[PATCH mptcp-next v3 0/2] BPF redundant scheduler, part 3

[PATCH mptcp-next v3 0/2] BPF redundant scheduler, part 3

[Geliang Tang]

v3:
- invoking __mptcp_retrans in __mptcp_subflow_push_pending fails
  with a soft lockup error, so use MPTCP_WORK_RTX instead.
- invoke __mptcp_retrans in __mptcp_push_pending iteratively for each
  dfrag.
- depends on "BPF redundant scheduler, part 2" v23.

v2:
- drop retrans_redundant flag.
- call __mptcp_retrans() directly.
- depends on "BPF redundant scheduler, part 2" v23.

v1:
- The DSS issue has been fixed in this version, and all tests
(mptcp_connect.sh, mptcp_join.sh, simult_flows.sh and BPF test_progs)
passed.
- No need to set already_sent to 0, drop this.
- Add retrans_redundant flag.
- depends on "BPF redundant scheduler, part 2" v22.

Geliang Tang (2):
  mptcp: update mptcp_push_release
  mptcp: retrans for redundant sends

 net/mptcp/protocol.c | 63 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 53 insertions(+), 10 deletions(-)

-- 
2.35.3

[PATCH mptcp-next v3 1/2] mptcp: update mptcp_push_release

[Geliang Tang]

This patch moves the NULL pointer check into mptcp_push_release(). Also
add a new parameter 'push' for it to set whether to invoke tcp_push in
it.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5505c1439b3e..0c4403c2aace 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1471,9 +1471,17 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	return ssk;
 }
 
-static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info)
+static void mptcp_push_release(struct sock *ssk,
+			       struct mptcp_sendmsg_info *info,
+			       bool push)
 {
-	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+	if (!ssk)
+		return;
+
+	if (push) {
+		tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle,
+			 info->size_goal);
+	}
 	release_sock(ssk);
 }
 
@@ -1579,8 +1587,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 					/* First check. If the ssk has changed since
 					 * the last round, release prev_ssk
 					 */
-					if (prev_ssk)
-						mptcp_push_release(prev_ssk, &info);
+					mptcp_push_release(prev_ssk, &info, do_check_data_fin);
 
 					/* Need to lock the new subflow only if different
 					 * from the previous one, otherwise we are still
@@ -1606,8 +1613,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	}
 
 	/* at this point we held the socket lock for the last subflow we used */
-	if (ssk)
-		mptcp_push_release(ssk, &info);
+	mptcp_push_release(ssk, &info, do_check_data_fin);
 
 	/* ensure the rtx timer is running */
 	if (!mptcp_timer_pending(sk))
-- 
2.35.3

[PATCH mptcp-next v3 2/2] mptcp: retrans for redundant sends

[Geliang Tang]

Redundant sends need to work more like the MPTCP retransmit code path.
When the scheduler selects multiple subflows, the first subflow to send
is a "normal" transmit, and any other subflows would act like a retransmit
when accessing the dfrags.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 45 ++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 41 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 0c4403c2aace..8c2480b4baec 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -45,6 +45,7 @@ static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_sm
 
 static void __mptcp_destroy_sock(struct sock *sk);
 static void __mptcp_check_send_data_fin(struct sock *sk);
+static void __mptcp_retrans(struct sock *sk);
 
 DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
@@ -998,7 +999,7 @@ static void __mptcp_clean_una(struct sock *sk)
 
 		if (unlikely(dfrag == msk->first_pending)) {
 			/* in recovery mode can see ack after the current snd head */
-			if (WARN_ON_ONCE(!msk->recovery))
+			if (!msk->recovery)
 				break;
 
 			WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
@@ -1013,7 +1014,7 @@ static void __mptcp_clean_una(struct sock *sk)
 
 		/* prevent wrap around in recovery mode */
 		if (unlikely(delta > dfrag->already_sent)) {
-			if (WARN_ON_ONCE(!msk->recovery))
+			if (!msk->recovery)
 				goto out;
 			if (WARN_ON_ONCE(delta > dfrag->data_len))
 				goto out;
@@ -1112,6 +1113,7 @@ struct mptcp_sendmsg_info {
 	u16 sent;
 	unsigned int flags;
 	bool data_lock_held;
+	struct mptcp_data_frag *last;
 };
 
 static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk,
@@ -1527,6 +1529,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 		info->sent = dfrag->already_sent;
 		info->limit = dfrag->data_len;
 		len = dfrag->data_len - dfrag->already_sent;
+		info->last = dfrag;
 		while (len > 0) {
 			int ret = 0;
 
@@ -1563,14 +1566,19 @@ 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_subflow_context *subflow;
+	struct mptcp_data_frag *head, *dfrag;
 	struct mptcp_sendmsg_info info = {
 				.flags = flags,
 	};
 	bool do_check_data_fin = false;
 	int push_count = 1;
 
+	head = mptcp_send_head(sk);
+	if (!head)
+		goto out;
+
 	while (mptcp_send_head(sk) && (push_count > 0)) {
-		int ret = 0;
+		int ret = 0, i = 0;
 
 		if (mptcp_sched_get_send(msk))
 			break;
@@ -1579,6 +1587,19 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 
 		mptcp_for_each_subflow(msk, subflow) {
 			if (READ_ONCE(subflow->scheduled)) {
+				if (i > 0) {
+					WRITE_ONCE(msk->first_pending, head);
+					mptcp_push_release(ssk, &info, do_check_data_fin);
+
+					while ((dfrag = mptcp_send_head(sk))) {
+						__mptcp_retrans(sk);
+						if (dfrag == info.last)
+							break;
+						WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+					}
+					goto out;
+				}
+
 				mptcp_subflow_set_scheduled(subflow, false);
 
 				prev_ssk = ssk;
@@ -1606,6 +1627,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 						push_count--;
 					continue;
 				}
+				i++;
 				do_check_data_fin = true;
 				msk->last_snd = ssk;
 			}
@@ -1615,6 +1637,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	/* at this point we held the socket lock for the last subflow we used */
 	mptcp_push_release(ssk, &info, do_check_data_fin);
 
+out:
 	/* ensure the rtx timer is running */
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
@@ -1629,14 +1652,19 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 	struct mptcp_sendmsg_info info = {
 		.data_lock_held = true,
 	};
+	struct mptcp_data_frag *head;
 	struct sock *xmit_ssk;
 	bool push = true;
 	int copied = 0;
 
+	head = mptcp_send_head(sk);
+	if (!head)
+		goto out;
+
 	info.flags = 0;
 	while (mptcp_send_head(sk) && push) {
 		bool delegate = false;
-		int ret = 0;
+		int ret = 0, i = 0;
 
 		/* check for a different subflow usage only after
 		 * spooling the first chunk of data
@@ -1656,6 +1684,13 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 
 		mptcp_for_each_subflow(msk, subflow) {
 			if (READ_ONCE(subflow->scheduled)) {
+				if (i > 0) {
+					WRITE_ONCE(msk->first_pending, head);
+					if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags))
+						mptcp_schedule_work(sk);
+					goto out;
+				}
+
 				mptcp_subflow_set_scheduled(subflow, false);
 
 				xmit_ssk = mptcp_subflow_tcp_sock(subflow);
@@ -1666,6 +1701,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 						goto out;
 					mptcp_subflow_delegate(subflow,
 							       MPTCP_DELEGATE_SEND);
+					i++;
 					msk->last_snd = ssk;
 					delegate = true;
 					push = false;
@@ -1677,6 +1713,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 					push = false;
 					continue;
 				}
+				i++;
 				copied += ret;
 				msk->last_snd = ssk;
 			}
-- 
2.35.3