From 393debc23c7820211d1c8253dd6a8408a7628fe7 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 21 Sep 2017 10:23:35 -0700
Subject: md: separate request handling
With commit cc27b0c78c79, pers->make_request could bail out without handling
the bio. If that happens, we should retry. The commit fixes md_make_request
but not other call sites. Separate the request handling part, so other call
sites can use it.
Reported-by: Nate Dailey <nate.dailey@stratus.com>
Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start())
Cc: stable@vger.kernel.org
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/md.c | 58 ++++++++++++++++++++++++++++++++-------------------------
drivers/md/md.h | 1 +
2 files changed, 34 insertions(+), 25 deletions(-)
(limited to 'drivers')
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 08fcaebc61bd..1db1a22ed835 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
* call has finished, the bio has been linked into some internal structure
* and so is visible to ->quiesce(), so we don't need the refcount any more.
*/
+void md_handle_request(struct mddev *mddev, struct bio *bio)
+{
+check_suspended:
+ rcu_read_lock();
+ if (mddev->suspended) {
+ DEFINE_WAIT(__wait);
+ for (;;) {
+ prepare_to_wait(&mddev->sb_wait, &__wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!mddev->suspended)
+ break;
+ rcu_read_unlock();
+ schedule();
+ rcu_read_lock();
+ }
+ finish_wait(&mddev->sb_wait, &__wait);
+ }
+ atomic_inc(&mddev->active_io);
+ rcu_read_unlock();
+
+ if (!mddev->pers->make_request(mddev, bio)) {
+ atomic_dec(&mddev->active_io);
+ wake_up(&mddev->sb_wait);
+ goto check_suspended;
+ }
+
+ if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+ wake_up(&mddev->sb_wait);
+}
+EXPORT_SYMBOL(md_handle_request);
+
static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
{
const int rw = bio_data_dir(bio);
@@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
bio_endio(bio);
return BLK_QC_T_NONE;
}
-check_suspended:
- rcu_read_lock();
- if (mddev->suspended) {
- DEFINE_WAIT(__wait);
- for (;;) {
- prepare_to_wait(&mddev->sb_wait, &__wait,
- TASK_UNINTERRUPTIBLE);
- if (!mddev->suspended)
- break;
- rcu_read_unlock();
- schedule();
- rcu_read_lock();
- }
- finish_wait(&mddev->sb_wait, &__wait);
- }
- atomic_inc(&mddev->active_io);
- rcu_read_unlock();
/*
* save the sectors now since our bio can
@@ -310,20 +324,14 @@ check_suspended:
sectors = bio_sectors(bio);
/* bio could be mergeable after passing to underlayer */
bio->bi_opf &= ~REQ_NOMERGE;
- if (!mddev->pers->make_request(mddev, bio)) {
- atomic_dec(&mddev->active_io);
- wake_up(&mddev->sb_wait);
- goto check_suspended;
- }
+
+ md_handle_request(mddev, bio);
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
part_stat_unlock();
- if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
- wake_up(&mddev->sb_wait);
-
return BLK_QC_T_NONE;
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 561d22b9a9a8..d8287d3cd1bf 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev);
extern int md_rdev_init(struct md_rdev *rdev);
extern void md_rdev_clear(struct md_rdev *rdev);
+extern void md_handle_request(struct mddev *mddev, struct bio *bio);
extern void mddev_suspend(struct mddev *mddev);
extern void mddev_resume(struct mddev *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
--
cgit v1.2.3
From 79bf31a3b2a7ca467cfec8ff97d359a77065d01f Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 21 Sep 2017 09:55:28 -0700
Subject: md: fix a race condition for flush request handling
md_submit_flush_data calls pers->make_request, which missed the suspend check.
Fix it with the new md_handle_request API.
Reported-by: Nate Dailey <nate.dailey@stratus.com>
Tested-by: Nate Dailey <nate.dailey@stratus.com>
Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start())
Cc: stable@vger.kernel.org
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/md.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
(limited to 'drivers')
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1db1a22ed835..0ff1bbf6c90e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -447,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws)
struct mddev *mddev = container_of(ws, struct mddev, flush_work);
struct bio *bio = mddev->flush_bio;
+ /*
+ * must reset flush_bio before calling into md_handle_request to avoid a
+ * deadlock, because other bios passed md_handle_request suspend check
+ * could wait for this and below md_handle_request could wait for those
+ * bios because of suspend check
+ */
+ mddev->flush_bio = NULL;
+ wake_up(&mddev->sb_wait);
+
if (bio->bi_iter.bi_size == 0)
/* an empty barrier - all done */
bio_endio(bio);
else {
bio->bi_opf &= ~REQ_PREFLUSH;
- mddev->pers->make_request(mddev, bio);
+ md_handle_request(mddev, bio);
}
-
- mddev->flush_bio = NULL;
- wake_up(&mddev->sb_wait);
}
void md_flush_request(struct mddev *mddev, struct bio *bio)
--
cgit v1.2.3
From c4d6a1b8e8ea79c439a4871cba540443c9eb13b9 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 21 Sep 2017 10:29:22 -0700
Subject: dm-raid: fix a race condition in request handling
raid_map calls pers->make_request, which missed the suspend check. Fix it with
the new md_handle_request API.
Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start())
Cc: Heinz Mauelshagen <heinzm@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/dm-raid.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'drivers')
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5bfe285ea9d1..1ac58c5651b7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
return DM_MAPIO_REQUEUE;
- mddev->pers->make_request(mddev, bio);
+ md_handle_request(mddev, bio);
return DM_MAPIO_SUBMITTED;
}
--
cgit v1.2.3
From 7d5d7b5058fbd638914e42504677141a69f43011 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 21 Sep 2017 11:03:52 -0700
Subject: md/raid5: cap worker count
static checker reports a potential integer overflow. Cap the worker count to
avoid the overflow.
Reported:-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/raid5.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
(limited to 'drivers')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 076409455b60..928e24a07133 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6575,14 +6575,17 @@ static ssize_t
raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
{
struct r5conf *conf;
- unsigned long new;
+ unsigned int new;
int err;
struct r5worker_group *new_groups, *old_groups;
int group_cnt, worker_cnt_per_group;
if (len >= PAGE_SIZE)
return -EINVAL;
- if (kstrtoul(page, 10, &new))
+ if (kstrtouint(page, 10, &new))
+ return -EINVAL;
+ /* 8192 should be big enough */
+ if (new > 8192)
return -EINVAL;
err = mddev_lock(mddev);
--
cgit v1.2.3