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

Pull block fixes from Jens Axboe:

 - Two sets of NVMe pull requests from Christoph:
      - Fixes for the Fibre Channel host/target to fix spec compliance
      - Allow a zero keep alive timeout
      - Make the debug printk for broken SGLs work better
      - Fix queue zeroing during initialization
      - Set of RDMA and FC fixes
      - Target div-by-zero fix

 - bsg double-free fix.

 - ndb unknown ioctl fix from Josef.

 - Buffered vs O_DIRECT page cache inconsistency fix. Has been floating
   around for a long time, well reviewed. From Lukas.

 - brd overflow fix from Mikulas.

 - Fix for a loop regression in this merge window, where using a union
   for two members of the loop_cmd turned out to be a really bad idea.
   From Omar.

 - Fix for an iostat regression fix in this series, using the wrong API
   to get at the block queue. From Shaohua.

 - Fix for a potential blktrace delection deadlock. From Waiman.

* 'for-linus' of git://git.kernel.dk/linux-block: (30 commits)
  nvme-fcloop: fix port deletes and callbacks
  nvmet-fc: sync header templates with comments
  nvmet-fc: ensure target queue id within range.
  nvmet-fc: on port remove call put outside lock
  nvme-rdma: don't fully stop the controller in error recovery
  nvme-rdma: give up reconnect if state change fails
  nvme-core: Use nvme_wq to queue async events and fw activation
  nvme: fix sqhd reference when admin queue connect fails
  block: fix a crash caused by wrong API
  fs: Fix page cache inconsistency when mixing buffered and AIO DIO
  nvmet: implement valid sqhd values in completions
  nvme-fabrics: Allow 0 as KATO value
  nvme: allow timed-out ios to retry
  nvme: stop aer posting if controller state not live
  nvme-pci: Print invalid SGL only once
  nvme-pci: initialize queue memory before interrupts
  nvmet-fc: fix failing max io queue connections
  nvme-fc: use transport-specific sgl format
  nvme: add transport SGL definitions
  nvme.h: remove FC transport-specific error values
  ...

block/blk-core.c

@@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_init(&q->blk_trace_mutex);
+#endif
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 

block/bsg-lib.c

@@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req)
 failjob_rls_rqst_payload:
 	kfree(job->request_payload.sg_list);
 failjob_rls_job:
-	kfree(job);
 	return -ENOMEM;
 }
 

block/partition-generic.c

@@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct request_queue *q = part_to_disk(p)->queue;
 	unsigned int inflight[2];
 	int cpu;
 

drivers/block/brd.c

@@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff,
 
 	if (!brd)
 		return -ENODEV;
-	page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512);
+	page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);

drivers/block/loop.h

@@ -67,10 +67,8 @@ struct loop_device {
 struct loop_cmd {
 	struct kthread_work work;
 	struct request *rq;
-	union {
-		bool use_aio; /* use AIO interface to handle I/O */
-		atomic_t ref; /* only for aio */
-	};
+	bool use_aio; /* use AIO interface to handle I/O */
+	atomic_t ref; /* only for aio */
 	long ret;
 	struct kiocb iocb;
 	struct bio_vec *bvec;

drivers/block/nbd.c

@@ -1194,6 +1194,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/* The block layer will pass back some non-nbd ioctls in case we have
+	 * special handling for them, but we don't so just return an error.
+	 */
+	if (_IOC_TYPE(cmd) != 0xab)
+		return -EINVAL;
+
 	mutex_lock(&nbd->config_lock);
 
 	/* Don't allow ioctl operations on a nbd device that was created with

drivers/nvme/host/core.c

@@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req)
 		return false;
 	if (nvme_req(req)->status & NVME_SC_DNR)
 		return false;
-	if (jiffies - req->start_time >= req->timeout)
-		return false;
 	if (nvme_req(req)->retries >= nvme_max_retries)
 		return false;
 	return true;
@@ -2590,7 +2588,7 @@ static void nvme_async_event_work(struct work_struct *work)
 		container_of(work, struct nvme_ctrl, async_event_work);
 
 	spin_lock_irq(&ctrl->lock);
-	while (ctrl->event_limit > 0) {
+	while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
 		int aer_idx = --ctrl->event_limit;
 
 		spin_unlock_irq(&ctrl->lock);
@@ -2677,7 +2675,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		/*FALLTHRU*/
 	case NVME_SC_ABORT_REQ:
 		++ctrl->event_limit;
-		queue_work(nvme_wq, &ctrl->async_event_work);
+		if (ctrl->state == NVME_CTRL_LIVE)
+			queue_work(nvme_wq, &ctrl->async_event_work);
 		break;
 	default:
 		break;
@@ -2692,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		schedule_work(&ctrl->fw_act_work);
+		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);

drivers/nvme/host/fabrics.c

@@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
 	opts->nr_io_queues = num_online_cpus();
 	opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+	opts->kato = NVME_DEFAULT_KATO;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 				goto out;
 			}
 
-			if (opts->discovery_nqn) {
-				pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
-				ret = -EINVAL;
-				goto out;
-			}
-
 			if (token < 0) {
 				pr_err("Invalid keep_alive_tmo %d\n", token);
 				ret = -EINVAL;
 				goto out;
-			} else if (token == 0) {
+			} else if (token == 0 && !opts->discovery_nqn) {
 				/* Allowed for debug */
 				pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
 			}
 			opts->kato = token;
+
+			if (opts->discovery_nqn && opts->kato) {
+				pr_err("Discovery controllers cannot accept KATO != 0\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
 			break;
 		case NVMF_OPT_CTRL_LOSS_TMO:
 			if (match_int(args, &token)) {
@@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	uuid_copy(&opts->host->id, &hostid);
 
 out:
-	if (!opts->discovery_nqn && !opts->kato)
-		opts->kato = NVME_DEFAULT_KATO;
 	kfree(options);
 	return ret;
 }

drivers/nvme/host/fc.c

@@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 	if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
 		status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
 	else if (freq->status)
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 
 	/*
 	 * For the linux implementation, if we have an unsuccesful
@@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 		 */
 		if (freq->transferred_length !=
 			be32_to_cpu(op->cmd_iu.data_len)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result.u64 = 0;
@@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 					freq->transferred_length ||
 			     op->rsp_iu.status_code ||
 			     sqe->common.command_id != cqe->command_id)) {
-			status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+			status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 			goto done;
 		}
 		result = cqe->result;
@@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 		break;
 
 	default:
-		status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_INTERNAL << 1);
 		goto done;
 	}
 
@@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	 * as well as those by FC-NVME spec.
 	 */
 	WARN_ON_ONCE(sqe->common.metadata);
-	WARN_ON_ONCE(sqe->common.dptr.prp1);
-	WARN_ON_ONCE(sqe->common.dptr.prp2);
 	sqe->common.flags |= NVME_CMD_SGL_METABUF;
 
 	/*
-	 * format SQE DPTR field per FC-NVME rules
-	 *    type=data block descr; subtype=offset;
-	 *    offset is currently 0.
+	 * format SQE DPTR field per FC-NVME rules:
+	 *    type=0x5     Transport SGL Data Block Descriptor
+	 *    subtype=0xA  Transport-specific value
+	 *    address=0
+	 *    length=length of the data series
 	 */
-	sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET;
+	sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) |
+					NVME_SGL_FMT_TRANSPORT_A;
 	sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
 	sqe->rw.dptr.sgl.addr = 0;
 

drivers/nvme/host/pci.c

@@ -24,6 +24,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/once.h>
 #include <linux/pci.h>
 #include <linux/poison.h>
 #include <linux/t10-pi.h>
@@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
 }
 #endif
 
+static void nvme_print_sgl(struct scatterlist *sgl, int nents)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		dma_addr_t phys = sg_phys(sg);
+		pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
+			"dma_address:%pad dma_length:%d\n",
+			i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
+			sg_dma_len(sg));
+	}
+}
+
 static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 	return BLK_STS_OK;
 
  bad_sgl:
-	if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n",
-				blk_rq_payload_bytes(req), iod->nents)) {
-		for_each_sg(iod->sg, sg, iod->nents, i) {
-			dma_addr_t phys = sg_phys(sg);
-			pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
-			       "dma_address:%pad dma_length:%d\n", i, &phys,
-					sg->offset, sg->length,
-					&sg_dma_address(sg),
-					sg_dma_len(sg));
-		}
-	}
+	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+			"Invalid SGL for payload:%d nents:%d\n",
+			blk_rq_payload_bytes(req), iod->nents);
 	return BLK_STS_IOERR;
-
 }
 
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@@ -1313,11 +1319,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_cq;
 
+	nvme_init_queue(nvmeq, qid);
 	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
-	nvme_init_queue(nvmeq, qid);
 	return result;
 
  release_sq:
@@ -1464,6 +1470,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 		return result;
 
 	nvmeq->cq_vector = 0;
+	nvme_init_queue(nvmeq, 0);
 	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
@@ -2156,7 +2163,6 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
-	nvme_init_queue(dev->queues[0], 0);
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
 		goto out;

drivers/nvme/host/rdma.c

@@ -942,7 +942,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	}
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
+	if (!changed) {
+		/* state change failure is ok if we're in DELETING state */
+		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+		return;
+	}
+
 	ctrl->ctrl.nr_reconnects = 0;
 
 	nvme_start_ctrl(&ctrl->ctrl);
@@ -962,7 +967,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	struct nvme_rdma_ctrl *ctrl = container_of(work,
 			struct nvme_rdma_ctrl, err_work);
 
-	nvme_stop_ctrl(&ctrl->ctrl);
+	nvme_stop_keep_alive(&ctrl->ctrl);
 
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);

drivers/nvme/target/core.c

@@ -390,10 +390,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 	if (status)
 		nvmet_set_status(req, status);
 
-	/* XXX: need to fill in something useful for sq_head */
-	req->rsp->sq_head = 0;
-	if (likely(req->sq)) /* may happen during early failure */
-		req->rsp->sq_id = cpu_to_le16(req->sq->qid);
+	if (req->sq->size)
+		req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size;
+	req->rsp->sq_head = cpu_to_le16(req->sq->sqhd);
+	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
 	req->rsp->command_id = req->cmd->common.command_id;
 
 	if (req->ns)
@@ -420,6 +420,7 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq,
 void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
 		u16 qid, u16 size)
 {
+	sq->sqhd = 0;
 	sq->qid = qid;
 	sq->size = size;
 

drivers/nvme/target/fabrics-cmd.c

@@ -109,9 +109,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 		pr_warn("queue already connected!\n");
 		return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
 	}
+	if (!sqsize) {
+		pr_warn("queue size zero!\n");
+		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+	}
 
-	nvmet_cq_setup(ctrl, req->cq, qid, sqsize);
-	nvmet_sq_setup(ctrl, req->sq, qid, sqsize);
+	/* note: convert queue size from 0's-based value to 1's-based value */
+	nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
+	nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
 	return 0;
 }
 

drivers/nvme/target/fc.c

@@ -148,7 +148,7 @@ struct nvmet_fc_tgt_assoc {
 	u32				a_id;
 	struct nvmet_fc_tgtport		*tgtport;
 	struct list_head		a_list;
-	struct nvmet_fc_tgt_queue	*queues[NVMET_NR_QUEUES];
+	struct nvmet_fc_tgt_queue	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 };
 
@@ -608,7 +608,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	unsigned long flags;
 	int ret;
 
-	if (qid >= NVMET_NR_QUEUES)
+	if (qid > NVMET_NR_QUEUES)
 		return NULL;
 
 	queue = kzalloc((sizeof(*queue) +
@@ -783,6 +783,9 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
 	u16 qid = nvmet_fc_getqueueid(connection_id);
 	unsigned long flags;
 
+	if (qid > NVMET_NR_QUEUES)
+		return NULL;
+
 	spin_lock_irqsave(&tgtport->lock, flags);
 	list_for_each_entry(assoc, &tgtport->assoc_list, a_list) {
 		if (association_id == assoc->association_id) {
@@ -888,7 +891,7 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	int i;
 
 	spin_lock_irqsave(&tgtport->lock, flags);
-	for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) {
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
 		queue = assoc->queues[i];
 		if (queue) {
 			if (!nvmet_fc_tgt_q_get(queue))
@@ -1910,8 +1913,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 			spin_lock_irqsave(&fod->flock, flags);
 			fod->writedataactive = false;
 			spin_unlock_irqrestore(&fod->flock, flags);
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 		} else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
 			fcpreq->fcp_error = ret;
 			fcpreq->transferred_length = 0;
@@ -1929,8 +1931,7 @@ __nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort)
 	/* if in the middle of an io and we need to tear down */
 	if (abort) {
 		if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return true;
 		}
 
@@ -1968,8 +1969,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 			fod->abort = true;
 			spin_unlock(&fod->flock);
 
-			nvmet_req_complete(&fod->req,
-					NVME_SC_FC_TRANSPORT_ERROR);
+			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;
 		}
 
@@ -2533,13 +2533,17 @@ nvmet_fc_remove_port(struct nvmet_port *port)
 {
 	struct nvmet_fc_tgtport *tgtport = port->priv;
 	unsigned long flags;
+	bool matched = false;
 
 	spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
 	if (tgtport->port == port) {
-		nvmet_fc_tgtport_put(tgtport);
+		matched = true;
 		tgtport->port = NULL;
 	}
 	spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
+
+	if (matched)
+		nvmet_fc_tgtport_put(tgtport);
 }
 
 static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {

drivers/nvme/target/fcloop.c

@@ -224,8 +224,6 @@ struct fcloop_nport {
 	struct fcloop_lport *lport;
 	struct list_head nport_list;
 	struct kref ref;
-	struct completion rport_unreg_done;
-	struct completion tport_unreg_done;
 	u64 node_name;
 	u64 port_name;
 	u32 port_role;
@@ -576,7 +574,7 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 	tfcp_req->aborted = true;
 	spin_unlock(&tfcp_req->reqlock);
 
-	tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+	tfcp_req->status = NVME_SC_INTERNAL;
 
 	/*
 	 * nothing more to do. If io wasn't active, the transport should
@@ -630,6 +628,32 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 	schedule_work(&inireq->iniwork);
 }
 
+static void
+fcloop_nport_free(struct kref *ref)
+{
+	struct fcloop_nport *nport =
+		container_of(ref, struct fcloop_nport, ref);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fcloop_lock, flags);
+	list_del(&nport->nport_list);
+	spin_unlock_irqrestore(&fcloop_lock, flags);
+
+	kfree(nport);
+}
+
+static void
+fcloop_nport_put(struct fcloop_nport *nport)
+{
+	kref_put(&nport->ref, fcloop_nport_free);
+}
+
+static int
+fcloop_nport_get(struct fcloop_nport *nport)
+{
+	return kref_get_unless_zero(&nport->ref);
+}
+
 static void
 fcloop_localport_delete(struct nvme_fc_local_port *localport)
 {
@@ -644,8 +668,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport)
 {
 	struct fcloop_rport *rport = remoteport->private;
 
-	/* release any threads waiting for the unreg to complete */
-	complete(&rport->nport->rport_unreg_done);
+	fcloop_nport_put(rport->nport);
 }
 
 static void
@@ -653,8 +676,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport)
 {
 	struct fcloop_tport *tport = targetport->private;
 
-	/* release any threads waiting for the unreg to complete */
-	complete(&tport->nport->tport_unreg_done);
+	fcloop_nport_put(tport->nport);
 }
 
 #define	FCLOOP_HW_QUEUES		4
@@ -722,6 +744,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
 		goto out_free_opts;
 	}
 
+	memset(&pinfo, 0, sizeof(pinfo));
 	pinfo.node_name = opts->wwnn;
 	pinfo.port_name = opts->wwpn;
 	pinfo.port_role = opts->roles;
@@ -804,32 +827,6 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr,
 	return ret ? ret : count;
 }
 
-static void
-fcloop_nport_free(struct kref *ref)
-{
-	struct fcloop_nport *nport =
-		container_of(ref, struct fcloop_nport, ref);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fcloop_lock, flags);
-	list_del(&nport->nport_list);
-	spin_unlock_irqrestore(&fcloop_lock, flags);
-
-	kfree(nport);
-}
-
-static void
-fcloop_nport_put(struct fcloop_nport *nport)
-{
-	kref_put(&nport->ref, fcloop_nport_free);
-}
-
-static int
-fcloop_nport_get(struct fcloop_nport *nport)
-{
-	return kref_get_unless_zero(&nport->ref);
-}
-
 static struct fcloop_nport *
 fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
 {
@@ -938,6 +935,7 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr,
 	if (!nport)
 		return -EIO;
 
+	memset(&pinfo, 0, sizeof(pinfo));
 	pinfo.node_name = nport->node_name;
 	pinfo.port_name = nport->port_name;
 	pinfo.port_role = nport->port_role;
@@ -979,24 +977,12 @@ __unlink_remote_port(struct fcloop_nport *nport)
 }
 
 static int
-__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
+__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
 {
-	int ret;
-
 	if (!rport)
 		return -EALREADY;
 
-	init_completion(&nport->rport_unreg_done);
-
-	ret = nvme_fc_unregister_remoteport(rport->remoteport);
-	if (ret)
-		return ret;
-
-	wait_for_completion(&nport->rport_unreg_done);
-
-	fcloop_nport_put(nport);
-
-	return ret;
+	return nvme_fc_unregister_remoteport(rport->remoteport);
 }
 
 static ssize_t
@@ -1029,7 +1015,7 @@ fcloop_delete_remote_port(struct device *dev, struct device_attribute *attr,
 	if (!nport)
 		return -ENOENT;
 
-	ret = __wait_remoteport_unreg(nport, rport);
+	ret = __remoteport_unreg(nport, rport);
 
 	return ret ? ret : count;
 }
@@ -1086,24 +1072,12 @@ __unlink_target_port(struct fcloop_nport *nport)
 }
 
 static int
-__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
+__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
 {
-	int ret;
-
 	if (!tport)
 		return -EALREADY;
 
-	init_completion(&nport->tport_unreg_done);
-
-	ret = nvmet_fc_unregister_targetport(tport->targetport);
-	if (ret)
-		return ret;
-
-	wait_for_completion(&nport->tport_unreg_done);
-
-	fcloop_nport_put(nport);
-
-	return ret;
+	return nvmet_fc_unregister_targetport(tport->targetport);
 }
 
 static ssize_t
@@ -1136,7 +1110,7 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr,
 	if (!nport)
 		return -ENOENT;
 
-	ret = __wait_targetport_unreg(nport, tport);
+	ret = __targetport_unreg(nport, tport);
 
 	return ret ? ret : count;
 }
@@ -1223,11 +1197,11 @@ static void __exit fcloop_exit(void)
 
 		spin_unlock_irqrestore(&fcloop_lock, flags);
 
-		ret = __wait_targetport_unreg(nport, tport);
+		ret = __targetport_unreg(nport, tport);
 		if (ret)
 			pr_warn("%s: Failed deleting target port\n", __func__);
 
-		ret = __wait_remoteport_unreg(nport, rport);
+		ret = __remoteport_unreg(nport, rport);
 		if (ret)
 			pr_warn("%s: Failed deleting remote port\n", __func__);
 

drivers/nvme/target/nvmet.h

@@ -74,6 +74,7 @@ struct nvmet_sq {
 	struct percpu_ref	ref;
 	u16			qid;
 	u16			size;
+	u16			sqhd;
 	struct completion	free_done;
 	struct completion	confirm_done;
 };

drivers/scsi/lpfc/lpfc_nvme.c

@@ -884,7 +884,7 @@ out_err:
 					 wcqe->total_data_placed);
 			nCmd->transferred_length = 0;
 			nCmd->rcv_rsplen = 0;
-			nCmd->status = NVME_SC_FC_TRANSPORT_ERROR;
+			nCmd->status = NVME_SC_INTERNAL;
 		}
 	}
 

drivers/scsi/qla2xxx/qla_nvme.c

@@ -180,7 +180,7 @@ static void qla_nvme_sp_done(void *ptr, int res)
 		goto rel;
 
 	if (unlikely(res == QLA_FUNCTION_FAILED))
-		fd->status = NVME_SC_FC_TRANSPORT_ERROR;
+		fd->status = NVME_SC_INTERNAL;
 	else
 		fd->status = 0;
 

fs/direct-io.c

@@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 {
 	loff_t offset = dio->iocb->ki_pos;
 	ssize_t transferred = 0;
+	int err;
 
 	/*
 	 * AIO submission can race with bio completion to get here while
@@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 	if (ret == 0)
 		ret = transferred;
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 */
+	if (ret > 0 && dio->op == REQ_OP_WRITE &&
+	    dio->inode->i_mapping->nrpages) {
+		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
+					offset >> PAGE_SHIFT,
+					(offset + ret - 1) >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
+	}
+
 	if (dio->end_io) {
-		int err;
 
 		// XXX: ki_pos??
 		err = dio->end_io(dio->iocb, offset, ret, dio->private);
@@ -304,6 +319,7 @@ static void dio_bio_end_aio(struct bio *bio)
 	struct dio *dio = bio->bi_private;
 	unsigned long remaining;
 	unsigned long flags;
+	bool defer_completion = false;
 
 	/* cleanup the bio */
 	dio_bio_complete(dio, bio);
@@ -315,7 +331,19 @@ static void dio_bio_end_aio(struct bio *bio)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
 	if (remaining == 0) {
-		if (dio->result && dio->defer_completion) {
+		/*
+		 * Defer completion when defer_completion is set or
+		 * when the inode has pages mapped and this is AIO write.
+		 * We need to invalidate those pages because there is a
+		 * chance they contain stale data in the case buffered IO
+		 * went in between AIO submission and completion into the
+		 * same region.
+		 */
+		if (dio->result)
+			defer_completion = dio->defer_completion ||
+					   (dio->op == REQ_OP_WRITE &&
+					    dio->inode->i_mapping->nrpages);
+		if (defer_completion) {
 			INIT_WORK(&dio->complete_work, dio_aio_complete_work);
 			queue_work(dio->inode->i_sb->s_dio_done_wq,
 				   &dio->complete_work);
@@ -1210,10 +1238,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
 	 * so that we can call ->fsync.
 	 */
-	if (dio->is_async && iov_iter_rw(iter) == WRITE &&
-	    ((iocb->ki_filp->f_flags & O_DSYNC) ||
-	     IS_SYNC(iocb->ki_filp->f_mapping->host))) {
-		retval = dio_set_defer_completion(dio);
+	if (dio->is_async && iov_iter_rw(iter) == WRITE) {
+		retval = 0;
+		if ((iocb->ki_filp->f_flags & O_DSYNC) ||
+		    IS_SYNC(iocb->ki_filp->f_mapping->host))
+			retval = dio_set_defer_completion(dio);
+		else if (!dio->inode->i_sb->s_dio_done_wq) {
+			/*
+			 * In case of AIO write racing with buffered read we
+			 * need to defer completion. We can't decide this now,
+			 * however the workqueue needs to be initialized here.
+			 */
+			retval = sb_init_dio_done_wq(dio->inode->i_sb);
+		}
 		if (retval) {
 			/*
 			 * We grab i_mutex only for reads so we don't have

fs/iomap.c

@@ -713,8 +713,24 @@ struct iomap_dio {
 static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	struct kiocb *iocb = dio->iocb;
+	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
+	/*
+	 * Try again to invalidate clean pages which might have been cached by
+	 * non-direct readahead, or faulted in by get_user_pages() if the source
+	 * of the write was an mmap'ed region of the file we're writing.  Either
+	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
+	 * this invalidation fails, tough, the write still worked...
+	 */
+	if (!dio->error &&
+	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+		ret = invalidate_inode_pages2_range(inode->i_mapping,
+				iocb->ki_pos >> PAGE_SHIFT,
+				(iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
+		WARN_ON_ONCE(ret);
+	}
+
 	if (dio->end_io) {
 		ret = dio->end_io(iocb,
 				dio->error ? dio->error : dio->size,
@@ -1042,19 +1058,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 	ret = iomap_dio_complete(dio);
 
-	/*
-	 * Try again to invalidate clean pages which might have been cached by
-	 * non-direct readahead, or faulted in by get_user_pages() if the source
-	 * of the write was an mmap'ed region of the file we're writing.  Either
-	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
-	 * this invalidation fails, tough, the write still worked...
-	 */
-	if (iov_iter_rw(iter) == WRITE) {
-		int err = invalidate_inode_pages2_range(mapping,
-				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(err);
-	}
-
 	return ret;
 
 out_free_dio:

include/linux/blkdev.h

@@ -551,6 +551,7 @@ struct request_queue {
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace	*blk_trace;
+	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations

include/linux/nvme-fc-driver.h

@@ -346,11 +346,6 @@ struct nvme_fc_remote_port {
  *       indicating an FC transport Aborted status.
  *       Entrypoint is Mandatory.
  *
- * @defer_rcv:  Called by the transport to signal the LLLD that it has
- *       begun processing of a previously received NVME CMD IU. The LLDD
- *       is now free to re-use the rcv buffer associated with the
- *       nvmefc_tgt_fcp_req.
- *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
  *       Value is Mandatory. Must be at least 1.
@@ -806,11 +801,19 @@ struct nvmet_fc_target_port {
  *       outstanding operation (if there was one) to complete, then will
  *       call the fcp_req_release() callback to return the command's
  *       exchange context back to the LLDD.
+ *       Entrypoint is Mandatory.
  *
  * @fcp_req_release:  Called by the transport to return a nvmefc_tgt_fcp_req
  *       to the LLDD after all operations on the fcp operation are complete.
  *       This may be due to the command completing or upon completion of
  *       abort cleanup.
+ *       Entrypoint is Mandatory.
+ *
+ * @defer_rcv:  Called by the transport to signal the LLLD that it has
+ *       begun processing of a previously received NVME CMD IU. The LLDD
+ *       is now free to re-use the rcv buffer associated with the
+ *       nvmefc_tgt_fcp_req.
+ *       Entrypoint is Optional.
  *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.

include/linux/nvme.h

@@ -471,12 +471,14 @@ enum nvme_opcode {
  *
  * @NVME_SGL_FMT_ADDRESS:     absolute address of the data block
  * @NVME_SGL_FMT_OFFSET:      relative offset of the in-capsule data block
+ * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA
  * @NVME_SGL_FMT_INVALIDATE:  RDMA transport specific remote invalidation
  *                            request subtype
  */
 enum {
 	NVME_SGL_FMT_ADDRESS		= 0x00,
 	NVME_SGL_FMT_OFFSET		= 0x01,
+	NVME_SGL_FMT_TRANSPORT_A	= 0x0A,
 	NVME_SGL_FMT_INVALIDATE		= 0x0f,
 };
 
@@ -490,12 +492,16 @@ enum {
  *
  * For struct nvme_keyed_sgl_desc:
  *   @NVME_KEY_SGL_FMT_DATA_DESC:	keyed data block descriptor
+ *
+ * Transport-specific SGL types:
+ *   @NVME_TRANSPORT_SGL_DATA_DESC:	Transport SGL data dlock descriptor
  */
 enum {
 	NVME_SGL_FMT_DATA_DESC		= 0x00,
 	NVME_SGL_FMT_SEG_DESC		= 0x02,
 	NVME_SGL_FMT_LAST_SEG_DESC	= 0x03,
 	NVME_KEY_SGL_FMT_DATA_DESC	= 0x04,
+	NVME_TRANSPORT_SGL_DATA_DESC	= 0x05,
 };
 
 struct nvme_sgl_desc {
@@ -1127,19 +1133,6 @@ enum {
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
 	NVME_SC_DNR			= 0x4000,
-
-
-	/*
-	 * FC Transport-specific error status values for NVME commands
-	 *
-	 * Transport-specific status code values must be in the range 0xB0..0xBF
-	 */
-
-	/* Generic FC failure - catchall */
-	NVME_SC_FC_TRANSPORT_ERROR	= 0x00B0,
-
-	/* I/O failure due to FC ABTS'd */
-	NVME_SC_FC_TRANSPORT_ABORTED	= 0x00B1,
 };
 
 struct nvme_completion {

kernel/trace/blktrace.c

@@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start)
 }
 EXPORT_SYMBOL_GPL(blk_trace_startstop);
 
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
 /**
  * blk_trace_ioctl: - handle the ioctls associated with tracing
  * @bdev:	the block device
@@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 	return ret;
 }
 
@@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!q->blk_trace);
@@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		if (value)
@@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out:

mm/filemap.c

@@ -2926,9 +2926,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	 * we're writing.  Either one is a pretty crazy thing to do,
 	 * so we don't support it 100%.  If this invalidation
 	 * fails, tough, the write still worked...
+	 *
+	 * Most of the time we do not need this since dio_complete() will do
+	 * the invalidation for us. However there are some file systems that
+	 * do not end up with dio_complete() being called, so let's not break
+	 * them by removing it completely
 	 */
-	invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT, end);
+	if (mapping->nrpages)
+		invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_SHIFT, end);
 
 	if (written > 0) {
 		pos += written;