mptcp: Write MPTCP DSS headers to outgoing data packets

Per-packet metadata required to write the MPTCP DSS option is written to
the skb_ext area. One write to the socket may contain more than one
packet of data, which is copied to page fragments and mapped in to MPTCP
DSS segments with size determined by the available page fragments and
the maximum mapping length allowed by the MPTCP specification. If
do_tcp_sendpages() splits a DSS segment in to multiple skbs, that's ok -
the later skbs can either have duplicated DSS mapping information or
none at all, and the receiver can handle that.

The current implementation uses the subflow frag cache and tcp
sendpages to avoid excessive code duplication. More work is required to
ensure that it works correctly under memory pressure and to support
MPTCP-level retransmissions.

The MPTCP DSS checksum is not yet implemented.

Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Peter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: Peter Krystad <peter.krystad@linux.intel.com>
Co-developed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 151 insertions, 4 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 52ff2301b68b..5ea127bc7f01 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -134,13 +134,13 @@ void mptcp_rcv_synsent(struct sock *sk)
 	}
 }
 
-bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
-			       unsigned int *size, unsigned int remaining,
-			       struct mptcp_out_options *opts)
+static bool mptcp_established_options_mp(struct sock *sk, unsigned int *size,
+					 unsigned int remaining,
+					 struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	if (subflow->mp_capable && !subflow->fourth_ack) {
+	if (!subflow->fourth_ack) {
 		opts->suboptions = OPTION_MPTCP_MPC_ACK;
 		opts->sndr_key = subflow->local_key;
 		opts->rcvr_key = subflow->remote_key;
@@ -153,6 +153,112 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 	return false;
 }
 
+static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
+				 struct mptcp_ext *ext)
+{
+	ext->data_fin = 1;
+
+	if (!ext->use_map) {
+		/* RFC6824 requires a DSS mapping with specific values
+		 * if DATA_FIN is set but no data payload is mapped
+		 */
+		ext->use_map = 1;
+		ext->dsn64 = 1;
+		ext->data_seq = mptcp_sk(subflow->conn)->write_seq;
+		ext->subflow_seq = 0;
+		ext->data_len = 1;
+	} else {
+		/* If there's an existing DSS mapping, DATA_FIN consumes
+		 * 1 additional byte of mapping space.
+		 */
+		ext->data_len++;
+	}
+}
+
+static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
+					  unsigned int *size,
+					  unsigned int remaining,
+					  struct mptcp_out_options *opts)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	unsigned int dss_size = 0;
+	struct mptcp_ext *mpext;
+	struct mptcp_sock *msk;
+	unsigned int ack_size;
+	u8 tcp_fin;
+
+	if (skb) {
+		mpext = mptcp_get_ext(skb);
+		tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+	} else {
+		mpext = NULL;
+		tcp_fin = 0;
+	}
+
+	if (!skb || (mpext && mpext->use_map) || tcp_fin) {
+		unsigned int map_size;
+
+		map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
+
+		remaining -= map_size;
+		dss_size = map_size;
+		if (mpext)
+			opts->ext_copy = *mpext;
+
+		if (skb && tcp_fin &&
+		    subflow->conn->sk_state != TCP_ESTABLISHED)
+			mptcp_write_data_fin(subflow, &opts->ext_copy);
+	}
+
+	ack_size = TCPOLEN_MPTCP_DSS_ACK64;
+
+	/* Add kind/length/subtype/flag overhead if mapping is not populated */
+	if (dss_size == 0)
+		ack_size += TCPOLEN_MPTCP_DSS_BASE;
+
+	dss_size += ack_size;
+
+	msk = mptcp_sk(mptcp_subflow_ctx(sk)->conn);
+	if (msk) {
+		opts->ext_copy.data_ack = msk->ack_seq;
+	} else {
+		mptcp_crypto_key_sha(mptcp_subflow_ctx(sk)->remote_key,
+				     NULL, &opts->ext_copy.data_ack);
+		opts->ext_copy.data_ack++;
+	}
+
+	opts->ext_copy.ack64 = 1;
+	opts->ext_copy.use_ack = 1;
+
+	*size = ALIGN(dss_size, 4);
+	return true;
+}
+
+bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+			       unsigned int *size, unsigned int remaining,
+			       struct mptcp_out_options *opts)
+{
+	unsigned int opt_size = 0;
+	bool ret = false;
+
+	if (mptcp_established_options_mp(sk, &opt_size, remaining, opts))
+		ret = true;
+	else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
+					       opts))
+		ret = true;
+
+	/* we reserved enough space for the above options, and exceeding the
+	 * TCP option space would be fatal
+	 */
+	if (WARN_ON_ONCE(opt_size > remaining))
+		return false;
+
+	*size += opt_size;
+	remaining -= opt_size;
+
+	return ret;
+}
+
 bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 			  struct mptcp_out_options *opts)
 {
@@ -194,4 +300,45 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 			ptr += 2;
 		}
 	}
+
+	if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
+		struct mptcp_ext *mpext = &opts->ext_copy;
+		u8 len = TCPOLEN_MPTCP_DSS_BASE;
+		u8 flags = 0;
+
+		if (mpext->use_ack) {
+			len += TCPOLEN_MPTCP_DSS_ACK64;
+			flags = MPTCP_DSS_HAS_ACK | MPTCP_DSS_ACK64;
+		}
+
+		if (mpext->use_map) {
+			len += TCPOLEN_MPTCP_DSS_MAP64;
+
+			/* Use only 64-bit mapping flags for now, add
+			 * support for optional 32-bit mappings later.
+			 */
+			flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
+			if (mpext->data_fin)
+				flags |= MPTCP_DSS_DATA_FIN;
+		}
+
+		*ptr++ = htonl((TCPOPT_MPTCP << 24) |
+			       (len  << 16) |
+			       (MPTCPOPT_DSS << 12) |
+			       (flags));
+
+		if (mpext->use_ack) {
+			put_unaligned_be64(mpext->data_ack, ptr);
+			ptr += 2;
+		}
+
+		if (mpext->use_map) {
+			put_unaligned_be64(mpext->data_seq, ptr);
+			ptr += 2;
+			put_unaligned_be32(mpext->subflow_seq, ptr);
+			ptr += 1;
+			put_unaligned_be32(mpext->data_len << 16 |
+					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+		}
+	}
 }