Merge tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - tcp, fc, and rdma target fixes (Maurizio, Daniel, Hannes,
        Christoph)
      - discard fixes and improvements (Christoph)
      - timeout debug improvements (Keith, Max)
      - various cleanups (Daniel, Max, Giuxen)
      - trace event string fixes (Arnd)
      - shadow doorbell setup on reset fix (William)
      - a write zeroes quirk for SK Hynix (Jim)

 - MD pull request via Song:
      - Sparse warning since v6.0 (Bart)
      - /proc/mdstat regression since v6.7 (Yu Kuai)

 - Use symbolic error value (Christian)

 - IO Priority documentation update (Christian)

 - Fix for accessing queue limits without having entered the queue
   (Christoph, me)

 - Fix for loop dio support (Christoph)

 - Move null_blk off deprecated ida interface (Christophe)

 - Ensure nbd initializes full msghdr (Eric)

 - Fix for a regression with the folio conversion, which is now easier
   to hit because of an unrelated change (Matthew)

 - Remove redundant check in virtio-blk (Li)

 - Fix for a potential hang in sbitmap (Ming)

 - Fix for partial zone appending (Damien)

 - Misc changes and fixes (Bart, me, Kemeng, Dmitry)

* tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux: (45 commits)
  Documentation: block: ioprio: Update schedulers
  loop: fix the the direct I/O support check when used on top of block devices
  blk-mq: Remove the hctx 'run' debugfs attribute
  nbd: always initialize struct msghdr completely
  block: Fix iterating over an empty bio with bio_for_each_folio_all
  block: bio-integrity: fix kcalloc() arguments order
  virtio_blk: remove duplicate check if queue is broken in virtblk_done
  sbitmap: remove stale comment in sbq_calc_wake_batch
  block: Correct a documentation comment in blk-cgroup.c
  null_blk: Remove usage of the deprecated ida_simple_xx() API
  block: ensure we hold a queue reference when using queue limits
  blk-mq: rename blk_mq_can_use_cached_rq
  block: print symbolic error name instead of error code
  blk-mq: fix IO hang from sbitmap wakeup race
  nvmet-rdma: avoid circular locking dependency on install_queue()
  nvmet-tcp: avoid circular locking dependency on install_queue()
  nvme-pci: set doorbell config before unquiescing
  block: fix partial zone append completion handling in req_bio_endio()
  block/iocost: silence warning on 'last_period' potentially being unused
  md/raid1: Use blk_opf_t for read and write operations
  ...

7 files changed, 67 insertions, 49 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0af612387083..85ab0fcf9e88 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1740,13 +1740,13 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		struct nvme_ns_head *head)
 {
 	struct request_queue *queue = disk->queue;
-	u32 size = queue_logical_block_size(queue);
+	u32 max_discard_sectors;
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX))
-		ctrl->max_discard_sectors =
-			nvme_lba_to_sect(head, ctrl->dmrsl);
-
-	if (ctrl->max_discard_sectors == 0) {
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
+		max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
+	} else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
+		max_discard_sectors = UINT_MAX;
+	} else {
 		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
@@ -1754,14 +1754,22 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_granularity = size;
-
-	/* If discard is already enabled, don't reset queue limits */
+	/*
+	 * If discard is already enabled, don't reset queue limits.
+	 *
+	 * This works around the fact that the block layer can't cope well with
+	 * updating the hardware limits when overridden through sysfs.  This is
+	 * harmless because discard limits in NVMe are purely advisory.
+	 */
 	if (queue->limits.max_discard_sectors)
 		return;
 
-	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
-	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
+	blk_queue_max_discard_sectors(queue, max_discard_sectors);
+	if (ctrl->dmrl)
+		blk_queue_max_discard_segments(queue, ctrl->dmrl);
+	else
+		blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
+	queue->limits.discard_granularity = queue_logical_block_size(queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
@@ -2930,14 +2938,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	struct nvme_id_ctrl_nvm *id;
 	int ret;
 
-	if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		ctrl->max_discard_sectors = UINT_MAX;
-		ctrl->max_discard_segments = NVME_DSM_MAX_RANGES;
-	} else {
-		ctrl->max_discard_sectors = 0;
-		ctrl->max_discard_segments = 0;
-	}
-
 	/*
 	 * Even though NVMe spec explicitly states that MDTS is not applicable
 	 * to the write-zeroes, we are cautious and limit the size to the
@@ -2967,8 +2967,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	if (ret)
 		goto free_data;
 
-	if (id->dmrl)
-		ctrl->max_discard_segments = id->dmrl;
+	ctrl->dmrl = id->dmrl;
 	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4be7f6822966..030c80818240 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -303,14 +303,13 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
-	u32 max_discard_sectors;
-	u32 max_discard_segments;
 	u32 max_zeroes_sectors;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32 max_zone_append;
 #endif
 	u16 crdt[3];
 	u16 oncs;
+	u8 dmrl;
 	u32 dmrsl;
 	u16 oacs;
 	u16 sqsize;
@@ -932,6 +931,10 @@ extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
 
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return disk->fops == &nvme_ns_head_ops;
+}
 #else
 #define multipath false
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
@@ -1009,6 +1012,10 @@ static inline void nvme_mpath_start_request(struct request *rq)
 static inline void nvme_mpath_end_request(struct request *rq)
 {
 }
+static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
+{
+	return false;
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
@@ -1037,7 +1044,10 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 {
-	return dev_to_disk(dev)->private_data;
+	struct gendisk *disk = dev_to_disk(dev);
+
+	WARN_ON(nvme_disk_is_ns_head(disk));
+	return disk->private_data;
 }
 
 #ifdef CONFIG_NVME_HWMON
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 61af7ff1a9d6..c1d6357ec98a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
@@ -1310,8 +1311,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, completion polled\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		return BLK_EH_DONE;
 	}
 
@@ -1327,8 +1328,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) QID %d timeout, disable controller\n",
+			 req->tag, nvme_cid(req), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
@@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
+			 req->tag, nvme_cid(req), opcode,
+			 nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -1362,10 +1365,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode),
+		 nvmeq->qid, blk_op_str(req_op(req)), req_op(req),
+		 blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
@@ -2743,10 +2746,10 @@ static void nvme_reset_work(struct work_struct *work)
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
@@ -3408,6 +3411,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1c5c, 0x1D59),   /* SK Hynix BC901 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 391b1465ebfd..fc3eed00f9ff 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -98,7 +98,7 @@ static int nvme_send_pr_command(struct block_device *bdev,
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
 	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
-	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+	    nvme_disk_is_ns_head(bdev->bd_disk))
 		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
 
 	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index c89503da24d7..11dde0d83044 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1946,9 +1946,14 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
-
-	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
-		 rq->tag, nvme_rdma_queue_idx(queue));
+	u8 opcode = req->req.cmd->common.opcode;
+	u8 fctype = req->req.cmd->fabrics.fctype;
+	int qid = nvme_rdma_queue_idx(queue);
+
+	dev_warn(ctrl->ctrl.device,
+		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), opcode,
+		 nvme_opcode_str(qid, opcode, fctype), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index ac24ad102380..754e91111042 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -39,10 +39,9 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->fops == &nvme_bdev_ops)
-		return nvme_get_ns_from_dev(dev)->head;
-	else
+	if (nvme_disk_is_ns_head(disk))
 		return disk->private_data;
+	return nvme_get_ns_from_dev(dev)->head;
 }
 
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
@@ -233,7 +232,8 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 	}
 #ifdef CONFIG_NVME_MULTIPATH
 	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
-		if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */
+		/* per-path attr */
+		if (nvme_disk_is_ns_head(dev_to_disk(dev)))
 			return 0;
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 08805f027810..d058d990532b 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1922,14 +1922,13 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 						      ctrl->opts->subsysnqn);
 		if (!pskid) {
 			dev_err(ctrl->device, "no valid PSK found\n");
-			ret = -ENOKEY;
-			goto out_free_queue;
+			return -ENOKEY;
 		}
 	}
 
 	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		goto out_free_queue;
+		return ret;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
@@ -2433,9 +2432,9 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
-		"queue %d: timeout cid %#x type %d opcode %#x (%s)\n",
-		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
-		opc, nvme_opcode_str(qid, opc, fctype));
+		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, opc,
+		 nvme_opcode_str(qid, opc, fctype), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*