Series comparison

From: Geliang Tang <tanggeliang@kylinos.cn>

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

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 (13):
  mptcp: check sk_stream_memory_free in loop
  mptcp: make mptcp_subflow_set_scheduled inline
  mptcp: add mptcp_validate_scheduler helper
  Squash to "bpf: Add bpf_mptcp_sched_ops"
  Squash to "selftests/bpf: Add bpf scheduler test"
  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"
  Squash to "bpf: Export mptcp packet scheduler helpers"
  Revert "mptcp: add sched_data helpers"
  mptcp: drop subflow contexts in mptcp_sched_data

include/net/mptcp.h                           |  2 -
 net/mptcp/bpf.c                               | 45 +++++------
 net/mptcp/protocol.c                          |  5 +-
 net/mptcp/protocol.h                          | 12 ++-
 net/mptcp/sched.c                             | 45 ++++-------
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 45 +++++------
 tools/testing/selftests/bpf/progs/mptcp_bpf.h | 14 ++--
 .../selftests/bpf/progs/mptcp_bpf_bkup.c      | 18 +----
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 74 ++++++++-----------
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  4 +-
 .../selftests/bpf/progs/mptcp_bpf_red.c       | 10 +--
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 33 ++++-----
 12 files changed, 131 insertions(+), 176 deletions(-)

-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

In order to make it easier to implement similar logic to the burst
scheduler in BPF program, the sk_stream_memory_free() check is moved
forward into mptcp_for_each_subflow loop.

Assignment like "ssk = send_info[SSK_MODE_ACTIVE].ssk" is not allowed
in BPF, so bpf_core_cast() is used to cast it. But a casted pointer can't
pass to a kfunc (sk_stream_memory_free). To solve this, In BPF burst
scheduler sk_stream_memory_free check is moved forward to the position
of mptcp_subflow_active() in bpf_for_each() loop.

To keep mptcp_subflow_get_send() and BPF burst scheduler code consistent,
this patch also synchronizes the change in BPF burst scheduler into
mptcp_subflow_get_send().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/protocol.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

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 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 
 		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
-		if (!mptcp_subflow_active(subflow))
+		if (!mptcp_subflow_active(subflow) ||
+		    !sk_stream_memory_free(ssk))
 			continue;
 
 		tout = max(tout, mptcp_timeout_from_subflow(subflow));
@@ -XXX,XX +XXX,XX @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	 * to check that subflow has a non empty cwin.
 	 */
 	ssk = send_info[SSK_MODE_ACTIVE].ssk;
-	if (!ssk || !sk_stream_memory_free(ssk))
+	if (!ssk)
 		return NULL;
 
 	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

Now mptcp_subflow_set_scheduled is no longer used in BPF, but only in
kernel. A new mptcp_subflow_set_scheduled helper has been implemented
in BPF specifically for use with BPF. To avoid compilation errors due
to duplicate names, this function has been made inline in kernel and
moved to protocol.h.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/protocol.h | 9 +++++++--
 net/mptcp/sched.c    | 6 ------
 2 files changed, 7 insertions(+), 8 deletions(-)

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_sched_init(void);
 int mptcp_init_sched(struct mptcp_sock *msk,
 		     struct mptcp_sched_ops *sched);
 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);
 int mptcp_sched_get_send(struct mptcp_sock *msk);
 int mptcp_sched_get_retrans(struct mptcp_sock *msk);
 
+static inline void
+mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
+			    bool scheduled)
+{
+	WRITE_ONCE(subflow->scheduled, scheduled);
+}
+
 static inline u64 mptcp_data_avail(const struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed);
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_release_sched(struct mptcp_sock *msk)
 	bpf_module_put(sched, sched->owner);
 }
 
-void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
-				 bool scheduled)
-{
-	WRITE_ONCE(subflow->scheduled, scheduled);
-}
-
 static void mptcp_sched_data_set_contexts(const struct mptcp_sock *msk,
 					  struct mptcp_sched_data *data)
 {
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

New interface .validate is added in bpf_struct_ops recently, implement
.validate as mptcp_validate_scheduler() for struct mptcp_sched_ops. In it
check whether the required ops "get_subflow" of struct mptcp_sched_ops
is implemented.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/protocol.h |  1 +
 net/mptcp/sched.c    | 17 +++++++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

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_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
 struct mptcp_sched_ops *mptcp_sched_find(const char *name);
+int mptcp_validate_scheduler(struct mptcp_sched_ops *sched);
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 void mptcp_sched_init(void);
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_get_available_schedulers(char *buf, size_t maxlen)
 	rcu_read_unlock();
 }
 
-int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+int mptcp_validate_scheduler(struct mptcp_sched_ops *sched)
 {
-	if (!sched->get_subflow)
+	if (!sched->get_subflow) {
+		pr_err("%s does not implement required ops\n", sched->name);
 		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	int ret;
+
+	ret = mptcp_validate_scheduler(sched);
+	if (ret)
+		return ret;
 
 	spin_lock(&mptcp_sched_list_lock);
 	if (mptcp_sched_find(sched->name)) {
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

Please update the subject to

bpf: Add mptcp packet scheduler struct_ops

1. validate interface is added in bpf_struct_ops by commit 68b04864ca42
("bpf: Create links for BPF struct_ops maps."), implement it in
mptcp_sched_ops.

2. Drop mptcp_sched_find. This part of mptcp_sched_find() code comes from
bpf_tcp_ca_init_member, but it was recently deleted by commit 68b04864ca42.

3. Add write access for scheduled of mptcp_subflow_context.

4. Drop mptcp_sock_type and mptcp_subflow_type.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c | 35 ++++++++++++++++++-----------------
 1 file changed, 18 insertions(+), 17 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 @@
 
 #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;
+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,
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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);
 			break;
+		case offsetof(struct mptcp_subflow_context, scheduled):
+			end = offsetofend(struct mptcp_subflow_context, scheduled);
+			break;
 		default:
 			bpf_log(log, "no write support to mptcp_subflow_context at off %d\n",
 				off);
@@ -XXX,XX +XXX,XX @@ 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;
 	}
@@ -XXX,XX +XXX,XX @@ static int bpf_mptcp_sched_init_member(const struct btf_type *t,
 	const struct mptcp_sched_ops *usched;
 	struct mptcp_sched_ops *sched;
 	u32 moff;
-	int ret;
 
 	usched = (const struct mptcp_sched_ops *)udata;
 	sched = (struct mptcp_sched_ops *)kdata;
@@ -XXX,XX +XXX,XX @@ static int bpf_mptcp_sched_init_member(const struct btf_type *t,
 		if (bpf_obj_name_cpy(sched->name, usched->name,
 				     sizeof(sched->name)) <= 0)
 			return -EINVAL;
-
-		rcu_read_lock();
-		ret = mptcp_sched_find(usched->name) ? -EEXIST : 1;
-		rcu_read_unlock();
-
-		return ret;
+		return 1;
 	}
 
 	return 0;
@@ -XXX,XX +XXX,XX @@ 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;
 }
 
+static int bpf_mptcp_sched_validate(void *kdata)
+{
+	return mptcp_validate_scheduler(kdata);
+}
+
 static int __bpf_mptcp_sched_get_subflow(struct mptcp_sock *msk,
 					 struct mptcp_sched_data *data)
 {
@@ -XXX,XX +XXX,XX @@ static struct bpf_struct_ops bpf_mptcp_sched_ops = {
 	.check_member	= bpf_mptcp_sched_check_member,
 	.init_member	= bpf_mptcp_sched_init_member,
 	.init		= bpf_mptcp_sched_init,
+	.validate	= bpf_mptcp_sched_validate,
 	.name		= "mptcp_sched_ops",
 	.cfi_stubs	= &__bpf_mptcp_sched_ops,
 };
-- 
2.45.2

From: Geliang Tang <tanggeliang@kylinos.cn>

A cleanup, move create_netns() out of sched_init().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 22 +++++++++----------
 1 file changed, 10 insertions(+), 12 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

1. Update sched_init.

2. For drop bpf_object__find_map_by_name in test_bpf_sched(), change the
first parameter of it as bpf_map.

3. Implement mptcp_subflow_set_scheduled in BPF.

4. Drop bpf_mptcp_subflow_ctx_by_pos.

5. 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/prog_tests/mptcp.c    | 15 +++++++++------
 tools/testing/selftests/bpf/progs/mptcp_bpf.h     | 14 ++++++++------
 .../testing/selftests/bpf/progs/mptcp_bpf_first.c |  4 ++--
 3 files changed, 19 insertions(+), 14 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Update test_bpf_sched().

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/prog_tests/mptcp.c |  2 +-
 .../selftests/bpf/progs/mptcp_bpf_bkup.c       | 18 ++++--------------
 2 files changed, 5 insertions(+), 15 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Update test_bpf_sched().

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

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  |  2 +-
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 33 ++++++++-----------
 2 files changed, 15 insertions(+), 20 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Update test_bpf_sched().

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/prog_tests/mptcp.c    |  2 +-
 tools/testing/selftests/bpf/progs/mptcp_bpf_red.c | 10 ++++------
 2 files changed, 5 insertions(+), 7 deletions(-)

From: Geliang Tang <tanggeliang@kylinos.cn>

Update test_bpf_sched().

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

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  |  2 +-
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 74 ++++++++-----------
 2 files changed, 33 insertions(+), 43 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index XXXXXXX..XXXXXXX 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -XXX,XX +XXX,XX @@ static void test_burst(void)
 	if (!ASSERT_OK_PTR(skel, "open_and_load: burst"))
 		return;
 
-	test_bpf_sched(skel->obj, "burst", WITH_DATA, WITH_DATA);
+	test_bpf_sched(skel->maps.burst, "burst", WITH_DATA, WITH_DATA);
 	mptcp_bpf_burst__destroy(skel);
 }
 
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 MPTCP_SEND_BURST_SIZE	65428
 
+#define SSK_MODE_ACTIVE	0
+#define SSK_MODE_BACKUP	1
+#define SSK_MODE_MAX	2
+
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
 struct bpf_subflow_send_info {
-	__u8 subflow_id;
+	struct mptcp_subflow_context *subflow;
 	__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 @@ 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,
 
 	/* 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].subflow = 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;
-
-		backup = subflow->backup || subflow->request_bkup;
+	bpf_for_each(mptcp_subflow, subflow, msk) {
+		bool backup = subflow->backup || subflow->request_bkup;
 
 		ssk = mptcp_subflow_tcp_sock(subflow);
-		if (!mptcp_subflow_active(subflow))
+		if (!mptcp_subflow_active(subflow) ||
+		    !sk_stream_memory_free(ssk))
 			continue;
 
 		nr_active += !backup;
@@ -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 = subflow;
 			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].subflow = send_info[SSK_MODE_BACKUP].subflow;
 
-	subflow = bpf_mptcp_subflow_ctx_by_pos(data, send_info[SSK_MODE_ACTIVE].subflow_id);
+	subflow = bpf_core_cast(send_info[SSK_MODE_ACTIVE].subflow,
+				struct mptcp_subflow_context);
 	if (!subflow)
 		return -1;
 	ssk = mptcp_subflow_tcp_sock(subflow);
-	if (!ssk || !sk_stream_memory_free(ssk))
+	if (!ssk)
 		return -1;
 
 	burst = min(MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
@@ -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 = 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>

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_release_sched(struct mptcp_sock *msk)
 	bpf_module_put(sched, sched->owner);
 }
 
-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

From: Geliang Tang <tanggeliang@kylinos.cn>

v11:
If another squash-to patchset (Squash to "Add mptcp_subflow bpf_iter
support") under review is merged before this set, v10 will fail to run.
v11 fixes this issue and can run regardless of whether it is merged
before or after the squash-to patchset.

Compared with v10, only patches 3, 5, and 8 have been modified:
 - use mptcp_subflow_tcp_sock instead of bpf_mptcp_subflow_tcp_sock in
   patch 3 and patch 5.
 - drop bpf_mptcp_sched_kfunc_set, use bpf_mptcp_common_kfunc_set instead
   in patch 8.

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

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

include/net/mptcp.h                           |  2 -
 include/uapi/linux/bpf.h                      |  7 +++
 net/mptcp/bpf.c                               | 47 ++++++++--------
 net/mptcp/protocol.c                          |  5 --
 net/mptcp/protocol.h                          |  7 ++-
 net/mptcp/sched.c                             | 22 --------
 tools/include/uapi/linux/bpf.h                |  7 +++
 tools/testing/selftests/bpf/progs/mptcp_bpf.h |  3 --
 .../selftests/bpf/progs/mptcp_bpf_bkup.c      | 16 ++----
 .../selftests/bpf/progs/mptcp_bpf_burst.c     | 54 ++++++++-----------
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  8 ++-
 .../selftests/bpf/progs/mptcp_bpf_red.c       |  8 ++-
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 31 +++++------
 13 files changed, 93 insertions(+), 124 deletions(-)

-- 
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(-)

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;
 }
 
-- 
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        | 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 = 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(-)

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;
 }
-- 
2.45.2

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     | 54 ++++++++-----------
 1 file changed, 21 insertions(+), 33 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++) {
+	bpf_for_each(mptcp_subflow, subflow, msk) {
 		bool backup;
 
-		subflow = bpf_mptcp_subflow_ctx_by_pos(data, i);
-		if (!subflow)
-			break;
-
 		backup = subflow->backup || subflow->request_bkup;
 
 		ssk = mptcp_subflow_tcp_sock(subflow);
@@ -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) {
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
@@ -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.

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

From: Geliang Tang <tanggeliang@kylinos.cn>

Remove bpf_mptcp_subflow_ctx_by_pos from BPF kfunc set.
Drop bpf_mptcp_sched_kfunc_set, use bpf_mptcp_common_kfunc_set instead.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 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 @@ BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_mptcp_sock_acquire, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_mptcp_sock_release, KF_RELEASE)
-BTF_KFUNCS_END(bpf_mptcp_common_kfunc_ids)
-
-static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
-	.owner	= THIS_MODULE,
-	.set	= &bpf_mptcp_common_kfunc_ids,
-};
-
-BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)
 BTF_ID_FLAGS(func, mptcp_subflow_set_scheduled)
-BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx_by_pos)
 BTF_ID_FLAGS(func, mptcp_subflow_active)
 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)
+BTF_KFUNCS_END(bpf_mptcp_common_kfunc_ids)
 
-static const struct btf_kfunc_id_set bpf_mptcp_sched_kfunc_set = {
+static const struct btf_kfunc_id_set bpf_mptcp_common_kfunc_set = {
 	.owner	= THIS_MODULE,
-	.set	= &bpf_mptcp_sched_kfunc_ids,
+	.set	= &bpf_mptcp_common_kfunc_ids,
 };
 
 static int __init bpf_mptcp_kfunc_init(void)
@@ -XXX,XX +XXX,XX @@ static int __init bpf_mptcp_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC,
 					       &bpf_mptcp_common_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
-					       &bpf_mptcp_sched_kfunc_set);
+					       &bpf_mptcp_common_kfunc_set);
 #ifdef CONFIG_BPF_JIT
 	ret = ret ?: register_bpf_struct_ops(&bpf_mptcp_sched_ops, mptcp_sched_ops);
 #endif
-- 
2.45.2