This patch defines the packet scheduler wrapper mptcp_sched_get_retrans(),
invoke data_init() and get_subflow() of msk->sched in it.

Set data->reinject to true in mptcp_sched_get_retrans(). If msk->sched is
NULL, use default functions mptcp_subflow_get_retrans() to retrans data.

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

Add 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.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 69 +++++++++++++++++++++++++-------------------
 net/mptcp/protocol.h |  2 ++
 net/mptcp/sched.c    | 30 +++++++++++++++++++
 3 files changed, 72 insertions(+), 29 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 90ddbd82a805..659589a51bb0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2240,17 +2240,12 @@ static void mptcp_timeout_timer(struct timer_list *t)
  *
  * A backup subflow is returned only if that is the only kind available.
  */
-static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 {
 	struct sock *backup = NULL, *pick = NULL;
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
 
-	sock_owned_by_me((const struct sock *)msk);
-
-	if (__mptcp_check_fallback(msk))
-		return NULL;
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2525,16 +2520,17 @@ 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)) {
@@ -2553,31 +2549,46 @@ 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;
+			ssk = mptcp_subflow_tcp_sock(subflow);
+			if (!ssk)
+				goto reset_timer;
 
-		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);
-	}
+			lock_sock(ssk);
 
-	release_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;
+			mptcp_subflow_set_scheduled(subflow, false);
+		}
+	}
+	dfrag->already_sent = max(dfrag->already_sent, len);
 
 reset_timer:
 	mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 77ca5f04b7d0..0694ce6a4e39 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -651,7 +651,9 @@ void mptcp_release_sched(struct mptcp_sock *msk);
 void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 				 bool scheduled);
 struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk);
 int mptcp_sched_get_send(struct mptcp_sock *msk);
+int mptcp_sched_get_retrans(struct mptcp_sock *msk);
 
 static inline bool __tcp_can_send(const struct sock *ssk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index bc5d82300863..edddd7cceada 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -149,3 +149,33 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 	msk->sched->data_init(msk, &data);
 	return msk->sched->get_subflow(msk, &data);
 }
+
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sched_data data;
+	struct sock *ssk = NULL;
+
+	sock_owned_by_me((const struct sock *)msk);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled))
+			return 0;
+	}
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return -EINVAL;
+
+	if (!msk->sched) {
+		ssk = mptcp_subflow_get_retrans(msk);
+		if (!ssk)
+			return -EINVAL;
+		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+		return 0;
+	}
+
+	data.reinject = true;
+	msk->sched->data_init(msk, &data);
+	return msk->sched->get_subflow(msk, &data);
+}
-- 
2.35.3