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

Pull block fixes from Jens Axboe:
 "A set of fixes for this series. This contains:

   - Set of fixes for the nvme target code

   - A revert of patch from this merge window, causing a regression with
     WRITE_SAME on iSCSI targets at least.

   - A fix for a use-after-free in the new O_DIRECT bdev code.

   - Two fixes for the xen-blkfront driver"

* 'for-linus' of git://git.kernel.dk/linux-block:
  Revert "sd: remove __data_len hack for WRITE SAME"
  nvme-fc: use blk_rq_nr_phys_segments
  nvmet-rdma: Fix missing dma sync to nvme data structures
  nvmet: Call fatal_error from keep-alive timout expiration
  nvmet: cancel fatal error and flush async work before free controller
  nvmet: delete controllers deletion upon subsystem release
  nvmet_fc: correct logic in disconnect queue LS handling
  block: fix use after free in __blkdev_direct_IO
  xen-blkfront: correct maximum segment accounting
  xen-blkfront: feature flags handling adjustments

drivers/block/xen-blkfront.c

@@ -197,13 +197,13 @@ struct blkfront_info
 	/* Number of pages per ring buffer. */
 	unsigned int nr_ring_pages;
 	struct request_queue *rq;
-	unsigned int feature_flush;
+	unsigned int feature_flush:1;
-	unsigned int feature_fua;
+	unsigned int feature_fua:1;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
+	unsigned int feature_persistent:1;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
-	unsigned int feature_persistent:1;
 	/* Number of 4KB segments handled */
 	unsigned int max_indirect_segments;
 	int is_ready;
@@ -2223,7 +2223,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 	}
 	else
 		grants = info->max_indirect_segments;
-	psegs = grants / GRANTS_PER_PSEG;
+	psegs = DIV_ROUND_UP(grants, GRANTS_PER_PSEG);
 
 	err = fill_grant_buffer(rinfo,
 				(grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info));
@@ -2323,13 +2323,16 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 		blkfront_setup_discard(info);
 
 	info->feature_persistent =
-		xenbus_read_unsigned(info->xbdev->otherend,
+		!!xenbus_read_unsigned(info->xbdev->otherend,
-				     "feature-persistent", 0);
+				       "feature-persistent", 0);
 
 	indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
 					"feature-max-indirect-segments", 0);
-	info->max_indirect_segments = min(indirect_segments,
+	if (indirect_segments > xen_blkif_max_segments)
-					  xen_blkif_max_segments);
+		indirect_segments = xen_blkif_max_segments;
+	if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST)
+		indirect_segments = 0;
+	info->max_indirect_segments = indirect_segments;
 }
 
 /*
@@ -2652,6 +2655,9 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST)
+		xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
 	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
 		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
 			xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);

drivers/nvme/host/fc.c

@@ -1663,13 +1663,13 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 		return 0;
 
 	freq->sg_table.sgl = freq->first_sgl;
-	ret = sg_alloc_table_chained(&freq->sg_table, rq->nr_phys_segments,
+	ret = sg_alloc_table_chained(&freq->sg_table,
-			freq->sg_table.sgl);
+			blk_rq_nr_phys_segments(rq), freq->sg_table.sgl);
 	if (ret)
 		return -ENOMEM;
 
 	op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl);
-	WARN_ON(op->nents > rq->nr_phys_segments);
+	WARN_ON(op->nents > blk_rq_nr_phys_segments(rq));
 	dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
 				op->nents, dir);

drivers/nvme/target/configfs.c

@@ -631,6 +631,7 @@ static void nvmet_subsys_release(struct config_item *item)
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
 
+	nvmet_subsys_del_ctrls(subsys);
 	nvmet_subsys_put(subsys);
 }
 

drivers/nvme/target/core.c

@@ -200,7 +200,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
 		ctrl->cntlid, ctrl->kato);
 
-	ctrl->ops->delete_ctrl(ctrl);
+	nvmet_ctrl_fatal_error(ctrl);
 }
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
@@ -816,6 +816,9 @@ static void nvmet_ctrl_free(struct kref *ref)
 	list_del(&ctrl->subsys_entry);
 	mutex_unlock(&subsys->lock);
 
+	flush_work(&ctrl->async_event_work);
+	cancel_work_sync(&ctrl->fatal_err_work);
+
 	ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid);
 	nvmet_subsys_put(subsys);
 
@@ -935,6 +938,16 @@ static void nvmet_subsys_free(struct kref *ref)
 	kfree(subsys);
 }
 
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		ctrl->ops->delete_ctrl(ctrl);
+	mutex_unlock(&subsys->lock);
+}
+
 void nvmet_subsys_put(struct nvmet_subsys *subsys)
 {
 	kref_put(&subsys->ref, nvmet_subsys_free);

drivers/nvme/target/fc.c

@@ -1314,7 +1314,7 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			(struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf;
 	struct fcnvme_ls_disconnect_acc *acc =
 			(struct fcnvme_ls_disconnect_acc *)iod->rspbuf;
-	struct nvmet_fc_tgt_queue *queue;
+	struct nvmet_fc_tgt_queue *queue = NULL;
 	struct nvmet_fc_tgt_assoc *assoc;
 	int ret = 0;
 	bool del_assoc = false;
@@ -1348,7 +1348,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		assoc = nvmet_fc_find_target_assoc(tgtport,
 				be64_to_cpu(rqst->associd.association_id));
 		iod->assoc = assoc;
-		if (!assoc)
+		if (assoc) {
+			if (rqst->discon_cmd.scope ==
+					FCNVME_DISCONN_CONNECTION) {
+				queue = nvmet_fc_find_target_queue(tgtport,
+						be64_to_cpu(
+							rqst->discon_cmd.id));
+				if (!queue) {
+					nvmet_fc_tgt_a_put(assoc);
+					ret = VERR_NO_CONN;
+				}
+			}
+		} else
 			ret = VERR_NO_ASSOC;
 	}
 
@@ -1373,21 +1384,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			FCNVME_LS_DISCONNECT);
 
 
-	if (rqst->discon_cmd.scope == FCNVME_DISCONN_CONNECTION) {
+	/* are we to delete a Connection ID (queue) */
-		queue = nvmet_fc_find_target_queue(tgtport,
+	if (queue) {
-					be64_to_cpu(rqst->discon_cmd.id));
+		int qid = queue->qid;
-		if (queue) {
-			int qid = queue->qid;
 
-			nvmet_fc_delete_target_queue(queue);
+		nvmet_fc_delete_target_queue(queue);
 
-			/* release the get taken by find_target_queue */
+		/* release the get taken by find_target_queue */
-			nvmet_fc_tgt_q_put(queue);
+		nvmet_fc_tgt_q_put(queue);
 
-			/* tear association down if io queue terminated */
+		/* tear association down if io queue terminated */
-			if (!qid)
+		if (!qid)
-				del_assoc = true;
+			del_assoc = true;
-		}
 	}
 
 	/* release get taken in nvmet_fc_find_target_assoc */

drivers/nvme/target/nvmet.h

@@ -282,6 +282,7 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
 struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 		enum nvme_subsys_type type);
 void nvmet_subsys_put(struct nvmet_subsys *subsys);
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys);
 
 struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid);
 void nvmet_put_namespace(struct nvmet_ns *ns);

drivers/nvme/target/rdma.c

@@ -438,6 +438,10 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 {
 	struct ib_recv_wr *bad_wr;
 
+	ib_dma_sync_single_for_device(ndev->device,
+		cmd->sge[0].addr, cmd->sge[0].length,
+		DMA_FROM_DEVICE);
+
 	if (ndev->srq)
 		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
 	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
@@ -538,6 +542,11 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		first_wr = &rsp->send_wr;
 
 	nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
+
+	ib_dma_sync_single_for_device(rsp->queue->dev->device,
+		rsp->send_sge.addr, rsp->send_sge.length,
+		DMA_TO_DEVICE);
+
 	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
@@ -698,6 +707,14 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 	cmd->n_rdma = 0;
 	cmd->req.port = queue->port;
 
+
+	ib_dma_sync_single_for_cpu(queue->dev->device,
+		cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
+		DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_cpu(queue->dev->device,
+		cmd->send_sge.addr, cmd->send_sge.length,
+		DMA_TO_DEVICE);
+
 	if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
 			&queue->nvme_sq, &nvmet_rdma_ops))
 		return;

drivers/scsi/sd.c

@@ -836,6 +836,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	struct bio *bio = rq->bio;
 	sector_t sector = blk_rq_pos(rq);
 	unsigned int nr_sectors = blk_rq_sectors(rq);
+	unsigned int nr_bytes = blk_rq_bytes(rq);
 	int ret;
 
 	if (sdkp->device->no_write_same)
@@ -868,7 +869,21 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 
 	cmd->transfersize = sdp->sector_size;
 	cmd->allowed = SD_MAX_RETRIES;
-	return scsi_init_io(cmd);
+
+	/*
+	 * For WRITE SAME the data transferred via the DATA OUT buffer is
+	 * different from the amount of data actually written to the target.
+	 *
+	 * We set up __data_len to the amount of data transferred via the
+	 * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list
+	 * to transfer a single sector of data first, but then reset it to
+	 * the amount of data to be written right after so that the I/O path
+	 * knows how much to actually write.
+	 */
+	rq->__data_len = sdp->sector_size;
+	ret = scsi_init_io(cmd);
+	rq->__data_len = nr_bytes;
+	return ret;
 }
 
 static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd)

fs/block_dev.c

@@ -331,7 +331,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
-	bool is_read = (iov_iter_rw(iter) == READ);
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
 	int ret;
@@ -344,7 +344,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	bio_get(bio); /* extra ref for the completion handler */
 
 	dio = container_of(bio, struct blkdev_dio, bio);
-	dio->is_sync = is_sync_kiocb(iocb);
+	dio->is_sync = is_sync = is_sync_kiocb(iocb);
 	if (dio->is_sync)
 		dio->waiter = current;
 	else
@@ -398,7 +398,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	}
 	blk_finish_plug(&plug);
 
-	if (!dio->is_sync)
+	if (!is_sync)
 		return -EIOCBQUEUED;
 
 	for (;;) {