Series comparison

From: Geliang Tang <tanggeliang@kylinos.cn>

v7:
 - move cleanup patches out of this set.
 - rebased.

v6:
 - rebased to "add mptcp_subflow bpf_iter" v10

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);
        }

Geliang Tang (5):
  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"
  Squash to "selftests/bpf: Add bpf_first scheduler & test"

tools/testing/selftests/bpf/progs/mptcp_bpf.h |  3 -
 .../selftests/bpf/progs/mptcp_bpf_bkup.c      | 18 +----
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 79 ++++++++++---------
 .../selftests/bpf/progs/mptcp_bpf_first.c     | 10 ++-
 .../selftests/bpf/progs/mptcp_bpf_red.c       | 10 +--
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 26 +++---
 6 files changed, 67 insertions(+), 79 deletions(-)

-- 
2.45.2

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_bkup.c       | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_bkup.c
@@ -XXX,XX +XXX,XX @@ 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;
 }
 
-SEC(".struct_ops")
+SEC(".struct_ops.link")
 struct mptcp_sched_ops bkup = {
 	.init		= (void *)mptcp_sched_bkup_init,
 	.release	= (void *)mptcp_sched_bkup_release,
-- 
2.45.2

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        | 26 ++++++++-----------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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;
 }
 
-SEC(".struct_ops")
+SEC(".struct_ops.link")
 struct mptcp_sched_ops rr = {
 	.init		= (void *)mptcp_sched_rr_init,
 	.release	= (void *)mptcp_sched_rr_release,
-- 
2.45.2

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 | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_red.c
@@ -XXX,XX +XXX,XX @@ 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;
 }
 
-SEC(".struct_ops")
+SEC(".struct_ops.link")
 struct mptcp_sched_ops red = {
 	.init		= (void *)mptcp_sched_red_init,
 	.release	= (void *)mptcp_sched_red_release,
-- 
2.45.2

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_burst.c     | 79 ++++++++++---------
 1 file changed, 40 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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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)
 {
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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;
 
@@ -XXX,XX +XXX,XX @@ 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;
 		}
 	}
@@ -XXX,XX +XXX,XX @@ 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;
 
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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")
+SEC(".struct_ops.link")
 struct mptcp_sched_ops burst = {
 	.init		= (void *)mptcp_sched_burst_init,
 	.release	= (void *)mptcp_sched_burst_release,
-- 
2.45.2

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 | 10 ++++++++--
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf.h
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -XXX,XX +XXX,XX @@ extern bool bpf_ipv6_addr_v4mapped(const struct mptcp_addr_info *a) __ksym;
 extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 					bool scheduled) __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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
@@ -XXX,XX +XXX,XX @@ 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;
 }
 
-SEC(".struct_ops")
+SEC(".struct_ops.link")
 struct mptcp_sched_ops first = {
 	.init		= (void *)mptcp_sched_first_init,
 	.release	= (void *)mptcp_sched_first_release,
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

v10:
 - drop mptcp_subflow_set_scheduled() helper and WRITE_ONCE() in BPF.
 - add new bpf helper bpf_mptcp_send_info_to_ssk() for burst scheduler.

v9:
 - merge 'Fixes for "use bpf_iter in bpf schedulers" v8' into this set.
 - rebased on "add netns helpers" v4

v8:
 - address Mat's comments in v7.
 - move sk_stream_memory_free check inside bpf_for_each() loop.
 - implement mptcp_subflow_set_scheduled helper in BPF.
 - add cleanup patches into this set again.

v7:
 - move cleanup patches out of this set.
 - rebased.

v6:
 - rebased to "add mptcp_subflow bpf_iter" v10

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

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

Geliang Tang (9):
  bpf: Add bpf_mptcp_send_info_to_ssk
  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"
  Squash to "selftests/bpf: Add bpf_first scheduler & test"
  Revert "mptcp: add sched_data helpers"
  Squash to "bpf: Export mptcp packet scheduler helpers"
  mptcp: drop subflow contexts in mptcp_sched_data

-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

Burst scheduler needs to allocate an array of struct subflow_send_info
on the stack and then select a subflow to send data. In order to implement
burst scheduler in BPF, this patch adds a new bpf_mptcp_send_info_to_ssk()
helper to get ssk from subflow_send_info and sets its parameter type as
ARG_PTR_TO_STACK.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/uapi/linux/bpf.h       |  7 +++++++
 net/mptcp/bpf.c                | 22 ++++++++++++++++++++++
 net/mptcp/protocol.c           |  5 -----
 net/mptcp/protocol.h           |  5 +++++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 5 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index XXXXXXX..XXXXXXX 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -XXX,XX +XXX,XX @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * void *bpf_mptcp_send_info_to_ssk(void *info)
+ *	Description
+ *		Dynamically cast a *info* pointer to a *sock* pointer.
+ *	Return
+ *		*info* if casting is valid, or **NULL** otherwise.
  */
 #define ___BPF_FUNC_MAPPER(FN, ctx...)			\
 	FN(unspec, 0, ##ctx)				\
@@ -XXX,XX +XXX,XX @@ union bpf_attr {
 	FN(user_ringbuf_drain, 209, ##ctx)		\
 	FN(cgrp_storage_get, 210, ##ctx)		\
 	FN(cgrp_storage_delete, 211, ##ctx)		\
+	FN(mptcp_send_info_to_ssk, 212, ##ctx)			\
 	/* */
 
 /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -XXX,XX +XXX,XX @@ 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;
 
+BPF_CALL_1(bpf_mptcp_send_info_to_ssk, struct subflow_send_info *, info)
+{
+	BTF_TYPE_EMIT(struct sock);
+
+	if (info && info->ssk && sk_fullsock(info->ssk) &&
+	    info->ssk->sk_protocol == IPPROTO_TCP &&
+	    sk_is_mptcp(info->ssk))
+		return (unsigned long)info->ssk;
+
+	return (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_mptcp_send_info_to_ssk_proto = {
+	.func		= bpf_mptcp_send_info_to_ssk,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_STACK,
+	.ret_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+};
+
 static const struct bpf_func_proto *
 bpf_mptcp_sched_get_func_proto(enum bpf_func_id func_id,
 			       const struct bpf_prog *prog)
@@ -XXX,XX +XXX,XX @@ bpf_mptcp_sched_get_func_proto(enum bpf_func_id func_id,
 		return &bpf_skc_to_tcp6_sock_proto;
 	case BPF_FUNC_skc_to_tcp_sock:
 		return &bpf_skc_to_tcp_sock_proto;
+	case BPF_FUNC_mptcp_send_info_to_ssk:
+		return &bpf_mptcp_send_info_to_ssk_proto;
 	default:
 		return bpf_base_func_proto(func_id, prog);
 	}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 					 sizeof(struct ipv6hdr) - \
 					 sizeof(struct frag_hdr))
 
-struct subflow_send_info {
-	struct sock *ssk;
-	u64 linger_time;
-};
-
 void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow)
 {
 	if (!subflow->stale)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
 	WRITE_ONCE(subflow->local_id, -1);
 }
 
+struct subflow_send_info {
+	struct sock *ssk;
+	u64 linger_time;
+};
+
 /* Convert reset reasons in MPTCP to enum sk_rst_reason type */
 static inline enum sk_rst_reason
 sk_rst_convert_mptcp_reason(u32 reason)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index XXXXXXX..XXXXXXX 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -XXX,XX +XXX,XX @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * void *bpf_mptcp_send_info_to_ssk(void *info)
+ *	Description
+ *		Dynamically cast a *info* pointer to a *sock* pointer.
+ *	Return
+ *		*info* if casting is valid, or **NULL** otherwise.
  */
 #define ___BPF_FUNC_MAPPER(FN, ctx...)			\
 	FN(unspec, 0, ##ctx)				\
@@ -XXX,XX +XXX,XX @@ union bpf_attr {
 	FN(user_ringbuf_drain, 209, ##ctx)		\
 	FN(cgrp_storage_get, 210, ##ctx)		\
 	FN(cgrp_storage_delete, 211, ##ctx)		\
+	FN(mptcp_send_info_to_ssk, 212, ##ctx)			\
 	/* */
 
 /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
-- 
2.45.2

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(-)

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        | 31 +++++++++----------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
@@ -XXX,XX +XXX,XX @@ 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);
 	if (!ptr)
 		return -1;
 
-	last_snd = ptr->last_snd;
+	next = bpf_mptcp_subflow_ctx(msk->first);
+	if (!next)
+		return -1;
 
-	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)
-			break;
+	if (!ptr->last_snd)
+		goto out;
 
-		if (mptcp_subflow_tcp_sock(subflow) == last_snd) {
-			if (i + 1 == MPTCP_SUBFLOWS_MAX ||
-			    !bpf_mptcp_subflow_ctx_by_pos(data, i + 1))
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		if (mptcp_subflow_tcp_sock(subflow) == ptr->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);
+out:
+	mptcp_subflow_set_scheduled(next, true);
+	ptr->last_snd = bpf_mptcp_subflow_tcp_sock(next);
 	return 0;
 }
 
-- 
2.45.2

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(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

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

Use bpf_mptcp_send_info_to_ssk() helper.

Drop bpf_subflow_send_info, use subflow_send_info instead.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 62 +++++++------------
 1 file changed, 24 insertions(+), 38 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_burst.c
@@ -XXX,XX +XXX,XX @@ char _license[] SEC("license") = "GPL";
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
-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;
@@ -XXX,XX +XXX,XX @@ 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)
 {
-	struct bpf_subflow_send_info send_info[SSK_MODE_MAX];
+	struct subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
 	__u32 pace, burst, wmem;
@@ -XXX,XX +XXX,XX @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 
 	/* pick the subflow with the lower wmem/wspace ratio */
 	for (i = 0; i < SSK_MODE_MAX; ++i) {
-		send_info[i].subflow_id = MPTCP_SUBFLOWS_MAX;
+		send_info[i].ssk = NULL;
 		send_info[i].linger_time = -1;
 	}
 
-	for (i = 0; i < data->subflows && i < MPTCP_SUBFLOWS_MAX; i++) {
-		bool backup;
-
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		bool backup = subflow->backup || subflow->request_bkup;
 
-		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;
 
@@ -XXX,XX +XXX,XX @@ 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].ssk = ssk;
 			send_info[backup].linger_time = linger_time;
 		}
 	}
@@ -XXX,XX +XXX,XX @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 
 	/* pick the best backup if no other subflow is active */
 	if (!nr_active)
-		send_info[SSK_MODE_ACTIVE].subflow_id = send_info[SSK_MODE_BACKUP].subflow_id;
+		send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk;
 
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, send_info[SSK_MODE_ACTIVE].subflow_id);
-	if (!subflow)
-		return -1;
-	ssk = mptcp_subflow_tcp_sock(subflow);
+	ssk = bpf_mptcp_send_info_to_ssk(&send_info[SSK_MODE_ACTIVE]);
 	if (!ssk || !sk_stream_memory_free(ssk))
 		return -1;
 
+	subflow = bpf_mptcp_subflow_ctx(ssk);
+	if (!subflow)
+		return -1;
+
 	burst = min(MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
 	wmem = ssk->sk_wmem_queued;
 	if (!burst)
@@ -XXX,XX +XXX,XX @@ static int bpf_burst_get_send(struct mptcp_sock *msk,
 static int bpf_burst_get_retrans(struct mptcp_sock *msk,
 				 struct mptcp_sched_data *data)
 {
-	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 = 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);
@@ -XXX,XX +XXX,XX @@ 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);
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

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

Drop bpf_mptcp_subflow_ctx_by_pos declaration.

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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf.h
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -XXX,XX +XXX,XX @@ bpf_mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) __ksym;
 extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 					bool scheduled) __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 XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
@@ -XXX,XX +XXX,XX @@ 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;
+
+	subflow = bpf_mptcp_subflow_ctx(msk->first);
+	if (!subflow)
+		return -1;
+
+	mptcp_subflow_set_scheduled(subflow, true);
 	return 0;
 }
 
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

Drop this patch. bpf_mptcp_subflow_ctx_by_pos and
mptcp_sched_data_set_contexts are uesless now.

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 XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -XXX,XX +XXX,XX @@ __bpf_kfunc static 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 static 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 XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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 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 XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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);
 }
 
@@ -XXX,XX +XXX,XX @@ 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);
 }
-- 
2.45.2