Re: [PATCH mptcp-next v21 2/7] mptcp: use get_send wrapper

[Mat Martineau <mathew.j.martineau@linux.intel.com>]

On Mon, 28 Nov 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 | 118 ++++++++++++++++++++++++++-----------------
> net/mptcp/sched.c    |  13 +++++
> 2 files changed, 84 insertions(+), 47 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index d8ad68dd504a..65eaf59c9a6f 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 +1554,58 @@ 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;
> +	bool err = false;

The code below will still quit the "while (mptcp send_head() && !err)" 
loop if the previous iteration had an error on one subflow (even if 
multiple subflows were scheduled and there were successful sends).

I suggest removing the "bool err" and instead add

 	int push_count = -1;

(more info below)

>
> -	while (mptcp_send_head(sk)) {
> +	while (mptcp_send_head(sk) && !err) {

Change to

 	while (mptcp_send_head(sk) && (push_count == 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)
> +		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);

add:

 		push_count = 0;

> +		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);
> +				}
> +

add:

 				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))
> +						err = true;

replace with:

 						push_count--;

This way push_count will be a positive number at the end of the loop 
iteration if any __subflow_push_pending() calls succeeded, and the loop 
will continue sending on the working subflow(s).

- Mat

> +					continue;
> +				}
> +				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);
> @@ -1614,33 +1616,55 @@ 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 err = false;
> 	int copied = 0;
>
> 	info.flags = 0;
> -	while (mptcp_send_head(sk)) {
> +	while (mptcp_send_head(sk) && !err) {
> 		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) {
> +					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) {
> +					err = true;
> +					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