This patch adds the multiple subflows support for __mptcp_retrans(). Use
get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.

Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.

Move sock_owned_by_me() check and fallback check into get_retrans()
wrapper from mptcp_subflow_get_retrans().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 66 +++++++++++++++++++++++++-------------------
 net/mptcp/sched.c    |  6 ++++
 2 files changed, 44 insertions(+), 28 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 57967438e70f..91b84321885c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2249,11 +2249,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
 
-	msk_owned_by_me(msk);
-
-	if (__mptcp_check_fallback(msk))
-		return NULL;
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2523,16 +2518,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 static void __mptcp_retrans(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
-	size_t copied = 0;
 	struct sock *ssk;
-	int ret;
+	int ret, err;
+	u16 len = 0;
 
 	mptcp_clean_una_wakeup(sk);
 
 	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_subflow_get_retrans(msk);
+	err = mptcp_sched_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2551,31 +2547,45 @@ static void __mptcp_retrans(struct sock *sk)
 		goto reset_timer;
 	}
 
-	if (!ssk)
+	if (err)
 		goto reset_timer;
 
-	lock_sock(ssk);
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled)) {
+			u16 copied = 0;
 
-	/* limit retransmission to the bytes already sent on some subflows */
-	info.sent = 0;
-	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
-	while (info.sent < info.limit) {
-		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-		if (ret <= 0)
-			break;
+			mptcp_subflow_set_scheduled(subflow, false);
 
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-		copied += ret;
-		info.sent += ret;
-	}
-	if (copied) {
-		dfrag->already_sent = max(dfrag->already_sent, info.sent);
-		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
-			 info.size_goal);
-		WRITE_ONCE(msk->allow_infinite_fallback, false);
-	}
+			ssk = mptcp_subflow_tcp_sock(subflow);
 
-	release_sock(ssk);
+			lock_sock(ssk);
+
+			/* limit retransmission to the bytes already sent on some subflows */
+			info.sent = 0;
+			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
+								    dfrag->already_sent;
+			while (info.sent < info.limit) {
+				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+				if (ret <= 0)
+					break;
+
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+				copied += ret;
+				info.sent += ret;
+			}
+			if (copied) {
+				len = max(copied, len);
+				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+					 info.size_goal);
+				WRITE_ONCE(msk->allow_infinite_fallback, false);
+			}
+
+			release_sock(ssk);
+
+			msk->last_snd = ssk;
+		}
+	}
+	dfrag->already_sent = max(dfrag->already_sent, len);
 
 reset_timer:
 	mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 6428323d8c7f..c7c167e48d72 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -156,6 +156,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sched_data data;
 
+	msk_owned_by_me(msk);
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return -EINVAL;
+
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled))
 			return 0;
-- 
2.35.3