'''
mptcp: add sched_get_send wrapper

This patch defines a wrapper named mptcp_sched_get_send(), invoke
mptcp_subflow_get_send() or get_subflow() of msk->sched in it.

Set the subflow pointers array in struct mptcp_sched_data before invoking
get_subflow(), then it can be used in get_subflow() in the BPF contexts.

Move sock_owned_by_me() and the fallback check code from
mptcp_subflow_get_send() into this wrapper.
'''

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 15 +++++++----
 net/mptcp/protocol.h |  4 +--
 net/mptcp/sched.c    | 60 ++++++++++++--------------------------------
 3 files changed, 27 insertions(+), 52 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d6aef4b13b8a..8d93df73a9e3 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1567,7 +1567,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			int ret = 0;
 
 			prev_ssk = ssk;
-			ssk = mptcp_sched_get_send(msk);
+			ssk = mptcp_subflow_get_send(msk);
 
 			/* First check. If the ssk has changed since
 			 * the last round, release prev_ssk
@@ -1634,7 +1634,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			 * check for a different subflow usage only after
 			 * spooling the first chunk of data
 			 */
-			xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk));
+			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
@@ -2195,12 +2195,17 @@ static void mptcp_timeout_timer(struct timer_list *t)
  *
  * A backup subflow is returned only if that is the only kind available.
  */
-struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+static 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);
 
@@ -2453,7 +2458,7 @@ static void __mptcp_retrans(struct sock *sk)
 	mptcp_clean_una_wakeup(sk);
 
 	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_sched_get_retrans(msk);
+	ssk = mptcp_subflow_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -3107,7 +3112,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		return;
 
 	if (!sock_owned_by_user(sk)) {
-		struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk));
+		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
 
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d406b5afbee4..0fb2970a7a2d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -632,9 +632,7 @@ 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);
-struct sock *mptcp_sched_get_send(struct mptcp_sock *msk);
-struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk);
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 8858e1fc8b74..a0585182a2b1 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -117,63 +117,35 @@ static int mptcp_sched_data_init(struct mptcp_sock *msk, bool reinject,
 	return 0;
 }
 
-struct sock *mptcp_sched_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err)
 {
 	struct mptcp_sched_data data;
 	struct sock *ssk = NULL;
-	int i;
 
+	*err = -EINVAL;
 	sock_owned_by_me((struct sock *)msk);
 
 	/* the following check is moved out of mptcp_subflow_get_send */
 	if (__mptcp_check_fallback(msk)) {
-		if (!msk->first)
-			return NULL;
-		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
-	}
-
-	if (!msk->sched)
-		return mptcp_subflow_get_send(msk);
-
-	mptcp_sched_data_init(msk, false, &data);
-	msk->sched->get_subflow(msk, &data);
-
-	for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
-		if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
-			ssk = data.contexts[i]->tcp_sock;
-			msk->last_snd = ssk;
-			break;
+		if (msk->first && sk_stream_memory_free(msk->first)) {
+			mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
+			*err = 0;
+			return msk->first;
 		}
-	}
-
-	return ssk;
-}
-
-struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk)
-{
-	struct mptcp_sched_data data;
-	struct sock *ssk = NULL;
-	int i;
-
-	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 NULL;
+	}
 
-	if (!msk->sched)
-		return mptcp_subflow_get_retrans(msk);
+	if (!msk->sched) {
+		ssk = mptcp_subflow_get_send(msk);
+		if (!ssk)
+			return NULL;
+		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+		*err = 0;
+		return ssk;
+	}
 
-	mptcp_sched_data_init(msk, true, &data);
+	mptcp_sched_data_init(msk, false, &data);
 	msk->sched->get_subflow(msk, &data);
 
-	for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
-		if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
-			ssk = data.contexts[i]->tcp_sock;
-			msk->last_snd = ssk;
-			break;
-		}
-	}
-
 	return ssk;
 }
-- 
2.34.1

On Mon, 6 Jun 2022, Geliang Tang wrote:

> '''
> mptcp: add sched_get_send wrapper
>
> This patch defines a wrapper named mptcp_sched_get_send(), invoke
> mptcp_subflow_get_send() or get_subflow() of msk->sched in it.
>
> Set the subflow pointers array in struct mptcp_sched_data before invoking
> get_subflow(), then it can be used in get_subflow() in the BPF contexts.
>
> Move sock_owned_by_me() and the fallback check code from
> mptcp_subflow_get_send() into this wrapper.
> '''
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 15 +++++++----
> net/mptcp/protocol.h |  4 +--
> net/mptcp/sched.c    | 60 ++++++++++++--------------------------------
> 3 files changed, 27 insertions(+), 52 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index d6aef4b13b8a..8d93df73a9e3 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1567,7 +1567,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> 			int ret = 0;
>
> 			prev_ssk = ssk;
> -			ssk = mptcp_sched_get_send(msk);
> +			ssk = mptcp_subflow_get_send(msk);
>
> 			/* First check. If the ssk has changed since
> 			 * the last round, release prev_ssk
> @@ -1634,7 +1634,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
> 			 * check for a different subflow usage only after
> 			 * spooling the first chunk of data
> 			 */
> -			xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk));
> +			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
> 			if (!xmit_ssk)
> 				goto out;
> 			if (xmit_ssk != ssk) {
> @@ -2195,12 +2195,17 @@ static void mptcp_timeout_timer(struct timer_list *t)
>  *
>  * A backup subflow is returned only if that is the only kind available.
>  */
> -struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
> +static 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);
>
> @@ -2453,7 +2458,7 @@ static void __mptcp_retrans(struct sock *sk)
> 	mptcp_clean_una_wakeup(sk);
>
> 	/* first check ssk: need to kick "stale" logic */
> -	ssk = mptcp_sched_get_retrans(msk);
> +	ssk = mptcp_subflow_get_retrans(msk);
> 	dfrag = mptcp_rtx_head(sk);
> 	if (!dfrag) {
> 		if (mptcp_data_fin_enabled(msk)) {
> @@ -3107,7 +3112,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
> 		return;
>
> 	if (!sock_owned_by_user(sk)) {
> -		struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk));
> +		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
>
> 		if (xmit_ssk == ssk)
> 			__mptcp_subflow_push_pending(sk, ssk);
> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index d406b5afbee4..0fb2970a7a2d 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -632,9 +632,7 @@ 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);
> -struct sock *mptcp_sched_get_send(struct mptcp_sock *msk);
> -struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk);
> +struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err);
>
> static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
> {
> diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
> index 8858e1fc8b74..a0585182a2b1 100644
> --- a/net/mptcp/sched.c
> +++ b/net/mptcp/sched.c
> @@ -117,63 +117,35 @@ static int mptcp_sched_data_init(struct mptcp_sock *msk, bool reinject,
> 	return 0;
> }
>
> -struct sock *mptcp_sched_get_send(struct mptcp_sock *msk)
> +struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err)
> {
> 	struct mptcp_sched_data data;
> 	struct sock *ssk = NULL;
> -	int i;
>
> +	*err = -EINVAL;
> 	sock_owned_by_me((struct sock *)msk);
>
> 	/* the following check is moved out of mptcp_subflow_get_send */
> 	if (__mptcp_check_fallback(msk)) {
> -		if (!msk->first)
> -			return NULL;
> -		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
> -	}
> -
> -	if (!msk->sched)
> -		return mptcp_subflow_get_send(msk);
> -
> -	mptcp_sched_data_init(msk, false, &data);
> -	msk->sched->get_subflow(msk, &data);
> -
> -	for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
> -		if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
> -			ssk = data.contexts[i]->tcp_sock;
> -			msk->last_snd = ssk;
> -			break;
> +		if (msk->first && sk_stream_memory_free(msk->first)) {
> +			mptcp_subflow_set_scheduled(mptcp_subflow_ctx(msk->first), true);
> +			*err = 0;
> +			return msk->first;
> 		}
> -	}
> -
> -	return ssk;
> -}
> -
> -struct sock *mptcp_sched_get_retrans(struct mptcp_sock *msk)
> -{
> -	struct mptcp_sched_data data;
> -	struct sock *ssk = NULL;
> -	int i;
> -
> -	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 NULL;
> +	}
>
> -	if (!msk->sched)
> -		return mptcp_subflow_get_retrans(msk);
> +	if (!msk->sched) {
> +		ssk = mptcp_subflow_get_send(msk);
> +		if (!ssk)
> +			return NULL;
> +		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
> +		*err = 0;
> +		return ssk;
> +	}
>
> -	mptcp_sched_data_init(msk, true, &data);
> +	mptcp_sched_data_init(msk, false, &data);
> 	msk->sched->get_subflow(msk, &data);

Need to add *err = 0 here.

>
> -	for (i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
> -		if (data.contexts[i] && READ_ONCE(data.contexts[i]->scheduled)) {
> -			ssk = data.contexts[i]->tcp_sock;
> -			msk->last_snd = ssk;
> -			break;
> -		}
> -	}
> -
> 	return ssk;
> }
> -- 
> 2.34.1
>
>
>

--
Mat Martineau
Intel