Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A small collection of fixes that should go into this series. This
  contains:

   - NVMe pull request from Christoph, with various fixes for nvme
     proper and nvme-fc.

   - disable runtime PM for blk-mq for now.

     With scsi now defaulting to using blk-mq, this reared its head as
     an issue. Longer term we'll fix up runtime PM for blk-mq, for now
     just disable it to prevent a hang on laptop resume for some folks.

   - blk-mq CPU <-> hw queue map fix from Christoph.

   - xen/blkfront pull request from Konrad, with two small fixes for the
     blkfront driver.

   - a few fixups for nbd from Joseph.

   - a stable fix for pblk from Javier"

* 'for-linus' of git://git.kernel.dk/linux-block:
  lightnvm: pblk: advance bio according to lba index
  nvme: validate admin queue before unquiesce
  nbd: clear disconnected on reconnect
  nvme-pci: fix HMB size calculation
  nvme-fc: revise TRADDR parsing
  nvme-fc: address target disconnect race conditions in fcp io submit
  nvme: fabrics commands should use the fctype field for data direction
  nvme: also provide a UUID in the WWID sysfs attribute
  xen/blkfront: always allocate grants first from per-queue persistent grants
  xen-blkfront: fix mq start/stop race
  blk-mq: map queues to all present CPUs
  block: disable runtime-pm for blk-mq
  xen-blkfront: Fix handling of non-supported operations
  nbd: only set sndtimeo if we have a timeout set
  nbd: take tx_lock before disconnecting
  nbd: allow multiple disconnects to be sent

Author: torvalds

block/blk-core.c

@@ -3421,6 +3421,10 @@ EXPORT_SYMBOL(blk_finish_plug);
  */
 void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
 {
+	/* not support for RQF_PM and ->rpm_status in blk-mq yet */
+	if (q->mq_ops)
+		return;
+
 	q->dev = dev;
 	q->rpm_status = RPM_ACTIVE;
 	pm_runtime_set_autosuspend_delay(q->dev, -1);

block/blk-mq-cpumap.c

@@ -17,9 +17,9 @@
 static int cpu_to_queue_index(unsigned int nr_queues, const int cpu)
 {
 	/*
-	 * Non online CPU will be mapped to queue index 0.
+	 * Non present CPU will be mapped to queue index 0.
 	 */
-	if (!cpu_online(cpu))
+	if (!cpu_present(cpu))
 		return 0;
 	return cpu % nr_queues;
 }

drivers/block/nbd.c

@@ -908,7 +908,8 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 			continue;
 		}
 		sk_set_memalloc(sock->sk);
-		sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
+		if (nbd->tag_set.timeout)
+			sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
 		atomic_inc(&config->recv_threads);
 		refcount_inc(&nbd->config_refs);
 		old = nsock->sock;
@@ -922,6 +923,8 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		mutex_unlock(&nsock->tx_lock);
 		sockfd_put(old);
 
+		clear_bit(NBD_DISCONNECTED, &config->runtime_flags);
+
 		/* We take the tx_mutex in an error path in the recv_work, so we
 		 * need to queue_work outside of the tx_mutex.
 		 */
@@ -978,11 +981,15 @@ static void send_disconnects(struct nbd_device *nbd)
 	int i, ret;
 
 	for (i = 0; i < config->num_connections; i++) {
+		struct nbd_sock *nsock = config->socks[i];
+
 		iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
+		mutex_lock(&nsock->tx_lock);
 		ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
 		if (ret <= 0)
 			dev_err(disk_to_dev(nbd->disk),
 				"Send disconnect failed %d\n", ret);
+		mutex_unlock(&nsock->tx_lock);
 	}
 }
 
@@ -991,9 +998,8 @@ static int nbd_disconnect(struct nbd_device *nbd)
 	struct nbd_config *config = nbd->config;
 
 	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
-	if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED,
-			      &config->runtime_flags))
-		send_disconnects(nbd);
+	set_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+	send_disconnects(nbd);
 	return 0;
 }
 
@@ -1074,7 +1080,9 @@ static int nbd_start_device(struct nbd_device *nbd)
 			return -ENOMEM;
 		}
 		sk_set_memalloc(config->socks[i]->sock->sk);
-		config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
+		if (nbd->tag_set.timeout)
+			config->socks[i]->sock->sk->sk_sndtimeo =
+				nbd->tag_set.timeout;
 		atomic_inc(&config->recv_threads);
 		refcount_inc(&nbd->config_refs);
 		INIT_WORK(&args->work, recv_work);

drivers/block/xen-blkfront.c

@@ -111,7 +111,7 @@ struct blk_shadow {
 };
 
 struct blkif_req {
-	int	error;
+	blk_status_t	error;
 };
 
 static inline struct blkif_req *blkif_req(struct request *rq)
@@ -708,6 +708,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 	 * existing persistent grants, or if we have to get new grants,
 	 * as there are not sufficiently many free.
 	 */
+	bool new_persistent_gnts = false;
 	struct scatterlist *sg;
 	int num_sg, max_grefs, num_grant;
 
@@ -719,19 +720,21 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		 */
 		max_grefs += INDIRECT_GREFS(max_grefs);
 
-	/*
-	 * We have to reserve 'max_grefs' grants because persistent
-	 * grants are shared by all rings.
-	 */
-	if (max_grefs > 0)
-		if (gnttab_alloc_grant_references(max_grefs, &setup.gref_head) < 0) {
+	/* Check if we have enough persistent grants to allocate a requests */
+	if (rinfo->persistent_gnts_c < max_grefs) {
+		new_persistent_gnts = true;
+
+		if (gnttab_alloc_grant_references(
+		    max_grefs - rinfo->persistent_gnts_c,
+		    &setup.gref_head) < 0) {
 			gnttab_request_free_callback(
 				&rinfo->callback,
 				blkif_restart_queue_callback,
 				rinfo,
-				max_grefs);
+				max_grefs - rinfo->persistent_gnts_c);
 			return 1;
 		}
+	}
 
 	/* Fill out a communications ring structure. */
 	id = blkif_ring_get_request(rinfo, req, &ring_req);
@@ -832,7 +835,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 	if (unlikely(require_extra_req))
 		rinfo->shadow[extra_id].req = *extra_ring_req;
 
-	if (max_grefs > 0)
+	if (new_persistent_gnts)
 		gnttab_free_grant_references(setup.gref_head);
 
 	return 0;
@@ -906,8 +909,8 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_IOERR;
 
 out_busy:
-	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	blk_mq_stop_hw_queue(hctx);
+	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	return BLK_STS_RESOURCE;
 }
 
@@ -1616,7 +1619,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				blkif_req(req)->error = -EOPNOTSUPP;
+				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
 			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {

drivers/lightnvm/pblk-rb.c

@@ -657,7 +657,7 @@ unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
  * be directed to disk.
  */
 int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
-			struct ppa_addr ppa, int bio_iter)
+			struct ppa_addr ppa, int bio_iter, bool advanced_bio)
 {
 	struct pblk *pblk = container_of(rb, struct pblk, rwb);
 	struct pblk_rb_entry *entry;
@@ -694,7 +694,7 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 	 * filled with data from the cache). If part of the data resides on the
 	 * media, we will read later on
 	 */
-	if (unlikely(!bio->bi_iter.bi_idx))
+	if (unlikely(!advanced_bio))
 		bio_advance(bio, bio_iter * PBLK_EXPOSED_PAGE_SIZE);
 
 	data = bio_data(bio);

drivers/lightnvm/pblk-read.c

@@ -26,15 +26,16 @@
  */
 static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 				sector_t lba, struct ppa_addr ppa,
-				int bio_iter)
+				int bio_iter, bool advanced_bio)
 {
 #ifdef CONFIG_NVM_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(pblk_ppa_empty(ppa));
 	BUG_ON(!pblk_addr_in_cache(ppa));
 #endif
 
-	return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa, bio_iter);
+	return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa,
+						bio_iter, advanced_bio);
 }
 
 static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -44,7 +45,7 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
 	sector_t blba = pblk_get_lba(bio);
 	int nr_secs = rqd->nr_ppas;
-	int advanced_bio = 0;
+	bool advanced_bio = false;
 	int i, j = 0;
 
 	/* logic error: lba out-of-bounds. Ignore read request */
@@ -62,19 +63,26 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 retry:
 		if (pblk_ppa_empty(p)) {
 			WARN_ON(test_and_set_bit(i, read_bitmap));
-			continue;
+
+			if (unlikely(!advanced_bio)) {
+				bio_advance(bio, (i) * PBLK_EXPOSED_PAGE_SIZE);
+				advanced_bio = true;
+			}
+
+			goto next;
 		}
 
 		/* Try to read from write buffer. The address is later checked
 		 * on the write buffer to prevent retrieving overwritten data.
 		 */
 		if (pblk_addr_in_cache(p)) {
-			if (!pblk_read_from_cache(pblk, bio, lba, p, i)) {
+			if (!pblk_read_from_cache(pblk, bio, lba, p, i,
+								advanced_bio)) {
 				pblk_lookup_l2p_seq(pblk, &p, lba, 1);
 				goto retry;
 			}
 			WARN_ON(test_and_set_bit(i, read_bitmap));
-			advanced_bio = 1;
+			advanced_bio = true;
 #ifdef CONFIG_NVM_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
 #endif
@@ -83,6 +91,7 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
 			rqd->ppa_list[j++] = p;
 		}
 
+next:
 		if (advanced_bio)
 			bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
 	}
@@ -282,7 +291,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
 	 * write buffer to prevent retrieving overwritten data.
 	 */
 	if (pblk_addr_in_cache(ppa)) {
-		if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0)) {
+		if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0, 1)) {
 			pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
 			goto retry;
 		}

drivers/lightnvm/pblk.h

@@ -670,7 +670,7 @@ unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
 				      struct list_head *list,
 				      unsigned int max);
 int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
-			struct ppa_addr ppa, int bio_iter);
+			struct ppa_addr ppa, int bio_iter, bool advanced_bio);
 unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
 
 unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);

drivers/nvme/host/core.c

@@ -1995,6 +1995,9 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 	int serial_len = sizeof(ctrl->serial);
 	int model_len = sizeof(ctrl->model);
 
+	if (!uuid_is_null(&ns->uuid))
+		return sprintf(buf, "uuid.%pU\n", &ns->uuid);
+
 	if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
 		return sprintf(buf, "eui.%16phN\n", ns->nguid);
 
@@ -2709,7 +2712,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	mutex_lock(&ctrl->namespaces_mutex);
 
 	/* Forcibly unquiesce queues to avoid blocking dispatch */
-	blk_mq_unquiesce_queue(ctrl->admin_q);
+	if (ctrl->admin_q)
+		blk_mq_unquiesce_queue(ctrl->admin_q);
 
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
 		/*