1 files changed, 75 insertions, 60 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0808f9eb8ab..365a2ddbeaa7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -68,14 +68,14 @@ static int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 
-static int write_queues;
-module_param(write_queues, int, 0644);
+static unsigned int write_queues;
+module_param(write_queues, uint, 0644);
 MODULE_PARM_DESC(write_queues,
 	"Number of queues to use for writes. If not set, reads and writes "
 	"will share a queue set.");
 
-static int poll_queues;
-module_param(poll_queues, int, 0644);
+static unsigned int poll_queues;
+module_param(poll_queues, uint, 0644);
 MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");
 
 struct nvme_dev;
@@ -176,7 +176,6 @@ struct nvme_queue {
 	u16 sq_tail;
 	u16 last_sq_tail;
 	u16 cq_head;
-	u16 last_cq_head;
 	u16 qid;
 	u8 cq_phase;
 	u8 sqes;
@@ -773,7 +772,8 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
 		struct bio_vec *bv)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset;
+	unsigned int offset = bv->bv_offset & (dev->ctrl.page_size - 1);
+	unsigned int first_prp_len = dev->ctrl.page_size - offset;
 
 	iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
 	if (dma_mapping_error(dev->dev, iod->first_dma))
@@ -924,7 +924,6 @@ static void nvme_pci_complete_rq(struct request *req)
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_dev *dev = iod->nvmeq->dev;
 
-	nvme_cleanup_cmd(req);
 	if (blk_integrity_rq(req))
 		dma_unmap_page(dev->dev, iod->meta_dma,
 			       rq_integrity_vec(req)->bv_len, rq_data_dir(req));
@@ -967,8 +966,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvmeq->qid == 0 &&
-			cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) {
+	if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) {
 		nvme_complete_async_event(&nvmeq->dev->ctrl,
 				cqe->status, &cqe->result);
 		return;
@@ -1027,10 +1025,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 	 * the irq handler, even if that was on another CPU.
 	 */
 	rmb();
-	if (nvmeq->cq_head != nvmeq->last_cq_head)
-		ret = IRQ_HANDLED;
 	nvme_process_cq(nvmeq, &start, &end, -1);
-	nvmeq->last_cq_head = nvmeq->cq_head;
 	wmb();
 
 	if (start != end) {
@@ -1550,7 +1545,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
 		return result;
-	else if (result)
+	if (result)
 		goto release_cq;
 
 	nvmeq->cq_vector = vector;
@@ -2059,7 +2054,6 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.priv		= dev,
 	};
 	unsigned int irq_queues, this_p_queues;
-	unsigned int nr_cpus = num_possible_cpus();
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one IO
@@ -2070,10 +2064,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		this_p_queues = nr_io_queues - 1;
 		irq_queues = 1;
 	} else {
-		if (nr_cpus < nr_io_queues - this_p_queues)
-			irq_queues = nr_cpus + 1;
-		else
-			irq_queues = nr_io_queues - this_p_queues + 1;
+		irq_queues = nr_io_queues - this_p_queues + 1;
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
@@ -2263,10 +2254,7 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 	return true;
 }
 
-/*
- * return error value only when tagset allocation failed
- */
-static int nvme_dev_add(struct nvme_dev *dev)
+static void nvme_dev_add(struct nvme_dev *dev)
 {
 	int ret;
 
@@ -2296,7 +2284,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		if (ret) {
 			dev_warn(dev->ctrl.device,
 				"IO queues tagset allocation failed %d\n", ret);
-			return ret;
+			return;
 		}
 		dev->ctrl.tagset = &dev->tagset;
 	} else {
@@ -2307,7 +2295,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	}
 
 	nvme_dbbuf_set(dev);
-	return 0;
 }
 
 static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2467,6 +2454,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	mutex_unlock(&dev->shutdown_lock);
 }
 
+static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
+{
+	if (!nvme_wait_reset(&dev->ctrl))
+		return -EBUSY;
+	nvme_dev_disable(dev, shutdown);
+	return 0;
+}
+
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
@@ -2490,14 +2485,20 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
 	dma_pool_destroy(dev->prp_small_pool);
 }
 
+static void nvme_free_tagset(struct nvme_dev *dev)
+{
+	if (dev->tagset.tags)
+		blk_mq_free_tag_set(&dev->tagset);
+	dev->ctrl.tagset = NULL;
+}
+
 static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
 
 	nvme_dbbuf_dma_free(dev);
 	put_device(dev->dev);
-	if (dev->tagset.tags)
-		blk_mq_free_tag_set(&dev->tagset);
+	nvme_free_tagset(dev);
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
@@ -2508,6 +2509,11 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 
 static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
 {
+	/*
+	 * Set state to deleting now to avoid blocking nvme_wait_reset(), which
+	 * may be holding this pci_dev's device lock.
+	 */
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 	nvme_get_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, false);
 	nvme_kill_queues(&dev->ctrl);
@@ -2521,7 +2527,6 @@ static void nvme_reset_work(struct work_struct *work)
 		container_of(work, struct nvme_dev, ctrl.reset_work);
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
-	enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;
 
 	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
 		result = -ENODEV;
@@ -2615,13 +2620,11 @@ static void nvme_reset_work(struct work_struct *work)
 		dev_warn(dev->ctrl.device, "IO queues not created\n");
 		nvme_kill_queues(&dev->ctrl);
 		nvme_remove_namespaces(&dev->ctrl);
-		new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_free_tagset(dev);
 	} else {
 		nvme_start_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
-		/* hit this only when allocate tagset fails */
-		if (nvme_dev_add(dev))
-			new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_dev_add(dev);
 		nvme_unfreeze(&dev->ctrl);
 	}
 
@@ -2629,9 +2632,9 @@ static void nvme_reset_work(struct work_struct *work)
 	 * If only admin queue live, keep it to do further investigation or
 	 * recovery.
 	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
 		dev_warn(dev->ctrl.device,
-			"failed to mark controller state %d\n", new_state);
+			"failed to mark controller live state\n");
 		result = -ENODEV;
 		goto out;
 	}
@@ -2672,7 +2675,7 @@ static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 
 static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 {
-	*val = readq(to_nvme_dev(ctrl)->bar + off);
+	*val = lo_hi_readq(to_nvme_dev(ctrl)->bar + off);
 	return 0;
 }
 
@@ -2836,19 +2839,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void nvme_reset_prepare(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, false);
+
+	/*
+	 * We don't need to check the return value from waiting for the reset
+	 * state as pci_dev device lock is held, making it impossible to race
+	 * with ->remove().
+	 */
+	nvme_disable_prepare_reset(dev, false);
+	nvme_sync_queues(&dev->ctrl);
 }
 
 static void nvme_reset_done(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_reset_ctrl_sync(&dev->ctrl);
+
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		flush_work(&dev->ctrl.reset_work);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, true);
+	nvme_disable_prepare_reset(dev, true);
 }
 
 /*
@@ -2901,7 +2913,7 @@ static int nvme_resume(struct device *dev)
 
 	if (ndev->last_ps == U32_MAX ||
 	    nvme_set_power_state(ctrl, ndev->last_ps) != 0)
-		nvme_reset_ctrl(ctrl);
+		return nvme_try_sched_reset(&ndev->ctrl);
 	return 0;
 }
 
@@ -2929,43 +2941,42 @@ static int nvme_suspend(struct device *dev)
 	 */
 	if (pm_suspend_via_firmware() || !ctrl->npss ||
 	    !pcie_aspm_enabled(pdev) ||
-	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) {
-		nvme_dev_disable(ndev, true);
-		return 0;
-	}
+	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
+		return nvme_disable_prepare_reset(ndev, true);
 
 	nvme_start_freeze(ctrl);
 	nvme_wait_freeze(ctrl);
 	nvme_sync_queues(ctrl);
 
-	if (ctrl->state != NVME_CTRL_LIVE &&
-	    ctrl->state != NVME_CTRL_ADMIN_ONLY)
+	if (ctrl->state != NVME_CTRL_LIVE)
 		goto unfreeze;
 
 	ret = nvme_get_power_state(ctrl, &ndev->last_ps);
 	if (ret < 0)
 		goto unfreeze;
 
+	/*
+	 * A saved state prevents pci pm from generically controlling the
+	 * device's power. If we're using protocol specific settings, we don't
+	 * want pci interfering.
+	 */
+	pci_save_state(pdev);
+
 	ret = nvme_set_power_state(ctrl, ctrl->npss);
 	if (ret < 0)
 		goto unfreeze;
 
 	if (ret) {
+		/* discard the saved state */
+		pci_load_saved_state(pdev, NULL);
+
 		/*
 		 * Clearing npss forces a controller reset on resume. The
-		 * correct value will be resdicovered then.
+		 * correct value will be rediscovered then.
 		 */
-		nvme_dev_disable(ndev, true);
+		ret = nvme_disable_prepare_reset(ndev, true);
 		ctrl->npss = 0;
-		ret = 0;
-		goto unfreeze;
 	}
-	/*
-	 * A saved state prevents pci pm from generically controlling the
-	 * device's power. If we're using protocol specific settings, we don't
-	 * want pci interfering.
-	 */
-	pci_save_state(pdev);
 unfreeze:
 	nvme_unfreeze(ctrl);
 	return ret;
@@ -2974,9 +2985,7 @@ unfreeze:
 static int nvme_simple_suspend(struct device *dev)
 {
 	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
-
-	nvme_dev_disable(ndev, true);
-	return 0;
+	return nvme_disable_prepare_reset(ndev, true);
 }
 
 static int nvme_simple_resume(struct device *dev)
@@ -2984,8 +2993,7 @@ static int nvme_simple_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-	nvme_reset_ctrl(&ndev->ctrl);
-	return 0;
+	return nvme_try_sched_reset(&ndev->ctrl);
 }
 
 static const struct dev_pm_ops nvme_dev_pm_ops = {
@@ -3064,7 +3072,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
-				NVME_QUIRK_MEDIUM_PRIO_SQ },
+				NVME_QUIRK_MEDIUM_PRIO_SQ |
+				NVME_QUIRK_NO_TEMP_THRESH_CHANGE },
 	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
@@ -3090,6 +3099,9 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
@@ -3122,6 +3134,9 @@ static int __init nvme_init(void)
 	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
 	BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2);
+
+	write_queues = min(write_queues, num_possible_cpus());
+	poll_queues = min(poll_queues, num_possible_cpus());
 	return pci_register_driver(&nvme_driver);
 }