacik
2020-03-17 15:10 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 11/15] btrfs: put direct I/O checksums in btrfs_dio_private instead of bio Omar Sandoval
2020-03-11 18:04 ` Josef Bacik
2020-03-17 16:37 ` Nikolay Borisov
2020-04-03 16:18 ` David Sterba
2020-03-09 21:32 ` [PATCH 12/15] btrfs: get rid of one layer of bios in direct I/O Omar Sandoval
2020-03-10 16:38 ` Christoph Hellwig
2020-03-11 9:19 ` Omar Sandoval
2020-03-16 10:49 ` Christoph Hellwig
2020-03-11 18:07 ` Josef Bacik
2020-03-17 16:48 ` Nikolay Borisov
2020-03-09 21:32 ` [PATCH 13/15] btrfs: simplify direct I/O read repair Omar Sandoval
2020-03-11 18:16 ` Josef Bacik
2020-04-03 16:40 ` David Sterba
2020-04-03 18:05 ` Omar Sandoval
2020-04-16 10:08 ` David Sterba
2020-03-09 21:32 ` [PATCH 14/15] btrfs: get rid of endio_repair_workers Omar Sandoval
2020-03-11 18:16 ` Josef Bacik
2020-03-09 21:32 ` [PATCH 15/15] btrfs: unify buffered and direct I/O read repair Omar Sandoval
2020-03-11 18:19 ` Josef Bacik
2020-03-19 8:53 ` Nikolay Borisov
2020-03-19 9:03 ` Christoph Hellwig
2020-03-20 21:28 ` Omar Sandoval
2020-03-10 16:39 ` [PATCH 00/15] btrfs: read repair/direct I/O improvements Christoph Hellwig
2020-03-11 9:22 ` Omar Sandoval
2020-03-18 16:33 ` Goldwyn Rodrigues
2020-03-19 14:08 ` David Sterba
2020-03-18 22:07 ` David Sterba
2020-03-20 21:29 ` Omar Sandoval
2020-03-20 14:10 ` Christoph Hellwig
2020-03-20 14:11 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=b4b45179cc951dde98feea48723572683daf7fb3.1583789410.git.osandov@fb.com \
--to=osandov@osandov.com \
--cc=hch@lst.de \
--cc=kernel-team@fb.com \
--cc=linux-btrfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).