[net,1/7] mptcp: sched: check both directions for backup

Commit Message

Matthieu Baerts (NGI0) July 27, 2024, 10:01 a.m. UTC

The 'mptcp_subflow_context' structure has two items related to the
backup flags:

 - 'backup': the subflow has been marked as backup by the other peer

 - 'request_bkup': the backup flag has been set by the host

Before this patch, the scheduler was only looking at the 'backup' flag.
That can make sense in some cases, but it looks like that's not what we
wanted for the general use, because either the path-manager was setting
both of them when sending an MP_PRIO, or the receiver was duplicating
the 'backup' flag in the subflow request.

Note that the use of these two flags in the path-manager are going to be
fixed in the next commits, but this change here is needed not to modify
the behaviour.

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Cc: [e-mail]
Reviewed-by: Mat Martineau <[e-mail]>
Signed-off-by: Matthieu Baerts (NGI0) <[e-mail]>
---
To: Steven Rostedt <[e-mail]>
To: Masami Hiramatsu <[e-mail]>
To: Mathieu Desnoyers <[e-mail]>
Cc: [e-mail]
---
 include/trace/events/mptcp.h |  2 +-
 net/mptcp/protocol.c         | 10 ++++++----
 2 files changed, 7 insertions(+), 5 deletions(-)

Patch

diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
index 09e72215b9f9..085b749cdd97 100644
--- a/include/trace/events/mptcp.h
+++ b/include/trace/events/mptcp.h
@@ -34,7 +34,7 @@  TRACE_EVENT(mptcp_subflow_get_send,
 		struct sock *ssk;
 
 		__entry->active = mptcp_subflow_active(subflow);
-		__entry->backup = subflow->backup;
+		__entry->backup = subflow->backup || subflow->request_bkup;
 
 		if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock))
 			__entry->free = sk_stream_memory_free(subflow->tcp_sock);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a26c2c840fd9..a2fc54ed68c0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1422,13 +1422,15 @@  struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	}
 
 	mptcp_for_each_subflow(msk, subflow) {
+		bool backup = subflow->backup || subflow->request_bkup;
+
 		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
 		tout = max(tout, mptcp_timeout_from_subflow(subflow));
-		nr_active += !subflow->backup;
+		nr_active += !backup;
 		pace = subflow->avg_pacing_rate;
 		if (unlikely(!pace)) {
 			/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@  struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		}
 
 		linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
-		if (linger_time < send_info[subflow->backup].linger_time) {
-			send_info[subflow->backup].ssk = ssk;
-			send_info[subflow->backup].linger_time = linger_time;
+		if (linger_time < send_info[backup].linger_time) {
+			send_info[backup].ssk = ssk;
+			send_info[backup].linger_time = linger_time;
 		}
 	}
 	__mptcp_set_timeout(sk, tout);