Merge branch 'nvme-4.21' of git://git.infradead.org/nvme into for-4.21/block

Pull NVMe updates from Christoph:

"Here is the second large chunk of nvme updates for 4.21:

 - host and target support for NVMe over TCP (Sagi Grimberg,
	Roy Shterman, Solganik Alexander)
 - error log page support in target (Chaitanya Kulkarni)

plus small fixes and improvements from Jens Axboe and Chengguang Xu."

* 'nvme-4.21' of git://git.infradead.org/nvme: (33 commits)
  nvme-rdma: support separate queue maps for read and write
  nvme-tcp: support separate queue maps for read and write
  nvme-fabrics: allow user to set nr_write_queues for separate queue maps
  nvme-fabrics: add missing nvmf_ctrl_options documentation
  blk-mq-rdma: pass in queue map to blk_mq_rdma_map_queues
  nvmet: update smart log with num err log entries
  nvmet: add error log page cmd handler
  nvmet: add error log support for file backend
  nvmet: add error log support for bdev backend
  nvmet: add error log support for admin-cmd
  nvmet: add error log support for rdma backend
  nvmet: add error log support for fabrics-cmd
  nvmet: add error log support in the core
  nvmet: add interface to update error-log page
  nvmet: add error-log definitions
  nvme: add error log page slot definition
  nvme: remove nvme_common command cdw10 array
  nvmet: remove unused variable
  nvme: provide fallback for discard alloc failure
  nvme: add __exit annotation
  ...

block/blk-mq-rdma.c

@@ -29,24 +29,24 @@
  * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
  * vector, we fallback to the naive mapping.
  */
-int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
 		struct ib_device *dev, int first_vec)
 {
 	const struct cpumask *mask;
 	unsigned int queue, cpu;
 
-	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+	for (queue = 0; queue < map->nr_queues; queue++) {
 		mask = ib_get_vector_affinity(dev, first_vec + queue);
 		if (!mask)
 			goto fallback;
 
 		for_each_cpu(cpu, mask)
-			set->map[0].mq_map[cpu] = queue;
+			map->mq_map[cpu] = map->queue_offset + queue;
 	}
 
 	return 0;
 
 fallback:
-	return blk_mq_map_queues(&set->map[0]);
+	return blk_mq_map_queues(map);
 }
 EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);

drivers/net/wireless/ath/ath6kl/cfg80211.c

@@ -1322,7 +1322,7 @@ static int ath6kl_cfg80211_set_default_key(struct wiphy *wiphy,
 	struct ath6kl_vif *vif = netdev_priv(ndev);
 	struct ath6kl_key *key = NULL;
 	u8 key_usage;
-	enum crypto_type key_type = NONE_CRYPT;
+	enum ath6kl_crypto_type key_type = NONE_CRYPT;
 
 	ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index);
 

drivers/net/wireless/ath/ath6kl/common.h

@@ -67,7 +67,7 @@ struct ath6kl_llc_snap_hdr {
 	__be16 eth_type;
 } __packed;
 
-enum crypto_type {
+enum ath6kl_crypto_type {
 	NONE_CRYPT          = 0x01,
 	WEP_CRYPT           = 0x02,
 	TKIP_CRYPT          = 0x04,

drivers/net/wireless/ath/ath6kl/wmi.c

@@ -1849,9 +1849,9 @@ int ath6kl_wmi_connect_cmd(struct wmi *wmi, u8 if_idx,
 			   enum network_type nw_type,
 			   enum dot11_auth_mode dot11_auth_mode,
 			   enum auth_mode auth_mode,
-			   enum crypto_type pairwise_crypto,
+			   enum ath6kl_crypto_type pairwise_crypto,
 			   u8 pairwise_crypto_len,
-			   enum crypto_type group_crypto,
+			   enum ath6kl_crypto_type group_crypto,
 			   u8 group_crypto_len, int ssid_len, u8 *ssid,
 			   u8 *bssid, u16 channel, u32 ctrl_flags,
 			   u8 nw_subtype)
@@ -2301,7 +2301,7 @@ int ath6kl_wmi_disctimeout_cmd(struct wmi *wmi, u8 if_idx, u8 timeout)
 }
 
 int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index,
-			  enum crypto_type key_type,
+			  enum ath6kl_crypto_type key_type,
 			  u8 key_usage, u8 key_len,
 			  u8 *key_rsc, unsigned int key_rsc_len,
 			  u8 *key_material,

drivers/net/wireless/ath/ath6kl/wmi.h

@@ -2556,9 +2556,9 @@ int ath6kl_wmi_connect_cmd(struct wmi *wmi, u8 if_idx,
 			   enum network_type nw_type,
 			   enum dot11_auth_mode dot11_auth_mode,
 			   enum auth_mode auth_mode,
-			   enum crypto_type pairwise_crypto,
+			   enum ath6kl_crypto_type pairwise_crypto,
 			   u8 pairwise_crypto_len,
-			   enum crypto_type group_crypto,
+			   enum ath6kl_crypto_type group_crypto,
 			   u8 group_crypto_len, int ssid_len, u8 *ssid,
 			   u8 *bssid, u16 channel, u32 ctrl_flags,
 			   u8 nw_subtype);
@@ -2610,7 +2610,7 @@ int ath6kl_wmi_config_debug_module_cmd(struct wmi *wmi, u32 valid, u32 config);
 
 int ath6kl_wmi_get_stats_cmd(struct wmi *wmi, u8 if_idx);
 int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index,
-			  enum crypto_type key_type,
+			  enum ath6kl_crypto_type key_type,
 			  u8 key_usage, u8 key_len,
 			  u8 *key_rsc, unsigned int key_rsc_len,
 			  u8 *key_material,

drivers/nvme/host/Kconfig

@@ -57,3 +57,18 @@ config NVME_FC
 	  from https://github.com/linux-nvme/nvme-cli.
 
 	  If unsure, say N.
+
+config NVME_TCP
+	tristate "NVM Express over Fabrics TCP host driver"
+	depends on INET
+	depends on BLK_DEV_NVME
+	select NVME_FABRICS
+	help
+	  This provides support for the NVMe over Fabrics protocol using
+	  the TCP transport.  This allows you to use remote block devices
+	  exported using the NVMe protocol set.
+
+	  To configure a NVMe over Fabrics controller use the nvme-cli tool
+	  from https://github.com/linux-nvme/nvme-cli.
+
+	  If unsure, say N.

drivers/nvme/host/Makefile

@@ -7,6 +7,7 @@ obj-$(CONFIG_BLK_DEV_NVME)		+= nvme.o
 obj-$(CONFIG_NVME_FABRICS)		+= nvme-fabrics.o
 obj-$(CONFIG_NVME_RDMA)			+= nvme-rdma.o
 obj-$(CONFIG_NVME_FC)			+= nvme-fc.o
+obj-$(CONFIG_NVME_TCP)			+= nvme-tcp.o
 
 nvme-core-y				:= core.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
@@ -21,3 +22,5 @@ nvme-fabrics-y				+= fabrics.o
 nvme-rdma-y				+= rdma.o
 
 nvme-fc-y				+= fc.o
+
+nvme-tcp-y				+= tcp.o

drivers/nvme/host/core.c

@@ -564,9 +564,19 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	struct nvme_dsm_range *range;
 	struct bio *bio;
 
-	range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
-	if (!range)
-		return BLK_STS_RESOURCE;
+	range = kmalloc_array(segments, sizeof(*range),
+				GFP_ATOMIC | __GFP_NOWARN);
+	if (!range) {
+		/*
+		 * If we fail allocation our range, fallback to the controller
+		 * discard page. If that's also busy, it's safe to return
+		 * busy, as we know we can make progress once that's freed.
+		 */
+		if (test_and_set_bit_lock(0, &ns->ctrl->discard_page_busy))
+			return BLK_STS_RESOURCE;
+
+		range = page_address(ns->ctrl->discard_page);
+	}
 
 	__rq_for_each_bio(bio, req) {
 		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
@@ -581,7 +591,10 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	}
 
 	if (WARN_ON_ONCE(n != segments)) {
-		kfree(range);
+		if (virt_to_page(range) == ns->ctrl->discard_page)
+			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
+		else
+			kfree(range);
 		return BLK_STS_IOERR;
 	}
 
@@ -664,8 +677,13 @@ void nvme_cleanup_cmd(struct request *req)
 				blk_rq_bytes(req) >> ns->lba_shift);
 	}
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		kfree(page_address(req->special_vec.bv_page) +
-		      req->special_vec.bv_offset);
+		struct nvme_ns *ns = req->rq_disk->private_data;
+		struct page *page = req->special_vec.bv_page;
+
+		if (page == ns->ctrl->discard_page)
+			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
+		else
+			kfree(page_address(page) + req->special_vec.bv_offset);
 	}
 }
 EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
@@ -1265,12 +1283,12 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	c.common.nsid = cpu_to_le32(cmd.nsid);
 	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
 	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
-	c.common.cdw10[0] = cpu_to_le32(cmd.cdw10);
-	c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
-	c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
-	c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
-	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
-	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);
+	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
 
 	if (cmd.timeout_ms)
 		timeout = msecs_to_jiffies(cmd.timeout_ms);
@@ -1631,7 +1649,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = op;
 	c.common.nsid = cpu_to_le32(ns->head->ns_id);
-	c.common.cdw10[0] = cpu_to_le32(cdw10);
+	c.common.cdw10 = cpu_to_le32(cdw10);
 
 	ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
 	nvme_put_ns_from_disk(head, srcu_idx);
@@ -1705,8 +1723,8 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 	else
 		cmd.common.opcode = nvme_admin_security_recv;
 	cmd.common.nsid = 0;
-	cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
-	cmd.common.cdw10[1] = cpu_to_le32(len);
+	cmd.common.cdw10 = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
+	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
 				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
@@ -3578,6 +3596,7 @@ static void nvme_free_ctrl(struct device *dev)
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
 	nvme_mpath_uninit(ctrl);
+	kfree(ctrl->discard_page);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);
@@ -3618,6 +3637,14 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 
+	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
+			PAGE_SIZE);
+	ctrl->discard_page = alloc_page(GFP_KERNEL);
+	if (!ctrl->discard_page) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
@@ -3655,6 +3682,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 out_release_instance:
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 out:
+	if (ctrl->discard_page)
+		__free_page(ctrl->discard_page);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_ctrl);
@@ -3802,7 +3831,7 @@ int __init nvme_core_init(void)
 	return result;
 }
 
-void nvme_core_exit(void)
+void __exit nvme_core_exit(void)
 {
 	ida_destroy(&nvme_subsystems_ida);
 	class_destroy(nvme_subsys_class);

drivers/nvme/host/fabrics.c

@@ -614,6 +614,9 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_HOST_ID,		"hostid=%s"		},
 	{ NVMF_OPT_DUP_CONNECT,		"duplicate_connect"	},
 	{ NVMF_OPT_DISABLE_SQFLOW,	"disable_sqflow"	},
+	{ NVMF_OPT_HDR_DIGEST,		"hdr_digest"		},
+	{ NVMF_OPT_DATA_DIGEST,		"data_digest"		},
+	{ NVMF_OPT_NR_WRITE_QUEUES,	"nr_write_queues=%d"	},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -633,6 +636,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
 	opts->kato = NVME_DEFAULT_KATO;
 	opts->duplicate_connect = false;
+	opts->hdr_digest = false;
+	opts->data_digest = false;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -827,6 +832,24 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 		case NVMF_OPT_DISABLE_SQFLOW:
 			opts->disable_sqflow = true;
 			break;
+		case NVMF_OPT_HDR_DIGEST:
+			opts->hdr_digest = true;
+			break;
+		case NVMF_OPT_DATA_DIGEST:
+			opts->data_digest = true;
+			break;
+		case NVMF_OPT_NR_WRITE_QUEUES:
+			if (match_int(args, &token)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (token <= 0) {
+				pr_err("Invalid nr_write_queues %d\n", token);
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->nr_write_queues = token;
+			break;
 		default:
 			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
 				p);

drivers/nvme/host/fabrics.h

@@ -59,6 +59,9 @@ enum {
 	NVMF_OPT_HOST_ID	= 1 << 12,
 	NVMF_OPT_DUP_CONNECT	= 1 << 13,
 	NVMF_OPT_DISABLE_SQFLOW = 1 << 14,
+	NVMF_OPT_HDR_DIGEST	= 1 << 15,
+	NVMF_OPT_DATA_DIGEST	= 1 << 16,
+	NVMF_OPT_NR_WRITE_QUEUES = 1 << 17,
 };
 
 /**
@@ -86,6 +89,10 @@ enum {
  * @max_reconnects: maximum number of allowed reconnect attempts before removing
  *              the controller, (-1) means reconnect forever, zero means remove
  *              immediately;
+ * @disable_sqflow: disable controller sq flow control
+ * @hdr_digest: generate/verify header digest (TCP)
+ * @data_digest: generate/verify data digest (TCP)
+ * @nr_write_queues: number of queues for write I/O
  */
 struct nvmf_ctrl_options {
 	unsigned		mask;
@@ -103,6 +110,9 @@ struct nvmf_ctrl_options {
 	struct nvmf_host	*host;
 	int			max_reconnects;
 	bool			disable_sqflow;
+	bool			hdr_digest;
+	bool			data_digest;
+	unsigned int		nr_write_queues;
 };
 
 /*

drivers/nvme/host/lightnvm.c

@@ -937,9 +937,9 @@ static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
 	/* cdw11-12 */
 	c.ph_rw.length = cpu_to_le16(vcmd.nppas);
 	c.ph_rw.control  = cpu_to_le16(vcmd.control);
-	c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
-	c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
-	c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
+	c.common.cdw13 = cpu_to_le32(vcmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(vcmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(vcmd.cdw15);
 
 	if (vcmd.timeout_ms)
 		timeout = msecs_to_jiffies(vcmd.timeout_ms);

drivers/nvme/host/nvme.h

@@ -241,6 +241,9 @@ struct nvme_ctrl {
 	u16 maxcmd;
 	int nr_reconnects;
 	struct nvmf_ctrl_options *opts;
+
+	struct page *discard_page;
+	unsigned long discard_page_busy;
 };
 
 struct nvme_subsystem {
@@ -565,6 +568,6 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 }
 
 int __init nvme_core_init(void);
-void nvme_core_exit(void);
+void __exit nvme_core_exit(void);
 
 #endif /* _NVME_H */

drivers/nvme/host/rdma.c

@@ -645,6 +645,8 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	nr_io_queues = min_t(unsigned int, nr_io_queues,
 				ibdev->num_comp_vectors);
 
+	nr_io_queues += min(opts->nr_write_queues, num_online_cpus());
+
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
 		return ret;
@@ -714,6 +716,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		set->driver_data = ctrl;
 		set->nr_hw_queues = nctrl->queue_count - 1;
 		set->timeout = NVME_IO_TIMEOUT;
+		set->nr_maps = 2 /* default + read */;
 	}
 
 	ret = blk_mq_alloc_tag_set(set);
@@ -1751,7 +1754,25 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 {
 	struct nvme_rdma_ctrl *ctrl = set->driver_data;
 
-	return blk_mq_rdma_map_queues(set, ctrl->device->dev, 0);
+	set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+	set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues;
+	if (ctrl->ctrl.opts->nr_write_queues) {
+		/* separate read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+				ctrl->ctrl.opts->nr_write_queues;
+		set->map[HCTX_TYPE_READ].queue_offset =
+				ctrl->ctrl.opts->nr_write_queues;
+	} else {
+		/* mixed read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+				ctrl->ctrl.opts->nr_io_queues;
+		set->map[HCTX_TYPE_READ].queue_offset = 0;
+	}
+	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
+			ctrl->device->dev, 0);
+	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_READ],
+			ctrl->device->dev, 0);
+	return 0;
 }
 
 static const struct blk_mq_ops nvme_rdma_mq_ops = {
@@ -1906,7 +1927,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work);
 
-	ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */
+	ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1;
 	ctrl->ctrl.sqsize = opts->queue_size - 1;
 	ctrl->ctrl.kato = opts->kato;
 
@@ -1957,7 +1978,8 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
 	.module		= THIS_MODULE,
 	.required_opts	= NVMF_OPT_TRADDR,
 	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
-			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
+			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
+			  NVMF_OPT_NR_WRITE_QUEUES,
 	.create_ctrl	= nvme_rdma_create_ctrl,
 };
 

drivers/nvme/host/trace.h

@@ -115,8 +115,8 @@ TRACE_EVENT(nvme_setup_cmd,
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
 		__assign_disk_name(__entry->disk, req->rq_disk);
-		memcpy(__entry->cdw10, cmd->common.cdw10,
-		       sizeof(__entry->cdw10));
+		memcpy(__entry->cdw10, &cmd->common.cdw10,
+			6 * sizeof(__entry->cdw10));
 	    ),
 	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
 		      __entry->ctrl_id, __print_disk_name(__entry->disk),

drivers/nvme/target/Kconfig

@@ -60,3 +60,13 @@ config NVME_TARGET_FCLOOP
 	  to test NVMe-FC transport interfaces.
 
 	  If unsure, say N.
+
+config NVME_TARGET_TCP
+	tristate "NVMe over Fabrics TCP target support"
+	depends on INET
+	depends on NVME_TARGET
+	help
+	  This enables the NVMe TCP target support, which allows exporting NVMe
+	  devices over TCP.
+
+	  If unsure, say N.

drivers/nvme/target/Makefile

@@ -5,6 +5,7 @@ obj-$(CONFIG_NVME_TARGET_LOOP)		+= nvme-loop.o
 obj-$(CONFIG_NVME_TARGET_RDMA)		+= nvmet-rdma.o
 obj-$(CONFIG_NVME_TARGET_FC)		+= nvmet-fc.o
 obj-$(CONFIG_NVME_TARGET_FCLOOP)	+= nvme-fcloop.o
+obj-$(CONFIG_NVME_TARGET_TCP)		+= nvmet-tcp.o
 
 nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
 			discovery.o io-cmd-file.o io-cmd-bdev.o
@@ -12,3 +13,4 @@ nvme-loop-y	+= loop.o
 nvmet-rdma-y	+= rdma.o
 nvmet-fc-y	+= fc.o
 nvme-fcloop-y	+= fcloop.o
+nvmet-tcp-y	+= tcp.o

drivers/nvme/target/admin-cmd.c

@@ -37,6 +37,34 @@ static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
 }
 
+static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	u16 status = NVME_SC_SUCCESS;
+	unsigned long flags;
+	off_t offset = 0;
+	u64 slot;
+	u64 i;
+
+	spin_lock_irqsave(&ctrl->error_lock, flags);
+	slot = ctrl->err_counter % NVMET_ERROR_LOG_SLOTS;
+
+	for (i = 0; i < NVMET_ERROR_LOG_SLOTS; i++) {
+		status = nvmet_copy_to_sgl(req, offset, &ctrl->slots[slot],
+				sizeof(struct nvme_error_slot));
+		if (status)
+			break;
+
+		if (slot == 0)
+			slot = NVMET_ERROR_LOG_SLOTS - 1;
+		else
+			slot--;
+		offset += sizeof(struct nvme_error_slot);
+	}
+	spin_unlock_irqrestore(&ctrl->error_lock, flags);
+	nvmet_req_complete(req, status);
+}
+
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
@@ -47,6 +75,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	if (!ns) {
 		pr_err("Could not find namespace id : %d\n",
 				le32_to_cpu(req->cmd->get_log_page.nsid));
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
 		return NVME_SC_INVALID_NS;
 	}
 
@@ -106,6 +135,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 {
 	struct nvme_smart_log *log;
 	u16 status = NVME_SC_INTERNAL;
+	unsigned long flags;
 
 	if (req->data_len != sizeof(*log))
 		goto out;
@@ -121,6 +151,11 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 	if (status)
 		goto out_free_log;
 
+	spin_lock_irqsave(&req->sq->ctrl->error_lock, flags);
+	put_unaligned_le64(req->sq->ctrl->err_counter,
+			&log->num_err_log_entries);
+	spin_unlock_irqrestore(&req->sq->ctrl->error_lock, flags);
+
 	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
 out_free_log:
 	kfree(log);
@@ -380,6 +415,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	u16 status = 0;
 
 	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
 		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto out;
 	}
@@ -500,6 +536,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
 
 	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
 	if (!ns) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
 		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto out;
 	}
@@ -557,13 +594,15 @@ static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
 
 static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
 {
-	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw11);
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
 	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
-	if (unlikely(!req->ns))
+	if (unlikely(!req->ns)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return status;
+	}
 
 	mutex_lock(&subsys->lock);
 	switch (write_protect) {
@@ -589,7 +628,7 @@ static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
 
 u16 nvmet_set_feat_kato(struct nvmet_req *req)
 {
-	u32 val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
+	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
 
 	req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
 
@@ -600,10 +639,12 @@ u16 nvmet_set_feat_kato(struct nvmet_req *req)
 
 u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
 {
-	u32 val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
+	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
 
-	if (val32 & ~mask)
+	if (val32 & ~mask) {
+		req->error_loc = offsetof(struct nvme_common_command, cdw11);
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
 
 	WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
 	nvmet_set_result(req, val32);
@@ -614,7 +655,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
 static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
-	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
 	switch (cdw10 & 0xff) {
@@ -635,6 +676,7 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 		status = nvmet_set_feat_write_protect(req);
 		break;
 	default:
+		req->error_loc = offsetof(struct nvme_common_command, cdw10);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -648,9 +690,10 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
 	u32 result;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
-	if (!req->ns)
+	if (!req->ns)  {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
-
+	}
 	mutex_lock(&subsys->lock);
 	if (req->ns->readonly == true)
 		result = NVME_NS_WRITE_PROTECT;
@@ -675,7 +718,7 @@ void nvmet_get_feat_async_event(struct nvmet_req *req)
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
-	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 status = 0;
 
 	switch (cdw10 & 0xff) {
@@ -715,7 +758,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		break;
 	case NVME_FEAT_HOST_ID:
 		/* need 128-bit host identifier flag */
-		if (!(req->cmd->common.cdw10[1] & cpu_to_le32(1 << 0))) {
+		if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
+			req->error_loc =
+				offsetof(struct nvme_common_command, cdw11);
 			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 			break;
 		}
@@ -727,6 +772,8 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_get_feat_write_protect(req);
 		break;
 	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -776,13 +823,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 		switch (cmd->get_log_page.lid) {
 		case NVME_LOG_ERROR:
-			/*
-			 * We currently never set the More bit in the status
-			 * field, so all error log entries are invalid and can
-			 * be zeroed out.  This is called a minum viable
-			 * implementation (TM) of this mandatory log page.
-			 */
-			req->execute = nvmet_execute_get_log_page_noop;
+			req->execute = nvmet_execute_get_log_page_error;
 			return 0;
 		case NVME_LOG_SMART:
 			req->execute = nvmet_execute_get_log_page_smart;
@@ -848,5 +889,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 	pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
 	       req->sq->qid);
+	req->error_loc = offsetof(struct nvme_common_command, opcode);
 	return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 }

drivers/nvme/target/configfs.c

@@ -34,6 +34,7 @@ static const struct nvmet_transport_name {
 } nvmet_transport_names[] = {
 	{ NVMF_TRTYPE_RDMA,	"rdma" },
 	{ NVMF_TRTYPE_FC,	"fc" },
+	{ NVMF_TRTYPE_TCP,	"tcp" },
 	{ NVMF_TRTYPE_LOOP,	"loop" },
 };
 

drivers/nvme/target/core.c

@@ -45,28 +45,72 @@ u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
 u64 nvmet_ana_chgcnt;
 DECLARE_RWSEM(nvmet_ana_sem);
 
+inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
+{
+	u16 status;
+
+	switch (errno) {
+	case -ENOSPC:
+		req->error_loc = offsetof(struct nvme_rw_command, length);
+		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+		break;
+	case -EREMOTEIO:
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		break;
+	case -EOPNOTSUPP:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_dsm:
+		case nvme_cmd_write_zeroes:
+			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+			break;
+		default:
+			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+		break;
+	case -ENODATA:
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
+		status = NVME_SC_ACCESS_DENIED;
+		break;
+	case -EIO:
+		/* FALLTHRU */
+	default:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+	}
+
+	return status;
+}
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
 u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
 		size_t len)
 {
-	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+	if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
 u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
 {
-	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len)
+	if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
 u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
 {
-	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
+	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	}
 	return 0;
 }
 
@@ -611,14 +655,44 @@ static void nvmet_update_sq_head(struct nvmet_req *req)
 	req->rsp->sq_head = cpu_to_le16(req->sq->sqhd & 0x0000FFFF);
 }
 
+static void nvmet_set_error(struct nvmet_req *req, u16 status)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_error_slot *new_error_slot;
+	unsigned long flags;
+
+	req->rsp->status = cpu_to_le16(status << 1);
+
+	if (!ctrl || req->error_loc == -1)
+		return;
+
+	spin_lock_irqsave(&ctrl->error_lock, flags);
+	ctrl->err_counter++;
+	new_error_slot =
+		&ctrl->slots[ctrl->err_counter % NVMET_ERROR_LOG_SLOTS];
+
+	new_error_slot->error_count = cpu_to_le64(ctrl->err_counter);
+	new_error_slot->sqid = cpu_to_le16(req->sq->qid);
+	new_error_slot->cmdid = cpu_to_le16(req->cmd->common.command_id);
+	new_error_slot->status_field = cpu_to_le16(status << 1);
+	new_error_slot->param_error_location = cpu_to_le16(req->error_loc);
+	new_error_slot->lba = cpu_to_le64(req->error_slba);
+	new_error_slot->nsid = req->cmd->common.nsid;
+	spin_unlock_irqrestore(&ctrl->error_lock, flags);
+
+	/* set the more bit for this request */
+	req->rsp->status |= cpu_to_le16(1 << 14);
+}
+
 static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 {
 	if (!req->sq->sqhd_disabled)
 		nvmet_update_sq_head(req);
 	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
 	req->rsp->command_id = req->cmd->common.command_id;
+
 	if (unlikely(status))
-		nvmet_set_status(req, status);
+		nvmet_set_error(req, status);
 	if (req->ns)
 		nvmet_put_namespace(req->ns);
 	req->ops->queue_response(req);
@@ -739,14 +813,20 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 		return ret;
 
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
-	if (unlikely(!req->ns))
+	if (unlikely(!req->ns)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	}
 	ret = nvmet_check_ana_state(req->port, req->ns);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return ret;
+	}
 	ret = nvmet_io_cmd_check_access(req);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		req->error_loc = offsetof(struct nvme_common_command, nsid);
 		return ret;
+	}
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -769,9 +849,12 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	req->rsp->status = 0;
 	req->rsp->sq_head = 0;
 	req->ns = NULL;
+	req->error_loc = -1;
+	req->error_slba = 0;
 
 	/* no support for fused commands yet */
 	if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
+		req->error_loc = offsetof(struct nvme_common_command, flags);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
 	}
@@ -782,6 +865,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
 	 * byte aligned.
 	 */
 	if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
+		req->error_loc = offsetof(struct nvme_common_command, flags);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		goto fail;
 	}
@@ -827,9 +911,10 @@ EXPORT_SYMBOL_GPL(nvmet_req_uninit);
 
 void nvmet_req_execute(struct nvmet_req *req)
 {
-	if (unlikely(req->data_len != req->transfer_len))
+	if (unlikely(req->data_len != req->transfer_len)) {
+		req->error_loc = offsetof(struct nvme_common_command, dptr);
 		nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
-	else
+	} else
 		req->execute(req);
 }
 EXPORT_SYMBOL_GPL(nvmet_req_execute);
@@ -1174,6 +1259,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	/* keep-alive timeout in seconds */
 	ctrl->kato = DIV_ROUND_UP(kato, 1000);
 
+	ctrl->err_counter = 0;
+	spin_lock_init(&ctrl->error_lock);
+
 	nvmet_start_keep_alive_timer(ctrl);
 
 	mutex_lock(&subsys->lock);

drivers/nvme/target/discovery.c

@@ -247,7 +247,7 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 
 static void nvmet_execute_disc_set_features(struct nvmet_req *req)
 {
-	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 stat;
 
 	switch (cdw10 & 0xff) {
@@ -259,6 +259,8 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req)
 						  NVMET_DISC_AEN_CFG_OPTIONAL);
 		break;
 	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
 		stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -268,7 +270,7 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req)
 
 static void nvmet_execute_disc_get_features(struct nvmet_req *req)
 {
-	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10[0]);
+	u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
 	u16 stat = 0;
 
 	switch (cdw10 & 0xff) {
@@ -279,6 +281,8 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req)
 		nvmet_get_feat_async_event(req);
 		break;
 	default:
+		req->error_loc =
+			offsetof(struct nvme_common_command, cdw10);
 		stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
 	}
@@ -293,6 +297,8 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 	if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
 		pr_err("got cmd %d while not ready\n",
 		       cmd->common.opcode);
+		req->error_loc =
+			offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
@@ -323,6 +329,8 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		default:
 			pr_err("unsupported get_log_page lid %d\n",
 			       cmd->get_log_page.lid);
+			req->error_loc =
+				offsetof(struct nvme_get_log_page_command, lid);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	case nvme_admin_identify:
@@ -335,10 +343,12 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 		default:
 			pr_err("unsupported identify cns %d\n",
 			       cmd->identify.cns);
+			req->error_loc = offsetof(struct nvme_identify, cns);
 			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 	default:
 		pr_err("unhandled cmd %d\n", cmd->common.opcode);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 

drivers/nvme/target/fabrics-cmd.c

@@ -17,23 +17,26 @@
 
 static void nvmet_execute_prop_set(struct nvmet_req *req)
 {
+	u64 val = le64_to_cpu(req->cmd->prop_set.value);
 	u16 status = 0;
 
-	if (!(req->cmd->prop_set.attrib & 1)) {
-		u64 val = le64_to_cpu(req->cmd->prop_set.value);
-
-		switch (le32_to_cpu(req->cmd->prop_set.offset)) {
-		case NVME_REG_CC:
-			nvmet_update_cc(req->sq->ctrl, val);
-			break;
-		default:
-			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-			break;
-		}
-	} else {
+	if (req->cmd->prop_set.attrib & 1) {
+		req->error_loc =
+			offsetof(struct nvmf_property_set_command, attrib);
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto out;
 	}
 
+	switch (le32_to_cpu(req->cmd->prop_set.offset)) {
+	case NVME_REG_CC:
+		nvmet_update_cc(req->sq->ctrl, val);
+		break;
+	default:
+		req->error_loc =
+			offsetof(struct nvmf_property_set_command, offset);
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+out:
 	nvmet_req_complete(req, status);
 }
 
@@ -69,6 +72,14 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
 		}
 	}
 
+	if (status && req->cmd->prop_get.attrib & 1) {
+		req->error_loc =
+			offsetof(struct nvmf_property_get_command, offset);
+	} else {
+		req->error_loc =
+			offsetof(struct nvmf_property_get_command, attrib);
+	}
+
 	req->rsp->result.u64 = cpu_to_le64(val);
 	nvmet_req_complete(req, status);
 }
@@ -89,6 +100,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
 	default:
 		pr_err("received unknown capsule type 0x%x\n",
 			cmd->fabrics.fctype);
+		req->error_loc = offsetof(struct nvmf_common_command, fctype);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 
@@ -105,10 +117,12 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
 	if (old) {
 		pr_warn("queue already connected!\n");
+		req->error_loc = offsetof(struct nvmf_connect_command, opcode);
 		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
 	}
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
+		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
 		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
 	}
 
@@ -121,6 +135,16 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 		req->rsp->sq_head = cpu_to_le16(0xffff);
 	}
 
+	if (ctrl->ops->install_queue) {
+		u16 ret = ctrl->ops->install_queue(req->sq);
+
+		if (ret) {
+			pr_err("failed to install queue %d cntlid %d ret %x\n",
+				qid, ret, ctrl->cntlid);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -147,6 +171,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	if (c->recfmt != 0) {
 		pr_warn("invalid connect version (%d).\n",
 			le16_to_cpu(c->recfmt));
+		req->error_loc = offsetof(struct nvmf_connect_command, recfmt);
 		status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
 		goto out;
 	}
@@ -161,8 +186,13 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 
 	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
 				  le32_to_cpu(c->kato), &ctrl);
-	if (status)
+	if (status) {
+		if (status == (NVME_SC_INVALID_FIELD | NVME_SC_DNR))
+			req->error_loc =
+				offsetof(struct nvme_common_command, opcode);
 		goto out;
+	}
+
 	uuid_copy(&ctrl->hostid, &d->hostid);
 
 	status = nvmet_install_queue(ctrl, req);
@@ -249,11 +279,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
 	if (cmd->common.opcode != nvme_fabrics_command) {
 		pr_err("invalid command 0x%x on unconnected queue.\n",
 			cmd->fabrics.opcode);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 	if (cmd->fabrics.fctype != nvme_fabrics_type_connect) {
 		pr_err("invalid capsule type 0x%x on unconnected queue.\n",
 			cmd->fabrics.fctype);
+		req->error_loc = offsetof(struct nvmf_common_command, fctype);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 

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

@@ -44,13 +44,69 @@ void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
 	}
 }
 
+static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+{
+	u16 status = NVME_SC_SUCCESS;
+
+	if (likely(blk_sts == BLK_STS_OK))
+		return status;
+	/*
+	 * Right now there exists M : 1 mapping between block layer error
+	 * to the NVMe status code (see nvme_error_status()). For consistency,
+	 * when we reverse map we use most appropriate NVMe Status code from
+	 * the group of the NVMe staus codes used in the nvme_error_status().
+	 */
+	switch (blk_sts) {
+	case BLK_STS_NOSPC:
+		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_rw_command, length);
+		break;
+	case BLK_STS_TARGET:
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		break;
+	case BLK_STS_NOTSUPP:
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_dsm:
+		case nvme_cmd_write_zeroes:
+			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+			break;
+		default:
+			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+		}
+		break;
+	case BLK_STS_MEDIUM:
+		status = NVME_SC_ACCESS_DENIED;
+		req->error_loc = offsetof(struct nvme_rw_command, nsid);
+		break;
+	case BLK_STS_IOERR:
+		/* fallthru */
+	default:
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
+	}
+
+	switch (req->cmd->common.opcode) {
+	case nvme_cmd_read:
+	case nvme_cmd_write:
+		req->error_slba = le64_to_cpu(req->cmd->rw.slba);
+		break;
+	case nvme_cmd_write_zeroes:
+		req->error_slba =
+			le64_to_cpu(req->cmd->write_zeroes.slba);
+		break;
+	default:
+		req->error_slba = 0;
+	}
+	return status;
+}
+
 static void nvmet_bio_done(struct bio *bio)
 {
 	struct nvmet_req *req = bio->bi_private;
 
-	nvmet_req_complete(req,
-		bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
-
+	nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
 	if (bio != &req->b.inline_bio)
 		bio_put(bio);
 }
@@ -61,7 +117,6 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 	struct bio *bio;
 	struct scatterlist *sg;
 	sector_t sector;
-	blk_qc_t cookie;
 	int op, op_flags = 0, i;
 
 	if (!req->sg_cnt) {
@@ -114,7 +169,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 		sg_cnt--;
 	}
 
-	cookie = submit_bio(bio);
+	submit_bio(bio);
 }
 
 static void nvmet_bdev_execute_flush(struct nvmet_req *req)
@@ -137,18 +192,21 @@ u16 nvmet_bdev_flush(struct nvmet_req *req)
 	return 0;
 }
 
-static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
+static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
+	struct nvmet_ns *ns = req->ns;
 	int ret;
 
 	ret = __blkdev_issue_discard(ns->bdev,
 			le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
 			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
 			GFP_KERNEL, 0, bio);
-	if (ret && ret != -EOPNOTSUPP)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+
+	if (ret)
+		req->error_slba = le64_to_cpu(range->slba);
+
+	return blk_to_nvme_status(req, errno_to_blk_status(ret));
 }
 
 static void nvmet_bdev_execute_discard(struct nvmet_req *req)
@@ -164,7 +222,7 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req)
 		if (status)
 			break;
 
-		status = nvmet_bdev_discard_range(req->ns, &range, &bio);
+		status = nvmet_bdev_discard_range(req, &range, &bio);
 		if (status)
 			break;
 	}
@@ -205,16 +263,16 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
 	u16 status = NVME_SC_SUCCESS;
 	sector_t sector;
 	sector_t nr_sector;
+	int ret;
 
 	sector = le64_to_cpu(write_zeroes->slba) <<
 		(req->ns->blksize_shift - 9);
 	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 		(req->ns->blksize_shift - 9));
 
-	if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
-				GFP_KERNEL, &bio, 0))
-		status = NVME_SC_INTERNAL | NVME_SC_DNR;
-
+	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;
@@ -249,6 +307,7 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 	default:
 		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
 		       req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }

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

@@ -112,6 +112,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 {
 	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+	u16 status = NVME_SC_SUCCESS;
 
 	if (req->f.bvec != req->inline_bvec) {
 		if (likely(req->f.mpool_alloc == false))
@@ -120,8 +121,9 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 			mempool_free(req->f.bvec, req->ns->bvec_pool);
 	}
 
-	nvmet_req_complete(req, ret != req->data_len ?
-			NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	if (unlikely(ret != req->data_len))
+		status = errno_to_nvme_status(req, ret);
+	nvmet_req_complete(req, status);
 }
 
 static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
@@ -140,7 +142,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 
 	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
 	if (unlikely(pos + req->data_len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return true;
 	}
 
@@ -254,9 +256,7 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 
 u16 nvmet_file_flush(struct nvmet_req *req)
 {
-	if (vfs_fsync(req->ns->file, 1) < 0)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+	return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1));
 }
 
 static void nvmet_file_flush_work(struct work_struct *w)
@@ -277,30 +277,34 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
 	loff_t offset, len;
-	u16 ret;
+	u16 status = 0;
+	int ret;
 	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
 					sizeof(range));
-		if (ret)
+		if (status)
 			break;
 
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb);
 		len <<= req->ns->blksize_shift;
 		if (offset + len > req->ns->size) {
-			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, -ENOSPC);
 			break;
 		}
 
-		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
-			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+		ret = vfs_fallocate(req->ns->file, mode, offset, len);
+		if (ret) {
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, ret);
 			break;
 		}
 	}
 
-	nvmet_req_complete(req, ret);
+	nvmet_req_complete(req, status);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -340,12 +344,12 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 			req->ns->blksize_shift);
 
 	if (unlikely(offset + len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return;
 	}
 
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0);
 }
 
 static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
@@ -380,6 +384,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	default:
 		pr_err("unhandled cmd for file ns %d on qid %d\n",
 				cmd->common.opcode, req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }

drivers/nvme/target/nvmet.h

@@ -202,6 +202,10 @@ struct nvmet_ctrl {
 
 	struct device		*p2p_client;
 	struct radix_tree_root	p2p_ns_map;
+
+	spinlock_t		error_lock;
+	u64			err_counter;
+	struct nvme_error_slot	slots[NVMET_ERROR_LOG_SLOTS];
 };
 
 struct nvmet_subsys {
@@ -279,6 +283,7 @@ struct nvmet_fabrics_ops {
 	void (*delete_ctrl)(struct nvmet_ctrl *ctrl);
 	void (*disc_traddr)(struct nvmet_req *req,
 			struct nvmet_port *port, char *traddr);
+	u16 (*install_queue)(struct nvmet_sq *nvme_sq);
 };
 
 #define NVMET_MAX_INLINE_BIOVEC	8
@@ -316,15 +321,12 @@ struct nvmet_req {
 
 	struct pci_dev		*p2p_dev;
 	struct device		*p2p_client;
+	u16			error_loc;
+	u64			error_slba;
 };
 
 extern struct workqueue_struct *buffered_io_wq;
 
-static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
-{
-	req->rsp->status = cpu_to_le16(status << 1);
-}
-
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
 	req->rsp->result.u32 = cpu_to_le32(result);
@@ -348,7 +350,7 @@ struct nvmet_async_event {
 
 static inline void nvmet_clear_aen_bit(struct nvmet_req *req, u32 bn)
 {
-	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+	int rae = le32_to_cpu(req->cmd->common.cdw10) & 1 << 15;
 
 	if (!rae)
 		clear_bit(bn, &req->sq->ctrl->aen_masked);
@@ -492,4 +494,6 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req)
 	return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
 			req->ns->blksize_shift;
 }
+
+u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
 #endif /* _NVMET_H */

drivers/nvme/target/rdma.c

@@ -630,8 +630,11 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	u64 off = le64_to_cpu(sgl->addr);
 	u32 len = le32_to_cpu(sgl->length);
 
-	if (!nvme_is_write(rsp->req.cmd))
+	if (!nvme_is_write(rsp->req.cmd)) {
+		rsp->req.error_loc =
+			offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
 
 	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
@@ -696,6 +699,8 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
 			return nvmet_rdma_map_sgl_inline(rsp);
 		default:
 			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			rsp->req.error_loc =
+				offsetof(struct nvme_common_command, dptr);
 			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		}
 	case NVME_KEY_SGL_FMT_DATA_DESC:
@@ -706,10 +711,13 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
 			return nvmet_rdma_map_sgl_keyed(rsp, sgl, false);
 		default:
 			pr_err("invalid SGL subtype: %#x\n", sgl->type);
+			rsp->req.error_loc =
+				offsetof(struct nvme_common_command, dptr);
 			return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		}
 	default:
 		pr_err("invalid SGL type: %#x\n", sgl->type);
+		rsp->req.error_loc = offsetof(struct nvme_common_command, dptr);
 		return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
 	}
 }

include/linux/blk-mq-rdma.h

@@ -4,7 +4,7 @@
 struct blk_mq_tag_set;
 struct ib_device;
 
-int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
 		struct ib_device *dev, int first_vec);
 
 #endif /* _LINUX_BLK_MQ_RDMA_H */

include/linux/nvme-tcp.h

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe over Fabrics TCP protocol header.
+ * Copyright (c) 2018 Lightbits Labs. All rights reserved.
+ */
+
+#ifndef _LINUX_NVME_TCP_H
+#define _LINUX_NVME_TCP_H
+
+#include <linux/nvme.h>
+
+#define NVME_TCP_DISC_PORT	8009
+#define NVME_TCP_ADMIN_CCSZ	SZ_8K
+#define NVME_TCP_DIGEST_LENGTH	4
+
+enum nvme_tcp_pfv {
+	NVME_TCP_PFV_1_0 = 0x0,
+};
+
+enum nvme_tcp_fatal_error_status {
+	NVME_TCP_FES_INVALID_PDU_HDR		= 0x01,
+	NVME_TCP_FES_PDU_SEQ_ERR		= 0x02,
+	NVME_TCP_FES_HDR_DIGEST_ERR		= 0x03,
+	NVME_TCP_FES_DATA_OUT_OF_RANGE		= 0x04,
+	NVME_TCP_FES_R2T_LIMIT_EXCEEDED		= 0x05,
+	NVME_TCP_FES_DATA_LIMIT_EXCEEDED	= 0x05,
+	NVME_TCP_FES_UNSUPPORTED_PARAM		= 0x06,
+};
+
+enum nvme_tcp_digest_option {
+	NVME_TCP_HDR_DIGEST_ENABLE	= (1 << 0),
+	NVME_TCP_DATA_DIGEST_ENABLE	= (1 << 1),
+};
+
+enum nvme_tcp_pdu_type {
+	nvme_tcp_icreq		= 0x0,
+	nvme_tcp_icresp		= 0x1,
+	nvme_tcp_h2c_term	= 0x2,
+	nvme_tcp_c2h_term	= 0x3,
+	nvme_tcp_cmd		= 0x4,
+	nvme_tcp_rsp		= 0x5,
+	nvme_tcp_h2c_data	= 0x6,
+	nvme_tcp_c2h_data	= 0x7,
+	nvme_tcp_r2t		= 0x9,
+};
+
+enum nvme_tcp_pdu_flags {
+	NVME_TCP_F_HDGST		= (1 << 0),
+	NVME_TCP_F_DDGST		= (1 << 1),
+	NVME_TCP_F_DATA_LAST		= (1 << 2),
+	NVME_TCP_F_DATA_SUCCESS		= (1 << 3),
+};
+
+/**
+ * struct nvme_tcp_hdr - nvme tcp pdu common header
+ *
+ * @type:          pdu type
+ * @flags:         pdu specific flags
+ * @hlen:          pdu header length
+ * @pdo:           pdu data offset
+ * @plen:          pdu wire byte length
+ */
+struct nvme_tcp_hdr {
+	__u8	type;
+	__u8	flags;
+	__u8	hlen;
+	__u8	pdo;
+	__le32	plen;
+};
+
+/**
+ * struct nvme_tcp_icreq_pdu - nvme tcp initialize connection request pdu
+ *
+ * @hdr:           pdu generic header
+ * @pfv:           pdu version format
+ * @hpda:          host pdu data alignment (dwords, 0's based)
+ * @digest:        digest types enabled
+ * @maxr2t:        maximum r2ts per request supported
+ */
+struct nvme_tcp_icreq_pdu {
+	struct nvme_tcp_hdr	hdr;
+	__le16			pfv;
+	__u8			hpda;
+	__u8			digest;
+	__le32			maxr2t;
+	__u8			rsvd2[112];
+};
+
+/**
+ * struct nvme_tcp_icresp_pdu - nvme tcp initialize connection response pdu
+ *
+ * @hdr:           pdu common header
+ * @pfv:           pdu version format
+ * @cpda:          controller pdu data alignment (dowrds, 0's based)
+ * @digest:        digest types enabled
+ * @maxdata:       maximum data capsules per r2t supported
+ */
+struct nvme_tcp_icresp_pdu {
+	struct nvme_tcp_hdr	hdr;
+	__le16			pfv;
+	__u8			cpda;
+	__u8			digest;
+	__le32			maxdata;
+	__u8			rsvd[112];
+};
+
+/**
+ * struct nvme_tcp_term_pdu - nvme tcp terminate connection pdu
+ *
+ * @hdr:           pdu common header
+ * @fes:           fatal error status
+ * @fei:           fatal error information
+ */
+struct nvme_tcp_term_pdu {
+	struct nvme_tcp_hdr	hdr;
+	__le16			fes;
+	__le32			fei;
+	__u8			rsvd[8];
+};
+
+/**
+ * struct nvme_tcp_cmd_pdu - nvme tcp command capsule pdu
+ *
+ * @hdr:           pdu common header
+ * @cmd:           nvme command
+ */
+struct nvme_tcp_cmd_pdu {
+	struct nvme_tcp_hdr	hdr;
+	struct nvme_command	cmd;
+};
+
+/**
+ * struct nvme_tcp_rsp_pdu - nvme tcp response capsule pdu
+ *
+ * @hdr:           pdu common header
+ * @hdr:           nvme-tcp generic header
+ * @cqe:           nvme completion queue entry
+ */
+struct nvme_tcp_rsp_pdu {
+	struct nvme_tcp_hdr	hdr;
+	struct nvme_completion	cqe;
+};
+
+/**
+ * struct nvme_tcp_r2t_pdu - nvme tcp ready-to-transfer pdu
+ *
+ * @hdr:           pdu common header
+ * @command_id:    nvme command identifier which this relates to
+ * @ttag:          transfer tag (controller generated)
+ * @r2t_offset:    offset from the start of the command data
+ * @r2t_length:    length the host is allowed to send
+ */
+struct nvme_tcp_r2t_pdu {
+	struct nvme_tcp_hdr	hdr;
+	__u16			command_id;
+	__u16			ttag;
+	__le32			r2t_offset;
+	__le32			r2t_length;
+	__u8			rsvd[4];
+};
+
+/**
+ * struct nvme_tcp_data_pdu - nvme tcp data pdu
+ *
+ * @hdr:           pdu common header
+ * @command_id:    nvme command identifier which this relates to
+ * @ttag:          transfer tag (controller generated)
+ * @data_offset:   offset from the start of the command data
+ * @data_length:   length of the data stream
+ */
+struct nvme_tcp_data_pdu {
+	struct nvme_tcp_hdr	hdr;
+	__u16			command_id;
+	__u16			ttag;
+	__le32			data_offset;
+	__le32			data_length;
+	__u8			rsvd[4];
+};
+
+union nvme_tcp_pdu {
+	struct nvme_tcp_icreq_pdu	icreq;
+	struct nvme_tcp_icresp_pdu	icresp;
+	struct nvme_tcp_cmd_pdu		cmd;
+	struct nvme_tcp_rsp_pdu		rsp;
+	struct nvme_tcp_r2t_pdu		r2t;
+	struct nvme_tcp_data_pdu	data;
+};
+
+#endif /* _LINUX_NVME_TCP_H */

include/linux/nvme.h

@@ -52,6 +52,7 @@ enum {
 enum {
 	NVMF_TRTYPE_RDMA	= 1,	/* RDMA */
 	NVMF_TRTYPE_FC		= 2,	/* Fibre Channel */
+	NVMF_TRTYPE_TCP		= 3,	/* TCP/IP */
 	NVMF_TRTYPE_LOOP	= 254,	/* Reserved for host usage */
 	NVMF_TRTYPE_MAX,
 };
@@ -661,7 +662,12 @@ struct nvme_common_command {
 	__le32			cdw2[2];
 	__le64			metadata;
 	union nvme_data_ptr	dptr;
-	__le32			cdw10[6];
+	__le32			cdw10;
+	__le32			cdw11;
+	__le32			cdw12;
+	__le32			cdw13;
+	__le32			cdw14;
+	__le32			cdw15;
 };
 
 struct nvme_rw_command {
@@ -1162,6 +1168,20 @@ struct nvme_command {
 	};
 };
 
+struct nvme_error_slot {
+	__le64		error_count;
+	__le16		sqid;
+	__le16		cmdid;
+	__le16		status_field;
+	__le16		param_error_location;
+	__le64		lba;
+	__le32		nsid;
+	__u8		vs;
+	__u8		resv[3];
+	__le64		cs;
+	__u8		resv2[24];
+};
+
 static inline bool nvme_is_write(struct nvme_command *cmd)
 {
 	/*

include/linux/skbuff.h

@@ -3325,6 +3325,9 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 }
 int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 				   struct msghdr *msg);
+int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len,
+			   struct ahash_request *hash);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);

include/linux/uio.h

@@ -11,6 +11,7 @@
 
 #include <linux/kernel.h>
 #include <linux/thread_info.h>
+#include <crypto/hash.h>
 #include <uapi/linux/uio.h>
 
 struct page;
@@ -266,9 +267,11 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
 	i->count = count;
 }
-size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
+size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i);
 
 int import_iovec(int type, const struct iovec __user * uvector,
 		 unsigned nr_segs, unsigned fast_segs,

lib/iov_iter.c

@@ -6,6 +6,7 @@
 #include <linux/vmalloc.h>
 #include <linux/splice.h>
 #include <net/checksum.h>
+#include <linux/scatterlist.h>
 
 #define PIPE_PARANOIA /* for now */
 
@@ -1464,10 +1465,11 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum,
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter_full);
 
-size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum,
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
 			     struct iov_iter *i)
 {
 	const char *from = addr;
+	__wsum *csum = csump;
 	__wsum sum, next;
 	size_t off = 0;
 
@@ -1510,6 +1512,21 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum,
 }
 EXPORT_SYMBOL(csum_and_copy_to_iter);
 
+size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i)
+{
+	struct ahash_request *hash = hashp;
+	struct scatterlist sg;
+	size_t copied;
+
+	copied = copy_to_iter(addr, bytes, i);
+	sg_init_one(&sg, addr, copied);
+	ahash_request_set_crypt(hash, &sg, NULL, copied);
+	crypto_ahash_update(hash);
+	return copied;
+}
+EXPORT_SYMBOL(hash_and_copy_to_iter);
+
 int iov_iter_npages(const struct iov_iter *i, int maxpages)
 {
 	size_t size = i->count;

net/core/datagram.c

@@ -408,27 +408,20 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 }
 EXPORT_SYMBOL(skb_kill_datagram);
 
-/**
- *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
- *	@skb: buffer to copy
- *	@offset: offset in the buffer to start copying from
- *	@to: iovec iterator to copy to
- *	@len: amount of data to copy from buffer to iovec
- */
-int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
-			   struct iov_iter *to, int len)
+int __skb_datagram_iter(const struct sk_buff *skb, int offset,
+			struct iov_iter *to, int len, bool fault_short,
+			size_t (*cb)(const void *, size_t, void *, struct iov_iter *),
+			void *data)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset, start_off = offset, n;
 	struct sk_buff *frag_iter;
 
-	trace_skb_copy_datagram_iovec(skb, len);
-
 	/* Copy header. */
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		n = copy_to_iter(skb->data + offset, copy, to);
+		n = cb(skb->data + offset, copy, data, to);
 		offset += n;
 		if (n != copy)
 			goto short_copy;
@@ -445,11 +438,14 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
+			struct page *page = skb_frag_page(frag);
+			u8 *vaddr = kmap(page);
+
 			if (copy > len)
 				copy = len;
-			n = copy_page_to_iter(skb_frag_page(frag),
-					      frag->page_offset + offset -
-					      start, copy, to);
+			n = cb(vaddr + frag->page_offset +
+				offset - start, copy, data, to);
+			kunmap(page);
 			offset += n;
 			if (n != copy)
 				goto short_copy;
@@ -468,8 +464,8 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (skb_copy_datagram_iter(frag_iter, offset - start,
-						   to, copy))
+			if (__skb_datagram_iter(frag_iter, offset - start,
+						to, copy, fault_short, cb, data))
 				goto fault;
 			if ((len -= copy) == 0)
 				return 0;
@@ -490,11 +486,50 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 	return -EFAULT;
 
 short_copy:
-	if (iov_iter_count(to))
+	if (fault_short || iov_iter_count(to))
 		goto fault;
 
 	return 0;
 }
+
+/**
+ *	skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator
+ *          and update a hash.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *      @hash: hash request to update
+ */
+int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len,
+			   struct ahash_request *hash)
+{
+	return __skb_datagram_iter(skb, offset, to, len, true,
+			hash_and_copy_to_iter, hash);
+}
+EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter);
+
+static size_t simple_copy_to_iter(const void *addr, size_t bytes,
+		void *data __always_unused, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
+/**
+ *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ */
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len)
+{
+	trace_skb_copy_datagram_iovec(skb, len);
+	return __skb_datagram_iter(skb, offset, to, len, false,
+			simple_copy_to_iter, NULL);
+}
 EXPORT_SYMBOL(skb_copy_datagram_iter);
 
 /**
@@ -645,87 +680,21 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
+/**
+ *	skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ *          and update a checksum.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *      @csump: checksum pointer
+ */
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
-	int start = skb_headlen(skb);
-	int i, copy = start - offset, start_off = offset;
-	struct sk_buff *frag_iter;
-	int pos = 0;
-	int n;
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
-		offset += n;
-		if (n != copy)
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		pos = copy;
-	}
-
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			__wsum csum2 = 0;
-			struct page *page = skb_frag_page(frag);
-			u8  *vaddr = kmap(page);
-
-			if (copy > len)
-				copy = len;
-			n = csum_and_copy_to_iter(vaddr + frag->page_offset +
-						  offset - start, copy,
-						  &csum2, to);
-			kunmap(page);
-			offset += n;
-			if (n != copy)
-				goto fault;
-			*csump = csum_block_add(*csump, csum2, pos);
-			if (!(len -= copy))
-				return 0;
-			pos += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			__wsum csum2 = 0;
-			if (copy > len)
-				copy = len;
-			if (skb_copy_and_csum_datagram(frag_iter,
-						       offset - start,
-						       to, copy,
-						       &csum2))
-				goto fault;
-			*csump = csum_block_add(*csump, csum2, pos);
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-			pos += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	iov_iter_revert(to, offset - start_off);
-	return -EFAULT;
+	return __skb_datagram_iter(skb, offset, to, len, true,
+			csum_and_copy_to_iter, csump);
 }
 
 __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)