Merge tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - blk-mq scheduling framework from me and Omar, with a port of the
   deadline scheduler for this framework. A port of BFQ from Paolo is in
   the works, and should be ready for 4.12.

 - Various fixups and improvements to the above scheduling framework
   from Omar, Paolo, Bart, me, others.

 - Cleanup of the exported sysfs blk-mq data into debugfs, from Omar.
   This allows us to export more information that helps debug hangs or
   performance issues, without cluttering or abusing the sysfs API.

 - Fixes for the sbitmap code, the scalable bitmap code that was
   migrated from blk-mq, from Omar.

 - Removal of the BLOCK_PC support in struct request, and refactoring of
   carrying SCSI payloads in the block layer. This cleans up the code
   nicely, and enables us to kill the SCSI specific parts of struct
   request, shrinking it down nicely. From Christoph mainly, with help
   from Hannes.

 - Support for ranged discard requests and discard merging, also from
   Christoph.

 - Support for OPAL in the block layer, and for NVMe as well. Mainly
   from Scott Bauer, with fixes/updates from various others folks.

 - Error code fixup for gdrom from Christophe.

 - cciss pci irq allocation cleanup from Christoph.

 - Making the cdrom device operations read only, from Kees Cook.

 - Fixes for duplicate bdi registrations and bdi/queue life time
   problems from Jan and Dan.

 - Set of fixes and updates for lightnvm, from Matias and Javier.

 - A few fixes for nbd from Josef, using idr to name devices and a
   workqueue deadlock fix on receive. Also marks Josef as the current
   maintainer of nbd.

 - Fix from Josef, overwriting queue settings when the number of
   hardware queues is updated for a blk-mq device.

 - NVMe fix from Keith, ensuring that we don't repeatedly mark and IO
   aborted, if we didn't end up aborting it.

 - SG gap merging fix from Ming Lei for block.

 - Loop fix also from Ming, fixing a race and crash between setting loop
   status and IO.

 - Two block race fixes from Tahsin, fixing request list iteration and
   fixing a race between device registration and udev device add
   notifiations.

 - Double free fix from cgroup writeback, from Tejun.

 - Another double free fix in blkcg, from Hou Tao.

 - Partition overflow fix for EFI from Alden Tondettar.

* tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block: (156 commits)
  nvme: Check for Security send/recv support before issuing commands.
  block/sed-opal: allocate struct opal_dev dynamically
  block/sed-opal: tone down not supported warnings
  block: don't defer flushes on blk-mq + scheduling
  blk-mq-sched: ask scheduler for work, if we failed dispatching leftovers
  blk-mq: don't special case flush inserts for blk-mq-sched
  blk-mq-sched: don't add flushes to the head of requeue queue
  blk-mq: have blk_mq_dispatch_rq_list() return if we queued IO or not
  block: do not allow updates through sysfs until registration completes
  lightnvm: set default lun range when no luns are specified
  lightnvm: fix off-by-one error on target initialization
  Maintainers: Modify SED list from nvme to block
  Move stack parameters for sed_ioctl to prevent oversized stack with CONFIG_KASAN
  uapi: sed-opal fix IOW for activate lsp to use correct struct
  cdrom: Make device operations read-only
  elevator: fix loading wrong elevator type for blk-mq devices
  cciss: switch to pci_irq_alloc_vectors
  block/loop: fix race between I/O and set_status
  blk-mq-sched: don't hold queue_lock when calling exit_icq
  block: set make_request_fn manually in blk_mq_update_nr_hw_queues
  ...

1 files changed, 126 insertions, 79 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 264c5eac12b0..024b473524c0 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -52,11 +52,13 @@ struct virtio_blk {
 };
 
 struct virtblk_req {
-	struct request *req;
-	struct virtio_blk_outhdr out_hdr;
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	struct scsi_request sreq;	/* for SCSI passthrough, must be first */
+	u8 sense[SCSI_SENSE_BUFFERSIZE];
 	struct virtio_scsi_inhdr in_hdr;
+#endif
+	struct virtio_blk_outhdr out_hdr;
 	u8 status;
-	u8 sense[SCSI_SENSE_BUFFERSIZE];
 	struct scatterlist sg[];
 };
 
@@ -72,28 +74,88 @@ static inline int virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static int __virtblk_add_req(struct virtqueue *vq,
-			     struct virtblk_req *vbr,
-			     struct scatterlist *data_sg,
-			     bool have_data)
+/*
+ * If this is a packet command we need a couple of additional headers.  Behind
+ * the normal outhdr we put a segment with the scsi command block, and before
+ * the normal inhdr we put the sense data and the inhdr with additional status
+ * information.
+ */
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
 {
 	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
 	unsigned int num_out = 0, num_in = 0;
-	__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
 
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
+	sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len);
+	sgs[num_out++] = &cmd;
+
+	if (have_data) {
+		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
+			sgs[num_out++] = data_sg;
+		else
+			sgs[num_out + num_in++] = data_sg;
+	}
+
+	sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
+	sgs[num_out + num_in++] = &sense;
+	sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
+	sgs[num_out + num_in++] = &inhdr;
+	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
+	sgs[num_out + num_in++] = &status;
+
+	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
+}
+
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	struct virtio_blk *vblk = req->q->queuedata;
+	struct scsi_request *sreq = &vbr->sreq;
+
+	sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+	sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+	req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+}
+
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long data)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct virtio_blk *vblk = disk->private_data;
 
 	/*
-	 * If this is a packet command we need a couple of additional headers.
-	 * Behind the normal outhdr we put a segment with the scsi command
-	 * block, and before the normal inhdr we put the sense data and the
-	 * inhdr with additional status information.
+	 * Only allow the generic SCSI ioctls if the host can support it.
 	 */
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
-		sgs[num_out++] = &cmd;
-	}
+	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+		return -ENOTTY;
+
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
+}
+#else
+static inline int virtblk_add_req_scsi(struct virtqueue *vq,
+		struct virtblk_req *vbr, struct scatterlist *data_sg,
+		bool have_data)
+{
+	return -EIO;
+}
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+}
+#define virtblk_ioctl	NULL
+#endif /* CONFIG_VIRTIO_BLK_SCSI */
+
+static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
+{
+	struct scatterlist hdr, status, *sgs[3];
+	unsigned int num_out = 0, num_in = 0;
+
+	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
+	sgs[num_out++] = &hdr;
 
 	if (have_data) {
 		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
@@ -102,14 +164,6 @@ static int __virtblk_add_req(struct virtqueue *vq,
 			sgs[num_out + num_in++] = data_sg;
 	}
 
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
-		sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
-		sgs[num_out + num_in++] = &sense;
-		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
-		sgs[num_out + num_in++] = &inhdr;
-	}
-
 	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
 	sgs[num_out + num_in++] = &status;
 
@@ -119,15 +173,16 @@ static int __virtblk_add_req(struct virtqueue *vq,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
-	struct virtio_blk *vblk = req->q->queuedata;
 	int error = virtblk_result(vbr);
 
-	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
-		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
-		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
-	} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+	switch (req_op(req)) {
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		virtblk_scsi_reques_done(req);
+		break;
+	case REQ_OP_DRV_IN:
 		req->errors = (error != 0);
+		break;
 	}
 
 	blk_mq_end_request(req, error);
@@ -146,7 +201,9 @@ static void virtblk_done(struct virtqueue *vq)
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
-			blk_mq_complete_request(vbr->req, vbr->req->errors);
+			struct request *req = blk_mq_rq_from_pdu(vbr);
+
+			blk_mq_complete_request(req, req->errors);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -170,49 +227,50 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int qid = hctx->queue_num;
 	int err;
 	bool notify = false;
+	u32 type;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	vbr->req = req;
-	if (req_op(req) == REQ_OP_FLUSH) {
-		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
-		vbr->out_hdr.sector = 0;
-		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-	} else {
-		switch (req->cmd_type) {
-		case REQ_TYPE_FS:
-			vbr->out_hdr.type = 0;
-			vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		case REQ_TYPE_BLOCK_PC:
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
-			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		case REQ_TYPE_DRV_PRIV:
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
-			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		default:
-			/* We don't put anything else in the queue. */
-			BUG();
-		}
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		type = 0;
+		break;
+	case REQ_OP_FLUSH:
+		type = VIRTIO_BLK_T_FLUSH;
+		break;
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		type = VIRTIO_BLK_T_SCSI_CMD;
+		break;
+	case REQ_OP_DRV_IN:
+		type = VIRTIO_BLK_T_GET_ID;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
+	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
+	vbr->out_hdr.sector = type ?
+		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
+	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+
 	blk_mq_start_request(req);
 
-	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
+	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
 	if (num) {
-		if (rq_data_dir(vbr->req) == WRITE)
+		if (rq_data_dir(req) == WRITE)
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
 		else
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = __virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	if (req_op(req) == REQ_OP_SCSI_IN || req_op(req) == REQ_OP_SCSI_OUT)
+		err = virtblk_add_req_scsi(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	else
+		err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		blk_mq_stop_hw_queue(hctx);
@@ -242,10 +300,9 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	struct request *req;
 	int err;
 
-	req = blk_get_request(q, READ, GFP_KERNEL);
+	req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->cmd_type = REQ_TYPE_DRV_PRIV;
 
 	err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
 	if (err)
@@ -257,22 +314,6 @@ out:
 	return err;
 }
 
-static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long data)
-{
-	struct gendisk *disk = bdev->bd_disk;
-	struct virtio_blk *vblk = disk->private_data;
-
-	/*
-	 * Only allow the generic SCSI ioctls if the host can support it.
-	 */
-	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
-		return -ENOTTY;
-
-	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
-				  (void __user *)data);
-}
-
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
@@ -538,6 +579,9 @@ static int virtblk_init_request(void *data, struct request *rq,
 	struct virtio_blk *vblk = data;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
 
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	vbr->sreq.sense = vbr->sense;
+#endif
 	sg_init_table(vbr->sg, vblk->sg_elems);
 	return 0;
 }
@@ -821,7 +865,10 @@ static const struct virtio_device_id id_table[] = {
 
 static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
-	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	VIRTIO_BLK_F_SCSI,
+#endif
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
 }