This patch adds the multiple subflows support for __mptcp_push_pending
and __mptcp_subflow_push_pending. Use get_send() wrapper instead of
mptcp_subflow_get_send() in them.
Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.
Move sock_owned_by_me() check and fallback check into get_send() wrapper
from mptcp_subflow_get_send().
This commit allows the scheduler to set the subflow->scheduled bit in
multiple subflows, but it does not allow for sending redundant data.
Multiple scheduled subflows will send sequential data on each subflow.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 117 ++++++++++++++++++++++++++-----------------
net/mptcp/sched.c | 13 +++++
2 files changed, 85 insertions(+), 45 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 14c69a519898..57967438e70f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1407,15 +1407,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
u64 linger_time;
long tout = 0;
- msk_owned_by_me(msk);
-
- if (__mptcp_check_fallback(msk)) {
- if (!msk->first)
- return NULL;
- return __tcp_can_send(msk->first) &&
- sk_stream_memory_free(msk->first) ? msk->first : NULL;
- }
-
/* pick the subflow with the lower wmem/wspace ratio */
for (i = 0; i < SSK_MODE_MAX; ++i) {
send_info[i].ssk = NULL;
@@ -1566,43 +1557,57 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
.flags = flags,
};
bool do_check_data_fin = false;
+ int push_count = 1;
- while (mptcp_send_head(sk)) {
+ while (mptcp_send_head(sk) && (push_count > 0)) {
+ struct mptcp_subflow_context *subflow;
int ret = 0;
- prev_ssk = ssk;
- ssk = mptcp_subflow_get_send(msk);
+ if (mptcp_sched_get_send(msk))
+ break;
- /* 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;
+ push_count = 0;
- /* 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);
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ mptcp_subflow_set_scheduled(subflow, false);
- ret = __subflow_push_pending(sk, ssk, &info);
- if (ret <= 0) {
- if (ret == -EAGAIN)
- continue;
- mptcp_push_release(ssk, &info);
- goto out;
+ prev_ssk = ssk;
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ if (ssk != prev_ssk) {
+ /* First check. If the ssk has changed since
+ * the last round, release prev_ssk
+ */
+ if (prev_ssk)
+ mptcp_push_release(prev_ssk, &info);
+
+ /* Need to lock the new subflow only if different
+ * from the previous one, otherwise we are still
+ * helding the relevant lock
+ */
+ lock_sock(ssk);
+ }
+
+ push_count++;
+
+ ret = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0) {
+ if (ret != -EAGAIN ||
+ (1 << ssk->sk_state) &
+ (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE))
+ push_count--;
+ continue;
+ }
+ do_check_data_fin = true;
+ msk->last_snd = ssk;
+ }
}
- do_check_data_fin = true;
}
/* at this point we held the socket lock for the last subflow we used */
if (ssk)
mptcp_push_release(ssk, &info);
-out:
/* ensure the rtx timer is running */
if (!mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
@@ -1616,30 +1621,52 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
struct mptcp_sendmsg_info info = {
.data_lock_held = true,
};
+ bool keep_pushing = true;
struct sock *xmit_ssk;
int copied = 0;
info.flags = 0;
- while (mptcp_send_head(sk)) {
+ while (mptcp_send_head(sk) && keep_pushing) {
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
int ret = 0;
/* check for a different subflow usage only after
* spooling the first chunk of data
*/
- xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
- if (!xmit_ssk)
- goto out;
- if (xmit_ssk != ssk) {
- mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
- MPTCP_DELEGATE_SEND);
+ if (first) {
+ mptcp_subflow_set_scheduled(subflow, false);
+ ret = __subflow_push_pending(sk, ssk, &info);
+ first = false;
+ if (ret <= 0)
+ break;
+ copied += ret;
+ msk->last_snd = ssk;
+ continue;
+ }
+
+ if (mptcp_sched_get_send(msk))
goto out;
+
+ if (READ_ONCE(subflow->scheduled)) {
+ mptcp_subflow_set_scheduled(subflow, false);
+ ret = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0)
+ keep_pushing = false;
+ copied += ret;
+ msk->last_snd = ssk;
}
- ret = __subflow_push_pending(sk, ssk, &info);
- first = false;
- if (ret <= 0)
- break;
- copied += ret;
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ xmit_ssk = mptcp_subflow_tcp_sock(subflow);
+ if (xmit_ssk != ssk) {
+ mptcp_subflow_delegate(subflow,
+ MPTCP_DELEGATE_SEND);
+ msk->last_snd = xmit_ssk;
+ keep_pushing = false;
+ }
+ }
+ }
}
out:
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index c4006f142f10..6428323d8c7f 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -118,6 +118,19 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
struct mptcp_subflow_context *subflow;
struct mptcp_sched_data data;
+ msk_owned_by_me(msk);
+
+ /* the following check is moved out of mptcp_subflow_get_send */
+ if (__mptcp_check_fallback(msk)) {
+ if (msk->first &&
+ __tcp_can_send(msk->first) &&
+ sk_stream_memory_free(msk->first)) {
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
+ return 0;
+ }
+ return -EINVAL;
+ }
+
mptcp_for_each_subflow(msk, subflow) {
if (READ_ONCE(subflow->scheduled))
return 0;
--
2.35.3On Thu, 15 Dec 2022, Geliang Tang wrote:
> This patch adds the multiple subflows support for __mptcp_push_pending
> and __mptcp_subflow_push_pending. Use get_send() wrapper instead of
> mptcp_subflow_get_send() in them.
>
> Check the subflow scheduled flags to test which subflow or subflows are
> picked by the scheduler, use them to send data.
>
> Move sock_owned_by_me() check and fallback check into get_send() wrapper
> from mptcp_subflow_get_send().
>
> This commit allows the scheduler to set the subflow->scheduled bit in
> multiple subflows, but it does not allow for sending redundant data.
> Multiple scheduled subflows will send sequential data on each subflow.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 117 ++++++++++++++++++++++++++-----------------
> net/mptcp/sched.c | 13 +++++
> 2 files changed, 85 insertions(+), 45 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 14c69a519898..57967438e70f 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1407,15 +1407,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
> u64 linger_time;
> long tout = 0;
>
> - msk_owned_by_me(msk);
> -
> - if (__mptcp_check_fallback(msk)) {
> - if (!msk->first)
> - return NULL;
> - return __tcp_can_send(msk->first) &&
> - sk_stream_memory_free(msk->first) ? msk->first : NULL;
> - }
> -
> /* pick the subflow with the lower wmem/wspace ratio */
> for (i = 0; i < SSK_MODE_MAX; ++i) {
> send_info[i].ssk = NULL;
> @@ -1566,43 +1557,57 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> .flags = flags,
> };
> bool do_check_data_fin = false;
> + int push_count = 1;
>
> - while (mptcp_send_head(sk)) {
> + while (mptcp_send_head(sk) && (push_count > 0)) {
> + struct mptcp_subflow_context *subflow;
> int ret = 0;
>
> - prev_ssk = ssk;
> - ssk = mptcp_subflow_get_send(msk);
> + if (mptcp_sched_get_send(msk))
> + break;
>
> - /* 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;
> + push_count = 0;
>
> - /* 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);
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + mptcp_subflow_set_scheduled(subflow, false);
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - if (ret <= 0) {
> - if (ret == -EAGAIN)
> - continue;
> - mptcp_push_release(ssk, &info);
> - goto out;
> + prev_ssk = ssk;
> + ssk = mptcp_subflow_tcp_sock(subflow);
> + if (ssk != prev_ssk) {
> + /* First check. If the ssk has changed since
> + * the last round, release prev_ssk
> + */
> + if (prev_ssk)
> + mptcp_push_release(prev_ssk, &info);
> +
> + /* Need to lock the new subflow only if different
> + * from the previous one, otherwise we are still
> + * helding the relevant lock
> + */
> + lock_sock(ssk);
> + }
> +
> + push_count++;
> +
> + ret = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0) {
> + if (ret != -EAGAIN ||
> + (1 << ssk->sk_state) &
> + (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE))
> + push_count--;
> + continue;
> + }
> + do_check_data_fin = true;
> + msk->last_snd = ssk;
> + }
> }
> - do_check_data_fin = true;
> }
>
> /* at this point we held the socket lock for the last subflow we used */
> if (ssk)
> mptcp_push_release(ssk, &info);
>
> -out:
> /* ensure the rtx timer is running */
> if (!mptcp_timer_pending(sk))
> mptcp_reset_timer(sk);
> @@ -1616,30 +1621,52 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
> struct mptcp_sendmsg_info info = {
> .data_lock_held = true,
> };
> + bool keep_pushing = true;
> struct sock *xmit_ssk;
> int copied = 0;
>
> info.flags = 0;
> - while (mptcp_send_head(sk)) {
> + while (mptcp_send_head(sk) && keep_pushing) {
> + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
> int ret = 0;
>
> /* check for a different subflow usage only after
> * spooling the first chunk of data
> */
> - xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk);
> - if (!xmit_ssk)
> - goto out;
> - if (xmit_ssk != ssk) {
> - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
> - MPTCP_DELEGATE_SEND);
> + if (first) {
> + mptcp_subflow_set_scheduled(subflow, false);
> + ret = __subflow_push_pending(sk, ssk, &info);
> + first = false;
> + if (ret <= 0)
> + break;
> + copied += ret;
> + msk->last_snd = ssk;
> + continue;
> + }
> +
> + if (mptcp_sched_get_send(msk))
> goto out;
> +
> + if (READ_ONCE(subflow->scheduled)) {
> + mptcp_subflow_set_scheduled(subflow, false);
> + ret = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0)
> + keep_pushing = false;
> + copied += ret;
> + msk->last_snd = ssk;
> }
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - first = false;
> - if (ret <= 0)
> - break;
> - copied += ret;
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + xmit_ssk = mptcp_subflow_tcp_sock(subflow);
> + if (xmit_ssk != ssk) {
> + mptcp_subflow_delegate(subflow,
> + MPTCP_DELEGATE_SEND);
> + msk->last_snd = xmit_ssk;
Hi Geliang/Matthieu -
Following up to my earlier replay about this series, this is the line to
delete (the assignment to msk->last_snd).
Similar to the removal of subflow_set_scheduled(subflow, false) in this
block of code, the subflow hasn't been used to send yet so last_snd
shouldn't be updated. It will get changed when __subflow_push_pending() is
called later.
- Mat
> + keep_pushing = false;
> + }
> + }
> + }
> }
>
> out:
> diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
> index c4006f142f10..6428323d8c7f 100644
> --- a/net/mptcp/sched.c
> +++ b/net/mptcp/sched.c
> @@ -118,6 +118,19 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
> struct mptcp_subflow_context *subflow;
> struct mptcp_sched_data data;
>
> + msk_owned_by_me(msk);
> +
> + /* the following check is moved out of mptcp_subflow_get_send */
> + if (__mptcp_check_fallback(msk)) {
> + if (msk->first &&
> + __tcp_can_send(msk->first) &&
> + sk_stream_memory_free(msk->first)) {
> + mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
> + return 0;
> + }
> + return -EINVAL;
> + }
> +
> mptcp_for_each_subflow(msk, subflow) {
> if (READ_ONCE(subflow->scheduled))
> return 0;
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
© 2016 - 2024 Red Hat, Inc.