[PATCH mptcp-next RFC v4 2/2] mptcp: send MP_FAIL and infinite mapping on the same ACK

[Chenguang Zhao <chenguang.zhao@linux.dev>]

From: Chenguang Zhao <zhaochenguang@kylinos.cn>

On a single subflow, accepting MP_FAIL must leave MPTCP mode at once
(RFC8684 §3.7). Emit the infinite mapping on the MP_FAIL reply ACK,
then call mptcp_try_fallback() immediately after.

Fixes: 1e39e5a32ad7 ("mptcp: infinite mapping sending")
Signed-off-by: Chenguang Zhao <zhaochenguang@kylinos.cn>
---
 net/mptcp/options.c  | 33 ++++++++++++++++++++++++++++++++-
 net/mptcp/pm.c       |  5 +++++
 net/mptcp/protocol.c |  8 +-------
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 97da22668dbe..ecf77e77d2de 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -638,7 +638,29 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	opts->csum_reqd = READ_ONCE(msk->csum_enabled);
 	mpext = skb ? mptcp_get_ext(skb) : NULL;
 
-	if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
+	if (unlikely(subflow->send_infinite_map)) {
+		unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
+
+		if (opts->csum_reqd)
+			map_size += TCPOLEN_MPTCP_DSS_CHECKSUM;
+
+		if (mpext) {
+			opts->ext_copy = *mpext;
+			opts->ext_copy.infinite_map = 1;
+			opts->ext_copy.data_len = 0;
+		} else {
+			opts->ext_copy.use_map = 1;
+			opts->ext_copy.dsn64 = 1;
+			opts->ext_copy.infinite_map = 1;
+			opts->ext_copy.data_len = 0;
+			opts->ext_copy.data_seq = READ_ONCE(msk->snd_nxt);
+			opts->ext_copy.subflow_seq = subflow->rel_write_seq;
+		}
+
+		dss_size = map_size;
+		opts->suboptions = OPTION_MPTCP_DSS;
+		ret = true;
+	} else if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
 		unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
 
 		if (mpext) {
@@ -1566,6 +1588,15 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 			}
 			ptr += 1;
+
+			if (unlikely(mpext->infinite_map)) {
+				subflow = mptcp_subflow_ctx(ssk);
+				if (subflow->send_infinite_map) {
+					subflow->send_infinite_map = 0;
+					MPTCP_INC_STATS(sock_net(ssk),
+							MPTCP_MIB_INFINITEMAPTX);
+				}
+			}
 		}
 
 		/* We might need to add MP_FAIL options in rare cases */
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index ba7c6f80a183..69701ac7e436 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -895,6 +895,11 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 		pr_debug("MP_FAIL response received\n");
 		WRITE_ONCE(subflow->fail_tout, 0);
 	}
+
+	if (!mptcp_try_fallback(sk, MPTCP_MIB_MPFAILFALLBACK)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_FALLBACKFAILED);
+		mptcp_subflow_reset(sk);
+	}
 }
 
 static int mptcp_add_addr_len(int family, bool echo, bool port)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f879b1061f2d..abe45a31ca5f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1417,13 +1417,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 
 	mpext->infinite_map = 1;
 	mpext->data_len = 0;
-
-	if (!mptcp_try_fallback(ssk, MPTCP_MIB_INFINITEMAPTX)) {
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_FALLBACKFAILED);
-		mptcp_subflow_reset(ssk);
-		return;
-	}
-
+	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
 	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
 }
 
-- 
2.25.1