Skip to contentSkip to conversation

nvme: In-kernel TLS support for TCP

PATCH Superseded Hannes Reinecke 4 participants 49 messages Apr 17, 2023 – Apr 18, 2023

Subsystems (7)

v3 of 11 Superseded Latest is v11 →

lore
Share & tools
lore
#0 lore raw

v3 cover nvme: In-kernel TLS support for TCP

Hi all,

finally I've managed to put all things together and enable in-kernel TLS support for NVMe-over-TCP.

The patchset is based on the TLS upcall mechanism from Chuck Lever (cf '[PATCH v7 0/2] Another crack at a handshake upcall mechanism' posted to the linux netdev list), and requires the 'tlshd' userspace daemon (https://github.com/oracle/ktls-utils) for the actual TLS handshake. Changes for nvme-cli are already included in the upstream repository.

Theory of operation:
A dedicated '.nvme' keyring is created to hold the pre-shared keys (PSKs) for the TLS handshake. Keys will have to be provisioned before TLS handshake is attempted; that can be done with the 'nvme gen-tls-key' command for nvme-cli (patches are already merged upstream).
After connection to the remote TCP port the client side will use the 'best' PSK (as inferred from the NVMe TCP spec) or the PSK specified by the '--tls_key' option to nvme-cli and call the TLS userspace daemon to initiate a TLS handshake.
The server side will then invoke the TLS userspace daemon to run the TLS handshake.
If the TLS handshake succeeds the userspace daemon will be activating kTLS on the socket, and control is passed back to the kernel.

To make this work I had to implement the 'read_sock()' functionality for TLS; it seems to be holding up well enough (for me), but it really could do with reviews from persons with more network stack knowledge.

As usual, comments and reviews are welcome.

Changes to v2:
- Included reviews from Sagi
- Removed MSG_SENDPAGE_NOTLAST
- Improved MSG_EOR handling for TLS
- Add config options NVME_TCP_TLS
and NVME_TARGET_TCP_TLS

Changes to the original RFC:
- Add a CONFIG_NVME_TLS config option
- Use a single PSK for the TLS handshake
- Make TLS connections mandatory
- Do not peek messages for the server
- Simplify data_ready callback
- Implement read_sock() for TLS

Hannes Reinecke (18):
nvme-keyring: register '.nvme' keyring
nvme-keyring: define a 'psk' keytype
nvme: add TCP TSAS definitions
nvme-tcp: add definitions for TLS cipher suites
nvme-keyring: implement nvme_tls_psk_default() net/tls: implement ->read_sock()
net/tls: sanitize MSG_EOR handling
nvme-tcp: do not set MSG_SENDPAGE_NOTLAST security/keys: export key_lookup() nvme/tcp: allocate socket file
nvme-tcp: enable TLS handshake upcall
nvme-tcp: control message handling for recvmsg()
nvme-fabrics: parse options 'keyring' and 'tls_key'
nvmet: make TCP sectype settable via configfs
nvmet-tcp: allocate socket file
nvmet-tcp: enable TLS handshake upcall
nvmet-tcp: control messages for recvmsg()
nvmet-tcp: add configfs attribute 'param_keyring'

 drivers/nvme/common/Kconfig    |   4 +
 drivers/nvme/common/Makefile   |   3 +-
 drivers/nvme/common/keyring.c  | 182 ++++++++++++++++++++++++++++
 drivers/nvme/host/Kconfig      |  14 +++
 drivers/nvme/host/core.c       |  33 ++++-
 drivers/nvme/host/fabrics.c    |  77 +++++++++++-
 drivers/nvme/host/fabrics.h    |   9 ++
 drivers/nvme/host/nvme.h       |   1 +
 drivers/nvme/host/tcp.c        | 175 +++++++++++++++++++++++++--
 drivers/nvme/target/Kconfig    |  14 +++
 drivers/nvme/target/configfs.c | 173 +++++++++++++++++++++++++-
 drivers/nvme/target/nvmet.h    |   1 +
 drivers/nvme/target/tcp.c      | 213 ++++++++++++++++++++++++++++++---
 include/linux/nvme-keyring.h   |  36 ++++++
 include/linux/nvme-tcp.h       |   6 +
 include/linux/nvme.h           |  10 ++
 net/tls/tls.h                  |   2 +
 net/tls/tls_device.c           |  10 ++
 net/tls/tls_main.c             |   2 +
 net/tls/tls_sw.c               |  92 ++++++++++++++
 security/keys/key.c            |   1 +
 21 files changed, 1020 insertions(+), 38 deletions(-)
 create mode 100644 drivers/nvme/common/keyring.c
 create mode 100644 include/linux/nvme-keyring.h
Signature · 1 line
2.35.3
#1 lore raw

PATCH v3 1/18 nvme-keyring: register '.nvme' keyring

Register a '.nvme' keyring to hold keys for TLS and DH-HMAC-CHAP and add a new config option NVME_KEYRING.
We need a separate keyring for NVMe as the configuration is done via individual commands (eg for configfs), and the usual per-session or per-process keyrings can't be used.

---
 drivers/nvme/common/Kconfig   |  4 ++++
 drivers/nvme/common/Makefile  |  3 ++-
 drivers/nvme/common/keyring.c | 40 +++++++++++++++++++++++++++++++++++
 drivers/nvme/host/core.c      | 10 +++++++--
 include/linux/nvme-keyring.h  | 28 ++++++++++++++++++++++++
 5 files changed, 82 insertions(+), 3 deletions(-)
 create mode 100644 drivers/nvme/common/keyring.c
 create mode 100644 include/linux/nvme-keyring.h
drivers/nvme/common/Kconfig +4 -0
index 4514f44362dd..641b27adb047 100644
@@ -2,3 +2,7 @@
 
 config NVME_COMMON
        tristate
+
+config NVME_KEYRING
+       bool
+       select KEYS
drivers/nvme/common/Makefile +2 -1
index 720c625b8a52..0cbd0b0b8d49 100644
@@ -4,4 +4,5 @@ ccflags-y			+= -I$(src)
 
 obj-$(CONFIG_NVME_COMMON)	+= nvme-common.o
 
-nvme-common-y			+= auth.o
+nvme-common-$(CONFIG_NVME_AUTH)	+= auth.o
+nvme-common-$(CONFIG_NVME_KEYRING) += keyring.o
drivers/nvme/common/keyring.c new file +40 -0
new file mode 100644
index 000000000000..5cf64b278119
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Hannes Reinecke, SUSE Labs
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/nvme.h>
+
+static struct key *nvme_keyring;
+
+key_serial_t nvme_keyring_id(void)
+{
+	return nvme_keyring->serial;
+}
+EXPORT_SYMBOL_GPL(nvme_keyring_id);
+
+int nvme_keyring_init(void)
+{
+	nvme_keyring = keyring_alloc(".nvme",
+				     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				     current_cred(),
+				     (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				     (KEY_USR_ALL & ~KEY_USR_SETATTR),
+				     KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	if (IS_ERR(nvme_keyring))
+		return PTR_ERR(nvme_keyring);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_keyring_init);
+
+void nvme_keyring_exit(void)
+{
+	key_revoke(nvme_keyring);
+	key_put(nvme_keyring);
+}
+EXPORT_SYMBOL_GPL(nvme_keyring_exit);
drivers/nvme/host/core.c +8 -2
index 6c1e7d6709e0..79aa215aec76 100644
@@ -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"
@@ -5401,12 +5402,16 @@ 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:
@@ -5430,6 +5435,7 @@ static int __init nvme_core_init(void)
 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);
include/linux/nvme-keyring.h new file +28 -0
new file mode 100644
index 000000000000..32bd264a71e6
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Hannes Reinecke, SUSE Labs
+ */
+
+#ifndef _NVME_KEYRING_H
+#define _NVME_KEYRING_H
+
+#ifdef CONFIG_NVME_KEYRING
+
+key_serial_t nvme_keyring_id(void);
+int nvme_keyring_init(void);
+void nvme_keyring_exit(void);
+
+#else
+
+static inline key_serial_t nvme_keyring_id(void)
+{
+	return 0;
+}
+static inline int nvme_keyring_init(void)
+{
+	return 0;
+}
+static inline void nvme_keyring_exit(void) {}
+
+#endif /* !CONFIG_NVME_KEYRING */
+#endif /* _NVME_KEYRING_H */
Signature · 1 line
2.35.3
#2 lore raw

PATCH v3 2/18 nvme-keyring: define a 'psk' keytype

In reply to Hannes Reinecke

Define a 'psk' keytype to hold the NVMe TLS PSKs.

---
 drivers/nvme/common/keyring.c | 94 +++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)
drivers/nvme/common/keyring.c +94 -0
index 5cf64b278119..494dd365052e 100644
@@ -8,6 +8,8 @@
 #include <linux/key-type.h>
 #include <keys/user-type.h>
 #include <linux/nvme.h>
+#include <linux/nvme-tcp.h>
+#include <linux/nvme-keyring.h>
 
 static struct key *nvme_keyring;
 
@@ -17,8 +19,94 @@ key_serial_t nvme_keyring_id(void)
 }
 EXPORT_SYMBOL_GPL(nvme_keyring_id);
 
+static void nvme_tls_psk_describe(const struct key *key, struct seq_file *m)
+{
+	seq_puts(m, key->description);
+	seq_printf(m, ": %u", key->datalen);
+}
+
+static bool nvme_tls_psk_match(const struct key *key,
+			       const struct key_match_data *match_data)
+{
+	const char *match_id;
+	size_t match_len;
+
+	if (!key->description) {
+		pr_debug("%s: no key description\n", __func__);
+		return false;
+	}
+	match_len = strlen(key->description);
+	pr_debug("%s: id %s len %zd\n", __func__, key->description, match_len);
+
+	if (!match_data->raw_data) {
+		pr_debug("%s: no match data\n", __func__);
+		return false;
+	}
+	match_id = match_data->raw_data;
+	pr_debug("%s: match '%s' '%s' len %zd\n",
+		 __func__, match_id, key->description, match_len);
+	return !memcmp(key->description, match_id, match_len);
+}
+
+static int nvme_tls_psk_match_preparse(struct key_match_data *match_data)
+{
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	match_data->cmp = nvme_tls_psk_match;
+	return 0;
+}
+
+static struct key_type nvme_tls_psk_key_type = {
+	.name           = "psk",
+	.flags          = KEY_TYPE_NET_DOMAIN,
+	.preparse       = user_preparse,
+	.free_preparse  = user_free_preparse,
+	.match_preparse = nvme_tls_psk_match_preparse,
+	.instantiate    = generic_key_instantiate,
+	.revoke         = user_revoke,
+	.destroy        = user_destroy,
+	.describe       = nvme_tls_psk_describe,
+	.read           = user_read,
+};
+
+static struct key *nvme_tls_psk_lookup(struct key *keyring,
+		const char *hostnqn, const char *subnqn,
+		int hmac, bool generated)
+{
+	char *identity;
+	size_t identity_len = (NVMF_NQN_SIZE) * 2 + 11;
+	key_ref_t keyref;
+	key_serial_t keyring_id;
+
+	identity = kzalloc(identity_len, GFP_KERNEL);
+	if (!identity)
+		return ERR_PTR(-ENOMEM);
+
+	snprintf(identity, identity_len, "NVMe0%c%02d %s %s",
+		 generated ? 'G' : 'R', hmac, hostnqn, subnqn);
+
+	if (!keyring)
+		keyring = nvme_keyring;
+	keyring_id = key_serial(keyring);
+	pr_debug("keyring %x lookup tls psk '%s'\n",
+		 keyring_id, identity);
+	keyref = keyring_search(make_key_ref(keyring, true),
+				&nvme_tls_psk_key_type,
+				identity, false);
+	if (IS_ERR(keyref)) {
+		pr_debug("lookup tls psk '%s' failed, error %ld\n",
+			 identity, PTR_ERR(keyref));
+		kfree(identity);
+		return ERR_PTR(-ENOKEY);
+	}
+	kfree(identity);
+
+	return key_ref_to_ptr(keyref);
+}
+
 int nvme_keyring_init(void)
 {
+	int err;
+
 	nvme_keyring = keyring_alloc(".nvme",
 				     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
 				     current_cred(),
@@ -28,12 +116,18 @@ int nvme_keyring_init(void)
 	if (IS_ERR(nvme_keyring))
 		return PTR_ERR(nvme_keyring);
 
+	err = register_key_type(&nvme_tls_psk_key_type);
+	if (err) {
+		key_put(nvme_keyring);
+		return err;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvme_keyring_init);
 
 void nvme_keyring_exit(void)
 {
+	unregister_key_type(&nvme_tls_psk_key_type);
 	key_revoke(nvme_keyring);
 	key_put(nvme_keyring);
 }
Signature · 1 line
2.35.3
#3 lore raw

PATCH v3 3/18 nvme: add TCP TSAS definitions

In reply to Hannes Reinecke
---
 include/linux/nvme.h | 10 ++++++++++
 1 file changed, 10 insertions(+)
include/linux/nvme.h +10 -0
index 4fad4aa245fb..6e55a7a701e6 100644
@@ -108,6 +108,13 @@ enum {
 	NVMF_RDMA_CMS_RDMA_CM	= 1, /* Sockets based endpoint addressing */
 };
 
+/* TSAS SECTYPE for TCP transport */
+enum {
+	NVMF_TCP_SECTYPE_NONE = 0, /* No Security */
+	NVMF_TCP_SECTYPE_TLS12 = 1, /* TLSv1.2, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */
+	NVMF_TCP_SECTYPE_TLS13 = 2, /* TLSv1.3, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */
+};
+
 #define NVME_AQ_DEPTH		32
 #define NVME_NR_AEN_COMMANDS	1
 #define NVME_AQ_BLK_MQ_DEPTH	(NVME_AQ_DEPTH - NVME_NR_AEN_COMMANDS)
@@ -1453,6 +1460,9 @@ struct nvmf_disc_rsp_page_entry {
 			__u16	pkey;
 			__u8	resv10[246];
 		} rdma;
+		struct tcp {
+			__u8	sectype;
+		} tcp;
 	} tsas;
 };
 
Signature · 1 line
2.35.3
#4 lore raw

PATCH v3 4/18 nvme-tcp: add definitions for TLS cipher suites

In reply to Hannes Reinecke
---
 include/linux/nvme-tcp.h | 6 ++++++
 1 file changed, 6 insertions(+)
include/linux/nvme-tcp.h +6 -0
index 75470159a194..19ca863813f1 100644
@@ -18,6 +18,12 @@ enum nvme_tcp_pfv {
 	NVME_TCP_PFV_1_0 = 0x0,
 };
 
+enum nvme_tcp_tls_cipher {
+	NVME_TCP_TLS_CIPHER_INVALID     = 0,
+	NVME_TCP_TLS_CIPHER_SHA256      = 1,
+	NVME_TCP_TLS_CIPHER_SHA384      = 2,
+};
+
 enum nvme_tcp_fatal_error_status {
 	NVME_TCP_FES_INVALID_PDU_HDR		= 0x01,
 	NVME_TCP_FES_PDU_SEQ_ERR		= 0x02,
Signature · 1 line
2.35.3
#5 lore raw

PATCH v3 5/18 nvme-keyring: implement nvme_tls_psk_default()

In reply to Hannes Reinecke

Implement a function to select the preferred PSK for TLS.

---
 drivers/nvme/common/keyring.c | 48 +++++++++++++++++++++++++++++++++++
 include/linux/nvme-keyring.h  |  8 ++++++
 2 files changed, 56 insertions(+)
drivers/nvme/common/keyring.c +48 -0
index 494dd365052e..f8d9a208397b 100644
@@ -5,6 +5,7 @@
 
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/key.h>
 #include <linux/key-type.h>
 #include <keys/user-type.h>
 #include <linux/nvme.h>
@@ -103,6 +104,53 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring,
 	return key_ref_to_ptr(keyref);
 }
 
+/*
+ * NVMe PSK priority list
+ *
+ * 'Retained' PSKs (ie 'generated == false')
+ * should be preferred to 'generated' PSKs,
+ * and SHA-384 should be preferred to SHA-256.
+ */
+struct nvme_tls_psk_priority_list {
+	bool generated;
+	enum nvme_tcp_tls_cipher cipher;
+} nvme_tls_psk_prio[] = {
+	{ .generated = false,
+	  .cipher = NVME_TCP_TLS_CIPHER_SHA384, },
+	{ .generated = false,
+	  .cipher = NVME_TCP_TLS_CIPHER_SHA256, },
+	{ .generated = true,
+	  .cipher = NVME_TCP_TLS_CIPHER_SHA384, },
+	{ .generated = true,
+	  .cipher = NVME_TCP_TLS_CIPHER_SHA256, },
+};
+
+/*
+ * nvme_tls_psk_default - Return the preferred PSK to use for TLS ClientHello
+ */
+key_serial_t nvme_tls_psk_default(struct key *keyring,
+		      const char *hostnqn, const char *subnqn)
+{
+	struct key *tls_key;
+	key_serial_t tls_key_id;
+	int prio;
+
+	for (prio = 0; prio < ARRAY_SIZE(nvme_tls_psk_prio); prio++) {
+		bool generated = nvme_tls_psk_prio[prio].generated;
+		enum nvme_tcp_tls_cipher cipher = nvme_tls_psk_prio[prio].cipher;
+
+		tls_key = nvme_tls_psk_lookup(keyring, hostnqn, subnqn,
+					      cipher, generated);
+		if (!IS_ERR(tls_key)) {
+			tls_key_id = tls_key->serial;
+			key_put(tls_key);
+			return tls_key_id;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_tls_psk_default);
+
 int nvme_keyring_init(void)
 {
 	int err;
include/linux/nvme-keyring.h +8 -0
index 32bd264a71e6..4efea9dd967c 100644
@@ -8,12 +8,20 @@
 
 #ifdef CONFIG_NVME_KEYRING
 
+key_serial_t nvme_tls_psk_default(struct key *keyring,
+		const char *hostnqn, const char *subnqn);
+
 key_serial_t nvme_keyring_id(void);
 int nvme_keyring_init(void);
 void nvme_keyring_exit(void);
 
 #else
 
+static inline key_serial_t nvme_tls_psk_default(struct key *keyring,
+		const char *hostnqn, const char *subnqn)
+{
+	return 0;
+}
 static inline key_serial_t nvme_keyring_id(void)
 {
 	return 0;
Signature · 1 line
2.35.3
#6 lore raw

PATCH v3 6/18 net/tls: implement ->read_sock()

In reply to Hannes Reinecke

Implement ->read_sock() function for use with nvme-tcp.

---
 net/tls/tls.h      |  2 ++
 net/tls/tls_main.c |  2 ++
 net/tls/tls_sw.c   | 71 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 75 insertions(+)
net/tls/tls.h +2 -0
index 804c3880d028..a5bf3a9ce142 100644
@@ -113,6 +113,8 @@ bool tls_sw_sock_is_readable(struct sock *sk);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor);
 
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_device_sendpage(struct sock *sk, struct page *page,
net/tls/tls_main.c +2 -0
index b32c112984dd..0b51b19aa46d 100644
@@ -921,9 +921,11 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
 
 	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
 	ops[TLS_BASE][TLS_SW  ].splice_read	= tls_sw_splice_read;
+	ops[TLS_BASE][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 	ops[TLS_SW  ][TLS_SW  ] = ops[TLS_SW  ][TLS_BASE];
 	ops[TLS_SW  ][TLS_SW  ].splice_read	= tls_sw_splice_read;
+	ops[TLS_SW  ][TLS_SW  ].read_sock	= tls_sw_read_sock;
 
 #ifdef CONFIG_TLS_DEVICE
 	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
net/tls/tls_sw.c +71 -0

77 lines not on this page · raw message

Signature · 1 line
2.35.3
#8 lore raw

PATCH v3 7/18 net/tls: sanitize MSG_EOR handling

In reply to Hannes Reinecke

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

---
 net/tls/tls_device.c | 10 ++++++++++
 net/tls/tls_sw.c     | 21 +++++++++++++++++++++
 2 files changed, 31 insertions(+)
net/tls/tls_device.c +10 -0
index a7cc4f9faac2..38e44e216865 100644
@@ -576,6 +576,10 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
+	/* MSG_EOR conflicts with MSG_MORE, so clear both */
+	if (msg->msg_flags & MSG_EOR)
+		msg->msg_flags &= ~(MSG_EOR | MSG_MORE);
+
 	if (unlikely(msg->msg_controllen)) {
 		rc = tls_process_cmsg(sk, msg, &record_type);
 		if (rc)
@@ -604,6 +608,12 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
+	/*
+	 * MSG_EOR conflicts with MSG_MORE/MSG_SENDPAGE_NOTLAST,
+	 * so clear all of them */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_EOR | MSG_SENDPAGE_NOTLAST | MSG_MORE);
+
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
net/tls/tls_sw.c +21 -0
index 827292e29f99..d0e6b7a04176 100644
@@ -952,6 +952,11 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret = 0;
 	int pending;
 
+	if (msg->msg_flags & MSG_EOR) {
+		eor = true;
+		/* MSG_EOR conflicts with MSG_MORE, so clear both */
+		msg->msg_flags &= ~(MSG_EOR | MSG_MORE);
+	}
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 			       MSG_CMSG_COMPAT))
 		return -EOPNOTSUPP;
@@ -1274,6 +1279,14 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
 			   int offset, size_t size, int flags)
 {
+	/*
+	 * MSG_EOR is invalid for TLS, and conflicts
+	 * with MSG_MORE / MSG_SENDPAGE_NOTLAST.
+	 * So clear all of them.
+	 */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_MORE | MSG_SENDPAGE_NOTLAST | MSG_EOR);
+
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
 		      MSG_NO_SHARED_FRAGS))
@@ -1288,6 +1301,14 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	int ret;
 
+	/*
+	 * MSG_EOR is invalid for TLS, and conflicts
+	 * with MSG_MORE / MSG_SENDPAGE_NOTLAST.
+	 * So clear all of them.
+	 */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_MORE | MSG_SENDPAGE_NOTLAST | MSG_EOR);
+
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
 		return -EOPNOTSUPP;
Signature · 1 line
2.35.3
maintainer
#9 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

CC'ing Jakub for starters.

Quoted 80 lines
---
  net/tls/tls_device.c | 10 ++++++++++
  net/tls/tls_sw.c     | 21 +++++++++++++++++++++
  2 files changed, 31 insertions(+)
net/tls/tls_device.c +10 -0
index a7cc4f9faac2..38e44e216865 100644
@@ -576,6 +576,10 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
  	mutex_lock(&tls_ctx->tx_lock);
  	lock_sock(sk);
 
+	/* MSG_EOR conflicts with MSG_MORE, so clear both */
+	if (msg->msg_flags & MSG_EOR)
+		msg->msg_flags &= ~(MSG_EOR | MSG_MORE);
+
  	if (unlikely(msg->msg_controllen)) {
  		rc = tls_process_cmsg(sk, msg, &record_type);
  		if (rc)
@@ -604,6 +608,12 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
  	if (flags & MSG_SENDPAGE_NOTLAST)
  		flags |= MSG_MORE;
 
+	/*
+	 * MSG_EOR conflicts with MSG_MORE/MSG_SENDPAGE_NOTLAST,
+	 * so clear all of them */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_EOR | MSG_SENDPAGE_NOTLAST | MSG_MORE);
+
  	mutex_lock(&tls_ctx->tx_lock);
  	lock_sock(sk);
 
net/tls/tls_sw.c +21 -0
index 827292e29f99..d0e6b7a04176 100644
@@ -952,6 +952,11 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
  	int ret = 0;
  	int pending;
 
+	if (msg->msg_flags & MSG_EOR) {
+		eor = true;
+		/* MSG_EOR conflicts with MSG_MORE, so clear both */
+		msg->msg_flags &= ~(MSG_EOR | MSG_MORE);
+	}
  	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
  			       MSG_CMSG_COMPAT))
  		return -EOPNOTSUPP;
@@ -1274,6 +1279,14 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
  int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
  			   int offset, size_t size, int flags)
  {
+	/*
+	 * MSG_EOR is invalid for TLS, and conflicts
+	 * with MSG_MORE / MSG_SENDPAGE_NOTLAST.
+	 * So clear all of them.
+	 */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_MORE | MSG_SENDPAGE_NOTLAST | MSG_EOR);
+
  	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
  		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
  		      MSG_NO_SHARED_FRAGS))
@@ -1288,6 +1301,14 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
  	struct tls_context *tls_ctx = tls_get_ctx(sk);
  	int ret;
 
+	/*
+	 * MSG_EOR is invalid for TLS, and conflicts
+	 * with MSG_MORE / MSG_SENDPAGE_NOTLAST.
+	 * So clear all of them.
+	 */
+	if (flags & MSG_EOR)
+		flags &= ~(MSG_MORE | MSG_SENDPAGE_NOTLAST | MSG_EOR);
+
  	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
  		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
  		return -EOPNOTSUPP;
maintainer
#10 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 9 lines · On Mon, 17 Apr 2023 18:19:12 +0300 Sagi Grimberg wrote:
Quoted 5 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :( No ack.

maintainer
#11 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 7 lines
Quoted 7 lines
Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

Quoted 6 lines
Quoted 3 lines

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :( No ack.

Obviously neither Hannes or I have sufficient tls knowledge to properly support it... It needs to be done by someone who knows the implementation.

Is this a large scope to add support for it? Because if it is, I'd simply change nvme to clear MSG_EOR when tls is used (despite my preference to not do special things for tls).

#12 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 14 lines · Sagi Grimberg
Quoted 7 lines
Quoted 7 lines
Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

Quoted 6 lines
Quoted 3 lines

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :(  No ack.

Quoted 7 lines

Obviously neither Hannes or I have sufficient tls knowledge to properly support it... It needs to be done by someone who knows the implementation.

Is this a large scope to add support for it? Because if it is, I'd simply change nvme to clear MSG_EOR when tls is used (despite my preference to not do special things for tls).

There's a rather simple patch for tls_sw. It already paces the data internally by an 'eor' variable, which is currently set to !MSG_MORE. So evaluating MSG_EOR here is really trivial, and doesn't seem to cause any issues.

Or, at least, none which would show up with NVMe-over-TLS :-)

Cheers,

Hannes

#13 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 19 lines · Hannes Reinecke
Quoted 18 lines · Sagi Grimberg
Quoted 7 lines
Quoted 7 lines
Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

Quoted 6 lines
Quoted 3 lines

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :(  No ack.

Obviously neither Hannes or I have sufficient tls knowledge to properly support it... It needs to be done by someone who knows the implementation.

Quoted 9 lines
Quoted 3 lines

Is this a large scope to add support for it? Because if it is, I'd simply change nvme to clear MSG_EOR when tls is used (despite my preference to not do special things for tls).

There's a rather simple patch for tls_sw. It already paces the data internally by an 'eor' variable, which is currently set to !MSG_MORE. So evaluating MSG_EOR here is really trivial, and doesn't seem to cause any issues.

Or, at least, none which would show up with NVMe-over-TLS :-)

Suggestion is to change it like this (sendpage follows suit):

net/tls/tls_sw.c +4 -1
index 827292e29f99..7b28b11ff611 100644
@@ -953,9 +953,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
        int pending;
 
        if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-                              MSG_CMSG_COMPAT))
+                              MSG_EOR | MSG_CMSG_COMPAT))
                return -EOPNOTSUPP;
 
+       if (MSG_EOR)
+               eor = true;
+
        ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
        if (ret)
                return ret;

Cheers,

Hannes

maintainer
#14 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 36 lines · Hannes Reinecke
Quoted 19 lines · Hannes Reinecke
Quoted 18 lines · Sagi Grimberg
Quoted 7 lines
Quoted 7 lines
Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

Quoted 6 lines
Quoted 3 lines

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :(  No ack.

Obviously neither Hannes or I have sufficient tls knowledge to properly support it... It needs to be done by someone who knows the implementation.

Quoted 9 lines
Quoted 3 lines

Is this a large scope to add support for it? Because if it is, I'd simply change nvme to clear MSG_EOR when tls is used (despite my preference to not do special things for tls).

There's a rather simple patch for tls_sw. It already paces the data internally by an 'eor' variable, which is currently set to !MSG_MORE. So evaluating MSG_EOR here is really trivial, and doesn't seem to cause any issues.

Or, at least, none which would show up with NVMe-over-TLS :-)

Suggestion is to change it like this (sendpage follows suit):

net/tls/tls_sw.c +0 -0
index 827292e29f99..7b28b11ff611 100644

net/tls/tls_sw.c int tls_sw_sendmsg(struct sock *sk, struct msghdr · line 960

Quoted 9 lines
net/tls/tls_sw.c +2 -1
@@ -953,9 +953,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr 
 *msg, size_t size)
         int pending;
 
         if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-                              MSG_CMSG_COMPAT))
+                              MSG_EOR | MSG_CMSG_COMPAT))
                 return -EOPNOTSUPP;
 
+       if (MSG_EOR)

You probably meant if (msg->msg_flags & MSG_EOR)...

#15 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 42 lines · Sagi Grimberg
Quoted 39 lines · Hannes Reinecke
Quoted 19 lines · Hannes Reinecke
Quoted 18 lines · Sagi Grimberg
Quoted 7 lines
Quoted 7 lines
Quoted 6 lines

The TLS stack is using MSG_EOR internally, so the flag cannot be set for sendmsg()/sendpage(). But to avoid having the caller to check whether TLS is active modify the code to clear the MSG_EOR flag. And blank out MSG_MORE / MSG_SENDPAGE_NOTLAST, too, as they conflict with MSG_EOR anyway.

Quoted 6 lines
Quoted 3 lines

This looks like a temporary workaround to me.

The networking folks really need to be CC'd on this (same for patch 6).

Thanks, when I said "we can support EOR" I obviously meant support not ignore it :(  No ack.

Obviously neither Hannes or I have sufficient tls knowledge to properly support it... It needs to be done by someone who knows the implementation.

Quoted 9 lines
Quoted 3 lines

Is this a large scope to add support for it? Because if it is, I'd simply change nvme to clear MSG_EOR when tls is used (despite my preference to not do special things for tls).

There's a rather simple patch for tls_sw. It already paces the data internally by an 'eor' variable, which is currently set to !MSG_MORE. So evaluating MSG_EOR here is really trivial, and doesn't seem to cause any issues.

Or, at least, none which would show up with NVMe-over-TLS :-)

Suggestion is to change it like this (sendpage follows suit):

net/tls/tls_sw.c +0 -0
index 827292e29f99..7b28b11ff611 100644
@@ -953,9 +953,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr 
 *msg, size_t size)
          int pending;
 
Quoted 9 lines
Quoted 6 lines

         if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | -                              MSG_CMSG_COMPAT))
+                              MSG_EOR | MSG_CMSG_COMPAT)) return -EOPNOTSUPP;

+       if (MSG_EOR)

You probably meant if (msg->msg_flags & MSG_EOR)...

Of course.

Cheers,

Hannes

maintainer
#16 lore raw

Re: [PATCH 07/18] net/tls: sanitize MSG_EOR handling

Quoted 13 lines · On Tue, 18 Apr 2023 13:02:34 +0200 Hannes Reinecke wrote:
Quoted 13 lines
Quoted 13 lines
net/tls/tls_sw.c +0 -0
index 827292e29f99..7b28b11ff611 100644
@@ -953,9 +953,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr 
 *msg, size_t size)
          int pending;
 

         if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | -                              MSG_CMSG_COMPAT))
+                              MSG_EOR | MSG_CMSG_COMPAT)) return -EOPNOTSUPP;

Quoted 5 lines
Quoted 4 lines
Quoted 1 line

+       if (MSG_EOR)

You probably meant if (msg->msg_flags & MSG_EOR)...

Of course.

Neat. And similarly for sendpage() and in tls_device.c, it should be fairly small changes in all 3 places. You don't need to worry about tls_device itself using EOR, FWIW, it's just to try to make the offload start on a skb boundary. Adding more EORs should not confuse anything.

#17 lore raw

PATCH v3 8/18 nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

In reply to Hannes Reinecke

MSG_SENDPAGE_NOTLAST was introduced with commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once") to fix issues with the ->sendfile() call, and the implication seems to be that the flag should be strictly internal to sendfile.
Hence we shouldn't be setting it on nvme-tcp, and anyway doing so will cause TLS sending invalid data.

---
 drivers/nvme/host/tcp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/nvme/host/tcp.c +3 -3
index 273c1f2760a4..732aa2296560 100644
@@ -995,7 +995,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
 			flags |= MSG_EOR;
 		else
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			flags |= MSG_MORE;
 
 		if (sendpage_ok(page)) {
 			ret = kernel_sendpage(queue->sock, page, offset, len,
@@ -1049,7 +1049,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 	int ret;
 
 	if (inline_data || nvme_tcp_queue_more(queue))
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		flags |= MSG_MORE;
 	else
 		flags |= MSG_EOR;
 
@@ -1091,7 +1091,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 	if (!req->h2cdata_left)
 		ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
 				offset_in_page(pdu) + req->offset, len,
-				MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);
+				MSG_DONTWAIT | MSG_MORE);
 	else
 		ret = sock_no_sendpage(queue->sock, virt_to_page(pdu),
 				offset_in_page(pdu) + req->offset, len,
Signature · 1 line
2.35.3
maintainer
#18 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

nak from me.

Quoted 4 lines

MSG_SENDPAGE_NOTLAST was introduced with commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once") to fix issues with the ->sendfile() call, and the implication seems to be that the flag should be strictly internal to sendfile.

no, the use case was to allow sendpage consumers to build larger tso packets for large payloads (splice being the primary one), nvme-tcp also benefits from it (as do others), just like sendfile.

Quoted 2 lines

Hence we shouldn't be setting it on nvme-tcp, and anyway doing so will cause TLS sending invalid data.

That is something else. I don't recall the full details on the discussion with Jakub, but it was not my intention to strike it altogether, just remove it if !sendpage_ok.

#19 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 11 lines · Sagi Grimberg

nak from me.

Quoted 4 lines

MSG_SENDPAGE_NOTLAST was introduced with commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once") to fix issues with the ->sendfile() call, and the implication seems to be that the flag should be strictly internal to sendfile.

no, the use case was to allow sendpage consumers to build larger tso packets for large payloads (splice being the primary one), nvme-tcp also benefits from it (as do others), just like sendfile.

Quoted 7 lines
Quoted 2 lines

Hence we shouldn't be setting it on nvme-tcp, and anyway doing so will cause TLS sending invalid data.

That is something else. I don't recall the full details on the discussion with Jakub, but it was not my intention to strike it altogether, just remove it if !sendpage_ok.

But then we're running afoul with tls_sw_do_sendpage(), which uses MSG_SENDPAGE_NOTLAST as a record indicator. Forwarding MSG_SENDPAGE_NOTLAST to tls results in incorrect TLS records on the wire and a transmission stall.

Took me days to figure that out.

If you have a better idea, I'm all ears.

Cheers,

Hannes

Signature · 5 lines
Dr. Hannes Reinecke                Kernel Storage Architect
[email protected]                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
maintainer
#20 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 19 lines
Quoted 12 lines

nak from me.

Quoted 4 lines

MSG_SENDPAGE_NOTLAST was introduced with commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once") to fix issues with the ->sendfile() call, and the implication seems to be that the flag should be strictly internal to sendfile.

no, the use case was to allow sendpage consumers to build larger tso packets for large payloads (splice being the primary one), nvme-tcp also benefits from it (as do others), just like sendfile.

Quoted 7 lines
Quoted 2 lines

Hence we shouldn't be setting it on nvme-tcp, and anyway doing so will cause TLS sending invalid data.

That is something else. I don't recall the full details on the discussion with Jakub, but it was not my intention to strike it altogether, just remove it if !sendpage_ok.

Quoted 5 lines

But then we're running afoul with tls_sw_do_sendpage(), which uses MSG_SENDPAGE_NOTLAST as a record indicator. Forwarding MSG_SENDPAGE_NOTLAST to tls results in incorrect TLS records on the wire and a transmission stall.

Took me days to figure that out.

If you have a better idea, I'm all ears.

So sendfile is unsupported over kTLS? Or is there some special case for it in the upper layer?

Jakub?

#21 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 19 lines · Sagi Grimberg
Quoted 19 lines
Quoted 19 lines

nak from me.

Quoted 4 lines

MSG_SENDPAGE_NOTLAST was introduced with commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once") to fix issues with the ->sendfile() call, and the implication seems to be that the flag should be strictly internal to sendfile.

no, the use case was to allow sendpage consumers to build larger tso packets for large payloads (splice being the primary one), nvme-tcp also benefits from it (as do others), just like sendfile.

Quoted 2 lines

Hence we shouldn't be setting it on nvme-tcp, and anyway doing so will cause TLS sending invalid data.

That is something else. I don't recall the full details on the discussion with Jakub, but it was not my intention to strike it altogether, just remove it if !sendpage_ok.

Quoted 9 lines
Quoted 5 lines

But then we're running afoul with tls_sw_do_sendpage(), which uses MSG_SENDPAGE_NOTLAST as a record indicator. Forwarding MSG_SENDPAGE_NOTLAST to tls results in incorrect TLS records on the wire and a transmission stall.

Took me days to figure that out.

If you have a better idea, I'm all ears.

So sendfile is unsupported over kTLS? Or is there some special case for it in the upper layer?

Dunno. Seems to work, at least according to commit d452d48b9f8b ("tls: prevent oversized sendfile() hangs by ignoring MSG_MORE")

Which is also where I got the notion about sendfile() from. If MSG_SENDPAGE_NOTLAST is valid for non-sendfile users then tls_sw_do_sendpage() has a bug.

Cheers,

Hannes

Signature · 5 lines
Dr. Hannes Reinecke                Kernel Storage Architect
[email protected]                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
maintainer
#22 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

In reply to Sagi Grimberg
Quoted 5 lines · On Mon, 17 Apr 2023 18:28:12 +0300 Sagi Grimberg wrote:
Quoted 5 lines

But then we're running afoul with tls_sw_do_sendpage(), which uses MSG_SENDPAGE_NOTLAST as a record indicator. Forwarding MSG_SENDPAGE_NOTLAST to tls results in incorrect TLS records on the wire and a transmission stall.

Quoted 8 lines
Quoted 3 lines

Took me days to figure that out.

If you have a better idea, I'm all ears.

So sendfile is unsupported over kTLS? Or is there some special case for it in the upper layer?

Jakub?

First I hear of it. 10 sec look at the code doesn't indicate that the author missed this case completely either.

Hannes, any more details on what's going wrong?

What incorrect TLS record have you seen? What's the sequence of sends? Offload or no offload? Easy to repro or stars need to (mis)align?

#23 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 15 lines · Jakub Kicinski
Quoted 5 lines · On Mon, 17 Apr 2023 18:28:12 +0300 Sagi Grimberg wrote:
Quoted 5 lines

But then we're running afoul with tls_sw_do_sendpage(), which uses MSG_SENDPAGE_NOTLAST as a record indicator. Forwarding MSG_SENDPAGE_NOTLAST to tls results in incorrect TLS records on the wire and a transmission stall.

Quoted 8 lines
Quoted 3 lines

Took me days to figure that out.

If you have a better idea, I'm all ears.

So sendfile is unsupported over kTLS? Or is there some special case for it in the upper layer?

Jakub?

Quoted 8 lines

First I hear of it. 10 sec look at the code doesn't indicate that the author missed this case completely either.

Hannes, any more details on what's going wrong?

What incorrect TLS record have you seen? What's the sequence of sends? Offload or no offload? Easy to repro or stars need to (mis)align?

Ah-ha. Found it.

Turns out to be an arguably invalid control flow on our side.

The initial 'connect' command is a command PDU with inline data.
So in our (current) flow we do a 'sendpage()' with the MORE/SENDPAGE_NOTLAST flag set as we have to transfer more data.
Ok so far.
But for transmitting the actual data we evaluate 'sendpage_ok()', which returns _false_. And then we continue to call 'sendmsg()' for the inline data. This confuses the TLS software stack as sendpage() and sendmsg() are two distinct code paths, and we end up with a TX stall.

Solution: check 'sendpage_ok()' when we have inline data and use 'sendmsg' for the command pdu if required.

It always pays to dig deeper if one's not exactly sure what's happening ...

Will be updating the patchset.

Cheers,

Hannes

maintainer
#24 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 14 lines · On Tue, 18 Apr 2023 12:33:03 +0200 Hannes Reinecke wrote:

Ah-ha. Found it.

Turns out to be an arguably invalid control flow on our side.

The initial 'connect' command is a command PDU with inline data. So in our (current) flow we do a 'sendpage()' with the MORE/SENDPAGE_NOTLAST flag set as we have to transfer more data. Ok so far.
But for transmitting the actual data we evaluate 'sendpage_ok()', which returns _false_. And then we continue to call 'sendmsg()' for the inline data.
This confuses the TLS software stack as sendpage() and sendmsg() are two distinct code paths, and we end up with a TX stall.

Quoted 6 lines

Solution: check 'sendpage_ok()' when we have inline data and use 'sendmsg' for the command pdu if required.

It always pays to dig deeper if one's not exactly sure what's happening ...

Will be updating the patchset.

Hm, yeah, sendpage(NOT_LAST)+sendmsg() could indeed be buggy/untested. It wasn't something we could have tested from user space, we'd need kunit or some such :(

Adding it the backlog. And adding Vadim to CC in case he has cycles to take a look.

#25 lore raw

Re: [PATCH 08/18] nvme-tcp: do not set MSG_SENDPAGE_NOTLAST

Quoted 20 lines · Jakub Kicinski
Quoted 19 lines · On Tue, 18 Apr 2023 12:33:03 +0200 Hannes Reinecke wrote:

Ah-ha. Found it.

Turns out to be an arguably invalid control flow on our side.

The initial 'connect' command is a command PDU with inline data. So in our (current) flow we do a 'sendpage()' with the MORE/SENDPAGE_NOTLAST flag set as we have to transfer more data. Ok so far.
But for transmitting the actual data we evaluate 'sendpage_ok()', which returns _false_. And then we continue to call 'sendmsg()' for the inline data.
This confuses the TLS software stack as sendpage() and sendmsg() are two distinct code paths, and we end up with a TX stall.

Solution: check 'sendpage_ok()' when we have inline data and use 'sendmsg' for the command pdu if required.

It always pays to dig deeper if one's not exactly sure what's happening ...

Quoted 9 lines
Quoted 1 line

Will be updating the patchset.

Hm, yeah, sendpage(NOT_LAST)+sendmsg() could indeed be buggy/untested. It wasn't something we could have tested from user space, we'd need kunit or some such :(

Adding it the backlog. And adding Vadim to CC in case he has cycles to take a look.

Bear in mind that that distinction will become meaningless once dhowells patches for MSG_SPLICE are in, as that will get rid of sendpage() altogether. (At least to my understanding.)

Cheers,

Hannes

#26 lore raw

PATCH v3 9/18 security/keys: export key_lookup()

In reply to Hannes Reinecke

For in-kernel consumers one cannot readily assign a user (eg when running from a workqueue), so the normal key search permissions cannot be applied.
This patch exports the 'key_lookup()' function for a simple lookup of keys without checking for permissions.

---
 security/keys/key.c | 1 +
 1 file changed, 1 insertion(+)
security/keys/key.c +1 -0
index 5c0c7df833f8..bd1b7d45df90 100644
@@ -693,6 +693,7 @@ struct key *key_lookup(key_serial_t id)
 	spin_unlock(&key_serial_lock);
 	return key;
 }
+EXPORT_SYMBOL_GPL(key_lookup);
 
 /*
  * Find and lock the specified key type against removal.
Signature · 1 line
2.35.3
#27 lore raw

PATCH v3 10/18 nvme/tcp: allocate socket file

In reply to Hannes Reinecke

When using the TLS upcall we need to allocate a socket file such that the userspace daemon is able to use the socket.

---
 drivers/nvme/host/tcp.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
drivers/nvme/host/tcp.c +12 -2
index 732aa2296560..0a39743da4e4 100644
@@ -1321,7 +1321,9 @@ 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);
@@ -1495,6 +1497,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 	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;
@@ -1517,6 +1520,12 @@ 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)) {
+		sock_release(queue->sock);
+		ret = PTR_ERR(sock_file);
+		goto err_sock;
+	}
 	nvme_tcp_reclassify_socket(queue->sock);
 
 	/* Single syn retry */
@@ -1638,7 +1647,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
 	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);
Signature · 1 line
2.35.3
#28 lore raw

PATCH v3 11/18 nvme-tcp: enable TLS handshake upcall

In reply to Hannes Reinecke

Add a fabrics option 'tls' and start the TLS handshake upcall with the default PSK. When TLS is started the PSK key serial number is displayed in the sysfs attribute 'tls_key'

---
 drivers/nvme/host/Kconfig   |  14 ++++
 drivers/nvme/host/core.c    |  23 ++++++-
 drivers/nvme/host/fabrics.c |  10 +++
 drivers/nvme/host/fabrics.h |   3 +
 drivers/nvme/host/nvme.h    |   1 +
 drivers/nvme/host/tcp.c     | 127 ++++++++++++++++++++++++++++++++++--
 6 files changed, 170 insertions(+), 8 deletions(-)
drivers/nvme/host/Kconfig +14 -0
index 2f6a7f8c94e8..96a74041bb0a 100644
@@ -92,6 +92,20 @@ config NVME_TCP
 
 	  If unsure, say N.
 
+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
+	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_AUTH
 	bool "NVM Express over Fabrics In-Band Authentication"
 	depends on NVME_CORE
drivers/nvme/host/core.c +21 -2
index 79aa215aec76..937013127c91 100644
@@ -3889,6 +3889,19 @@ 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,
@@ -3915,6 +3928,9 @@ static struct attribute *nvme_dev_attrs[] = {
 #ifdef CONFIG_NVME_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
 };
@@ -3945,7 +3961,10 @@ 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)
+		return 0;
+#endif
 	return a->mode;
 }
 
@@ -5080,7 +5099,7 @@ 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);
drivers/nvme/host/fabrics.c +10 -0
index bbaa04a0c502..a8d6c22515ca 100644
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
 	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+	{ NVMF_OPT_TLS,			"tls"			},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -632,6 +633,7 @@ 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;
 
 	options = o = kstrdup(buf, GFP_KERNEL);
 	if (!options)
@@ -918,6 +920,14 @@ 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);
drivers/nvme/host/fabrics.h +3 -0
index dcac3df8a5f7..5db36e250e7a 100644
@@ -70,6 +70,7 @@ enum {
 	NVMF_OPT_DISCOVERY	= 1 << 22,
 	NVMF_OPT_DHCHAP_SECRET	= 1 << 23,
 	NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24,
+	NVMF_OPT_TLS		= 1 << 25,
 };
 
 /**
@@ -102,6 +103,7 @@ enum {
  * @dhchap_secret: DH-HMAC-CHAP secret
  * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional
  *              authentication
+ * @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 +130,7 @@ struct nvmf_ctrl_options {
 	int			max_reconnects;
 	char			*dhchap_secret;
 	char			*dhchap_ctrl_secret;
+	bool			tls;
 	bool			disable_sqflow;
 	bool			hdr_digest;
 	bool			data_digest;
drivers/nvme/host/nvme.h +1 -0
index bf46f122e9e1..fbcc0ccf2ef2 100644
@@ -347,6 +347,7 @@ struct nvme_ctrl {
 	struct nvme_dhchap_key *ctrl_key;
 	u16 transaction;
 #endif
+	struct key *tls_key;
 
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
drivers/nvme/host/tcp.c +121 -6

182 lines not on this page · raw message

Signature · 1 line
2.35.3
maintainer
#29 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 338 lines · Hannes Reinecke

Add a fabrics option 'tls' and start the TLS handshake upcall with the default PSK. When TLS is started the PSK key serial number is displayed in the sysfs attribute 'tls_key'

---
  drivers/nvme/host/Kconfig   |  14 ++++
  drivers/nvme/host/core.c    |  23 ++++++-
  drivers/nvme/host/fabrics.c |  10 +++
  drivers/nvme/host/fabrics.h |   3 +
  drivers/nvme/host/nvme.h    |   1 +
  drivers/nvme/host/tcp.c     | 127 ++++++++++++++++++++++++++++++++++--
  6 files changed, 170 insertions(+), 8 deletions(-)
drivers/nvme/host/Kconfig +14 -0
index 2f6a7f8c94e8..96a74041bb0a 100644
@@ -92,6 +92,20 @@ config NVME_TCP
 
  	  If unsure, say N.
 
+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
+	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_AUTH
  	bool "NVM Express over Fabrics In-Band Authentication"
  	depends on NVME_CORE
drivers/nvme/host/core.c +21 -2
index 79aa215aec76..937013127c91 100644
@@ -3889,6 +3889,19 @@ 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,
@@ -3915,6 +3928,9 @@ static struct attribute *nvme_dev_attrs[] = {
  #ifdef CONFIG_NVME_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
  };
@@ -3945,7 +3961,10 @@ 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)
+		return 0;
+#endif
  	return a->mode;
  }
 
@@ -5080,7 +5099,7 @@ 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);
drivers/nvme/host/fabrics.c +10 -0
index bbaa04a0c502..a8d6c22515ca 100644
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
  	{ NVMF_OPT_DISCOVERY,		"discovery"		},
  	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
  	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+	{ NVMF_OPT_TLS,			"tls"			},
  	{ NVMF_OPT_ERR,			NULL			}
  };
 
@@ -632,6 +633,7 @@ 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;
 
  	options = o = kstrdup(buf, GFP_KERNEL);
  	if (!options)
@@ -918,6 +920,14 @@ 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);
drivers/nvme/host/fabrics.h +3 -0
index dcac3df8a5f7..5db36e250e7a 100644
@@ -70,6 +70,7 @@ enum {
  	NVMF_OPT_DISCOVERY	= 1 << 22,
  	NVMF_OPT_DHCHAP_SECRET	= 1 << 23,
  	NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24,
+	NVMF_OPT_TLS		= 1 << 25,
  };
 
  /**
@@ -102,6 +103,7 @@ enum {
   * @dhchap_secret: DH-HMAC-CHAP secret
   * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional
   *              authentication
+ * @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 +130,7 @@ struct nvmf_ctrl_options {
  	int			max_reconnects;
  	char			*dhchap_secret;
  	char			*dhchap_ctrl_secret;
+	bool			tls;
  	bool			disable_sqflow;
  	bool			hdr_digest;
  	bool			data_digest;
drivers/nvme/host/nvme.h +1 -0
index bf46f122e9e1..fbcc0ccf2ef2 100644
@@ -347,6 +347,7 @@ struct nvme_ctrl {
  	struct nvme_dhchap_key *ctrl_key;
  	u16 transaction;
  #endif
+	struct key *tls_key;
 
  	/* Power saving configuration */
  	u64 ps_max_latency_us;
drivers/nvme/host/tcp.c +113 -4
index 0a39743da4e4..b80bcc5fe447 100644
@@ -8,9 +8,13 @@
  #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/handshake.h>
  #include <linux/blk-mq.h>
  #include <crypto/hash.h>
  #include <net/busy_poll.h>
@@ -31,6 +35,16 @@ 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 +160,10 @@ 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 *);
@@ -1492,7 +1509,79 @@ 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);
+	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;
+	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;
+	}
+	if (wait_for_completion_timeout(&queue->tls_complete, tmo) == 0) {
+		dev_err(nctrl->device,
+			"queue %d: TLS handshake timeout\n", qid);
+		ret = -ETIMEDOUT;
+	} else {
+		dev_dbg(nctrl->device,
+			"queue %d: TLS handshake complete, error %d\n",
+			qid, queue->tls_err);
+		ret = queue->tls_err;
+	}
+	return ret;
+}
+#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];
@@ -1616,6 +1705,14 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
  		goto err_rcv_pdu;
  	}
 
+#ifdef CONFIG_NVME_TCP_TLS
+	/* If PSKs are configured try to start TLS */
+	if (pskid) {
+		ret = nvme_tcp_start_tls(nctrl, queue, pskid);
+		if (ret)
+			goto err_init_connect;
+	}
+#endif
  	ret = nvme_tcp_init_connection(queue);
  	if (ret)
  		goto err_init_connect;
@@ -1759,10 +1856,22 @@ static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
  static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
  {
  	int ret;
+	key_serial_t psk_id = 0;
+
+	if (ctrl->opts->tls) {
+		psk_id = nvme_tls_psk_default(NULL,
+					      ctrl->opts->host->nqn,
+					      ctrl->opts->subsysnqn);
+		if (!psk_id) {
+			dev_err(ctrl->device, "no valid PSK found\n");
+			ret = -ENOKEY;
+			goto out_free_queue;
+		}
+	}
 
-	ret = nvme_tcp_alloc_queue(ctrl, 0);
+	ret = nvme_tcp_alloc_queue(ctrl, 0, psk_id);
  	if (ret)
-		return ret;
+		goto out_free_queue;
 
  	ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
  	if (ret)

drivers/nvme/host/tcp.c static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) · line 1895

Quoted 9 lines
drivers/nvme/host/tcp.c +5 -0
@@ -1778,9 +1887,15 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
  static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
  {
  	int i, ret;
+	key_serial_t psk_id;
 
+	if (!ctrl->tls_key) {
+		dev_err(ctrl->device, "no PSK negotiated\n");
+		return -ENOKEY;
+	}

is ctrl->tls_key always set? Looks like this is the expectation.

#30 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 339 lines · Sagi Grimberg
Quoted 336 lines · Hannes Reinecke

Add a fabrics option 'tls' and start the TLS handshake upcall with the default PSK. When TLS is started the PSK key serial number is displayed in the sysfs attribute 'tls_key'

---
  drivers/nvme/host/Kconfig   |  14 ++++ drivers/nvme/host/core.c    |  23 ++++++- drivers/nvme/host/fabrics.c |  10 +++ drivers/nvme/host/fabrics.h |   3 + drivers/nvme/host/nvme.h    |   1 + drivers/nvme/host/tcp.c     | 127 ++++++++++++++++++++++++++++++++++--

  6 files changed, 170 insertions(+), 8 deletions(-)
drivers/nvme/host/Kconfig +0 -0
index 2f6a7f8c94e8..96a74041bb0a 100644
@@ -92,6 +92,20 @@ config NVME_TCP

        If unsure, say N.
+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
+    help
+      Enables TLS encryption for NVMe TCP using the netlink handshake API.

drivers/nvme/host/Kconfig +6 -0
+
+      The TLS handshake daemon is availble at
+      https://github.com/oracle/ktls-utils.
+
+      If unsure, say N.
+

  config NVME_AUTH
      bool "NVM Express over Fabrics In-Band Authentication" depends on NVME_CORE

drivers/nvme/host/core.c +16 -0
index 79aa215aec76..937013127c91 100644
@@ -3889,6 +3889,19 @@ 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,
@@ -3915,6 +3928,9 @@ static struct attribute *nvme_dev_attrs[] = {
   #ifdef CONFIG_NVME_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
  };

drivers/nvme/host/core.c +5 -2
@@ -3945,7 +3961,10 @@ 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)
+        return 0;
+#endif
       return a->mode;
   }
@@ -5080,7 +5099,7 @@ 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);
drivers/nvme/host/fabrics.c +1 -0
index bbaa04a0c502..a8d6c22515ca 100644
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
       { NVMF_OPT_DISCOVERY,        "discovery"        },
       { NVMF_OPT_DHCHAP_SECRET,    "dhchap_secret=%s"    },
       { NVMF_OPT_DHCHAP_CTRL_SECRET,    "dhchap_ctrl_secret=%s"    },
+    { NVMF_OPT_TLS,            "tls"            },
       { NVMF_OPT_ERR,            NULL            }
   };
@@ -632,6 +633,7 @@ 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;
      options = o = kstrdup(buf, GFP_KERNEL); if (!options)

drivers/nvme/host/fabrics.c +8 -0
@@ -918,6 +920,14 @@ 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);

drivers/nvme/host/fabrics.h +3 -0
index dcac3df8a5f7..5db36e250e7a 100644
@@ -70,6 +70,7 @@ enum {
       NVMF_OPT_DISCOVERY    = 1 << 22,
       NVMF_OPT_DHCHAP_SECRET    = 1 << 23,
       NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24,
+    NVMF_OPT_TLS        = 1 << 25,
   };
   /**
@@ -102,6 +103,7 @@ enum {
    * @dhchap_secret: DH-HMAC-CHAP secret
    * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional
    *              authentication
+ * @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 +130,7 @@ struct nvmf_ctrl_options {
       int            max_reconnects;
       char            *dhchap_secret;
       char            *dhchap_ctrl_secret;
+    bool            tls;
       bool            disable_sqflow;
       bool            hdr_digest;
       bool            data_digest;
drivers/nvme/host/nvme.h +1 -0
index bf46f122e9e1..fbcc0ccf2ef2 100644
@@ -347,6 +347,7 @@ struct nvme_ctrl {
       struct nvme_dhchap_key *ctrl_key;
       u16 transaction;
   #endif
+    struct key *tls_key;
       /* Power saving configuration */
       u64 ps_max_latency_us;
drivers/nvme/host/tcp.c +91 -2
index 0a39743da4e4..b80bcc5fe447 100644
@@ -8,9 +8,13 @@
   #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/handshake.h>
   #include <linux/blk-mq.h>
   #include <crypto/hash.h>
   #include <net/busy_poll.h>
@@ -31,6 +35,16 @@ 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 +160,10 @@ 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 *);
@@ -1492,7 +1509,79 @@ 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);
+    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;
+    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;
+    }
+    if (wait_for_completion_timeout(&queue->tls_complete, tmo) == 0) {
+        dev_err(nctrl->device,
+            "queue %d: TLS handshake timeout\n", qid);
+        ret = -ETIMEDOUT;
+    } else {
+        dev_dbg(nctrl->device,
+            "queue %d: TLS handshake complete, error %d\n",
+            qid, queue->tls_err);
+        ret = queue->tls_err;
+    }
+    return ret;
+}
+#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];

drivers/nvme/host/tcp.c +22 -2
@@ -1616,6 +1705,14 @@ static int nvme_tcp_alloc_queue(struct 
 nvme_ctrl *nctrl, int qid)
           goto err_rcv_pdu;
       }
+#ifdef CONFIG_NVME_TCP_TLS
+    /* If PSKs are configured try to start TLS */
+    if (pskid) {
+        ret = nvme_tcp_start_tls(nctrl, queue, pskid);
+        if (ret)
+            goto err_init_connect;
+    }
+#endif
       ret = nvme_tcp_init_connection(queue);
       if (ret)
           goto err_init_connect;
@@ -1759,10 +1856,22 @@ static int nvme_tcp_start_io_queues(struct 
 nvme_ctrl *ctrl,
   static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
   {
       int ret;
+    key_serial_t psk_id = 0;
+
+    if (ctrl->opts->tls) {
+        psk_id = nvme_tls_psk_default(NULL,
+                          ctrl->opts->host->nqn,
+                          ctrl->opts->subsysnqn);
+        if (!psk_id) {
+            dev_err(ctrl->device, "no valid PSK found\n");
+            ret = -ENOKEY;
+            goto out_free_queue;
+        }
+    }
-    ret = nvme_tcp_alloc_queue(ctrl, 0);
+    ret = nvme_tcp_alloc_queue(ctrl, 0, psk_id);
       if (ret)
-        return ret;
+        goto out_free_queue;
       ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl));
       if (ret)
@@ -1778,9 +1887,15 @@ static int nvme_tcp_alloc_admin_queue(struct 
 nvme_ctrl *ctrl)
   static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
   {
Quoted 9 lines

drivers/nvme/host/tcp.c static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) · line 1895

Quoted 6 lines
drivers/nvme/host/tcp.c +5 -0
       int i, ret;
+    key_serial_t psk_id;
+    if (!ctrl->tls_key) {
+        dev_err(ctrl->device, "no PSK negotiated\n");
+        return -ENOKEY;
+    }

is ctrl->tls_key always set? Looks like this is the expectation.

It needs to be set when TLS is enabled for the admin queue. Otherwise no.

Cheers,

Hannes

Signature · 5 lines
Dr. Hannes Reinecke                Kernel Storage Architect
[email protected]                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
maintainer
#31 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 37 lines
Quoted 27 lines
Quoted 27 lines

  static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) {
      int ret;
+    key_serial_t psk_id = 0;
+
+    if (ctrl->opts->tls) {
+        psk_id = nvme_tls_psk_default(NULL,
+                          ctrl->opts->host->nqn,
+                          ctrl->opts->subsysnqn);
+        if (!psk_id) {
+            dev_err(ctrl->device, "no valid PSK found\n"); +            ret = -ENOKEY;
+            goto out_free_queue;
+        }
+    }
-    ret = nvme_tcp_alloc_queue(ctrl, 0);
+    ret = nvme_tcp_alloc_queue(ctrl, 0, psk_id);
      if (ret)
-        return ret;
+        goto out_free_queue;
      ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl)); if (ret)

drivers/nvme/host/tcp.c +0 -0
@@ -1778,9 +1887,15 @@ static int nvme_tcp_alloc_admin_queue(struct 
 nvme_ctrl *ctrl)
   static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
   {
Quoted 9 lines

drivers/nvme/host/tcp.c static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) · line 1895

Quoted 6 lines
drivers/nvme/host/tcp.c +5 -0
       int i, ret;
+    key_serial_t psk_id;
+    if (!ctrl->tls_key) {
+        dev_err(ctrl->device, "no PSK negotiated\n");
+        return -ENOKEY;
+    }

is ctrl->tls_key always set? Looks like this is the expectation.

Quoted 2 lines

It needs to be set when TLS is enabled for the admin queue. Otherwise no.

Then aren't you missing also and statement with (ctrl->opts->tls) ?

#32 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 37 lines · Sagi Grimberg
Quoted 37 lines
Quoted 36 lines
Quoted 24 lines

  static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) {
      int ret;
+    key_serial_t psk_id = 0;
+
+    if (ctrl->opts->tls) {
+        psk_id = nvme_tls_psk_default(NULL,
+                          ctrl->opts->host->nqn,
+                          ctrl->opts->subsysnqn);
+        if (!psk_id) {
+            dev_err(ctrl->device, "no valid PSK found\n"); +            ret = -ENOKEY;
+            goto out_free_queue;
+        }
+    }
-    ret = nvme_tcp_alloc_queue(ctrl, 0);
+    ret = nvme_tcp_alloc_queue(ctrl, 0, psk_id);
      if (ret)
-        return ret;
+        goto out_free_queue;
      ret = nvme_tcp_alloc_async_req(to_tcp_ctrl(ctrl)); if (ret)

drivers/nvme/host/tcp.c static int nvme_tcp_alloc_admin_queue(struct · line 1895

Quoted 9 lines
drivers/nvme/host/tcp.c +5 -0
@@ -1778,9 +1887,15 @@ static int nvme_tcp_alloc_admin_queue(struct 
 nvme_ctrl *ctrl)
   static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
   {
       int i, ret;
+    key_serial_t psk_id;
+    if (!ctrl->tls_key) {
+        dev_err(ctrl->device, "no PSK negotiated\n");
+        return -ENOKEY;
+    }

is ctrl->tls_key always set? Looks like this is the expectation.

Quoted 5 lines
Quoted 2 lines

It needs to be set when TLS is enabled for the admin queue. Otherwise no.

Then aren't you missing also and statement with (ctrl->opts->tls) ?

Indeed, I do. Will be fixing it up.

Cheers,

Hannes

Signature · 5 lines
Dr. Hannes Reinecke                Kernel Storage Architect
[email protected]                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
#33 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

In reply to Hannes Reinecke

On Mon, Apr 17, 2023 at 03:02:55PM +0200, Hannes Reinecke wrote:
--- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
 	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+	{ NVMF_OPT_TLS,			"tls"			},
 	{ NVMF_OPT_ERR,			NULL			}
 };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

#34 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 15 lines · Daniel Wagner

On Mon, Apr 17, 2023 at 03:02:55PM +0200, Hannes Reinecke wrote:
--- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
  	{ NVMF_OPT_DISCOVERY,		"discovery"		},
  	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
  	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+	{ NVMF_OPT_TLS,			"tls"			},
  	{ NVMF_OPT_ERR,			NULL			}
  };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

Quoted 9 lines

https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

And that is a good question.
I've just removed most of the #ifdef annotations on request from Sagi. If we were going with your suggestion I would need to bring them back.

So, Sagi: What should we do?
Re-clutter and allow nvme-cli to figure out if TLS is supported? And have it always enabled and invent other means for nvme-cli?

Cheers,

Hannes

maintainer
#35 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 24 lines
Quoted 15 lines

  --- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
       { NVMF_OPT_DISCOVERY,        "discovery"        },
       { NVMF_OPT_DHCHAP_SECRET,    "dhchap_secret=%s"    },
       { NVMF_OPT_DHCHAP_CTRL_SECRET,    "dhchap_ctrl_secret=%s"    },
+    { NVMF_OPT_TLS,            "tls"            },
       { NVMF_OPT_ERR,            NULL            }
   };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

Quoted 9 lines

   https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

Quoted 7 lines

And that is a good question.
I've just removed most of the #ifdef annotations on request from Sagi. If we were going with your suggestion I would need to bring them back.

So, Sagi: What should we do?
Re-clutter and allow nvme-cli to figure out if TLS is supported? And have it always enabled and invent other means for nvme-cli?

I don't understand the issue.

userspace already has a way to know if a feature is supported by reading the misc device.

#36 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 28 lines · Sagi Grimberg
Quoted 28 lines
Quoted 15 lines

  --- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
       { NVMF_OPT_DISCOVERY,        "discovery"        },
       { NVMF_OPT_DHCHAP_SECRET,    "dhchap_secret=%s"    },
       { NVMF_OPT_DHCHAP_CTRL_SECRET,    "dhchap_ctrl_secret=%s"    },
+    { NVMF_OPT_TLS,            "tls"            },
       { NVMF_OPT_ERR,            NULL            }
   };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

Quoted 9 lines

   https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

And that is a good question.
I've just removed most of the #ifdef annotations on request from Sagi. If we were going with your suggestion I would need to bring them back.

Quoted 9 lines
Quoted 3 lines

So, Sagi: What should we do?
Re-clutter and allow nvme-cli to figure out if TLS is supported? And have it always enabled and invent other means for nvme-cli?

I don't understand the issue.

userspace already has a way to know if a feature is supported by reading the misc device.

Yes. But the output there is generated by evaluating the fields from the fabrics 'opts' structure.

So if the 'tls' option is present it assumes that TLS is supported.
With my current patchset the _option_ is always present, but the evaluation of the option once set by nvme-cli might return -EINVAL if it's not compiled in.

The request from Daniel is to have the compile option for the fabrics 'tls' option, too, such that it doesn't show up with the misc device. IE revert the changes which you requested to convert all the
'#ifdef CONFIG_NVME_TCP_TLS' conditionals.

Cheers,

Hannes

maintainer
#37 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 38 lines · Hannes Reinecke
Quoted 28 lines · Sagi Grimberg
Quoted 28 lines
Quoted 15 lines

  --- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
       { NVMF_OPT_DISCOVERY,        "discovery"        },
       { NVMF_OPT_DHCHAP_SECRET,    "dhchap_secret=%s"    },
       { NVMF_OPT_DHCHAP_CTRL_SECRET,    "dhchap_ctrl_secret=%s"    },
+    { NVMF_OPT_TLS,            "tls"            },
       { NVMF_OPT_ERR,            NULL            }
   };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

Quoted 9 lines

   https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

And that is a good question.
I've just removed most of the #ifdef annotations on request from Sagi. If we were going with your suggestion I would need to bring them back.

Quoted 9 lines
Quoted 3 lines

So, Sagi: What should we do?
Re-clutter and allow nvme-cli to figure out if TLS is supported? And have it always enabled and invent other means for nvme-cli?

I don't understand the issue.

userspace already has a way to know if a feature is supported by reading the misc device.

Quoted 8 lines

Yes. But the output there is generated by evaluating the fields from the fabrics 'opts' structure.

So if the 'tls' option is present it assumes that TLS is supported.
With my current patchset the _option_ is always present, but the evaluation of the option once set by nvme-cli might return -EINVAL if it's not compiled in.

The request from Daniel is to have the compile option for the fabrics 'tls' option, too, such that it doesn't show up with the misc device. IE revert the changes which you requested to convert all the
'#ifdef CONFIG_NVME_TCP_TLS' conditionals.

Thanks for explaining.

Then we can add the ifdef on the opts statement alone, with a comment.

#38 lore raw

Re: [PATCH 11/18] nvme-tcp: enable TLS handshake upcall

Quoted 46 lines · Sagi Grimberg
Quoted 43 lines · Hannes Reinecke
Quoted 28 lines · Sagi Grimberg
Quoted 28 lines
Quoted 15 lines

  --- a/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c static const match_table_t opt_tokens = { · line 614

Quoted 8 lines

+++ b/drivers/nvme/host/fabrics.c

drivers/nvme/host/fabrics.c +1 -0
@@ -609,6 +609,7 @@ static const match_table_t opt_tokens = {
       { NVMF_OPT_DISCOVERY,        "discovery"        },
       { NVMF_OPT_DHCHAP_SECRET,    "dhchap_secret=%s"    },
       { NVMF_OPT_DHCHAP_CTRL_SECRET,    "dhchap_ctrl_secret=%s"    },
+    { NVMF_OPT_TLS,            "tls"            },
       { NVMF_OPT_ERR,            NULL            }
   };

Coming back to your previous discussion about this. 'tls' is always announced but not always supported. This renders the unsupported option filtering added to libnvme useles:

Quoted 9 lines

   https://github.com/linux-nvme/libnvme/issues/612

Let's assume we go ahead with this patch. The user set explicit the tls option via 'nvme connect ... --tls' and the kernel will return EINVAL, but userland can't really know what it was and drop --tls and retry again (or print some useful information). It could be any other parameter provided by the user.

How is userland supposed to do any feature detection?

And that is a good question.
I've just removed most of the #ifdef annotations on request from Sagi. If we were going with your suggestion I would need to bring them back.

Quoted 9 lines
Quoted 3 lines

So, Sagi: What should we do?
Re-clutter and allow nvme-cli to figure out if TLS is supported? And have it always enabled and invent other means for nvme-cli?

I don't understand the issue.

userspace already has a way to know if a feature is supported by reading the misc device.

Yes. But the output there is generated by evaluating the fields from the fabrics 'opts' structure.

So if the 'tls' option is present it assumes that TLS is supported.
With my current patchset the _option_ is always present, but the evaluation of the option once set by nvme-cli might return -EINVAL if it's not compiled in.

Quoted 7 lines
Quoted 3 lines

The request from Daniel is to have the compile option for the fabrics 'tls' option, too, such that it doesn't show up with the misc device. IE revert the changes which you requested to convert all the
'#ifdef CONFIG_NVME_TCP_TLS' conditionals.

Thanks for explaining.

Then we can add the ifdef on the opts statement alone, with a comment.

Good, will do for the next round.

Cheers,

Hannes

#39 lore raw

PATCH v3 12/18 nvme-tcp: control message handling for recvmsg()

In reply to Hannes Reinecke

kTLS is sending TLS ALERT messages as control messages for recvmsg(). As we can't do anything sensible with it just abort the connection and let the userspace agent to a re-negotiation.

---
 drivers/nvme/host/tcp.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)
drivers/nvme/host/tcp.c +22 -1
index b80bcc5fe447..eeb3f85fe259 100644
@@ -1352,6 +1352,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 {
 	struct nvme_tcp_icreq_pdu *icreq;
 	struct nvme_tcp_icresp_pdu *icresp;
+#ifdef CONFIG_NVME_TCP_TLS
+	char cbuf[CMSG_LEN(sizeof(char))] = {};
+	struct cmsghdr *cmsg;
+	unsigned char ctype;
+#endif
 	struct msghdr msg = {};
 	struct kvec iov;
 	bool ctrl_hdgst, ctrl_ddgst;
@@ -1389,11 +1394,27 @@ 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);
+#ifdef CONFIG_NVME_TCP_TLS
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+#endif
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
 	if (ret < 0)
 		goto free_icresp;
-
+#ifdef CONFIG_NVME_TCP_TLS
+	cmsg = (struct cmsghdr *)cbuf;
+	if (CMSG_OK(&msg, cmsg) &&
+	    cmsg->cmsg_level == SOL_TLS &&
+	    cmsg->cmsg_type == TLS_GET_RECORD_TYPE) {
+		ctype = *((unsigned char *)CMSG_DATA(cmsg));
+		if (ctype != TLS_RECORD_TYPE_DATA) {
+			pr_err("queue %d: unhandled TLS record %d\n",
+			       nvme_tcp_queue_id(queue), ctype);
+			return -ENOTCONN;
+		}
+	}
+#endif
 	ret = -EINVAL;
 	if (icresp->hdr.type != nvme_tcp_icresp) {
 		pr_err("queue %d: bad type returned %d\n",
Signature · 1 line
2.35.3
maintainer
#40 lore raw

Re: [PATCH 12/18] nvme-tcp: control message handling for recvmsg()

Quoted 15 lines · Hannes Reinecke

kTLS is sending TLS ALERT messages as control messages for recvmsg(). As we can't do anything sensible with it just abort the connection and let the userspace agent to a re-negotiation.

---
  drivers/nvme/host/tcp.c | 23 ++++++++++++++++++++++-
  1 file changed, 22 insertions(+), 1 deletion(-)
drivers/nvme/host/tcp.c +0 -0
index b80bcc5fe447..eeb3f85fe259 100644

drivers/nvme/host/tcp.c static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) · line 1355

Quoted 4 lines
drivers/nvme/host/tcp.c +1 -0
@@ -1352,6 +1352,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
  {
  	struct nvme_tcp_icreq_pdu *icreq;
  	struct nvme_tcp_icresp_pdu *icresp;
+#ifdef CONFIG_NVME_TCP_TLS

I don't think you need the ifdef(s) here, right?

#41 lore raw

Re: [PATCH 12/18] nvme-tcp: control message handling for recvmsg()

Quoted 13 lines · Sagi Grimberg
Quoted 10 lines · Hannes Reinecke

kTLS is sending TLS ALERT messages as control messages for recvmsg(). As we can't do anything sensible with it just abort the connection and let the userspace agent to a re-negotiation.

---
  drivers/nvme/host/tcp.c | 23 ++++++++++++++++++++++-

  1 file changed, 22 insertions(+), 1 deletion(-)
Quoted 13 lines

drivers/nvme/host/tcp.c static int nvme_tcp_init_connection(struct · line 1356

Quoted 10 lines
drivers/nvme/host/tcp.c +1 -0
index b80bcc5fe447..eeb3f85fe259 100644
@@ -1352,6 +1352,11 @@ static int nvme_tcp_init_connection(struct 
 nvme_tcp_queue *queue)
   {
       struct nvme_tcp_icreq_pdu *icreq;
       struct nvme_tcp_icresp_pdu *icresp;
+#ifdef CONFIG_NVME_TCP_TLS

I don't think you need the ifdef(s) here, right?

Leftovers, sorry.
Will be cleaning it up with the next round.

Cheers,

Hannes

Signature · 5 lines
Dr. Hannes Reinecke                Kernel Storage Architect
[email protected]                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
#42 lore raw

PATCH v3 13/18 nvme-fabrics: parse options 'keyring' and 'tls_key'

In reply to Hannes Reinecke

Parse the fabrics options 'keyring' and 'tls_key' and store the referenced keys in the options structure.

---
 drivers/nvme/host/fabrics.c | 67 ++++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/fabrics.h |  6 ++++
 drivers/nvme/host/tcp.c     | 11 ++++--
 3 files changed, 80 insertions(+), 4 deletions(-)
drivers/nvme/host/fabrics.c +66 -1
index a8d6c22515ca..6c28e2f424d4 100644
@@ -605,6 +605,8 @@ 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"		},
+	{ NVMF_OPT_KEYRING,		"keyring=%d"		},
+	{ NVMF_OPT_TLS_KEY,		"tls_key=%d"		},
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
@@ -620,8 +622,9 @@ 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;
+	struct key *key = NULL;
 
 	/* Set defaults */
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -889,6 +892,66 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			}
 			opts->tos = token;
 			break;
+		case NVMF_OPT_KEYRING:
+			if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) {
+				pr_err("TLS is not supported\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (match_int(args, &key_id)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (key_id < 0) {
+				pr_err("Invalid keyring id %d\n", key_id);
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!key_id) {
+				pr_debug("Using default keyring\n");
+				key_put(opts->keyring);
+				opts->keyring = NULL;
+				break;
+			}
+			key = key_lookup(key_id);
+			if (!key) {
+				pr_err("Keyring id %08x not found\n", key_id);
+				ret = -ENOKEY;
+				goto out;
+			}
+			key_put(opts->keyring);
+			opts->keyring = key;
+			break;
+		case NVMF_OPT_TLS_KEY:
+			if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) {
+				pr_err("TLS is not supported\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (match_int(args, &key_id)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			if (key_id < 0) {
+				pr_err("Invalid key id %d\n", key_id);
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!key_id) {
+				pr_debug("Using 'best' PSK\n");
+				key_put(opts->tls_key);
+				opts->tls_key = NULL;
+				break;
+			}
+			key = key_lookup(key_id);
+			if (!key) {
+				pr_err("Key id %08x not found\n", key_id);
+				ret = -ENOKEY;
+				goto out;
+			}
+			key_put(opts->tls_key);
+			opts->tls_key = key;
+			break;
 		case NVMF_OPT_DISCOVERY:
 			opts->discovery_nqn = true;
 			break;
@@ -1053,6 +1116,8 @@ 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);
drivers/nvme/host/fabrics.h +6 -0
index 5db36e250e7a..2ff7b7168a40 100644
@@ -71,6 +71,8 @@ enum {
 	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,
 };
 
 /**
@@ -103,6 +105,8 @@ 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)
@@ -130,6 +134,8 @@ struct nvmf_ctrl_options {
 	int			max_reconnects;
 	char			*dhchap_secret;
 	char			*dhchap_ctrl_secret;
+	struct key		*keyring;
+	struct key		*tls_key;
 	bool			tls;
 	bool			disable_sqflow;
 	bool			hdr_digest;
drivers/nvme/host/tcp.c +8 -3
index eeb3f85fe259..7714c2bdfc19 100644
@@ -1572,6 +1572,8 @@ static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
 
 	dev_dbg(nctrl->device, "queue %d: start TLS with key %x\n",
 		qid, pskid);
+	if (nctrl->opts->keyring)
+		keyring = key_serial(nctrl->opts->keyring);
 	args.ta_sock = queue->sock;
 	args.ta_done = nvme_tcp_tls_done;
 	args.ta_data = queue;
@@ -1880,9 +1882,12 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 	key_serial_t psk_id = 0;
 
 	if (ctrl->opts->tls) {
-		psk_id = nvme_tls_psk_default(NULL,
-					      ctrl->opts->host->nqn,
-					      ctrl->opts->subsysnqn);
+		if (ctrl->opts->tls_key)
+			psk_id = key_serial(ctrl->opts->tls_key);
+		else
+			psk_id = nvme_tls_psk_default(ctrl->opts->keyring,
+						      ctrl->opts->host->nqn,
+						      ctrl->opts->subsysnqn);
 		if (!psk_id) {
 			dev_err(ctrl->device, "no valid PSK found\n");
 			ret = -ENOKEY;
Signature · 1 line
2.35.3
#43 lore raw

PATCH v3 14/18 nvmet: make TCP sectype settable via configfs

In reply to Hannes Reinecke

Add a new configfs attribute 'addr_tsas' to make the TCP sectype settable via configfs.

---
 drivers/nvme/target/configfs.c | 65 ++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
drivers/nvme/target/configfs.c +65 -0
index 907143870da5..7f826ac8b75c 100644
@@ -303,6 +303,11 @@ static void nvmet_port_init_tsas_rdma(struct nvmet_port *port)
 	port->disc_addr.tsas.rdma.cms = NVMF_RDMA_CMS_RDMA_CM;
 }
 
+static void nvmet_port_init_tsas_tcp(struct nvmet_port *port, int sectype)
+{
+	port->disc_addr.tsas.tcp.sectype = sectype;
+}
+
 static ssize_t nvmet_addr_trtype_store(struct config_item *item,
 		const char *page, size_t count)
 {
@@ -325,11 +330,70 @@ static ssize_t nvmet_addr_trtype_store(struct config_item *item,
 	port->disc_addr.trtype = nvmet_transport[i].type;
 	if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA)
 		nvmet_port_init_tsas_rdma(port);
+	else if (port->disc_addr.trtype == NVMF_TRTYPE_TCP)
+		nvmet_port_init_tsas_tcp(port, NVMF_TCP_SECTYPE_NONE);
 	return count;
 }
 
 CONFIGFS_ATTR(nvmet_, addr_trtype);
 
+static const struct nvmet_type_name_map nvmet_addr_tsas_tcp[] = {
+	{ NVMF_TCP_SECTYPE_NONE,	"none" },
+	{ NVMF_TCP_SECTYPE_TLS13,	"tls1.3" },
+};
+
+static const struct nvmet_type_name_map nvmet_addr_tsas_rdma[] = {
+	{ NVMF_RDMA_QPTYPE_CONNECTED,	"connected" },
+	{ NVMF_RDMA_QPTYPE_DATAGRAM,	"datagram"  },
+};
+
+static ssize_t nvmet_addr_tsas_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int i;
+
+	if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) {
+		for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+			if (port->disc_addr.tsas.tcp.sectype == nvmet_addr_tsas_tcp[i].type)
+				return sprintf(page, "%s\n", nvmet_addr_tsas_tcp[i].name);
+		}
+	} else if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) {
+		for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_rdma); i++) {
+			if (port->disc_addr.tsas.rdma.qptype == nvmet_addr_tsas_rdma[i].type)
+				return sprintf(page, "%s\n", nvmet_addr_tsas_rdma[i].name);
+		}
+	}
+	return sprintf(page, "reserved\n");
+}
+
+static ssize_t nvmet_addr_tsas_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int i;
+
+	if (nvmet_is_port_enabled(port, __func__))
+		return -EACCES;
+
+	if (port->disc_addr.trtype != NVMF_TRTYPE_TCP)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+		if (sysfs_streq(page, nvmet_addr_tsas_tcp[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for tsas\n", page);
+	return -EINVAL;
+
+found:
+	nvmet_port_init_tsas_tcp(port, nvmet_addr_tsas_tcp[i].type);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_tsas);
+
 /*
  * Namespace structures & file operation functions below
  */
@@ -1741,6 +1805,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_addr_tsas,
 	&nvmet_attr_param_inline_data_size,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	&nvmet_attr_param_pi_enable,
Signature · 1 line
2.35.3
#44 lore raw

PATCH v3 15/18 nvmet-tcp: allocate socket file

In reply to Hannes Reinecke

For the TLS upcall we need to allocate a socket file such that the userspace daemon is able to use the socket.

---
 drivers/nvme/target/tcp.c | 36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)
drivers/nvme/target/tcp.c +23 -13
index ed98df72c76b..fc7a9fb56a83 100644
@@ -122,6 +122,7 @@ struct nvmet_tcp_cmd {
 
 enum nvmet_tcp_queue_state {
 	NVMET_TCP_Q_CONNECTING,
+	NVMET_TCP_Q_TLS_HANDSHAKE,
 	NVMET_TCP_Q_LIVE,
 	NVMET_TCP_Q_DISCONNECTING,
 };
@@ -1481,12 +1482,12 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
 	nvmet_sq_destroy(&queue->nvme_sq);
 	cancel_work_sync(&queue->io_work);
 	nvmet_tcp_free_cmd_data_in_buffers(queue);
-	sock_release(queue->sock);
+	/* ->sock will be released by fput() */
+	fput(queue->sock->file);
 	nvmet_tcp_free_cmds(queue);
 	if (queue->hdr_digest || queue->data_digest)
 		nvmet_tcp_free_crypto(queue);
 	ida_free(&nvmet_tcp_queue_ida, queue->idx);
-
 	page = virt_to_head_page(queue->pf_cache.va);
 	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
 	kfree(queue);
@@ -1609,15 +1610,16 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 	return ret;
 }
 
-static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
+static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 		struct socket *newsock)
 {
 	struct nvmet_tcp_queue *queue;
+	struct file *sock_file;
 	int ret;
 
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 	if (!queue)
-		return -ENOMEM;
+		return;
 
 	INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work);
 	INIT_WORK(&queue->io_work, nvmet_tcp_io_work);
@@ -1625,15 +1627,25 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	queue->port = port;
 	queue->nr_cmds = 0;
 	spin_lock_init(&queue->state_lock);
-	queue->state = NVMET_TCP_Q_CONNECTING;
+	if (queue->port->nport->disc_addr.tsas.tcp.sectype ==
+	    NVMF_TCP_SECTYPE_TLS13)
+		queue->state = NVMET_TCP_Q_TLS_HANDSHAKE;
+	else
+		queue->state = NVMET_TCP_Q_CONNECTING;
 	INIT_LIST_HEAD(&queue->free_list);
 	init_llist_head(&queue->resp_list);
 	INIT_LIST_HEAD(&queue->resp_send_list);
 
+	sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL);
+	if (IS_ERR(sock_file)) {
+		ret = PTR_ERR(sock_file);
+		goto out_free_queue;
+	}
+
 	queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL);
 	if (queue->idx < 0) {
 		ret = queue->idx;
-		goto out_free_queue;
+		goto out_sock;
 	}
 
 	ret = nvmet_tcp_alloc_cmd(queue, &queue->connect);
@@ -1654,7 +1666,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	if (ret)
 		goto out_destroy_sq;
 
-	return 0;
+	return;
 out_destroy_sq:
 	mutex_lock(&nvmet_tcp_queue_mutex);
 	list_del_init(&queue->queue_list);
@@ -1664,9 +1676,11 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	nvmet_tcp_free_cmd(&queue->connect);
 out_ida_remove:
 	ida_free(&nvmet_tcp_queue_ida, queue->idx);
+out_sock:
+	fput(queue->sock->file);
 out_free_queue:
 	kfree(queue);
-	return ret;
+	pr_err("failed to allocate queue");
 }
 
 static void nvmet_tcp_accept_work(struct work_struct *w)
@@ -1683,11 +1697,7 @@ static void nvmet_tcp_accept_work(struct work_struct *w)
 				pr_warn("failed to accept err=%d\n", ret);
 			return;
 		}
-		ret = nvmet_tcp_alloc_queue(port, newsock);
-		if (ret) {
-			pr_err("failed to allocate queue\n");
-			sock_release(newsock);
-		}
+		nvmet_tcp_alloc_queue(port, newsock);
 	}
 }
 
Signature · 1 line
2.35.3
maintainer
#45 lore raw

Re: [PATCH 15/18] nvmet-tcp: allocate socket file

Quoted 13 lines · Hannes Reinecke

For the TLS upcall we need to allocate a socket file such that the userspace daemon is able to use the socket.

---
  drivers/nvme/target/tcp.c | 36 +++++++++++++++++++++++-------------
  1 file changed, 23 insertions(+), 13 deletions(-)
drivers/nvme/target/tcp.c +0 -0
index ed98df72c76b..fc7a9fb56a83 100644

drivers/nvme/target/tcp.c struct nvmet_tcp_cmd { · line 125

Quoted 4 lines
drivers/nvme/target/tcp.c +1 -0
@@ -122,6 +122,7 @@ struct nvmet_tcp_cmd {
 
  enum nvmet_tcp_queue_state {
  	NVMET_TCP_Q_CONNECTING,
+	NVMET_TCP_Q_TLS_HANDSHAKE,

I think you got some misplaced chunks in the patch.

Quoted 100 lines
drivers/nvme/target/tcp.c +22 -13
  	NVMET_TCP_Q_LIVE,
  	NVMET_TCP_Q_DISCONNECTING,
  };
@@ -1481,12 +1482,12 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
  	nvmet_sq_destroy(&queue->nvme_sq);
  	cancel_work_sync(&queue->io_work);
  	nvmet_tcp_free_cmd_data_in_buffers(queue);
-	sock_release(queue->sock);
+	/* ->sock will be released by fput() */
+	fput(queue->sock->file);
  	nvmet_tcp_free_cmds(queue);
  	if (queue->hdr_digest || queue->data_digest)
  		nvmet_tcp_free_crypto(queue);
  	ida_free(&nvmet_tcp_queue_ida, queue->idx);
-
  	page = virt_to_head_page(queue->pf_cache.va);
  	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
  	kfree(queue);
@@ -1609,15 +1610,16 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
  	return ret;
  }
 
-static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
+static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
  		struct socket *newsock)
  {
  	struct nvmet_tcp_queue *queue;
+	struct file *sock_file;
  	int ret;
 
  	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
  	if (!queue)
-		return -ENOMEM;
+		return;
 
  	INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work);
  	INIT_WORK(&queue->io_work, nvmet_tcp_io_work);
@@ -1625,15 +1627,25 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
  	queue->port = port;
  	queue->nr_cmds = 0;
  	spin_lock_init(&queue->state_lock);
-	queue->state = NVMET_TCP_Q_CONNECTING;
+	if (queue->port->nport->disc_addr.tsas.tcp.sectype ==
+	    NVMF_TCP_SECTYPE_TLS13)
+		queue->state = NVMET_TCP_Q_TLS_HANDSHAKE;
+	else
+		queue->state = NVMET_TCP_Q_CONNECTING;
  	INIT_LIST_HEAD(&queue->free_list);
  	init_llist_head(&queue->resp_list);
  	INIT_LIST_HEAD(&queue->resp_send_list);
 
+	sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL);
+	if (IS_ERR(sock_file)) {
+		ret = PTR_ERR(sock_file);
+		goto out_free_queue;
+	}
+
  	queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL);
  	if (queue->idx < 0) {
  		ret = queue->idx;
-		goto out_free_queue;
+		goto out_sock;
  	}
 
  	ret = nvmet_tcp_alloc_cmd(queue, &queue->connect);
@@ -1654,7 +1666,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
  	if (ret)
  		goto out_destroy_sq;
 
-	return 0;
+	return;
  out_destroy_sq:
  	mutex_lock(&nvmet_tcp_queue_mutex);
  	list_del_init(&queue->queue_list);
@@ -1664,9 +1676,11 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
  	nvmet_tcp_free_cmd(&queue->connect);
  out_ida_remove:
  	ida_free(&nvmet_tcp_queue_ida, queue->idx);
+out_sock:
+	fput(queue->sock->file);
  out_free_queue:
  	kfree(queue);
-	return ret;
+	pr_err("failed to allocate queue");
  }
 
  static void nvmet_tcp_accept_work(struct work_struct *w)
@@ -1683,11 +1697,7 @@ static void nvmet_tcp_accept_work(struct work_struct *w)
  				pr_warn("failed to accept err=%d\n", ret);
  			return;
  		}
-		ret = nvmet_tcp_alloc_queue(port, newsock);
-		if (ret) {
-			pr_err("failed to allocate queue\n");
-			sock_release(newsock);
-		}
+		nvmet_tcp_alloc_queue(port, newsock);
  	}
  }
 
#46 lore raw

PATCH v3 16/18 nvmet-tcp: enable TLS handshake upcall

In reply to Hannes Reinecke

Add functions to start the TLS handshake upcall when the TCP TSAS sectype is set to 'tls1.3' and add a config option NVME_TARGET_TCP_TLS.

---
 drivers/nvme/target/Kconfig    |  14 ++++
 drivers/nvme/target/configfs.c |  63 ++++++++++++++++-
 drivers/nvme/target/nvmet.h    |   1 +
 drivers/nvme/target/tcp.c      | 126 ++++++++++++++++++++++++++++++++-
 4 files changed, 199 insertions(+), 5 deletions(-)
drivers/nvme/target/Kconfig +14 -0
index 79fc64035ee3..15af2b4341f6 100644
@@ -84,6 +84,20 @@ config NVME_TARGET_TCP
 
 	  If unsure, say N.
 
+config NVME_TARGET_TCP_TLS
+	bool "NVMe over Fabrics TCP target TLS encryption support"
+	depends on NVME_TARGET_TCP
+	select NVME_COMMON
+	select NVME_KEYRING
+	select NET_HANDSHAKE
+	help
+	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
+
+	  The TLS handshake daemon is availble at
+	  https://github.com/oracle/ktls-utils.
+
+	  If unsure, say N.
+
 config NVME_TARGET_AUTH
 	bool "NVMe over Fabrics In-band Authentication support"
 	depends on NVME_TARGET
drivers/nvme/target/configfs.c +60 -3

123 lines not on this page · raw message

drivers/nvme/target/nvmet.h +1 -0
index dc60a22646f7..a22f817f5935 100644
@@ -158,6 +158,7 @@ struct nvmet_port {
 	struct config_group		ana_groups_group;
 	struct nvmet_ana_group		ana_default_group;
 	enum nvme_ana_state		*ana_state;
+	struct key			*keyring;
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
drivers/nvme/target/tcp.c +124 -2

171 lines not on this page · raw message

Signature · 1 line
2.35.3
#47 lore raw

PATCH v3 17/18 nvmet-tcp: control messages for recvmsg()

In reply to Hannes Reinecke

kTLS requires control messages for recvmsg() to relay any out-of-band TLS messages (eg TLS alerts) to the caller.

---
 drivers/nvme/target/tcp.c | 51 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)
drivers/nvme/target/tcp.c +49 -2
index ea853658430f..2974abd30b45 100644
@@ -13,6 +13,7 @@
 #include <linux/nvme-keyring.h>
 #include <net/sock.h>
 #include <net/tcp.h>
+#include <net/tls.h>
 #include <net/handshake.h>
 #include <linux/inet.h>
 #include <linux/llist.h>
@@ -117,6 +118,7 @@ struct nvmet_tcp_cmd {
 	u32				pdu_len;
 	u32				pdu_recv;
 	int				sg_idx;
+	char				recv_cbuf[CMSG_LEN(sizeof(char))];
 	struct msghdr			recv_msg;
 	struct bio_vec			*iov;
 	u32				flags;
@@ -1103,12 +1105,39 @@ static inline bool nvmet_tcp_pdu_valid(u8 type)
 	return false;
 }
 
+static bool nvmet_tcp_tls_record_ok(struct msghdr *msg, char *cbuf)
+{
+	struct cmsghdr *cmsg = (struct cmsghdr *)cbuf;
+	unsigned char ctype;
+
+	if (!IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS))
+		return 0;
+
+	if (CMSG_OK(msg, cmsg) &&
+	    cmsg->cmsg_level == SOL_TLS &&
+	    cmsg->cmsg_type == TLS_GET_RECORD_TYPE) {
+		ctype = *((unsigned char *)CMSG_DATA(cmsg));
+		if (ctype != TLS_RECORD_TYPE_DATA) {
+			pr_err("unhandled TLS record %d\n", ctype);
+			return false;
+		}
+	}
+	return true;
+}
+
 static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
 	int len;
 	struct kvec iov;
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
+	char cbuf[CMSG_LEN(sizeof(char))] = {};
+	struct msghdr msg = {
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+		.msg_control = cbuf,
+		.msg_controllen = sizeof(cbuf),
+#endif
+		.msg_flags = MSG_DONTWAIT
+	};
 
 recv:
 	iov.iov_base = (void *)&queue->pdu + queue->offset;
@@ -1117,6 +1146,8 @@ static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
 			iov.iov_len, msg.msg_flags);
 	if (unlikely(len < 0))
 		return len;
+	if (!nvmet_tcp_tls_record_ok(&msg, cbuf))
+		return -ENOTCONN;
 
 	queue->offset += len;
 	queue->left -= len;
@@ -1176,6 +1207,9 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
 			cmd->recv_msg.msg_flags);
 		if (ret <= 0)
 			return ret;
+		if (!nvmet_tcp_tls_record_ok(&cmd->recv_msg,
+					     cmd->recv_cbuf))
+			return -ENOTCONN;
 
 		cmd->pdu_recv += ret;
 		cmd->rbytes_done += ret;
@@ -1197,7 +1231,14 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
 {
 	struct nvmet_tcp_cmd *cmd = queue->cmd;
 	int ret;
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
+	char cbuf[CMSG_LEN(sizeof(char))] = {};
+	struct msghdr msg = {
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+		.msg_control = cbuf,
+		.msg_controllen = sizeof(cbuf),
+#endif
+		.msg_flags = MSG_DONTWAIT
+	};
 	struct kvec iov = {
 		.iov_base = (void *)&cmd->recv_ddgst + queue->offset,
 		.iov_len = queue->left
@@ -1207,6 +1248,8 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
 			iov.iov_len, msg.msg_flags);
 	if (unlikely(ret < 0))
 		return ret;
+	if (!nvmet_tcp_tls_record_ok(&msg, cbuf))
+		return -ENOTCONN;
 
 	queue->offset += ret;
 	queue->left -= ret;
@@ -1376,6 +1419,10 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
 	if (!c->r2t_pdu)
 		goto out_free_data;
 
+	if (IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS)) {
+		c->recv_msg.msg_control = c->recv_cbuf;
+		c->recv_msg.msg_controllen = sizeof(c->recv_cbuf);
+	}
 	c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
 
 	list_add_tail(&c->entry, &queue->free_list);
Signature · 1 line
2.35.3
#48 lore raw

PATCH v3 18/18 nvmet-tcp: add configfs attribute 'param_keyring'

In reply to Hannes Reinecke

Add a configfs attribute to list and change the default keyring.

---
 drivers/nvme/target/configfs.c | 45 ++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
drivers/nvme/target/configfs.c +45 -0
index 49b407702ad5..493f5524c922 100644
@@ -309,6 +309,47 @@ static ssize_t nvmet_param_pi_enable_store(struct config_item *item,
 CONFIGFS_ATTR(nvmet_, param_pi_enable);
 #endif
 
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+static ssize_t nvmet_param_keyring_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	if (!port->keyring)
+		return sprintf(page, "\n");
+	return snprintf(page, PAGE_SIZE, "%s\n",
+			port->keyring->description);
+}
+
+static ssize_t nvmet_param_keyring_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	struct key *keyring;
+	unsigned int keyring_id;
+	int ret;
+
+	if (nvmet_is_port_enabled(port, __func__))
+		return -EACCES;
+
+	ret = kstrtou32(page, 0, &keyring_id);
+	if (ret) {
+		pr_err("Invalid keyring id '%s'\n", page);
+		return ret;
+	}
+	keyring = key_lookup(keyring_id);
+	if (IS_ERR(keyring)) {
+		pr_err("Invalid keyring '%08x'\n", keyring_id);
+		return PTR_ERR(keyring);
+	}
+	key_put(port->keyring);
+	port->keyring = keyring;
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_keyring);
+#endif
+
 static ssize_t nvmet_addr_trtype_show(struct config_item *item,
 		char *page)
 {
@@ -412,6 +453,7 @@ static ssize_t nvmet_addr_tsas_store(struct config_item *item,
 		pr_err("TLS is not supported\n");
 		return -EINVAL;
 	}
+
 	if (!port->keyring) {
 		pr_err("TLS keyring not configured\n");
 		return -EINVAL;
@@ -1858,6 +1900,9 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_param_inline_data_size,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	&nvmet_attr_param_pi_enable,
+#endif
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+	&nvmet_attr_param_keyring,
 #endif
 	NULL,
 };
Signature · 1 line
2.35.3