[PATCH mptcp-next v6 0/9] BPF redundant scheduler

[PATCH mptcp-next v6 0/9] BPF redundant scheduler

[Geliang Tang]

v6:
 - Add redundant flag for struct mptcp_sched_ops.
 - add a dedicated function __mptcp_subflows_push_pending() to deal with
   redundat subflows push pending.

v5:
 - address to Paolo's comment, keep the optimization to
mptcp_subflow_get_send() for the non eBPF case.
 - merge mptcp_sched_get_send() and __mptcp_sched_get_send() in v4 into one.
 - depends on "cleanups for bpf sched selftests".

v4:
 - small cleanups in patch 1, 2.
 - add TODO in patch 3.
 - rebase patch 5 on 'cleanups for bpf sched selftests'.

v3:
 - use new API.
 - fix the link failure tests issue mentioned in ("https://patchwork.kernel.org/project/mptcp/cover/cover.1653033459.git.geliang.tang@suse.com/").

v2:
 - add MPTCP_SUBFLOWS_MAX limit to avoid infinite loops when the
   scheduler always sets call_again to true.
 - track the largest copied amount.
 - deal with __mptcp_subflow_push_pending() and the retransmit loop.
 - depends on "BPF round-robin scheduler" v14.

v1:

Implements the redundant BPF MPTCP scheduler, which sends all packets
redundantly on all available subflows.

Geliang Tang (9):
  Squash to "mptcp: add struct mptcp_sched_ops"
  Squash to "mptcp: add get_subflow wrappers"
  mptcp: redundant subflows push pending
  mptcp: add sched_get_retrans wrapper
  mptcp: redundant subflows retrans support
  Squash to "bpf: Add bpf_mptcp_sched_ops"
  Squash to "selftests/bpf: Add mptcp sched structs"
  selftests/bpf: Add bpf_red scheduler
  selftests/bpf: Add bpf_red test

 include/net/mptcp.h                           |   1 +
 net/mptcp/bpf.c                               |   3 +
 net/mptcp/protocol.c                          | 122 ++++++++++++++----
 net/mptcp/protocol.h                          |   4 +-
 net/mptcp/sched.c                             |  62 +++++----
 net/mptcp/subflow.c                           |   1 -
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |   1 +
 .../testing/selftests/bpf/prog_tests/mptcp.c  |  34 +++++
 .../selftests/bpf/progs/mptcp_bpf_red.c       |  37 ++++++
 9 files changed, 215 insertions(+), 50 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c

-- 
2.35.3

[PATCH mptcp-next v6 1/9] Squash to "mptcp: add struct mptcp_sched_ops"

[Geliang Tang]

Add redundant flag for struct mptcp_sched_ops.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 7af7fd48acc7..5f34e32830ad 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -109,6 +109,7 @@ struct mptcp_sched_ops {
 			    struct mptcp_sched_data *data);
 
 	char			name[MPTCP_SCHED_NAME_MAX];
+	bool			redundant;
 	struct module		*owner;
 	struct list_head	list;
 
-- 
2.35.3

[PATCH mptcp-next v6 2/9] Squash to "mptcp: add get_subflow wrappers"

[Geliang Tang]

Please update the subject and commit log:

'''
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    | 67 ++++++++++++++++++--------------------------
 3 files changed, 38 insertions(+), 48 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 58427fabb061..ab42059143fa 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) {
@@ -2180,12 +2180,17 @@ 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);
 
@@ -2438,7 +2443,7 @@ 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)) {
@@ -3092,7 +3097,7 @@ 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 bef7dea9f358..a5a6e8aed5c7 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -633,9 +633,7 @@ 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..527ea07982c5 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -117,60 +117,47 @@ 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_subflow_context *subflow;
 	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;
+	mptcp_for_each_subflow(msk, subflow) {
+		if (READ_ONCE(subflow->scheduled)) {
+			/*
+			 * TODO: Redundant subflows are not supported in
+			 * __mptcp_subflow_push_pending() yet. Here's a
+			 * placeholder to pick the first subflow for the
+			 * redundant subflows case.
+			 */
+			ssk = subflow->tcp_sock;
+			*err = 0;
 			break;
 		}
 	}
-- 
2.35.3

[PATCH mptcp-next v6 3/9] mptcp: redundant subflows push pending

[Geliang Tang]

This patch adds the redundant subflows support for __mptcp_push_pending().
Use mptcp_sched_get_send() wrapper instead of mptcp_subflow_get_send()
in it.

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

Redundant subflows are not supported in __mptcp_subflow_push_pending()
yet. This patch adds a placeholder in mptcp_sched_get_send() to pick the
first subflow for the redundant subflows case.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 73 +++++++++++++++++++++++++++++++++++++++++---
 net/mptcp/subflow.c  |  1 -
 2 files changed, 68 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ab42059143fa..257b04315271 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1549,6 +1549,62 @@ void mptcp_check_and_set_pending(struct sock *sk)
 		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
 }
 
+static int __mptcp_subflows_push_pending(struct sock *sk, struct mptcp_sendmsg_info *info)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_data_frag *dfrag;
+	int len, copied = 0, err = 0;
+	struct sock *ssk = NULL;
+
+	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, max = 0;
+
+			mptcp_sched_get_send(msk, &err);
+			if (err)
+				goto out;
+
+			mptcp_for_each_subflow(msk, subflow) {
+				if (READ_ONCE(subflow->scheduled)) {
+					ssk = mptcp_subflow_tcp_sock(subflow);
+					if (!ssk)
+						goto out;
+
+					lock_sock(ssk);
+
+					ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info);
+					if (ret <= 0) {
+						mptcp_push_release(ssk, info);
+						goto out;
+					}
+
+					if (ret > max)
+						max = ret;
+
+					mptcp_push_release(ssk, info);
+
+					msk->last_snd = ssk;
+					mptcp_subflow_set_scheduled(subflow, false);
+				}
+			}
+
+			info->sent += max;
+			copied += max;
+			len -= max;
+
+			mptcp_update_post_push(msk, dfrag, max);
+		}
+		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+	}
+
+out:
+	return copied;
+}
+
 void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
 	struct sock *prev_ssk = NULL, *ssk = NULL;
@@ -1559,15 +1615,20 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	struct mptcp_data_frag *dfrag;
 	int len, copied = 0;
 
+	if (unlikely(msk->sched && msk->sched->redundant)) {
+		copied = __mptcp_subflows_push_pending(sk, &info);
+		goto out;
+	}
+
 	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;
+			int ret = 0, err = 0;
 
 			prev_ssk = ssk;
-			ssk = mptcp_subflow_get_send(msk);
+			ssk = mptcp_sched_get_send(msk, &err);
 
 			/* First check. If the ssk has changed since
 			 * the last round, release prev_ssk
@@ -1628,13 +1689,13 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 		info.limit = dfrag->data_len;
 		len = dfrag->data_len - dfrag->already_sent;
 		while (len > 0) {
-			int ret = 0;
+			int ret = 0, err = 0;
 
 			/* the caller already invoked the packet scheduler,
 			 * check for a different subflow usage only after
 			 * spooling the first chunk of data
 			 */
-			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
+			xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk), &err);
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
@@ -3093,11 +3154,13 @@ void __mptcp_data_acked(struct sock *sk)
 
 void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 {
+	int err = 0;
+
 	if (!mptcp_send_head(sk))
 		return;
 
 	if (!sock_owned_by_user(sk)) {
-		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
+		struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk), &err);
 
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 5351d54e514a..021b454640a3 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -881,7 +881,6 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
 				  subflow->map_data_len))) {
 		/* Mapping does covers past subflow data, invalid */
 		dbg_bad_map(subflow, ssn);
-		return false;
 	}
 	return true;
 }
-- 
2.35.3

[PATCH mptcp-next v6 4/9] mptcp: add sched_get_retrans wrapper

[Geliang Tang]

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

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

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c |  7 +------
 net/mptcp/protocol.h |  2 ++
 net/mptcp/sched.c    | 25 +++++++++++++++++++++++++
 3 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 257b04315271..3bb3445c1eaf 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2241,17 +2241,12 @@ 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);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a5a6e8aed5c7..c4ce576458a2 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -633,7 +633,9 @@ 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);
 struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err);
+int mptcp_sched_get_retrans(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 527ea07982c5..0ac80eb9a428 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -164,3 +164,28 @@ struct sock *mptcp_sched_get_send(struct mptcp_sock *msk, int *err)
 
 	return ssk;
 }
+
+int mptcp_sched_get_retrans(struct mptcp_sock *msk)
+{
+	struct mptcp_sched_data data;
+	struct sock *ssk = NULL;
+
+	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;
+
+	if (!msk->sched) {
+		ssk = mptcp_subflow_get_retrans(msk);
+		if (!ssk)
+			return -EINVAL;
+		mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+		return 0;
+	}
+
+	mptcp_sched_data_init(msk, true, &data);
+	msk->sched->get_subflow(msk, &data);
+
+	return 0;
+}
-- 
2.35.3

[PATCH mptcp-next v6 5/9] mptcp: redundant subflows retrans support

[Geliang Tang]

This patch adds the redundant subflows support for __mptcp_retrans(). In
it, use sched_get_retrans() wrapper instead of mptcp_subflow_get_retrans().

Iterate each subflow of msk, check the scheduled flag to test if it is
picked by the scheduler. If so, use it to send data.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 49 +++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 17 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3bb3445c1eaf..14d3637d1e88 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2490,16 +2490,14 @@ 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;
 
 	mptcp_clean_una_wakeup(sk);
 
-	/* first check ssk: need to kick "stale" logic */
-	ssk = mptcp_subflow_get_retrans(msk);
 	dfrag = mptcp_rtx_head(sk);
 	if (!dfrag) {
 		if (mptcp_data_fin_enabled(msk)) {
@@ -2518,32 +2516,49 @@ static void __mptcp_retrans(struct sock *sk)
 		goto reset_timer;
 	}
 
-	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;
+		int ret = 0, max = 0, err;
+
+		err = mptcp_sched_get_retrans(msk);
+		if (err)
+			goto reset_timer;
+
+		mptcp_for_each_subflow(msk, subflow) {
+			if (READ_ONCE(subflow->scheduled)) {
+				ssk = mptcp_subflow_tcp_sock(subflow);
+				if (!ssk)
+					goto reset_timer;
 
+				lock_sock(ssk);
+
+				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+				if (ret <= 0)
+					break;
+
+				if (ret > max)
+					max = ret;
+
+				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+					 info.size_goal);
+
+				release_sock(ssk);
+
+				msk->last_snd = ssk;
+				mptcp_subflow_set_scheduled(subflow, false);
+			}
+		}
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
-		copied += ret;
-		info.sent += ret;
+		copied += max;
+		info.sent += max;
 	}
 	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);
 	}
 
-	release_sock(ssk);
-
 reset_timer:
 	mptcp_check_and_set_pending(sk);
 
-- 
2.35.3

[PATCH mptcp-next v6 6/9] Squash to "bpf: Add bpf_mptcp_sched_ops"

[Geliang Tang]

Add access to redundant flag.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/bpf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index e86dff4272d5..66cb9d6051e1 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -125,6 +125,9 @@ static int bpf_mptcp_sched_init_member(const struct btf_type *t,
 		if (mptcp_sched_find(usched->name))
 			return -EEXIST;
 		return 1;
+	case offsetof(struct mptcp_sched_ops, redundant):
+		sched->redundant = usched->redundant;
+		return 1;
 	}
 
 	if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
-- 
2.35.3

[PATCH mptcp-next v6 7/9] Squash to "selftests/bpf: Add mptcp sched structs"

[Geliang Tang]

Add redundant flag for struct mptcp_sched_ops.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index c7d4a9a69cfc..3f570a4ffb12 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -245,6 +245,7 @@ struct mptcp_sched_data {
 
 struct mptcp_sched_ops {
 	char name[MPTCP_SCHED_NAME_MAX];
+	bool redundant;
 
 	void (*init)(const struct mptcp_sock *msk);
 	void (*release)(const struct mptcp_sock *msk);
-- 
2.35.3

[PATCH mptcp-next v6 8/9] selftests/bpf: Add bpf_red scheduler

[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       | 37 +++++++++++++++++++
 1 file changed, 37 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..8592c881471b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
@@ -0,0 +1,37 @@
+// 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_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);
+	}
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops red = {
+	.init		= (void *)mptcp_sched_red_init,
+	.release	= (void *)mptcp_sched_red_release,
+	.get_subflow	= (void *)bpf_red_get_subflow,
+	.redundant	= 1,
+	.name		= "bpf_red",
+};
-- 
2.35.3

[PATCH mptcp-next v6 9/9] selftests/bpf: Add bpf_red test

[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

Re: selftests/bpf: Add bpf_red test: Tests Results

[MPTCP CI]

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/6031967358550016
  - Summary: https://api.cirrus-ci.com/v1/artifact/task/6031967358550016/summary/summary.txt

- KVM Validation: debug:
  - Unstable: 2 failed test(s): selftest_diag selftest_mptcp_join 🔴:
  - Task: https://cirrus-ci.com/task/5469017405128704
  - Summary: https://api.cirrus-ci.com/v1/artifact/task/5469017405128704/summary/summary.txt

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/9e69e1319523


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)

Re: [PATCH mptcp-next v6 3/9] mptcp: redundant subflows push pending

[Mat Martineau]

On Fri, 10 Jun 2022, Geliang Tang wrote:

> This patch adds the redundant subflows support for __mptcp_push_pending().
> Use mptcp_sched_get_send() wrapper instead of mptcp_subflow_get_send()
> in it.
>
> Check the subflow scheduled flags to test which subflow or subflows are
> picked by the scheduler, use them to send data.
>
> Redundant subflows are not supported in __mptcp_subflow_push_pending()
> yet. This patch adds a placeholder in mptcp_sched_get_send() to pick the
> first subflow for the redundant subflows case.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 73 +++++++++++++++++++++++++++++++++++++++++---
> net/mptcp/subflow.c  |  1 -
> 2 files changed, 68 insertions(+), 6 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index ab42059143fa..257b04315271 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -1549,6 +1549,62 @@ void mptcp_check_and_set_pending(struct sock *sk)
> 		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
> }
>
> +static int __mptcp_subflows_push_pending(struct sock *sk, struct mptcp_sendmsg_info *info)

This separate function is fine for experimenting with the transmit loop. I 
do think it will be easier to try some different approaches to handling 
the redundant transmissions, but before upstreaming I hope we can reduce 
the duplicate code.

I suggest renaming this to __mptcp_redundant_push_pending() for now.

> +{
> +	struct mptcp_sock *msk = mptcp_sk(sk);
> +	struct mptcp_subflow_context *subflow;
> +	struct mptcp_data_frag *dfrag;
> +	int len, copied = 0, err = 0;
> +	struct sock *ssk = NULL;
> +
> +	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, max = 0;
> +
> +			mptcp_sched_get_send(msk, &err);
> +			if (err)
> +				goto out;
> +
> +			mptcp_for_each_subflow(msk, subflow) {
> +				if (READ_ONCE(subflow->scheduled)) {
> +					ssk = mptcp_subflow_tcp_sock(subflow);
> +					if (!ssk)
> +						goto out;

Wouldn't it be better to 'continue'? Other subflows might not have errors.

> +
> +					lock_sock(ssk);
> +
> +					ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info);
> +					if (ret <= 0) {
> +						mptcp_push_release(ssk, info);
> +						goto out;

Same here (to 'continue' instead), the transmit might succeed on other 
subflows.

> +					}
> +
> +					if (ret > max)
> +						max = ret;
> +
> +					mptcp_push_release(ssk, info);
> +
> +					msk->last_snd = ssk;
> +					mptcp_subflow_set_scheduled(subflow, false);
> +				}
> +			}
> +
> +			info->sent += max;
> +			copied += max;
> +			len -= max;
> +
> +			mptcp_update_post_push(msk, dfrag, max);
> +		}
> +		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
> +	}
> +
> +out:
> +	return copied;
> +}
> +
> void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> {
> 	struct sock *prev_ssk = NULL, *ssk = NULL;
> @@ -1559,15 +1615,20 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
> 	struct mptcp_data_frag *dfrag;
> 	int len, copied = 0;
>
> +	if (unlikely(msk->sched && msk->sched->redundant)) {
> +		copied = __mptcp_subflows_push_pending(sk, &info);
> +		goto out;
> +	}
> +
> 	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;
> +			int ret = 0, err = 0;
>
> 			prev_ssk = ssk;
> -			ssk = mptcp_subflow_get_send(msk);
> +			ssk = mptcp_sched_get_send(msk, &err);
>
> 			/* First check. If the ssk has changed since
> 			 * the last round, release prev_ssk
> @@ -1628,13 +1689,13 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
> 		info.limit = dfrag->data_len;
> 		len = dfrag->data_len - dfrag->already_sent;
> 		while (len > 0) {
> -			int ret = 0;
> +			int ret = 0, err = 0;
>
> 			/* the caller already invoked the packet scheduler,
> 			 * check for a different subflow usage only after
> 			 * spooling the first chunk of data
> 			 */
> -			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
> +			xmit_ssk = first ? ssk : mptcp_sched_get_send(mptcp_sk(sk), &err);
> 			if (!xmit_ssk)
> 				goto out;
> 			if (xmit_ssk != ssk) {
> @@ -3093,11 +3154,13 @@ void __mptcp_data_acked(struct sock *sk)
>
> void __mptcp_check_push(struct sock *sk, struct sock *ssk)
> {
> +	int err = 0;
> +
> 	if (!mptcp_send_head(sk))
> 		return;
>
> 	if (!sock_owned_by_user(sk)) {
> -		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
> +		struct sock *xmit_ssk = mptcp_sched_get_send(mptcp_sk(sk), &err);
>
> 		if (xmit_ssk == ssk)
> 			__mptcp_subflow_push_pending(sk, ssk);
> diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
> index 5351d54e514a..021b454640a3 100644
> --- a/net/mptcp/subflow.c
> +++ b/net/mptcp/subflow.c
> @@ -881,7 +881,6 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
> 				  subflow->map_data_len))) {
> 		/* Mapping does covers past subflow data, invalid */
> 		dbg_bad_map(subflow, ssn);
> -		return false;

Is this change intended?

> 	}
> 	return true;
> }
> -- 
> 2.35.3
>
>
>

--
Mat Martineau
Intel

Re: [PATCH mptcp-next v6 5/9] mptcp: redundant subflows retrans support

[Mat Martineau]

On Fri, 10 Jun 2022, Geliang Tang wrote:

> This patch adds the redundant subflows support for __mptcp_retrans(). In
> it, use sched_get_retrans() wrapper instead of mptcp_subflow_get_retrans().
>
> Iterate each subflow of msk, check the scheduled flag to test if it is
> picked by the scheduler. If so, use it to send data.
>
> Signed-off-by: Geliang Tang <geliang.tang@suse.com>
> ---
> net/mptcp/protocol.c | 49 +++++++++++++++++++++++++++++---------------
> 1 file changed, 32 insertions(+), 17 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 3bb3445c1eaf..14d3637d1e88 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -2490,16 +2490,14 @@ 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;
>
> 	mptcp_clean_una_wakeup(sk);
>
> -	/* first check ssk: need to kick "stale" logic */
> -	ssk = mptcp_subflow_get_retrans(msk);
> 	dfrag = mptcp_rtx_head(sk);
> 	if (!dfrag) {
> 		if (mptcp_data_fin_enabled(msk)) {
> @@ -2518,32 +2516,49 @@ static void __mptcp_retrans(struct sock *sk)
> 		goto reset_timer;
> 	}
>
> -	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;
> +		int ret = 0, max = 0, err;
> +
> +		err = mptcp_sched_get_retrans(msk);

The existing code calls the scheduler once and then loops to send data on 
the selected subflow.

I think the redundant scheduler can still work like that: call the 
scheduler once, then try to retransmit on each of the scheduled subflows. 
If we can reduce the number of calls to the scheduler, and also call 
mptcp_sendmsg_frag() multiple times on each subflow without releasing the 
lock, that's much more efficient.

> +		if (err)
> +			goto reset_timer;
> +
> +		mptcp_for_each_subflow(msk, subflow) {
> +			if (READ_ONCE(subflow->scheduled)) {
> +				ssk = mptcp_subflow_tcp_sock(subflow);
> +				if (!ssk)
> +					goto reset_timer;
>
> +				lock_sock(ssk);
> +
> +				ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
> +				if (ret <= 0)
> +					break;
> +
> +				if (ret > max)
> +					max = ret;
> +
> +				tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
> +					 info.size_goal);
> +
> +				release_sock(ssk);
> +
> +				msk->last_snd = ssk;
> +				mptcp_subflow_set_scheduled(subflow, false);
> +			}
> +		}
> 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
> -		copied += ret;
> -		info.sent += ret;
> +		copied += max;
> +		info.sent += max;
> 	}
> 	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);
> 	}
>
> -	release_sock(ssk);
> -
> reset_timer:
> 	mptcp_check_and_set_pending(sk);
>
> -- 
> 2.35.3
>
>
>

--
Mat Martineau
Intel