* [PATCH mptcp-next v22 1/5] mptcp: add scheduler wrappers
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
@ 2022-12-02 13:30 ` Geliang Tang
2022-12-02 13:30 ` [PATCH mptcp-next v22 2/5] mptcp: use get_send wrapper Geliang Tang
` (4 subsequent siblings)
5 siblings, 0 replies; 10+ messages in thread
From: Geliang Tang @ 2022-12-02 13:30 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch defines two packet scheduler wrappers mptcp_sched_get_send()
and mptcp_sched_get_retrans(), invoke data_init() and get_subflow() of
msk->sched in them.
Set data->reinject to true in mptcp_sched_get_retrans(), set it false in
mptcp_sched_get_send().
If msk->sched is NULL, use default functions mptcp_subflow_get_send()
and mptcp_subflow_get_retrans() to send data.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 4 ++--
net/mptcp/protocol.h | 4 ++++
net/mptcp/sched.c | 50 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 56 insertions(+), 2 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 99f5e51d5ca4..d8ad68dd504a 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1397,7 +1397,7 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
* returns the subflow that will transmit the next DSS
* additionally updates the rtx timeout
*/
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
{
struct subflow_send_info send_info[SSK_MODE_MAX];
struct mptcp_subflow_context *subflow;
@@ -2213,7 +2213,7 @@ static void mptcp_timeout_timer(struct timer_list *t)
*
* A backup subflow is returned only if that is the only kind available.
*/
-static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
{
struct sock *backup = NULL, *pick = NULL;
struct mptcp_subflow_context *subflow;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 224f03a899c5..adfb758a842f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -657,6 +657,10 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
bool scheduled);
void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
struct mptcp_sched_data *data);
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
+struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk);
+int mptcp_sched_get_send(struct mptcp_sock *msk);
+int mptcp_sched_get_retrans(struct mptcp_sock *msk);
static inline bool __tcp_can_send(const struct sock *ssk)
{
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 0d7c73e9562e..c4006f142f10 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -112,3 +112,53 @@ void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
for (; i < MPTCP_SUBFLOWS_MAX; i++)
data->contexts[i] = NULL;
}
+
+int mptcp_sched_get_send(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sched_data data;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ return 0;
+ }
+
+ if (!msk->sched) {
+ struct sock *ssk;
+
+ ssk = mptcp_subflow_get_send(msk);
+ if (!ssk)
+ return -EINVAL;
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+ return 0;
+ }
+
+ data.reinject = false;
+ msk->sched->data_init(msk, &data);
+ return msk->sched->get_subflow(msk, &data);
+}
+
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sched_data data;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ return 0;
+ }
+
+ if (!msk->sched) {
+ struct sock *ssk;
+
+ ssk = mptcp_subflow_get_retrans(msk);
+ if (!ssk)
+ return -EINVAL;
+ mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+ return 0;
+ }
+
+ data.reinject = true;
+ msk->sched->data_init(msk, &data);
+ return msk->sched->get_subflow(msk, &data);
+}
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH mptcp-next v22 2/5] mptcp: use get_send wrapper
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
2022-12-02 13:30 ` [PATCH mptcp-next v22 1/5] mptcp: add scheduler wrappers Geliang Tang
@ 2022-12-02 13:30 ` Geliang Tang
2022-12-06 1:09 ` Mat Martineau
2022-12-02 13:30 ` [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper Geliang Tang
` (3 subsequent siblings)
5 siblings, 1 reply; 10+ messages in thread
From: Geliang Tang @ 2022-12-02 13:30 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
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 | 129 +++++++++++++++++++++++++++----------------
net/mptcp/sched.c | 13 +++++
2 files changed, 95 insertions(+), 47 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d8ad68dd504a..cef6086c7f40 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1408,15 +1408,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
u64 linger_time;
long tout = 0;
- sock_owned_by_me(sk);
-
- 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;
@@ -1563,47 +1554,61 @@ 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_sendmsg_info info = {
.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)) {
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)) {
+ prev_ssk = ssk;
+ ssk = mptcp_subflow_tcp_sock(subflow);
- ret = __subflow_push_pending(sk, ssk, &info);
- if (ret <= 0) {
- if (ret == -EAGAIN)
- continue;
- mptcp_push_release(ssk, &info);
- goto out;
+ 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;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
}
- 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);
@@ -1614,33 +1619,63 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sendmsg_info info = {
.data_lock_held = true,
};
- struct sock *xmit_ssk;
+ bool push = true;
int copied = 0;
info.flags = 0;
- while (mptcp_send_head(sk)) {
+ while (mptcp_send_head(sk) && push) {
+ bool delegate = false;
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);
- goto out;
+ if (first) {
+ ret = __subflow_push_pending(sk, ssk, &info);
+ first = false;
+ if (ret <= 0)
+ break;
+ copied += ret;
+ msk->last_snd = ssk;
+ continue;
}
- ret = __subflow_push_pending(sk, ssk, &info);
- first = false;
- if (ret <= 0)
- break;
- copied += ret;
+ if (mptcp_sched_get_send(msk))
+ goto out;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ struct sock *xmit_ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (xmit_ssk != ssk) {
+ /* Only delegate to one subflow recently,
+ * TODO: chain delegated calls for more subflows.
+ */
+ if (delegate)
+ goto out;
+ mptcp_subflow_delegate(subflow,
+ MPTCP_DELEGATE_SEND);
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ delegate = true;
+ push = false;
+ continue;
+ }
+
+ ret = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0) {
+ push = false;
+ continue;
+ }
+ copied += ret;
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
+ }
}
out:
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index c4006f142f10..18518a81afb3 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;
+ sock_owned_by_me((const struct sock *)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
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH mptcp-next v22 2/5] mptcp: use get_send wrapper
2022-12-02 13:30 ` [PATCH mptcp-next v22 2/5] mptcp: use get_send wrapper Geliang Tang
@ 2022-12-06 1:09 ` Mat Martineau
0 siblings, 0 replies; 10+ messages in thread
From: Mat Martineau @ 2022-12-06 1:09 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Fri, 2 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 | 129 +++++++++++++++++++++++++++----------------
> net/mptcp/sched.c | 13 +++++
> 2 files changed, 95 insertions(+), 47 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index d8ad68dd504a..cef6086c7f40 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1408,15 +1408,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
> u64 linger_time;
> long tout = 0;
>
> - sock_owned_by_me(sk);
> -
> - 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;
> @@ -1563,47 +1554,61 @@ 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_sendmsg_info info = {
> .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)) {
Hi Geliang -
Thanks, this is the correct logic (I had a typo in my suggested code for
this).
> 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)) {
> + prev_ssk = ssk;
> + ssk = mptcp_subflow_tcp_sock(subflow);
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - if (ret <= 0) {
> - if (ret == -EAGAIN)
> - continue;
> - mptcp_push_release(ssk, &info);
> - goto out;
> + 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;
> + mptcp_subflow_set_scheduled(subflow, false);
I missed this before: the subflow->scheduled flag should be cleared on the
error path too. If it's only cleared on success there could be problems
with the __mptcp_subflow_push_pending() code path in later patches.
- Mat
> + }
> }
> - 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);
> @@ -1614,33 +1619,63 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
> {
> struct mptcp_sock *msk = mptcp_sk(sk);
> + struct mptcp_subflow_context *subflow;
> struct mptcp_sendmsg_info info = {
> .data_lock_held = true,
> };
> - struct sock *xmit_ssk;
> + bool push = true;
> int copied = 0;
>
> info.flags = 0;
> - while (mptcp_send_head(sk)) {
> + while (mptcp_send_head(sk) && push) {
> + bool delegate = false;
> 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);
> - goto out;
> + if (first) {
> + ret = __subflow_push_pending(sk, ssk, &info);
> + first = false;
> + if (ret <= 0)
> + break;
> + copied += ret;
> + msk->last_snd = ssk;
> + continue;
> }
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - first = false;
> - if (ret <= 0)
> - break;
> - copied += ret;
> + if (mptcp_sched_get_send(msk))
> + goto out;
> +
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + struct sock *xmit_ssk = mptcp_subflow_tcp_sock(subflow);
> +
> + if (xmit_ssk != ssk) {
> + /* Only delegate to one subflow recently,
> + * TODO: chain delegated calls for more subflows.
> + */
> + if (delegate)
> + goto out;
> + mptcp_subflow_delegate(subflow,
> + MPTCP_DELEGATE_SEND);
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
> + delegate = true;
> + push = false;
> + continue;
> + }
> +
> + ret = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0) {
> + push = false;
> + continue;
> + }
> + copied += ret;
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
> + }
> + }
> }
>
> out:
> diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
> index c4006f142f10..18518a81afb3 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;
>
> + sock_owned_by_me((const struct sock *)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
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
2022-12-02 13:30 ` [PATCH mptcp-next v22 1/5] mptcp: add scheduler wrappers Geliang Tang
2022-12-02 13:30 ` [PATCH mptcp-next v22 2/5] mptcp: use get_send wrapper Geliang Tang
@ 2022-12-02 13:30 ` Geliang Tang
2022-12-06 1:10 ` Mat Martineau
2022-12-02 13:30 ` [PATCH mptcp-next v22 4/5] selftests/bpf: Add bpf_red scheduler Geliang Tang
` (2 subsequent siblings)
5 siblings, 1 reply; 10+ messages in thread
From: Geliang Tang @ 2022-12-02 13:30 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch adds the multiple subflows support for __mptcp_retrans(). Use
get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.
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_retrans()
wrapper from mptcp_subflow_get_retrans().
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 67 ++++++++++++++++++++++++++------------------
net/mptcp/sched.c | 6 ++++
2 files changed, 45 insertions(+), 28 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index cef6086c7f40..7d7048b0774f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2254,11 +2254,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
struct mptcp_subflow_context *subflow;
int min_stale_count = INT_MAX;
- sock_owned_by_me((const struct sock *)msk);
-
- if (__mptcp_check_fallback(msk))
- return NULL;
-
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -2528,16 +2523,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
static void __mptcp_retrans(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sendmsg_info info = {};
struct mptcp_data_frag *dfrag;
- size_t copied = 0;
struct sock *ssk;
- int ret;
+ int ret, err;
+ u16 len = 0;
mptcp_clean_una_wakeup(sk);
/* first check ssk: need to kick "stale" logic */
- ssk = mptcp_subflow_get_retrans(msk);
+ err = mptcp_sched_get_retrans(msk);
dfrag = mptcp_rtx_head(sk);
if (!dfrag) {
if (mptcp_data_fin_enabled(msk)) {
@@ -2556,31 +2552,46 @@ static void __mptcp_retrans(struct sock *sk)
goto reset_timer;
}
- if (!ssk)
+ if (err)
goto reset_timer;
- lock_sock(ssk);
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ u16 copied = 0;
- /* limit retransmission to the bytes already sent on some subflows */
- info.sent = 0;
- info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
- while (info.sent < info.limit) {
- ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
- if (ret <= 0)
- break;
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ if (!ssk)
+ goto reset_timer;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
- copied += ret;
- info.sent += ret;
- }
- if (copied) {
- dfrag->already_sent = max(dfrag->already_sent, info.sent);
- tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
- info.size_goal);
- WRITE_ONCE(msk->allow_infinite_fallback, false);
- }
+ lock_sock(ssk);
- release_sock(ssk);
+ /* limit retransmission to the bytes already sent on some subflows */
+ info.sent = 0;
+ info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
+ dfrag->already_sent;
+ while (info.sent < info.limit) {
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0)
+ break;
+
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+ copied += ret;
+ info.sent += ret;
+ }
+ if (copied) {
+ len = max(copied, len);
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
+ WRITE_ONCE(msk->allow_infinite_fallback, false);
+ }
+
+ release_sock(ssk);
+
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
+ }
+ dfrag->already_sent = max(dfrag->already_sent, len);
reset_timer:
mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 18518a81afb3..c55f2f1cb7ac 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -156,6 +156,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
struct mptcp_subflow_context *subflow;
struct mptcp_sched_data data;
+ sock_owned_by_me((const struct sock *)msk);
+
+ /* the following check is moved out of mptcp_subflow_get_retrans */
+ if (__mptcp_check_fallback(msk))
+ return -EINVAL;
+
mptcp_for_each_subflow(msk, subflow) {
if (READ_ONCE(subflow->scheduled))
return 0;
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper
2022-12-02 13:30 ` [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper Geliang Tang
@ 2022-12-06 1:10 ` Mat Martineau
0 siblings, 0 replies; 10+ messages in thread
From: Mat Martineau @ 2022-12-06 1:10 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Fri, 2 Dec 2022, Geliang Tang wrote:
> This patch adds the multiple subflows support for __mptcp_retrans(). Use
> get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.
>
> 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_retrans()
> wrapper from mptcp_subflow_get_retrans().
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 67 ++++++++++++++++++++++++++------------------
> net/mptcp/sched.c | 6 ++++
> 2 files changed, 45 insertions(+), 28 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index cef6086c7f40..7d7048b0774f 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -2254,11 +2254,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
> struct mptcp_subflow_context *subflow;
> int min_stale_count = INT_MAX;
>
> - sock_owned_by_me((const struct sock *)msk);
> -
> - if (__mptcp_check_fallback(msk))
> - return NULL;
> -
> mptcp_for_each_subflow(msk, subflow) {
> struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
>
> @@ -2528,16 +2523,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
> static void __mptcp_retrans(struct sock *sk)
> {
> struct mptcp_sock *msk = mptcp_sk(sk);
> + struct mptcp_subflow_context *subflow;
> struct mptcp_sendmsg_info info = {};
> struct mptcp_data_frag *dfrag;
> - size_t copied = 0;
> struct sock *ssk;
> - int ret;
> + int ret, err;
> + u16 len = 0;
>
> mptcp_clean_una_wakeup(sk);
>
> /* first check ssk: need to kick "stale" logic */
> - ssk = mptcp_subflow_get_retrans(msk);
> + err = mptcp_sched_get_retrans(msk);
> dfrag = mptcp_rtx_head(sk);
> if (!dfrag) {
> if (mptcp_data_fin_enabled(msk)) {
> @@ -2556,31 +2552,46 @@ static void __mptcp_retrans(struct sock *sk)
> goto reset_timer;
> }
>
> - if (!ssk)
> + if (err)
> goto reset_timer;
>
> - lock_sock(ssk);
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + u16 copied = 0;
>
> - /* limit retransmission to the bytes already sent on some subflows */
> - info.sent = 0;
> - info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
> - while (info.sent < info.limit) {
> - ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> - if (ret <= 0)
> - break;
> + ssk = mptcp_subflow_tcp_sock(subflow);
> + if (!ssk)
> + goto reset_timer;
>
> - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
> - copied += ret;
> - info.sent += ret;
> - }
> - if (copied) {
> - dfrag->already_sent = max(dfrag->already_sent, info.sent);
> - tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> - info.size_goal);
> - WRITE_ONCE(msk->allow_infinite_fallback, false);
> - }
> + lock_sock(ssk);
>
> - release_sock(ssk);
> + /* limit retransmission to the bytes already sent on some subflows */
> + info.sent = 0;
> + info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
> + dfrag->already_sent;
> + while (info.sent < info.limit) {
> + ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> + if (ret <= 0)
> + break;
> +
> + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
> + copied += ret;
> + info.sent += ret;
> + }
> + if (copied) {
> + len = max(copied, len);
> + tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> + info.size_goal);
> + WRITE_ONCE(msk->allow_infinite_fallback, false);
> + }
> +
> + release_sock(ssk);
> +
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
Like patch 2, the scheduled bit should always be cleared (on success and
on error).
- Mat
> + }
> + }
> + dfrag->already_sent = max(dfrag->already_sent, len);
>
> reset_timer:
> mptcp_check_and_set_pending(sk);
> diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
> index 18518a81afb3..c55f2f1cb7ac 100644
> --- a/net/mptcp/sched.c
> +++ b/net/mptcp/sched.c
> @@ -156,6 +156,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
> struct mptcp_subflow_context *subflow;
> struct mptcp_sched_data data;
>
> + sock_owned_by_me((const struct sock *)msk);
> +
> + /* the following check is moved out of mptcp_subflow_get_retrans */
> + if (__mptcp_check_fallback(msk))
> + return -EINVAL;
> +
> mptcp_for_each_subflow(msk, subflow) {
> if (READ_ONCE(subflow->scheduled))
> return 0;
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH mptcp-next v22 4/5] selftests/bpf: Add bpf_red scheduler
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
` (2 preceding siblings ...)
2022-12-02 13:30 ` [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper Geliang Tang
@ 2022-12-02 13:30 ` Geliang Tang
2022-12-02 13:30 ` [PATCH mptcp-next v22 5/5] selftests/bpf: Add bpf_red test Geliang Tang
2022-12-06 1:13 ` [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Mat Martineau
5 siblings, 0 replies; 10+ messages in thread
From: Geliang Tang @ 2022-12-02 13:30 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch implements the redundant BPF MPTCP scheduler, named bpf_red,
which sends all packets redundantly on all available subflows.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
.../selftests/bpf/progs/mptcp_bpf_red.c | 45 +++++++++++++++++++
1 file changed, 45 insertions(+)
create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
new file mode 100644
index 000000000000..30dd6f521b7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/mptcp_sched_red_init")
+void BPF_PROG(mptcp_sched_red_init, const struct mptcp_sock *msk)
+{
+}
+
+SEC("struct_ops/mptcp_sched_red_release")
+void BPF_PROG(mptcp_sched_red_release, const struct mptcp_sock *msk)
+{
+}
+
+void BPF_STRUCT_OPS(bpf_red_data_init, const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
+{
+ mptcp_sched_data_set_contexts(msk, data);
+}
+
+int BPF_STRUCT_OPS(bpf_red_get_subflow, const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
+{
+ for (int i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
+ if (!data->contexts[i])
+ break;
+
+ mptcp_subflow_set_scheduled(data->contexts[i], true);
+ }
+
+ return 0;
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops red = {
+ .init = (void *)mptcp_sched_red_init,
+ .release = (void *)mptcp_sched_red_release,
+ .data_init = (void *)bpf_red_data_init,
+ .get_subflow = (void *)bpf_red_get_subflow,
+ .name = "bpf_red",
+};
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH mptcp-next v22 5/5] selftests/bpf: Add bpf_red test
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
` (3 preceding siblings ...)
2022-12-02 13:30 ` [PATCH mptcp-next v22 4/5] selftests/bpf: Add bpf_red scheduler Geliang Tang
@ 2022-12-02 13:30 ` Geliang Tang
2022-12-02 14:36 ` selftests/bpf: Add bpf_red test: Tests Results MPTCP CI
2022-12-06 1:13 ` [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Mat Martineau
5 siblings, 1 reply; 10+ messages in thread
From: Geliang Tang @ 2022-12-02 13:30 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch adds the redundant BPF MPTCP scheduler test: test_red(). Use
sysctl to set net.mptcp.scheduler to use this sched. Add two veth net
devices to simulate the multiple addresses case. Use 'ip mptcp endpoint'
command to add the new endpoint ADDR_2 to PM netlink. Send data and check
bytes_sent of 'ss' output after it to make sure the data has been
redundantly sent on both net devices.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
.../testing/selftests/bpf/prog_tests/mptcp.c | 34 +++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 647d313475bc..8426a5aba721 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -9,6 +9,7 @@
#include "mptcp_bpf_first.skel.h"
#include "mptcp_bpf_bkup.skel.h"
#include "mptcp_bpf_rr.skel.h"
+#include "mptcp_bpf_red.skel.h"
#ifndef TCP_CA_NAME_MAX
#define TCP_CA_NAME_MAX 16
@@ -381,6 +382,37 @@ static void test_rr(void)
mptcp_bpf_rr__destroy(rr_skel);
}
+static void test_red(void)
+{
+ struct mptcp_bpf_red *red_skel;
+ int server_fd, client_fd;
+ struct bpf_link *link;
+
+ red_skel = mptcp_bpf_red__open_and_load();
+ if (!ASSERT_OK_PTR(red_skel, "bpf_red__open_and_load"))
+ return;
+
+ link = bpf_map__attach_struct_ops(red_skel->maps.red);
+ if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
+ mptcp_bpf_red__destroy(red_skel);
+ return;
+ }
+
+ sched_init("subflow", "bpf_red");
+ server_fd = start_mptcp_server(AF_INET, ADDR_1, 0, 0);
+ client_fd = connect_to_fd(server_fd, 0);
+
+ send_data(server_fd, client_fd);
+ ASSERT_OK(has_bytes_sent(ADDR_1), "has_bytes_sent addr 1");
+ ASSERT_OK(has_bytes_sent(ADDR_2), "has_bytes_sent addr 2");
+
+ close(client_fd);
+ close(server_fd);
+ sched_cleanup();
+ bpf_link__destroy(link);
+ mptcp_bpf_red__destroy(red_skel);
+}
+
void test_mptcp(void)
{
if (test__start_subtest("base"))
@@ -391,4 +423,6 @@ void test_mptcp(void)
test_bkup();
if (test__start_subtest("rr"))
test_rr();
+ if (test__start_subtest("red"))
+ test_red();
}
--
2.35.3
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2
2022-12-02 13:30 [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2 Geliang Tang
` (4 preceding siblings ...)
2022-12-02 13:30 ` [PATCH mptcp-next v22 5/5] selftests/bpf: Add bpf_red test Geliang Tang
@ 2022-12-06 1:13 ` Mat Martineau
5 siblings, 0 replies; 10+ messages in thread
From: Mat Martineau @ 2022-12-06 1:13 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Fri, 2 Dec 2022, Geliang Tang wrote:
> v22:
> - update patch 2 as Mat suggested.
> - patch 4 and 5 in v21 will send later.
Ok, thanks for the note on v21 patches 4/5. My only other comments on v22
are on patches 2 & 3 (already replied on those).
- Mat
>
> v21:
> - address Mat's comments in v20.
> - redundant sends on retransmit code path.
>
> v20:
> - rebased on "Squash to "mptcp: refactor push_pending logic" v19"
>
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 10+ messages in thread