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
  ...

block/genhd.c

@@ -385,6 +385,8 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
 		return -EINVAL;
+	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
 

drivers/block/loop.c

@@ -1102,7 +1102,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 	if (partscan)
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
+		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1198,7 +1198,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	 */
 	lo->lo_flags = 0;
 	if (!part_shift)
-		lo->lo_disk->flags |= GENHD_FL_NO_PART;
+		set_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 	mutex_lock(&lo->lo_mutex);
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
@@ -1308,7 +1308,7 @@ out_unfreeze:
 
 	if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
+		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 		partscan = true;
 	}
 out_unlock:
@@ -2011,7 +2011,7 @@ static int loop_add(int i)
 	 * userspace tools. Parameters like this in general should be avoided.
 	 */
 	if (!part_shift)
-		disk->flags |= GENHD_FL_NO_PART;
+		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 	mutex_init(&lo->lo_mutex);
 	lo->lo_number		= i;
 	spin_lock_init(&lo->lo_lock);

drivers/block/nbd.c

@@ -403,13 +403,14 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	if (!mutex_trylock(&cmd->lock))
 		return BLK_EH_RESET_TIMER;
 
-	if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+	if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
 		mutex_unlock(&cmd->lock);
 		return BLK_EH_DONE;
 	}
 
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		cmd->status = BLK_STS_TIMEOUT;
+		__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
 		mutex_unlock(&cmd->lock);
 		goto done;
 	}
@@ -478,6 +479,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n");
 	set_bit(NBD_RT_TIMEDOUT, &config->runtime_flags);
 	cmd->status = BLK_STS_IOERR;
+	__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
 	mutex_unlock(&cmd->lock);
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
@@ -745,7 +747,7 @@ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
 	cmd = blk_mq_rq_to_pdu(req);
 
 	mutex_lock(&cmd->lock);
-	if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+	if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
 		dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)",
 			tag, cmd->status, cmd->flags);
 		ret = -ENOENT;
@@ -854,8 +856,16 @@ static void recv_work(struct work_struct *work)
 		}
 
 		rq = blk_mq_rq_from_pdu(cmd);
-		if (likely(!blk_should_fake_timeout(rq->q)))
-			blk_mq_complete_request(rq);
+		if (likely(!blk_should_fake_timeout(rq->q))) {
+			bool complete;
+
+			mutex_lock(&cmd->lock);
+			complete = __test_and_clear_bit(NBD_CMD_INFLIGHT,
+							&cmd->flags);
+			mutex_unlock(&cmd->lock);
+			if (complete)
+				blk_mq_complete_request(rq);
+		}
 		percpu_ref_put(&q->q_usage_counter);
 	}
 
@@ -1419,7 +1429,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd)
 static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 				 struct block_device *bdev)
 {
-	sock_shutdown(nbd);
+	nbd_clear_sock(nbd);
 	__invalidate_device(bdev, true);
 	nbd_bdev_reset(nbd);
 	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
@@ -1518,15 +1528,20 @@ static struct nbd_config *nbd_alloc_config(void)
 {
 	struct nbd_config *config;
 
+	if (!try_module_get(THIS_MODULE))
+		return ERR_PTR(-ENODEV);
+
 	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
-	if (!config)
-		return NULL;
+	if (!config) {
+		module_put(THIS_MODULE);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
 	config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
 	atomic_set(&config->live_connections, 0);
-	try_module_get(THIS_MODULE);
 	return config;
 }
 
@@ -1553,12 +1568,13 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		config = nbd->config = nbd_alloc_config();
-		if (!config) {
-			ret = -ENOMEM;
+		config = nbd_alloc_config();
+		if (IS_ERR(config)) {
+			ret = PTR_ERR(config);
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
+		nbd->config = config;
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
@@ -1798,17 +1814,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	refcount_set(&nbd->refs, 0);
 	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
-
-	/* Too big first_minor can cause duplicate creation of
-	 * sysfs files/links, since index << part_shift might overflow, or
-	 * MKDEV() expect that the max bits of first_minor is 20.
-	 */
 	disk->first_minor = index << part_shift;
-	if (disk->first_minor < index || disk->first_minor > MINORMASK) {
-		err = -EINVAL;
-		goto out_free_work;
-	}
-
 	disk->minors = 1 << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
@@ -1913,14 +1919,25 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (info->attrs[NBD_ATTR_INDEX])
+	if (info->attrs[NBD_ATTR_INDEX]) {
 		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+		/*
+		 * Too big first_minor can cause duplicate creation of
+		 * sysfs files/links, since index << part_shift might overflow, or
+		 * MKDEV() expect that the max bits of first_minor is 20.
+		 */
+		if (index < 0 || index > MINORMASK >> part_shift) {
+			pr_err("illegal input index %d\n", index);
+			return -EINVAL;
+		}
+	}
 	if (!info->attrs[NBD_ATTR_SOCKETS]) {
-		printk(KERN_ERR "nbd: must specify at least one socket\n");
+		pr_err("must specify at least one socket\n");
 		return -EINVAL;
 	}
 	if (!info->attrs[NBD_ATTR_SIZE_BYTES]) {
-		printk(KERN_ERR "nbd: must specify a size in bytes for the device\n");
+		pr_err("must specify a size in bytes for the device\n");
 		return -EINVAL;
 	}
 again:
@@ -1956,7 +1973,7 @@ again:
 		nbd_put(nbd);
 		if (index == -1)
 			goto again;
-		printk(KERN_ERR "nbd: nbd%d already in use\n", index);
+		pr_err("nbd%d already in use\n", index);
 		return -EBUSY;
 	}
 	if (WARN_ON(nbd->config)) {
@@ -1964,13 +1981,14 @@ again:
 		nbd_put(nbd);
 		return -EINVAL;
 	}
-	config = nbd->config = nbd_alloc_config();
-	if (!nbd->config) {
+	config = nbd_alloc_config();
+	if (IS_ERR(config)) {
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
-		printk(KERN_ERR "nbd: couldn't allocate config\n");
-		return -ENOMEM;
+		pr_err("couldn't allocate config\n");
+		return PTR_ERR(config);
 	}
+	nbd->config = config;
 	refcount_set(&nbd->config_refs, 1);
 	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 
@@ -2023,7 +2041,7 @@ again:
 			struct nlattr *socks[NBD_SOCK_MAX+1];
 
 			if (nla_type(attr) != NBD_SOCK_ITEM) {
-				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				pr_err("socks must be embedded in a SOCK_ITEM attr\n");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -2032,7 +2050,7 @@ again:
 							  nbd_sock_policy,
 							  info->extack);
 			if (ret != 0) {
-				printk(KERN_ERR "nbd: error processing sock list\n");
+				pr_err("error processing sock list\n");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -2104,7 +2122,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 		return -EPERM;
 
 	if (!info->attrs[NBD_ATTR_INDEX]) {
-		printk(KERN_ERR "nbd: must specify an index to disconnect\n");
+		pr_err("must specify an index to disconnect\n");
 		return -EINVAL;
 	}
 	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
@@ -2112,14 +2130,12 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
 	nbd = idr_find(&nbd_index_idr, index);
 	if (!nbd) {
 		mutex_unlock(&nbd_index_mutex);
-		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
-		       index);
+		pr_err("couldn't find device at index %d\n", index);
 		return -EINVAL;
 	}
 	if (!refcount_inc_not_zero(&nbd->refs)) {
 		mutex_unlock(&nbd_index_mutex);
-		printk(KERN_ERR "nbd: device at index %d is going down\n",
-		       index);
+		pr_err("device at index %d is going down\n", index);
 		return -EINVAL;
 	}
 	mutex_unlock(&nbd_index_mutex);
@@ -2144,7 +2160,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 		return -EPERM;
 
 	if (!info->attrs[NBD_ATTR_INDEX]) {
-		printk(KERN_ERR "nbd: must specify a device to reconfigure\n");
+		pr_err("must specify a device to reconfigure\n");
 		return -EINVAL;
 	}
 	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
@@ -2152,8 +2168,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	nbd = idr_find(&nbd_index_idr, index);
 	if (!nbd) {
 		mutex_unlock(&nbd_index_mutex);
-		printk(KERN_ERR "nbd: couldn't find a device at index %d\n",
-		       index);
+		pr_err("couldn't find a device at index %d\n", index);
 		return -EINVAL;
 	}
 	if (nbd->backend) {
@@ -2174,8 +2189,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	}
 	if (!refcount_inc_not_zero(&nbd->refs)) {
 		mutex_unlock(&nbd_index_mutex);
-		printk(KERN_ERR "nbd: device at index %d is going down\n",
-		       index);
+		pr_err("device at index %d is going down\n", index);
 		return -EINVAL;
 	}
 	mutex_unlock(&nbd_index_mutex);
@@ -2239,7 +2253,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 			struct nlattr *socks[NBD_SOCK_MAX+1];
 
 			if (nla_type(attr) != NBD_SOCK_ITEM) {
-				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				pr_err("socks must be embedded in a SOCK_ITEM attr\n");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -2248,7 +2262,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 							  nbd_sock_policy,
 							  info->extack);
 			if (ret != 0) {
-				printk(KERN_ERR "nbd: error processing sock list\n");
+				pr_err("error processing sock list\n");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -2465,7 +2479,7 @@ static int __init nbd_init(void)
 	BUILD_BUG_ON(sizeof(struct nbd_request) != 28);
 
 	if (max_part < 0) {
-		printk(KERN_ERR "nbd: max_part must be >= 0\n");
+		pr_err("max_part must be >= 0\n");
 		return -EINVAL;
 	}
 
@@ -2528,6 +2542,12 @@ static void __exit nbd_cleanup(void)
 	struct nbd_device *nbd;
 	LIST_HEAD(del_list);
 
+	/*
+	 * Unregister netlink interface prior to waiting
+	 * for the completion of netlink commands.
+	 */
+	genl_unregister_family(&nbd_genl_family);
+
 	nbd_dbg_close();
 
 	mutex_lock(&nbd_index_mutex);
@@ -2537,8 +2557,11 @@ static void __exit nbd_cleanup(void)
 	while (!list_empty(&del_list)) {
 		nbd = list_first_entry(&del_list, struct nbd_device, list);
 		list_del_init(&nbd->list);
+		if (refcount_read(&nbd->config_refs))
+			pr_err("possibly leaking nbd_config (ref %d)\n",
+					refcount_read(&nbd->config_refs));
 		if (refcount_read(&nbd->refs) != 1)
-			printk(KERN_ERR "nbd: possibly leaking a device\n");
+			pr_err("possibly leaking a device\n");
 		nbd_put(nbd);
 	}
 
@@ -2546,7 +2569,6 @@ static void __exit nbd_cleanup(void)
 	destroy_workqueue(nbd_del_wq);
 
 	idr_destroy(&nbd_index_idr);
-	genl_unregister_family(&nbd_genl_family);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }
 

drivers/block/null_blk/main.c

@@ -77,12 +77,6 @@ enum {
 	NULL_IRQ_TIMER		= 2,
 };
 
-enum {
-	NULL_Q_BIO		= 0,
-	NULL_Q_RQ		= 1,
-	NULL_Q_MQ		= 2,
-};
-
 static bool g_virt_boundary = false;
 module_param_named(virt_boundary, g_virt_boundary, bool, 0444);
 MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False");

drivers/block/null_blk/null_blk.h

@@ -60,6 +60,13 @@ struct nullb_zone {
 	unsigned int capacity;
 };
 
+/* Queue modes */
+enum {
+	NULL_Q_BIO	= 0,
+	NULL_Q_RQ	= 1,
+	NULL_Q_MQ	= 2,
+};
+
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_item item;

drivers/block/null_blk/zoned.c

@@ -398,10 +398,10 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	 */
 	if (append) {
 		sector = zone->wp;
-		if (cmd->bio)
-			cmd->bio->bi_iter.bi_sector = sector;
-		else
+		if (dev->queue_mode == NULL_Q_MQ)
 			cmd->rq->__sector = sector;
+		else
+			cmd->bio->bi_iter.bi_sector = sector;
 	} else if (sector != zone->wp) {
 		ret = BLK_STS_IOERR;
 		goto unlock;

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 {

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;
 }
 

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;

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);

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 */

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;

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:

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);
+
+		rw_unlock(0, c->root);
 		return;
 	}
 
-	state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
-	if (!state) {
-		pr_warn("sectors dirty init failed: cannot allocate memory\n");
-		return;
-	}
+	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);
 
-	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 */
+	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);
 }

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

drivers/md/dm-raid.c

@@ -3725,7 +3725,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev, false);
 		}
 	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;

drivers/md/md-linear.c

@@ -206,7 +206,6 @@ static void linear_free(struct mddev *mddev, void *priv)
 
 static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 {
-	char b[BDEVNAME_SIZE];
 	struct dev_info *tmp_dev;
 	sector_t start_sector, end_sector, data_offset;
 	sector_t bio_sector = bio->bi_iter.bi_sector;
@@ -256,10 +255,10 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	return true;
 
 out_of_bounds:
-	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",
+	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
 	       mdname(mddev),
 	       (unsigned long long)bio->bi_iter.bi_sector,
-	       bdevname(tmp_dev->rdev->bdev, b),
+	       tmp_dev->rdev->bdev,
 	       (unsigned long long)tmp_dev->rdev->sectors,
 	       (unsigned long long)start_sector);
 	bio_io_error(bio);

drivers/md/md-multipath.c

@@ -87,10 +87,9 @@ static void multipath_end_request(struct bio *bio)
 		/*
 		 * oops, IO error:
 		 */
-		char b[BDEVNAME_SIZE];
 		md_error (mp_bh->mddev, rdev);
-		pr_info("multipath: %s: rescheduling sector %llu\n",
-			bdevname(rdev->bdev,b),
+		pr_info("multipath: %pg: rescheduling sector %llu\n",
+			rdev->bdev,
 			(unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
@@ -154,7 +153,6 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev)
 static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct mpconf *conf = mddev->private;
-	char b[BDEVNAME_SIZE];
 
 	if (conf->raid_disks - mddev->degraded <= 1) {
 		/*
@@ -177,9 +175,9 @@ static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	pr_err("multipath: IO failure on %s, disabling IO path.\n"
+	pr_err("multipath: IO failure on %pg, disabling IO path.\n"
 	       "multipath: Operation continuing on %d IO paths.\n",
-	       bdevname(rdev->bdev, b),
+	       rdev->bdev,
 	       conf->raid_disks - mddev->degraded);
 }
 
@@ -197,12 +195,11 @@ static void print_multipath_conf (struct mpconf *conf)
 		 conf->raid_disks);
 
 	for (i = 0; i < conf->raid_disks; i++) {
-		char b[BDEVNAME_SIZE];
 		tmp = conf->multipaths + i;
 		if (tmp->rdev)
-			pr_debug(" disk%d, o:%d, dev:%s\n",
+			pr_debug(" disk%d, o:%d, dev:%pg\n",
 				 i,!test_bit(Faulty, &tmp->rdev->flags),
-				 bdevname(tmp->rdev->bdev,b));
+				 tmp->rdev->bdev);
 	}
 }
 

drivers/md/md.h

@@ -719,7 +719,7 @@ extern struct md_thread *md_register_thread(
 extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev);
+extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
 extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);