block-6.7-2023-12-01

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmVqKo4QHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpqL9D/9bPvuA+Oogx+C/kNConjxnuyPBiXcZjb/4
 5gO/6N0FC8yu+HQqgscGTyEjJO2FKfLx+YxxBs1UVIt4Tm+jZwC3nPqw9X4W3RCz
 pK9fxCNlzxey0SZU3ZJQIOtqP3df5Yuas9V/h35GS4m1XaoDE6cPpsIVUrAnoNwg
 W990L8sOy6y4XzMPzyHJCyoDCay1Qp2ly0Vdlz4/ESRmEp564i42nFN+8zpZ/w7h
 V+Ekn6JwP1ssqUeY/k43QcfRzYwSvvnTQJ1y9t3erf6HcHtpbCgnL1jTaGEmr4IS
 1sw3ffqo23xBSsGP+D2OF4+9pwGI9+xwNpYnRdrpDPxKhCn5EEh+g6+f+m7YEnFV
 q1swlMTqHtRLFdYbKe8Tl8hPRwEeSpKy8sXph56hwGZY0T/IyB+Pe3aXrh1DYPA5
 4+GASZHFQPH82P1ibVNdpMRZe4rPPblw38GZauZ1JbI0m0zXqEveB2AgZeCcw1ky
 l7KBdMdGBqSWYVmfKcJd3f30vKPyhMSp4eE9/LFp24vmyIIw+dSp6vup0yrM6jk9
 taUU6PCHzaxmI1YGz1BzNVa8cfYKB6aiWeQ2OGa4Z7ba4TuksMLkbfVvu21jdi+z
 PsL/KlqPSPwFL/3XAZagIb3BXUhoQyfwIU8GnAuw2wTU5RJzWnbwF3wXpNaBIJxI
 8y5OWsFqIg==
 =5kb6
 -----END PGP SIGNATURE-----

Merge tag 'block-6.7-2023-12-01' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
     - Invalid namespace identification error handling (Marizio Ewan,
       Keith)
     - Fabrics keep-alive tuning (Mark)

 - Fix for a bad error check regression in bcache (Markus)

 - Fix for a performance regression with O_DIRECT (Ming)

 - Fix for a flush related deadlock (Ming)

 - Make the read-only warn on per-partition (Yu)

* tag 'block-6.7-2023-12-01' of git://git.kernel.dk/linux:
  nvme-core: check for too small lba shift
  blk-mq: don't count completed flush data request as inflight in case of quiesce
  block: Document the role of the two attribute groups
  block: warn once for each partition in bio_check_ro()
  block: move .bd_inode into 1st cacheline of block_device
  nvme: check for valid nvme_identify_ns() before using it
  nvme-core: fix a memory leak in nvme_ns_info_from_identify()
  nvme: fine-tune sending of first keep-alive
  bcache: revert replacing IS_ERR_OR_NULL with IS_ERR

block/blk-core.c

@@ -501,9 +501,17 @@ static inline void bio_check_ro(struct bio *bio)
 	if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return;
-		pr_warn_ratelimited("Trying to write to read-only block-device %pg\n",
+
-				    bio->bi_bdev);
+		if (bio->bi_bdev->bd_ro_warned)
-		/* Older lvm-tools actually trigger this */
+			return;
+
+		bio->bi_bdev->bd_ro_warned = true;
+		/*
+		 * Use ioctl to set underlying disk of raid/dm to read-only
+		 * will trigger this.
+		 */
+		pr_warn("Trying to write to read-only block-device %pg\n",
+			bio->bi_bdev);
 	}
 }
 

block/blk-mq.c

@@ -1512,14 +1512,26 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
+static bool blk_is_flush_data_rq(struct request *rq)
+{
+	return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq);
+}
+
 static bool blk_mq_rq_inflight(struct request *rq, void *priv)
 {
 	/*
 	 * If we find a request that isn't idle we know the queue is busy
 	 * as it's checked in the iter.
 	 * Return false to stop the iteration.
+	 *
+	 * In case of queue quiesce, if one flush data request is completed,
+	 * don't count it as inflight given the flush sequence is suspended,
+	 * and the original flush data request is invisible to driver, just
+	 * like other pending requests because of quiesce
 	 */
-	if (blk_mq_request_started(rq)) {
+	if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) &&
+				blk_is_flush_data_rq(rq) &&
+				blk_mq_request_completed(rq))) {
 		bool *busy = priv;
 
 		*busy = true;

block/blk-sysfs.c

@@ -615,6 +615,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
 #endif
 
+/* Common attributes for bio-based and request-based queues. */
 static struct attribute *queue_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
@@ -659,6 +660,7 @@ static struct attribute *queue_attrs[] = {
 	NULL,
 };
 
+/* Request-based queue attributes that are not relevant for bio-based queues. */
 static struct attribute *blk_mq_queue_attrs[] = {
 	&queue_requests_entry.attr,
 	&elv_iosched_entry.attr,

drivers/md/bcache/btree.c

@@ -1522,7 +1522,7 @@ out_nocoalesce:
 	bch_keylist_free(&keylist);
 
 	for (i = 0; i < nodes; i++)
-		if (!IS_ERR(new_nodes[i])) {
+		if (!IS_ERR_OR_NULL(new_nodes[i])) {
 			btree_node_free(new_nodes[i]);
 			rw_unlock(true, new_nodes[i]);
 		}

drivers/nvme/host/core.c

@@ -1192,8 +1192,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
 
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work,
+	unsigned long now = jiffies;
-			   nvme_keep_alive_work_period(ctrl));
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay;
+
+	if (time_after(now, ka_next_check_tm))
+		delay = 0;
+	else
+		delay = ka_next_check_tm - now;
+
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1479,7 +1487,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto error;
 	}
 
 	info->anagrpid = id->anagrpid;
@@ -1497,8 +1506,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
 			memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
 	}
+
+error:
 	kfree(id);
-	return 0;
+	return ret;
 }
 
 static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
@@ -1890,9 +1901,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
+	 * or smaller than a sector size yet, so catch this early and don't
+	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT) {
+	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -2029,6 +2041,13 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (id->ncap == 0) {
+		/* namespace not allocated or attached */
+		info->is_removed = true;
+		ret = -ENODEV;
+		goto error;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->lba_shift = id->lbaf[lbaf].ds;
@@ -2090,6 +2109,8 @@ out:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
+
+error:
 	kfree(id);
 	return ret;
 }
@@ -4471,6 +4492,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+	ctrl->ka_last_check_time = jiffies;
 
 	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
 			PAGE_SIZE);

include/linux/blk_types.h

@@ -49,9 +49,10 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
@@ -69,6 +70,7 @@ struct block_device {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	bool			bd_ro_warned;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path