From: Qu Wenruo <wqu@suse.com>
To: linux-btrfs@vger.kernel.org
Subject: [PATCH 08/27] btrfs: handle errors properly inside btrfs_submit_compressed_read()
Date: Tue, 13 Jul 2021 14:14:57 +0800 [thread overview]
Message-ID: <20210713061516.163318-9-wqu@suse.com> (raw)
In-Reply-To: <20210713061516.163318-1-wqu@suse.com>
There are quite some BUG_ON()s inside btrfs_submit_compressed_read(),
namingly all errors inside the for() loop relies on BUG_ON() to handle
-ENOMEM.
Handle these errors properly by:
- Wait for submitted bios to finish first
Using wake_var_event() APIs to wait without introducing extra memory
overhead inside compressed_bio.
This allows us to wait for any submitted bio to finish, while still
keeps the compressed_bio from being freed.
- Introduce finish_compressed_bio_read() to finish the compressed_bio
- Properly end the bio and finish compressed_bio when error happens
Now in btrfs_submit_compressed_read() even when the bio submission
failed, we can properly handle the error without triggering BUG_ON().
Signed-off-by: Qu Wenruo <wqu@suse.com>
---
fs/btrfs/compression.c | 133 +++++++++++++++++++++++++----------------
1 file changed, 83 insertions(+), 50 deletions(-)
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index be81e34fbd56..51f83684dbb0 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -223,9 +223,60 @@ static bool dec_and_test_compressed_bio(struct compressed_bio *cb,
last_io = refcount_sub_and_test(bi_size >> fs_info->sectorsize_bits,
&cb->pending_sectors);
atomic_dec(&cb->pending_bios);
+ /*
+ * Here we must wake up the possible error handler after all other
+ * operations on @cb finished, or we can race with
+ * finish_compressed_bio_*() which may free @cb.
+ */
+ wake_up_var(cb);
+
return last_io;
}
+static void finish_compressed_bio_read(struct compressed_bio *cb,
+ struct bio *bio)
+{
+ unsigned int index;
+ struct page *page;
+
+ /* Release the compressed pages */
+ for (index = 0; index < cb->nr_pages; index++) {
+ page = cb->compressed_pages[index];
+ page->mapping = NULL;
+ put_page(page);
+ }
+
+ /* Do io completion on the original bio */
+ if (cb->errors) {
+ bio_io_error(cb->orig_bio);
+ } else {
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ ASSERT(bio);
+ ASSERT(!bio->bi_status);
+ /*
+ * We have verified the checksum already, set page
+ * checked so the end_io handlers know about it
+ */
+ ASSERT(!bio_flagged(bio, BIO_CLONED));
+ bio_for_each_segment_all(bvec, cb->orig_bio, iter_all) {
+ u64 bvec_start = page_offset(bvec->bv_page) +
+ bvec->bv_offset;
+
+ btrfs_page_set_checked(btrfs_sb(cb->inode->i_sb),
+ bvec->bv_page, bvec_start,
+ bvec->bv_len);
+ }
+
+ bio_endio(cb->orig_bio);
+ }
+
+ /* Finally free the cb struct */
+ kfree(cb->compressed_pages);
+ kfree(cb);
+}
+
/* when we finish reading compressed pages from the disk, we
* decompress them and then run the bio end_io routines on the
* decompressed pages (in the inode address space).
@@ -240,8 +291,6 @@ static void end_compressed_bio_read(struct bio *bio)
{
struct compressed_bio *cb = bio->bi_private;
struct inode *inode;
- struct page *page;
- unsigned int index;
unsigned int mirror = btrfs_io_bio(bio)->mirror_num;
int ret = 0;
@@ -276,42 +325,7 @@ static void end_compressed_bio_read(struct bio *bio)
csum_failed:
if (ret)
cb->errors = 1;
-
- /* release the compressed pages */
- index = 0;
- for (index = 0; index < cb->nr_pages; index++) {
- page = cb->compressed_pages[index];
- page->mapping = NULL;
- put_page(page);
- }
-
- /* do io completion on the original bio */
- if (cb->errors) {
- bio_io_error(cb->orig_bio);
- } else {
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
-
- /*
- * we have verified the checksum already, set page
- * checked so the end_io handlers know about it
- */
- ASSERT(!bio_flagged(bio, BIO_CLONED));
- bio_for_each_segment_all(bvec, cb->orig_bio, iter_all) {
- u64 bvec_start = page_offset(bvec->bv_page) +
- bvec->bv_offset;
-
- btrfs_page_set_checked(btrfs_sb(cb->inode->i_sb),
- bvec->bv_page, bvec_start,
- bvec->bv_len);
- }
-
- bio_endio(cb->orig_bio);
- }
-
- /* finally free the cb struct */
- kfree(cb->compressed_pages);
- kfree(cb);
+ finish_compressed_bio_read(cb, bio);
out:
bio_put(bio);
}
@@ -834,20 +848,20 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
atomic_inc(&cb->pending_bios);
ret = btrfs_bio_wq_end_io(fs_info, comp_bio,
BTRFS_WQ_ENDIO_DATA);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto finish_cb;
ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto finish_cb;
nr_sectors = DIV_ROUND_UP(comp_bio->bi_iter.bi_size,
fs_info->sectorsize);
sums += fs_info->csum_size * nr_sectors;
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
- if (ret) {
- comp_bio->bi_status = ret;
- bio_endio(comp_bio);
- }
+ if (ret)
+ goto finish_cb;
comp_bio = btrfs_bio_alloc(cur_disk_byte);
comp_bio->bi_opf = REQ_OP_READ;
@@ -861,16 +875,16 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
atomic_inc(&cb->pending_bios);
ret = btrfs_bio_wq_end_io(fs_info, comp_bio, BTRFS_WQ_ENDIO_DATA);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto last_bio;
ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto last_bio;
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
- if (ret) {
- comp_bio->bi_status = ret;
- bio_endio(comp_bio);
- }
+ if (ret)
+ goto last_bio;
return 0;
@@ -886,6 +900,25 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
out:
free_extent_map(em);
return ret;
+last_bio:
+ comp_bio->bi_status = ret;
+ /* This is the last bio, endio functions will free @cb */
+ bio_endio(comp_bio);
+ return ret;
+finish_cb:
+ if (comp_bio) {
+ comp_bio->bi_status = ret;
+ bio_endio(comp_bio);
+ }
+ wait_var_event(cb, atomic_read(&cb->pending_bios) == 0);
+ /*
+ * Even with previous bio ended, we should still have io not yet
+ * submitted, thus need to finish @cb manually.
+ */
+ ASSERT(refcount_read(&cb->pending_sectors));
+ /* Now we are the only one referring @cb, can finish it safely. */
+ finish_compressed_bio_read(cb, NULL);
+ return ret;
}
/*
--
2.32.0
next prev parent reply other threads:[~2021-07-13 6:15 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-13 6:14 [PATCH 00/27] btrfs: limited subpage compressed write support Qu Wenruo
2021-07-13 6:14 ` [PATCH 01/27] btrfs: remove unused parameter @nr_pages in add_ra_bio_pages() Qu Wenruo
2021-07-13 6:14 ` [PATCH 02/27] btrfs: remove unnecessary parameter @delalloc_start for writepage_delalloc() Qu Wenruo
2021-07-13 6:14 ` [PATCH 03/27] btrfs: use async_chunk::async_cow to replace the confusing pending pointer Qu Wenruo
2021-07-13 7:36 ` Nikolay Borisov
2021-07-13 6:14 ` [PATCH 04/27] btrfs: don't pass compressed pages to btrfs_writepage_endio_finish_ordered() Qu Wenruo
2021-07-13 6:14 ` [PATCH 05/27] btrfs: make add_ra_bio_pages() to be subpage compatible Qu Wenruo
2021-07-13 6:14 ` [PATCH 06/27] btrfs: introduce compressed_bio::pending_sectors to trace compressed bio more elegantly Qu Wenruo
2021-07-13 6:14 ` [PATCH 07/27] btrfs: add subpage checked_bitmap to make PageChecked flag to be subpage compatible Qu Wenruo
2021-07-16 7:54 ` Qu Wenruo
2021-07-13 6:14 ` Qu Wenruo [this message]
2021-07-13 6:14 ` [PATCH 09/27] btrfs: handle errors properly inside btrfs_submit_compressed_write() Qu Wenruo
2021-07-13 6:14 ` [PATCH 10/27] btrfs: introduce submit_compressed_bio() for compression Qu Wenruo
2021-07-13 6:15 ` [PATCH 11/27] btrfs: introduce alloc_compressed_bio() " Qu Wenruo
2021-07-13 6:15 ` [PATCH 12/27] btrfs: make btrfs_submit_compressed_read() to determine stripe boundary at bio allocation time Qu Wenruo
2021-07-13 6:15 ` [PATCH 13/27] btrfs: make btrfs_submit_compressed_write() " Qu Wenruo
2021-07-13 6:15 ` [PATCH 14/27] btrfs: remove unused function btrfs_bio_fits_in_stripe() Qu Wenruo
2021-07-13 6:15 ` [PATCH 15/27] btrfs: refactor submit_compressed_extents() Qu Wenruo
2021-07-13 6:15 ` [PATCH 16/27] btrfs: cleanup for extent_write_locked_range() Qu Wenruo
2021-07-13 6:15 ` [PATCH 17/27] btrfs: make compress_file_range() to be subpage compatible Qu Wenruo
2021-07-13 6:15 ` [PATCH 18/27] btrfs: make btrfs_submit_compressed_write() " Qu Wenruo
2021-07-13 6:15 ` [PATCH 19/27] btrfs: make end_compressed_bio_writeback() to be subpage compatble Qu Wenruo
2021-07-13 6:15 ` [PATCH 20/27] btrfs: make extent_write_locked_range() to be subpage compatible Qu Wenruo
2021-07-13 6:15 ` [PATCH 21/27] btrfs: extract uncompressed async extent submission code into a new helper Qu Wenruo
2021-07-13 6:15 ` [PATCH 22/27] btrfs: rework lzo_compress_pages() to make it subpage compatible Qu Wenruo
2021-07-13 6:15 ` [PATCH 23/27] btrfs: teach __extent_writepage() to handle locked page differently Qu Wenruo
2021-07-13 6:15 ` [PATCH 24/27] btrfs: allow page to be unlocked by btrfs_page_end_writer_lock() even if it's locked by plain page_lock() Qu Wenruo
2021-07-13 6:15 ` [PATCH 25/27] btrfs: allow subpage to compress a range which only covers one page Qu Wenruo
2021-07-13 6:15 ` [PATCH 26/27] btrfs: don't run delalloc range which is beyond the locked_page to prevent deadlock for subpage compression Qu Wenruo
2021-07-13 6:15 ` [PATCH 27/27] btrfs: only allow subpage compression if the range is fully page aligned Qu Wenruo
2021-07-16 9:11 ` [PATCH 00/27] btrfs: limited subpage compressed write support Qu Wenruo
2021-07-20 5:00 ` Qu Wenruo
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=20210713061516.163318-9-wqu@suse.com \
--to=wqu@suse.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).