1 files changed, 72 insertions, 35 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a970168a3014..777db89fdaa7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -431,6 +431,12 @@ static inline void nvme_end_req_zoned(struct request *req)
 
 static inline void __nvme_end_req(struct request *req)
 {
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -441,12 +447,6 @@ void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
-		if (blk_rq_is_passthrough(req))
-			nvme_log_err_passthru(req);
-		else
-			nvme_log_error(req);
-	}
 	__nvme_end_req(req);
 	blk_mq_end_request(req, status);
 }
@@ -564,8 +564,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
-		case NVME_CTRL_NEW:
-		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
 			fallthrough;
@@ -885,6 +883,12 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	return BLK_STS_OK;
 }
 
+static void nvme_set_app_tag(struct request *req, struct nvme_command *cmnd)
+{
+	cmnd->rw.lbat = cpu_to_le16(bio_integrity(req->bio)->app_tag);
+	cmnd->rw.lbatm = cpu_to_le16(0xffff);
+}
+
 static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
 			      struct request *req)
 {
@@ -1017,18 +1021,17 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			control |= NVME_RW_PRINFO_PRACT;
 		}
 
-		switch (ns->head->pi_type) {
-		case NVME_NS_DPS_PI_TYPE3:
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD))
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
-			break;
-		case NVME_NS_DPS_PI_TYPE1:
-		case NVME_NS_DPS_PI_TYPE2:
-			control |= NVME_RW_PRINFO_PRCHK_GUARD |
-					NVME_RW_PRINFO_PRCHK_REF;
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_REFTAG)) {
+			control |= NVME_RW_PRINFO_PRCHK_REF;
 			if (op == nvme_cmd_zone_append)
 				control |= NVME_RW_APPEND_PIREMAP;
 			nvme_set_ref_tag(ns, cmnd, req);
-			break;
+		}
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_APPTAG)) {
+			control |= NVME_RW_PRINFO_PRCHK_APP;
+			nvme_set_app_tag(req, cmnd);
 		}
 	}
 
@@ -1695,7 +1698,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 
 	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
 			&result);
-	if (status < 0)
+
+	/*
+	 * It's either a kernel error or the host observed a connection
+	 * lost. In either case it's not possible communicate with the
+	 * controller and thus enter the error code path.
+	 */
+	if (status < 0 || status == NVME_SC_HOST_PATH_ERROR)
 		return status;
 
 	/*
@@ -2002,6 +2011,7 @@ static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
 	lim->atomic_write_hw_boundary = boundary;
 	lim->atomic_write_hw_unit_min = bs;
 	lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
+	lim->features |= BLK_FEAT_ATOMIC_WRITES;
 }
 
 static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
@@ -2126,14 +2136,16 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
 	struct queue_limits lim;
+	unsigned int memflags;
 	int ret;
 
-	blk_mq_freeze_queue(ns->disk->queue);
 	lim = queue_limits_start_update(ns->disk->queue);
 	nvme_set_ctrl_limits(ns->ctrl, &lim);
+
+	memflags = blk_mq_freeze_queue(ns->disk->queue);
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
-	blk_mq_unfreeze_queue(ns->disk->queue);
+	blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 
 	/* Hide the block-interface for these devices */
 	if (!ret)
@@ -2148,6 +2160,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	struct nvme_id_ns_nvm *nvm = NULL;
 	struct nvme_zone_info zi = {};
 	struct nvme_id_ns *id;
+	unsigned int memflags;
 	sector_t capacity;
 	unsigned lbaf;
 	int ret;
@@ -2177,12 +2190,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 			goto out;
 	}
 
-	blk_mq_freeze_queue(ns->disk->queue);
+	lim = queue_limits_start_update(ns->disk->queue);
+
+	memflags = blk_mq_freeze_queue(ns->disk->queue);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
 	capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
-
-	lim = queue_limits_start_update(ns->disk->queue);
 	nvme_set_ctrl_limits(ns->ctrl, &lim);
 	nvme_configure_metadata(ns->ctrl, ns->head, id, nvm, info);
 	nvme_set_chunk_sectors(ns, id, &lim);
@@ -2212,7 +2225,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	if (ret) {
-		blk_mq_unfreeze_queue(ns->disk->queue);
+		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 		goto out;
 	}
 
@@ -2228,7 +2241,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	set_bit(NVME_NS_READY, &ns->flags);
-	blk_mq_unfreeze_queue(ns->disk->queue);
+	blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 
 	if (blk_queue_is_zoned(ns->queue)) {
 		ret = blk_revalidate_disk_zones(ns->disk);
@@ -2284,8 +2297,10 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 	if (!ret && nvme_ns_head_multipath(ns->head)) {
 		struct queue_limits *ns_lim = &ns->disk->queue->limits;
 		struct queue_limits lim;
+		unsigned int memflags;
 
-		blk_mq_freeze_queue(ns->head->disk->queue);
+		lim = queue_limits_start_update(ns->head->disk->queue);
+		memflags = blk_mq_freeze_queue(ns->head->disk->queue);
 		/*
 		 * queue_limits mixes values that are the hardware limitations
 		 * for bio splitting with what is the device configuration.
@@ -2301,7 +2316,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		 * the splitting limits in to make sure we still obey possibly
 		 * lower limitations of other controllers.
 		 */
-		lim = queue_limits_start_update(ns->head->disk->queue);
 		lim.logical_block_size = ns_lim->logical_block_size;
 		lim.physical_block_size = ns_lim->physical_block_size;
 		lim.io_min = ns_lim->io_min;
@@ -2318,7 +2332,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
 
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
+		blk_mq_unfreeze_queue(ns->head->disk->queue, memflags);
 	}
 
 	return ret;
@@ -3092,7 +3106,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 				struct nvme_effects_log **log)
 {
-	struct nvme_effects_log	*cel = xa_load(&ctrl->cels, csi);
+	struct nvme_effects_log *old, *cel = xa_load(&ctrl->cels, csi);
 	int ret;
 
 	if (cel)
@@ -3109,7 +3123,11 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 		return ret;
 	}
 
-	xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+	old = xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		kfree(cel);
+		return xa_err(old);
+	}
 out:
 	*log = cel;
 	return 0;
@@ -3171,6 +3189,25 @@ free_data:
 	return ret;
 }
 
+static int nvme_init_effects_log(struct nvme_ctrl *ctrl,
+		u8 csi, struct nvme_effects_log **log)
+{
+	struct nvme_effects_log *effects, *old;
+
+	effects = kzalloc(sizeof(*effects), GFP_KERNEL);
+	if (!effects)
+		return -ENOMEM;
+
+	old = xa_store(&ctrl->cels, csi, effects, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		kfree(effects);
+		return xa_err(old);
+	}
+
+	*log = effects;
+	return 0;
+}
+
 static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl)
 {
 	struct nvme_effects_log	*log = ctrl->effects;
@@ -3217,10 +3254,9 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	}
 
 	if (!ctrl->effects) {
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
-		if (!ctrl->effects)
-			return -ENOMEM;
-		xa_store(&ctrl->cels, NVME_CSI_NVM, ctrl->effects, GFP_KERNEL);
+		ret = nvme_init_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
+		if (ret < 0)
+			return ret;
 	}
 
 	nvme_init_known_nvm_effects(ctrl);
@@ -3982,6 +4018,9 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
+
+	nvme_mpath_remove_sysfs_link(ns);
+
 	del_gendisk(ns->disk);
 
 	mutex_lock(&ns->ctrl->namespaces_lock);
@@ -4564,7 +4603,6 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		/* Reserved for fabric connect and keep alive */
 		set->reserved_tags = 2;
 	set->numa_node = ctrl->numa_node;
-	set->flags = BLK_MQ_F_NO_SCHED;
 	if (ctrl->ops->flags & NVME_F_BLOCKING)
 		set->flags |= BLK_MQ_F_BLOCKING;
 	set->cmd_size = cmd_size;
@@ -4639,7 +4677,6 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		/* Reserved for fabric connect */
 		set->reserved_tags = 1;
 	set->numa_node = ctrl->numa_node;
-	set->flags = BLK_MQ_F_SHOULD_MERGE;
 	if (ctrl->ops->flags & NVME_F_BLOCKING)
 		set->flags |= BLK_MQ_F_BLOCKING;
 	set->cmd_size = cmd_size;