Merge tag 'block-5.8-2020-06-11' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Some followup fixes for this merge window. In particular:

   - Seqcount write missing preemption disable for stats (Ahmed)

   - blktrace fixes (Chaitanya)

   - Redundant initializations (Colin)

   - Various small NVMe fixes (Chaitanya, Christoph, Daniel, Max,
     Niklas, Rikard)

   - loop flag bug regression fix (Martijn)

   - blk-mq tagging fixes (Christoph, Ming)"

* tag 'block-5.8-2020-06-11' of git://git.kernel.dk/linux-block:
  umem: remove redundant initialization of variable ret
  pktcdvd: remove redundant initialization of variable ret
  nvmet: fail outstanding host posted AEN req
  nvme-pci: use simple suspend when a HMB is enabled
  nvme-fc: don't call nvme_cleanup_cmd() for AENs
  nvmet-tcp: constify nvmet_tcp_ops
  nvme-tcp: constify nvme_tcp_mq_ops and nvme_tcp_admin_mq_ops
  nvme: do not call del_gendisk() on a disk that was never added
  blk-mq: fix blk_mq_all_tag_iter
  blk-mq: split out a __blk_mq_get_driver_tag helper
  blktrace: fix endianness for blk_log_remap()
  blktrace: fix endianness in get_pdu_int()
  blktrace: use errno instead of bi_status
  block: nr_sects_write(): Disable preemption on seqcount write
  block: remove the error argument to the block_bio_complete tracepoint
  loop: Fix wrong masking of status flags
  block/bio-integrity: don't free 'buf' if bio_integrity_add_page() failed

block/bio-integrity.c

@@ -281,7 +281,6 @@ bool bio_integrity_prep(struct bio *bio)
 
 		if (ret == 0) {
 			printk(KERN_ERR "could not attach integrity payload\n");
-			kfree(buf);
 			status = BLK_STS_RESOURCE;
 			goto err_end_io;
 		}

block/bio.c

@@ -1434,8 +1434,7 @@ void bio_endio(struct bio *bio)
 	}
 
 	if (bio->bi_disk && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
-		trace_block_bio_complete(bio->bi_disk->queue, bio,
-					 blk_status_to_errno(bio->bi_status));
+		trace_block_bio_complete(bio->bi_disk->queue, bio);
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 	}
 

block/blk-mq-tag.c

@@ -191,6 +191,33 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	return tag + tag_offset;
 }
 
+bool __blk_mq_get_driver_tag(struct request *rq)
+{
+	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
+	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
+	bool shared = blk_mq_tag_busy(rq->mq_hctx);
+	int tag;
+
+	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
+		bt = &rq->mq_hctx->tags->breserved_tags;
+		tag_offset = 0;
+	}
+
+	if (!hctx_may_queue(rq->mq_hctx, bt))
+		return false;
+	tag = __sbitmap_queue_get(bt);
+	if (tag == BLK_MQ_NO_TAG)
+		return false;
+
+	rq->tag = tag + tag_offset;
+	if (shared) {
+		rq->rq_flags |= RQF_MQ_INFLIGHT;
+		atomic_inc(&rq->mq_hctx->nr_active);
+	}
+	rq->mq_hctx->tags->rqs[rq->tag] = rq;
+	return true;
+}
+
 void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 		    unsigned int tag)
 {
@@ -269,6 +296,7 @@ struct bt_tags_iter_data {
 
 #define BT_TAG_ITER_RESERVED		(1 << 0)
 #define BT_TAG_ITER_STARTED		(1 << 1)
+#define BT_TAG_ITER_STATIC_RQS		(1 << 2)
 
 static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 {
@@ -282,8 +310,11 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 
 	/*
 	 * We can hit rq == NULL here, because the tagging functions
-	 * test and set the bit before assining ->rqs[].
+	 * test and set the bit before assigning ->rqs[].
 	 */
+	if (iter_data->flags & BT_TAG_ITER_STATIC_RQS)
+		rq = tags->static_rqs[bitnr];
+	else
 		rq = tags->rqs[bitnr];
 	if (!rq)
 		return true;
@@ -339,11 +370,13 @@ static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags,
  *		indicates whether or not @rq is a reserved request. Return
  *		true to continue iterating tags, false to stop.
  * @priv:	Will be passed as second argument to @fn.
+ *
+ * Caller has to pass the tag map from which requests are allocated.
  */
 void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
 		void *priv)
 {
-	return __blk_mq_all_tag_iter(tags, fn, priv, 0);
+	return __blk_mq_all_tag_iter(tags, fn, priv, BT_TAG_ITER_STATIC_RQS);
 }
 
 /**

block/blk-mq-tag.h

@@ -51,6 +51,14 @@ enum {
 	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
 };
 
+bool __blk_mq_get_driver_tag(struct request *rq);
+static inline bool blk_mq_get_driver_tag(struct request *rq)
+{
+	if (rq->tag != BLK_MQ_NO_TAG)
+		return true;
+	return __blk_mq_get_driver_tag(rq);
+}
+
 extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
 extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 

block/blk-mq.c

@@ -1052,35 +1052,6 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq)
-{
-	struct blk_mq_alloc_data data = {
-		.q = rq->q,
-		.hctx = rq->mq_hctx,
-		.flags = BLK_MQ_REQ_NOWAIT,
-		.cmd_flags = rq->cmd_flags,
-	};
-	bool shared;
-
-	if (rq->tag != BLK_MQ_NO_TAG)
-		return true;
-
-	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
-		data.flags |= BLK_MQ_REQ_RESERVED;
-
-	shared = blk_mq_tag_busy(data.hctx);
-	rq->tag = blk_mq_get_tag(&data);
-	if (rq->tag >= 0) {
-		if (shared) {
-			rq->rq_flags |= RQF_MQ_INFLIGHT;
-			atomic_inc(&data.hctx->nr_active);
-		}
-		data.hctx->tags->rqs[rq->tag] = rq;
-	}
-
-	return rq->tag != BLK_MQ_NO_TAG;
-}
-
 static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 				int flags, void *key)
 {

block/blk-mq.h

@@ -44,7 +44,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 				bool kick_requeue_list);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
 

block/blk.h

@@ -420,9 +420,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	preempt_disable();
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
+	preempt_enable();
 #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	preempt_disable();
 	part->nr_sects = size;

drivers/block/loop.c

@@ -1390,7 +1390,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		goto out_unfreeze;
 
 	/* Mask out flags that can't be set using LOOP_SET_STATUS. */
-	lo->lo_flags &= ~LOOP_SET_STATUS_SETTABLE_FLAGS;
+	lo->lo_flags &= LOOP_SET_STATUS_SETTABLE_FLAGS;
 	/* For those flags, use the previous values instead */
 	lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS;
 	/* For flags that can't be cleared, use previous values too */

drivers/block/pktcdvd.c

@@ -1613,7 +1613,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 	disc_information di;
 	track_information ti;
 	__u32 last_track;
-	int ret = -1;
+	int ret;
 
 	ret = pkt_get_disc_info(pd, &di);
 	if (ret)

drivers/block/umem.c

@@ -784,7 +784,7 @@ static const struct block_device_operations mm_fops = {
 
 static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
-	int ret = -ENODEV;
+	int ret;
 	struct cardinfo *card = &cards[num_cards];
 	unsigned char	mem_present;
 	unsigned char	batt_status;

drivers/nvme/host/core.c

@@ -3669,7 +3669,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	ns->disk = disk;
 
 	if (__nvme_revalidate_disk(disk, id))
-		goto out_free_disk;
+		goto out_put_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
 		ret = nvme_nvm_register(ns, disk_name, node);
@@ -3696,8 +3696,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	/* prevent double queue cleanup */
 	ns->disk->queue = NULL;
 	put_disk(ns->disk);
- out_free_disk:
-	del_gendisk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);

drivers/nvme/host/fc.c

@@ -2634,10 +2634,11 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 		opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
 		__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 
-		if (!(op->flags & FCOP_FLAGS_AEN))
+		if (!(op->flags & FCOP_FLAGS_AEN)) {
 			nvme_fc_unmap_data(ctrl, op->rq, op);
-
 			nvme_cleanup_cmd(op->rq);
+		}
+
 		nvme_fc_ctrl_put(ctrl);
 
 		if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE &&

drivers/nvme/host/nvme.h

@@ -599,8 +599,7 @@ static inline void nvme_trace_bio_complete(struct request *req,
 	struct nvme_ns *ns = req->q->queuedata;
 
 	if (req->cmd_flags & REQ_NVME_MPATH)
-		trace_block_bio_complete(ns->head->disk->queue,
-					 req->bio, status);
+		trace_block_bio_complete(ns->head->disk->queue, req->bio);
 }
 
 extern struct device_attribute dev_attr_ana_grpid;

drivers/nvme/host/pci.c

@@ -2950,9 +2950,15 @@ static int nvme_suspend(struct device *dev)
 	 * the PCI bus layer to put it into D3 in order to take the PCIe link
 	 * down, so as to allow the platform to achieve its minimum low-power
 	 * state (which may not be possible if the link is up).
+	 *
+	 * If a host memory buffer is enabled, shut down the device as the NVMe
+	 * specification allows the device to access the host memory buffer in
+	 * host DRAM from all power states, but hosts will fail access to DRAM
+	 * during S3.
 	 */
 	if (pm_suspend_via_firmware() || !ctrl->npss ||
 	    !pcie_aspm_enabled(pdev) ||
+	    ndev->nr_host_mem_descs ||
 	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
 		return nvme_disable_prepare_reset(ndev, true);
 

drivers/nvme/host/tcp.c

@@ -131,8 +131,8 @@ struct nvme_tcp_ctrl {
 static LIST_HEAD(nvme_tcp_ctrl_list);
 static DEFINE_MUTEX(nvme_tcp_ctrl_mutex);
 static struct workqueue_struct *nvme_tcp_wq;
-static struct blk_mq_ops nvme_tcp_mq_ops;
-static struct blk_mq_ops nvme_tcp_admin_mq_ops;
+static const struct blk_mq_ops nvme_tcp_mq_ops;
+static const struct blk_mq_ops nvme_tcp_admin_mq_ops;
 static int nvme_tcp_try_send(struct nvme_tcp_queue *queue);
 
 static inline struct nvme_tcp_ctrl *to_tcp_ctrl(struct nvme_ctrl *ctrl)
@@ -2301,7 +2301,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
 	return queue->nr_cqe;
 }
 
-static struct blk_mq_ops nvme_tcp_mq_ops = {
+static const struct blk_mq_ops nvme_tcp_mq_ops = {
 	.queue_rq	= nvme_tcp_queue_rq,
 	.complete	= nvme_complete_rq,
 	.init_request	= nvme_tcp_init_request,
@@ -2312,7 +2312,7 @@ static struct blk_mq_ops nvme_tcp_mq_ops = {
 	.poll		= nvme_tcp_poll,
 };
 
-static struct blk_mq_ops nvme_tcp_admin_mq_ops = {
+static const struct blk_mq_ops nvme_tcp_admin_mq_ops = {
 	.queue_rq	= nvme_tcp_queue_rq,
 	.complete	= nvme_complete_rq,
 	.init_request	= nvme_tcp_init_request,

drivers/nvme/target/core.c

@@ -129,7 +129,22 @@ static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
 	return aen->event_type | (aen->event_info << 8) | (aen->log_page << 16);
 }
 
-static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status)
+static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl)
+{
+	u16 status = NVME_SC_INTERNAL | NVME_SC_DNR;
+	struct nvmet_req *req;
+
+	mutex_lock(&ctrl->lock);
+	while (ctrl->nr_async_event_cmds) {
+		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
+		mutex_unlock(&ctrl->lock);
+		nvmet_req_complete(req, status);
+		mutex_lock(&ctrl->lock);
+	}
+	mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_async_events_process(struct nvmet_ctrl *ctrl)
 {
 	struct nvmet_async_event *aen;
 	struct nvmet_req *req;
@@ -139,7 +154,6 @@ static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status)
 		aen = list_first_entry(&ctrl->async_events,
 				       struct nvmet_async_event, entry);
 		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
-		if (status == 0)
 		nvmet_set_result(req, nvmet_async_event_result(aen));
 
 		list_del(&aen->entry);
@@ -147,7 +161,7 @@ static void nvmet_async_events_process(struct nvmet_ctrl *ctrl, u16 status)
 
 		mutex_unlock(&ctrl->lock);
 		trace_nvmet_async_event(ctrl, req->cqe->result.u32);
-		nvmet_req_complete(req, status);
+		nvmet_req_complete(req, 0);
 		mutex_lock(&ctrl->lock);
 	}
 	mutex_unlock(&ctrl->lock);
@@ -170,7 +184,7 @@ static void nvmet_async_event_work(struct work_struct *work)
 	struct nvmet_ctrl *ctrl =
 		container_of(work, struct nvmet_ctrl, async_event_work);
 
-	nvmet_async_events_process(ctrl, 0);
+	nvmet_async_events_process(ctrl);
 }
 
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
@@ -779,7 +793,6 @@ static void nvmet_confirm_sq(struct percpu_ref *ref)
 
 void nvmet_sq_destroy(struct nvmet_sq *sq)
 {
-	u16 status = NVME_SC_INTERNAL | NVME_SC_DNR;
 	struct nvmet_ctrl *ctrl = sq->ctrl;
 
 	/*
@@ -787,7 +800,7 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 	 * queue doesn't have outstanding requests on it.
 	 */
 	if (ctrl && ctrl->sqs && ctrl->sqs[0] == sq)
-		nvmet_async_events_process(ctrl, status);
+		nvmet_async_events_failall(ctrl);
 	percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq);
 	wait_for_completion(&sq->confirm_done);
 	wait_for_completion(&sq->free_done);

drivers/nvme/target/tcp.c

@@ -153,7 +153,7 @@ static LIST_HEAD(nvmet_tcp_queue_list);
 static DEFINE_MUTEX(nvmet_tcp_queue_mutex);
 
 static struct workqueue_struct *nvmet_tcp_wq;
-static struct nvmet_fabrics_ops nvmet_tcp_ops;
+static const struct nvmet_fabrics_ops nvmet_tcp_ops;
 static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c);
 static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd);
 
@@ -1713,7 +1713,7 @@ static void nvmet_tcp_disc_port_addr(struct nvmet_req *req,
 	}
 }
 
-static struct nvmet_fabrics_ops nvmet_tcp_ops = {
+static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_TCP,
 	.msdbd			= 1,

include/trace/events/block.h

@@ -261,9 +261,9 @@ TRACE_EVENT(block_bio_bounce,
  */
 TRACE_EVENT(block_bio_complete,
 
-	TP_PROTO(struct request_queue *q, struct bio *bio, int error),
+	TP_PROTO(struct request_queue *q, struct bio *bio),
 
-	TP_ARGS(q, bio, error),
+	TP_ARGS(q, bio),
 
 	TP_STRUCT__entry(
 		__field( dev_t,		dev		)
@@ -277,7 +277,7 @@ TRACE_EVENT(block_bio_complete,
 		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		__entry->error		= error;
+		__entry->error		= blk_status_to_errno(bio->bi_status);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 	),
 

kernel/trace/blktrace.c

@@ -885,10 +885,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 }
 
 static void blk_add_trace_bio_complete(void *ignore,
-				       struct request_queue *q, struct bio *bio,
-				       int error)
+				       struct request_queue *q, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
+	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE,
+			  blk_status_to_errno(bio->bi_status));
 }
 
 static void blk_add_trace_bio_backmerge(void *ignore,
@@ -995,8 +995,10 @@ static void blk_add_trace_split(void *ignore,
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
-				&rpdu, blk_trace_bio_get_cgid(q, bio));
+				BLK_TA_SPLIT,
+				blk_status_to_errno(bio->bi_status),
+				sizeof(rpdu), &rpdu,
+				blk_trace_bio_get_cgid(q, bio));
 	}
 	rcu_read_unlock();
 }
@@ -1033,7 +1035,8 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
+			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -1253,21 +1256,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
 
 static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent, has_cg);
+	const __be64 *val = pdu_start(ent, has_cg);
 	return be64_to_cpu(*val);
 }
 
-static void get_pdu_remap(const struct trace_entry *ent,
-			  struct blk_io_trace_remap *r, bool has_cg)
-{
-	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
-	__u64 sector_from = __r->sector_from;
-
-	r->device_from = be32_to_cpu(__r->device_from);
-	r->device_to   = be32_to_cpu(__r->device_to);
-	r->sector_from = be64_to_cpu(sector_from);
-}
-
 typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
 	bool has_cg);
 
@@ -1407,13 +1399,13 @@ static void blk_log_with_error(struct trace_seq *s,
 
 static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
-	struct blk_io_trace_remap r = { .device_from = 0, };
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 
-	get_pdu_remap(ent, &r, has_cg);
 	trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
 			 t_sector(ent), t_sec(ent),
-			 MAJOR(r.device_from), MINOR(r.device_from),
-			 (unsigned long long)r.sector_from);
+			 MAJOR(be32_to_cpu(__r->device_from)),
+			 MINOR(be32_to_cpu(__r->device_from)),
+			 be64_to_cpu(__r->sector_from));
 }
 
 static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)