linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wilfred Mallawa <wilfred.opensource@gmail.com>
To: alistair.francis@wdc.com, dlemoal@kernel.org,
	chuck.lever@oracle.com, davem@davemloft.net, edumazet@google.com,
	kuba@kernel.org, pabeni@redhat.com, horms@kernel.org,
	donald.hunter@gmail.com, corbet@lwn.net, kbusch@kernel.org,
	axboe@kernel.dk, hch@lst.de, sagi@grimberg.me, kch@nvidia.com,
	borisp@nvidia.com, john.fastabend@gmail.com, jlayton@kernel.org,
	neil@brown.name, okorniev@redhat.com, Dai.Ngo@oracle.com,
	tom@talpey.com, trondmy@kernel.org, anna@kernel.org,
	kernel-tls-handshake@lists.linux.dev, netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-nvme@lists.infradead.org, linux-nfs@vger.kernel.org,
	Wilfred Mallawa <wilfred.mallawa@wdc.com>
Subject: [RFC 1/4] net/handshake: get negotiated tls record size limit
Date: Tue, 29 Jul 2025 12:41:49 +1000	[thread overview]
Message-ID: <20250729024150.222513-4-wilfred.opensource@gmail.com> (raw)
In-Reply-To: <20250729024150.222513-2-wilfred.opensource@gmail.com>

From: Wilfred Mallawa <wilfred.mallawa@wdc.com>

During a handshake, an endpoint may specify a maximum record size limit.
Currently, this limit is not visble to the kernel particularly in the case
where userspace handles the handshake (tlshd/gnutls). This patch adds
support for retrieving the record size limit.

This is the first step in ensuring that the kernel can respect the record
size limit imposed by the endpoint.

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
---
 Documentation/netlink/specs/handshake.yaml |  3 +++
 Documentation/networking/tls-handshake.rst |  8 +++++++-
 drivers/nvme/host/tcp.c                    |  3 ++-
 drivers/nvme/target/tcp.c                  |  3 ++-
 include/net/handshake.h                    |  4 +++-
 include/uapi/linux/handshake.h             |  1 +
 net/handshake/genl.c                       |  5 +++--
 net/handshake/tlshd.c                      | 15 +++++++++++++--
 net/sunrpc/svcsock.c                       |  4 +++-
 net/sunrpc/xprtsock.c                      |  4 +++-
 10 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml
index b934cc513e3d..35d5eb91a3f9 100644
--- a/Documentation/netlink/specs/handshake.yaml
+++ b/Documentation/netlink/specs/handshake.yaml
@@ -84,6 +84,9 @@ attribute-sets:
         name: remote-auth
         type: u32
         multi-attr: true
+      -
+        name: record-size-limit
+        type: u32
 
 operations:
   list:
diff --git a/Documentation/networking/tls-handshake.rst b/Documentation/networking/tls-handshake.rst
index 6f5ea1646a47..cd984a137779 100644
--- a/Documentation/networking/tls-handshake.rst
+++ b/Documentation/networking/tls-handshake.rst
@@ -169,7 +169,8 @@ The synopsis of this function is:
 .. code-block:: c
 
   typedef void	(*tls_done_func_t)(void *data, int status,
-                                   key_serial_t peerid);
+                                   key_serial_t peerid,
+                                   size_t tls_record_size_limit);
 
 The consumer provides a cookie in the @ta_data field of the
 tls_handshake_args structure that is returned in the @data parameter of
@@ -200,6 +201,11 @@ The @peerid parameter contains the serial number of a key containing the
 remote peer's identity or the value TLS_NO_PEERID if the session is not
 authenticated.
 
+The @tls_record_size_limit parameter, if non-zero, exposes the tls max
+record size advertised by the endpoint. Record size must not exceed this amount.
+A negative value shall indicate that the endpoint did not advertise the
+maximum record size limit.
+
 A best practice is to close and destroy the socket immediately if the
 handshake failed.
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d924008c3949..65ceadb4ffed 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1673,7 +1673,8 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 		qid, queue->io_cpu);
 }
 
-static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
+static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid,
+			      size_t tls_record_size_limit)
 {
 	struct nvme_tcp_queue *queue = data;
 	struct nvme_tcp_ctrl *ctrl = queue->ctrl;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 470bf37e5a63..60e308401a54 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1780,7 +1780,8 @@ static int nvmet_tcp_tls_key_lookup(struct nvmet_tcp_queue *queue,
 }
 
 static void nvmet_tcp_tls_handshake_done(void *data, int status,
-					 key_serial_t peerid)
+					key_serial_t peerid,
+					size_t tls_record_size_limit)
 {
 	struct nvmet_tcp_queue *queue = data;
 
diff --git a/include/net/handshake.h b/include/net/handshake.h
index 8ebd4f9ed26e..c00b1aaa7aba 100644
--- a/include/net/handshake.h
+++ b/include/net/handshake.h
@@ -15,10 +15,12 @@ enum {
 	TLS_NO_PEERID = 0,
 	TLS_NO_CERT = 0,
 	TLS_NO_PRIVKEY = 0,
+	TLS_NO_RECORD_SIZE_LIMIT = 0,
 };
 
 typedef void	(*tls_done_func_t)(void *data, int status,
-				   key_serial_t peerid);
+				   key_serial_t peerid,
+				   size_t tls_record_size_limit);
 
 struct tls_handshake_args {
 	struct socket		*ta_sock;
diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h
index 3d7ea58778c9..0768eb8eb415 100644
--- a/include/uapi/linux/handshake.h
+++ b/include/uapi/linux/handshake.h
@@ -54,6 +54,7 @@ enum {
 	HANDSHAKE_A_DONE_STATUS = 1,
 	HANDSHAKE_A_DONE_SOCKFD,
 	HANDSHAKE_A_DONE_REMOTE_AUTH,
+	HANDSHAKE_A_DONE_RECORD_SIZE_LIMIT,
 
 	__HANDSHAKE_A_DONE_MAX,
 	HANDSHAKE_A_DONE_MAX = (__HANDSHAKE_A_DONE_MAX - 1)
diff --git a/net/handshake/genl.c b/net/handshake/genl.c
index f55d14d7b726..44c43ce18361 100644
--- a/net/handshake/genl.c
+++ b/net/handshake/genl.c
@@ -16,10 +16,11 @@ static const struct nla_policy handshake_accept_nl_policy[HANDSHAKE_A_ACCEPT_HAN
 };
 
 /* HANDSHAKE_CMD_DONE - do */
-static const struct nla_policy handshake_done_nl_policy[HANDSHAKE_A_DONE_REMOTE_AUTH + 1] = {
+static const struct nla_policy handshake_done_nl_policy[HANDSHAKE_A_DONE_RECORD_SIZE_LIMIT + 1] = {
 	[HANDSHAKE_A_DONE_STATUS] = { .type = NLA_U32, },
 	[HANDSHAKE_A_DONE_SOCKFD] = { .type = NLA_S32, },
 	[HANDSHAKE_A_DONE_REMOTE_AUTH] = { .type = NLA_U32, },
+	[HANDSHAKE_A_DONE_RECORD_SIZE_LIMIT] = { .type = NLA_U32, },
 };
 
 /* Ops table for handshake */
@@ -35,7 +36,7 @@ static const struct genl_split_ops handshake_nl_ops[] = {
 		.cmd		= HANDSHAKE_CMD_DONE,
 		.doit		= handshake_nl_done_doit,
 		.policy		= handshake_done_nl_policy,
-		.maxattr	= HANDSHAKE_A_DONE_REMOTE_AUTH,
+		.maxattr	= HANDSHAKE_A_DONE_RECORD_SIZE_LIMIT,
 		.flags		= GENL_CMD_CAP_DO,
 	},
 };
diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c
index d6f52839827e..7cafac6cff1f 100644
--- a/net/handshake/tlshd.c
+++ b/net/handshake/tlshd.c
@@ -26,7 +26,8 @@
 
 struct tls_handshake_req {
 	void			(*th_consumer_done)(void *data, int status,
-						    key_serial_t peerid);
+						    key_serial_t peerid,
+						    size_t tls_record_size_limit);
 	void			*th_consumer_data;
 
 	int			th_type;
@@ -39,6 +40,8 @@ struct tls_handshake_req {
 
 	unsigned int		th_num_peerids;
 	key_serial_t		th_peerid[5];
+
+	size_t			record_size_limit;
 };
 
 static struct tls_handshake_req *
@@ -55,6 +58,7 @@ tls_handshake_req_init(struct handshake_req *req,
 	treq->th_num_peerids = 0;
 	treq->th_certificate = TLS_NO_CERT;
 	treq->th_privkey = TLS_NO_PRIVKEY;
+	treq->record_size_limit = TLS_NO_RECORD_SIZE_LIMIT;
 	return treq;
 }
 
@@ -83,6 +87,13 @@ static void tls_handshake_remote_peerids(struct tls_handshake_req *treq,
 		if (i >= treq->th_num_peerids)
 			break;
 	}
+
+	nla_for_each_attr(nla, head, len, rem) {
+		if (nla_type(nla) == HANDSHAKE_A_DONE_RECORD_SIZE_LIMIT) {
+			treq->record_size_limit = nla_get_u32(nla);
+			break;
+		}
+	}
 }
 
 /**
@@ -105,7 +116,7 @@ static void tls_handshake_done(struct handshake_req *req,
 		set_bit(HANDSHAKE_F_REQ_SESSION, &req->hr_flags);
 
 	treq->th_consumer_done(treq->th_consumer_data, -status,
-			       treq->th_peerid[0]);
+			       treq->th_peerid[0], treq->record_size_limit);
 }
 
 #if IS_ENABLED(CONFIG_KEYS)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index e1c85123b445..2014d906ff06 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -417,13 +417,15 @@ static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
  * @data: address of xprt to wake
  * @status: status of handshake
  * @peerid: serial number of key containing the remote peer's identity
+ * @tls_record_size_limit: Max tls_record_size_limit of the endpoint
  *
  * If a security policy is specified as an export option, we don't
  * have a specific export here to check. So we set a "TLS session
  * is present" flag on the xprt and let an upper layer enforce local
  * security policy.
  */
-static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid)
+static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid,
+				   size_t tls_record_size_limit)
 {
 	struct svc_xprt *xprt = data;
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 04ff66758fc3..509aa6269b0a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2569,9 +2569,11 @@ static int xs_tcp_tls_finish_connecting(struct rpc_xprt *lower_xprt,
  * @data: address of xprt to wake
  * @status: status of handshake
  * @peerid: serial number of key containing the remote's identity
+ * @tls_record_size_limit: Max tls_record_size_limit of the endpoint
  *
  */
-static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid)
+static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid,
+				  size_t tls_record_size_limit)
 {
 	struct rpc_xprt *lower_xprt = data;
 	struct sock_xprt *lower_transport =
-- 
2.50.1


  reply	other threads:[~2025-07-29  2:43 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-29  2:41 [RFC 0/4] net/tls: add support for the record size limit extension Wilfred Mallawa
2025-07-29  2:41 ` Wilfred Mallawa [this message]
2025-07-29  8:07   ` [RFC 1/4] net/handshake: get negotiated tls record size limit Damien Le Moal
2025-07-29  8:12   ` Hannes Reinecke
2025-08-07  0:03     ` Wilfred Mallawa
2025-07-29  2:41 ` [RFC 2/4] net/tls/tls_sw: use the record size limit specified Wilfred Mallawa
2025-07-29  8:13   ` Damien Le Moal
2025-08-07  0:04     ` Wilfred Mallawa
2025-07-29  2:41 ` [RFC 3/4] nvme/host/tcp: set max record size in the tls context Wilfred Mallawa
2025-07-29  8:16   ` Hannes Reinecke
2025-07-29  2:41 ` [RFC 4/4] nvme/target/tcp: " Wilfred Mallawa
2025-07-29  8:16   ` Hannes Reinecke
2025-07-29 13:37 ` [RFC 0/4] net/tls: add support for the record size limit extension Chuck Lever
2025-08-07  0:14   ` Wilfred Mallawa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250729024150.222513-4-wilfred.opensource@gmail.com \
    --to=wilfred.opensource@gmail.com \
    --cc=Dai.Ngo@oracle.com \
    --cc=alistair.francis@wdc.com \
    --cc=anna@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=borisp@nvidia.com \
    --cc=chuck.lever@oracle.com \
    --cc=corbet@lwn.net \
    --cc=davem@davemloft.net \
    --cc=dlemoal@kernel.org \
    --cc=donald.hunter@gmail.com \
    --cc=edumazet@google.com \
    --cc=hch@lst.de \
    --cc=horms@kernel.org \
    --cc=jlayton@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=kbusch@kernel.org \
    --cc=kch@nvidia.com \
    --cc=kernel-tls-handshake@lists.linux.dev \
    --cc=kuba@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=neil@brown.name \
    --cc=netdev@vger.kernel.org \
    --cc=okorniev@redhat.com \
    --cc=pabeni@redhat.com \
    --cc=sagi@grimberg.me \
    --cc=tom@talpey.com \
    --cc=trondmy@kernel.org \
    --cc=wilfred.mallawa@wdc.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).