Merge branch 'nvme-5.2' of git://git.infradead.org/nvme into for-5.2/block

Pull NVMe changes from Christoph:

"Below is the first batch of nvme updates for 5.2. This includes the
performance improvements for single segment I/O on PCIe, which introduce
new block helpers, so it might be a good idea to get them in early.

 - various performance optimizations in the PCIe code (Keith and me)
 - new block helpers to support the above (me)
 - nvmet error conversion cleanup (me)
 - nvmet-fc variable sized array cleanup (Gustavo)
 - passthrough ioctl error printk cleanup (Kenneth)
 - small nvmet fixes (Max)
 - endianess conversion cleanup (Max)
 - nvmet-tcp faspath completion optimization (Sagi)"

* 'nvme-5.2' of git://git.infradead.org/nvme: (24 commits)
  nvme: log the error status on Identify Namespace failure
  nvmet: add safety check for subsystem lock during nvmet_ns_changed
  nvmet: never fail double namespace enablement
  nvme-pci: tidy up nvme_map_data
  nvme-pci: optimize mapping single segment requests using SGLs
  nvme-pci: optimize mapping of small single segment requests
  nvme-pci: remove the inline scatterlist optimization
  nvme-pci: split metadata handling from nvme_map_data / nvme_unmap_data
  nvme-pci: do not build a scatterlist to map metadata
  nvme-pci: only call nvme_unmap_data for requests transferring data
  nvme-pci: merge nvme_free_iod into nvme_unmap_data
  nvme-pci: move the call to nvme_cleanup_cmd out of nvme_unmap_data
  nvme-pci: remove nvme_init_iod
  block: add dma_map_bvec helper
  block: add a rq_dma_dir helper
  block: add a rq_integrity_vec helper
  block: add a req_bvec helper
  nvme-pci: remove unused nvme_iod member
  nvme-pci: remove q_dmadev from nvme_queue
  nvme-pci: use a flag for polled queues
  ...

drivers/nvme/host/core.c

@@ -1105,7 +1105,7 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
 
 	error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
 	if (error) {
-		dev_warn(ctrl->device, "Identify namespace failed\n");
+		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
 		kfree(id);
 		return NULL;
 	}
@@ -1588,7 +1588,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 static void nvme_update_disk_info(struct gendisk *disk,
 		struct nvme_ns *ns, struct nvme_id_ns *id)
 {
-	sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
+	sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
 
 	blk_mq_freeze_queue(disk->queue);
@@ -2549,7 +2549,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->crdt[2] = le16_to_cpu(id->crdt3);
 
 	ctrl->oacs = le16_to_cpu(id->oacs);
-	ctrl->oncs = le16_to_cpup(&id->oncs);
+	ctrl->oncs = le16_to_cpu(id->oncs);
 	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;

drivers/nvme/target/core.c

@@ -214,6 +214,8 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 {
 	struct nvmet_ctrl *ctrl;
 
+	lockdep_assert_held(&subsys->lock);
+
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
 		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR))
@@ -494,13 +496,14 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	int ret;
 
 	mutex_lock(&subsys->lock);
-	ret = -EMFILE;
-	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
-		goto out_unlock;
 	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+
 	ret = nvmet_bdev_ns_enable(ns);
 	if (ret == -ENOTBLK)
 		ret = nvmet_file_ns_enable(ns);

drivers/nvme/target/fc.c

@@ -128,12 +128,12 @@ struct nvmet_fc_tgt_queue {
 	struct nvmet_cq			nvme_cq;
 	struct nvmet_sq			nvme_sq;
 	struct nvmet_fc_tgt_assoc	*assoc;
-	struct nvmet_fc_fcp_iod		*fod;		/* array of fcp_iods */
 	struct list_head		fod_list;
 	struct list_head		pending_cmd_list;
 	struct list_head		avail_defer_list;
 	struct workqueue_struct		*work_q;
 	struct kref			ref;
+	struct nvmet_fc_fcp_iod		fod[];		/* array of fcp_iods */
 } __aligned(sizeof(unsigned long long));
 
 struct nvmet_fc_tgt_assoc {
@@ -588,9 +588,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	if (qid > NVMET_NR_QUEUES)
 		return NULL;
 
-	queue = kzalloc((sizeof(*queue) +
-				(sizeof(struct nvmet_fc_fcp_iod) * sqsize)),
-				GFP_KERNEL);
+	queue = kzalloc(struct_size(queue, fod, sqsize), GFP_KERNEL);
 	if (!queue)
 		return NULL;
 
@@ -603,7 +601,6 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	if (!queue->work_q)
 		goto out_a_put;
 
-	queue->fod = (struct nvmet_fc_fcp_iod *)&queue[1];
 	queue->qid = qid;
 	queue->sqsize = sqsize;
 	queue->assoc = assoc;

drivers/nvme/target/io-cmd-bdev.c

@@ -196,7 +196,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
 			GFP_KERNEL, 0, bio);
 	if (ret && ret != -EOPNOTSUPP) {
 		req->error_slba = le64_to_cpu(range->slba);
-		return blk_to_nvme_status(req, errno_to_blk_status(ret));
+		return errno_to_nvme_status(req, ret);
 	}
 	return NVME_SC_SUCCESS;
 }
@@ -252,7 +252,6 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 {
 	struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
 	struct bio *bio = NULL;
-	u16 status = NVME_SC_SUCCESS;
 	sector_t sector;
 	sector_t nr_sector;
 	int ret;
@@ -264,13 +263,12 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 
 	ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
 			GFP_KERNEL, &bio, 0);
-	status = blk_to_nvme_status(req, errno_to_blk_status(ret));
 	if (bio) {
 		bio->bi_private = req;
 		bio->bi_end_io = nvmet_bio_done;
 		submit_bio(bio);
 	} else {
-		nvmet_req_complete(req, status);
+		nvmet_req_complete(req, errno_to_nvme_status(req, ret));
 	}
 }
 

drivers/nvme/target/tcp.c

@@ -371,7 +371,8 @@ static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd)
 	cmd->state = NVMET_TCP_SEND_DATA_PDU;
 
 	pdu->hdr.type = nvme_tcp_c2h_data;
-	pdu->hdr.flags = NVME_TCP_F_DATA_LAST;
+	pdu->hdr.flags = NVME_TCP_F_DATA_LAST | (queue->nvme_sq.sqhd_disabled ?
+						NVME_TCP_F_DATA_SUCCESS : 0);
 	pdu->hdr.hlen = sizeof(*pdu);
 	pdu->hdr.pdo = pdu->hdr.hlen + hdgst;
 	pdu->hdr.plen =
@@ -542,8 +543,19 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 		cmd->state = NVMET_TCP_SEND_DDGST;
 		cmd->offset = 0;
 	} else {
-		nvmet_setup_response_pdu(cmd);
+		if (queue->nvme_sq.sqhd_disabled) {
+			cmd->queue->snd_cmd = NULL;
+			nvmet_tcp_put_cmd(cmd);
+		} else {
+			nvmet_setup_response_pdu(cmd);
+		}
 	}
+
+	if (queue->nvme_sq.sqhd_disabled) {
+		kfree(cmd->iov);
+		sgl_free(cmd->req.sg);
+	}
+
 	return 1;
 
 }
@@ -619,7 +631,13 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
 		return ret;
 
 	cmd->offset += ret;
-	nvmet_setup_response_pdu(cmd);
+
+	if (queue->nvme_sq.sqhd_disabled) {
+		cmd->queue->snd_cmd = NULL;
+		nvmet_tcp_put_cmd(cmd);
+	} else {
+		nvmet_setup_response_pdu(cmd);
+	}
 	return 1;
 }
 

include/linux/blkdev.h

@@ -641,6 +641,13 @@ static inline bool blk_account_rq(struct request *rq)
 
 #define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
 
+#define rq_dma_dir(rq) \
+	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
+#define dma_map_bvec(dev, bv, dir, attrs) \
+	dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
+	(dir), (attrs))
+
 static inline bool queue_is_mq(struct request_queue *q)
 {
 	return q->mq_ops;
@@ -932,6 +939,17 @@ static inline unsigned int blk_rq_payload_bytes(struct request *rq)
 	return blk_rq_bytes(rq);
 }
 
+/*
+ * Return the first full biovec in the request.  The caller needs to check that
+ * there are any bvecs before calling this helper.
+ */
+static inline struct bio_vec req_bvec(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return rq->special_vec;
+	return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
+}
+
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
@@ -1548,6 +1566,17 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
 }
 
+/*
+ * Return the first bvec that contains integrity data.  Only drivers that are
+ * limited to a single integrity segment should use this helper.
+ */
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
+		return NULL;
+	return rq->bio->bi_integrity->bip_vec;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1622,6 +1651,11 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return 0;
 }
 
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {