[PATCH mptcp-next v5 0/8] BPF packet scheduler

[PATCH mptcp-next v5 0/8] BPF packet scheduler

[Geliang Tang]

v5:
 - patch 1: define per-namespace sched_list (but only used init_net
   namespace. It is difficult to get 'net' in bpf_mptcp_sched_reg and
   bpf_mptcp_sched_unreg. I need some suggestions here.)
 - patch 2: skip mptcp_sched_default in mptcp_unregister_scheduler.
 - patch 8: add tests into mptcp.c, instead of bpf_tcp_ca.c.
 - depends on: "add skc_to_mptcp_sock" v11.

v4:
 - set msk->sched to &mptcp_sched_default when the sched argument is NULL
in mptcp_init_sched().

v3:
 - add mptcp_release_sched helper in patch 4.
 - rename mptcp_set_sched to mptcp_init_sched in patch 4.
 - add mptcp_sched_first_release in patch 7.
 - do some cleanups.

v2:
 - split into more small patches.
 - change all parameters of mptcp_sched_ops from sk to msk:
       void (*init)(struct mptcp_sock *msk);
       void (*release)(struct mptcp_sock *msk);
       struct sock *   (*get_subflow)(struct mptcp_sock *msk);
 - add tests in bpf_tcp_ca.c, instead of adding a new one.

v1:
 - Addressed to the commends in the RFC version.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/75

Geliang Tang (8):
  mptcp: add struct mptcp_sched_ops
  mptcp: register default scheduler
  mptcp: add a new sysctl scheduler
  mptcp: add sched in mptcp_sock
  mptcp: add mptcp_get_subflow wrapper
  mptcp: add bpf_mptcp_sched_ops
  selftests: bpf: add bpf_first scheduler
  selftests: bpf: add bpf_first test

 Documentation/networking/mptcp-sysctl.rst     |   8 +
 include/net/mptcp.h                           |  13 ++
 kernel/bpf/bpf_struct_ops_types.h             |   4 +
 net/mptcp/Makefile                            |   2 +-
 net/mptcp/bpf.c                               | 102 ++++++++++++
 net/mptcp/ctrl.c                              |  14 ++
 net/mptcp/protocol.c                          |  13 +-
 net/mptcp/protocol.h                          |  11 ++
 net/mptcp/sched.c                             | 149 ++++++++++++++++++
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  12 ++
 .../testing/selftests/bpf/prog_tests/mptcp.c  |  42 +++++
 tools/testing/selftests/bpf/progs/bpf_first.c |  30 ++++
 12 files changed, 395 insertions(+), 5 deletions(-)
 create mode 100644 net/mptcp/sched.c
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_first.c

-- 
2.34.1

[PATCH mptcp-next v5 1/8] mptcp: add struct mptcp_sched_ops

[Geliang Tang]

This patch added struct mptcp_sched_ops. And define the scheduler
register, unregister and find functions.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h  |  13 +++++
 net/mptcp/Makefile   |   2 +-
 net/mptcp/protocol.c |   1 +
 net/mptcp/protocol.h |   4 ++
 net/mptcp/sched.c    | 111 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 130 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/sched.c

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 8b1afd6f5cc4..e3a0baa8dbd7 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -95,6 +95,19 @@ struct mptcp_out_options {
 #endif
 };
 
+#define MPTCP_SCHED_NAME_MAX 16
+
+struct mptcp_sched_ops {
+	struct sock *	(*get_subflow)(struct mptcp_sock *msk);
+
+	char			name[MPTCP_SCHED_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
 #ifdef CONFIG_MPTCP
 extern struct request_sock_ops mptcp_subflow_request_sock_ops;
 
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index 0a0608b6b4b4..aa5c10d1b80a 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o
 ccflags-y += -DDEBUG
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
-	   mib.o pm_netlink.o sockopt.o
+	   mib.o pm_netlink.o sockopt.o sched.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index fbb14dfe62b3..95f7c3fc943b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3743,6 +3743,7 @@ void __init mptcp_proto_init(void)
 
 	mptcp_subflow_init();
 	mptcp_pm_init();
+	mptcp_sched_init();
 	mptcp_token_init();
 
 	if (proto_register(&mptcp_prot, MPTCP_USE_SLAB) != 0)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c8bada4537e2..dd10899bedfd 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -605,6 +605,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 			 struct sockaddr_storage *addr,
 			 unsigned short family);
+struct mptcp_sched_ops *mptcp_sched_find(const struct net *net, const char *name);
+int mptcp_register_scheduler(const struct net *net, struct mptcp_sched_ops *sched);
+void mptcp_unregister_scheduler(const struct net *net, struct mptcp_sched_ops *sched);
+void mptcp_sched_init(void);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
new file mode 100644
index 000000000000..52e7c74b33ae
--- /dev/null
+++ b/net/mptcp/sched.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2022, SUSE.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <net/tcp.h>
+#include <net/netns/generic.h>
+#include "protocol.h"
+
+static int sched_pernet_id;
+
+struct sched_pernet {
+	/* protects pernet updates */
+	spinlock_t		lock;
+	struct list_head	sched_list;
+};
+
+static struct sched_pernet *sched_get_pernet(const struct net *net)
+{
+	return net_generic(net, sched_pernet_id);
+}
+
+struct mptcp_sched_ops *mptcp_sched_find(const struct net *net, const char *name)
+{
+	struct sched_pernet *pernet = sched_get_pernet(net);
+	struct mptcp_sched_ops *sched, *ret = NULL;
+
+	spin_lock(&pernet->lock);
+	list_for_each_entry_rcu(sched, &pernet->sched_list, list) {
+		if (!strcmp(sched->name, name)) {
+			ret = sched;
+			break;
+		}
+	}
+	spin_unlock(&pernet->lock);
+
+	return ret;
+}
+
+int mptcp_register_scheduler(const struct net *net, struct mptcp_sched_ops *sched)
+{
+	struct sched_pernet *pernet = sched_get_pernet(net);
+
+	if (!sched->get_subflow)
+		return -EINVAL;
+
+	if (mptcp_sched_find(net, sched->name))
+		return -EEXIST;
+
+	spin_lock(&pernet->lock);
+	list_add_tail_rcu(&sched->list, &pernet->sched_list);
+	spin_unlock(&pernet->lock);
+
+	pr_debug("%s registered", sched->name);
+	return 0;
+}
+
+void mptcp_unregister_scheduler(const struct net *net, struct mptcp_sched_ops *sched)
+{
+	struct sched_pernet *pernet = sched_get_pernet(net);
+
+	spin_lock(&pernet->lock);
+	list_del_rcu(&sched->list);
+	spin_unlock(&pernet->lock);
+
+	synchronize_rcu();
+}
+
+static int __net_init sched_init_net(struct net *net)
+{
+	struct sched_pernet *pernet = sched_get_pernet(net);
+
+	INIT_LIST_HEAD_RCU(&pernet->sched_list);
+	spin_lock_init(&pernet->lock);
+
+	return 0;
+}
+
+static void __net_exit sched_exit_net(struct net *net)
+{
+	struct sched_pernet *pernet = sched_get_pernet(net);
+	struct mptcp_sched_ops *sched;
+
+	spin_lock(&pernet->lock);
+	list_for_each_entry_rcu(sched, &pernet->sched_list, list)
+		list_del_rcu(&sched->list);
+	spin_unlock(&pernet->lock);
+
+	synchronize_rcu();
+}
+
+static struct pernet_operations mptcp_sched_pernet_ops = {
+	.init = sched_init_net,
+	.exit = sched_exit_net,
+	.id = &sched_pernet_id,
+	.size = sizeof(struct sched_pernet),
+};
+
+void mptcp_sched_init(void)
+{
+	if (register_pernet_subsys(&mptcp_sched_pernet_ops) < 0)
+		panic("Failed to register MPTCP sched pernet subsystem.\n");
+}
-- 
2.34.1

[PATCH mptcp-next v5 2/8] mptcp: register default scheduler

[Geliang Tang]

This patch defined the default packet scheduler mptcp_sched_default,
registered it in mptcp_sched_init().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c |  2 +-
 net/mptcp/protocol.h |  1 +
 net/mptcp/sched.c    | 10 ++++++++++
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 95f7c3fc943b..11e19ac9d5af 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1424,7 +1424,7 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
  * returns the subflow that will transmit the next DSS
  * additionally updates the rtx timeout
  */
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 {
 	struct subflow_send_info send_info[SSK_MODE_MAX];
 	struct mptcp_subflow_context *subflow;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index dd10899bedfd..85642ba3354c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -608,6 +608,7 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 struct mptcp_sched_ops *mptcp_sched_find(const struct net *net, const char *name);
 int mptcp_register_scheduler(const struct net *net, struct mptcp_sched_ops *sched);
 void mptcp_unregister_scheduler(const struct net *net, struct mptcp_sched_ops *sched);
+struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
 void mptcp_sched_init(void);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 52e7c74b33ae..3ee23b24b771 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -23,6 +23,12 @@ struct sched_pernet {
 	struct list_head	sched_list;
 };
 
+static struct mptcp_sched_ops mptcp_sched_default = {
+	.get_subflow    = mptcp_subflow_get_send,
+	.name           = "default",
+	.owner          = THIS_MODULE,
+};
+
 static struct sched_pernet *sched_get_pernet(const struct net *net)
 {
 	return net_generic(net, sched_pernet_id);
@@ -67,6 +73,9 @@ void mptcp_unregister_scheduler(const struct net *net, struct mptcp_sched_ops *s
 {
 	struct sched_pernet *pernet = sched_get_pernet(net);
 
+	if (sched == &mptcp_sched_default)
+		return;
+
 	spin_lock(&pernet->lock);
 	list_del_rcu(&sched->list);
 	spin_unlock(&pernet->lock);
@@ -108,4 +117,5 @@ void mptcp_sched_init(void)
 {
 	if (register_pernet_subsys(&mptcp_sched_pernet_ops) < 0)
 		panic("Failed to register MPTCP sched pernet subsystem.\n");
+	mptcp_register_scheduler(&init_net, &mptcp_sched_default);
 }
-- 
2.34.1

[PATCH mptcp-next v5 3/8] mptcp: add a new sysctl scheduler

[Geliang Tang]

This patch added a new sysctl, named scheduler, to support for selection
of different schedulers.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 Documentation/networking/mptcp-sysctl.rst |  8 ++++++++
 net/mptcp/ctrl.c                          | 14 ++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 23 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index e263dfcc4b40..d9e69fdc7ea3 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -75,3 +75,11 @@ stale_loss_cnt - INTEGER
 	This is a per-namespace sysctl.
 
 	Default: 4
+
+scheduler - STRING
+	Select the scheduler of your choice.
+
+	Support for selection of different schedulers. This is a per-namespace
+	sysctl.
+
+	Default: "default"
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index ae20b7d92e28..c46c22a84d23 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -32,6 +32,7 @@ struct mptcp_pernet {
 	u8 checksum_enabled;
 	u8 allow_join_initial_addr_port;
 	u8 pm_type;
+	char scheduler[MPTCP_SCHED_NAME_MAX];
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(const struct net *net)
@@ -69,6 +70,11 @@ int mptcp_get_pm_type(const struct net *net)
 	return mptcp_get_pernet(net)->pm_type;
 }
 
+const char *mptcp_get_scheduler(const struct net *net)
+{
+	return mptcp_get_pernet(net)->scheduler;
+}
+
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
@@ -77,6 +83,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->allow_join_initial_addr_port = 1;
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
+	strcpy(pernet->scheduler, "default");
 }
 
 #ifdef CONFIG_SYSCTL
@@ -128,6 +135,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = &mptcp_pm_type_max
 	},
+	{
+		.procname = "scheduler",
+		.maxlen	= MPTCP_SCHED_NAME_MAX,
+		.mode = 0644,
+		.proc_handler = proc_dostring,
+	},
 	{}
 };
 
@@ -149,6 +162,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[3].data = &pernet->allow_join_initial_addr_port;
 	table[4].data = &pernet->stale_loss_cnt;
 	table[5].data = &pernet->pm_type;
+	table[6].data = &pernet->scheduler;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 85642ba3354c..ffe7e551ac84 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -583,6 +583,7 @@ int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 int mptcp_get_pm_type(const struct net *net);
+const char *mptcp_get_scheduler(const struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
-- 
2.34.1

[PATCH mptcp-next v5 4/8] mptcp: add sched in mptcp_sock

[Geliang Tang]

This patch added a new struct member sched in struct mptcp_sock.
And two helpers mptcp_init_sched() and mptcp_release_sched() to
init and release it.

Init it with the sysctl scheduler in mptcp_init_sock(), copy the
scheduler from the parent in mptcp_sk_clone(), and release it in
__mptcp_destroy_sock().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c |  4 ++++
 net/mptcp/protocol.h |  4 ++++
 net/mptcp/sched.c    | 21 +++++++++++++++++++++
 3 files changed, 29 insertions(+)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 11e19ac9d5af..c309922bdb66 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2609,6 +2609,8 @@ static int mptcp_init_sock(struct sock *sk)
 	 * propagate the correct value
 	 */
 	mptcp_ca_reset(sk);
+	mptcp_init_sched(mptcp_sk(sk),
+			 mptcp_sched_find(net, mptcp_get_scheduler(net)));
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
@@ -2760,6 +2762,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
+	mptcp_release_sched(msk);
 
 	/* clears msk->subflow, allowing the following loop to close
 	 * even the initial subflow
@@ -2933,6 +2936,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->snd_una = msk->write_seq;
 	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
 	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {
 		msk->can_ack = true;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ffe7e551ac84..9441a510ec6e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -286,6 +286,7 @@ struct mptcp_sock {
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
+	struct mptcp_sched_ops	*sched;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */
 		u32	copied; /* bytes copied in this measurement window */
@@ -611,6 +612,9 @@ int mptcp_register_scheduler(const struct net *net, struct mptcp_sched_ops *sche
 void mptcp_unregister_scheduler(const struct net *net, struct mptcp_sched_ops *sched);
 struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
 void mptcp_sched_init(void);
+void mptcp_init_sched(struct mptcp_sock *msk,
+		      struct mptcp_sched_ops *sched);
+void mptcp_release_sched(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 3ee23b24b771..9ddfeb553c78 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -119,3 +119,24 @@ void mptcp_sched_init(void)
 		panic("Failed to register MPTCP sched pernet subsystem.\n");
 	mptcp_register_scheduler(&init_net, &mptcp_sched_default);
 }
+
+void mptcp_init_sched(struct mptcp_sock *msk,
+		      struct mptcp_sched_ops *sched)
+{
+	if (!sched)
+		msk->sched = &mptcp_sched_default;
+	else
+		msk->sched = sched;
+
+	if (msk->sched->init)
+		msk->sched->init(msk);
+
+	pr_debug("sched=%s", msk->sched->name);
+}
+
+void mptcp_release_sched(struct mptcp_sock *msk)
+{
+	if (msk->sched && msk->sched->release)
+		msk->sched->release(msk);
+	msk->sched = NULL;
+}
-- 
2.34.1

[PATCH mptcp-next v5 5/8] mptcp: add mptcp_get_subflow wrapper

[Geliang Tang]

This patch defined a new wrapper mptcp_get_subflow(), invoke get_subflow
of msk->sched in it. Use the wrapper instead of mptcp_subflow_get_send().

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 net/mptcp/protocol.c | 6 +++---
 net/mptcp/protocol.h | 1 +
 net/mptcp/sched.c    | 7 +++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c309922bdb66..4560cdde96af 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1567,7 +1567,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			int ret = 0;
 
 			prev_ssk = ssk;
-			ssk = mptcp_subflow_get_send(msk);
+			ssk = mptcp_get_subflow(msk);
 
 			/* First check. If the ssk has changed since
 			 * the last round, release prev_ssk
@@ -1634,7 +1634,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			 * check for a different subflow usage only after
 			 * spooling the first chunk of data
 			 */
-			xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk));
+			xmit_ssk = first ? ssk : mptcp_get_subflow(mptcp_sk(sk));
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
@@ -3074,7 +3074,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		return;
 
 	if (!sock_owned_by_user(sk)) {
-		struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk));
+		struct sock *xmit_ssk = mptcp_get_subflow(mptcp_sk(sk));
 
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 9441a510ec6e..c5957fbff35c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -615,6 +615,7 @@ void mptcp_sched_init(void);
 void mptcp_init_sched(struct mptcp_sock *msk,
 		      struct mptcp_sched_ops *sched);
 void mptcp_release_sched(struct mptcp_sock *msk);
+struct sock *mptcp_get_subflow(struct mptcp_sock *msk);
 
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 9ddfeb553c78..464f030bcd86 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/rculist.h>
 #include <linux/spinlock.h>
+#include <linux/indirect_call_wrapper.h>
 #include <net/tcp.h>
 #include <net/netns/generic.h>
 #include "protocol.h"
@@ -140,3 +141,9 @@ void mptcp_release_sched(struct mptcp_sock *msk)
 		msk->sched->release(msk);
 	msk->sched = NULL;
 }
+
+struct sock *mptcp_get_subflow(struct mptcp_sock *msk)
+{
+	return INDIRECT_CALL_INET_1(msk->sched->get_subflow,
+				    mptcp_subflow_get_send, msk);
+}
-- 
2.34.1

[PATCH mptcp-next v5 6/8] mptcp: add bpf_mptcp_sched_ops

[Geliang Tang]

This patch implemented a new struct bpf_struct_ops, bpf_mptcp_sched_ops.
Register and unregister the mptcp scheduler in .reg and .unreg.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 kernel/bpf/bpf_struct_ops_types.h |   4 ++
 net/mptcp/bpf.c                   | 102 ++++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+)

diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h
index 5678a9ddf817..5a6b0c0d8d3d 100644
--- a/kernel/bpf/bpf_struct_ops_types.h
+++ b/kernel/bpf/bpf_struct_ops_types.h
@@ -8,5 +8,9 @@ BPF_STRUCT_OPS_TYPE(bpf_dummy_ops)
 #ifdef CONFIG_INET
 #include <net/tcp.h>
 BPF_STRUCT_OPS_TYPE(tcp_congestion_ops)
+#ifdef CONFIG_MPTCP
+#include <net/mptcp.h>
+BPF_STRUCT_OPS_TYPE(mptcp_sched_ops)
+#endif
 #endif
 #endif
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index c3b6f94f033f..c706850f0a87 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -8,8 +8,110 @@
  */
 
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include "protocol.h"
 
+extern struct bpf_struct_ops bpf_mptcp_sched_ops;
+extern struct btf *btf_vmlinux;
+
+static u32 optional_ops[] = {
+	offsetof(struct mptcp_sched_ops, init),
+	offsetof(struct mptcp_sched_ops, release),
+	offsetof(struct mptcp_sched_ops, get_subflow),
+};
+
+static const struct bpf_func_proto *
+bpf_mptcp_sched_get_func_proto(enum bpf_func_id func_id,
+			       const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id);
+}
+
+static const struct bpf_verifier_ops bpf_mptcp_sched_verifier_ops = {
+	.get_func_proto		= bpf_mptcp_sched_get_func_proto,
+	.is_valid_access	= btf_ctx_access,
+	.btf_struct_access	= btf_struct_access,
+};
+
+static int bpf_mptcp_sched_reg(void *kdata)
+{
+	return mptcp_register_scheduler(&init_net, kdata);
+}
+
+static void bpf_mptcp_sched_unreg(void *kdata)
+{
+	mptcp_unregister_scheduler(&init_net, kdata);
+}
+
+static int bpf_mptcp_sched_check_member(const struct btf_type *t,
+					const struct btf_member *member)
+{
+	return 0;
+}
+
+static bool is_optional(u32 member_offset)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
+		if (member_offset == optional_ops[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int bpf_mptcp_sched_init_member(const struct btf_type *t,
+				       const struct btf_member *member,
+				       void *kdata, const void *udata)
+{
+	const struct mptcp_sched_ops *usched;
+	struct mptcp_sched_ops *sched;
+	int prog_fd;
+	u32 moff;
+
+	usched = (const struct mptcp_sched_ops *)udata;
+	sched = (struct mptcp_sched_ops *)kdata;
+
+	moff = __btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct mptcp_sched_ops, name):
+		if (bpf_obj_name_cpy(sched->name, usched->name,
+				     sizeof(sched->name)) <= 0)
+			return -EINVAL;
+		if (mptcp_sched_find(&init_net, usched->name))
+			return -EEXIST;
+		return 1;
+	}
+
+	if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
+		return 0;
+
+	/* Ensure bpf_prog is provided for compulsory func ptr */
+	prog_fd = (int)(*(unsigned long *)(udata + moff));
+	if (!prog_fd && !is_optional(moff))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int bpf_mptcp_sched_init(struct btf *btf)
+{
+	return 0;
+}
+
+struct bpf_struct_ops bpf_mptcp_sched_ops = {
+	.verifier_ops	= &bpf_mptcp_sched_verifier_ops,
+	.reg		= bpf_mptcp_sched_reg,
+	.unreg		= bpf_mptcp_sched_unreg,
+	.check_member	= bpf_mptcp_sched_check_member,
+	.init_member	= bpf_mptcp_sched_init_member,
+	.init		= bpf_mptcp_sched_init,
+	.name		= "mptcp_sched_ops",
+};
+
 struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
 {
 	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
-- 
2.34.1

[PATCH mptcp-next v5 7/8] selftests: bpf: add bpf_first scheduler

[Geliang Tang]

This patch implemented the simplest MPTCP scheduler, named bpf_first,
which always picks the first subflow to send data.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 12 ++++++++
 tools/testing/selftests/bpf/progs/bpf_first.c | 30 +++++++++++++++++++
 2 files changed, 42 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_first.c

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index f92357597e63..5bb21b24231f 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -197,6 +197,18 @@ struct tcp_congestion_ops {
 	void *owner;
 };
 
+#define MPTCP_SCHED_NAME_MAX 16
+
+struct mptcp_sched_ops {
+	char name[MPTCP_SCHED_NAME_MAX];
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+
+	struct sock *	(*get_subflow)(struct mptcp_sock *msk);
+	void *owner;
+};
+
 #define min(a, b) ((a) < (b) ? (a) : (b))
 #define max(a, b) ((a) > (b) ? (a) : (b))
 #define min_not_zero(x, y) ({			\
diff --git a/tools/testing/selftests/bpf/progs/bpf_first.c b/tools/testing/selftests/bpf/progs/bpf_first.c
new file mode 100644
index 000000000000..3ae5c1eab5f5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_first.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/mptcp_sched_first_init")
+void BPF_PROG(mptcp_sched_first_init, struct mptcp_sock *msk)
+{
+}
+
+SEC("struct_ops/mptcp_sched_first_release")
+void BPF_PROG(mptcp_sched_first_release, struct mptcp_sock *msk)
+{
+}
+
+struct sock *BPF_STRUCT_OPS(bpf_first_get_subflow, struct mptcp_sock *msk)
+{
+	return msk->first;
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops first = {
+	.init		= (void *)mptcp_sched_first_init,
+	.release	= (void *)mptcp_sched_first_release,
+	.get_subflow	= (void *)bpf_first_get_subflow,
+	.name		= "bpf_first",
+};
-- 
2.34.1

[PATCH mptcp-next v5 8/8] selftests: bpf: add bpf_first test

[Geliang Tang]

This patch expended the MPTCP test base to support MPTCP packet
scheduler tests. Add the bpf_first MPTCP sched test in it. Use
sysctl to set net.mptcp.scheduler to use this sched.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 42 +++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 325f8b51f621..873027cf92fd 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
+#include "bpf_first.skel.h"
 
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
@@ -19,6 +20,15 @@ struct mptcp_storage {
 };
 
 static char monitor_log_path[64];
+static int duration;
+
+static void send_byte(int fd)
+{
+	char b = 0x55;
+
+	if (CHECK_FAIL(write(fd, &b, sizeof(b)) != 1))
+		perror("Failed to send single byte");
+}
 
 static int verify_tsk(int map_fd, int client_fd)
 {
@@ -185,6 +195,8 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 		goto close_client_fd;
 	}
 
+	send_byte(client_fd);
+
 	err += is_mptcp ? verify_msk(map_fd, client_fd) :
 			  verify_tsk(map_fd, client_fd);
 
@@ -237,8 +249,38 @@ void test_base(void)
 	close(cgroup_fd);
 }
 
+static void test_first(void)
+{
+	struct bpf_first *first_skel;
+	int server_fd, client_fd;
+	struct bpf_link *link;
+
+	first_skel = bpf_first__open_and_load();
+	if (CHECK(!first_skel, "bpf_first__open_and_load", "failed\n"))
+		return;
+
+	link = bpf_map__attach_struct_ops(first_skel->maps.first);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
+		bpf_first__destroy(first_skel);
+		return;
+	}
+
+	system("sysctl -q net.mptcp.scheduler=bpf_first");
+	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	client_fd = connect_to_mptcp_fd(server_fd, 0);
+
+	send_byte(client_fd);
+
+	close(client_fd);
+	close(server_fd);
+	bpf_link__destroy(link);
+	bpf_first__destroy(first_skel);
+}
+
 void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
+	if (test__start_subtest("first"))
+		test_first();
 }
-- 
2.34.1