To support redundant package schedulers more easily, this patch refactors
the data sending loop in __subflow_push_pending(), to delay updating
first_pending until all data is sent.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 36 ++++++++++++++++++++++++++++++++----
 net/mptcp/protocol.h | 13 ++++++++++---
 2 files changed, 42 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b8265badbe29..4c249d1b9ec6 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1112,6 +1112,7 @@ struct mptcp_sendmsg_info {
 	u16 sent;
 	unsigned int flags;
 	bool data_lock_held;
+	struct mptcp_data_frag *last_frag;
 };
 
 static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk,
@@ -1502,6 +1503,19 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
 		msk->snd_nxt = snd_nxt_new;
 }
 
+static void mptcp_update_first_pending(struct sock *sk, struct mptcp_sendmsg_info *info)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (info->last_frag)
+		WRITE_ONCE(msk->first_pending, mptcp_next_frag(sk, info->last_frag));
+}
+
+static void mptcp_update_dfrags(struct sock *sk, struct mptcp_sendmsg_info *info)
+{
+	mptcp_update_first_pending(sk, info);
+}
+
 void mptcp_check_and_set_pending(struct sock *sk)
 {
 	if (mptcp_send_head(sk))
@@ -1515,7 +1529,13 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 	struct mptcp_data_frag *dfrag;
 	int len, copied = 0, err = 0;
 
-	while ((dfrag = mptcp_send_head(sk))) {
+	info->last_frag = NULL;
+
+	dfrag = mptcp_send_head(sk);
+	if (!dfrag)
+		goto out;
+
+	do {
 		info->sent = dfrag->already_sent;
 		info->limit = dfrag->data_len;
 		len = dfrag->data_len - dfrag->already_sent;
@@ -1534,7 +1554,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 
 			mptcp_update_post_push(msk, dfrag, ret);
 		}
-		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+		info->last_frag = dfrag;
+		dfrag = mptcp_next_frag(sk, dfrag);
 
 		if (msk->snd_burst <= 0 ||
 		    !sk_stream_memory_free(ssk) ||
@@ -1543,7 +1564,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
 			goto out;
 		}
 		mptcp_set_timeout(sk);
-	}
+	} while (dfrag);
 	err = copied;
 
 out:
@@ -1587,6 +1608,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 
 				ret = __subflow_push_pending(sk, ssk, &info);
 				if (ret <= 0) {
+					mptcp_update_first_pending(sk, &info);
 					if (ret != -EAGAIN ||
 					    inet_sk_state_load(ssk) == TCP_FIN_WAIT1 ||
 					    inet_sk_state_load(ssk) == TCP_FIN_WAIT2 ||
@@ -1599,6 +1621,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 				mptcp_subflow_set_scheduled(subflow, false);
 			}
 		}
+		mptcp_update_dfrags(sk, &info);
 	}
 
 out:
@@ -1632,10 +1655,13 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 		if (first) {
 			ret = __subflow_push_pending(sk, ssk, &info);
 			first = false;
-			if (ret <= 0)
+			if (ret <= 0) {
+				mptcp_update_first_pending(sk, &info);
 				break;
+			}
 			copied += ret;
 			msk->last_snd = ssk;
+			mptcp_update_dfrags(sk, &info);
 			continue;
 		}
 
@@ -1656,6 +1682,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 
 				ret = __subflow_push_pending(sk, ssk, &info);
 				if (ret <= 0) {
+					mptcp_update_first_pending(sk, &info);
 					err = 1;
 					continue;
 				}
@@ -1664,6 +1691,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
 				mptcp_subflow_set_scheduled(subflow, false);
 			}
 		}
+		mptcp_update_dfrags(sk, &info);
 	}
 
 out:
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 8536035a71d0..cdce0c092c3c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -358,16 +358,23 @@ static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
 	return READ_ONCE(msk->first_pending);
 }
 
-static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
+static inline struct mptcp_data_frag *mptcp_next_frag(const struct sock *sk,
+						      struct mptcp_data_frag *cur)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct mptcp_data_frag *cur;
 
-	cur = msk->first_pending;
+	if (!cur)
+		return NULL;
+
 	return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
 						     list_next_entry(cur, list);
 }
 
+static inline struct mptcp_data_frag *mptcp_send_next(const struct sock *sk)
+{
+	return mptcp_next_frag(sk, mptcp_send_head(sk));
+}
+
 static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-- 
2.35.3