Merge tag 'nvme-6.12-2024-09-06' of git://git.infradead.org/nvme into for-6.12/block

Pull NVMe updates from Keith:

"nvme updates for Linux 6.12

 - Asynchronous namespace scanning (Stuart)
 - TCP TLS updates (Hannes)
 - RDMA queue controller validation (Niklas)
 - Align field names to the spec (Anuj)
 - Metadata support validation (Puranjay)"

* tag 'nvme-6.12-2024-09-06' of git://git.infradead.org/nvme:
  nvme: fix metadata handling in nvme-passthrough
  nvme: rename apptag and appmask to lbat and lbatm
  nvme-rdma: send cntlid in the RDMA_CM_REQUEST Private Data
  nvme-target: do not check authentication status for admin commands twice
  nvmet-auth: allow to clear DH-HMAC-CHAP keys
  nvme-sysfs: add 'tls_keyring' attribute
  nvme-sysfs: add 'tls_configured_key' sysfs attribute
  nvme: split off TLS sysfs attributes into a separate group
  nvme: add a newline to the 'tls_key' sysfs attribute
  nvme-tcp: check for invalidated or revoked key
  nvme-tcp: sanitize TLS key handling
  nvme-keyring: restrict match length for version '1' identifiers
  nvme_core: scan namespaces asynchronously

8 files changed, 174 insertions, 53 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index a3caef75aa0a..883aaab2d83e 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -109,6 +109,7 @@ config NVME_HOST_AUTH
 	bool "NVMe over Fabrics In-Band Authentication in host side"
 	depends on NVME_CORE
 	select NVME_AUTH
+	select NVME_KEYRING if NVME_TCP_TLS
 	help
 	  This provides support for NVMe over Fabrics In-Band Authentication in
 	  host side.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 053d5b4909cd..75ab62cb4aa4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2014, Intel Corporation.
  */
 
+#include <linux/async.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-integrity.h>
@@ -986,8 +987,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	cmnd->rw.length =
 		cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
 	cmnd->rw.reftag = 0;
-	cmnd->rw.apptag = 0;
-	cmnd->rw.appmask = 0;
+	cmnd->rw.lbat = 0;
+	cmnd->rw.lbatm = 0;
 
 	if (ns->head->ms) {
 		/*
@@ -4040,6 +4041,35 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	}
 }
 
+/**
+ * struct async_scan_info - keeps track of controller & NSIDs to scan
+ * @ctrl:	Controller on which namespaces are being scanned
+ * @next_nsid:	Index of next NSID to scan in ns_list
+ * @ns_list:	Pointer to list of NSIDs to scan
+ *
+ * Note: There is a single async_scan_info structure shared by all instances
+ * of nvme_scan_ns_async() scanning a given controller, so the atomic
+ * operations on next_nsid are critical to ensure each instance scans a unique
+ * NSID.
+ */
+struct async_scan_info {
+	struct nvme_ctrl *ctrl;
+	atomic_t next_nsid;
+	__le32 *ns_list;
+};
+
+static void nvme_scan_ns_async(void *data, async_cookie_t cookie)
+{
+	struct async_scan_info *scan_info = data;
+	int idx;
+	u32 nsid;
+
+	idx = (u32)atomic_fetch_inc(&scan_info->next_nsid);
+	nsid = le32_to_cpu(scan_info->ns_list[idx]);
+
+	nvme_scan_ns(scan_info->ctrl, nsid);
+}
+
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					unsigned nsid)
 {
@@ -4066,11 +4096,15 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 	__le32 *ns_list;
 	u32 prev = 0;
 	int ret = 0, i;
+	ASYNC_DOMAIN(domain);
+	struct async_scan_info scan_info;
 
 	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
 	if (!ns_list)
 		return -ENOMEM;
 
+	scan_info.ctrl = ctrl;
+	scan_info.ns_list = ns_list;
 	for (;;) {
 		struct nvme_command cmd = {
 			.identify.opcode	= nvme_admin_identify,
@@ -4086,19 +4120,23 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
 			goto free;
 		}
 
+		atomic_set(&scan_info.next_nsid, 0);
 		for (i = 0; i < nr_entries; i++) {
 			u32 nsid = le32_to_cpu(ns_list[i]);
 
 			if (!nsid)	/* end of the list? */
 				goto out;
-			nvme_scan_ns(ctrl, nsid);
+			async_schedule_domain(nvme_scan_ns_async, &scan_info,
+						&domain);
 			while (++prev < nsid)
 				nvme_ns_remove_by_nsid(ctrl, prev);
 		}
+		async_synchronize_full_domain(&domain);
 	}
  out:
 	nvme_remove_invalid_namespaces(ctrl, prev);
  free:
+	async_synchronize_full_domain(&domain);
 	kfree(ns_list);
 	return ret;
 }
@@ -4677,7 +4715,6 @@ static void nvme_free_ctrl(struct device *dev)
 
 	if (!subsys || ctrl->instance != subsys->instance)
 		ida_free(&nvme_instance_ida, ctrl->instance);
-	key_put(ctrl->tls_key);
 	nvme_free_cels(ctrl);
 	nvme_mpath_uninit(ctrl);
 	cleanup_srcu_struct(&ctrl->srcu);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index f5f545fa0103..432efcbf9e2f 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -665,7 +665,7 @@ static struct key *nvmf_parse_key(int key_id)
 		return ERR_PTR(-EINVAL);
 	}
 
-	key = key_lookup(key_id);
+	key = nvme_tls_key_lookup(key_id);
 	if (IS_ERR(key))
 		pr_err("key id %08x not found\n", key_id);
 	else
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index f1d58e70933f..1d769c842fbf 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2017-2021 Christoph Hellwig.
  */
 #include <linux/bio-integrity.h>
+#include <linux/blk-integrity.h>
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
 #include <linux/io_uring/cmd.h>
@@ -119,9 +120,14 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
+	bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk);
+	bool has_metadata = meta_buffer && meta_len;
 	struct bio *bio = NULL;
 	int ret;
 
+	if (has_metadata && !supports_metadata)
+		return -EINVAL;
+
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
 		struct iov_iter iter;
 
@@ -143,15 +149,15 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		goto out;
 
 	bio = req->bio;
-	if (bdev) {
+	if (bdev)
 		bio_set_dev(bio, bdev);
-		if (meta_buffer && meta_len) {
-			ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
-						     meta_seed);
-			if (ret)
-				goto out_unmap;
-			req->cmd_flags |= REQ_INTEGRITY;
-		}
+
+	if (has_metadata) {
+		ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
+					     meta_seed);
+		if (ret)
+			goto out_unmap;
+		req->cmd_flags |= REQ_INTEGRITY;
 	}
 
 	return ret;
@@ -260,8 +266,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.control = cpu_to_le16(io.control);
 	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
 	c.rw.reftag = cpu_to_le32(io.reftag);
-	c.rw.apptag = cpu_to_le16(io.apptag);
-	c.rw.appmask = cpu_to_le16(io.appmask);
+	c.rw.lbat = cpu_to_le16(io.apptag);
+	c.rw.lbatm = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
 			meta_len, lower_32_bits(io.slba), NULL, 0, 0);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f900e44243ae..af22368800e7 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -373,7 +373,7 @@ struct nvme_ctrl {
 	struct nvme_dhchap_key *ctrl_key;
 	u16 transaction;
 #endif
-	struct key *tls_key;
+	key_serial_t tls_pskid;
 
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2eb33842f971..15b5e06039a5 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1363,8 +1363,8 @@ static void nvme_rdma_set_sig_domain(struct blk_integrity *bi,
 	if (control & NVME_RW_PRINFO_PRCHK_REF)
 		domain->sig.dif.ref_remap = true;
 
-	domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag);
-	domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask);
+	domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.lbat);
+	domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.lbatm);
 	domain->sig.dif.app_escape = true;
 	if (pi_type == NVME_NS_DPS_PI_TYPE3)
 		domain->sig.dif.ref_escape = true;
@@ -1876,6 +1876,8 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
 		 */
 		priv.hrqsize = cpu_to_le16(queue->queue_size);
 		priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
+		/* cntlid should only be set when creating an I/O queue */
+		priv.cntlid = cpu_to_le16(ctrl->ctrl.cntlid);
 	}
 
 	ret = rdma_connect_locked(queue->cm_id, &param);
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index ba05faaac562..eb345551d6fe 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -664,19 +664,6 @@ static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR,
 	nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store);
 #endif
 
-#ifdef CONFIG_NVME_TCP_TLS
-static ssize_t tls_key_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{
-	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
-
-	if (!ctrl->tls_key)
-		return 0;
-	return sysfs_emit(buf, "%08x", key_serial(ctrl->tls_key));
-}
-static DEVICE_ATTR_RO(tls_key);
-#endif
-
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -704,9 +691,6 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_dhchap_secret.attr,
 	&dev_attr_dhchap_ctrl_secret.attr,
 #endif
-#ifdef CONFIG_NVME_TCP_TLS
-	&dev_attr_tls_key.attr,
-#endif
 	&dev_attr_adm_passthru_err_log_enabled.attr,
 	NULL
 };
@@ -737,11 +721,6 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 	if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts)
 		return 0;
 #endif
-#ifdef CONFIG_NVME_TCP_TLS
-	if (a == &dev_attr_tls_key.attr &&
-	    (!ctrl->opts || strcmp(ctrl->opts->transport, "tcp")))
-		return 0;
-#endif
 
 	return a->mode;
 }
@@ -752,8 +731,77 @@ const struct attribute_group nvme_dev_attrs_group = {
 };
 EXPORT_SYMBOL_GPL(nvme_dev_attrs_group);
 
+#ifdef CONFIG_NVME_TCP_TLS
+static ssize_t tls_key_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (!ctrl->tls_pskid)
+		return 0;
+	return sysfs_emit(buf, "%08x\n", ctrl->tls_pskid);
+}
+static DEVICE_ATTR_RO(tls_key);
+
+static ssize_t tls_configured_key_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct key *key = ctrl->opts->tls_key;
+
+	return sysfs_emit(buf, "%08x\n", key_serial(key));
+}
+static DEVICE_ATTR_RO(tls_configured_key);
+
+static ssize_t tls_keyring_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct key *keyring = ctrl->opts->keyring;
+
+	return sysfs_emit(buf, "%s\n", keyring->description);
+}
+static DEVICE_ATTR_RO(tls_keyring);
+
+static struct attribute *nvme_tls_attrs[] = {
+	&dev_attr_tls_key.attr,
+	&dev_attr_tls_configured_key.attr,
+	&dev_attr_tls_keyring.attr,
+};
+
+static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj,
+		struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (!ctrl->opts || strcmp(ctrl->opts->transport, "tcp"))
+		return 0;
+
+	if (a == &dev_attr_tls_key.attr &&
+	    !ctrl->opts->tls)
+		return 0;
+	if (a == &dev_attr_tls_configured_key.attr &&
+	    !ctrl->opts->tls_key)
+		return 0;
+	if (a == &dev_attr_tls_keyring.attr &&
+	    !ctrl->opts->keyring)
+		return 0;
+
+	return a->mode;
+}
+
+const struct attribute_group nvme_tls_attrs_group = {
+	.attrs		= nvme_tls_attrs,
+	.is_visible	= nvme_tls_attrs_are_visible,
+};
+#endif
+
 const struct attribute_group *nvme_dev_attr_groups[] = {
 	&nvme_dev_attrs_group,
+#ifdef CONFIG_NVME_TCP_TLS
+	&nvme_tls_attrs_group,
+#endif
 	NULL,
 };
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9ea6be0b0392..89c44413c593 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -165,6 +165,7 @@ struct nvme_tcp_queue {
 
 	bool			hdr_digest;
 	bool			data_digest;
+	bool			tls_enabled;
 	struct ahash_request	*rcv_hash;
 	struct ahash_request	*snd_hash;
 	__le32			exp_ddgst;
@@ -213,7 +214,21 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
-static inline bool nvme_tcp_tls(struct nvme_ctrl *ctrl)
+/*
+ * Check if the queue is TLS encrypted
+ */
+static inline bool nvme_tcp_queue_tls(struct nvme_tcp_queue *queue)
+{
+	if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
+		return 0;
+
+	return queue->tls_enabled;
+}
+
+/*
+ * Check if TLS is configured for the controller.
+ */
+static inline bool nvme_tcp_tls_configured(struct nvme_ctrl *ctrl)
 {
 	if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
 		return 0;
@@ -368,7 +383,7 @@ static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue)
 
 static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
 {
-	return !nvme_tcp_tls(&queue->ctrl->ctrl) &&
+	return !nvme_tcp_queue_tls(queue) &&
 		nvme_tcp_queue_has_pending(queue);
 }
 
@@ -1427,7 +1442,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	memset(&msg, 0, sizeof(msg));
 	iov.iov_base = icresp;
 	iov.iov_len = sizeof(*icresp);
-	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
+	if (nvme_tcp_queue_tls(queue)) {
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
@@ -1439,7 +1454,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;
-	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
+	if (nvme_tcp_queue_tls(queue)) {
 		ctype = tls_get_record_type(queue->sock->sk,
 					    (struct cmsghdr *)cbuf);
 		if (ctype != TLS_RECORD_TYPE_DATA) {
@@ -1581,13 +1596,16 @@ static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
 		goto out_complete;
 	}
 
-	tls_key = key_lookup(pskid);
+	tls_key = nvme_tls_key_lookup(pskid);
 	if (IS_ERR(tls_key)) {
 		dev_warn(ctrl->ctrl.device, "queue %d: Invalid key %x\n",
 			 qid, pskid);
 		queue->tls_err = -ENOKEY;
 	} else {
-		ctrl->ctrl.tls_key = tls_key;
+		queue->tls_enabled = true;
+		if (qid == 0)
+			ctrl->ctrl.tls_pskid = key_serial(tls_key);
+		key_put(tls_key);
 		queue->tls_err = 0;
 	}
 
@@ -1768,7 +1786,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 	}
 
 	/* If PSKs are configured try to start TLS */
-	if (IS_ENABLED(CONFIG_NVME_TCP_TLS) && pskid) {
+	if (nvme_tcp_tls_configured(nctrl) && pskid) {
 		ret = nvme_tcp_start_tls(nctrl, queue, pskid);
 		if (ret)
 			goto err_init_connect;
@@ -1829,6 +1847,8 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	mutex_lock(&queue->queue_lock);
 	if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		__nvme_tcp_stop_queue(queue);
+	/* Stopping the queue will disable TLS */
+	queue->tls_enabled = false;
 	mutex_unlock(&queue->queue_lock);
 }
 
@@ -1925,16 +1945,17 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 	int ret;
 	key_serial_t pskid = 0;
 
-	if (nvme_tcp_tls(ctrl)) {
+	if (nvme_tcp_tls_configured(ctrl)) {
 		if (ctrl->opts->tls_key)
 			pskid = key_serial(ctrl->opts->tls_key);
-		else
+		else {
 			pskid = nvme_tls_psk_default(ctrl->opts->keyring,
 						      ctrl->opts->host->nqn,
 						      ctrl->opts->subsysnqn);
-		if (!pskid) {
-			dev_err(ctrl->device, "no valid PSK found\n");
-			return -ENOKEY;
+			if (!pskid) {
+				dev_err(ctrl->device, "no valid PSK found\n");
+				return -ENOKEY;
+			}
 		}
 	}
 
@@ -1957,13 +1978,14 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	int i, ret;
 
-	if (nvme_tcp_tls(ctrl) && !ctrl->tls_key) {
+	if (nvme_tcp_tls_configured(ctrl) && !ctrl->tls_pskid) {
 		dev_err(ctrl->device, "no PSK negotiated\n");
 		return -ENOKEY;
 	}
+
 	for (i = 1; i < ctrl->queue_count; i++) {
 		ret = nvme_tcp_alloc_queue(ctrl, i,
-				key_serial(ctrl->tls_key));
+				ctrl->tls_pskid);
 		if (ret)
 			goto out_free_queues;
 	}
@@ -2144,6 +2166,11 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_unquiesce_admin_queue(ctrl);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
+	if (ctrl->tls_pskid) {
+		dev_dbg(ctrl->device, "Wipe negotiated TLS_PSK %08x\n",
+			ctrl->tls_pskid);
+		ctrl->tls_pskid = 0;
+	}
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,