Merge branch 'for-4.8/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This branch also contains core changes.  I've come to the conclusion
  that from 4.9 and forward, I'll be doing just a single branch.  We
  often have dependencies between core and drivers, and it's hard to
  always split them up appropriately without pulling core into drivers
  when that happens.

  That said, this contains:

   - separate secure erase type for the core block layer, from
     Christoph.

   - set of discard fixes, from Christoph.

   - bio shrinking fixes from Christoph, as a followup up to the
     op/flags change in the core branch.

   - map and append request fixes from Christoph.

   - NVMeF (NVMe over Fabrics) code from Christoph.  This is pretty
     exciting!

   - nvme-loop fixes from Arnd.

   - removal of ->driverfs_dev from Dan, after providing a
     device_add_disk() helper.

   - bcache fixes from Bhaktipriya and Yijing.

   - cdrom subchannel read fix from Vchannaiah.

   - set of lightnvm updates from Wenwei, Matias, Johannes, and Javier.

   - set of drbd updates and fixes from Fabian, Lars, and Philipp.

   - mg_disk error path fix from Bart.

   - user notification for failed device add for loop, from Minfei.

   - NVMe in general:
        + NVMe delay quirk from Guilherme.
        + SR-IOV support and command retry limits from Keith.
        + fix for memory-less NUMA node from Masayoshi.
        + use UINT_MAX for discard sectors, from Minfei.
        + cancel IO fixes from Ming.
        + don't allocate unused major, from Neil.
        + error code fixup from Dan.
        + use constants for PSDT/FUSE from James.
        + variable init fix from Jay.
        + fabrics fixes from Ming, Sagi, and Wei.
        + various fixes"

* 'for-4.8/drivers' of git://git.kernel.dk/linux-block: (115 commits)
  nvme/pci: Provide SR-IOV support
  nvme: initialize variable before logical OR'ing it
  block: unexport various bio mapping helpers
  scsi/osd: open code blk_make_request
  target: stop using blk_make_request
  block: simplify and export blk_rq_append_bio
  block: ensure bios return from blk_get_request are properly initialized
  virtio_blk: use blk_rq_map_kern
  memstick: don't allow REQ_TYPE_BLOCK_PC requests
  block: shrink bio size again
  block: simplify and cleanup bvec pool handling
  block: get rid of bio_rw and READA
  block: don't ignore -EOPNOTSUPP blkdev_issue_write_same
  block: introduce BLKDEV_DISCARD_ZERO to fix zeroout
  NVMe: don't allocate unused nvme_major
  nvme: avoid crashes when node 0 is memoryless node.
  nvme: Limit command retries
  loop: Make user notify for adding loop device failed
  nvme-loop: fix nvme-loop Kconfig dependencies
  nvmet: fix return value check in nvmet_subsys_alloc()
  ...

1 files changed, 36 insertions, 32 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index befac5b19490..4cb9b156cab7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -310,6 +310,11 @@ static int nvme_init_iod(struct request *rq, unsigned size,
 	iod->npages = -1;
 	iod->nents = 0;
 	iod->length = size;
+
+	if (!(rq->cmd_flags & REQ_DONTPREP)) {
+		rq->retries = 0;
+		rq->cmd_flags |= REQ_DONTPREP;
+	}
 	return 0;
 }
 
@@ -520,8 +525,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 			goto out_unmap;
 	}
 
-	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+	cmnd->rw.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->rw.dptr.prp2 = cpu_to_le64(iod->first_dma);
 	if (blk_integrity_rq(req))
 		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg));
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -623,6 +628,7 @@ static void nvme_complete_rq(struct request *req)
 
 	if (unlikely(req->errors)) {
 		if (nvme_req_needs_retry(req, req->errors)) {
+			req->retries++;
 			nvme_requeue_req(req);
 			return;
 		}
@@ -901,7 +907,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		 req->tag, nvmeq->qid);
 
 	abort_req = nvme_alloc_request(dev->ctrl.admin_q, &cmd,
-			BLK_MQ_REQ_NOWAIT);
+			BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(abort_req)) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
@@ -919,22 +925,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	return BLK_EH_RESET_TIMER;
 }
 
-static void nvme_cancel_io(struct request *req, void *data, bool reserved)
-{
-	int status;
-
-	if (!blk_mq_request_started(req))
-		return;
-
-	dev_dbg_ratelimited(((struct nvme_dev *) data)->ctrl.device,
-				"Cancelling I/O %d", req->tag);
-
-	status = NVME_SC_ABORT_REQ;
-	if (blk_queue_dying(req->q))
-		status |= NVME_SC_DNR;
-	blk_mq_complete_request(req, status);
-}
-
 static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
@@ -1399,16 +1389,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	/*
-	 * Degraded controllers might return an error when setting the queue
-	 * count.  We still want to be able to bring them online and offer
-	 * access to the admin queue, as that might be only way to fix them up.
-	 */
-	if (result > 0) {
-		dev_err(dev->ctrl.device,
-			"Could not set queue count (%d)\n", result);
+	if (nr_io_queues == 0)
 		return 0;
-	}
 
 	if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
@@ -1536,7 +1518,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
-	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT);
+	req = nvme_alloc_request(q, &cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1727,8 +1709,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	}
 	nvme_pci_disable(dev);
 
-	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_io, dev);
-	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_io, dev);
+	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
+	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1902,6 +1884,7 @@ static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
+	.name			= "pcie",
 	.module			= THIS_MODULE,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
@@ -1940,7 +1923,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
-		set_dev_node(&pdev->dev, 0);
+		set_dev_node(&pdev->dev, first_memory_node);
 
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
@@ -2037,6 +2020,24 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_put_ctrl(&dev->ctrl);
 }
 
+static int nvme_pci_sriov_configure(struct pci_dev *pdev, int numvfs)
+{
+	int ret = 0;
+
+	if (numvfs == 0) {
+		if (pci_vfs_assigned(pdev)) {
+			dev_warn(&pdev->dev,
+				"Cannot disable SR-IOV VFs while assigned\n");
+			return -EPERM;
+		}
+		pci_disable_sriov(pdev);
+		return 0;
+	}
+
+	ret = pci_enable_sriov(pdev, numvfs);
+	return ret ? ret : numvfs;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int nvme_suspend(struct device *dev)
 {
@@ -2122,6 +2123,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DISCARD_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ 0, }
@@ -2137,6 +2140,7 @@ static struct pci_driver nvme_driver = {
 	.driver		= {
 		.pm	= &nvme_dev_pm_ops,
 	},
+	.sriov_configure = nvme_pci_sriov_configure,
 	.err_handler	= &nvme_err_handler,
 };