Merge tag 'for-5.19/drivers-2022-06-02' of git://git.kernel.dk/linux-block

Pull more block driver updates from Jens Axboe:
 "A collection of stragglers that were late on sending in their changes
  and just followup fixes.

   - NVMe fixes pull request via Christoph:
       - set controller enable bit in a separate write (Niklas Cassel)
       - disable namespace identifiers for the MAXIO MAP1001 (Christoph)
       - fix a comment typo (Julia Lawall)"

   - MD fixes pull request via Song:
       - Remove uses of bdevname (Christoph Hellwig)
       - Bug fixes (Guoqing Jiang, and Xiao Ni)

   - bcache fixes series (Coly)

   - null_blk zoned write fix (Damien)

   - nbd fixes (Yu, Zhang)

   - Fix for loop partition scanning (Christoph)"

* tag 'for-5.19/drivers-2022-06-02' of git://git.kernel.dk/linux-block: (23 commits)
  block: null_blk: Fix null_zone_write()
  nvmet: fix typo in comment
  nvme: set controller enable bit in a separate write
  nvme-pci: disable namespace identifiers for the MAXIO MAP1001
  bcache: avoid unnecessary soft lockup in kworker update_writeback_rate()
  nbd: use pr_err to output error message
  nbd: fix possible overflow on 'first_minor' in nbd_dev_add()
  nbd: fix io hung while disconnecting device
  nbd: don't clear 'NBD_CMD_INFLIGHT' flag if request is not completed
  nbd: fix race between nbd_alloc_config() and module removal
  nbd: call genl_unregister_family() first in nbd_cleanup()
  md: bcache: check the return value of kzalloc() in detached_dev_do_request()
  bcache: memset on stack variables in bch_btree_check() and bch_sectors_dirty_init()
  block, loop: support partitions without scanning
  bcache: avoid journal no-space deadlock by reserving 1 journal bucket
  bcache: remove incremental dirty sector counting for bch_sectors_dirty_init()
  bcache: improve multithreaded bch_sectors_dirty_init()
  bcache: improve multithreaded bch_btree_check()
  md: fix double free of io_acct_set bioset
  md: Don't set mddev private to NULL in raid0 pers->free
  ...

9 files changed, 130 insertions, 113 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 9ed9c955add7..2acda9cea0f9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -395,6 +395,13 @@ struct cached_dev {
 	atomic_t		io_errors;
 	unsigned int		error_limit;
 	unsigned int		offline_seconds;
+
+	/*
+	 * Retry to update writeback_rate if contention happens for
+	 * down_read(dc->writeback_lock) in update_writeback_rate()
+	 */
+#define BCH_WBRATE_UPDATE_MAX_SKIPS	15
+	unsigned int		rate_update_retry;
 };
 
 enum alloc_reserve {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ad9f16689419..e136d6edc1ed 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -2006,8 +2006,7 @@ int bch_btree_check(struct cache_set *c)
 	int i;
 	struct bkey *k = NULL;
 	struct btree_iter iter;
-	struct btree_check_state *check_state;
-	char name[32];
+	struct btree_check_state check_state;
 
 	/* check and mark root node keys */
 	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
@@ -2018,63 +2017,59 @@ int bch_btree_check(struct cache_set *c)
 	if (c->root->level == 0)
 		return 0;
 
-	check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL);
-	if (!check_state)
-		return -ENOMEM;
-
-	check_state->c = c;
-	check_state->total_threads = bch_btree_chkthread_nr();
-	check_state->key_idx = 0;
-	spin_lock_init(&check_state->idx_lock);
-	atomic_set(&check_state->started, 0);
-	atomic_set(&check_state->enough, 0);
-	init_waitqueue_head(&check_state->wait);
+	memset(&check_state, 0, sizeof(struct btree_check_state));
+	check_state.c = c;
+	check_state.total_threads = bch_btree_chkthread_nr();
+	check_state.key_idx = 0;
+	spin_lock_init(&check_state.idx_lock);
+	atomic_set(&check_state.started, 0);
+	atomic_set(&check_state.enough, 0);
+	init_waitqueue_head(&check_state.wait);
 
+	rw_lock(0, c->root, c->root->level);
 	/*
 	 * Run multiple threads to check btree nodes in parallel,
-	 * if check_state->enough is non-zero, it means current
+	 * if check_state.enough is non-zero, it means current
 	 * running check threads are enough, unncessary to create
 	 * more.
 	 */
-	for (i = 0; i < check_state->total_threads; i++) {
-		/* fetch latest check_state->enough earlier */
+	for (i = 0; i < check_state.total_threads; i++) {
+		/* fetch latest check_state.enough earlier */
 		smp_mb__before_atomic();
-		if (atomic_read(&check_state->enough))
+		if (atomic_read(&check_state.enough))
 			break;
 
-		check_state->infos[i].result = 0;
-		check_state->infos[i].state = check_state;
-		snprintf(name, sizeof(name), "bch_btrchk[%u]", i);
-		atomic_inc(&check_state->started);
+		check_state.infos[i].result = 0;
+		check_state.infos[i].state = &check_state;
 
-		check_state->infos[i].thread =
+		check_state.infos[i].thread =
 			kthread_run(bch_btree_check_thread,
-				    &check_state->infos[i],
-				    name);
-		if (IS_ERR(check_state->infos[i].thread)) {
+				    &check_state.infos[i],
+				    "bch_btrchk[%d]", i);
+		if (IS_ERR(check_state.infos[i].thread)) {
 			pr_err("fails to run thread bch_btrchk[%d]\n", i);
 			for (--i; i >= 0; i--)
-				kthread_stop(check_state->infos[i].thread);
+				kthread_stop(check_state.infos[i].thread);
 			ret = -ENOMEM;
 			goto out;
 		}
+		atomic_inc(&check_state.started);
 	}
 
 	/*
 	 * Must wait for all threads to stop.
 	 */
-	wait_event_interruptible(check_state->wait,
-				 atomic_read(&check_state->started) == 0);
+	wait_event(check_state.wait, atomic_read(&check_state.started) == 0);
 
-	for (i = 0; i < check_state->total_threads; i++) {
-		if (check_state->infos[i].result) {
-			ret = check_state->infos[i].result;
+	for (i = 0; i < check_state.total_threads; i++) {
+		if (check_state.infos[i].result) {
+			ret = check_state.infos[i].result;
 			goto out;
 		}
 	}
 
 out:
-	kfree(check_state);
+	rw_unlock(0, c->root);
 	return ret;
 }
 
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index 50482107134f..1b5fdbc0d83e 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -226,7 +226,7 @@ struct btree_check_info {
 	int				result;
 };
 
-#define BCH_BTR_CHKTHREAD_MAX	64
+#define BCH_BTR_CHKTHREAD_MAX	12
 struct btree_check_state {
 	struct cache_set		*c;
 	int				total_threads;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index df5347ea450b..e5da469a4235 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -405,6 +405,11 @@ err:
 	return ret;
 }
 
+void bch_journal_space_reserve(struct journal *j)
+{
+	j->do_reserve = true;
+}
+
 /* Journalling */
 
 static void btree_flush_write(struct cache_set *c)
@@ -621,12 +626,30 @@ static void do_journal_discard(struct cache *ca)
 	}
 }
 
+static unsigned int free_journal_buckets(struct cache_set *c)
+{
+	struct journal *j = &c->journal;
+	struct cache *ca = c->cache;
+	struct journal_device *ja = &c->cache->journal;
+	unsigned int n;
+
+	/* In case njournal_buckets is not power of 2 */
+	if (ja->cur_idx >= ja->discard_idx)
+		n = ca->sb.njournal_buckets +  ja->discard_idx - ja->cur_idx;
+	else
+		n = ja->discard_idx - ja->cur_idx;
+
+	if (n > (1 + j->do_reserve))
+		return n - (1 + j->do_reserve);
+
+	return 0;
+}
+
 static void journal_reclaim(struct cache_set *c)
 {
 	struct bkey *k = &c->journal.key;
 	struct cache *ca = c->cache;
 	uint64_t last_seq;
-	unsigned int next;
 	struct journal_device *ja = &ca->journal;
 	atomic_t p __maybe_unused;
 
@@ -649,12 +672,10 @@ static void journal_reclaim(struct cache_set *c)
 	if (c->journal.blocks_free)
 		goto out;
 
-	next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
-	/* No space available on this device */
-	if (next == ja->discard_idx)
+	if (!free_journal_buckets(c))
 		goto out;
 
-	ja->cur_idx = next;
+	ja->cur_idx = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
 	k->ptr[0] = MAKE_PTR(0,
 			     bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
 			     ca->sb.nr_this_dev);
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index f2ea34d5f431..cd316b4a1e95 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -105,6 +105,7 @@ struct journal {
 	spinlock_t		lock;
 	spinlock_t		flush_write_lock;
 	bool			btree_flushing;
+	bool			do_reserve;
 	/* used when waiting because the journal was full */
 	struct closure_waitlist	wait;
 	struct closure		io;
@@ -182,5 +183,6 @@ int bch_journal_replay(struct cache_set *c, struct list_head *list);
 
 void bch_journal_free(struct cache_set *c);
 int bch_journal_alloc(struct cache_set *c);
+void bch_journal_space_reserve(struct journal *j);
 
 #endif /* _BCACHE_JOURNAL_H */
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 9c5dde73da88..f2c5a7e06fa9 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1105,6 +1105,12 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
 	 * which would call closure_get(&dc->disk.cl)
 	 */
 	ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
+	if (!ddip) {
+		bio->bi_status = BLK_STS_RESOURCE;
+		bio->bi_end_io(bio);
+		return;
+	}
+
 	ddip->d = d;
 	/* Count on the bcache device */
 	ddip->orig_bdev = orig_bdev;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2f49e31142f6..3563d15dbaf2 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2127,6 +2127,7 @@ static int run_cache_set(struct cache_set *c)
 
 	flash_devs_run(c);
 
+	bch_journal_space_reserve(&c->journal);
 	set_bit(CACHE_SET_RUNNING, &c->flags);
 	return 0;
 err:
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 9ee0005874cd..3f0ff3aab6f2 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -235,19 +235,27 @@ static void update_writeback_rate(struct work_struct *work)
 		return;
 	}
 
-	if (atomic_read(&dc->has_dirty) && dc->writeback_percent) {
-		/*
-		 * If the whole cache set is idle, set_at_max_writeback_rate()
-		 * will set writeback rate to a max number. Then it is
-		 * unncessary to update writeback rate for an idle cache set
-		 * in maximum writeback rate number(s).
-		 */
-		if (!set_at_max_writeback_rate(c, dc)) {
-			down_read(&dc->writeback_lock);
+	/*
+	 * If the whole cache set is idle, set_at_max_writeback_rate()
+	 * will set writeback rate to a max number. Then it is
+	 * unncessary to update writeback rate for an idle cache set
+	 * in maximum writeback rate number(s).
+	 */
+	if (atomic_read(&dc->has_dirty) && dc->writeback_percent &&
+	    !set_at_max_writeback_rate(c, dc)) {
+		do {
+			if (!down_read_trylock((&dc->writeback_lock))) {
+				dc->rate_update_retry++;
+				if (dc->rate_update_retry <=
+				    BCH_WBRATE_UPDATE_MAX_SKIPS)
+					break;
+				down_read(&dc->writeback_lock);
+				dc->rate_update_retry = 0;
+			}
 			__update_writeback_rate(dc);
 			update_gc_after_writeback(c);
 			up_read(&dc->writeback_lock);
-		}
+		} while (0);
 	}
 
 
@@ -805,13 +813,11 @@ static int bch_writeback_thread(void *arg)
 
 /* Init */
 #define INIT_KEYS_EACH_TIME	500000
-#define INIT_KEYS_SLEEP_MS	100
 
 struct sectors_dirty_init {
 	struct btree_op	op;
 	unsigned int	inode;
 	size_t		count;
-	struct bkey	start;
 };
 
 static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -827,11 +833,8 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 					     KEY_START(k), KEY_SIZE(k));
 
 	op->count++;
-	if (atomic_read(&b->c->search_inflight) &&
-	    !(op->count % INIT_KEYS_EACH_TIME)) {
-		bkey_copy_key(&op->start, k);
-		return -EAGAIN;
-	}
+	if (!(op->count % INIT_KEYS_EACH_TIME))
+		cond_resched();
 
 	return MAP_CONTINUE;
 }
@@ -846,24 +849,16 @@ static int bch_root_node_dirty_init(struct cache_set *c,
 	bch_btree_op_init(&op.op, -1);
 	op.inode = d->id;
 	op.count = 0;
-	op.start = KEY(op.inode, 0, 0);
-
-	do {
-		ret = bcache_btree(map_keys_recurse,
-				   k,
-				   c->root,
-				   &op.op,
-				   &op.start,
-				   sectors_dirty_init_fn,
-				   0);
-		if (ret == -EAGAIN)
-			schedule_timeout_interruptible(
-				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
-		else if (ret < 0) {
-			pr_warn("sectors dirty init failed, ret=%d!\n", ret);
-			break;
-		}
-	} while (ret == -EAGAIN);
+
+	ret = bcache_btree(map_keys_recurse,
+			   k,
+			   c->root,
+			   &op.op,
+			   &KEY(op.inode, 0, 0),
+			   sectors_dirty_init_fn,
+			   0);
+	if (ret < 0)
+		pr_warn("sectors dirty init failed, ret=%d!\n", ret);
 
 	return ret;
 }
@@ -907,7 +902,6 @@ static int bch_dirty_init_thread(void *arg)
 				goto out;
 			}
 			skip_nr--;
-			cond_resched();
 		}
 
 		if (p) {
@@ -917,7 +911,6 @@ static int bch_dirty_init_thread(void *arg)
 
 		p = NULL;
 		prev_idx = cur_idx;
-		cond_resched();
 	}
 
 out:
@@ -948,67 +941,56 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	struct btree_iter iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
-	struct bch_dirty_init_state *state;
-	char name[32];
+	struct bch_dirty_init_state state;
 
 	/* Just count root keys if no leaf node */
+	rw_lock(0, c->root, c->root->level);
 	if (c->root->level == 0) {
 		bch_btree_op_init(&op.op, -1);
 		op.inode = d->id;
 		op.count = 0;
-		op.start = KEY(op.inode, 0, 0);
 
 		for_each_key_filter(&c->root->keys,
 				    k, &iter, bch_ptr_invalid)
 			sectors_dirty_init_fn(&op.op, c->root, k);
-		return;
-	}
 
-	state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
-	if (!state) {
-		pr_warn("sectors dirty init failed: cannot allocate memory\n");
+		rw_unlock(0, c->root);
 		return;
 	}
 
-	state->c = c;
-	state->d = d;
-	state->total_threads = bch_btre_dirty_init_thread_nr();
-	state->key_idx = 0;
-	spin_lock_init(&state->idx_lock);
-	atomic_set(&state->started, 0);
-	atomic_set(&state->enough, 0);
-	init_waitqueue_head(&state->wait);
-
-	for (i = 0; i < state->total_threads; i++) {
-		/* Fetch latest state->enough earlier */
+	memset(&state, 0, sizeof(struct bch_dirty_init_state));
+	state.c = c;
+	state.d = d;
+	state.total_threads = bch_btre_dirty_init_thread_nr();
+	state.key_idx = 0;
+	spin_lock_init(&state.idx_lock);
+	atomic_set(&state.started, 0);
+	atomic_set(&state.enough, 0);
+	init_waitqueue_head(&state.wait);
+
+	for (i = 0; i < state.total_threads; i++) {
+		/* Fetch latest state.enough earlier */
 		smp_mb__before_atomic();
-		if (atomic_read(&state->enough))
+		if (atomic_read(&state.enough))
 			break;
 
-		state->infos[i].state = state;
-		atomic_inc(&state->started);
-		snprintf(name, sizeof(name), "bch_dirty_init[%d]", i);
-
-		state->infos[i].thread =
-			kthread_run(bch_dirty_init_thread,
-				    &state->infos[i],
-				    name);
-		if (IS_ERR(state->infos[i].thread)) {
+		state.infos[i].state = &state;
+		state.infos[i].thread =
+			kthread_run(bch_dirty_init_thread, &state.infos[i],
+				    "bch_dirtcnt[%d]", i);
+		if (IS_ERR(state.infos[i].thread)) {
 			pr_err("fails to run thread bch_dirty_init[%d]\n", i);
 			for (--i; i >= 0; i--)
-				kthread_stop(state->infos[i].thread);
+				kthread_stop(state.infos[i].thread);
 			goto out;
 		}
+		atomic_inc(&state.started);
 	}
 
-	/*
-	 * Must wait for all threads to stop.
-	 */
-	wait_event_interruptible(state->wait,
-		 atomic_read(&state->started) == 0);
-
 out:
-	kfree(state);
+	/* Must wait for all threads to stop. */
+	wait_event(state.wait, atomic_read(&state.started) == 0);
+	rw_unlock(0, c->root);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -1032,6 +1014,9 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_rate_fp_term_high = 1000;
 	dc->writeback_rate_i_term_inverse = 10000;
 
+	/* For dc->writeback_lock contention in update_writeback_rate() */
+	dc->rate_update_retry = 0;
+
 	WARN_ON(test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags));
 	INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
 }
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 02b2f9df73f6..31df716951f6 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -20,7 +20,7 @@
 #define BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID 57
 #define BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH 64
 
-#define BCH_DIRTY_INIT_THRD_MAX	64
+#define BCH_DIRTY_INIT_THRD_MAX	12
 /*
  * 14 (16384ths) is chosen here as something that each backing device
  * should be a reasonable fraction of the share, and not to blow up