* [PATCH mptcp-next v2 1/8] mptcp: add struct mptcp_sched_ops
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 2/8] mptcp: register default scheduler Geliang Tang
` (6 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: 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.h | 3 +++
net/mptcp/sched.c | 56 ++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 73 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.h b/net/mptcp/protocol.h
index c8bada4537e2..500dc7b3fde8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -605,6 +605,9 @@ 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..88ddc4aba4ea
--- /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/indirect_call_wrapper.h>
+#include "protocol.h"
+
+static DEFINE_SPINLOCK(mptcp_sched_list_lock);
+static LIST_HEAD(mptcp_sched_list);
+
+struct mptcp_sched_ops *mptcp_sched_find(const char *name)
+{
+ struct mptcp_sched_ops *ops;
+
+ list_for_each_entry_rcu(ops, &mptcp_sched_list, list) {
+ if (!strcmp(ops->name, name))
+ return ops;
+ }
+
+ return NULL;
+}
+
+int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+{
+ int ret = 0;
+
+ if (!sched->get_subflow)
+ return -EINVAL;
+
+ spin_lock(&mptcp_sched_list_lock);
+ if (mptcp_sched_find(sched->name)) {
+ pr_debug("%s already registered", sched->name);
+ ret = -EEXIST;
+ } else {
+ list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+ pr_debug("%s registered", sched->name);
+ }
+ spin_unlock(&mptcp_sched_list_lock);
+
+ return ret;
+}
+
+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);
+
+ synchronize_rcu();
+}
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 2/8] mptcp: register default scheduler
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 1/8] mptcp: add struct mptcp_sched_ops Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 3/8] mptcp: add a new sysctl scheduler Geliang Tang
` (5 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: 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 | 3 ++-
net/mptcp/protocol.h | 2 ++
net/mptcp/sched.c | 11 +++++++++++
3 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index fbb14dfe62b3..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;
@@ -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 500dc7b3fde8..c186d199cf5b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -608,6 +608,8 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
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);
+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 88ddc4aba4ea..9612e182b7b7 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -54,3 +54,14 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
synchronize_rcu();
}
+
+static struct mptcp_sched_ops mptcp_sched_default = {
+ .get_subflow = mptcp_subflow_get_send,
+ .name = "default",
+ .owner = THIS_MODULE,
+};
+
+void mptcp_sched_init(void)
+{
+ mptcp_register_scheduler(&mptcp_sched_default);
+}
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 3/8] mptcp: add a new sysctl scheduler
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 1/8] mptcp: add struct mptcp_sched_ops Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 2/8] mptcp: register default scheduler Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 4/8] mptcp: add sched for struct mptcp_sock Geliang Tang
` (4 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: 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 c186d199cf5b..f0bd2e17f2d6 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
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 4/8] mptcp: add sched for struct mptcp_sock
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
` (2 preceding siblings ...)
2022-03-18 2:58 ` [PATCH mptcp-next v2 3/8] mptcp: add a new sysctl scheduler Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 5/8] mptcp: add mptcp_get_subflow wrapper Geliang Tang
` (3 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch added a new struct member sched in struct mptcp_sock. Set it
in mptcp_set_sched() with the scheduler sysctl.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
net/mptcp/protocol.c | 3 +++
net/mptcp/protocol.h | 2 ++
net/mptcp/sched.c | 16 ++++++++++++++++
3 files changed, 21 insertions(+)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 11e19ac9d5af..b6b8f41a3ccb 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2609,6 +2609,7 @@ static int mptcp_init_sock(struct sock *sk)
* propagate the correct value
*/
mptcp_ca_reset(sk);
+ mptcp_set_sched(sk);
sk_sockets_allocated_inc(sk);
sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
@@ -2760,6 +2761,7 @@ 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;
+ msk->sched = NULL;
/* clears msk->subflow, allowing the following loop to close
* even the initial subflow
@@ -2933,6 +2935,7 @@ 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;
+ msk->sched = 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 f0bd2e17f2d6..d18c54e2f28c 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 */
@@ -609,6 +610,7 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
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);
+void mptcp_set_sched(struct sock *sk);
struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
void mptcp_sched_init(void);
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 9612e182b7b7..727d185af86e 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -55,6 +55,22 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched)
synchronize_rcu();
}
+void mptcp_set_sched(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct net *net = sock_net(sk);
+
+ msk->sched = mptcp_sched_find(mptcp_get_scheduler(net));
+ if (!msk->sched) {
+ pr_debug("sched %s not found", mptcp_get_scheduler(net));
+ return;
+ }
+
+ pr_debug("sched=%s", msk->sched->name);
+ if (msk->sched->init)
+ msk->sched->init(msk);
+}
+
static struct mptcp_sched_ops mptcp_sched_default = {
.get_subflow = mptcp_subflow_get_send,
.name = "default",
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 5/8] mptcp: add mptcp_get_subflow wrapper
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
` (3 preceding siblings ...)
2022-03-18 2:58 ` [PATCH mptcp-next v2 4/8] mptcp: add sched for struct mptcp_sock Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 6/8] mptcp: add bpf_mptcp_sched_ops Geliang Tang
` (2 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch defined a new wrapper mptcp_get_subflow(), used it 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 | 6 ++++++
3 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b6b8f41a3ccb..5222849eacb1 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) {
@@ -3073,7 +3073,7 @@ 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 d18c54e2f28c..8871a17f8b82 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -613,6 +613,7 @@ void mptcp_unregister_scheduler(struct mptcp_sched_ops *sched);
void mptcp_set_sched(struct sock *sk);
struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk);
void mptcp_sched_init(void);
+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 727d185af86e..61cbb0237beb 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -81,3 +81,9 @@ void mptcp_sched_init(void)
{
mptcp_register_scheduler(&mptcp_sched_default);
}
+
+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
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 6/8] mptcp: add bpf_mptcp_sched_ops
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
` (4 preceding siblings ...)
2022-03-18 2:58 ` [PATCH mptcp-next v2 5/8] mptcp: add mptcp_get_subflow wrapper Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 7/8] selftests: bpf: add bpf_first scheduler Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 8/8] selftests: bpf: add bpf_first test Geliang Tang
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: 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 da79dae559b2..5f7f9d30ecd4 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(kdata);
+}
+
+static void bpf_mptcp_sched_unreg(void *kdata)
+{
+ mptcp_unregister_scheduler(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(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
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 7/8] selftests: bpf: add bpf_first scheduler
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
` (5 preceding siblings ...)
2022-03-18 2:58 ` [PATCH mptcp-next v2 6/8] mptcp: add bpf_mptcp_sched_ops Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
2022-03-18 2:58 ` [PATCH mptcp-next v2 8/8] selftests: bpf: add bpf_first test Geliang Tang
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: 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 | 24 +++++++++++++++++++
2 files changed, 36 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..ad6822d61741
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_first.c
@@ -0,0 +1,24 @@
+// 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)
+{
+}
+
+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,
+ .get_subflow = (void *)bpf_first_get_subflow,
+ .name = "bpf_first",
+};
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH mptcp-next v2 8/8] selftests: bpf: add bpf_first test
2022-03-18 2:58 [PATCH mptcp-next v2 0/8] BPF packet scheduler Geliang Tang
` (6 preceding siblings ...)
2022-03-18 2:58 ` [PATCH mptcp-next v2 7/8] selftests: bpf: add bpf_first scheduler Geliang Tang
@ 2022-03-18 2:58 ` Geliang Tang
7 siblings, 0 replies; 9+ messages in thread
From: Geliang Tang @ 2022-03-18 2:58 UTC (permalink / raw)
To: mptcp; +Cc: Geliang Tang
This patch added the MPTCP sched testcases. Use sysctl to set
net.mptcp.scheduler in the tests.
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
.../selftests/bpf/prog_tests/bpf_tcp_ca.c | 42 +++++++++++++++++--
1 file changed, 38 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 8f7a1cef7d87..979b6e90b372 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -9,6 +9,7 @@
#include "bpf_cubic.skel.h"
#include "bpf_tcp_nogpl.skel.h"
#include "bpf_dctcp_release.skel.h"
+#include "bpf_first.skel.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
@@ -16,6 +17,10 @@
#define ENOTSUPP 524
#endif
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
static const unsigned int total_bytes = 10 * 1024 * 1024;
static int expected_stg = 0xeB9F;
static int stop, duration;
@@ -85,21 +90,26 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
socklen_t addrlen = sizeof(sa6);
void *thread_ret;
char batch[1500];
+ int proto = 0;
int err;
WRITE_ONCE(stop, 0);
- lfd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (!strcmp(tcp_ca, "bpf_first"))
+ proto = IPPROTO_MPTCP;
+
+ lfd = socket(AF_INET6, SOCK_STREAM, proto);
if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
return;
- fd = socket(AF_INET6, SOCK_STREAM, 0);
+ fd = socket(AF_INET6, SOCK_STREAM, proto);
if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
close(lfd);
return;
}
- if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
- settimeo(lfd, 0) || settimeo(fd, 0))
+ if (!proto &&
+ (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+ settimeo(lfd, 0) || settimeo(fd, 0)))
goto done;
/* bind, listen and start server thread to accept */
@@ -324,6 +334,28 @@ static void test_rel_setsockopt(void)
bpf_dctcp_release__destroy(rel_skel);
}
+static void test_first(void)
+{
+ struct bpf_first *first_skel;
+ 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");
+ do_test("bpf_first", NULL);
+
+ bpf_link__destroy(link);
+ bpf_first__destroy(first_skel);
+}
+
void test_bpf_tcp_ca(void)
{
if (test__start_subtest("dctcp"))
@@ -336,4 +368,6 @@ void test_bpf_tcp_ca(void)
test_dctcp_fallback();
if (test__start_subtest("rel_setsockopt"))
test_rel_setsockopt();
+ if (test__start_subtest("first"))
+ test_first();
}
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread