[PATCH mptcp-next v10 2/5] mptcp: redundant subflows push pending

[Geliang Tang <geliang.tang@suse.com>]

This patch adds the redundant subflows support for __mptcp_push_pending().
Use mptcp_sched_get_send() wrapper instead of mptcp_subflow_get_send()
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 | 96 ++++++++++++++++++++++++++------------------
 net/mptcp/protocol.h | 10 +++++
 2 files changed, 66 insertions(+), 40 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6e44786e01fd..f97e6c318c0b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1516,57 +1516,73 @@ void mptcp_check_and_set_pending(struct sock *sk)
 
 void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
-	struct sock *prev_ssk = NULL, *ssk = NULL;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct mptcp_sendmsg_info info = {
-				.flags = flags,
-	};
-	struct mptcp_data_frag *dfrag;
+	struct mptcp_subflow_context *subflow;
 	int len, copied = 0;
 
-	while ((dfrag = mptcp_send_head(sk))) {
-		info.sent = dfrag->already_sent;
-		info.limit = dfrag->data_len;
-		len = dfrag->data_len - dfrag->already_sent;
-		while (len > 0) {
-			int ret = 0;
+	if (!mptcp_sched_get_send(msk))
+		goto out;
 
-			prev_ssk = ssk;
-			ssk = mptcp_subflow_get_send(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled)) {
+			struct sock *prev_ssk = NULL, *ssk = NULL;
+			struct mptcp_sendmsg_info info = {
+				.flags = flags,
+			};
+			struct mptcp_data_frag *dfrag;
 
-			/* First check. If the ssk has changed since
-			 * the last round, release prev_ssk
-			 */
-			if (ssk != prev_ssk && prev_ssk)
-				mptcp_push_release(prev_ssk, &info);
-			if (!ssk)
+			dfrag = mptcp_send_head(sk);
+			if (!dfrag)
 				goto out;
 
-			/* Need to lock the new subflow only if different
-			 * from the previous one, otherwise we are still
-			 * helding the relevant lock
-			 */
-			if (ssk != prev_ssk)
-				lock_sock(ssk);
-
-			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-			if (ret <= 0) {
+			do {
+				info.sent = dfrag->already_sent;
+				info.limit = dfrag->data_len;
+				len = dfrag->data_len - dfrag->already_sent;
+				while (len > 0) {
+					int ret = 0;
+
+					prev_ssk = ssk;
+					ssk = mptcp_subflow_tcp_sock(subflow);
+
+					/* First check. If the ssk has changed since
+					 * the last round, release prev_ssk
+					 */
+					if (ssk != prev_ssk && prev_ssk)
+						mptcp_push_release(prev_ssk, &info);
+					if (!ssk)
+						goto out;
+
+					/* Need to lock the new subflow only if different
+					 * from the previous one, otherwise we are still
+					 * helding the relevant lock
+					 */
+					if (ssk != prev_ssk)
+						lock_sock(ssk);
+
+					ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+					if (ret <= 0) {
+						mptcp_push_release(ssk, &info);
+						goto out;
+					}
+
+					info.sent += ret;
+					copied += ret;
+					len -= ret;
+
+					mptcp_update_post_push(msk, dfrag, ret);
+				}
+			} while ((dfrag = mptcp_next_frag(sk, dfrag)));
+
+			/* at this point we held the socket lock for the last subflow we used */
+			if (ssk) {
 				mptcp_push_release(ssk, &info);
-				goto out;
+				msk->last_snd = ssk;
+				mptcp_subflow_set_scheduled(subflow, false);
 			}
-
-			info.sent += ret;
-			copied += ret;
-			len -= ret;
-
-			mptcp_update_post_push(msk, dfrag, ret);
 		}
-		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
-
-	/* at this point we held the socket lock for the last subflow we used */
-	if (ssk)
-		mptcp_push_release(ssk, &info);
+	WRITE_ONCE(msk->first_pending, NULL);
 
 out:
 	/* ensure the rtx timer is running */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index af414cd8b7cd..09a9797d2dfb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -355,6 +355,16 @@ static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
 						     list_next_entry(cur, list);
 }
 
+static inline struct mptcp_data_frag *mptcp_next_frag(struct sock *sk,
+						      struct mptcp_data_frag *cur)
+{
+	if (!cur)
+		return NULL;
+
+	return list_is_last(&cur->list, &mptcp_sk(sk)->rtx_queue) ? NULL :
+						     list_next_entry(cur, list);
+}
+
 static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-- 
2.35.3