1 files changed, 92 insertions, 40 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ce1b61519441..e68a8c4ac5a6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -179,7 +179,7 @@ int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
 
-int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
@@ -192,7 +192,6 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
 
 static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -280,14 +279,13 @@ static blk_status_t nvme_error_status(u16 status)
 
 static void nvme_retry_req(struct request *req)
 {
-	struct nvme_ns *ns = req->q->queuedata;
 	unsigned long delay = 0;
 	u16 crd;
 
 	/* The mask and shift result must be <= 3 */
 	crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
-	if (ns && crd)
-		delay = ns->ctrl->crdt[crd - 1] * 100;
+	if (crd)
+		delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
 
 	nvme_req(req)->retries++;
 	blk_mq_requeue_request(req, false);
@@ -331,7 +329,7 @@ static inline void nvme_end_req(struct request *req)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
 
-	nvme_trace_bio_complete(req, status);
+	nvme_trace_bio_complete(req);
 	blk_mq_end_request(req, status);
 }
 
@@ -357,6 +355,21 @@ void nvme_complete_rq(struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
+/*
+ * Called to unwind from ->queue_rq on a failed command submission so that the
+ * multipathing code gets called to potentially failover to another path.
+ * The caller needs to unwind all transport specific resource allocations and
+ * must return propagate the return value.
+ */
+blk_status_t nvme_host_path_error(struct request *req)
+{
+	nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
+	blk_mq_set_request_complete(req);
+	nvme_complete_rq(req);
+	return BLK_STS_OK;
+}
+EXPORT_SYMBOL_GPL(nvme_host_path_error);
+
 bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 {
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
@@ -372,6 +385,26 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
 
+void nvme_cancel_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->tagset) {
+		blk_mq_tagset_busy_iter(ctrl->tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
+
+void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->admin_tagset) {
+		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset);
+
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
@@ -578,7 +611,7 @@ struct request *nvme_alloc_request(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
 
-struct request *nvme_alloc_request_qid(struct request_queue *q,
+static struct request *nvme_alloc_request_qid(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
 {
 	struct request *req;
@@ -589,7 +622,6 @@ struct request *nvme_alloc_request_qid(struct request_queue *q,
 		nvme_init_request(req, cmd);
 	return req;
 }
-EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
 
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
@@ -844,11 +876,11 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 void nvme_cleanup_cmd(struct request *req)
 {
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		struct nvme_ns *ns = req->rq_disk->private_data;
+		struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 		struct page *page = req->special_vec.bv_page;
 
-		if (page == ns->ctrl->discard_page)
-			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
+		if (page == ctrl->discard_page)
+			clear_bit_unlock(0, &ctrl->discard_page_busy);
 		else
 			kfree(page_address(page) + req->special_vec.bv_offset);
 	}
@@ -927,7 +959,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 
 	rq->cmd_flags |= REQ_HIPRI;
 	rq->end_io_data = &wait;
-	blk_execute_rq_nowait(q, bd_disk, rq, at_head, nvme_end_sync_rq);
+	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
 
 	while (!completion_done(&wait)) {
 		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
@@ -966,7 +998,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	if (poll)
 		nvme_execute_rq_polled(req->q, NULL, req, at_head);
 	else
-		blk_execute_rq(req->q, NULL, req, at_head);
+		blk_execute_rq(NULL, req, at_head);
 	if (result)
 		*result = nvme_req(req)->result;
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
@@ -1103,7 +1135,7 @@ void nvme_execute_passthru_rq(struct request *rq)
 	u32 effects;
 
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
-	blk_execute_rq(rq->q, disk, rq, 0);
+	blk_execute_rq(disk, rq, 0);
 	nvme_passthru_end(ctrl, effects);
 }
 EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
@@ -1115,7 +1147,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
-	struct gendisk *disk = ns ? ns->disk : NULL;
+	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	struct request *req;
 	struct bio *bio = NULL;
 	void *meta = NULL;
@@ -1135,8 +1167,9 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 		if (ret)
 			goto out;
 		bio = req->bio;
-		bio->bi_disk = disk;
-		if (disk && meta_buffer && meta_len) {
+		if (bdev)
+			bio_set_dev(bio, bdev);
+		if (bdev && meta_buffer && meta_len) {
 			meta = nvme_add_user_metadata(bio, meta_buffer, meta_len,
 					meta_seed, write);
 			if (IS_ERR(meta)) {
@@ -1204,7 +1237,7 @@ static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
 
-	blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
+	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
 
 	return 0;
 }
@@ -1545,8 +1578,21 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	}
 
 	length = (io.nblocks + 1) << ns->lba_shift;
-	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = nvme_to_user_ptr(io.metadata);
+
+	if ((io.control & NVME_RW_PRINFO_PRACT) &&
+	    ns->ms == sizeof(struct t10_pi_tuple)) {
+		/*
+		 * Protection information is stripped/inserted by the
+		 * controller.
+		 */
+		if (nvme_to_user_ptr(io.metadata))
+			return -EINVAL;
+		meta_len = 0;
+		metadata = NULL;
+	} else {
+		meta_len = (io.nblocks + 1) * ns->ms;
+		metadata = nvme_to_user_ptr(io.metadata);
+	}
 
 	if (ns->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
@@ -2114,9 +2160,8 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	nvme_config_discard(disk, ns);
 	nvme_config_write_zeroes(disk, ns);
 
-	if ((id->nsattr & NVME_NS_ATTR_RO) ||
-	    test_bit(NVME_NS_FORCE_RO, &ns->flags))
-		set_disk_ro(disk, true);
+	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
+		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -2165,17 +2210,18 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	ns->lba_shift = id->lbaf[lbaf].ds;
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
+	ret = nvme_configure_metadata(ns, id);
+	if (ret)
+		goto out_unfreeze;
+	nvme_set_chunk_sectors(ns, id);
+	nvme_update_disk_info(ns->disk, ns, id);
+
 	if (ns->head->ids.csi == NVME_CSI_ZNS) {
 		ret = nvme_update_zone_info(ns, lbaf);
 		if (ret)
 			goto out_unfreeze;
 	}
 
-	ret = nvme_configure_metadata(ns, id);
-	if (ret)
-		goto out_unfreeze;
-	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->disk, ns, id);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
@@ -2819,7 +2865,7 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev,
 	struct nvme_subsystem *subsys =
 		container_of(dev, struct nvme_subsystem, dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", subsys->subnqn);
+	return sysfs_emit(buf, "%s\n", subsys->subnqn);
 }
 static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);
 
@@ -2849,7 +2895,7 @@ static struct attribute *nvme_subsys_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group nvme_subsys_attrs_group = {
+static const struct attribute_group nvme_subsys_attrs_group = {
 	.attrs = nvme_subsys_attrs,
 };
 
@@ -2858,6 +2904,11 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = {
 	NULL,
 };
 
+static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl)
+{
+	return ctrl->opts && ctrl->opts->discovery_nqn;
+}
+
 static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 		struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 {
@@ -2877,7 +2928,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 		}
 
 		if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
-		    (ctrl->opts && ctrl->opts->discovery_nqn))
+		    nvme_discovery_ctrl(ctrl))
 			continue;
 
 		dev_err(ctrl->device,
@@ -3146,7 +3197,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 			goto out_free;
 		}
 
-		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+		if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
 			dev_err(ctrl->device,
 				"keep-alive support is mandatory for fabrics\n");
 			ret = -EINVAL;
@@ -3186,7 +3237,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
-	if (!ctrl->identified) {
+	if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
 		ret = nvme_hwmon_init(ctrl);
 		if (ret < 0)
 			return ret;
@@ -3507,7 +3558,7 @@ static ssize_t nvme_sysfs_show_transport(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
+	return sysfs_emit(buf, "%s\n", ctrl->ops->name);
 }
 static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
 
@@ -3541,7 +3592,7 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subsys->subnqn);
+	return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn);
 }
 static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
 
@@ -3551,7 +3602,7 @@ static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
+	return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn);
 }
 static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);
 
@@ -3561,7 +3612,7 @@ static ssize_t nvme_sysfs_show_hostid(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
+	return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id);
 }
 static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);
 
@@ -3679,7 +3730,7 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static struct attribute_group nvme_dev_attrs_group = {
+static const struct attribute_group nvme_dev_attrs_group = {
 	.attrs		= nvme_dev_attrs,
 	.is_visible	= nvme_dev_attrs_are_visible,
 };
@@ -3813,7 +3864,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 		}
 	}
 
-	list_add_tail(&ns->siblings, &head->list);
+	list_add_tail_rcu(&ns->siblings, &head->list);
 	ns->head = head;
 	mutex_unlock(&ctrl->subsys->lock);
 	return 0;
@@ -4422,6 +4473,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_hwmon_exit(ctrl);
 	nvme_fault_inject_fini(&ctrl->fault_inject);
 	dev_pm_qos_hide_latency_tolerance(ctrl->device);
 	cdev_device_del(&ctrl->cdev, ctrl->device);
@@ -4434,7 +4486,7 @@ static void nvme_free_cels(struct nvme_ctrl *ctrl)
 	struct nvme_effects_log	*cel;
 	unsigned long i;
 
-	xa_for_each (&ctrl->cels, i, cel) {
+	xa_for_each(&ctrl->cels, i, cel) {
 		xa_erase(&ctrl->cels, i);
 		kfree(cel);
 	}