Merge tag 'md/4.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD fixes from Shaohua Li:
 "A few fixes for MD. Mainly fix a problem introduced in 4.13, which we
  retry bio for some code paths but not all in some situations"

* tag 'md/4.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md/raid5: cap worker count
  dm-raid: fix a race condition in request handling
  md: fix a race condition for flush request handling
  md: separate request handling

4 files changed, 50 insertions, 32 deletions

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;
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 08fcaebc61bd..0ff1bbf6c90e 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;
 }
 
@@ -439,16 +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)
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,
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);