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 <[e-mail]>
Reviewed-by: Sabrina Dubroca <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

Documentation/networking/tls.rst

···
 record it will be decrypted again into a kernel buffer without zero copy.
 Such events are counted in the ``TlsDecryptRetry`` statistic.
 
+TLS_TX_MAX_PAYLOAD_LEN
+~~~~~~~~~~~~~~~~~~~~~~
+
+Specifies the maximum size of the plaintext payload for transmitted TLS records.
+
+When this option is set, the kernel enforces the specified limit on all outgoing
+TLS records. No plaintext fragment will exceed this size. This option can be used
+to implement the TLS Record Size Limit extension [1].
+
+* For TLS 1.2, the value corresponds directly to the record size limit.
+* For TLS 1.3, the value should be set to record_size_limit - 1, since
+  the record size limit includes one additional byte for the ContentType
+  field.
+
+The valid range for this option is 64 to 16384 bytes for TLS 1.2, and 63 to
+16384 bytes for TLS 1.3. The lower minimum for TLS 1.3 accounts for the
+extra byte used by the ContentType field.
+
+[1] https://datatracker.ietf.org/doc/html/rfc8449
+
 Statistics
 ==========
 

include/net/tls.h

···
 
 /* Maximum data size carried in a TLS record */
 #define TLS_MAX_PAYLOAD_SIZE		((size_t)1 << 14)
+/* Minimum record size limit as per RFC8449 */
+#define TLS_MIN_RECORD_SIZE_LIM		((size_t)1 << 6)
 
 #define TLS_HEADER_SIZE			5
 #define TLS_NONCE_OFFSET		TLS_HEADER_SIZE
···
 	u8 rx_conf:3;
 	u8 zerocopy_sendfile:1;
 	u8 rx_no_pad:1;
+	u16 tx_max_payload_len;
 
 	int (*push_pending_record)(struct sock *sk, int flags);
 	void (*sk_write_space)(struct sock *sk);

include/uapi/linux/tls.h

···
 #define TLS_RX			2	/* Set receive parameters */
 #define TLS_TX_ZEROCOPY_RO	3	/* TX zerocopy (only sendfile now) */
 #define TLS_RX_EXPECT_NO_PAD	4	/* Attempt opportunistic zero-copy */
+#define TLS_TX_MAX_PAYLOAD_LEN	5	/* Maximum plaintext size */
 
 /* Supported versions */
 #define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
···
 	TLS_INFO_RXCONF,
 	TLS_INFO_ZC_RO_TX,
 	TLS_INFO_RX_NO_PAD,
+	TLS_INFO_TX_MAX_PAYLOAD_LEN,
 	__TLS_INFO_MAX,
 };
 #define TLS_INFO_MAX (__TLS_INFO_MAX - 1)

net/tls/tls_device.c

···
 	/* TLS_HEADER_SIZE is not counted as part of the TLS record, and
 	 * we need to leave room for an authentication tag.
 	 */
-	max_open_record_len = TLS_MAX_PAYLOAD_SIZE +
+	max_open_record_len = tls_ctx->tx_max_payload_len +
 			      prot->prepend_size;
 	do {
 		rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size);

net/tls/tls_main.c

···
 	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)
 {
···
 		break;
 	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;
···
 	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)
 {
···
 		break;
 	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;
···
 
 	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);
···
 			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;
···
 		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;

net/tls/tls_sw.c

···
 		orig_size = msg_pl->sg.size;
 		full_record = false;
 		try_to_copy = msg_data_left(msg);
-		record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
+		record_room = tls_ctx->tx_max_payload_len - msg_pl->sg.size;
 		if (try_to_copy >= record_room) {
 			try_to_copy = record_room;
 			full_record = true;