1. Patchew
  2. MPTCP
  3. [PATCH mptcp-next v22 0/5] BPF redundant scheduler, part 2
  4. View patch

[PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper

Geliang Tang posted 5 patches 2 years ago
Maintainers: Mat Martineau <mathew.j.martineau@linux.intel.com>, Matthieu Baerts <matthieu.baerts@tessares.net>, "David S. Miller" <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, Andrii Nakryiko <andrii@kernel.org>, Mykola Lysenko <mykolal@fb.com>, Alexei Starovoitov <ast@kernel.org>, Daniel Borkmann <daniel@iogearbox.net>, Martin KaFai Lau <martin.lau@linux.dev>, Song Liu <song@kernel.org>, Yonghong Song <yhs@fb.com>, John Fastabend <john.fastabend@gmail.com>, KP Singh <kpsingh@kernel.org>, Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>, Jiri Olsa <jolsa@kernel.org>, Shuah Khan <shuah@kernel.org>
There is a newer version of this series
[PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper
Posted by Geliang Tang 2 years ago 
This patch adds the multiple subflows support for __mptcp_retrans(). Use
get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.

Check the subflow scheduled flags to test which subflow or subflows are
picked by the scheduler, use them to send data.

Move sock_owned_by_me() check and fallback check into get_retrans()
wrapper from mptcp_subflow_get_retrans().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 67 ++++++++++++++++++++++++++------------------
 net/mptcp/sched.c    |  6 ++++
 2 files changed, 45 insertions(+), 28 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index cef6086c7f40..7d7048b0774f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2254,11 +2254,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
 
-	sock_owned_by_me((const struct sock *)msk);
-
-	if (__mptcp_check_fallback(msk))
-		return NULL;
-
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2528,16 +2523,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 static void __mptcp_retrans(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
-	size_t copied = 0;
 	struct sock *ssk;
-	int ret;
+	int ret, err;
+	u16 len = 0;
 
 	mptcp_clean_una_wakeup(sk);
 
 	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_subflow_get_retrans(msk);
+	err = mptcp_sched_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2556,31 +2552,46 @@ static void __mptcp_retrans(struct sock *sk)
 		goto reset_timer;
 	}
 
-	if (!ssk)
+	if (err)
 		goto reset_timer;
 
-	lock_sock(ssk);
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled)) {
+			u16 copied = 0;
 
-	/* limit retransmission to the bytes already sent on some subflows */
-	info.sent = 0;
-	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
-	while (info.sent < info.limit) {
-		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
-		if (ret <= 0)
-			break;
+			ssk = mptcp_subflow_tcp_sock(subflow);
+			if (!ssk)
+				goto reset_timer;
 
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-		copied += ret;
-		info.sent += ret;
-	}
-	if (copied) {
-		dfrag->already_sent = max(dfrag->already_sent, info.sent);
-		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
-			 info.size_goal);
-		WRITE_ONCE(msk->allow_infinite_fallback, false);
-	}
+			lock_sock(ssk);
 
-	release_sock(ssk);
+			/* limit retransmission to the bytes already sent on some subflows */
+			info.sent = 0;
+			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
+								    dfrag->already_sent;
+			while (info.sent < info.limit) {
+				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+				if (ret <= 0)
+					break;
+
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+				copied += ret;
+				info.sent += ret;
+			}
+			if (copied) {
+				len = max(copied, len);
+				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+					 info.size_goal);
+				WRITE_ONCE(msk->allow_infinite_fallback, false);
+			}
+
+			release_sock(ssk);
+
+			msk->last_snd = ssk;
+			mptcp_subflow_set_scheduled(subflow, false);
+		}
+	}
+	dfrag->already_sent = max(dfrag->already_sent, len);
 
 reset_timer:
 	mptcp_check_and_set_pending(sk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 18518a81afb3..c55f2f1cb7ac 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -156,6 +156,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sched_data data;
 
+	sock_owned_by_me((const struct sock *)msk);
+
+	/* the following check is moved out of mptcp_subflow_get_retrans */
+	if (__mptcp_check_fallback(msk))
+		return -EINVAL;
+
 	mptcp_for_each_subflow(msk, subflow) {
 		if (READ_ONCE(subflow->scheduled))
 			return 0;
-- 
2.35.3
Re: [PATCH mptcp-next v22 3/5] mptcp: use get_retrans wrapper
Posted by Mat Martineau 2 years ago 
On Fri, 2 Dec 2022, Geliang Tang wrote:

> This patch adds the multiple subflows support for __mptcp_retrans(). Use
> get_retrans() wrapper instead of mptcp_subflow_get_retrans() in it.
>
> Check the subflow scheduled flags to test which subflow or subflows are
> picked by the scheduler, use them to send data.
>
> Move sock_owned_by_me() check and fallback check into get_retrans()
> wrapper from mptcp_subflow_get_retrans().
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 67 ++++++++++++++++++++++++++------------------
> net/mptcp/sched.c    |  6 ++++
> 2 files changed, 45 insertions(+), 28 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index cef6086c7f40..7d7048b0774f 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -2254,11 +2254,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
> 	struct mptcp_subflow_context *subflow;
> 	int min_stale_count = INT_MAX;
>
> -	sock_owned_by_me((const struct sock *)msk);
> -
> -	if (__mptcp_check_fallback(msk))
> -		return NULL;
> -
> 	mptcp_for_each_subflow(msk, subflow) {
> 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
>
> @@ -2528,16 +2523,17 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
> static void __mptcp_retrans(struct sock *sk)
> {
> 	struct mptcp_sock *msk = mptcp_sk(sk);
> +	struct mptcp_subflow_context *subflow;
> 	struct mptcp_sendmsg_info info = {};
> 	struct mptcp_data_frag *dfrag;
> -	size_t copied = 0;
> 	struct sock *ssk;
> -	int ret;
> +	int ret, err;
> +	u16 len = 0;
>
> 	mptcp_clean_una_wakeup(sk);
>
> 	/* first check ssk: need to kick "stale" logic */
> -	ssk = mptcp_subflow_get_retrans(msk);
> +	err = mptcp_sched_get_retrans(msk);
> 	dfrag = mptcp_rtx_head(sk);
> 	if (!dfrag) {
> 		if (mptcp_data_fin_enabled(msk)) {
> @@ -2556,31 +2552,46 @@ static void __mptcp_retrans(struct sock *sk)
> 		goto reset_timer;
> 	}
>
> -	if (!ssk)
> +	if (err)
> 		goto reset_timer;
>
> -	lock_sock(ssk);
> +	mptcp_for_each_subflow(msk, subflow) {
> +		if (READ_ONCE(subflow->scheduled)) {
> +			u16 copied = 0;
>
> -	/* limit retransmission to the bytes already sent on some subflows */
> -	info.sent = 0;
> -	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
> -	while (info.sent < info.limit) {
> -		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> -		if (ret <= 0)
> -			break;
> +			ssk = mptcp_subflow_tcp_sock(subflow);
> +			if (!ssk)
> +				goto reset_timer;
>
> -		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
> -		copied += ret;
> -		info.sent += ret;
> -	}
> -	if (copied) {
> -		dfrag->already_sent = max(dfrag->already_sent, info.sent);
> -		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> -			 info.size_goal);
> -		WRITE_ONCE(msk->allow_infinite_fallback, false);
> -	}
> +			lock_sock(ssk);
>
> -	release_sock(ssk);
> +			/* limit retransmission to the bytes already sent on some subflows */
> +			info.sent = 0;
> +			info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len :
> +								    dfrag->already_sent;
> +			while (info.sent < info.limit) {
> +				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> +				if (ret <= 0)
> +					break;
> +
> +				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
> +				copied += ret;
> +				info.sent += ret;
> +			}
> +			if (copied) {
> +				len = max(copied, len);
> +				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> +					 info.size_goal);
> +				WRITE_ONCE(msk->allow_infinite_fallback, false);
> +			}
> +
> +			release_sock(ssk);
> +
> +			msk->last_snd = ssk;
> +			mptcp_subflow_set_scheduled(subflow, false);

Like patch 2, the scheduled bit should always be cleared (on success and 
on error).

- Mat

> +		}
> +	}
> +	dfrag->already_sent = max(dfrag->already_sent, len);
>
> reset_timer:
> 	mptcp_check_and_set_pending(sk);
> diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
> index 18518a81afb3..c55f2f1cb7ac 100644
> --- a/net/mptcp/sched.c
> +++ b/net/mptcp/sched.c
> @@ -156,6 +156,12 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
> 	struct mptcp_subflow_context *subflow;
> 	struct mptcp_sched_data data;
>
> +	sock_owned_by_me((const struct sock *)msk);
> +
> +	/* the following check is moved out of mptcp_subflow_get_retrans */
> +	if (__mptcp_check_fallback(msk))
> +		return -EINVAL;
> +
> 	mptcp_for_each_subflow(msk, subflow) {
> 		if (READ_ONCE(subflow->scheduled))
> 			return 0;
> -- 
> 2.35.3
>
>
>

--
Mat Martineau
Intel

Patchew 2.1-devel-b67e4c2

© 2016 - 2024 Red Hat, Inc.