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 | 50 ++++++++++++++++++--------------------------
1 file changed, 20 insertions(+), 30 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7ca21915b3d1..37a252a3f05b 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;
@@ -1530,15 +1522,21 @@ 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;
+ ssk = mptcp_sched_get_send(msk);
+ if (!ssk)
+ goto out;
+
+ lock_sock(ssk);
+
while ((dfrag = mptcp_send_head(sk))) {
info.sent = dfrag->already_sent;
info.limit = dfrag->data_len;
@@ -1546,24 +1544,6 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
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);
-
ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
if (ret <= 0) {
if (ret == -EAGAIN)
@@ -1579,11 +1559,21 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
mptcp_update_post_push(msk, dfrag, ret);
}
WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+
+ if (msk->snd_burst > 0 &&
+ sk_stream_memory_free(ssk) &&
+ mptcp_subflow_active(mptcp_subflow_ctx(ssk))) {
+ mptcp_set_timeout(sk);
+ } else {
+ break;
+ }
}
- /* at this point we held the socket lock for the last subflow we used */
- if (ssk)
- mptcp_push_release(ssk, &info);
+ if (do_check_data_fin) {
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
+ }
+ release_sock(ssk);
out:
/* ensure the rtx timer is running */
--
2.35.3On Thu, 29 Sep 2022, Geliang Tang wrote:
> 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 | 50 ++++++++++++++++++--------------------------
> 1 file changed, 20 insertions(+), 30 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 7ca21915b3d1..37a252a3f05b 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;
> - }
> -
With msk->last_snd not used here any more, it seems like it can be
removed.
> /* pick the subflow with the lower wmem/wspace ratio */
> for (i = 0; i < SSK_MODE_MAX; ++i) {
> send_info[i].ssk = NULL;
> @@ -1530,15 +1522,21 @@ 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;
>
> + ssk = mptcp_sched_get_send(msk);
> + if (!ssk)
> + goto out;
> +
> + lock_sock(ssk);
> +
> while ((dfrag = mptcp_send_head(sk))) {
> info.sent = dfrag->already_sent;
> info.limit = dfrag->data_len;
> @@ -1546,24 +1544,6 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> 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);
> -
> ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> if (ret <= 0) {
> if (ret == -EAGAIN)
> @@ -1579,11 +1559,21 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> mptcp_update_post_push(msk, dfrag, ret);
> }
> WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
> +
> + if (msk->snd_burst > 0 &&
> + sk_stream_memory_free(ssk) &&
> + mptcp_subflow_active(mptcp_subflow_ctx(ssk))) {
> + mptcp_set_timeout(sk);
> + } else {
> + break;
> + }
> }
>
> - /* at this point we held the socket lock for the last subflow we used */
> - if (ssk)
> - mptcp_push_release(ssk, &info);
> + if (do_check_data_fin) {
> + tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> + info.size_goal);
> + }
> + release_sock(ssk);
>
> out:
> /* ensure the rtx timer is running */
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
© 2016 - 2026 Red Hat, Inc.