Merge branch 'nvme-5.4' of git://git.infradead.org/nvme into for-linus

Pull NVMe changes from Sagi:

"This set consists of various fixes and cleanups:
 - controller removal race fix from Balbir
 - quirk additions from Gabriel and Jian-Hong
 - nvme-pci power state save fix from Mario
 - Add 64bit user commands (for 64bit registers) from Marta
 - nvme-rdma/nvme-tcp fixes from Max, Mark and Me
 - Minor cleanups and nits from James, Dan and John"

* 'nvme-5.4' of git://git.infradead.org/nvme:
  nvme-rdma: fix possible use-after-free in connect timeout
  nvme: Move ctrl sqsize to generic space
  nvme: Add ctrl attributes for queue_count and sqsize
  nvme: allow 64-bit results in passthru commands
  nvme: Add quirk for Kingston NVME SSD running FW E8FK11.T
  nvmet-tcp: remove superflous check on request sgl
  Added QUIRKs for ADATA XPG SX8200 Pro 512GB
  nvme-rdma: Fix max_hw_sectors calculation
  nvme: fix an error code in nvme_init_subsystem()
  nvme-pci: Save PCI state before putting drive into deepest state
  nvme-tcp: fix wrong stop condition in io_work
  nvme-pci: Fix a race in controller removal
  nvmet: change ppl to lpp

drivers/nvme/host/core.c

@@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	 */
 	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
-	revalidate_disk(ns->disk);
 	blk_set_queue_dying(ns->queue);
 	/* Forcibly unquiesce queues to avoid blocking dispatch */
 	blk_mq_unquiesce_queue(ns->queue);
+	/*
+	 * Revalidate after unblocking dispatchers that may be holding bd_butex
+	 */
+	revalidate_disk(ns->disk);
 }
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -847,7 +850,7 @@ static void *nvme_add_user_metadata(struct bio *bio, void __user *ubuf,
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u32 *result, unsigned timeout)
+		u32 meta_seed, u64 *result, unsigned timeout)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -888,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	else
 		ret = nvme_req(req)->status;
 	if (result)
-		*result = le32_to_cpu(nvme_req(req)->result.u32);
+		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (meta && !ret && !write) {
 		if (copy_to_user(meta_buffer, meta, meta_len))
 			ret = -EFAULT;
@@ -1335,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct nvme_command c;
 	unsigned timeout = 0;
 	u32 effects;
+	u64 result;
+	int status;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+	if (cmd.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = cmd.opcode;
+	c.common.flags = cmd.flags;
+	c.common.nsid = cpu_to_le32(cmd.nsid);
+	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+	if (cmd.timeout_ms)
+		timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+			(void __user *)(uintptr_t)cmd.metadata,
+			cmd.metadata_len, 0, &result, timeout);
+	nvme_passthru_end(ctrl, effects);
+
+	if (status >= 0) {
+		if (put_user(result, &ucmd->result))
+			return -EFAULT;
+	}
+
+	return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			struct nvme_passthru_cmd64 __user *ucmd)
+{
+	struct nvme_passthru_cmd64 cmd;
+	struct nvme_command c;
+	unsigned timeout = 0;
+	u32 effects;
 	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1405,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 		srcu_read_unlock(&head->srcu, idx);
 }
 
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+		return true;
+	if (is_sed_ioctl(cmd))
+		return true;
+	return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+				  void __user *argp,
+				  struct nvme_ns_head *head,
+				  int srcu_idx)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
+
+	nvme_get_ctrl(ns->ctrl);
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	switch (cmd) {
+	case NVME_IOCTL_ADMIN_CMD:
+		ret = nvme_user_cmd(ctrl, NULL, argp);
+		break;
+	case NVME_IOCTL_ADMIN64_CMD:
+		ret = nvme_user_cmd64(ctrl, NULL, argp);
+		break;
+	default:
+		ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+		break;
+	}
+	nvme_put_ctrl(ctrl);
+	return ret;
+}
+
 static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
@@ -1422,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 	 * seperately and drop the ns SRCU reference early.  This avoids a
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
-	if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
-		struct nvme_ctrl *ctrl = ns->ctrl;
-
-		nvme_get_ctrl(ns->ctrl);
-		nvme_put_ns_from_disk(head, srcu_idx);
-
-		if (cmd == NVME_IOCTL_ADMIN_CMD)
-			ret = nvme_user_cmd(ctrl, NULL, argp);
-		else
-			ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
-		nvme_put_ctrl(ctrl);
-		return ret;
-	}
+	if (is_ctrl_ioctl(cmd))
+		return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
 	switch (cmd) {
 	case NVME_IOCTL_ID:
@@ -1448,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 	case NVME_IOCTL_SUBMIT_IO:
 		ret = nvme_submit_io(ns, argp);
 		break;
+	case NVME_IOCTL_IO64_CMD:
+		ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+		break;
 	default:
 		if (ns->ndev)
 			ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2289,6 +2366,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
 		.vid = 0x14a4,
 		.fr = "22301111",
 		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+	},
+	{
+		/*
+		 * This Kingston E8FK11.T firmware version has no interrupt
+		 * after resume with actions related to suspend to idle
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=204887
+		 */
+		.vid = 0x2646,
+		.fr = "E8FK11.T",
+		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
 	}
 };
 
@@ -2540,8 +2627,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		list_add_tail(&subsys->entry, &nvme_subsystems);
 	}
 
-	if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
-			dev_name(ctrl->device))) {
+	ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+				dev_name(ctrl->device));
+	if (ret) {
 		dev_err(ctrl->device,
 			"failed to create sysfs link from subsystem.\n");
 		goto out_put_subsystem;
@@ -2838,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
+	case NVME_IOCTL_ADMIN64_CMD:
+		return nvme_user_cmd64(ctrl, NULL, argp);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
@@ -3045,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
 
 nvme_show_int_function(cntlid);
 nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
 
 static ssize_t nvme_sysfs_delete(struct device *dev,
 				struct device_attribute *attr, const char *buf,
@@ -3125,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_address.attr,
 	&dev_attr_state.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_queue_count.attr,
+	&dev_attr_sqsize.attr,
 	NULL
 };
 

drivers/nvme/host/nvme.h

@@ -221,6 +221,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u16 sqsize;
 	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
@@ -269,7 +270,6 @@ struct nvme_ctrl {
 	u16 hmmaxd;
 
 	/* Fabrics only */
-	u16 sqsize;
 	u32 ioccsz;
 	u32 iorcsz;
 	u16 icdoff;

drivers/nvme/host/pci.c

@@ -2946,11 +2946,21 @@ static int nvme_suspend(struct device *dev)
 	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.
@@ -2958,14 +2968,7 @@ static int nvme_suspend(struct device *dev)
 		nvme_dev_disable(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;
@@ -3090,6 +3093,9 @@ 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) },

drivers/nvme/host/rdma.c

@@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
 static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
 {
 	return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
-		     ibdev->attrs.max_fast_reg_page_list_len);
+		     ibdev->attrs.max_fast_reg_page_list_len - 1);
 }
 
 static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
@@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	const int cq_factor = send_wr_factor + 1;	/* + RECV */
 	int comp_vector, idx = nvme_rdma_queue_idx(queue);
 	enum ib_poll_context poll_ctx;
-	int ret;
+	int ret, pages_per_mr;
 
 	queue->device = nvme_rdma_find_get_device(queue->cm_id);
 	if (!queue->device) {
@@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 		goto out_destroy_qp;
 	}
 
+	/*
+	 * Currently we don't use SG_GAPS MR's so if the first entry is
+	 * misaligned we'll end up using two entries for a single data page,
+	 * so one additional entry is required.
+	 */
+	pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1;
 	ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
 			      queue->queue_size,
 			      IB_MR_TYPE_MEM_REG,
-			      nvme_rdma_get_max_fr_pages(ibdev), 0);
+			      pages_per_mr, 0);
 	if (ret) {
 		dev_err(queue->ctrl->ctrl.device,
 			"failed to initialize MR pool sized %d for QID %d\n",
@@ -614,6 +620,7 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
 	if (!ret) {
 		set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
 	} else {
+		if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
 			__nvme_rdma_stop_queue(queue);
 		dev_info(ctrl->ctrl.device,
 			"failed to connect queue: %d ret=%d\n", idx, ret);
@@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (error)
 		goto out_stop_queue;
 
-	ctrl->ctrl.max_hw_sectors =
-		(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+	ctrl->ctrl.max_segments = ctrl->max_fr_pages;
+	ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9);
 
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 

drivers/nvme/host/tcp.c

@@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 {
 	struct nvme_tcp_queue *queue =
 		container_of(w, struct nvme_tcp_queue, io_work);
-	unsigned long start = jiffies + msecs_to_jiffies(1);
+	unsigned long deadline = jiffies + msecs_to_jiffies(1);
 
 	do {
 		bool pending = false;
@@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		if (!pending)
 			return;
 
-	} while (time_after(jiffies, start)); /* quota is exhausted */
+	} while (!time_after(jiffies, deadline)); /* quota is exhausted */
 
 	queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }

drivers/nvme/target/io-cmd-bdev.c

@@ -11,10 +11,10 @@
 void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 {
 	const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
-	/* Number of physical blocks per logical block. */
-	const u32 ppl = ql->physical_block_size / ql->logical_block_size;
-	/* Physical blocks per logical block, 0's based. */
-	const __le16 ppl0b = to0based(ppl);
+	/* Number of logical blocks per physical block. */
+	const u32 lpp = ql->physical_block_size / ql->logical_block_size;
+	/* Logical blocks per physical block, 0's based. */
+	const __le16 lpp0b = to0based(lpp);
 
 	/*
 	 * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
@@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 	 * field from the identify controller data structure should be used.
 	 */
 	id->nsfeat |= 1 << 1;
-	id->nawun = ppl0b;
-	id->nawupf = ppl0b;
-	id->nacwu = ppl0b;
+	id->nawun = lpp0b;
+	id->nawupf = lpp0b;
+	id->nacwu = lpp0b;
 
 	/*
 	 * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 	 */
 	id->nsfeat |= 1 << 4;
 	/* NPWG = Namespace Preferred Write Granularity. 0's based */
-	id->npwg = ppl0b;
+	id->npwg = lpp0b;
 	/* NPWA = Namespace Preferred Write Alignment. 0's based */
 	id->npwa = id->npwg;
 	/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */

drivers/nvme/target/tcp.c

@@ -348,7 +348,6 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
 
 	return 0;
 err:
-	if (cmd->req.sg_cnt)
 	sgl_free(cmd->req.sg);
 	return NVME_SC_INTERNAL;
 }
@@ -554,7 +553,6 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 
 	if (queue->nvme_sq.sqhd_disabled) {
 		kfree(cmd->iov);
-		if (cmd->req.sg_cnt)
 		sgl_free(cmd->req.sg);
 	}
 
@@ -586,7 +584,6 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 		return -EAGAIN;
 
 	kfree(cmd->iov);
-	if (cmd->req.sg_cnt)
 	sgl_free(cmd->req.sg);
 	cmd->queue->snd_cmd = NULL;
 	nvmet_tcp_put_cmd(cmd);
@@ -1310,7 +1307,6 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
 	nvmet_req_uninit(&cmd->req);
 	nvmet_tcp_unmap_pdu_iovec(cmd);
 	kfree(cmd->iov);
-	if (cmd->req.sg_cnt)
 	sgl_free(cmd->req.sg);
 }
 

include/uapi/linux/nvme_ioctl.h

@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
 	__u32	result;
 };
 
+struct nvme_passthru_cmd64 {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u64	result;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
 #define NVME_IOCTL_RESET	_IO('N', 0x44)
 #define NVME_IOCTL_SUBSYS_RESET	_IO('N', 0x45)
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */