To support redundant package schedulers more easily, this patch moves the
packet scheduler out of the dfrags loop in __mptcp_push_pending(), invoke
mptcp_sched_get_send() only once. And update the socket locks
correspondingly.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 85 +++++++++++++++++---------------------------
 1 file changed, 33 insertions(+), 52 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3641fb73bc1f..99a9ec70c7e9 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1417,14 +1417,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	u64 linger_time;
 	long tout = 0;
 
-	/* re-use last subflow, if the burst allow that */
-	if (msk->last_snd && msk->snd_burst > 0 &&
-	    sk_stream_memory_free(msk->last_snd) &&
-	    mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
-		mptcp_set_timeout(sk);
-		return msk->last_snd;
-	}
-
 	/* pick the subflow with the lower wmem/wspace ratio */
 	for (i = 0; i < SSK_MODE_MAX; ++i) {
 		send_info[i].ssk = NULL;
@@ -1477,16 +1469,13 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
 	wmem = READ_ONCE(ssk->sk_wmem_queued);
-	if (!burst) {
-		msk->last_snd = NULL;
+	if (!burst)
 		return ssk;
-	}
 
 	subflow = mptcp_subflow_ctx(ssk);
 	subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
 					   READ_ONCE(ssk->sk_pacing_rate) * burst,
 					   burst + wmem);
-	msk->last_snd = ssk;
 	msk->snd_burst = burst;
 	return ssk;
 }
@@ -1530,60 +1519,52 @@ 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,
 	};
 	bool do_check_data_fin = false;
 	struct mptcp_data_frag *dfrag;
+	struct sock *ssk;
 	int len;
 
-	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;
-
-			prev_ssk = ssk;
-			ssk = mptcp_sched_get_send(msk);
-
-			/* 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);
+	while (mptcp_send_head(sk) && (ssk = mptcp_sched_get_send(msk))) {
+		lock_sock(ssk);
 
-			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-			if (ret <= 0) {
-				if (ret == -EAGAIN)
-					continue;
-				mptcp_push_release(ssk, &info);
-				goto out;
+		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;
+
+				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+				if (ret <= 0) {
+					if (ret == -EAGAIN)
+						continue;
+					mptcp_push_release(ssk, &info);
+					goto out;
+				}
+
+				do_check_data_fin = true;
+				info.sent += ret;
+				len -= ret;
+
+				mptcp_update_post_push(msk, dfrag, ret);
 			}
+			WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 
-			do_check_data_fin = true;
-			info.sent += ret;
-			len -= ret;
-
-			mptcp_update_post_push(msk, dfrag, ret);
+			if (msk->snd_burst > 0 &&
+			    sk_stream_memory_free(ssk) &&
+			    mptcp_subflow_active(mptcp_subflow_ctx(ssk))) {
+				mptcp_set_timeout(sk);
+			} else {
+				break;
+			}
 		}
-		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);
+	}
 
 out:
 	/* ensure the rtx timer is running */
-- 
2.35.3