Merge branch 'nvme-4.18' of git://git.infradead.org/nvme into for-4.18/block

Pull NVMe changes from Keith:

"This is just the first nvme pull request for 4.18. There are several
fabrics and target patches that I missed, so there will be more to
come."

* 'nvme-4.18' of git://git.infradead.org/nvme:
  nvme-pci: drop IRQ disabling on submission queue lock
  nvme-pci: split the nvme queue lock into submission and completion locks
  nvme-pci: handle completions outside of the queue lock
  nvme-pci: move ->cq_vector == -1 check outside of ->q_lock
  nvme-pci: remove cq check after submission
  nvme-pci: simplify nvme_cqe_valid
  nvme: mark the result argument to nvme_complete_async_event volatile
  nvme/pci: Sync controller reset for AER slot_reset
  nvme/pci: Hold controller reference during async probe
  nvme: only reconfigure discard if necessary
  nvme/pci: Use async_schedule for initial reset work
  nvme: lightnvm: add granby support
  NVMe: Add Quirk Delay before CHK RDY for Seagate Nytro Flash Storage
  nvme: change order of qid and cmdid in completion trace
  nvme: fc: provide a descriptive error

drivers/nvme/host/core.c

@@ -1348,13 +1348,19 @@ static void nvme_set_chunk_size(struct nvme_ns *ns)
 	blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
 }
 
-static void nvme_config_discard(struct nvme_ctrl *ctrl,
-		unsigned stream_alignment, struct request_queue *queue)
+static void nvme_config_discard(struct nvme_ns *ns)
 {
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	struct request_queue *queue = ns->queue;
 	u32 size = queue_logical_block_size(queue);
 
-	if (stream_alignment)
-		size *= stream_alignment;
+	if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+		return;
+	}
+
+	if (ctrl->nr_streams && ns->sws && ns->sgs)
+		size *= ns->sws * ns->sgs;
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
@@ -1362,9 +1368,12 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl,
 	queue->limits.discard_alignment = 0;
 	queue->limits.discard_granularity = size;
 
+	/* If discard is already enabled, don't reset queue limits */
+	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+		return;
+
 	blk_queue_max_discard_sectors(queue, UINT_MAX);
 	blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);
 
 	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
@@ -1408,10 +1417,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
-	unsigned stream_alignment = 0;
-
-	if (ns->ctrl->nr_streams && ns->sws && ns->sgs)
-		stream_alignment = ns->sws * ns->sgs;
 
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
@@ -1425,10 +1430,9 @@ static void nvme_update_disk_info(struct gendisk *disk,
 		nvme_init_integrity(disk, ns->ms, ns->pi_type);
 	if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk))
 		capacity = 0;
-	set_capacity(disk, capacity);
 
-	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
-		nvme_config_discard(ns->ctrl, stream_alignment, disk->queue);
+	set_capacity(disk, capacity);
+	nvme_config_discard(ns);
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
@@ -3317,7 +3321,7 @@ static void nvme_fw_act_work(struct work_struct *work)
 }
 
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
-		union nvme_result *res)
+		volatile union nvme_result *res)
 {
 	u32 result = le32_to_cpu(res->u32);
 

drivers/nvme/host/fc.c

@@ -3284,6 +3284,8 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 	}
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
+	pr_warn("%s: %s - %s combination not found\n",
+		__func__, opts->traddr, opts->host_traddr);
 	return ERR_PTR(-ENOENT);
 }
 

drivers/nvme/host/nvme.h

@@ -400,7 +400,7 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 		bool send);
 
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
-		union nvme_result *res);
+		volatile union nvme_result *res);
 
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);

drivers/nvme/host/pci.c

@@ -13,6 +13,7 @@
  */
 
 #include <linux/aer.h>
+#include <linux/async.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-mq-pci.h>
@@ -68,7 +69,6 @@ MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 struct nvme_dev;
 struct nvme_queue;
 
-static void nvme_process_cq(struct nvme_queue *nvmeq);
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
 
 /*
@@ -147,9 +147,10 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
 struct nvme_queue {
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
-	spinlock_t q_lock;
+	spinlock_t sq_lock;
 	struct nvme_command *sq_cmds;
 	struct nvme_command __iomem *sq_cmds_io;
+	spinlock_t cq_lock ____cacheline_aligned_in_smp;
 	volatile struct nvme_completion *cqes;
 	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
@@ -161,7 +162,6 @@ struct nvme_queue {
 	u16 cq_head;
 	u16 qid;
 	u8 cq_phase;
-	u8 cqe_seen;
 	u32 *dbbuf_sq_db;
 	u32 *dbbuf_cq_db;
 	u32 *dbbuf_sq_ei;
@@ -872,6 +872,13 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct nvme_command cmnd;
 	blk_status_t ret;
 
+	/*
+	 * We should not need to do this, but we're still using this to
+	 * ensure we can drain requests on a dying queue.
+	 */
+	if (unlikely(nvmeq->cq_vector < 0))
+		return BLK_STS_IOERR;
+
 	ret = nvme_setup_cmd(ns, req, &cmnd);
 	if (ret)
 		return ret;
@@ -888,15 +895,9 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(req);
 
-	spin_lock_irq(&nvmeq->q_lock);
-	if (unlikely(nvmeq->cq_vector < 0)) {
-		ret = BLK_STS_IOERR;
-		spin_unlock_irq(&nvmeq->q_lock);
-		goto out_cleanup_iod;
-	}
+	spin_lock(&nvmeq->sq_lock);
 	__nvme_submit_cmd(nvmeq, &cmnd);
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock(&nvmeq->sq_lock);
 	return BLK_STS_OK;
 out_cleanup_iod:
 	nvme_free_iod(dev, req);
@@ -914,10 +915,10 @@ static void nvme_pci_complete_rq(struct request *req)
 }
 
 /* We read the CQE phase first to check if the rest of the entry is valid */
-static inline bool nvme_cqe_valid(struct nvme_queue *nvmeq, u16 head,
-		u16 phase)
+static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
 {
-	return (le16_to_cpu(nvmeq->cqes[head].status) & 1) == phase;
+	return (le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) ==
+			nvmeq->cq_phase;
 }
 
 static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
@@ -931,9 +932,9 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
 	}
 }
 
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
-		struct nvme_completion *cqe)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
+	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
 	struct request *req;
 
 	if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
@@ -956,83 +957,81 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
 		return;
 	}
 
-	nvmeq->cqe_seen = 1;
 	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
 	nvme_end_request(req, cqe->status, cqe->result);
 }
 
-static inline bool nvme_read_cqe(struct nvme_queue *nvmeq,
-		struct nvme_completion *cqe)
+static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
 {
-	if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
-		*cqe = nvmeq->cqes[nvmeq->cq_head];
+	while (start != end) {
+		nvme_handle_cqe(nvmeq, start);
+		if (++start == nvmeq->q_depth)
+			start = 0;
+	}
+}
 
-		if (++nvmeq->cq_head == nvmeq->q_depth) {
-			nvmeq->cq_head = 0;
-			nvmeq->cq_phase = !nvmeq->cq_phase;
-		}
-		return true;
+static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
+{
+	if (++nvmeq->cq_head == nvmeq->q_depth) {
+		nvmeq->cq_head = 0;
+		nvmeq->cq_phase = !nvmeq->cq_phase;
 	}
-	return false;
 }
 
-static void nvme_process_cq(struct nvme_queue *nvmeq)
+static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
+		u16 *end, int tag)
 {
-	struct nvme_completion cqe;
-	int consumed = 0;
+	bool found = false;
 
-	while (nvme_read_cqe(nvmeq, &cqe)) {
-		nvme_handle_cqe(nvmeq, &cqe);
-		consumed++;
+	*start = nvmeq->cq_head;
+	while (!found && nvme_cqe_pending(nvmeq)) {
+		if (nvmeq->cqes[nvmeq->cq_head].command_id == tag)
+			found = true;
+		nvme_update_cq_head(nvmeq);
 	}
+	*end = nvmeq->cq_head;
 
-	if (consumed)
+	if (*start != *end)
 		nvme_ring_cq_doorbell(nvmeq);
+	return found;
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
 {
-	irqreturn_t result;
 	struct nvme_queue *nvmeq = data;
-	spin_lock(&nvmeq->q_lock);
-	nvme_process_cq(nvmeq);
-	result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
-	nvmeq->cqe_seen = 0;
-	spin_unlock(&nvmeq->q_lock);
-	return result;
+	u16 start, end;
+
+	spin_lock(&nvmeq->cq_lock);
+	nvme_process_cq(nvmeq, &start, &end, -1);
+	spin_unlock(&nvmeq->cq_lock);
+
+	if (start == end)
+		return IRQ_NONE;
+	nvme_complete_cqes(nvmeq, start, end);
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t nvme_irq_check(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
-	if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+	if (nvme_cqe_pending(nvmeq))
 		return IRQ_WAKE_THREAD;
 	return IRQ_NONE;
 }
 
 static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
 {
-	struct nvme_completion cqe;
-	int found = 0, consumed = 0;
+	u16 start, end;
+	bool found;
 
-	if (!nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+	if (!nvme_cqe_pending(nvmeq))
 		return 0;
 
-	spin_lock_irq(&nvmeq->q_lock);
-	while (nvme_read_cqe(nvmeq, &cqe)) {
-		nvme_handle_cqe(nvmeq, &cqe);
-		consumed++;
-
-		if (tag == cqe.command_id) {
-			found = 1;
-			break;
-		}
-       }
-
-	if (consumed)
-		nvme_ring_cq_doorbell(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
+	found = nvme_process_cq(nvmeq, &start, &end, tag);
+	spin_unlock_irq(&nvmeq->cq_lock);
 
+	nvme_complete_cqes(nvmeq, start, end);
 	return found;
 }
 
@@ -1053,9 +1052,9 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
 
-	spin_lock_irq(&nvmeq->q_lock);
+	spin_lock(&nvmeq->sq_lock);
 	__nvme_submit_cmd(nvmeq, &c);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock(&nvmeq->sq_lock);
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1312,15 +1311,21 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
 	int vector;
 
-	spin_lock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
 	if (nvmeq->cq_vector == -1) {
-		spin_unlock_irq(&nvmeq->q_lock);
+		spin_unlock_irq(&nvmeq->cq_lock);
 		return 1;
 	}
 	vector = nvmeq->cq_vector;
 	nvmeq->dev->online_queues--;
 	nvmeq->cq_vector = -1;
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->cq_lock);
+
+	/*
+	 * Ensure that nvme_queue_rq() sees it ->cq_vector == -1 without
+	 * having to grab the lock.
+	 */
+	mb();
 
 	if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
 		blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
@@ -1333,15 +1338,18 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 {
 	struct nvme_queue *nvmeq = &dev->queues[0];
+	u16 start, end;
 
 	if (shutdown)
 		nvme_shutdown_ctrl(&dev->ctrl);
 	else
 		nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
 
-	spin_lock_irq(&nvmeq->q_lock);
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
+	nvme_process_cq(nvmeq, &start, &end, -1);
+	spin_unlock_irq(&nvmeq->cq_lock);
+
+	nvme_complete_cqes(nvmeq, start, end);
 }
 
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
@@ -1399,7 +1407,8 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
 
 	nvmeq->q_dmadev = dev->dev;
 	nvmeq->dev = dev;
-	spin_lock_init(&nvmeq->q_lock);
+	spin_lock_init(&nvmeq->sq_lock);
+	spin_lock_init(&nvmeq->cq_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
@@ -1435,7 +1444,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
 	struct nvme_dev *dev = nvmeq->dev;
 
-	spin_lock_irq(&nvmeq->q_lock);
+	spin_lock_irq(&nvmeq->cq_lock);
 	nvmeq->sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
@@ -1443,7 +1452,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
 	nvme_dbbuf_init(dev, nvmeq, qid);
 	dev->online_queues++;
-	spin_unlock_irq(&nvmeq->q_lock);
+	spin_unlock_irq(&nvmeq->cq_lock);
 }
 
 static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
@@ -1988,19 +1997,22 @@ static void nvme_del_queue_end(struct request *req, blk_status_t error)
 static void nvme_del_cq_end(struct request *req, blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
+	u16 start, end;
 
 	if (!error) {
 		unsigned long flags;
 
 		/*
-		 * We might be called with the AQ q_lock held
-		 * and the I/O queue q_lock should always
+		 * We might be called with the AQ cq_lock held
+		 * and the I/O queue cq_lock should always
 		 * nest inside the AQ one.
 		 */
-		spin_lock_irqsave_nested(&nvmeq->q_lock, flags,
+		spin_lock_irqsave_nested(&nvmeq->cq_lock, flags,
 					SINGLE_DEPTH_NESTING);
-		nvme_process_cq(nvmeq);
-		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+		nvme_process_cq(nvmeq, &start, &end, -1);
+		spin_unlock_irqrestore(&nvmeq->cq_lock, flags);
+
+		nvme_complete_cqes(nvmeq, start, end);
 	}
 
 	nvme_del_queue_end(req, error);
@@ -2488,6 +2500,15 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 	return 0;
 }
 
+static void nvme_async_probe(void *data, async_cookie_t cookie)
+{
+	struct nvme_dev *dev = data;
+
+	nvme_reset_ctrl_sync(&dev->ctrl);
+	flush_work(&dev->ctrl.scan_work);
+	nvme_put_ctrl(&dev->ctrl);
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -2532,7 +2553,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
-	nvme_reset_ctrl(&dev->ctrl);
+	nvme_get_ctrl(&dev->ctrl);
+	async_schedule(nvme_async_probe, dev);
 
 	return 0;
 
@@ -2670,8 +2692,15 @@ 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);
-	nvme_reset_ctrl(&dev->ctrl);
-	return PCI_ERS_RESULT_RECOVERED;
+	nvme_reset_ctrl_sync(&dev->ctrl);
+
+	switch (dev->ctrl.state) {
+	case NVME_CTRL_LIVE:
+	case NVME_CTRL_ADMIN_ONLY:
+		return PCI_ERS_RESULT_RECOVERED;
+	default:
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
 }
 
 static void nvme_error_resume(struct pci_dev *pdev)
@@ -2704,6 +2733,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0023),	/* WDC SN200 adapter */
@@ -2718,6 +2749,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
+	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
+		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },

drivers/nvme/host/trace.h

@@ -148,8 +148,8 @@ TRACE_EVENT(nvme_complete_rq,
 		    __entry->flags = nvme_req(req)->flags;
 		    __entry->status = nvme_req(req)->status;
 	    ),
-	    TP_printk("cmdid=%u, qid=%d, res=%llu, retries=%u, flags=0x%x, status=%u",
-		      __entry->cid, __entry->qid, __entry->result,
+	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->qid, __entry->cid, __entry->result,
 		      __entry->retries, __entry->flags, __entry->status)
 
 );