net/tls: support setting the maximum payload size

During a handshake, an endpoint may specify a maximum record size limit.
Currently, the kernel defaults to TLS_MAX_PAYLOAD_SIZE (16KB) for the
maximum record size. Meaning that, the outgoing records from the kernel
can exceed a lower size negotiated during the handshake. In such a case,
the TLS endpoint must send a fatal "record_overflow" alert [1], and
thus the record is discarded.

Upcoming Western Digital NVMe-TCP hardware controllers implement TLS
support. For these devices, supporting TLS record size negotiation is
necessary because the maximum TLS record size supported by the controller
is less than the default 16KB currently used by the kernel.

Currently, there is no way to inform the kernel of such a limit. This patch
adds support to a new setsockopt() option `TLS_TX_MAX_PAYLOAD_LEN` that
allows for setting the maximum plaintext fragment size. Once set, outgoing
records are no larger than the size specified. This option can be used to
specify the record size limit.

[1] https://www.rfc-editor.org/rfc/rfc8449

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20251022001937.20155-1-wilfred.opensource@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 64 insertions, 0 deletions

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 39a2ab47fe72..56ce0bc8317b 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -541,6 +541,28 @@ static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval,
 	return 0;
 }
 
+static int do_tls_getsockopt_tx_payload_len(struct sock *sk, char __user *optval,
+					    int __user *optlen)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+	u16 payload_len = ctx->tx_max_payload_len;
+	int len;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	if (len < sizeof(payload_len))
+		return -EINVAL;
+
+	if (put_user(sizeof(payload_len), optlen))
+		return -EFAULT;
+
+	if (copy_to_user(optval, &payload_len, sizeof(payload_len)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int do_tls_getsockopt(struct sock *sk, int optname,
 			     char __user *optval, int __user *optlen)
 {
@@ -560,6 +582,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname,
 	case TLS_RX_EXPECT_NO_PAD:
 		rc = do_tls_getsockopt_no_pad(sk, optval, optlen);
 		break;
+	case TLS_TX_MAX_PAYLOAD_LEN:
+		rc = do_tls_getsockopt_tx_payload_len(sk, optval, optlen);
+		break;
 	default:
 		rc = -ENOPROTOOPT;
 		break;
@@ -809,6 +834,32 @@ static int do_tls_setsockopt_no_pad(struct sock *sk, sockptr_t optval,
 	return rc;
 }
 
+static int do_tls_setsockopt_tx_payload_len(struct sock *sk, sockptr_t optval,
+					    unsigned int optlen)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+	struct tls_sw_context_tx *sw_ctx = tls_sw_ctx_tx(ctx);
+	u16 value;
+	bool tls_13 = ctx->prot_info.version == TLS_1_3_VERSION;
+
+	if (sw_ctx && sw_ctx->open_rec)
+		return -EBUSY;
+
+	if (sockptr_is_null(optval) || optlen != sizeof(value))
+		return -EINVAL;
+
+	if (copy_from_sockptr(&value, optval, sizeof(value)))
+		return -EFAULT;
+
+	if (value < TLS_MIN_RECORD_SIZE_LIM - (tls_13 ? 1 : 0) ||
+	    value > TLS_MAX_PAYLOAD_SIZE)
+		return -EINVAL;
+
+	ctx->tx_max_payload_len = value;
+
+	return 0;
+}
+
 static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 			     unsigned int optlen)
 {
@@ -830,6 +881,11 @@ static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 	case TLS_RX_EXPECT_NO_PAD:
 		rc = do_tls_setsockopt_no_pad(sk, optval, optlen);
 		break;
+	case TLS_TX_MAX_PAYLOAD_LEN:
+		lock_sock(sk);
+		rc = do_tls_setsockopt_tx_payload_len(sk, optval, optlen);
+		release_sock(sk);
+		break;
 	default:
 		rc = -ENOPROTOOPT;
 		break;
@@ -1019,6 +1075,7 @@ static int tls_init(struct sock *sk)
 
 	ctx->tx_conf = TLS_BASE;
 	ctx->rx_conf = TLS_BASE;
+	ctx->tx_max_payload_len = TLS_MAX_PAYLOAD_SIZE;
 	update_sk_prot(sk, ctx);
 out:
 	write_unlock_bh(&sk->sk_callback_lock);
@@ -1108,6 +1165,12 @@ static int tls_get_info(struct sock *sk, struct sk_buff *skb, bool net_admin)
 			goto nla_failure;
 	}
 
+	err = nla_put_u16(skb, TLS_INFO_TX_MAX_PAYLOAD_LEN,
+			  ctx->tx_max_payload_len);
+
+	if (err)
+		goto nla_failure;
+
 	rcu_read_unlock();
 	nla_nest_end(skb, start);
 	return 0;
@@ -1129,6 +1192,7 @@ static size_t tls_get_info_size(const struct sock *sk, bool net_admin)
 		nla_total_size(sizeof(u16)) +	/* TLS_INFO_TXCONF */
 		nla_total_size(0) +		/* TLS_INFO_ZC_RO_TX */
 		nla_total_size(0) +		/* TLS_INFO_RX_NO_PAD */
+		nla_total_size(sizeof(u16)) +   /* TLS_INFO_TX_MAX_PAYLOAD_LEN */
 		0;
 
 	return size;