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;
@@ -1421,15 +1421,15 @@ 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;
 		status = cqe->status;
 		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;
 }