[PATCH mptcp-next v5 00/11] use bpf_iter in bpf schedulers

[PATCH mptcp-next v5 00/11] use bpf_iter in bpf schedulers

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

v5:
 - patch 2, drop mptcp_sock_type and mptcp_subflow_type.
 - patch 3, revert "bpf: Export more bpf_burst related functions"
 - patch 4, merge "bpf: Export more bpf_burst related functions" into it.

v4:
 - patch 2, a new cleanup for "bpf: Add bpf_mptcp_sched_ops".
 - patch 3 should be reverted.
 - patch 8, register kfunc_set.

v3:
 - rebased.
 - put the "drop has_bytes_sent" squash-to patch into this set.

v2:
 - update bpf_rr and bpf_burst

With the newly added mptcp_subflow bpf_iter, we can get rid of the
subflows array "contexts" in struct mptcp_sched_data. This set
uses bpf_for_each(mptcp_subflow) helper to update all the bpf
schedules:

        bpf_for_each(mptcp_subflow, subflow, msk) {
                ... ...
                mptcp_subflow_set_scheduled(subflow, true);
        }

Depends on:
 - "add mptcp_subflow bpf_iter" v9

Based-on: <cover.1728466623.git.tanggeliang@kylinos.cn>

Geliang Tang (11):
  Revert "mptcp: add sched_data helpers"
  Squash to "bpf: Add bpf_mptcp_sched_ops"
  Revert "bpf: Export more bpf_burst related functions"
  Squash to "bpf: Add bpf_mptcp_sched_kfunc_set"
  Squash to "selftests/bpf: Add bpf_first scheduler & test"
  Squash to "selftests/bpf: Add bpf_bkup scheduler & test"
  Squash to "selftests/bpf: Add bpf_rr scheduler & test"
  Squash to "selftests/bpf: Add bpf_red scheduler & test"
  Squash to "selftests/bpf: Add bpf_burst scheduler & test"
  mptcp: drop subflow contexts in mptcp_sched_data
  Squash to "selftests/bpf: Add bpf scheduler test" - drop
    has_bytes_sent

 include/net/mptcp.h                           |  2 -
 net/mptcp/bpf.c                               | 24 ++----
 net/mptcp/protocol.h                          |  3 -
 net/mptcp/sched.c                             | 22 ------
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 48 ++++++------
 tools/testing/selftests/bpf/progs/mptcp_bpf.h |  3 -
 .../selftests/bpf/progs/mptcp_bpf_bkup.c      | 16 +---
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 78 +++++++++----------
 .../selftests/bpf/progs/mptcp_bpf_bytes.c     | 39 ++++++++++
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  8 +-
 .../selftests/bpf/progs/mptcp_bpf_red.c       |  8 +-
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 24 +++---
 12 files changed, 133 insertions(+), 142 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_bytes.c

-- 
2.43.0

[PATCH mptcp-next v5 01/11] Revert "mptcp: add sched_data helpers"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Drop this patch.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c      |  8 --------
 net/mptcp/protocol.h |  2 --
 net/mptcp/sched.c    | 22 ----------------------
 3 files changed, 32 deletions(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 9b87eee13955..681a76f7c6a8 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -271,14 +271,6 @@ __bpf_kfunc void bpf_mptcp_sock_release(struct mptcp_sock *msk)
 	WARN_ON_ONCE(!sk || !refcount_dec_not_one(&sk->sk_refcnt));
 }
 
-__bpf_kfunc struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos)
-{
-	if (pos >= MPTCP_SUBFLOWS_MAX)
-		return NULL;
-	return data->contexts[pos];
-}
-
 __bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
 {
 	return tcp_rtx_queue_empty(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b963e68451b1..e774f28a6f8d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -723,8 +723,6 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent);
 u64 mptcp_wnd_end(const struct mptcp_sock *msk);
 void mptcp_set_timeout(struct sock *sk);
 bool bpf_mptcp_subflow_queues_empty(struct sock *sk);
-struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos);
 struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 5257bc6c8cd6..78ed508ebc1b 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -143,26 +143,6 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 	WRITE_ONCE(subflow->scheduled, scheduled);
 }
 
-static 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;
-	}
-	data->subflows = i;
-
-	for (; i < MPTCP_SUBFLOWS_MAX; i++)
-		data->contexts[i] = NULL;
-}
-
 int mptcp_sched_get_send(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -189,7 +169,6 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 	data.reinject = false;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
 		return mptcp_sched_default_get_subflow(msk, &data);
-	mptcp_sched_data_set_contexts(msk, &data);
 	return msk->sched->get_subflow(msk, &data);
 }
 
@@ -212,6 +191,5 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	data.reinject = true;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
 		return mptcp_sched_default_get_subflow(msk, &data);
-	mptcp_sched_data_set_contexts(msk, &data);
 	return msk->sched->get_subflow(msk, &data);
 }
-- 
2.43.0

[PATCH mptcp-next v5 02/11] Squash to "bpf: Add bpf_mptcp_sched_ops"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Please update the subject to

	bpf: Add mptcp packet scheduler struct_ops

Drop mptcp_sock_type and mptcp_subflow_type.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 681a76f7c6a8..3be587c7b21e 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -18,9 +18,10 @@
 
 #ifdef CONFIG_BPF_JIT
 static struct bpf_struct_ops bpf_mptcp_sched_ops;
-static const struct btf_type *mptcp_sock_type, *mptcp_subflow_type __read_mostly;
 static u32 mptcp_sock_id, mptcp_subflow_id;
 
+/* MPTCP BPF packet scheduler */
+
 static const struct bpf_func_proto *
 bpf_mptcp_sched_get_func_proto(enum bpf_func_id func_id,
 			       const struct bpf_prog *prog)
@@ -43,12 +44,10 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,
 					     const struct bpf_reg_state *reg,
 					     int off, int size)
 {
-	const struct btf_type *t;
+	u32 id = reg->btf_id;
 	size_t end;
 
-	t = btf_type_by_id(reg->btf, reg->btf_id);
-
-	if (t == mptcp_sock_type) {
+	if (id == mptcp_sock_id) {
 		switch (off) {
 		case offsetof(struct mptcp_sock, snd_burst):
 			end = offsetofend(struct mptcp_sock, snd_burst);
@@ -58,7 +57,7 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,
 				off);
 			return -EACCES;
 		}
-	} else if (t == mptcp_subflow_type) {
+	} else if (id == mptcp_subflow_id) {
 		switch (off) {
 		case offsetof(struct mptcp_subflow_context, avg_pacing_rate):
 			end = offsetofend(struct mptcp_subflow_context, avg_pacing_rate);
@@ -75,7 +74,7 @@ static int bpf_mptcp_sched_btf_struct_access(struct bpf_verifier_log *log,
 
 	if (off + size > end) {
 		bpf_log(log, "access beyond %s at off %u size %u ended at %zu",
-			t == mptcp_sock_type ? "mptcp_sock" : "mptcp_subflow_context",
+			id == mptcp_sock_id ? "mptcp_sock" : "mptcp_subflow_context",
 			off, size, end);
 		return -EACCES;
 	}
@@ -140,14 +139,12 @@ static int bpf_mptcp_sched_init(struct btf *btf)
 	if (type_id < 0)
 		return -EINVAL;
 	mptcp_sock_id = type_id;
-	mptcp_sock_type = btf_type_by_id(btf, mptcp_sock_id);
 
 	type_id = btf_find_by_name_kind(btf, "mptcp_subflow_context",
 					BTF_KIND_STRUCT);
 	if (type_id < 0)
 		return -EINVAL;
 	mptcp_subflow_id = type_id;
-	mptcp_subflow_type = btf_type_by_id(btf, mptcp_subflow_id);
 
 	return 0;
 }
-- 
2.43.0

[PATCH mptcp-next v5 03/11] Revert "bpf: Export more bpf_burst related functions"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

This reverts commit d0f5ca7a98fea075d60fb88f1c2b29a6f5f04d68.
---
 net/mptcp/bpf.c      | 10 ----------
 net/mptcp/protocol.c |  4 ++--
 net/mptcp/protocol.h |  3 ---
 3 files changed, 2 insertions(+), 15 deletions(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 3be587c7b21e..627839383b29 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -268,11 +268,6 @@ __bpf_kfunc void bpf_mptcp_sock_release(struct mptcp_sock *msk)
 	WARN_ON_ONCE(!sk || !refcount_dec_not_one(&sk->sk_refcnt));
 }
 
-__bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
-{
-	return tcp_rtx_queue_empty(sk);
-}
-
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(bpf_mptcp_common_kfunc_ids)
@@ -294,11 +289,6 @@ static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
 
 BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx_by_pos)
-BTF_ID_FLAGS(func, mptcp_set_timeout)
-BTF_ID_FLAGS(func, mptcp_wnd_end)
-BTF_ID_FLAGS(func, tcp_stream_memory_free)
-BTF_ID_FLAGS(func, bpf_mptcp_subflow_queues_empty)
-BTF_ID_FLAGS(func, mptcp_pm_subflow_chk_stale)
 BTF_KFUNCS_END(bpf_mptcp_sched_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_mptcp_sched_kfunc_set = {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e420ce9bbfb6..e978e05ec8d1 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
 
 /* Returns end sequence number of the receiver's advertised window */
-u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->wnd_end);
 }
@@ -489,7 +489,7 @@ static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subfl
 	       inet_csk(ssk)->icsk_timeout - jiffies : 0;
 }
 
-void mptcp_set_timeout(struct sock *sk)
+static void mptcp_set_timeout(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	long tout = 0;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e774f28a6f8d..a93e661ef5c4 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -720,9 +720,6 @@ void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
-u64 mptcp_wnd_end(const struct mptcp_sock *msk);
-void mptcp_set_timeout(struct sock *sk);
-bool bpf_mptcp_subflow_queues_empty(struct sock *sk);
 struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
-- 
2.43.0

[PATCH mptcp-next v5 04/11] Squash to "bpf: Add bpf_mptcp_sched_kfunc_set"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Please update the subject to

	"bpf: Export mptcp packet scheduler helpers"

Remove bpf_mptcp_subflow_ctx_by_pos from BPF kfunc set.
Merge "bpf: Export more bpf_burst related functions" into this patch.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c      | 11 ++++++++++-
 net/mptcp/protocol.c |  4 ++--
 net/mptcp/protocol.h |  2 ++
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 627839383b29..38034d3f28f8 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -268,6 +268,11 @@ __bpf_kfunc void bpf_mptcp_sock_release(struct mptcp_sock *msk)
 	WARN_ON_ONCE(!sk || !refcount_dec_not_one(&sk->sk_refcnt));
 }
 
+__bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
+{
+	return tcp_rtx_queue_empty(sk);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(bpf_mptcp_common_kfunc_ids)
@@ -288,7 +293,11 @@ static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
 };
 
 BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)
-BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx_by_pos)
+BTF_ID_FLAGS(func, mptcp_set_timeout)
+BTF_ID_FLAGS(func, mptcp_wnd_end)
+BTF_ID_FLAGS(func, tcp_stream_memory_free)
+BTF_ID_FLAGS(func, bpf_mptcp_subflow_queues_empty)
+BTF_ID_FLAGS(func, mptcp_pm_subflow_chk_stale)
 BTF_KFUNCS_END(bpf_mptcp_sched_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_mptcp_sched_kfunc_set = {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e978e05ec8d1..e420ce9bbfb6 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
 
 /* Returns end sequence number of the receiver's advertised window */
-static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->wnd_end);
 }
@@ -489,7 +489,7 @@ static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subfl
 	       inet_csk(ssk)->icsk_timeout - jiffies : 0;
 }
 
-static void mptcp_set_timeout(struct sock *sk)
+void mptcp_set_timeout(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	long tout = 0;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a93e661ef5c4..7848a1989d17 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -720,6 +720,8 @@ void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
+u64 mptcp_wnd_end(const struct mptcp_sock *msk);
+void mptcp_set_timeout(struct sock *sk);
 struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
-- 
2.43.0

[PATCH mptcp-next v5 05/11] Squash to "selftests/bpf: Add bpf_first scheduler & test"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the newly added bpf_for_each() helper to walk the conn_list.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/bpf/progs/mptcp_bpf.h       | 3 ---
 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c | 8 +++++++-
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
index e18796361394..260bc239655a 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf.h
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -55,7 +55,4 @@ bpf_mptcp_subflow_ctx(const struct sock *sk) __ksym;
 extern struct sock *
 bpf_mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) __ksym;
 
-extern struct mptcp_subflow_context *
-bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos) __ksym;
-
 #endif
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
index d57399b407a7..807685b3ab97 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
@@ -20,7 +20,13 @@ SEC("struct_ops")
 int BPF_PROG(bpf_first_get_subflow, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, 0), true);
+	struct mptcp_subflow_context *subflow;
+
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		mptcp_subflow_set_scheduled(subflow, true);
+		break;
+	}
+
 	return 0;
 }
 
-- 
2.43.0

[PATCH mptcp-next v5 06/11] Squash to "selftests/bpf: Add bpf_bkup scheduler & test"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the newly added bpf_for_each() helper to walk the conn_list.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/bpf/progs/mptcp_bpf_bkup.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
index 296f0318d843..70c3a69d4a47 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
@@ -20,26 +20,16 @@ SEC("struct_ops")
 int BPF_PROG(bpf_bkup_get_subflow, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	int nr = -1;
-
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		struct mptcp_subflow_context *subflow;
-
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
+	struct mptcp_subflow_context *subflow;
 
+	bpf_for_each(mptcp_subflow, subflow, msk) {
 		if (!BPF_CORE_READ_BITFIELD_PROBED(subflow, backup) ||
 		    !BPF_CORE_READ_BITFIELD_PROBED(subflow, request_bkup)) {
-			nr = i;
+			mptcp_subflow_set_scheduled(subflow, true);
 			break;
 		}
 	}
 
-	if (nr != -1) {
-		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, nr), true);
-		return -1;
-	}
 	return 0;
 }
 
-- 
2.43.0

[PATCH mptcp-next v5 07/11] Squash to "selftests/bpf: Add bpf_rr scheduler & test"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the newly added bpf_for_each() helper to walk the conn_list.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 24 ++++++++-----------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
index 638ea6aa63b7..0e806caa10df 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
@@ -34,10 +34,9 @@ SEC("struct_ops")
 int BPF_PROG(bpf_rr_get_subflow, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	struct mptcp_subflow_context *subflow;
+	struct mptcp_subflow_context *subflow, *next;
 	struct mptcp_rr_storage *ptr;
 	struct sock *last_snd = NULL;
-	int nr = 0;
 
 	ptr = bpf_sk_storage_get(&mptcp_rr_map, msk, 0,
 				 BPF_LOCAL_STORAGE_GET_F_CREATE);
@@ -45,27 +44,24 @@ int BPF_PROG(bpf_rr_get_subflow, struct mptcp_sock *msk,
 		return -1;
 
 	last_snd = ptr->last_snd;
+	next = bpf_mptcp_subflow_ctx(msk->first);
 
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!last_snd || !subflow)
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		if (!last_snd)
 			break;
 
-		if (mptcp_subflow_tcp_sock(subflow) == last_snd) {
-			if (i + 1 == MPTCP_SUBFLOWS_MAX ||
-			    !bpf_mptcp_subflow_ctx_by_pos(data, i + 1))
+		if (bpf_mptcp_subflow_tcp_sock(subflow) == last_snd) {
+			subflow = bpf_iter_mptcp_subflow_next(&___it);
+			if (!subflow)
 				break;
 
-			nr = i + 1;
+			next = subflow;
 			break;
 		}
 	}
 
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, nr);
-	if (!subflow)
-		return -1;
-	mptcp_subflow_set_scheduled(subflow, true);
-	ptr->last_snd = mptcp_subflow_tcp_sock(subflow);
+	mptcp_subflow_set_scheduled(next, true);
+	ptr->last_snd = bpf_mptcp_subflow_tcp_sock(next);
 	return 0;
 }
 
-- 
2.43.0

[PATCH mptcp-next v5 08/11] Squash to "selftests/bpf: Add bpf_red scheduler & test"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the newly added bpf_for_each() helper to walk the conn_list.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
index cc0aab732fc4..ce19d604b898 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
@@ -20,12 +20,10 @@ SEC("struct_ops")
 int BPF_PROG(bpf_red_get_subflow, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		if (!bpf_mptcp_subflow_ctx_by_pos(data, i))
-			break;
+	struct mptcp_subflow_context *subflow;
 
-		mptcp_subflow_set_scheduled(bpf_mptcp_subflow_ctx_by_pos(data, i), true);
-	}
+	bpf_for_each(mptcp_subflow, subflow, msk)
+		mptcp_subflow_set_scheduled(subflow, true);
 
 	return 0;
 }
-- 
2.43.0

[PATCH mptcp-next v5 09/11] Squash to "selftests/bpf: Add bpf_burst scheduler & test"

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Use the newly added bpf_for_each() helper to walk the conn_list.

Drop mptcp_subflow_active declaration.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 78 +++++++++----------
 1 file changed, 39 insertions(+), 39 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
index eb21119aa8f7..87b6d9dc876b 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
@@ -11,22 +11,21 @@ char _license[] SEC("license") = "GPL";
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
+#define SSK_MODE_ACTIVE	0
+#define SSK_MODE_BACKUP	1
+#define SSK_MODE_MAX	2
+
 struct bpf_subflow_send_info {
 	__u8 subflow_id;
 	__u64 linger_time;
 };
 
-extern bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) __ksym;
 extern void mptcp_set_timeout(struct sock *sk) __ksym;
 extern __u64 mptcp_wnd_end(const struct mptcp_sock *msk) __ksym;
 extern bool tcp_stream_memory_free(const struct sock *sk, int wake) __ksym;
 extern bool bpf_mptcp_subflow_queues_empty(struct sock *sk) __ksym;
 extern void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) __ksym;
 
-#define SSK_MODE_ACTIVE	0
-#define SSK_MODE_BACKUP	1
-#define SSK_MODE_MAX	2
-
 static __always_inline __u64 div_u64(__u64 dividend, __u32 divisor)
 {
 	return dividend / divisor;
@@ -57,6 +56,19 @@ static __always_inline bool sk_stream_memory_free(const struct sock *sk)
 	return __sk_stream_memory_free(sk, 0);
 }
 
+static struct mptcp_subflow_context *
+mptcp_lookup_subflow_by_id(struct mptcp_sock *msk, unsigned int id)
+{
+	struct mptcp_subflow_context *subflow;
+
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		if (subflow->subflow_id == id)
+			return subflow;
+	}
+
+	return NULL;
+}
+
 SEC("struct_ops")
 void BPF_PROG(mptcp_sched_burst_init, struct mptcp_sock *msk)
 {
@@ -67,8 +79,7 @@ void BPF_PROG(mptcp_sched_burst_release, struct mptcp_sock *msk)
 {
 }
 
-static int bpf_burst_get_send(struct mptcp_sock *msk,
-			      struct mptcp_sched_data *data)
+static int bpf_burst_get_send(struct mptcp_sock *msk)
 {
 	struct bpf_subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
@@ -84,16 +95,10 @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 		send_info[i].linger_time = -1;
 	}
 
-	for (i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		bool backup;
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		bool backup = subflow->backup || subflow->request_bkup;
 
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
-
-		backup = subflow->backup || subflow->request_bkup;
-
-		ssk = mptcp_subflow_tcp_sock(subflow);
+		ssk = bpf_mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
@@ -109,7 +114,7 @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 
 		linger_time = div_u64((__u64)ssk->sk_wmem_queued << 32, pace);
 		if (linger_time < send_info[backup].linger_time) {
-			send_info[backup].subflow_id = i;
+			send_info[backup].subflow_id = subflow->subflow_id;
 			send_info[backup].linger_time = linger_time;
 		}
 	}
@@ -119,10 +124,10 @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 	if (!nr_active)
 		send_info[SSK_MODE_ACTIVE].subflow_id = send_info[SSK_MODE_BACKUP].subflow_id;
 
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, send_info[SSK_MODE_ACTIVE].subflow_id);
+	subflow = mptcp_lookup_subflow_by_id(msk, send_info[SSK_MODE_ACTIVE].subflow_id);
 	if (!subflow)
 		return -1;
-	ssk = mptcp_subflow_tcp_sock(subflow);
+	ssk = bpf_mptcp_subflow_tcp_sock(subflow);
 	if (!ssk || !sk_stream_memory_free(ssk))
 		return -1;
 
@@ -141,23 +146,18 @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 	return 0;
 }
 
-static int bpf_burst_get_retrans(struct mptcp_sock *msk,
-				 struct mptcp_sched_data *data)
+static int bpf_burst_get_retrans(struct mptcp_sock *msk)
 {
-	int backup = MPTCP_SUBFLOWS_MAX, pick = MPTCP_SUBFLOWS_MAX, subflow_id;
+	struct sock *backup = NULL, *pick = NULL;
 	struct mptcp_subflow_context *subflow;
 	int min_stale_count = INT_MAX;
-	struct sock *ssk;
 
-	for (int i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		struct sock *ssk = bpf_mptcp_subflow_tcp_sock(subflow);
 
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
-		ssk = mptcp_subflow_tcp_sock(subflow);
 		/* still data outstanding at TCP level? skip this */
 		if (!tcp_rtx_and_write_queues_empty(ssk)) {
 			mptcp_pm_subflow_chk_stale(msk, ssk);
@@ -166,23 +166,23 @@ static int bpf_burst_get_retrans(struct mptcp_sock *msk,
 		}
 
 		if (subflow->backup || subflow->request_bkup) {
-			if (backup == MPTCP_SUBFLOWS_MAX)
-				backup = i;
+			if (!backup)
+				backup = ssk;
 			continue;
 		}
 
-		if (pick == MPTCP_SUBFLOWS_MAX)
-			pick = i;
+		if (!pick)
+			pick = ssk;
 	}
 
-	if (pick < MPTCP_SUBFLOWS_MAX) {
-		subflow_id = pick;
+	if (pick)
 		goto out;
-	}
-	subflow_id = min_stale_count > 1 ? backup : MPTCP_SUBFLOWS_MAX;
+	pick = min_stale_count > 1 ? backup : NULL;
 
 out:
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, subflow_id);
+	if (!pick)
+		return -1;
+	subflow = bpf_mptcp_subflow_ctx(pick);
 	if (!subflow)
 		return -1;
 	mptcp_subflow_set_scheduled(subflow, true);
@@ -194,8 +194,8 @@ int BPF_PROG(bpf_burst_get_subflow, struct mptcp_sock *msk,
 	     struct mptcp_sched_data *data)
 {
 	if (data->reinject)
-		return bpf_burst_get_retrans(msk, data);
-	return bpf_burst_get_send(msk, data);
+		return bpf_burst_get_retrans(msk);
+	return bpf_burst_get_send(msk);
 }
 
 SEC(".struct_ops")
-- 
2.43.0

[PATCH mptcp-next v5 10/11] mptcp: drop subflow contexts in mptcp_sched_data

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

The mptcp_subflow bpf_iter is added now, it's better to use the helper
bpf_for_each(mptcp_subflow) to traverse all subflows on the conn_list of
an MPTCP socket and then call kfunc to modify the fields of each subflow
in the WIP MPTCP BPF packet scheduler examples, instead of converting them
to a fixed array. With this helper, we can get rid of this subflow array
"contexts" and the size of it "subflows" in struct mptcp_sched_data.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/net/mptcp.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 814b5f2e3ed5..84d67947a517 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -104,8 +104,6 @@ struct mptcp_out_options {
 
 struct mptcp_sched_data {
 	bool	reinject;
-	u8	subflows;
-	struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX];
 };
 
 struct mptcp_sched_ops {
-- 
2.43.0

[PATCH mptcp-next v5 11/11] Squash to "selftests/bpf: Add bpf scheduler test" - drop has_bytes_sent

[Geliang Tang]

From: Geliang Tang <tanggeliang@kylinos.cn>

Drop ss_search() and has_bytes_sent(), add a new bpf program to check
the bytes_sent.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 48 ++++++++++---------
 .../selftests/bpf/progs/mptcp_bpf_bytes.c     | 39 +++++++++++++++
 2 files changed, 65 insertions(+), 22 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_bytes.c

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 2738951842f6..cb0511e62df8 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -12,6 +12,7 @@
 #include "mptcpify.skel.h"
 #include "mptcp_subflow.skel.h"
 #include "mptcp_bpf_iters_subflow.skel.h"
+#include "mptcp_bpf_bytes.skel.h"
 #include "mptcp_bpf_first.skel.h"
 #include "mptcp_bpf_bkup.skel.h"
 #include "mptcp_bpf_rr.skel.h"
@@ -603,56 +604,59 @@ static struct nstoken *sched_init(char *flags, char *sched)
 	return NULL;
 }
 
-static int ss_search(char *src, char *dst, char *port, char *keyword)
-{
-	return SYS_NOFAIL("ip netns exec %s ss -enita src %s dst %s %s %d | grep -q '%s'",
-			  NS_TEST, src, dst, port, PORT_1, keyword);
-}
-
-static int has_bytes_sent(char *dst)
-{
-	return ss_search(ADDR_1, dst, "sport", "bytes_sent:");
-}
-
 static void send_data_and_verify(char *sched, bool addr1, bool addr2)
 {
+	int server_fd, client_fd, err;
+	struct mptcp_bpf_bytes *skel;
 	struct timespec start, end;
-	int server_fd, client_fd;
 	unsigned int delta_ms;
 
+	skel = mptcp_bpf_bytes__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load: bytes"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	err = mptcp_bpf_bytes__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach: bytes"))
+		goto skel_destroy;
+
 	server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0);
 	if (!ASSERT_OK_FD(server_fd, "start_mptcp_server"))
-		return;
+		goto skel_destroy;
 
 	client_fd = connect_to_fd(server_fd, 0);
 	if (!ASSERT_OK_FD(client_fd, "connect_to_fd"))
-		goto fail;
+		goto close_server;
 
 	if (clock_gettime(CLOCK_MONOTONIC, &start) < 0)
-		goto fail;
+		goto close_client;
 
 	if (!ASSERT_OK(send_recv_data(server_fd, client_fd, total_bytes),
 		       "send_recv_data"))
-		goto fail;
+		goto close_client;
 
 	if (clock_gettime(CLOCK_MONOTONIC, &end) < 0)
-		goto fail;
+		goto close_client;
 
 	delta_ms = (end.tv_sec - start.tv_sec) * 1000 + (end.tv_nsec - start.tv_nsec) / 1000000;
 	printf("%s: %u ms\n", sched, delta_ms);
 
 	if (addr1)
-		CHECK(has_bytes_sent(ADDR_1), sched, "should have bytes_sent on addr1\n");
+		ASSERT_GT(skel->bss->bytes_sent_1, 0, "should have bytes_sent on addr1");
 	else
-		CHECK(!has_bytes_sent(ADDR_1), sched, "shouldn't have bytes_sent on addr1\n");
+		ASSERT_EQ(skel->bss->bytes_sent_1, 0, "shouldn't have bytes_sent on addr1");
 	if (addr2)
-		CHECK(has_bytes_sent(ADDR_2), sched, "should have bytes_sent on addr2\n");
+		ASSERT_GT(skel->bss->bytes_sent_2, 0, "should have bytes_sent on addr2");
 	else
-		CHECK(!has_bytes_sent(ADDR_2), sched, "shouldn't have bytes_sent on addr2\n");
+		ASSERT_EQ(skel->bss->bytes_sent_2, 0, "shouldn't have bytes_sent on addr2");
 
+close_client:
 	close(client_fd);
-fail:
+close_server:
 	close(server_fd);
+skel_destroy:
+	mptcp_bpf_bytes__destroy(skel);
 }
 
 static void test_default(void)
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_bytes.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_bytes.c
new file mode 100644
index 000000000000..95770b0ebcf0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_bytes.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Kylin Software */
+
+/* vmlinux.h, bpf_helpers.h and other 'define' */
+#include "bpf_tracing_net.h"
+#include "mptcp_bpf.h"
+
+char _license[] SEC("license") = "GPL";
+u64 bytes_sent_1 = 0;
+u64 bytes_sent_2 = 0;
+int pid;
+
+SEC("fexit/mptcp_sched_get_send")
+int BPF_PROG(trace_mptcp_sched_get_send, struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	if (!msk->pm.server_side)
+		return 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct tcp_sock *tp;
+		struct sock *ssk;
+
+		subflow = bpf_core_cast(subflow, struct mptcp_subflow_context);
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		tp = bpf_core_cast(ssk, struct tcp_sock);
+
+		if (subflow->subflow_id == 1)
+			bytes_sent_1 = tp->bytes_sent;
+		else if (subflow->subflow_id == 2)
+			bytes_sent_2 = tp->bytes_sent;
+	}
+
+	return 0;
+}
-- 
2.43.0