Merge tag 'io_uring-5.9-2020-08-23' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Sagi:
       - nvme completion rework from Christoph and Chao that mostly came
         from a bit of divergence of how we classify errors related to
         pathing/retry etc.
       - nvmet passthru fixes from Chaitanya
       - minor nvmet fixes from Amit and I
       - mpath round-robin path selection fix from Martin
       - ignore noiob for zoned devices from Keith
       - minor nvme-fc fix from Tianjia"

 - BFQ cgroup leak fix (Dmitry)

 - block layer MAINTAINERS addition (Geert)

 - fix null_blk FUA checking (Hou)

 - get_max_io_size() size fix (Keith)

 - fix block page_is_mergeable() for compound pages (Matthew)

 - discard granularity fixes (Ming)

 - IO scheduler ordering fix (Ming)

 - misc fixes

* tag 'io_uring-5.9-2020-08-23' of git://git.kernel.dk/linux-block: (31 commits)
  null_blk: fix passing of REQ_FUA flag in null_handle_rq
  nvmet: Disable keep-alive timer when kato is cleared to 0h
  nvme: redirect commands on dying queue
  nvme: just check the status code type in nvme_is_path_error
  nvme: refactor command completion
  nvme: rename and document nvme_end_request
  nvme: skip noiob for zoned devices
  nvme-pci: fix PRP pool size
  nvme-pci: Use u32 for nvme_dev.q_depth and nvme_queue.q_depth
  nvme: Use spin_lock_irq() when taking the ctrl->lock
  nvmet: call blk_mq_free_request() directly
  nvmet: fix oops in pt cmd execution
  nvmet: add ns tear down label for pt-cmd handling
  nvme: multipath: round-robin: eliminate "fallback" variable
  nvme: multipath: round-robin: fix single non-optimized path case
  nvme-fc: Fix wrong return value in __nvme_fc_init_request()
  nvmet-passthru: Reject commands with non-sgl flags set
  nvmet: fix a memory leak
  blkcg: fix memleak for iolatency
  MAINTAINERS: Add missing header files to BLOCK LAYER section
  ...

Documentation/fault-injection/nvme-fault-injection.rst

@@ -3,7 +3,7 @@ NVMe Fault Injection
 Linux's fault injection framework provides a systematic way to support
 error injection via debugfs in the /sys/kernel/debug directory. When
 enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
-injected into the nvme_end_request. Users can change the default status
+injected into the nvme_try_complete_req. Users can change the default status
 code and no retry flag via the debugfs. The list of Generic Command
 Status can be found in include/linux/nvme.h
 

MAINTAINERS

@@ -3205,6 +3205,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 

block/bfq-cgroup.c

@@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg)
 		kfree(bfqg);
 }
 
-void bfqg_and_blkg_get(struct bfq_group *bfqg)
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
 {
 	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
 	bfqg_get(bfqg);

block/bfq-iosched.h

@@ -986,7 +986,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_and_blkg_get(struct bfq_group *bfqg);
 void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

block/bfq-wf2q.c

@@ -533,9 +533,7 @@ static void bfq_get_entity(struct bfq_entity *entity)
 		bfqq->ref++;
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
 			     bfqq, bfqq->ref);
-	} else
-		bfqg_and_blkg_get(container_of(entity, struct bfq_group,
-					       entity));
+	}
 }
 
 /**
@@ -649,14 +647,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
 
 	entity->on_st_or_in_serv = false;
 	st->wsum -= entity->weight;
-	if (is_in_service)
-		return;
-
-	if (bfqq)
+	if (bfqq && !is_in_service)
 		bfq_put_queue(bfqq);
-	else
-		bfqg_and_blkg_put(container_of(entity, struct bfq_group,
-					       entity));
 }
 
 /**

block/bio.c

@@ -740,8 +740,8 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		struct page *page, unsigned int len, unsigned int off,
 		bool *same_page)
 {
-	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
-		bv->bv_offset + bv->bv_len - 1;
+	size_t bv_end = bv->bv_offset + bv->bv_len;
+	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
 	phys_addr_t page_addr = page_to_phys(page);
 
 	if (vec_end_addr + 1 != page_addr + off)
@@ -750,9 +750,9 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		return false;
 
 	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
-	if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page)
-		return false;
-	return true;
+	if (*same_page)
+		return true;
+	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
 }
 
 /*

block/blk-cgroup.c

@@ -1152,13 +1152,15 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
+	ret = blk_throtl_init(q);
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(q);
-	if (ret)
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
 		goto err_destroy_all;
+	}
 	return 0;
 
 err_destroy_all:

block/blk-merge.c

@@ -154,7 +154,7 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	if (max_sectors > start_offset)
 		return max_sectors - start_offset;
 
-	return sectors & (lbs - 1);
+	return sectors & ~(lbs - 1);
 }
 
 static inline unsigned get_max_segment_size(const struct request_queue *q,
@@ -533,10 +533,17 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(__blk_rq_map_sg);
 
+static inline unsigned int blk_rq_get_max_segments(struct request *rq)
+{
+	if (req_op(rq) == REQ_OP_DISCARD)
+		return queue_max_discard_segments(rq->q);
+	return queue_max_segments(rq->q);
+}
+
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
 		unsigned int nr_phys_segs)
 {
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q))
+	if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
 		goto no_merge;
 
 	if (blk_integrity_merge_bio(req->q, req, bio) == false)
@@ -624,7 +631,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (total_phys_segments > queue_max_segments(q))
+	if (total_phys_segments > blk_rq_get_max_segments(req))
 		return 0;
 
 	if (blk_integrity_merge_rq(q, req, next) == false)

block/blk-mq-sched.c

@@ -78,6 +78,15 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 		return;
 	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
+	/*
+	 * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch)
+	 * in blk_mq_run_hw_queue(). Its pair is the barrier in
+	 * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART,
+	 * meantime new request added to hctx->dispatch is missed to check in
+	 * blk_mq_run_hw_queue().
+	 */
+	smp_mb();
+
 	blk_mq_run_hw_queue(hctx, true);
 }
 

block/blk-mq.c

@@ -1437,6 +1437,15 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
+		/*
+		 * Order adding requests to hctx->dispatch and checking
+		 * SCHED_RESTART flag. The pair of this smp_mb() is the one
+		 * in blk_mq_sched_restart(). Avoid restart code path to
+		 * miss the new added requests to hctx->dispatch, meantime
+		 * SCHED_RESTART is observed here.
+		 */
+		smp_mb();
+
 		/*
 		 * If SCHED_RESTART was set by the caller of this function and
 		 * it is no longer set that means that it was cleared by another
@@ -1834,6 +1843,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
+ * @at_head: true if the request should be inserted at the head of the list.
  * @run_queue: If we should run the hardware queue after inserting the request.
  *
  * Should only be used carefully, when the caller knows we want to
@@ -2016,7 +2026,8 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, false, run_queue);
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+
 	return BLK_STS_OK;
 }
 

block/bsg-lib.c

@@ -378,7 +378,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	bset->timeout_fn = timeout;
 
 	set = &bset->tag_set;
-	set->ops = &bsg_mq_ops,
+	set->ops = &bsg_mq_ops;
 	set->nr_hw_queues = 1;
 	set->queue_depth = 128;
 	set->numa_node = NUMA_NO_NODE;

drivers/block/loop.c

@@ -878,6 +878,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	u32 granularity, max_discard_sectors;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -890,11 +891,10 @@ static void loop_config_discard(struct loop_device *lo)
 		struct request_queue *backingq;
 
 		backingq = bdev_get_queue(inode->i_bdev);
-		blk_queue_max_discard_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
 
-		blk_queue_max_write_zeroes_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
+		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
+		granularity = backingq->limits.discard_granularity ?:
+			queue_physical_block_size(backingq);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -903,23 +903,26 @@ static void loop_config_discard(struct loop_device *lo)
 	 * useful information.
 	 */
 	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
+		max_discard_sectors = 0;
+		granularity = 0;
 
 	} else {
-		q->limits.discard_granularity = inode->i_sb->s_blocksize;
-		q->limits.discard_alignment = 0;
-
-		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
 	}
 
-	if (q->limits.max_write_zeroes_sectors)
+	if (max_discard_sectors) {
+		q->limits.discard_granularity = granularity;
+		blk_queue_max_discard_sectors(q, max_discard_sectors);
+		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
 		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-	else
+	} else {
+		q->limits.discard_granularity = 0;
+		blk_queue_max_discard_sectors(q, 0);
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
+	}
+	q->limits.discard_alignment = 0;
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)

drivers/block/null_blk_main.c

@@ -1147,7 +1147,7 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
-				     req_op(rq) & REQ_FUA);
+				     rq->cmd_flags & REQ_FUA);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;

drivers/block/rnbd/rnbd-srv.c

@@ -148,7 +148,8 @@ static int process_rdma(struct rtrs_srv *sess,
 	/* Generate bio with pages pointing to the rdma buffer */
 	bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %ld\n", PTR_ERR(bio));
+		err = PTR_ERR(bio);
+		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err);
 		goto sess_dev_put;
 	}
 

drivers/block/virtio_blk.c

@@ -126,16 +126,31 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	if (!range)
 		return -ENOMEM;
 
-	__rq_for_each_bio(bio, req) {
-		u64 sector = bio->bi_iter.bi_sector;
-		u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
-
-		range[n].flags = cpu_to_le32(flags);
-		range[n].num_sectors = cpu_to_le32(num_sectors);
-		range[n].sector = cpu_to_le64(sector);
-		n++;
+	/*
+	 * Single max discard segment means multi-range discard isn't
+	 * supported, and block layer only runs contiguity merge like
+	 * normal RW request. So we can't reply on bio for retrieving
+	 * each range info.
+	 */
+	if (queue_max_discard_segments(req->q) == 1) {
+		range[0].flags = cpu_to_le32(flags);
+		range[0].num_sectors = cpu_to_le32(blk_rq_sectors(req));
+		range[0].sector = cpu_to_le64(blk_rq_pos(req));
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 sector = bio->bi_iter.bi_sector;
+			u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+
+			range[n].flags = cpu_to_le32(flags);
+			range[n].num_sectors = cpu_to_le32(num_sectors);
+			range[n].sector = cpu_to_le64(sector);
+			n++;
+		}
 	}
 
+	WARN_ON_ONCE(n != segments);
+
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
 	req->special_vec.bv_len = sizeof(*range) * segments;

drivers/nvme/host/core.c

@@ -241,17 +241,6 @@ static blk_status_t nvme_error_status(u16 status)
 	}
 }
 
-static inline bool nvme_req_needs_retry(struct request *req)
-{
-	if (blk_noretry_request(req))
-		return false;
-	if (nvme_req(req)->status & NVME_SC_DNR)
-		return false;
-	if (nvme_req(req)->retries >= nvme_max_retries)
-		return false;
-	return true;
-}
-
 static void nvme_retry_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
@@ -268,34 +257,67 @@ static void nvme_retry_req(struct request *req)
 	blk_mq_delay_kick_requeue_list(req->q, delay);
 }
 
-void nvme_complete_rq(struct request *req)
+enum nvme_disposition {
+	COMPLETE,
+	RETRY,
+	FAILOVER,
+};
+
+static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 {
-	blk_status_t status = nvme_error_status(nvme_req(req)->status);
+	if (likely(nvme_req(req)->status == 0))
+		return COMPLETE;
 
-	trace_nvme_complete_rq(req);
+	if (blk_noretry_request(req) ||
+	    (nvme_req(req)->status & NVME_SC_DNR) ||
+	    nvme_req(req)->retries >= nvme_max_retries)
+		return COMPLETE;
 
-	nvme_cleanup_cmd(req);
+	if (req->cmd_flags & REQ_NVME_MPATH) {
+		if (nvme_is_path_error(nvme_req(req)->status) ||
+		    blk_queue_dying(req->q))
+			return FAILOVER;
+	} else {
+		if (blk_queue_dying(req->q))
+			return COMPLETE;
+	}
 
-	if (nvme_req(req)->ctrl->kas)
-		nvme_req(req)->ctrl->comp_seen = true;
+	return RETRY;
+}
 
-	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
-			return;
+static inline void nvme_end_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-		if (!blk_queue_dying(req->q)) {
-			nvme_retry_req(req);
-			return;
-		}
-	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		   req_op(req) == REQ_OP_ZONE_APPEND) {
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
-	}
 
 	nvme_trace_bio_complete(req, status);
 	blk_mq_end_request(req, status);
 }
+
+void nvme_complete_rq(struct request *req)
+{
+	trace_nvme_complete_rq(req);
+	nvme_cleanup_cmd(req);
+
+	if (nvme_req(req)->ctrl->kas)
+		nvme_req(req)->ctrl->comp_seen = true;
+
+	switch (nvme_decide_disposition(req)) {
+	case COMPLETE:
+		nvme_end_req(req);
+		return;
+	case RETRY:
+		nvme_retry_req(req);
+		return;
+	case FAILOVER:
+		nvme_failover_req(req);
+		return;
+	}
+}
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
 bool nvme_cancel_request(struct request *req, void *data, bool reserved)
@@ -2075,7 +2097,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		}
 	}
 
-	if (iob)
+	if (iob && !blk_queue_is_zoned(ns->queue))
 		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
@@ -2965,14 +2987,14 @@ static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
 	struct nvme_cel *cel, *ret = NULL;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_for_each_entry(cel, &ctrl->cels, entry) {
 		if (cel->csi == csi) {
 			ret = cel;
 			break;
 		}
 	}
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 
 	return ret;
 }
@@ -2999,9 +3021,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 
 	cel->csi = csi;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_add_tail(&cel->entry, &ctrl->cels);
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 out:
 	*log = &cel->log;
 	return 0;

drivers/nvme/host/fc.c

@@ -2035,7 +2035,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	}
 
 	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
-	if (!nvme_end_request(rq, status, result))
+	if (!nvme_try_complete_req(rq, status, result))
 		nvme_fc_complete_rq(rq);
 
 check_error:
@@ -2078,7 +2078,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.cmddma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - cmdiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 		goto out_on_error;
 	}
 
@@ -2088,7 +2088,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.rspdma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - rspiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 	}
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);

drivers/nvme/host/multipath.c

@@ -65,51 +65,30 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	}
 }
 
-bool nvme_failover_req(struct request *req)
+void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
-	u16 status = nvme_req(req)->status;
+	u16 status = nvme_req(req)->status & 0x7ff;
 	unsigned long flags;
 
-	switch (status & 0x7ff) {
-	case NVME_SC_ANA_TRANSITION:
-	case NVME_SC_ANA_INACCESSIBLE:
-	case NVME_SC_ANA_PERSISTENT_LOSS:
-		/*
-		 * If we got back an ANA error we know the controller is alive,
-		 * but not ready to serve this namespaces.  The spec suggests
-		 * we should update our general state here, but due to the fact
-		 * that the admin and I/O queues are not serialized that is
-		 * fundamentally racy.  So instead just clear the current path,
-		 * mark the the path as pending and kick of a re-read of the ANA
-		 * log page ASAP.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		if (ns->ctrl->ana_log_buf) {
-			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
-			queue_work(nvme_wq, &ns->ctrl->ana_work);
-		}
-		break;
-	case NVME_SC_HOST_PATH_ERROR:
-	case NVME_SC_HOST_ABORTED_CMD:
-		/*
-		 * Temporary transport disruption in talking to the controller.
-		 * Try to send on a new path.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		break;
-	default:
-		/* This was a non-ANA error so follow the normal error path. */
-		return false;
+	nvme_mpath_clear_current_path(ns);
+
+	/*
+	 * If we got back an ANA error, we know the controller is alive but not
+	 * ready to serve this namespace.  Kick of a re-read of the ANA
+	 * information page, and just try any other available path for now.
+	 */
+	if (nvme_is_ana_error(status) && ns->ctrl->ana_log_buf) {
+		set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+		queue_work(nvme_wq, &ns->ctrl->ana_work);
 	}
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
-	blk_mq_end_request(req, 0);
 
+	blk_mq_end_request(req, 0);
 	kblockd_schedule_work(&ns->head->requeue_work);
-	return true;
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -233,7 +212,7 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
 static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 		int node, struct nvme_ns *old)
 {
-	struct nvme_ns *ns, *found, *fallback = NULL;
+	struct nvme_ns *ns, *found = NULL;
 
 	if (list_is_singular(&head->list)) {
 		if (nvme_path_is_disabled(old))
@@ -252,18 +231,22 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			goto out;
 		}
 		if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
-			fallback = ns;
+			found = ns;
 	}
 
-	/* No optimized path found, re-check the current path */
+	/*
+	 * The loop above skips the current path for round-robin semantics.
+	 * Fall back to the current path if either:
+	 *  - no other optimized path found and current is optimized,
+	 *  - no other usable path found and current is usable.
+	 */
 	if (!nvme_path_is_disabled(old) &&
-	    old->ana_state == NVME_ANA_OPTIMIZED) {
-		found = old;
-		goto out;
-	}
-	if (!fallback)
+	    (old->ana_state == NVME_ANA_OPTIMIZED ||
+	     (!found && old->ana_state == NVME_ANA_NONOPTIMIZED)))
+		return old;
+
+	if (!found)
 		return NULL;
-	found = fallback;
 out:
 	rcu_assign_pointer(head->current_path[node], found);
 	return found;

drivers/nvme/host/nvme.h

@@ -523,7 +523,31 @@ static inline u32 nvme_bytes_to_numd(size_t len)
 	return (len >> 2) - 1;
 }
 
-static inline bool nvme_end_request(struct request *req, __le16 status,
+static inline bool nvme_is_ana_error(u16 status)
+{
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool nvme_is_path_error(u16 status)
+{
+	/* check for a status code type of 'path related status' */
+	return (status & 0x700) == 0x300;
+}
+
+/*
+ * Fill in the status and result information from the CQE, and then figure out
+ * if blk-mq will need to use IPI magic to complete the request, and if yes do
+ * so.  If not let the caller complete the request without an indirect function
+ * call.
+ */
+static inline bool nvme_try_complete_req(struct request *req, __le16 status,
 		union nvme_result result)
 {
 	struct nvme_request *rq = nvme_req(req);
@@ -629,7 +653,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
-bool nvme_failover_req(struct request *req);
+void nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
@@ -688,9 +712,8 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
 }
 
-static inline bool nvme_failover_req(struct request *req)
+static inline void nvme_failover_req(struct request *req)
 {
-	return false;
 }
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {

drivers/nvme/host/pci.c

@@ -120,7 +120,7 @@ struct nvme_dev {
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	u16 q_depth;
+	u32 q_depth;
 	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
@@ -157,13 +157,13 @@ struct nvme_dev {
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
 	int ret;
-	u16 n;
+	u32 n;
 
-	ret = kstrtou16(val, 10, &n);
+	ret = kstrtou32(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_ushort(val, kp);
+	return param_set_uint(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -195,7 +195,7 @@ struct nvme_queue {
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
-	u16 q_depth;
+	u32 q_depth;
 	u16 cq_vector;
 	u16 sq_tail;
 	u16 cq_head;
@@ -961,7 +961,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 
 	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
-	if (!nvme_end_request(req, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
 		nvme_pci_complete_rq(req);
 }
 
@@ -2320,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
-	dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1,
+	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
 	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
@@ -2460,7 +2460,8 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
-						PAGE_SIZE, PAGE_SIZE, 0);
+						NVME_CTRL_PAGE_SIZE,
+						NVME_CTRL_PAGE_SIZE, 0);
 	if (!dev->prp_page_pool)
 		return -ENOMEM;
 

drivers/nvme/host/rdma.c

@@ -1189,7 +1189,7 @@ static void nvme_rdma_end_request(struct nvme_rdma_request *req)
 
 	if (!refcount_dec_and_test(&req->ref))
 		return;
-	if (!nvme_end_request(rq, req->status, req->result))
+	if (!nvme_try_complete_req(rq, req->status, req->result))
 		nvme_rdma_complete_rq(rq);
 }
 

drivers/nvme/host/tcp.c

@@ -481,7 +481,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		return -EINVAL;
 	}
 
-	if (!nvme_end_request(rq, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -672,7 +672,7 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
 	union nvme_result res = {};
 
-	if (!nvme_end_request(rq, cpu_to_le16(status << 1), res))
+	if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
 		nvme_complete_rq(rq);
 }
 

drivers/nvme/target/configfs.c

@@ -1136,6 +1136,7 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
 	up_write(&nvmet_config_sem);
 
 	kfree_rcu(new_model, rcuhead);
+	kfree(new_model_number);
 
 	return count;
 }

drivers/nvme/target/core.c

@@ -397,6 +397,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
@@ -406,6 +409,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 
 static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
 
 	cancel_delayed_work_sync(&ctrl->ka_work);

drivers/nvme/target/loop.c

@@ -115,7 +115,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 			return;
 		}
 
-		if (!nvme_end_request(rq, cqe->status, cqe->result))
+		if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
 			nvme_loop_complete_rq(rq);
 	}
 }

drivers/nvme/target/passthru.c

@@ -165,7 +165,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, status);
-	blk_put_request(rq);
+	blk_mq_free_request(rq);
 }
 
 static void nvmet_passthru_req_done(struct request *rq,
@@ -175,7 +175,7 @@ static void nvmet_passthru_req_done(struct request *rq,
 
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, nvme_req(rq)->status);
-	blk_put_request(rq);
+	blk_mq_free_request(rq);
 }
 
 static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
@@ -230,7 +230,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		if (unlikely(!ns)) {
 			pr_err("failed to get passthru ns nsid:%u\n", nsid);
 			status = NVME_SC_INVALID_NS | NVME_SC_DNR;
-			goto fail_out;
+			goto out;
 		}
 
 		q = ns->queue;
@@ -238,16 +238,15 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 
 	rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(rq)) {
-		rq = NULL;
 		status = NVME_SC_INTERNAL;
-		goto fail_out;
+		goto out_put_ns;
 	}
 
 	if (req->sg_cnt) {
 		ret = nvmet_passthru_map_sg(req, rq);
 		if (unlikely(ret)) {
 			status = NVME_SC_INTERNAL;
-			goto fail_out;
+			goto out_put_req;
 		}
 	}
 
@@ -274,11 +273,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 
 	return;
 
-fail_out:
+out_put_req:
+	blk_mq_free_request(rq);
+out_put_ns:
 	if (ns)
 		nvme_put_ns(ns);
+out:
 	nvmet_req_complete(req, status);
-	blk_put_request(rq);
 }
 
 /*
@@ -326,6 +327,10 @@ static u16 nvmet_setup_passthru_command(struct nvmet_req *req)
 
 u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
 {
+	/* Reject any commands with non-sgl flags set (ie. fused commands) */
+	if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL)
+		return NVME_SC_INVALID_FIELD;
+
 	switch (req->cmd->common.opcode) {
 	case nvme_cmd_resv_register:
 	case nvme_cmd_resv_report:
@@ -396,6 +401,10 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
 
 u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 {
+	/* Reject any commands with non-sgl flags set (ie. fused commands) */
+	if (req->cmd->common.flags & ~NVME_CMD_SGL_ALL)
+		return NVME_SC_INVALID_FIELD;
+
 	/*
 	 * Passthru all vendor specific commands
 	 */