[MPTCP] [RFC PATCH 2/2] mptcp: leverage the deferred actions for packet scheduling

[MPTCP] [RFC PATCH 2/2] mptcp: leverage the deferred actions for packet scheduling

[Paolo Abeni]

[-- Attachment #1: Type: text/plain, Size: 2730 bytes --]

This change leverage the infrastructure introduced by
the previous patch to avoid invoking the MPTCP worker
to spool the pending data, when the packet scheduler
picks a subflow other then the one currently processing
the incoming MPTCP-level ack.

Additinally we can fourther refine the subflow selection
invoking the packet scheduler for each chunk of data
even inside __mptcp_subflow_push_pending()

Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
---
 net/mptcp/protocol.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3d5ac817b2fb..af45affc0a17 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1508,7 +1508,9 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_sendmsg_info info;
 	struct mptcp_data_frag *dfrag;
+	struct sock *xmit_ssk;
 	int len, copied = 0;
+	bool first = true;
 
 	info.flags = 0;
 	while ((dfrag = mptcp_send_head(sk))) {
@@ -1518,6 +1520,18 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 		while (len > 0) {
 			int ret = 0;
 
+			/* the caller already invoked the packet scheduler,
+			 * check for a different subflow usage only after
+			 * spooling the first chunk of data
+			 */
+			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
+			if (!xmit_ssk)
+				goto out;
+			if (xmit_ssk != ssk) {
+				mptcp_subflow_defer(mptcp_subflow_ctx(xmit_ssk));
+				goto out;
+			}
+
 			if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) {
 				__mptcp_update_wmem(sk);
 				sk_mem_reclaim_partial(sk);
@@ -1536,6 +1550,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			msk->tx_pending_data -= ret;
 			copied += ret;
 			len -= ret;
+			first = false;
 		}
 		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
 	}
@@ -2244,7 +2259,6 @@ static void mptcp_worker(struct work_struct *work)
 	if (unlikely(state == TCP_CLOSE))
 		goto unlock;
 
-	mptcp_push_pending(sk, 0);
 	mptcp_check_data_fin_ack(sk);
 	__mptcp_flush_join_list(msk);
 
@@ -2905,10 +2919,12 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		return;
 
 	if (!sock_owned_by_user(sk)) {
-		if (mptcp_subflow_get_send(mptcp_sk(sk)) == ssk)
+		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
+
+		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
-		else
-			mptcp_schedule_work(sk);
+		else if (xmit_ssk)
+			mptcp_subflow_defer(mptcp_subflow_ctx(xmit_ssk));
 	} else {
 		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
 	}
-- 
2.26.2