Merge tag 'nvme-6.4-2023-04-14' of git://git.infradead.org/nvme into for-6.4/block

Pull NVMe updates from Christoph:

"nvme updates for Linux 6.4

 - drop redundant pci_enable_pcie_error_reporting (Bjorn Helgaas)
 - validate nvmet module parameters (Chaitanya Kulkarni)
 - fence TCP socket on receive error (Chris Leech)
 - fix async event trace event (Keith Busch)
 - minor cleanups (Chaitanya Kulkarni, zhenwei pi)
 - fix and cleanup nvmet Identify handling (Damien Le Moal,
   Christoph Hellwig)
 - fix double blk_mq_complete_request race in the timeout handler
   (Lei Yin)
 - fix irq locking in nvme-fcloop (Ming Lei)
 - remove queue mapping helper for rdma devices (Sagi Grimberg)"

* tag 'nvme-6.4-2023-04-14' of git://git.infradead.org/nvme:
  nvme-fcloop: fix "inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage"
  blk-mq-rdma: remove queue mapping helper for rdma devices
  nvme-rdma: minor cleanup in nvme_rdma_create_cq()
  nvme: fix double blk_mq_complete_request for timeout request with low probability
  nvme: fix async event trace event
  nvme-apple: return directly instead of else
  nvme-apple: return directly instead of else
  nvmet-tcp: validate idle poll modparam value
  nvmet-tcp: validate so_priority modparam value
  nvme-tcp: fence TCP socket on receive error
  nvmet: remove nvmet_req_cns_error_complete
  nvmet: rename nvmet_execute_identify_cns_cs_ns
  nvmet: fix Identify Identification Descriptor List handling
  nvmet: cleanup nvmet_execute_identify()
  nvmet: fix I/O Command Set specific Identify Controller
  nvmet: fix Identify Active Namespace ID list handling
  nvmet: fix Identify Controller handling
  nvmet: fix Identify Namespace handling
  nvmet: fix error handling in nvmet_execute_identify_cns_cs_ns()
  nvme-pci: drop redundant pci_enable_pcie_error_reporting()

Author: axboe

block/Kconfig

@@ -215,11 +215,6 @@ config BLK_MQ_VIRTIO
 	depends on VIRTIO
 	default y
 
-config BLK_MQ_RDMA
-	bool
-	depends on INFINIBAND
-	default y
-
 config BLK_PM
 	def_bool PM
 

block/Makefile

@@ -30,7 +30,6 @@ obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
-obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

block/blk-mq-rdma.c

@@ -209,16 +209,16 @@ static inline struct apple_nvme *queue_to_apple_nvme(struct apple_nvme_queue *q)
 {
 	if (q->is_adminq)
 		return container_of(q, struct apple_nvme, adminq);
-	else
-		return container_of(q, struct apple_nvme, ioq);
+
+	return container_of(q, struct apple_nvme, ioq);
 }
 
 static unsigned int apple_nvme_queue_depth(struct apple_nvme_queue *q)
 {
 	if (q->is_adminq)
 		return APPLE_NVME_AQ_DEPTH;
-	else
-		return APPLE_ANS_MAX_QUEUE_DEPTH;
+
+	return APPLE_ANS_MAX_QUEUE_DEPTH;
 }
 
 static void apple_nvme_rtkit_crashed(void *cookie)

drivers/nvme/host/apple.c

@@ -450,8 +450,8 @@ bool nvme_cancel_request(struct request *req, void *data)
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
 				"Cancelling I/O %d", req->tag);
 
-	/* don't abort one completed request */
-	if (blk_mq_request_completed(req))
+	/* don't abort one completed or idle request */
+	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
@@ -4808,8 +4808,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	u32 aer_notice_type = nvme_aer_subtype(result);
 	bool requeue = true;
 
-	trace_nvme_async_event(ctrl, aer_notice_type);
-
 	switch (aer_notice_type) {
 	case NVME_AER_NOTICE_NS_CHANGED:
 		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
@@ -4845,7 +4843,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 
 static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl)
 {
-	trace_nvme_async_event(ctrl, NVME_AER_ERROR);
 	dev_warn(ctrl->device, "resetting controller due to AER\n");
 	nvme_reset_ctrl(ctrl);
 }
@@ -4861,6 +4858,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS)
 		return;
 
+	trace_nvme_async_event(ctrl, result);
 	switch (aer_type) {
 	case NVME_AER_NOTICE:
 		requeue = nvme_handle_aen_notice(ctrl, result);
@@ -4878,7 +4876,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	case NVME_AER_SMART:
 	case NVME_AER_CSS:
 	case NVME_AER_VS:
-		trace_nvme_async_event(ctrl, aer_type);
 		ctrl->aen_result = result;
 		break;
 	default:

drivers/nvme/host/core.c

@@ -5,7 +5,6 @@
  */
 
 #include <linux/acpi.h>
-#include <linux/aer.h>
 #include <linux/async.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
@@ -2535,7 +2534,6 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	nvme_map_cmb(dev);
 
-	pci_enable_pcie_error_reporting(pdev);
 	pci_save_state(pdev);
 
 	result = nvme_pci_configure_admin_queue(dev);
@@ -2600,10 +2598,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_suspend_io_queues(dev);
 	nvme_suspend_queue(dev, 0);
 	pci_free_irq_vectors(pdev);
-	if (pci_is_enabled(pdev)) {
-		pci_disable_pcie_error_reporting(pdev);
+	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
-	}
 	nvme_reap_pending_cqes(dev);
 
 	nvme_cancel_tagset(&dev->ctrl);

drivers/nvme/host/pci.c

@@ -12,7 +12,6 @@
 #include <linux/string.h>
 #include <linux/atomic.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-mq-rdma.h>
 #include <linux/blk-integrity.h>
 #include <linux/types.h>
 #include <linux/list.h>
@@ -464,7 +463,6 @@ static int nvme_rdma_create_cq(struct ib_device *ibdev,
 		struct nvme_rdma_queue *queue)
 {
 	int ret, comp_vector, idx = nvme_rdma_queue_idx(queue);
-	enum ib_poll_context poll_ctx;
 
 	/*
 	 * Spread I/O queues completion vectors according their queue index.
@@ -473,15 +471,12 @@ static int nvme_rdma_create_cq(struct ib_device *ibdev,
 	comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors;
 
 	/* Polling queues need direct cq polling context */
-	if (nvme_rdma_poll_queue(queue)) {
-		poll_ctx = IB_POLL_DIRECT;
+	if (nvme_rdma_poll_queue(queue))
 		queue->ib_cq = ib_alloc_cq(ibdev, queue, queue->cq_size,
-					   comp_vector, poll_ctx);
-	} else {
-		poll_ctx = IB_POLL_SOFTIRQ;
+					   comp_vector, IB_POLL_DIRECT);
+	else
 		queue->ib_cq = ib_cq_pool_get(ibdev, queue->cq_size,
-					      comp_vector, poll_ctx);
-	}
+					      comp_vector, IB_POLL_SOFTIRQ);
 
 	if (IS_ERR(queue->ib_cq)) {
 		ret = PTR_ERR(queue->ib_cq);
@@ -2163,10 +2158,8 @@ static void nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 			ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
-	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
-			ctrl->device->dev, 0);
-	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_READ],
-			ctrl->device->dev, 0);
+	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
 
 	if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) {
 		/* map dedicated poll queues only if we have queues left */

drivers/nvme/host/rdma.c

@@ -876,6 +876,9 @@ static int nvme_tcp_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
 	size_t consumed = len;
 	int result;
 
+	if (unlikely(!queue->rd_enabled))
+		return -EFAULT;
+
 	while (len) {
 		switch (nvme_tcp_recv_state(queue)) {
 		case NVME_TCP_RECV_PDU:

drivers/nvme/host/tcp.c

@@ -127,15 +127,12 @@ TRACE_EVENT(nvme_async_event,
 	),
 	TP_printk("nvme%d: NVME_AEN=%#08x [%s]",
 		__entry->ctrl_id, __entry->result,
-		__print_symbolic(__entry->result,
-		aer_name(NVME_AER_NOTICE_NS_CHANGED),
-		aer_name(NVME_AER_NOTICE_ANA),
-		aer_name(NVME_AER_NOTICE_FW_ACT_STARTING),
-		aer_name(NVME_AER_NOTICE_DISC_CHANGED),
-		aer_name(NVME_AER_ERROR),
-		aer_name(NVME_AER_SMART),
-		aer_name(NVME_AER_CSS),
-		aer_name(NVME_AER_VS))
+		__print_symbolic(__entry->result & 0x7,
+			aer_name(NVME_AER_ERROR),
+			aer_name(NVME_AER_SMART),
+			aer_name(NVME_AER_NOTICE),
+			aer_name(NVME_AER_CSS),
+			aer_name(NVME_AER_VS))
 	)
 );
 

drivers/nvme/host/trace.h

@@ -668,21 +668,11 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
-static bool nvmet_handle_identify_desclist(struct nvmet_req *req)
+static void nvmet_execute_identify_ctrl_nvm(struct nvmet_req *req)
 {
-	switch (req->cmd->identify.csi) {
-	case NVME_CSI_NVM:
-		nvmet_execute_identify_desclist(req);
-		return true;
-	case NVME_CSI_ZNS:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			nvmet_execute_identify_desclist(req);
-			return true;
-		}
-		return false;
-	default:
-		return false;
-	}
+	/* Not supported: return zeroes */
+	nvmet_req_complete(req,
+		   nvmet_zero_sgl(req, 0, sizeof(struct nvme_id_ctrl_nvm)));
 }
 
 static void nvmet_execute_identify(struct nvmet_req *req)
@@ -692,54 +682,49 @@ static void nvmet_execute_identify(struct nvmet_req *req)
 
 	switch (req->cmd->identify.cns) {
 	case NVME_ID_CNS_NS:
+		nvmet_execute_identify_ns(req);
+		return;
+	case NVME_ID_CNS_CTRL:
+		nvmet_execute_identify_ctrl(req);
+		return;
+	case NVME_ID_CNS_NS_ACTIVE_LIST:
+		nvmet_execute_identify_nslist(req);
+		return;
+	case NVME_ID_CNS_NS_DESC_LIST:
+		nvmet_execute_identify_desclist(req);
+		return;
+	case NVME_ID_CNS_CS_NS:
 		switch (req->cmd->identify.csi) {
 		case NVME_CSI_NVM:
-			return nvmet_execute_identify_ns(req);
-		default:
+			/* Not supported */
 			break;
-		}
-		break;
-	case NVME_ID_CNS_CS_NS:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			switch (req->cmd->identify.csi) {
-			case NVME_CSI_ZNS:
-				return nvmet_execute_identify_cns_cs_ns(req);
-			default:
-				break;
+		case NVME_CSI_ZNS:
+			if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+				nvmet_execute_identify_ns_zns(req);
+				return;
 			}
-		}
-		break;
-	case NVME_ID_CNS_CTRL:
-		switch (req->cmd->identify.csi) {
-		case NVME_CSI_NVM:
-			return nvmet_execute_identify_ctrl(req);
+			break;
 		}
 		break;
 	case NVME_ID_CNS_CS_CTRL:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			switch (req->cmd->identify.csi) {
-			case NVME_CSI_ZNS:
-				return nvmet_execute_identify_cns_cs_ctrl(req);
-			default:
-				break;
-			}
-		}
-		break;
-	case NVME_ID_CNS_NS_ACTIVE_LIST:
 		switch (req->cmd->identify.csi) {
 		case NVME_CSI_NVM:
-			return nvmet_execute_identify_nslist(req);
-		default:
+			nvmet_execute_identify_ctrl_nvm(req);
+			return;
+		case NVME_CSI_ZNS:
+			if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+				nvmet_execute_identify_ctrl_zns(req);
+				return;
+			}
 			break;
 		}
 		break;
-	case NVME_ID_CNS_NS_DESC_LIST:
-		if (nvmet_handle_identify_desclist(req) == true)
-			return;
-		break;
 	}
 
-	nvmet_req_cns_error_complete(req);
+	pr_debug("unhandled identify cns %d on qid %d\n",
+	       req->cmd->identify.cns, req->sq->qid);
+	req->error_loc = offsetof(struct nvme_identify, cns);
+	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
 }
 
 /*