* [PATCH mptcp-next v18 01/15] mptcp: refactor push_pending logic
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-11 0:11 ` Mat Martineau
2022-11-08 9:08 ` [PATCH mptcp-next v18 02/15] mptcp: drop last_snd and MPTCP_RESET_SCHEDULER Geliang Tang
` (13 subsequent siblings)
14 siblings, 1 reply; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
To support redundant package schedulers more easily, this patch refactors
__mptcp_push_pending() logic from:
For each dfrag:
While sends succeed:
Call the scheduler (selects subflow and msk->snd_burst)
Update subflow locks (push/release/acquire as needed)
Send the dfrag data with mptcp_sendmsg_frag()
Update already_sent, snd_nxt, snd_burst
Update msk->first_pending
Push/release on final subflow
->
While first_pending isn't empty:
Call the scheduler (selects subflow and msk->snd_burst)
Update subflow locks (push/release/acquire as needed)
For each pending dfrag:
While sends succeed:
Send the dfrag data with mptcp_sendmsg_frag()
Update already_sent, snd_nxt, snd_burst
Update msk->first_pending
Break if required by msk->snd_burst / etc
Push/release on final subflow
Refactors __mptcp_subflow_push_pending logic from:
For each dfrag:
While sends succeed:
Call the scheduler (selects subflow and msk->snd_burst)
Send the dfrag data with mptcp_subflow_delegate(), break
Send the dfrag data with mptcp_sendmsg_frag()
Update dfrag->already_sent, msk->snd_nxt, msk->snd_burst
Update msk->first_pending
->
While first_pending isn't empty:
Call the scheduler (selects subflow and msk->snd_burst)
Send the dfrag data with mptcp_subflow_delegate(), break
Send the dfrag data with mptcp_sendmsg_frag()
For each pending dfrag:
While sends succeed:
Send the dfrag data with mptcp_sendmsg_frag()
Update already_sent, snd_nxt, snd_burst
Update msk->first_pending
Break if required by msk->snd_burst / etc
Move the duplicate code from __mptcp_push_pending() and
__mptcp_subflow_push_pending() into a new helper function, named
__subflow_push_pending(). Simplify __mptcp_push_pending() and
__mptcp_subflow_push_pending() by invoking this helper.
Also move the burst check conditions out of the function
mptcp_subflow_get_send(), check them in __subflow_push_pending() in
the inner "for each pending dfrag" loop.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 155 +++++++++++++++++++++++--------------------
1 file changed, 82 insertions(+), 73 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ede644556b20..1fb3b46fa427 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1426,14 +1426,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
sk_stream_memory_free(msk->first) ? msk->first : NULL;
}
- /* 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;
@@ -1537,57 +1529,86 @@ void mptcp_check_and_set_pending(struct sock *sk)
mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
}
-void __mptcp_push_pending(struct sock *sk, unsigned int flags)
+static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
+ struct mptcp_sendmsg_info *info)
{
- 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;
- int len;
+ int len, copied = 0, err = 0;
while ((dfrag = mptcp_send_head(sk))) {
- info.sent = dfrag->already_sent;
- info.limit = dfrag->data_len;
+ info->sent = dfrag->already_sent;
+ info->limit = dfrag->data_len;
len = dfrag->data_len - dfrag->already_sent;
while (len > 0) {
int ret = 0;
- prev_ssk = ssk;
- ssk = mptcp_subflow_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);
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info);
if (ret <= 0) {
- if (ret == -EAGAIN)
- continue;
- mptcp_push_release(ssk, &info);
+ err = copied ? : ret;
goto out;
}
- do_check_data_fin = true;
- info.sent += ret;
+ info->sent += ret;
+ copied += ret;
len -= ret;
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))) {
+ err = copied ? : -EAGAIN;
+ goto out;
+ }
+ mptcp_set_timeout(sk);
+ }
+ err = copied;
+
+out:
+ return err;
+}
+
+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;
+
+ while (mptcp_send_head(sk)) {
+ int ret = 0;
+
+ prev_ssk = ssk;
+ ssk = mptcp_subflow_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 = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0) {
+ if (ret == -EAGAIN)
+ continue;
+ mptcp_push_release(ssk, &info);
+ goto out;
+ }
+ do_check_data_fin = true;
}
/* at this point we held the socket lock for the last subflow we used */
@@ -1608,49 +1629,37 @@ 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 *dfrag;
struct sock *xmit_ssk;
- int len, copied = 0;
+ int ret = 0;
info.flags = 0;
- while ((dfrag = mptcp_send_head(sk))) {
- info.sent = dfrag->already_sent;
- info.limit = dfrag->data_len;
- len = dfrag->data_len - dfrag->already_sent;
- while (len > 0) {
- 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;
- }
-
- ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
- if (ret <= 0)
- goto out;
-
- info.sent += ret;
- copied += ret;
- len -= ret;
- first = false;
+ while (mptcp_send_head(sk)) {
+ /* 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;
+ }
- mptcp_update_post_push(msk, dfrag, ret);
+ ret = __subflow_push_pending(sk, ssk, &info);
+ first = false;
+ if (ret <= 0) {
+ if (ret == -EAGAIN)
+ continue;
+ break;
}
- WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
}
out:
/* __mptcp_alloc_tx_skb could have released some wmem and we are
* not going to flush it via release_sock()
*/
- if (copied) {
+ if (ret) {
tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
info.size_goal);
if (!mptcp_timer_pending(sk))
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH mptcp-next v18 01/15] mptcp: refactor push_pending logic
2022-11-08 9:08 ` [PATCH mptcp-next v18 01/15] mptcp: refactor push_pending logic Geliang Tang
@ 2022-11-11 0:11 ` Mat Martineau
0 siblings, 0 replies; 21+ messages in thread
From: Mat Martineau @ 2022-11-11 0:11 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Tue, 8 Nov 2022, Geliang Tang wrote:
> To support redundant package schedulers more easily, this patch refactors
> __mptcp_push_pending() logic from:
>
> For each dfrag:
> While sends succeed:
> Call the scheduler (selects subflow and msk->snd_burst)
> Update subflow locks (push/release/acquire as needed)
> Send the dfrag data with mptcp_sendmsg_frag()
> Update already_sent, snd_nxt, snd_burst
> Update msk->first_pending
> Push/release on final subflow
>
> ->
>
> While first_pending isn't empty:
> Call the scheduler (selects subflow and msk->snd_burst)
> Update subflow locks (push/release/acquire as needed)
> For each pending dfrag:
> While sends succeed:
> Send the dfrag data with mptcp_sendmsg_frag()
> Update already_sent, snd_nxt, snd_burst
> Update msk->first_pending
> Break if required by msk->snd_burst / etc
> Push/release on final subflow
>
> Refactors __mptcp_subflow_push_pending logic from:
>
> For each dfrag:
> While sends succeed:
> Call the scheduler (selects subflow and msk->snd_burst)
> Send the dfrag data with mptcp_subflow_delegate(), break
> Send the dfrag data with mptcp_sendmsg_frag()
> Update dfrag->already_sent, msk->snd_nxt, msk->snd_burst
> Update msk->first_pending
>
> ->
>
> While first_pending isn't empty:
> Call the scheduler (selects subflow and msk->snd_burst)
> Send the dfrag data with mptcp_subflow_delegate(), break
> Send the dfrag data with mptcp_sendmsg_frag()
> For each pending dfrag:
> While sends succeed:
> Send the dfrag data with mptcp_sendmsg_frag()
> Update already_sent, snd_nxt, snd_burst
> Update msk->first_pending
> Break if required by msk->snd_burst / etc
>
> Move the duplicate code from __mptcp_push_pending() and
> __mptcp_subflow_push_pending() into a new helper function, named
> __subflow_push_pending(). Simplify __mptcp_push_pending() and
> __mptcp_subflow_push_pending() by invoking this helper.
>
> Also move the burst check conditions out of the function
> mptcp_subflow_get_send(), check them in __subflow_push_pending() in
> the inner "for each pending dfrag" loop.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 155 +++++++++++++++++++++++--------------------
> 1 file changed, 82 insertions(+), 73 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index ede644556b20..1fb3b46fa427 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1426,14 +1426,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
> sk_stream_memory_free(msk->first) ? msk->first : NULL;
> }
>
> - /* 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;
> @@ -1537,57 +1529,86 @@ void mptcp_check_and_set_pending(struct sock *sk)
> mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
> }
>
> -void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> +static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
> + struct mptcp_sendmsg_info *info)
> {
> - 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;
> - int len;
> + int len, copied = 0, err = 0;
>
> while ((dfrag = mptcp_send_head(sk))) {
> - info.sent = dfrag->already_sent;
> - info.limit = dfrag->data_len;
> + info->sent = dfrag->already_sent;
> + info->limit = dfrag->data_len;
> len = dfrag->data_len - dfrag->already_sent;
> while (len > 0) {
> int ret = 0;
>
> - prev_ssk = ssk;
> - ssk = mptcp_subflow_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);
> + ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info);
> if (ret <= 0) {
> - if (ret == -EAGAIN)
> - continue;
> - mptcp_push_release(ssk, &info);
> + err = copied ? : ret;
> goto out;
> }
>
> - do_check_data_fin = true;
> - info.sent += ret;
> + info->sent += ret;
> + copied += ret;
> len -= ret;
>
> 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))) {
> + err = copied ? : -EAGAIN;
> + goto out;
> + }
> + mptcp_set_timeout(sk);
> + }
> + err = copied;
> +
> +out:
> + return err;
> +}
> +
> +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;
> +
> + while (mptcp_send_head(sk)) {
> + int ret = 0;
> +
> + prev_ssk = ssk;
> + ssk = mptcp_subflow_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 = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0) {
> + if (ret == -EAGAIN)
> + continue;
> + mptcp_push_release(ssk, &info);
> + goto out;
> + }
> + do_check_data_fin = true;
> }
>
> /* at this point we held the socket lock for the last subflow we used */
> @@ -1608,49 +1629,37 @@ 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 *dfrag;
> struct sock *xmit_ssk;
> - int len, copied = 0;
I'm not sure why copied is removed here, it's still useful for knowing
when a tcp_push() is required at the end of the function. The push needs
to happen if data has been sent. __subflow_push_pending() can be called
more than once, and if it returned a positive number on *any* call then
tcp_push() is required.
Option A: Continue using the 'copied' variable
Option B: Use a bool instead (like "bool do_push;").
> + int ret = 0;
>
> info.flags = 0;
> - while ((dfrag = mptcp_send_head(sk))) {
> - info.sent = dfrag->already_sent;
> - info.limit = dfrag->data_len;
> - len = dfrag->data_len - dfrag->already_sent;
> - while (len > 0) {
> - 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;
> - }
> -
> - ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> - if (ret <= 0)
> - goto out;
> -
> - info.sent += ret;
> - copied += ret;
> - len -= ret;
> - first = false;
> + while (mptcp_send_head(sk)) {
> + /* 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;
> + }
>
> - mptcp_update_post_push(msk, dfrag, ret);
> + ret = __subflow_push_pending(sk, ssk, &info);
> + first = false;
> + if (ret <= 0) {
> + if (ret == -EAGAIN)
> + continue;
> + break;
> }
> - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
Option A: "copied += ret;" here
Option B: "do_push = true;"
> }
>
> out:
> /* __mptcp_alloc_tx_skb could have released some wmem and we are
> * not going to flush it via release_sock()
> */
> - if (copied) {
> + if (ret) {
Option A: leave this unchanged
Option B: replace with "if (do_push) {"
> tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> info.size_goal);
> if (!mptcp_timer_pending(sk))
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH mptcp-next v18 02/15] mptcp: drop last_snd and MPTCP_RESET_SCHEDULER
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 01/15] mptcp: refactor push_pending logic Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 03/15] mptcp: add sched_data_set_contexts helper Geliang Tang
` (12 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Since the burst check conditions have moved out of the function
mptcp_subflow_get_send(), it makes some msk->last_snd useless.
This patch drops them as well as the macro MPTCP_RESET_SCHEDULER.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/pm.c | 9 +--------
net/mptcp/pm_netlink.c | 3 ---
net/mptcp/protocol.c | 7 +------
net/mptcp/protocol.h | 1 -
4 files changed, 2 insertions(+), 18 deletions(-)
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 45e2a48397b9..cdeb7280ac76 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -282,15 +282,8 @@ void mptcp_pm_mp_prio_received(struct sock *ssk, u8 bkup)
pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup);
msk = mptcp_sk(sk);
- if (subflow->backup != bkup) {
+ if (subflow->backup != bkup)
subflow->backup = bkup;
- mptcp_data_lock(sk);
- if (!sock_owned_by_user(sk))
- msk->last_snd = NULL;
- else
- __set_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags);
- mptcp_data_unlock(sk);
- }
mptcp_event(MPTCP_EVENT_SUB_PRIORITY, msk, ssk, GFP_ATOMIC);
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 02469d603261..b0b83e03a4fd 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -475,9 +475,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
slow = lock_sock_fast(ssk);
if (prio) {
- if (subflow->backup != backup)
- msk->last_snd = NULL;
-
subflow->send_mp_prio = 1;
subflow->backup = backup;
subflow->request_bkup = backup;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1fb3b46fa427..d7aaa49c64f4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1478,16 +1478,13 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
wmem = READ_ONCE(ssk->sk_wmem_queued);
- if (!burst) {
- msk->last_snd = NULL;
+ if (!burst)
return ssk;
- }
subflow = mptcp_subflow_ctx(ssk);
subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
READ_ONCE(ssk->sk_pacing_rate) * burst,
burst + wmem);
- msk->last_snd = ssk;
msk->snd_burst = burst;
return ssk;
}
@@ -3294,8 +3291,6 @@ static void mptcp_release_cb(struct sock *sk)
__mptcp_set_connected(sk);
if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
__mptcp_error_report(sk);
- if (__test_and_clear_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags))
- msk->last_snd = NULL;
}
__mptcp_update_rmem(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 8df6d95a3247..e93d64217896 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -124,7 +124,6 @@
#define MPTCP_RETRANSMIT 4
#define MPTCP_FLUSH_JOIN_LIST 5
#define MPTCP_CONNECTED 6
-#define MPTCP_RESET_SCHEDULER 7
static inline bool before64(__u64 seq1, __u64 seq2)
{
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 03/15] mptcp: add sched_data_set_contexts helper
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 01/15] mptcp: refactor push_pending logic Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 02/15] mptcp: drop last_snd and MPTCP_RESET_SCHEDULER Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 04/15] Squash to "mptcp: add struct mptcp_sched_ops" Geliang Tang
` (11 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Add a new helper mptcp_sched_data_set_contexts() to set the subflow
pointers array in struct mptcp_sched_data. It will be invoked by the
BPF schedulers to export the subflow pointers to the BPF contexts.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/sched.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index d295b92a5789..5a910da1452b 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -93,3 +93,22 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
{
WRITE_ONCE(subflow->scheduled, scheduled);
}
+
+void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
+{
+ struct mptcp_subflow_context *subflow;
+ int i = 0;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (i == MPTCP_SUBFLOWS_MAX) {
+ pr_warn_once("too many subflows");
+ break;
+ }
+ mptcp_subflow_set_scheduled(subflow, false);
+ data->contexts[i++] = subflow;
+ }
+
+ for (; i < MPTCP_SUBFLOWS_MAX; i++)
+ data->contexts[i] = NULL;
+}
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 04/15] Squash to "mptcp: add struct mptcp_sched_ops"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (2 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 03/15] mptcp: add sched_data_set_contexts helper Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 05/15] Squash to "bpf: Add bpf_mptcp_sched_ops" Geliang Tang
` (10 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
New api:
- add new data_init
- add an int return value for get_subflow
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
include/net/mptcp.h | 6 ++++--
net/mptcp/sched.c | 2 +-
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index c25939b2af68..0f386d805957 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -105,8 +105,10 @@ struct mptcp_sched_data {
};
struct mptcp_sched_ops {
- void (*get_subflow)(const struct mptcp_sock *msk,
- struct mptcp_sched_data *data);
+ void (*data_init)(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data);
+ int (*get_subflow)(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data);
char name[MPTCP_SCHED_NAME_MAX];
struct module *owner;
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 5a910da1452b..0d7c73e9562e 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -33,7 +33,7 @@ struct mptcp_sched_ops *mptcp_sched_find(const char *name)
int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
{
- if (!sched->get_subflow)
+ if (!sched->data_init || !sched->get_subflow)
return -EINVAL;
spin_lock(&mptcp_sched_list_lock);
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 05/15] Squash to "bpf: Add bpf_mptcp_sched_ops"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (3 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 04/15] Squash to "mptcp: add struct mptcp_sched_ops" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 06/15] Squash to "bpf: Add bpf_mptcp_sched_kfunc_set" Geliang Tang
` (9 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Use new API.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
tools/testing/selftests/bpf/bpf_tcp_helpers.h | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index c7d4a9a69cfc..72c618037386 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -249,8 +249,10 @@ struct mptcp_sched_ops {
void (*init)(const struct mptcp_sock *msk);
void (*release)(const struct mptcp_sock *msk);
- void (*get_subflow)(const struct mptcp_sock *msk,
- struct mptcp_sched_data *data);
+ void (*data_init)(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data);
+ int (*get_subflow)(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data);
void *owner;
};
@@ -265,5 +267,7 @@ struct mptcp_sock {
extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
bool scheduled) __ksym;
+extern void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data) __ksym;
#endif
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 06/15] Squash to "bpf: Add bpf_mptcp_sched_kfunc_set"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (4 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 05/15] Squash to "bpf: Add bpf_mptcp_sched_ops" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 07/15] Squash to "selftests/bpf: Add bpf_first scheduler" Geliang Tang
` (8 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Add mptcp_sched_data_set_contexts in kfunc_set.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/bpf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 0a768898990f..03decb05755f 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -164,6 +164,7 @@ struct bpf_struct_ops bpf_mptcp_sched_ops = {
BTF_SET8_START(bpf_mptcp_sched_kfunc_ids)
BTF_ID_FLAGS(func, mptcp_subflow_set_scheduled)
+BTF_ID_FLAGS(func, mptcp_sched_data_set_contexts)
BTF_SET8_END(bpf_mptcp_sched_kfunc_ids)
static const struct btf_kfunc_id_set bpf_mptcp_sched_kfunc_set = {
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 07/15] Squash to "selftests/bpf: Add bpf_first scheduler"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (5 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 06/15] Squash to "bpf: Add bpf_mptcp_sched_kfunc_set" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 08/15] Squash to "selftests/bpf: Add bpf_bkup scheduler" Geliang Tang
` (7 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Use new API.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
tools/testing/selftests/bpf/progs/mptcp_bpf_first.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
index fcd733e88b02..e4caa2dd8c6f 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
@@ -16,16 +16,24 @@ void BPF_PROG(mptcp_sched_first_release, const struct mptcp_sock *msk)
{
}
-void BPF_STRUCT_OPS(bpf_first_get_subflow, const struct mptcp_sock *msk,
+void BPF_STRUCT_OPS(bpf_first_data_init, const struct mptcp_sock *msk,
struct mptcp_sched_data *data)
+{
+ mptcp_sched_data_set_contexts(msk, data);
+}
+
+int BPF_STRUCT_OPS(bpf_first_get_subflow, const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
{
mptcp_subflow_set_scheduled(data->contexts[0], true);
+ return 0;
}
SEC(".struct_ops")
struct mptcp_sched_ops first = {
.init = (void *)mptcp_sched_first_init,
.release = (void *)mptcp_sched_first_release,
+ .data_init = (void *)bpf_first_data_init,
.get_subflow = (void *)bpf_first_get_subflow,
.name = "bpf_first",
};
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 08/15] Squash to "selftests/bpf: Add bpf_bkup scheduler"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (6 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 07/15] Squash to "selftests/bpf: Add bpf_first scheduler" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 09/15] Squash to "selftests/bpf: Add bpf_rr scheduler" Geliang Tang
` (6 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Use new API.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
index 949e053e980c..b2724426676e 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
@@ -16,8 +16,14 @@ void BPF_PROG(mptcp_sched_bkup_release, const struct mptcp_sock *msk)
{
}
-void BPF_STRUCT_OPS(bpf_bkup_get_subflow, const struct mptcp_sock *msk,
+void BPF_STRUCT_OPS(bpf_bkup_data_init, const struct mptcp_sock *msk,
struct mptcp_sched_data *data)
+{
+ mptcp_sched_data_set_contexts(msk, data);
+}
+
+int BPF_STRUCT_OPS(bpf_bkup_get_subflow, const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
{
int nr = 0;
@@ -32,12 +38,14 @@ void BPF_STRUCT_OPS(bpf_bkup_get_subflow, const struct mptcp_sock *msk,
}
mptcp_subflow_set_scheduled(data->contexts[nr], true);
+ return 0;
}
SEC(".struct_ops")
struct mptcp_sched_ops bkup = {
.init = (void *)mptcp_sched_bkup_init,
.release = (void *)mptcp_sched_bkup_release,
+ .data_init = (void *)bpf_bkup_data_init,
.get_subflow = (void *)bpf_bkup_get_subflow,
.name = "bpf_bkup",
};
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 09/15] Squash to "selftests/bpf: Add bpf_rr scheduler"
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (7 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 08/15] Squash to "selftests/bpf: Add bpf_bkup scheduler" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-11 0:29 ` Mat Martineau
2022-11-08 9:08 ` [PATCH mptcp-next v18 10/15] mptcp: use get_send wrapper Geliang Tang
` (5 subsequent siblings)
14 siblings, 1 reply; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
Use new API.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
index ce4e98f83e43..e101428e5906 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
@@ -16,8 +16,14 @@ void BPF_PROG(mptcp_sched_rr_release, const struct mptcp_sock *msk)
{
}
-void BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
+void BPF_STRUCT_OPS(bpf_rr_data_init, const struct mptcp_sock *msk,
struct mptcp_sched_data *data)
+{
+ mptcp_sched_data_set_contexts(msk, data);
+}
+
+int BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
+ struct mptcp_sched_data *data)
{
int nr = 0;
@@ -35,12 +41,14 @@ void BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
}
mptcp_subflow_set_scheduled(data->contexts[nr], true);
+ return 0;
}
SEC(".struct_ops")
struct mptcp_sched_ops rr = {
.init = (void *)mptcp_sched_rr_init,
.release = (void *)mptcp_sched_rr_release,
+ .data_init = (void *)bpf_rr_data_init,
.get_subflow = (void *)bpf_rr_get_subflow,
.name = "bpf_rr",
};
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH mptcp-next v18 09/15] Squash to "selftests/bpf: Add bpf_rr scheduler"
2022-11-08 9:08 ` [PATCH mptcp-next v18 09/15] Squash to "selftests/bpf: Add bpf_rr scheduler" Geliang Tang
@ 2022-11-11 0:29 ` Mat Martineau
0 siblings, 0 replies; 21+ messages in thread
From: Mat Martineau @ 2022-11-11 0:29 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Tue, 8 Nov 2022, Geliang Tang wrote:
> Use new API.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
After patch 1 is updated, I think the series is looking good up to this
patch.
- Mat
> ---
> tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c | 10 +++++++++-
> 1 file changed, 9 insertions(+), 1 deletion(-)
>
> diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
> index ce4e98f83e43..e101428e5906 100644
> --- a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
> +++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
> @@ -16,8 +16,14 @@ void BPF_PROG(mptcp_sched_rr_release, const struct mptcp_sock *msk)
> {
> }
>
> -void BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
> +void BPF_STRUCT_OPS(bpf_rr_data_init, const struct mptcp_sock *msk,
> struct mptcp_sched_data *data)
> +{
> + mptcp_sched_data_set_contexts(msk, data);
> +}
> +
> +int BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
> + struct mptcp_sched_data *data)
> {
> int nr = 0;
>
> @@ -35,12 +41,14 @@ void BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
> }
>
> mptcp_subflow_set_scheduled(data->contexts[nr], true);
> + return 0;
> }
>
> SEC(".struct_ops")
> struct mptcp_sched_ops rr = {
> .init = (void *)mptcp_sched_rr_init,
> .release = (void *)mptcp_sched_rr_release,
> + .data_init = (void *)bpf_rr_data_init,
> .get_subflow = (void *)bpf_rr_get_subflow,
> .name = "bpf_rr",
> };
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH mptcp-next v18 10/15] mptcp: use get_send wrapper
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (8 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 09/15] Squash to "selftests/bpf: Add bpf_rr scheduler" Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-11 1:04 ` Mat Martineau
2022-11-08 9:08 ` [PATCH mptcp-next v18 11/15] mptcp: use get_retrans wrapper Geliang Tang
` (4 subsequent siblings)
14 siblings, 1 reply; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch defines the packet scheduler wrapper mptcp_sched_get_send(),
invoke data_init() and get_subflow() of msk->sched in it.
Set data->reinject to false in mptcp_sched_get_send(). If msk->sched is
NULL, use default functions mptcp_subflow_get_send() to send data.
Move sock_owned_by_me() check and fallback check into the wrapper from
mptcp_subflow_get_send().
Add 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.
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 | 131 ++++++++++++++++++++++++++++---------------
net/mptcp/protocol.h | 2 +
net/mptcp/sched.c | 37 ++++++++++++
3 files changed, 124 insertions(+), 46 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d7aaa49c64f4..5bcadb36b99b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1406,7 +1406,7 @@ 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;
@@ -1417,15 +1417,6 @@ static 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;
@@ -1577,42 +1568,58 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
};
bool do_check_data_fin = false;
+again:
while (mptcp_send_head(sk)) {
+ struct mptcp_subflow_context *subflow, *last = NULL;
int ret = 0;
- prev_ssk = ssk;
- ssk = mptcp_subflow_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)
+ if (mptcp_sched_get_send(msk))
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);
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ last = subflow;
+ }
- ret = __subflow_push_pending(sk, ssk, &info);
- if (ret <= 0) {
- if (ret == -EAGAIN)
- continue;
- mptcp_push_release(ssk, &info);
- goto out;
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ prev_ssk = ssk;
+ ssk = mptcp_subflow_tcp_sock(subflow);
+
+ /* 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);
+
+ /* 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 = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0) {
+ if (ret == -EAGAIN &&
+ inet_sk_state_load(ssk) != TCP_CLOSE)
+ goto again;
+ if (last && subflow != last)
+ continue;
+ goto out;
+ }
+ do_check_data_fin = true;
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
}
- do_check_data_fin = true;
}
+out:
/* 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);
@@ -1626,29 +1633,61 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
struct mptcp_sendmsg_info info = {
.data_lock_held = true,
};
- struct sock *xmit_ssk;
int ret = 0;
info.flags = 0;
+again:
while (mptcp_send_head(sk)) {
+ struct mptcp_subflow_context *subflow, *last = NULL;
+
/* 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) {
+ ret = __subflow_push_pending(sk, ssk, &info);
+ first = false;
+ if (ret <= 0) {
+ if (ret == -EAGAIN &&
+ inet_sk_state_load(ssk) != TCP_CLOSE)
+ goto again;
+ break;
+ }
+ msk->last_snd = ssk;
+ continue;
+ }
+
+ if (mptcp_sched_get_send(msk))
goto out;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ last = subflow;
}
- ret = __subflow_push_pending(sk, ssk, &info);
- first = false;
- if (ret <= 0) {
- if (ret == -EAGAIN)
- continue;
- break;
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled)) {
+ struct sock *xmit_ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (xmit_ssk != ssk) {
+ mptcp_subflow_delegate(subflow,
+ MPTCP_DELEGATE_SEND);
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ goto out;
+ }
+
+ ret = __subflow_push_pending(sk, ssk, &info);
+ if (ret <= 0) {
+ if (ret == -EAGAIN &&
+ inet_sk_state_load(ssk) != TCP_CLOSE)
+ goto again;
+ if (last && subflow != last)
+ continue;
+ goto out;
+ }
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
}
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e93d64217896..2bc0acf2d659 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -640,6 +640,8 @@ int mptcp_init_sched(struct mptcp_sock *msk,
void mptcp_release_sched(struct mptcp_sock *msk);
void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
bool scheduled);
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
+int mptcp_sched_get_send(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..bc5d82300863 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -112,3 +112,40 @@ 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;
+ struct sock *ssk = NULL;
+
+ sock_owned_by_me((const struct sock *)msk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ return 0;
+ }
+
+ /* 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;
+ }
+
+ if (!msk->sched) {
+ 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);
+}
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH mptcp-next v18 10/15] mptcp: use get_send wrapper
2022-11-08 9:08 ` [PATCH mptcp-next v18 10/15] mptcp: use get_send wrapper Geliang Tang
@ 2022-11-11 1:04 ` Mat Martineau
0 siblings, 0 replies; 21+ messages in thread
From: Mat Martineau @ 2022-11-11 1:04 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
On Tue, 8 Nov 2022, Geliang Tang wrote:
> This patch defines the packet scheduler wrapper mptcp_sched_get_send(),
> invoke data_init() and get_subflow() of msk->sched in it.
>
> Set data->reinject to false in mptcp_sched_get_send(). If msk->sched is
> NULL, use default functions mptcp_subflow_get_send() to send data.
>
> Move sock_owned_by_me() check and fallback check into the wrapper from
> mptcp_subflow_get_send().
>
> Add 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.
>
> 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 | 131 ++++++++++++++++++++++++++++---------------
> net/mptcp/protocol.h | 2 +
> net/mptcp/sched.c | 37 ++++++++++++
> 3 files changed, 124 insertions(+), 46 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index d7aaa49c64f4..5bcadb36b99b 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1406,7 +1406,7 @@ 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;
> @@ -1417,15 +1417,6 @@ static 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;
> @@ -1577,42 +1568,58 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> };
> bool do_check_data_fin = false;
>
> +again:
> while (mptcp_send_head(sk)) {
> + struct mptcp_subflow_context *subflow, *last = NULL;
> int ret = 0;
>
> - prev_ssk = ssk;
> - ssk = mptcp_subflow_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)
> + if (mptcp_sched_get_send(msk))
> 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);
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled))
> + last = subflow;
> + }
Since mptcp_sched_get_send() is always called right before this, the
subflow->scheduled flags will always be set. Does the new code with 'last'
work as expected if the mptcp_sched_get_send() call is skipped when an
existing subflow->scheduled flag is found? That way the old flags will be
used the first time through this loop.
- Mat
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - if (ret <= 0) {
> - if (ret == -EAGAIN)
> - continue;
> - mptcp_push_release(ssk, &info);
> - goto out;
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + prev_ssk = ssk;
> + ssk = mptcp_subflow_tcp_sock(subflow);
> +
> + /* 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);
> +
> + /* 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 = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0) {
> + if (ret == -EAGAIN &&
> + inet_sk_state_load(ssk) != TCP_CLOSE)
> + goto again;
> + if (last && subflow != last)
> + continue;
> + goto out;
> + }
> + do_check_data_fin = true;
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
> + }
> }
> - do_check_data_fin = true;
> }
>
> +out:
> /* 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);
> @@ -1626,29 +1633,61 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
> struct mptcp_sendmsg_info info = {
> .data_lock_held = true,
> };
> - struct sock *xmit_ssk;
> int ret = 0;
>
> info.flags = 0;
> +again:
> while (mptcp_send_head(sk)) {
> + struct mptcp_subflow_context *subflow, *last = NULL;
> +
> /* 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) {
> + ret = __subflow_push_pending(sk, ssk, &info);
> + first = false;
> + if (ret <= 0) {
> + if (ret == -EAGAIN &&
> + inet_sk_state_load(ssk) != TCP_CLOSE)
> + goto again;
> + break;
> + }
> + msk->last_snd = ssk;
> + continue;
> + }
> +
> + if (mptcp_sched_get_send(msk))
> goto out;
> +
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled))
> + last = subflow;
> }
>
> - ret = __subflow_push_pending(sk, ssk, &info);
> - first = false;
> - if (ret <= 0) {
> - if (ret == -EAGAIN)
> - continue;
> - break;
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled)) {
> + struct sock *xmit_ssk = mptcp_subflow_tcp_sock(subflow);
> +
> + if (xmit_ssk != ssk) {
> + mptcp_subflow_delegate(subflow,
> + MPTCP_DELEGATE_SEND);
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
> + goto out;
> + }
> +
> + ret = __subflow_push_pending(sk, ssk, &info);
> + if (ret <= 0) {
> + if (ret == -EAGAIN &&
> + inet_sk_state_load(ssk) != TCP_CLOSE)
> + goto again;
> + if (last && subflow != last)
> + continue;
> + goto out;
> + }
> + msk->last_snd = ssk;
> + mptcp_subflow_set_scheduled(subflow, false);
> + }
> }
> }
>
> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index e93d64217896..2bc0acf2d659 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -640,6 +640,8 @@ int mptcp_init_sched(struct mptcp_sock *msk,
> void mptcp_release_sched(struct mptcp_sock *msk);
> void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
> bool scheduled);
> +struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
> +int mptcp_sched_get_send(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..bc5d82300863 100644
> --- a/net/mptcp/sched.c
> +++ b/net/mptcp/sched.c
> @@ -112,3 +112,40 @@ 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;
> + struct sock *ssk = NULL;
> +
> + sock_owned_by_me((const struct sock *)msk);
> +
> + mptcp_for_each_subflow(msk, subflow) {
> + if (READ_ONCE(subflow->scheduled))
> + return 0;
> + }
> +
> + /* 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;
> + }
> +
> + if (!msk->sched) {
> + 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);
> +}
> --
> 2.35.3
>
>
>
--
Mat Martineau
Intel
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH mptcp-next v18 11/15] mptcp: use get_retrans wrapper
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (9 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 10/15] mptcp: use get_send wrapper Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 12/15] mptcp: delay updating first_pending Geliang Tang
` (3 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch defines the packet scheduler wrapper mptcp_sched_get_retrans(),
invoke data_init() and get_subflow() of msk->sched in it.
Set data->reinject to true in mptcp_sched_get_retrans(). If msk->sched is
NULL, use default functions mptcp_subflow_get_retrans() to retrans data.
Move sock_owned_by_me() check and fallback check into the wrapper from
mptcp_subflow_get_retrans().
Add 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.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 69 +++++++++++++++++++++++++-------------------
net/mptcp/protocol.h | 2 ++
net/mptcp/sched.c | 30 +++++++++++++++++++
3 files changed, 72 insertions(+), 29 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5bcadb36b99b..bf49eaf203dc 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2264,17 +2264,12 @@ 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;
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);
@@ -2549,16 +2544,17 @@ 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)) {
@@ -2577,31 +2573,46 @@ 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;
+
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ if (!ssk)
+ goto reset_timer;
+
+ lock_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);
+ }
- /* 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;
+ release_sock(ssk);
- 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);
+ msk->last_snd = ssk;
+ mptcp_subflow_set_scheduled(subflow, false);
+ }
}
-
- release_sock(ssk);
+ dfrag->already_sent = max(dfrag->already_sent, len);
reset_timer:
mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2bc0acf2d659..f8cc14064573 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -641,7 +641,9 @@ void mptcp_release_sched(struct mptcp_sock *msk);
void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
bool scheduled);
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 bc5d82300863..edddd7cceada 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -149,3 +149,33 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
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;
+ struct sock *ssk = NULL;
+
+ sock_owned_by_me((const struct sock *)msk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ if (READ_ONCE(subflow->scheduled))
+ return 0;
+ }
+
+ /* the following check is moved out of mptcp_subflow_get_retrans */
+ if (__mptcp_check_fallback(msk))
+ return -EINVAL;
+
+ if (!msk->sched) {
+ 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] 21+ messages in thread* [PATCH mptcp-next v18 12/15] mptcp: delay updating first_pending
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (10 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 11/15] mptcp: use get_retrans wrapper Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 13/15] mptcp: delay updating already_sent Geliang Tang
` (2 subsequent siblings)
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
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 are sent.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 33 ++++++++++++++++++++++++++++++---
net/mptcp/protocol.h | 13 ++++++++++---
2 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index bf49eaf203dc..fc3498f84964 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1121,6 +1121,7 @@ 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,
@@ -1511,6 +1512,19 @@ 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))
@@ -1524,7 +1538,13 @@ 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;
@@ -1543,7 +1563,8 @@ 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) ||
@@ -1552,7 +1573,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
goto out;
}
mptcp_set_timeout(sk);
- }
+ } while (dfrag);
err = copied;
out:
@@ -1601,6 +1622,7 @@ 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_CLOSE)
goto again;
@@ -1613,6 +1635,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
mptcp_subflow_set_scheduled(subflow, false);
}
}
+ mptcp_update_dfrags(sk, &info);
}
out:
@@ -1647,12 +1670,14 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool
ret = __subflow_push_pending(sk, ssk, &info);
first = false;
if (ret <= 0) {
+ mptcp_update_first_pending(sk, &info);
if (ret == -EAGAIN &&
inet_sk_state_load(ssk) != TCP_CLOSE)
goto again;
break;
}
msk->last_snd = ssk;
+ mptcp_update_dfrags(sk, &info);
continue;
}
@@ -1678,6 +1703,7 @@ 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);
if (ret == -EAGAIN &&
inet_sk_state_load(ssk) != TCP_CLOSE)
goto again;
@@ -1689,6 +1715,7 @@ 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 f8cc14064573..4b13ba9df34f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -349,16 +349,23 @@ 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
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 13/15] mptcp: delay updating already_sent
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (11 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 12/15] mptcp: delay updating first_pending Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 14/15] selftests/bpf: Add bpf_red scheduler Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 15/15] selftests/bpf: Add bpf_red test Geliang Tang
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch adds a new member sent in struct mptcp_data_frag, save
info->sent in it, to support delay updating already_sent of dfrag
until all data are sent.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 18 ++++++++++++++++--
net/mptcp/protocol.h | 1 +
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index fc3498f84964..b179eb56b4f2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1108,6 +1108,7 @@ mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
dfrag->data_seq = msk->write_seq;
dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+ dfrag->sent = 0;
dfrag->already_sent = 0;
dfrag->page = pfrag->page;
@@ -1493,11 +1494,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
{
u64 snd_nxt_new = dfrag->data_seq;
- dfrag->already_sent += sent;
+ dfrag->sent += sent;
msk->snd_burst -= sent;
- snd_nxt_new += dfrag->already_sent;
+ snd_nxt_new += dfrag->sent;
/* snd_nxt_new can be smaller than snd_nxt in case mptcp
* is recovering after a failover. In that event, this re-sends
@@ -1522,6 +1523,18 @@ static void mptcp_update_first_pending(struct sock *sk, struct mptcp_sendmsg_inf
static void mptcp_update_dfrags(struct sock *sk, struct mptcp_sendmsg_info *info)
{
+ struct mptcp_data_frag *dfrag = mptcp_send_head(sk);
+
+ if (!dfrag)
+ return;
+
+ do {
+ if (dfrag->sent) {
+ dfrag->already_sent = max(dfrag->already_sent, dfrag->sent);
+ dfrag->sent = 0;
+ }
+ } while ((dfrag = mptcp_next_frag(sk, dfrag)));
+
mptcp_update_first_pending(sk, info);
}
@@ -1548,6 +1561,7 @@ 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;
+ dfrag->sent = info->sent;
while (len > 0) {
int ret = 0;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 4b13ba9df34f..5d85063dd5a2 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -241,6 +241,7 @@ struct mptcp_data_frag {
u16 data_len;
u16 offset;
u16 overhead;
+ u16 sent;
u16 already_sent;
struct page *page;
};
--
2.35.3
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH mptcp-next v18 14/15] selftests/bpf: Add bpf_red scheduler
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (12 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 13/15] mptcp: delay updating already_sent Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:08 ` [PATCH mptcp-next v18 15/15] selftests/bpf: Add bpf_red test Geliang Tang
14 siblings, 0 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 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] 21+ messages in thread* [PATCH mptcp-next v18 15/15] selftests/bpf: Add bpf_red test
2022-11-08 9:08 [PATCH mptcp-next v18 00/15] BPF redundant scheduler Geliang Tang
` (13 preceding siblings ...)
2022-11-08 9:08 ` [PATCH mptcp-next v18 14/15] selftests/bpf: Add bpf_red scheduler Geliang Tang
@ 2022-11-08 9:08 ` Geliang Tang
2022-11-08 9:34 ` selftests/bpf: Add bpf_red test: Build Failure MPTCP CI
2022-11-08 10:51 ` selftests/bpf: Add bpf_red test: Tests Results MPTCP CI
14 siblings, 2 replies; 21+ messages in thread
From: Geliang Tang @ 2022-11-08 9:08 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] 21+ messages in thread* Re: selftests/bpf: Add bpf_red test: Build Failure
2022-11-08 9:08 ` [PATCH mptcp-next v18 15/15] selftests/bpf: Add bpf_red test Geliang Tang
@ 2022-11-08 9:34 ` MPTCP CI
2022-11-08 10:51 ` selftests/bpf: Add bpf_red test: Tests Results MPTCP CI
1 sibling, 0 replies; 21+ messages in thread
From: MPTCP CI @ 2022-11-08 9:34 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
Hi Geliang,
Thank you for your modifications, that's great!
But sadly, our CI spotted some issues with it when trying to build it.
You can find more details there:
https://patchwork.kernel.org/project/mptcp/patch/92d945d60c7a97d26d30a7dd8dff441b5509968b.1667897099.git.geliang.tang@suse.com/
https://github.com/multipath-tcp/mptcp_net-next/actions/runs/3417962790
Status: failure
Initiator: MPTCPimporter
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/e24daa06c11e
Feel free to reply to this email if you cannot access logs, if you need
some support to fix the error, if this doesn't seem to be caused by your
modifications or if the error is a false positive one.
Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (Tessares)
^ permalink raw reply [flat|nested] 21+ messages in thread
* Re: selftests/bpf: Add bpf_red test: Tests Results
2022-11-08 9:08 ` [PATCH mptcp-next v18 15/15] selftests/bpf: Add bpf_red test Geliang Tang
2022-11-08 9:34 ` selftests/bpf: Add bpf_red test: Build Failure MPTCP CI
@ 2022-11-08 10:51 ` MPTCP CI
1 sibling, 0 replies; 21+ messages in thread
From: MPTCP CI @ 2022-11-08 10:51 UTC (permalink / raw)
To: Geliang Tang; +Cc: mptcp
Hi Geliang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- KVM Validation: normal:
- Success! ✅:
- Task: https://cirrus-ci.com/task/6199481423626240
- Summary: https://api.cirrus-ci.com/v1/artifact/task/6199481423626240/summary/summary.txt
- KVM Validation: debug:
- Critical: 2 Call Trace(s) ❌:
- Task: https://cirrus-ci.com/task/4792106540072960
- Summary: https://api.cirrus-ci.com/v1/artifact/task/4792106540072960/summary/summary.txt
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/e24daa06c11e
If there are some issues, you can reproduce them using the same environment as
the one used by the CI thanks to a docker image, e.g.:
$ cd [kernel source code]
$ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
--pull always mptcp/mptcp-upstream-virtme-docker:latest \
auto-debug
For more details:
https://github.com/multipath-tcp/mptcp-upstream-virtme-docker
Please note that despite all the efforts that have been already done to have a
stable tests suite when executed on a public CI like here, it is possible some
reported issues are not due to your modifications. Still, do not hesitate to
help us improve that ;-)
Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (Tessares)
^ permalink raw reply [flat|nested] 21+ messages in thread