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.

block/bio.c

@@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
+	bio->bi_iter.bi_done = 0;
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
 		bio_set_flag(split, BIO_TRACE_COMPLETION);

block/blk-mq.c

@@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
-	if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
-			MQ_RQ_IN_FLIGHT)
+	if (!blk_mq_mark_complete(rq))
 		return;
-
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 

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 @@ 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(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 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	 */
 	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 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		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;
 }
 

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;

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);
 

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)