1 files changed, 96 insertions, 111 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 60f7eab11865..5e52034ab010 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -16,6 +16,7 @@
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -88,7 +89,6 @@ struct nvme_dev {
 	unsigned max_qid;
 	int q_depth;
 	u32 db_stride;
-	struct msix_entry *entry;
 	void __iomem *bar;
 	struct work_struct reset_work;
 	struct work_struct remove_work;
@@ -99,6 +99,7 @@ struct nvme_dev {
 	dma_addr_t cmb_dma_addr;
 	u64 cmb_size;
 	u32 cmbsz;
+	u32 cmbloc;
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
 };
@@ -201,6 +202,11 @@ static unsigned int nvme_cmd_size(struct nvme_dev *dev)
 		nvme_iod_alloc_size(dev, NVME_INT_BYTES(dev), NVME_INT_PAGES);
 }
 
+static int nvmeq_irq(struct nvme_queue *nvmeq)
+{
+	return pci_irq_vector(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector);
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -263,6 +269,13 @@ static int nvme_init_request(void *data, struct request *req,
 	return 0;
 }
 
+static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_dev *dev = set->driver_data;
+
+	return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev));
+}
+
 /**
  * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
@@ -503,7 +516,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 		goto out;
 
 	ret = BLK_MQ_RQ_QUEUE_BUSY;
-	if (!dma_map_sg(dev->dev, iod->sg, iod->nents, dma_dir))
+	if (!dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
+				DMA_ATTR_NO_WARN))
 		goto out;
 
 	if (!nvme_setup_prps(dev, req, size))
@@ -880,7 +894,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);
-		queue_work(nvme_workq, &dev->reset_work);
+		nvme_reset(dev);
 
 		/*
 		 * Mark the request as handled, since the inline shutdown
@@ -960,7 +974,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 		spin_unlock_irq(&nvmeq->q_lock);
 		return 1;
 	}
-	vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+	vector = nvmeq_irq(nvmeq);
 	nvmeq->dev->online_queues--;
 	nvmeq->cq_vector = -1;
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -968,7 +982,6 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_stop_hw_queues(nvmeq->dev->ctrl.admin_q);
 
-	irq_set_affinity_hint(vector, NULL);
 	free_irq(vector, nvmeq);
 
 	return 0;
@@ -1075,15 +1088,14 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	return NULL;
 }
 
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
-							const char *name)
+static int queue_request_irq(struct nvme_queue *nvmeq)
 {
 	if (use_threaded_interrupts)
-		return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
-					nvme_irq_check, nvme_irq, IRQF_SHARED,
-					name, nvmeq);
-	return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
-				IRQF_SHARED, name, nvmeq);
+		return request_threaded_irq(nvmeq_irq(nvmeq), nvme_irq_check,
+				nvme_irq, IRQF_SHARED, nvmeq->irqname, nvmeq);
+	else
+		return request_irq(nvmeq_irq(nvmeq), nvme_irq, IRQF_SHARED,
+				nvmeq->irqname, nvmeq);
 }
 
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1114,7 +1126,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	if (result < 0)
 		goto release_cq;
 
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result < 0)
 		goto release_sq;
 
@@ -1131,7 +1143,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 static struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_admin_init_hctx,
 	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_admin_init_request,
@@ -1141,9 +1152,9 @@ static struct blk_mq_ops nvme_mq_admin_ops = {
 static struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_complete_rq,
-	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_init_hctx,
 	.init_request	= nvme_init_request,
+	.map_queues	= nvme_pci_map_queues,
 	.timeout	= nvme_timeout,
 	.poll		= nvme_poll,
 };
@@ -1204,7 +1215,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u64 cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 	struct nvme_queue *nvmeq;
 
-	dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1) ?
+	dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
 						NVME_CAP_NSSRC(cap) : 0;
 
 	if (dev->subsystem &&
@@ -1231,20 +1242,16 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	result = nvme_enable_ctrl(&dev->ctrl, cap);
 	if (result)
-		goto free_nvmeq;
+		return result;
 
 	nvmeq->cq_vector = 0;
-	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
-		goto free_nvmeq;
+		return result;
 	}
 
 	return result;
-
- free_nvmeq:
-	nvme_free_queues(dev, 0);
-	return result;
 }
 
 static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
@@ -1281,7 +1288,7 @@ static void nvme_watchdog_timer(unsigned long data)
 
 	/* Skip controllers under certain specific conditions. */
 	if (nvme_should_reset(dev, csts)) {
-		if (queue_work(nvme_workq, &dev->reset_work))
+		if (!nvme_reset(dev))
 			dev_warn(dev->dev,
 				"Failed status: 0x%x, reset controller.\n",
 				csts);
@@ -1306,10 +1313,8 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	max = min(dev->max_qid, dev->queue_count - 1);
 	for (i = dev->online_queues; i <= max; i++) {
 		ret = nvme_create_queue(dev->queues[i], i);
-		if (ret) {
-			nvme_free_queues(dev, i);
+		if (ret)
 			break;
-		}
 	}
 
 	/*
@@ -1321,28 +1326,37 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	return ret >= 0 ? 0 : ret;
 }
 
+static ssize_t nvme_cmb_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+	return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+		       ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
+
 static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 {
 	u64 szu, size, offset;
-	u32 cmbloc;
 	resource_size_t bar_size;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	void __iomem *cmb;
 	dma_addr_t dma_addr;
 
-	if (!use_cmb_sqes)
-		return NULL;
-
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!(NVME_CMB_SZ(dev->cmbsz)))
 		return NULL;
+	dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
 
-	cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+	if (!use_cmb_sqes)
+		return NULL;
 
 	szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
 	size = szu * NVME_CMB_SZ(dev->cmbsz);
-	offset = szu * NVME_CMB_OFST(cmbloc);
-	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+	offset = szu * NVME_CMB_OFST(dev->cmbloc);
+	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
 
 	if (offset > bar_size)
 		return NULL;
@@ -1355,7 +1369,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
 	cmb = ioremap_wc(dma_addr, size);
 	if (!cmb)
 		return NULL;
@@ -1382,7 +1396,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = dev->queues[0];
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int result, i, vecs, nr_io_queues, size;
+	int result, nr_io_queues, size;
 
 	nr_io_queues = num_online_cpus();
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
@@ -1417,29 +1431,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	}
 
 	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, adminq);
+	free_irq(pci_irq_vector(pdev, 0), adminq);
 
 	/*
 	 * If we enable msix early due to not intx, disable it again before
 	 * setting up the full range we need.
 	 */
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
-
-	for (i = 0; i < nr_io_queues; i++)
-		dev->entry[i].entry = i;
-	vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
-	if (vecs < 0) {
-		vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
-		if (vecs < 0) {
-			vecs = 1;
-		} else {
-			for (i = 0; i < vecs; i++)
-				dev->entry[i].vector = i + pdev->irq;
-		}
-	}
+	pci_free_irq_vectors(pdev);
+	nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
+	if (nr_io_queues <= 0)
+		return -EIO;
+	dev->max_qid = nr_io_queues;
 
 	/*
 	 * Should investigate if there's a performance win from allocating
@@ -1447,36 +1450,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * path to scale better, even if the receive path is limited by the
 	 * number of interrupts.
 	 */
-	nr_io_queues = vecs;
-	dev->max_qid = nr_io_queues;
 
-	result = queue_request_irq(dev, adminq, adminq->irqname);
+	result = queue_request_irq(adminq);
 	if (result) {
 		adminq->cq_vector = -1;
-		goto free_queues;
+		return result;
 	}
 	return nvme_create_io_queues(dev);
-
- free_queues:
-	nvme_free_queues(dev, 1);
-	return result;
-}
-
-static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
-{
-	struct nvme_dev *dev = to_nvme_dev(ctrl);
-	struct nvme_queue *nvmeq;
-	int i;
-
-	for (i = 0; i < dev->online_queues; i++) {
-		nvmeq = dev->queues[i];
-
-		if (!nvmeq->tags || !(*nvmeq->tags))
-			continue;
-
-		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-					blk_mq_tags_cpumask(*nvmeq->tags));
-	}
 }
 
 static void nvme_del_queue_end(struct request *req, int error)
@@ -1531,9 +1511,9 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	return 0;
 }
 
-static void nvme_disable_io_queues(struct nvme_dev *dev)
+static void nvme_disable_io_queues(struct nvme_dev *dev, int queues)
 {
-	int pass, queues = dev->online_queues - 1;
+	int pass;
 	unsigned long timeout;
 	u8 opcode = nvme_admin_delete_sq;
 
@@ -1615,15 +1595,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
 	 * adjust this later.
 	 */
-	if (pci_enable_msix(pdev, dev->entry, 1)) {
-		pci_enable_msi(pdev);
-		dev->entry[0].vector = pdev->irq;
-	}
-
-	if (!dev->entry[0].vector) {
-		result = -ENODEV;
-		goto disable;
-	}
+	result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (result < 0)
+		return result;
 
 	cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
@@ -1642,9 +1616,25 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 			dev->q_depth);
 	}
 
-	if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2))
+	/*
+	 * CMBs can currently only exist on >=1.2 PCIe devices. We only
+	 * populate sysfs if a CMB is implemented. Note that we add the
+	 * CMB attribute to the nvme_ctrl kobj which removes the need to remove
+	 * it on exit. Since nvme_dev_attrs_group has no name we can pass
+	 * NULL as final argument to sysfs_add_file_to_group.
+	 */
+
+	if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) {
 		dev->cmb = nvme_map_cmb(dev);
 
+		if (dev->cmbsz) {
+			if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
+						    &dev_attr_cmb.attr, NULL))
+				dev_warn(dev->dev,
+					 "failed to add sysfs attribute for CMB\n");
+		}
+	}
+
 	pci_enable_pcie_error_reporting(pdev);
 	pci_save_state(pdev);
 	return 0;
@@ -1665,10 +1655,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	if (pdev->msi_enabled)
-		pci_disable_msi(pdev);
-	else if (pdev->msix_enabled)
-		pci_disable_msix(pdev);
+	pci_free_irq_vectors(pdev);
 
 	if (pci_is_enabled(pdev)) {
 		pci_disable_pcie_error_reporting(pdev);
@@ -1678,7 +1665,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
-	int i;
+	int i, queues;
 	u32 csts = -1;
 
 	del_timer_sync(&dev->watchdog_timer);
@@ -1689,6 +1676,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 		csts = readl(dev->bar + NVME_REG_CSTS);
 	}
 
+	queues = dev->online_queues - 1;
 	for (i = dev->queue_count - 1; i > 0; i--)
 		nvme_suspend_queue(dev->queues[i]);
 
@@ -1700,7 +1688,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 		if (dev->queue_count)
 			nvme_suspend_queue(dev->queues[0]);
 	} else {
-		nvme_disable_io_queues(dev);
+		nvme_disable_io_queues(dev, queues);
 		nvme_disable_admin_queue(dev, shutdown);
 	}
 	nvme_pci_disable(dev);
@@ -1743,7 +1731,6 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 }
 
@@ -1848,11 +1835,10 @@ static int nvme_reset(struct nvme_dev *dev)
 {
 	if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
 		return -ENODEV;
-
+	if (work_busy(&dev->reset_work))
+		return -ENODEV;
 	if (!queue_work(nvme_workq, &dev->reset_work))
 		return -EBUSY;
-
-	flush_work(&dev->reset_work);
 	return 0;
 }
 
@@ -1876,7 +1862,12 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 
 static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 {
-	return nvme_reset(to_nvme_dev(ctrl));
+	struct nvme_dev *dev = to_nvme_dev(ctrl);
+	int ret = nvme_reset(dev);
+
+	if (!ret)
+		flush_work(&dev->reset_work);
+	return ret;
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
@@ -1887,7 +1878,6 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.reg_read64		= nvme_pci_reg_read64,
 	.reset_ctrl		= nvme_pci_reset_ctrl,
 	.free_ctrl		= nvme_pci_free_ctrl,
-	.post_scan		= nvme_pci_post_scan,
 	.submit_async_event	= nvme_pci_submit_async_event,
 };
 
@@ -1920,10 +1910,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
 		return -ENOMEM;
-	dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
-							GFP_KERNEL, node);
-	if (!dev->entry)
-		goto free;
 	dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
 							GFP_KERNEL, node);
 	if (!dev->queues)
@@ -1964,7 +1950,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_dev_unmap(dev);
  free:
 	kfree(dev->queues);
-	kfree(dev->entry);
 	kfree(dev);
 	return result;
 }
@@ -1976,7 +1961,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
 	if (prepare)
 		nvme_dev_disable(dev, false);
 	else
-		queue_work(nvme_workq, &dev->reset_work);
+		nvme_reset(dev);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
@@ -2045,7 +2030,7 @@ static int nvme_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-	queue_work(nvme_workq, &ndev->reset_work);
+	nvme_reset(ndev);
 	return 0;
 }
 #endif
@@ -2084,7 +2069,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	queue_work(nvme_workq, &dev->reset_work);
+	nvme_reset(dev);
 	return PCI_ERS_RESULT_RECOVERED;
 }