Merge tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Improvements to the queue_rqs() support, and adding null_blk support
   for that as well (Chengming)

 - Series improving badblocks support (Coly)

 - Key store support for sed-opal (Greg)

 - IBM partition string handling improvements (Jan)

 - Make number of ublk devices supported configurable (Mike)

 - Cancelation improvements for ublk (Ming)

 - MD pull requests via Song:
     - Handle timeout in md-cluster, by Denis Plotnikov
     - Cleanup pers->prepare_suspend, by Yu Kuai
     - Rewrite mddev_suspend(), by Yu Kuai
     - Simplify md_seq_ops, by Yu Kuai
     - Reduce unnecessary locking array_state_store(), by Mariusz
       Tkaczyk
     - Make rdev add/remove independent from daemon thread, by Yu Kuai
     - Refactor code around quiesce() and mddev_suspend(), by Yu Kuai

 - NVMe pull request via Keith:
     - nvme-auth updates (Mark)
     - nvme-tcp tls (Hannes)
     - nvme-fc annotaions (Kees)

 - Misc cleanups and improvements (Jiapeng, Joel)

* tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux: (95 commits)
  block: ublk_drv: Remove unused function
  md: cleanup pers->prepare_suspend()
  nvme-auth: allow mixing of secret and hash lengths
  nvme-auth: use transformed key size to create resp
  nvme-auth: alloc nvme_dhchap_key as single buffer
  nvmet-tcp: use 'spin_lock_bh' for state_lock()
  powerpc/pseries: PLPKS SED Opal keystore support
  block: sed-opal: keystore access for SED Opal keys
  block:sed-opal: SED Opal keystore
  ublk: simplify aborting request
  ublk: replace monitor with cancelable uring_cmd
  ublk: quiesce request queue when aborting queue
  ublk: rename mm_lock as lock
  ublk: move ublk_cancel_dev() out of ub->mutex
  ublk: make sure io cmd handled in submitter task context
  ublk: don't get ublk device reference in ublk_abort_queue()
  ublk: Make ublks_max configurable
  ublk: Limit dev_id/ub_number values
  md-cluster: check for timeout while a new disk adding
  nvme: rework NVME_AUTH Kconfig selection
  ...

10 files changed, 318 insertions, 45 deletions

diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 2f6a7f8c94e8..48f7d72de5e9 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -92,16 +92,26 @@ config NVME_TCP
 
 	  If unsure, say N.
 
-config NVME_AUTH
+config NVME_TCP_TLS
+	bool "NVMe over Fabrics TCP TLS encryption support"
+	depends on NVME_TCP
+	select NVME_COMMON
+	select NVME_KEYRING
+	select NET_HANDSHAKE
+	select KEYS
+	help
+	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
+
+	  The TLS handshake daemon is availble at
+	  https://github.com/oracle/ktls-utils.
+
+	  If unsure, say N.
+
+config NVME_HOST_AUTH
 	bool "NVM Express over Fabrics In-Band Authentication"
 	depends on NVME_CORE
 	select NVME_COMMON
-	select CRYPTO
-	select CRYPTO_HMAC
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
-	select CRYPTO_DH
-	select CRYPTO_DH_RFC7919_GROUPS
+	select NVME_AUTH
 	help
 	  This provides support for NVMe over Fabrics In-Band Authentication.
 
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index c7c3cf202d12..6414ec968f99 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -17,7 +17,7 @@ nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
-nvme-core-$(CONFIG_NVME_AUTH)		+= auth.o
+nvme-core-$(CONFIG_NVME_HOST_AUTH)	+= auth.o
 
 nvme-y					+= pci.o
 
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 064592a5d546..eaefebb2a799 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -23,6 +23,7 @@ struct nvme_dhchap_queue_context {
 	struct nvme_ctrl *ctrl;
 	struct crypto_shash *shash_tfm;
 	struct crypto_kpp *dh_tfm;
+	struct nvme_dhchap_key *transformed_key;
 	void *buf;
 	int qid;
 	int error;
@@ -36,7 +37,6 @@ struct nvme_dhchap_queue_context {
 	u8 c1[64];
 	u8 c2[64];
 	u8 response[64];
-	u8 *host_response;
 	u8 *ctrl_key;
 	u8 *host_key;
 	u8 *sess_key;
@@ -428,12 +428,12 @@ static int nvme_auth_dhchap_setup_host_response(struct nvme_ctrl *ctrl,
 	dev_dbg(ctrl->device, "%s: qid %d host response seq %u transaction %d\n",
 		__func__, chap->qid, chap->s1, chap->transaction);
 
-	if (!chap->host_response) {
-		chap->host_response = nvme_auth_transform_key(ctrl->host_key,
+	if (!chap->transformed_key) {
+		chap->transformed_key = nvme_auth_transform_key(ctrl->host_key,
 						ctrl->opts->host->nqn);
-		if (IS_ERR(chap->host_response)) {
-			ret = PTR_ERR(chap->host_response);
-			chap->host_response = NULL;
+		if (IS_ERR(chap->transformed_key)) {
+			ret = PTR_ERR(chap->transformed_key);
+			chap->transformed_key = NULL;
 			return ret;
 		}
 	} else {
@@ -442,7 +442,7 @@ static int nvme_auth_dhchap_setup_host_response(struct nvme_ctrl *ctrl,
 	}
 
 	ret = crypto_shash_setkey(chap->shash_tfm,
-			chap->host_response, ctrl->host_key->len);
+			chap->transformed_key->key, chap->transformed_key->len);
 	if (ret) {
 		dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n",
 			 chap->qid, ret);
@@ -508,19 +508,19 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl,
 		struct nvme_dhchap_queue_context *chap)
 {
 	SHASH_DESC_ON_STACK(shash, chap->shash_tfm);
-	u8 *ctrl_response;
+	struct nvme_dhchap_key *transformed_key;
 	u8 buf[4], *challenge = chap->c2;
 	int ret;
 
-	ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key,
+	transformed_key = nvme_auth_transform_key(ctrl->ctrl_key,
 				ctrl->opts->subsysnqn);
-	if (IS_ERR(ctrl_response)) {
-		ret = PTR_ERR(ctrl_response);
+	if (IS_ERR(transformed_key)) {
+		ret = PTR_ERR(transformed_key);
 		return ret;
 	}
 
 	ret = crypto_shash_setkey(chap->shash_tfm,
-			ctrl_response, ctrl->ctrl_key->len);
+			transformed_key->key, transformed_key->len);
 	if (ret) {
 		dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n",
 			 chap->qid, ret);
@@ -586,7 +586,7 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl,
 out:
 	if (challenge != chap->c2)
 		kfree(challenge);
-	kfree(ctrl_response);
+	nvme_auth_free_key(transformed_key);
 	return ret;
 }
 
@@ -648,8 +648,8 @@ gen_sesskey:
 
 static void nvme_auth_reset_dhchap(struct nvme_dhchap_queue_context *chap)
 {
-	kfree_sensitive(chap->host_response);
-	chap->host_response = NULL;
+	nvme_auth_free_key(chap->transformed_key);
+	chap->transformed_key = NULL;
 	kfree_sensitive(chap->host_key);
 	chap->host_key = NULL;
 	chap->host_key_len = 0;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 21783aa2ee8e..62612f87aafa 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -25,6 +25,7 @@
 #include "nvme.h"
 #include "fabrics.h"
 #include <linux/nvme-auth.h>
+#include <linux/nvme-keyring.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -420,7 +421,7 @@ void nvme_complete_rq(struct request *req)
 		nvme_failover_req(req);
 		return;
 	case AUTHENTICATE:
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 		queue_work(nvme_wq, &ctrl->dhchap_auth_work);
 		nvme_retry_req(req);
 #else
@@ -4399,7 +4400,7 @@ 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);
 	nvme_auth_stop(ctrl);
@@ -4723,12 +4724,16 @@ static int __init nvme_core_init(void)
 		result = PTR_ERR(nvme_ns_chr_class);
 		goto unregister_generic_ns;
 	}
-
-	result = nvme_init_auth();
+	result = nvme_keyring_init();
 	if (result)
 		goto destroy_ns_chr;
+	result = nvme_init_auth();
+	if (result)
+		goto keyring_exit;
 	return 0;
 
+keyring_exit:
+	nvme_keyring_exit();
 destroy_ns_chr:
 	class_destroy(nvme_ns_chr_class);
 unregister_generic_ns:
@@ -4752,6 +4757,7 @@ out:
 static void __exit nvme_core_exit(void)
 {
 	nvme_exit_auth();
+	nvme_keyring_exit();
 	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 8175d49f2909..4673ead69c5f 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include "nvme.h"
 #include "fabrics.h"
+#include <linux/nvme-keyring.h>
 
 static LIST_HEAD(nvmf_transports);
 static DECLARE_RWSEM(nvmf_transports_rwsem);
@@ -622,6 +623,23 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 	return NULL;
 }
 
+static struct key *nvmf_parse_key(int key_id)
+{
+	struct key *key;
+
+	if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) {
+		pr_err("TLS is not supported\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	key = key_lookup(key_id);
+	if (!IS_ERR(key))
+		pr_err("key id %08x not found\n", key_id);
+	else
+		pr_debug("Using key id %08x\n", key_id);
+	return key;
+}
+
 static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},
 	{ NVMF_OPT_TRADDR,		"traddr=%s"		},
@@ -643,10 +661,17 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_NR_WRITE_QUEUES,	"nr_write_queues=%d"	},
 	{ NVMF_OPT_NR_POLL_QUEUES,	"nr_poll_queues=%d"	},
 	{ NVMF_OPT_TOS,			"tos=%d"		},
+#ifdef CONFIG_NVME_TCP_TLS
+	{ NVMF_OPT_KEYRING,		"keyring=%d"		},
+	{ NVMF_OPT_TLS_KEY,		"tls_key=%d"		},
+#endif
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
 	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+#ifdef CONFIG_NVME_TCP_TLS
+	{ NVMF_OPT_TLS,			"tls"			},
+#endif
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -657,9 +682,10 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	char *options, *o, *p;
 	int token, ret = 0;
 	size_t nqnlen  = 0;
-	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
+	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO, key_id;
 	uuid_t hostid;
 	char hostnqn[NVMF_NQN_SIZE];
+	struct key *key;
 
 	/* Set defaults */
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -671,6 +697,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	opts->hdr_digest = false;
 	opts->data_digest = false;
 	opts->tos = -1; /* < 0 == use transport default */
+	opts->tls = false;
+	opts->tls_key = NULL;
+	opts->keyring = NULL;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -924,6 +953,32 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			}
 			opts->tos = token;
 			break;
+		case NVMF_OPT_KEYRING:
+			if (match_int(args, &key_id) || key_id <= 0) {
+				ret = -EINVAL;
+				goto out;
+			}
+			key = nvmf_parse_key(key_id);
+			if (IS_ERR(key)) {
+				ret = PTR_ERR(key);
+				goto out;
+			}
+			key_put(opts->keyring);
+			opts->keyring = key;
+			break;
+		case NVMF_OPT_TLS_KEY:
+			if (match_int(args, &key_id) || key_id <= 0) {
+				ret = -EINVAL;
+				goto out;
+			}
+			key = nvmf_parse_key(key_id);
+			if (IS_ERR(key)) {
+				ret = PTR_ERR(key);
+				goto out;
+			}
+			key_put(opts->tls_key);
+			opts->tls_key = key;
+			break;
 		case NVMF_OPT_DISCOVERY:
 			opts->discovery_nqn = true;
 			break;
@@ -955,6 +1010,14 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			kfree(opts->dhchap_ctrl_secret);
 			opts->dhchap_ctrl_secret = p;
 			break;
+		case NVMF_OPT_TLS:
+			if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) {
+				pr_err("TLS is not supported\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			opts->tls = true;
+			break;
 		default:
 			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
 				p);
@@ -1156,6 +1219,8 @@ static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
 void nvmf_free_options(struct nvmf_ctrl_options *opts)
 {
 	nvmf_host_put(opts->host);
+	key_put(opts->keyring);
+	key_put(opts->tls_key);
 	kfree(opts->transport);
 	kfree(opts->traddr);
 	kfree(opts->trsvcid);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 82e7a27ffbde..fbaee5a7be19 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -70,6 +70,9 @@ enum {
 	NVMF_OPT_DISCOVERY	= 1 << 22,
 	NVMF_OPT_DHCHAP_SECRET	= 1 << 23,
 	NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24,
+	NVMF_OPT_TLS		= 1 << 25,
+	NVMF_OPT_KEYRING	= 1 << 26,
+	NVMF_OPT_TLS_KEY	= 1 << 27,
 };
 
 /**
@@ -102,6 +105,9 @@ enum {
  * @dhchap_secret: DH-HMAC-CHAP secret
  * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional
  *              authentication
+ * @keyring:    Keyring to use for key lookups
+ * @tls_key:    TLS key for encrypted connections (TCP)
+ * @tls:        Start TLS encrypted connections (TCP)
  * @disable_sqflow: disable controller sq flow control
  * @hdr_digest: generate/verify header digest (TCP)
  * @data_digest: generate/verify data digest (TCP)
@@ -128,6 +134,9 @@ struct nvmf_ctrl_options {
 	struct nvmf_host	*host;
 	char			*dhchap_secret;
 	char			*dhchap_ctrl_secret;
+	struct key		*keyring;
+	struct key		*tls_key;
+	bool			tls;
 	bool			disable_sqflow;
 	bool			hdr_digest;
 	bool			data_digest;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f35647c470af..39a90b7cb125 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -349,7 +349,7 @@ struct nvme_ctrl {
 	struct work_struct ana_work;
 #endif
 
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 	struct work_struct dhchap_auth_work;
 	struct mutex dhchap_auth_mutex;
 	struct nvme_dhchap_queue_context *dhchap_ctxs;
@@ -357,6 +357,7 @@ struct nvme_ctrl {
 	struct nvme_dhchap_key *ctrl_key;
 	u16 transaction;
 #endif
+	struct key *tls_key;
 
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
@@ -1048,7 +1049,7 @@ static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl)
 	return ctrl->sgls & ((1 << 0) | (1 << 1));
 }
 
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 int __init nvme_init_auth(void);
 void __exit nvme_exit_auth(void);
 int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3f0c9ee09a12..507bc149046d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -924,7 +924,6 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
 	if (unlikely(!nvme_check_ready(&nvmeq->dev->ctrl, req, true)))
 		return false;
 
-	req->mq_hctx->tags->rqs[req->tag] = req;
 	return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
 }
 
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 212e1b05d298..c6b7fbd4d34d 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -409,7 +409,7 @@ static ssize_t dctype_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(dctype);
 
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -527,6 +527,19 @@ 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,
@@ -550,10 +563,13 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_kato.attr,
 	&dev_attr_cntrltype.attr,
 	&dev_attr_dctype.attr,
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 	&dev_attr_dhchap_secret.attr,
 	&dev_attr_dhchap_ctrl_secret.attr,
 #endif
+#ifdef CONFIG_NVME_TCP_TLS
+	&dev_attr_tls_key.attr,
+#endif
 	NULL
 };
 
@@ -577,12 +593,17 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 		return 0;
 	if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts)
 		return 0;
-#ifdef CONFIG_NVME_AUTH
+#ifdef CONFIG_NVME_HOST_AUTH
 	if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts)
 		return 0;
 	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;
 }
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 5b332d9f87fc..4714a902f4ca 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -8,9 +8,14 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/key.h>
 #include <linux/nvme-tcp.h>
+#include <linux/nvme-keyring.h>
 #include <net/sock.h>
 #include <net/tcp.h>
+#include <net/tls.h>
+#include <net/tls_prot.h>
+#include <net/handshake.h>
 #include <linux/blk-mq.h>
 #include <crypto/hash.h>
 #include <net/busy_poll.h>
@@ -31,6 +36,16 @@ static int so_priority;
 module_param(so_priority, int, 0644);
 MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
 
+#ifdef CONFIG_NVME_TCP_TLS
+/*
+ * TLS handshake timeout
+ */
+static int tls_handshake_timeout = 10;
+module_param(tls_handshake_timeout, int, 0644);
+MODULE_PARM_DESC(tls_handshake_timeout,
+		 "nvme TLS handshake timeout in seconds (default 10)");
+#endif
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 /* lockdep can detect a circular dependency of the form
  *   sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock
@@ -146,7 +161,10 @@ struct nvme_tcp_queue {
 	struct ahash_request	*snd_hash;
 	__le32			exp_ddgst;
 	__le32			recv_ddgst;
-
+#ifdef CONFIG_NVME_TCP_TLS
+	struct completion       tls_complete;
+	int                     tls_err;
+#endif
 	struct page_frag_cache	pf_cache;
 
 	void (*state_change)(struct sock *);
@@ -1338,7 +1356,9 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 	}
 
 	noreclaim_flag = memalloc_noreclaim_save();
-	sock_release(queue->sock);
+	/* ->sock will be released by fput() */
+	fput(queue->sock->file);
+	queue->sock = NULL;
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	kfree(queue->pdu);
@@ -1350,6 +1370,8 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 {
 	struct nvme_tcp_icreq_pdu *icreq;
 	struct nvme_tcp_icresp_pdu *icresp;
+	char cbuf[CMSG_LEN(sizeof(char))] = {};
+	u8 ctype;
 	struct msghdr msg = {};
 	struct kvec iov;
 	bool ctrl_hdgst, ctrl_ddgst;
@@ -1381,17 +1403,35 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	iov.iov_base = icreq;
 	iov.iov_len = sizeof(*icreq);
 	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
-	if (ret < 0)
+	if (ret < 0) {
+		pr_warn("queue %d: failed to send icreq, error %d\n",
+			nvme_tcp_queue_id(queue), ret);
 		goto free_icresp;
+	}
 
 	memset(&msg, 0, sizeof(msg));
 	iov.iov_base = icresp;
 	iov.iov_len = sizeof(*icresp);
+	if (queue->ctrl->ctrl.opts->tls) {
+		msg.msg_control = cbuf;
+		msg.msg_controllen = sizeof(cbuf);
+	}
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < 0)
+	if (ret < 0) {
+		pr_warn("queue %d: failed to receive icresp, error %d\n",
+			nvme_tcp_queue_id(queue), ret);
 		goto free_icresp;
-
+	}
+	if (queue->ctrl->ctrl.opts->tls) {
+		ctype = tls_get_record_type(queue->sock->sk,
+					    (struct cmsghdr *)cbuf);
+		if (ctype != TLS_RECORD_TYPE_DATA) {
+			pr_err("queue %d: unhandled TLS record %d\n",
+			       nvme_tcp_queue_id(queue), ctype);
+			return -ENOTCONN;
+		}
+	}
 	ret = -EINVAL;
 	if (icresp->hdr.type != nvme_tcp_icresp) {
 		pr_err("queue %d: bad type returned %d\n",
@@ -1507,11 +1547,99 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 	queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
 }
 
-static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
+#ifdef CONFIG_NVME_TCP_TLS
+static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
+{
+	struct nvme_tcp_queue *queue = data;
+	struct nvme_tcp_ctrl *ctrl = queue->ctrl;
+	int qid = nvme_tcp_queue_id(queue);
+	struct key *tls_key;
+
+	dev_dbg(ctrl->ctrl.device, "queue %d: TLS handshake done, key %x, status %d\n",
+		qid, pskid, status);
+
+	if (status) {
+		queue->tls_err = -status;
+		goto out_complete;
+	}
+
+	tls_key = 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_err = 0;
+	}
+
+out_complete:
+	complete(&queue->tls_complete);
+}
+
+static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
+			      struct nvme_tcp_queue *queue,
+			      key_serial_t pskid)
+{
+	int qid = nvme_tcp_queue_id(queue);
+	int ret;
+	struct tls_handshake_args args;
+	unsigned long tmo = tls_handshake_timeout * HZ;
+	key_serial_t keyring = nvme_keyring_id();
+
+	dev_dbg(nctrl->device, "queue %d: start TLS with key %x\n",
+		qid, pskid);
+	memset(&args, 0, sizeof(args));
+	args.ta_sock = queue->sock;
+	args.ta_done = nvme_tcp_tls_done;
+	args.ta_data = queue;
+	args.ta_my_peerids[0] = pskid;
+	args.ta_num_peerids = 1;
+	if (nctrl->opts->keyring)
+		keyring = key_serial(nctrl->opts->keyring);
+	args.ta_keyring = keyring;
+	args.ta_timeout_ms = tls_handshake_timeout * 1000;
+	queue->tls_err = -EOPNOTSUPP;
+	init_completion(&queue->tls_complete);
+	ret = tls_client_hello_psk(&args, GFP_KERNEL);
+	if (ret) {
+		dev_err(nctrl->device, "queue %d: failed to start TLS: %d\n",
+			qid, ret);
+		return ret;
+	}
+	ret = wait_for_completion_interruptible_timeout(&queue->tls_complete, tmo);
+	if (ret <= 0) {
+		if (ret == 0)
+			ret = -ETIMEDOUT;
+
+		dev_err(nctrl->device,
+			"queue %d: TLS handshake failed, error %d\n",
+			qid, ret);
+		tls_handshake_cancel(queue->sock->sk);
+	} else {
+		dev_dbg(nctrl->device,
+			"queue %d: TLS handshake complete, error %d\n",
+			qid, queue->tls_err);
+		ret = queue->tls_err;
+	}
+	return ret;
+}
+#else
+static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
+			      struct nvme_tcp_queue *queue,
+			      key_serial_t pskid)
+{
+	return -EPROTONOSUPPORT;
+}
+#endif
+
+static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
+				key_serial_t pskid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
 	int ret, rcv_pdu_size;
+	struct file *sock_file;
 
 	mutex_init(&queue->queue_lock);
 	queue->ctrl = ctrl;
@@ -1534,6 +1662,11 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 		goto err_destroy_mutex;
 	}
 
+	sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL);
+	if (IS_ERR(sock_file)) {
+		ret = PTR_ERR(sock_file);
+		goto err_destroy_mutex;
+	}
 	nvme_tcp_reclassify_socket(queue->sock);
 
 	/* Single syn retry */
@@ -1624,6 +1757,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 		goto err_rcv_pdu;
 	}
 
+	/* If PSKs are configured try to start TLS */
+	if (pskid) {
+		ret = nvme_tcp_start_tls(nctrl, queue, pskid);
+		if (ret)
+			goto err_init_connect;
+	}
+
 	ret = nvme_tcp_init_connection(queue);
 	if (ret)
 		goto err_init_connect;
@@ -1640,7 +1780,8 @@ err_crypto:
 	if (queue->hdr_digest || queue->data_digest)
 		nvme_tcp_free_crypto(queue);
 err_sock:
-	sock_release(queue->sock);
+	/* ->sock will be released by fput() */
+	fput(queue->sock->file);
 	queue->sock = NULL;
 err_destroy_mutex:
 	mutex_destroy(&queue->send_mutex);
@@ -1772,10 +1913,25 @@ out_stop_queues:
 static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 {
 	int ret;
+	key_serial_t pskid = 0;
 
-	ret = nvme_tcp_alloc_queue(ctrl, 0);
+	if (ctrl->opts->tls) {
+		if (ctrl->opts->tls_key)
+			pskid = key_serial(ctrl->opts->tls_key);
+		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");
+			ret = -ENOKEY;
+			goto out_free_queue;
+		}
+	}
+
+	ret = nvme_tcp_alloc_queue(ctrl, 0, pskid);
 	if (ret)
-		return ret;
+		goto out_free_queue;
 
 	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
 	if (ret)
@@ -1792,8 +1948,13 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	int i, ret;
 
+	if (ctrl->opts->tls && !ctrl->tls_key) {
+		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);
+		ret = nvme_tcp_alloc_queue(ctrl, i,
+				key_serial(ctrl->tls_key));
 		if (ret)
 			goto out_free_queues;
 	}
@@ -2621,7 +2782,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
 			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
 			  NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
 			  NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
-			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE,
+			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE | NVMF_OPT_TLS |
+			  NVMF_OPT_KEYRING | NVMF_OPT_TLS_KEY,
 	.create_ctrl	= nvme_tcp_create_ctrl,
 };