1 files changed, 113 insertions, 68 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5e52034ab010..26a5fd05fe88 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -43,6 +43,7 @@
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/unaligned.h>
+#include <linux/sed-opal.h>
 
 #include "nvme.h"
 
@@ -50,7 +51,7 @@
 #define NVME_AQ_DEPTH		256
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
-		
+
 /*
  * We handle AEN commands ourselves and don't even let the
  * block layer know about them.
@@ -141,6 +142,7 @@ struct nvme_queue {
  * allocated to store the PRP list.
  */
 struct nvme_iod {
+	struct nvme_request req;
 	struct nvme_queue *nvmeq;
 	int aborted;
 	int npages;		/* In the PRP list. 0 means small pool in use */
@@ -302,14 +304,14 @@ static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
 static __le64 **iod_list(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	return (__le64 **)(iod->sg + req->nr_phys_segments);
+	return (__le64 **)(iod->sg + blk_rq_nr_phys_segments(req));
 }
 
-static int nvme_init_iod(struct request *rq, unsigned size,
-		struct nvme_dev *dev)
+static int nvme_init_iod(struct request *rq, struct nvme_dev *dev)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(rq);
-	int nseg = rq->nr_phys_segments;
+	int nseg = blk_rq_nr_phys_segments(rq);
+	unsigned int size = blk_rq_payload_bytes(rq);
 
 	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
 		iod->sg = kmalloc(nvme_iod_alloc_size(dev, size, nseg), GFP_ATOMIC);
@@ -324,11 +326,11 @@ static int nvme_init_iod(struct request *rq, unsigned size,
 	iod->nents = 0;
 	iod->length = size;
 
-	if (!(rq->cmd_flags & REQ_DONTPREP)) {
+	if (!(rq->rq_flags & RQF_DONTPREP)) {
 		rq->retries = 0;
-		rq->cmd_flags |= REQ_DONTPREP;
+		rq->rq_flags |= RQF_DONTPREP;
 	}
-	return 0;
+	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
@@ -339,8 +341,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 	__le64 **list = iod_list(req);
 	dma_addr_t prp_dma = iod->first_dma;
 
-	nvme_cleanup_cmd(req);
-
 	if (iod->npages == 0)
 		dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
 	for (i = 0; i < iod->npages; i++) {
@@ -421,12 +421,11 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
 }
 #endif
 
-static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req,
-		int total_len)
+static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct dma_pool *pool;
-	int length = total_len;
+	int length = blk_rq_payload_bytes(req);
 	struct scatterlist *sg = iod->sg;
 	int dma_len = sg_dma_len(sg);
 	u64 dma_addr = sg_dma_address(sg);
@@ -502,7 +501,7 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req,
 }
 
 static int nvme_map_data(struct nvme_dev *dev, struct request *req,
-		unsigned size, struct nvme_command *cmnd)
+		struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct request_queue *q = req->q;
@@ -510,7 +509,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 			DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	int ret = BLK_MQ_RQ_QUEUE_ERROR;
 
-	sg_init_table(iod->sg, req->nr_phys_segments);
+	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
 	iod->nents = blk_rq_map_sg(q, req, iod->sg);
 	if (!iod->nents)
 		goto out;
@@ -520,7 +519,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
 				DMA_ATTR_NO_WARN))
 		goto out;
 
-	if (!nvme_setup_prps(dev, req, size))
+	if (!nvme_setup_prps(dev, req))
 		goto out_unmap;
 
 	ret = BLK_MQ_RQ_QUEUE_ERROR;
@@ -566,6 +565,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 		}
 	}
 
+	nvme_cleanup_cmd(req);
 	nvme_free_iod(dev, req);
 }
 
@@ -580,7 +580,6 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *req = bd->rq;
 	struct nvme_command cmnd;
-	unsigned map_len;
 	int ret = BLK_MQ_RQ_QUEUE_OK;
 
 	/*
@@ -590,45 +589,42 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (ns && ns->ms && !blk_integrity_rq(req)) {
 		if (!(ns->pi_type && ns->ms == 8) &&
-					req->cmd_type != REQ_TYPE_DRV_PRIV) {
+		    !blk_rq_is_passthrough(req)) {
 			blk_mq_end_request(req, -EFAULT);
 			return BLK_MQ_RQ_QUEUE_OK;
 		}
 	}
 
-	map_len = nvme_map_len(req);
-	ret = nvme_init_iod(req, map_len, dev);
-	if (ret)
+	ret = nvme_setup_cmd(ns, req, &cmnd);
+	if (ret != BLK_MQ_RQ_QUEUE_OK)
 		return ret;
 
-	ret = nvme_setup_cmd(ns, req, &cmnd);
-	if (ret)
-		goto out;
+	ret = nvme_init_iod(req, dev);
+	if (ret != BLK_MQ_RQ_QUEUE_OK)
+		goto out_free_cmd;
 
-	if (req->nr_phys_segments)
-		ret = nvme_map_data(dev, req, map_len, &cmnd);
+	if (blk_rq_nr_phys_segments(req))
+		ret = nvme_map_data(dev, req, &cmnd);
 
-	if (ret)
-		goto out;
+	if (ret != BLK_MQ_RQ_QUEUE_OK)
+		goto out_cleanup_iod;
 
-	cmnd.common.command_id = req->tag;
 	blk_mq_start_request(req);
 
 	spin_lock_irq(&nvmeq->q_lock);
 	if (unlikely(nvmeq->cq_vector < 0)) {
-		if (ns && !test_bit(NVME_NS_DEAD, &ns->flags))
-			ret = BLK_MQ_RQ_QUEUE_BUSY;
-		else
-			ret = BLK_MQ_RQ_QUEUE_ERROR;
+		ret = BLK_MQ_RQ_QUEUE_ERROR;
 		spin_unlock_irq(&nvmeq->q_lock);
-		goto out;
+		goto out_cleanup_iod;
 	}
 	__nvme_submit_cmd(nvmeq, &cmnd);
 	nvme_process_cq(nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
 	return BLK_MQ_RQ_QUEUE_OK;
-out:
+out_cleanup_iod:
 	nvme_free_iod(dev, req);
+out_free_cmd:
+	nvme_cleanup_cmd(req);
 	return ret;
 }
 
@@ -647,7 +643,7 @@ static void nvme_complete_rq(struct request *req)
 			return;
 		}
 
-		if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		if (blk_rq_is_passthrough(req))
 			error = req->errors;
 		else
 			error = nvme_error_status(req->errors);
@@ -703,23 +699,16 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
 		 */
 		if (unlikely(nvmeq->qid == 0 &&
 				cqe.command_id >= NVME_AQ_BLKMQ_DEPTH)) {
-			nvme_complete_async_event(&nvmeq->dev->ctrl, &cqe);
+			nvme_complete_async_event(&nvmeq->dev->ctrl,
+					cqe.status, &cqe.result);
 			continue;
 		}
 
 		req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id);
-		if (req->cmd_type == REQ_TYPE_DRV_PRIV && req->special)
-			memcpy(req->special, &cqe, sizeof(cqe));
+		nvme_req(req)->result = cqe.result;
 		blk_mq_complete_request(req, le16_to_cpu(cqe.status) >> 1);
-
 	}
 
-	/* If the controller ignores the cq head doorbell and continuously
-	 * writes to the queue, it is theoretically possible to wrap around
-	 * the queue twice and mistakenly return IRQ_NONE.  Linux only
-	 * requires that 0.1% of your interrupts are handled, so this isn't
-	 * a big problem.
-	 */
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
 		return;
 
@@ -904,12 +893,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		return BLK_EH_HANDLED;
 	}
 
-	iod->aborted = 1;
-
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
+	iod->aborted = 1;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
@@ -1050,9 +1038,10 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
-							int depth)
+							int depth, int node)
 {
-	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
+	struct nvme_queue *nvmeq = kzalloc_node(sizeof(*nvmeq), GFP_KERNEL,
+							node);
 	if (!nvmeq)
 		return NULL;
 
@@ -1187,6 +1176,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1228,7 +1218,8 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH,
+					dev_to_node(dev->dev));
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1281,6 +1272,24 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	return true;
 }
 
+static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
+{
+	/* Read a config register to help see what died. */
+	u16 pci_status;
+	int result;
+
+	result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
+				      &pci_status);
+	if (result == PCIBIOS_SUCCESSFUL)
+		dev_warn(dev->dev,
+			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
+			 csts, pci_status);
+	else
+		dev_warn(dev->dev,
+			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
+			 csts, result);
+}
+
 static void nvme_watchdog_timer(unsigned long data)
 {
 	struct nvme_dev *dev = (struct nvme_dev *)data;
@@ -1289,9 +1298,7 @@ static void nvme_watchdog_timer(unsigned long data)
 	/* Skip controllers under certain specific conditions. */
 	if (nvme_should_reset(dev, csts)) {
 		if (!nvme_reset(dev))
-			dev_warn(dev->dev,
-				"Failed status: 0x%x, reset controller.\n",
-				csts);
+			nvme_warn_reset(dev, csts);
 		return;
 	}
 
@@ -1304,7 +1311,9 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	int ret = 0;
 
 	for (i = dev->queue_count; i <= dev->max_qid; i++) {
-		if (!nvme_alloc_queue(dev, i, dev->q_depth)) {
+		/* vector == qid - 1, match nvme_create_queue */
+		if (!nvme_alloc_queue(dev, i, dev->q_depth,
+		     pci_irq_get_node(to_pci_dev(dev->dev), i - 1))) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -1332,7 +1341,7 @@ static ssize_t nvme_cmb_show(struct device *dev,
 {
 	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
 
-	return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+	return scnprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
 		       ndev->cmbloc, ndev->cmbsz);
 }
 static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
@@ -1666,21 +1675,34 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
 	int i, queues;
-	u32 csts = -1;
+	bool dead = true;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	del_timer_sync(&dev->watchdog_timer);
 
 	mutex_lock(&dev->shutdown_lock);
-	if (pci_is_enabled(to_pci_dev(dev->dev))) {
-		nvme_stop_queues(&dev->ctrl);
-		csts = readl(dev->bar + NVME_REG_CSTS);
+	if (pci_is_enabled(pdev)) {
+		u32 csts = readl(dev->bar + NVME_REG_CSTS);
+
+		if (dev->ctrl.state == NVME_CTRL_LIVE)
+			nvme_start_freeze(&dev->ctrl);
+		dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
+			pdev->error_state  != pci_channel_io_normal);
 	}
 
+	/*
+	 * Give the controller a chance to complete all entered requests if
+	 * doing a safe shutdown.
+	 */
+	if (!dead && shutdown)
+		nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
+	nvme_stop_queues(&dev->ctrl);
+
 	queues = dev->online_queues - 1;
 	for (i = dev->queue_count - 1; i > 0; i--)
 		nvme_suspend_queue(dev->queues[i]);
 
-	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
+	if (dead) {
 		/* A device might become IO incapable very soon during
 		 * probe, before the admin queue is configured. Thus,
 		 * queue_count can be 0 here.
@@ -1695,6 +1717,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 
 	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);
+
+	/*
+	 * The driver will not be starting up queues again if shutting down so
+	 * must flush all entered requests to their failed completion to avoid
+	 * deadlocking blk-mq hot-cpu notifier.
+	 */
+	if (shutdown)
+		nvme_start_queues(&dev->ctrl);
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -1731,6 +1761,7 @@ 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);
+	free_opal_dev(dev->ctrl.opal_dev);
 	kfree(dev);
 }
 
@@ -1747,6 +1778,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
 static void nvme_reset_work(struct work_struct *work)
 {
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
+	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result = -ENODEV;
 
 	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
@@ -1779,6 +1811,17 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
+	if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) {
+		if (!dev->ctrl.opal_dev)
+			dev->ctrl.opal_dev =
+				init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+		else if (was_suspend)
+			opal_unlock_from_suspend(dev->ctrl.opal_dev);
+	} else {
+		free_opal_dev(dev->ctrl.opal_dev);
+		dev->ctrl.opal_dev = NULL;
+	}
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;
@@ -1804,7 +1847,9 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_remove_namespaces(&dev->ctrl);
 	} else {
 		nvme_start_queues(&dev->ctrl);
+		nvme_wait_freeze(&dev->ctrl);
 		nvme_dev_add(dev);
+		nvme_unfreeze(&dev->ctrl);
 	}
 
 	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
@@ -1892,10 +1937,10 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	if (!dev->bar)
 		goto release;
 
-       return 0;
+	return 0;
   release:
-       pci_release_mem_regions(pdev);
-       return -ENODEV;
+	pci_release_mem_regions(pdev);
+	return -ENODEV;
 }
 
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -1983,8 +2028,10 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 
-	if (!pci_device_is_present(pdev))
+	if (!pci_device_is_present(pdev)) {
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
+		nvme_dev_disable(dev, false);
+	}
 
 	flush_work(&dev->reset_work);
 	nvme_uninit_ctrl(&dev->ctrl);
@@ -2085,9 +2132,6 @@ static const struct pci_error_handlers nvme_err_handler = {
 	.reset_notify	= nvme_reset_notify,
 };
 
-/* Move to pci_ids.h later */
-#define PCI_CLASS_STORAGE_EXPRESS	0x010802
-
 static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0953),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
@@ -2106,6 +2150,7 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);