This patch defines struct mptcp_sched_ops, which has three struct members,
name, owner and list, and three function pointers, init, release and
get_subflow.

Add the scheduler registering, unregistering and finding functions to add,
delete and find a packet scheduler on the global list mptcp_sched_list.

For supporting a "redundant" packet scheduler in the future, this patch
adds a flag in struct mptcp_sched_data named call_again to indicate that
get_subflow() function needs to be called again.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 include/net/mptcp.h                           | 19 +++++++
 net/mptcp/Makefile                            |  2 +-
 net/mptcp/protocol.h                          |  3 +
 net/mptcp/sched.c                             | 56 +++++++++++++++++++
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 18 ++++++
 5 files changed, 97 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/sched.c

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index a267cff36197..6e872d0a35af 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -176,6 +176,25 @@ struct mptcp_out_options {
 #endif
 };
 
+#define MPTCP_SCHED_NAME_MAX	16
+
+struct mptcp_sched_data {
+	struct sock	*sock;
+	bool		call_again;
+};
+
+struct mptcp_sched_ops {
+	void (*get_subflow)(const struct mptcp_sock *msk, bool reinject,
+			    struct mptcp_sched_data *data);
+
+	char			name[MPTCP_SCHED_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(const struct mptcp_sock *msk);
+	void (*release)(const 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 cb7f53f6ab22..b68eddf4639a 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_MPTCP) += mptcp.o
 
 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 pm_userspace.o
+	   mib.o pm_netlink.o sockopt.o pm_userspace.o sched.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2fc8aaf5cb05..86efc5a6d878 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -527,6 +527,9 @@ 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 char *name);
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched);
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
 
 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..c5d3bbafba71
--- /dev/null
+++ b/net/mptcp/sched.c
@@ -0,0 +1,56 @@
+// 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 "protocol.h"
+
+static DEFINE_SPINLOCK(mptcp_sched_list_lock);
+static LIST_HEAD(mptcp_sched_list);
+
+/* Must be called with rcu read lock held */
+struct mptcp_sched_ops *mptcp_sched_find(const char *name)
+{
+	struct mptcp_sched_ops *sched, *ret = NULL;
+
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		if (!strcmp(sched->name, name)) {
+			ret = sched;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+	if (!sched->get_subflow)
+		return -EINVAL;
+
+	spin_lock(&mptcp_sched_list_lock);
+	if (mptcp_sched_find(sched->name)) {
+		spin_unlock(&mptcp_sched_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+	spin_unlock(&mptcp_sched_list_lock);
+
+	pr_debug("%s registered", sched->name);
+	return 0;
+}
+
+void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
+{
+	spin_lock(&mptcp_sched_list_lock);
+	list_del_rcu(&sched->list);
+	spin_unlock(&mptcp_sched_list_lock);
+}
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 82a7c9de95f9..bca318d2cc78 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -230,6 +230,24 @@ static __always_inline bool tcp_cc_eq(const char *a, const char *b)
 extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
 extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
 
+#define MPTCP_SCHED_NAME_MAX	16
+
+struct mptcp_sched_data {
+	struct sock	*sock;
+	bool		call_again;
+};
+
+struct mptcp_sched_ops {
+	char name[MPTCP_SCHED_NAME_MAX];
+
+	void (*init)(const struct mptcp_sock *msk);
+	void (*release)(const struct mptcp_sock *msk);
+
+	void (*get_subflow)(const struct mptcp_sock *msk, bool reinject,
+			    struct mptcp_sched_data *data);
+	void *owner;
+};
+
 struct mptcp_sock {
 	struct inet_connection_sock	sk;
 
-- 
2.34.1