summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
authorGuoqing Jiang <jiangguoqing@kylinos.cn>2021-08-24 04:16:54 +0300
committerSong Liu <songliubraving@fb.com>2021-08-28 01:12:14 +0300
commit6607cd319b6b91bff94e90f798a61c031650b514 (patch)
tree2b1baab8e9462a35f47d16ca98cc937584e52f93 /drivers/md
parent46d4703b1db4c86ab5acb2331b10df999f005e8e (diff)
downloadlinux-6607cd319b6b91bff94e90f798a61c031650b514.tar.xz
raid1: ensure write behind bio has less than BIO_MAX_VECS sectors
We can't split write behind bio with more than BIO_MAX_VECS sectors, otherwise the below call trace was triggered because we could allocate oversized write behind bio later. [ 8.097936] bvec_alloc+0x90/0xc0 [ 8.098934] bio_alloc_bioset+0x1b3/0x260 [ 8.099959] raid1_make_request+0x9ce/0xc50 [raid1] [ 8.100988] ? __bio_clone_fast+0xa8/0xe0 [ 8.102008] md_handle_request+0x158/0x1d0 [md_mod] [ 8.103050] md_submit_bio+0xcd/0x110 [md_mod] [ 8.104084] submit_bio_noacct+0x139/0x530 [ 8.105127] submit_bio+0x78/0x1d0 [ 8.106163] ext4_io_submit+0x48/0x60 [ext4] [ 8.107242] ext4_writepages+0x652/0x1170 [ext4] [ 8.108300] ? do_writepages+0x41/0x100 [ 8.109338] ? __ext4_mark_inode_dirty+0x240/0x240 [ext4] [ 8.110406] do_writepages+0x41/0x100 [ 8.111450] __filemap_fdatawrite_range+0xc5/0x100 [ 8.112513] file_write_and_wait_range+0x61/0xb0 [ 8.113564] ext4_sync_file+0x73/0x370 [ext4] [ 8.114607] __x64_sys_fsync+0x33/0x60 [ 8.115635] do_syscall_64+0x33/0x40 [ 8.116670] entry_SYSCALL_64_after_hwframe+0x44/0xae Thanks for the comment from Christoph. [1]. https://bugs.archlinux.org/task/70992 Cc: stable@vger.kernel.org # v5.12+ Reported-by: Jens Stutte <jens@chianterastutte.eu> Tested-by: Jens Stutte <jens@chianterastutte.eu> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Guoqing Jiang <jiangguoqing@kylinos.cn> Signed-off-by: Song Liu <songliubraving@fb.com>
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/raid1.c19
1 files changed, 19 insertions, 0 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 51f2547c2007..21b348408478 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1331,6 +1331,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
struct raid1_plug_cb *plug = NULL;
int first_clone;
int max_sectors;
+ bool write_behind = false;
if (mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1383,6 +1384,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
max_sectors = r1_bio->sectors;
for (i = 0; i < disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+
+ /*
+ * The write-behind io is only attempted on drives marked as
+ * write-mostly, which means we could allocate write behind
+ * bio later.
+ */
+ if (rdev && test_bit(WriteMostly, &rdev->flags))
+ write_behind = true;
+
if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
atomic_inc(&rdev->nr_pending);
blocked_rdev = rdev;
@@ -1456,6 +1466,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
goto retry_write;
}
+ /*
+ * When using a bitmap, we may call alloc_behind_master_bio below.
+ * alloc_behind_master_bio allocates a copy of the data payload a page
+ * at a time and thus needs a new bio that can fit the whole payload
+ * this bio in page sized chunks.
+ */
+ if (write_behind && bitmap)
+ max_sectors = min_t(int, max_sectors,
+ BIO_MAX_VECS * (PAGE_SIZE >> 9));
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
GFP_NOIO, &conf->bio_split);