Merge tag 'for-linus-20180727' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Bigger than usual at this time, mostly due to the O_DIRECT corruption
  issue and the fact that I was on vacation last week. This contains:

   - NVMe pull request with two fixes for the FC code, and two target
     fixes (Christoph)

   - a DIF bio reset iteration fix (Greg Edwards)

   - two nbd reply and requeue fixes (Josef)

   - SCSI timeout fixup (Keith)

   - a small series that fixes an issue with bio_iov_iter_get_pages(),
     which ended up causing corruption for larger sized O_DIRECT writes
     that ended up racing with buffered writes (Martin Wilck)"

* tag 'for-linus-20180727' of git://git.kernel.dk/linux-block:
  block: reset bi_iter.bi_done after splitting bio
  block: bio_iov_iter_get_pages: pin more pages for multi-segment IOs
  blkdev: __blkdev_direct_IO_simple: fix leak in error case
  block: bio_iov_iter_get_pages: fix size of last iovec
  nvmet: only check for filebacking on -ENOTBLK
  nvmet: fixup crash on NULL device path
  scsi: set timed out out mq requests to complete
  blk-mq: export setting request completion state
  nvme: if_ready checks to fail io to deleting controller
  nvmet-fc: fix target sgl list on large transfers
  nbd: handle unexpected replies better
  nbd: don't requeue the same request twice.

10 files changed, 148 insertions, 36 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 74a05561b620..3fb95c8d9fd8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -112,12 +112,16 @@ struct nbd_device {
 	struct task_struct *task_setup;
 };
 
+#define NBD_CMD_REQUEUED	1
+
 struct nbd_cmd {
 	struct nbd_device *nbd;
+	struct mutex lock;
 	int index;
 	int cookie;
-	struct completion send_complete;
 	blk_status_t status;
+	unsigned long flags;
+	u32 cmd_cookie;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 	return disk_to_dev(nbd->disk);
 }
 
+static void nbd_requeue_cmd(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+
+	if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags))
+		blk_mq_requeue_request(req, true);
+}
+
+#define NBD_COOKIE_BITS 32
+
+static u64 nbd_cmd_handle(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+	u32 tag = blk_mq_unique_tag(req);
+	u64 cookie = cmd->cmd_cookie;
+
+	return (cookie << NBD_COOKIE_BITS) | tag;
+}
+
+static u32 nbd_handle_to_tag(u64 handle)
+{
+	return (u32)handle;
+}
+
+static u32 nbd_handle_to_cookie(u64 handle)
+{
+	return (u32)(handle >> NBD_COOKIE_BITS);
+}
+
 static const char *nbdcmd_to_ascii(int cmd)
 {
 	switch (cmd) {
@@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	config = nbd->config;
 
+	if (!mutex_trylock(&cmd->lock))
+		return BLK_EH_RESET_TIMER;
+
 	if (config->num_connections > 1) {
 		dev_err_ratelimited(nbd_to_dev(nbd),
 				    "Connection timed out, retrying (%d/%d alive)\n",
@@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 					nbd_mark_nsock_dead(nbd, nsock, 1);
 				mutex_unlock(&nsock->tx_lock);
 			}
-			blk_mq_requeue_request(req, true);
+			mutex_unlock(&cmd->lock);
+			nbd_requeue_cmd(cmd);
 			nbd_config_put(nbd);
 			return BLK_EH_DONE;
 		}
@@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
 	cmd->status = BLK_STS_IOERR;
+	mutex_unlock(&cmd->lock);
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
 done:
@@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct iov_iter from;
 	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
+	u64 handle;
 	u32 type;
 	u32 nbd_cmd_flags = 0;
-	u32 tag = blk_mq_unique_tag(req);
 	int sent = nsock->sent, skip = 0;
 
 	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
@@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 			goto send_pages;
 		}
 		iov_iter_advance(&from, sent);
+	} else {
+		cmd->cmd_cookie++;
 	}
 	cmd->index = index;
 	cmd->cookie = nsock->cookie;
@@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
 	}
-	memcpy(request.handle, &tag, sizeof(tag));
+	handle = nbd_cmd_handle(cmd);
+	memcpy(request.handle, &handle, sizeof(handle));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		req, nbdcmd_to_ascii(type),
@@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->pending = req;
 				nsock->sent = sent;
 			}
+			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 			return BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -541,6 +583,7 @@ send_pages:
 					 */
 					nsock->pending = req;
 					nsock->sent = sent;
+					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 					return BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
@@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	struct nbd_reply reply;
 	struct nbd_cmd *cmd;
 	struct request *req = NULL;
+	u64 handle;
 	u16 hwq;
 	u32 tag;
 	struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
 	struct iov_iter to;
+	int ret = 0;
 
 	reply.magic = 0;
 	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
@@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-EPROTO);
 	}
 
-	memcpy(&tag, reply.handle, sizeof(u32));
-
+	memcpy(&handle, reply.handle, sizeof(handle));
+	tag = nbd_handle_to_tag(handle);
 	hwq = blk_mq_unique_tag_to_hwq(tag);
 	if (hwq < nbd->tag_set.nr_hw_queues)
 		req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq],
@@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-ENOENT);
 	}
 	cmd = blk_mq_rq_to_pdu(req);
+
+	mutex_lock(&cmd->lock);
+	if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
+		dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
+			req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
+		ret = -ENOENT;
+		goto out;
+	}
+	if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
+		dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
+			req);
+		ret = -ENOENT;
+		goto out;
+	}
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
 		cmd->status = BLK_STS_IOERR;
-		return cmd;
+		goto out;
 	}
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
@@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				if (nbd_disconnected(config) ||
 				    config->num_connections <= 1) {
 					cmd->status = BLK_STS_IOERR;
-					return cmd;
+					goto out;
 				}
-				return ERR_PTR(-EIO);
+				ret = -EIO;
+				goto out;
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
 				req, bvec.bv_len);
 		}
-	} else {
-		/* See the comment in nbd_queue_rq. */
-		wait_for_completion(&cmd->send_complete);
 	}
-	return cmd;
+out:
+	mutex_unlock(&cmd->lock);
+	return ret ? ERR_PTR(ret) : cmd;
 }
 
 static void recv_work(struct work_struct *work)
@@ -805,7 +864,7 @@ again:
 	 */
 	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 		goto out;
 	}
@@ -818,7 +877,7 @@ again:
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 	}
 out:
@@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * that the server is misbehaving (or there was an error) before we're
 	 * done sending everything over the wire.
 	 */
-	init_completion(&cmd->send_complete);
+	mutex_lock(&cmd->lock);
+	clear_bit(NBD_CMD_REQUEUED, &cmd->flags);
 
 	/* We can be called directly from the user space process, which means we
 	 * could possibly have signals pending so our sendmsg will fail.  In
@@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		ret = BLK_STS_IOERR;
 	else if (!ret)
 		ret = BLK_STS_OK;
-	complete(&cmd->send_complete);
+	mutex_unlock(&cmd->lock);
 
 	return ret;
 }
@@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	cmd->nbd = set->driver_data;
+	cmd->flags = 0;
+	mutex_init(&cmd->lock);
 	return 0;
 }
 
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 903eb4545e26..f7efe5a58cc7 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 /*
  * For something we're not in a state to send to the device the default action
  * is to busy it and retry it after the controller state is recovered.  However,
- * anything marked for failfast or nvme multipath is immediately failed.
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
  *
  * Note: commands used to initialize the controller will be marked for failfast.
  * Note: nvme cli/ioctl commands are marked for failfast.
  */
-blk_status_t nvmf_fail_nonready_command(struct request *rq)
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
 {
-	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+	if (ctrl->state != NVME_CTRL_DELETING &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index e1818a27aa2d..aa2fdb2a2e8f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_fail_nonready_command(struct request *rq);
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq);
 bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 41d45a1b5c62..9bac912173ba 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
 	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_setup_cmd(ns, rq, sqe);
 	if (ret)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 518c5b09038c..66ec5985c9f3 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	WARN_ON_ONCE(rq->tag < 0);
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d3f3b3ec4d1a..ebea1373d1b7 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 {
 	struct nvmet_ns *ns = to_nvmet_ns(item);
 	struct nvmet_subsys *subsys = ns->subsys;
+	size_t len;
 	int ret;
 
 	mutex_lock(&subsys->lock);
@@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 	if (ns->enabled)
 		goto out_unlock;
 
-	kfree(ns->device_path);
+	ret = -EINVAL;
+	len = strcspn(page, "\n");
+	if (!len)
+		goto out_unlock;
 
+	kfree(ns->device_path);
 	ret = -ENOMEM;
-	ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
+	ns->device_path = kstrndup(page, len, GFP_KERNEL);
 	if (!ns->device_path)
 		goto out_unlock;
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 74d4b785d2da..9838103f2d62 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 		goto out_unlock;
 
 	ret = nvmet_bdev_ns_enable(ns);
-	if (ret)
+	if (ret == -ENOTBLK)
 		ret = nvmet_file_ns_enable(ns);
 	if (ret)
 		goto out_unlock;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 408279cb6f2c..29b4b236afd8 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod {
 	struct work_struct		work;
 } __aligned(sizeof(unsigned long long));
 
+/* desired maximum for a single sequence - if sg list allows it */
 #define NVMET_FC_MAX_SEQ_LENGTH		(256 * 1024)
-#define NVMET_FC_MAX_XFR_SGENTS		(NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE)
 
 enum nvmet_fcp_datadir {
 	NVMET_FCP_NODATA,
@@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod {
 	struct nvme_fc_cmd_iu		cmdiubuf;
 	struct nvme_fc_ersp_iu		rspiubuf;
 	dma_addr_t			rspdma;
+	struct scatterlist		*next_sg;
 	struct scatterlist		*data_sg;
 	int				data_sg_cnt;
 	u32				offset;
@@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	INIT_LIST_HEAD(&newrec->assoc_list);
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
-	newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS,
-					template->max_sgl_segments);
+	newrec->max_sg_cnt = template->max_sgl_segments;
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 				((fod->io_dir == NVMET_FCP_WRITE) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE));
 				/* note: write from initiator perspective */
+	fod->next_sg = fod->data_sg;
 
 	return 0;
 
@@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 				struct nvmet_fc_fcp_iod *fod, u8 op)
 {
 	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct scatterlist *sg = fod->next_sg;
 	unsigned long flags;
-	u32 tlen;
+	u32 remaininglen = fod->req.transfer_len - fod->offset;
+	u32 tlen = 0;
 	int ret;
 
 	fcpreq->op = op;
 	fcpreq->offset = fod->offset;
 	fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
 
-	tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
-			(fod->req.transfer_len - fod->offset));
+	/*
+	 * for next sequence:
+	 *  break at a sg element boundary
+	 *  attempt to keep sequence length capped at
+	 *    NVMET_FC_MAX_SEQ_LENGTH but allow sequence to
+	 *    be longer if a single sg element is larger
+	 *    than that amount. This is done to avoid creating
+	 *    a new sg list to use for the tgtport api.
+	 */
+	fcpreq->sg = sg;
+	fcpreq->sg_cnt = 0;
+	while (tlen < remaininglen &&
+	       fcpreq->sg_cnt < tgtport->max_sg_cnt &&
+	       tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) {
+		fcpreq->sg_cnt++;
+		tlen += sg_dma_len(sg);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen && fcpreq->sg_cnt == 0) {
+		fcpreq->sg_cnt++;
+		tlen += min_t(u32, sg_dma_len(sg), remaininglen);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen)
+		fod->next_sg = sg;
+	else
+		fod->next_sg = NULL;
+
 	fcpreq->transfer_length = tlen;
 	fcpreq->transferred_length = 0;
 	fcpreq->fcp_error = 0;
 	fcpreq->rsplen = 0;
 
-	fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE];
-	fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE);
-
 	/*
 	 * If the last READDATA request: check if LLDD supports
 	 * combined xfr with response.
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d8d91f04bd7e..ae7586b8be07 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_status_t ret;
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
-		return nvmf_fail_nonready_command(req);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
 	if (ret)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 8932ae81a15a..2715cdaa669c 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 		rtn = host->hostt->eh_timed_out(scmd);
 
 	if (rtn == BLK_EH_DONE) {
+		/*
+		 * For blk-mq, we must set the request state to complete now
+		 * before sending the request to the scsi error handler. This
+		 * will prevent a use-after-free in the event the LLD manages
+		 * to complete the request before the error handler finishes
+		 * processing this timed out request.
+		 *
+		 * If the request was already completed, then the LLD beat the
+		 * time out handler from transferring the request to the scsi
+		 * error handler. In that case we can return immediately as no
+		 * further action is required.
+		 */
+		if (req->q->mq_ops && !blk_mq_mark_complete(req))
+			return rtn;
 		if (scsi_abort_command(scmd) != SUCCESS) {
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_scmd_add(scmd);