add mptcp_subflow bpf_iter
Subsystems (5)
Geliang Tang
reviewerv2 cover add mptcp_subflow bpf_iter
From: Geliang Tang <[email protected]>
v2:
- update patch 1 as Martin and Andrii suggested.
- fix warnings and errors reported by MPTCP CI.
This patch set adds a mptcp_subflow type bpf_iter, and self tests.
Geliang Tang (4):
bpf: Add mptcp_subflow bpf_iter
bpf: Register mptcp tracing kfunc set selftests/bpf: Add mptcp_subflow bpf_iter test prog selftests/bpf: Add mptcp_subflow bpf_iter subtest
net/mptcp/bpf.c | 58 ++++++++++++- net/mptcp/protocol.h | 6 ++ .../testing/selftests/bpf/bpf_experimental.h | 7 ++ .../testing/selftests/bpf/prog_tests/mptcp.c | 85 +++++++++++++++++++ tools/testing/selftests/bpf/progs/mptcp_bpf.h | 4 + .../selftests/bpf/progs/mptcp_bpf_iter.c | 38 +++++++++ 6 files changed, 197 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_iter.c
Signature · 1 line
2.43.0
Geliang Tang
reviewerPATCH v2 1/4 bpf: Add mptcp_subflow bpf_iter
From: Geliang Tang <[email protected]>
It's necessary to traverse all subflows on the conn_list of an MPTCP socket and then call kfunc to modify the fields of each subflow. In kernel space, mptcp_for_each_subflow() helper is used for this:
mptcp_for_each_subflow(msk, subflow) kfunc(subflow);
But in the MPTCP BPF program, this has not yet been implemented. As Martin suggested recently, this conn_list walking + modify-by-kfunc usage fits the bpf_iter use case. So this patch adds a new bpf_iter type named "mptcp_subflow" to do this and implements its helpers bpf_iter_mptcp_subflow_new()/_next()/_destroy().
Then bpf_for_each() for mptcp_subflow can be used in BPF program like this:
bpf_rcu_read_lock(); bpf_for_each(mptcp_subflow, subflow, msk) kfunc(subflow); bpf_rcu_read_unlock();
--- net/mptcp/bpf.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ net/mptcp/protocol.h | 6 ++++++ 2 files changed, 57 insertions(+)
net/mptcp/bpf.c +51 -0
@@ -204,10 +204,59 @@ static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = { .set = &bpf_mptcp_fmodret_ids, }; +struct bpf_iter__mptcp_subflow { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct mptcp_sock *, msk); + __bpf_md_ptr(struct list_head *, pos); +}; + +struct bpf_iter_mptcp_subflow { +__u64 __opaque[2 ]; +} __attribute__((aligned (8 ))); + +struct bpf_iter_mptcp_subflow_kern { +struct mptcp_sock *msk; +struct list_head *pos; +} __attribute__((aligned (8 ))); +__diag_push ();__diag_ignore_all ("-Wmissing-prototypes" ,"kfuncs which will be used in BPF programs" ); +__bpf_kfunc_start_defs (); + +__bpf_kfunc int bpf_iter_mptcp_subflow_new(struct bpf_iter_mptcp_subflow *it, +struct mptcp_sock *msk) +{ +struct bpf_iter_mptcp_subflow_kern *kit = (void *)it; + +if (!msk) +return -EINVAL ; + + kit->msk = msk; + kit->pos = &msk->conn_list; +return 0 ; +} + +__bpf_kfunc struct mptcp_subflow_context * +bpf_iter_mptcp_subflow_next (struct bpf_iter_mptcp_subflow *it) +{ +struct bpf_iter_mptcp_subflow_kern *kit = (void *)it; +struct mptcp_subflow_context *subflow; +struct mptcp_sock *msk = kit->msk; + + subflow = list_entry((kit->pos)->next, struct mptcp_subflow_context, node); +if (!msk ||list_entry_is_head (subflow, &msk->conn_list, node)) +return NULL ; + + kit->pos = &subflow->node; +return subflow; +} + +__bpf_kfunc void bpf_iter_mptcp_subflow_destroy(struct bpf_iter_mptcp_subflow *it) +{ +} + __bpf_kfunc struct mptcp_subflow_context *bpf_mptcp_subflow_ctx_by_pos (const struct mptcp_sched_data *data,unsigned int pos) {
@@ -221,6 +270,8 @@ __bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk)return tcp_rtx_queue_empty (sk); } +__bpf_kfunc_end_defs (); +__diag_pop ();BTF_KFUNCS_START (bpf_mptcp_sched_kfunc_ids)
net/mptcp/protocol.h +6 -0
@@ -715,6 +715,12 @@ 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 bpf_iter_mptcp_subflow ; +int bpf_iter_mptcp_subflow_new (struct bpf_iter_mptcp_subflow *it, +struct mptcp_sock *msk); +struct mptcp_subflow_context * +bpf_iter_mptcp_subflow_next (struct bpf_iter_mptcp_subflow *it); +void bpf_iter_mptcp_subflow_destroy (struct bpf_iter_mptcp_subflow *it);bool bpf_mptcp_subflow_queues_empty (struct sock *sk);struct mptcp_subflow_context *bpf_mptcp_subflow_ctx_by_pos (const struct mptcp_sched_data *data,unsigned int pos);
Signature · 1 line
2.43.0
Geliang Tang
reviewerRe: [PATCH mptcp-next v2 1/4] bpf: Add mptcp_subflow bpf_iter
Quoted 40 lines · Geliang Tang
From: Geliang Tang <[email protected]>
It's necessary to traverse all subflows on the
conn_listof an MPTCP socket and then call kfunc to modify the fields of each subflow. In kernel space,mptcp_for_each_subflow()helper is used for this:mptcp_for_each_subflow(msk, subflow) kfunc(subflow);But in the MPTCP BPF program, this has not yet been implemented. As Martin suggested recently, this
conn_listwalking + modify-by-kfunc usage fits thebpf_iteruse case. So this patch adds a newbpf_itertype named "mptcp_subflow" to do this and implements its helpers bpf_iter_mptcp_subflow_new()/_next()/_destroy().Then
bpf_for_each()formptcp_subflowcan be used in BPF program like this:bpf_rcu_read_lock(); bpf_for_each(mptcp_subflow, subflow, msk) kfunc(subflow); bpf_rcu_read_unlock();Suggested-by Martin KaFai Lau <[email protected]>Signed-off-by Geliang Tang <[email protected]>---
net/mptcp/bpf.c | 51
++++++++++++++++++++++++++++++++++++++++++++
net/mptcp/protocol.h | 6 ++++++2 files changed, 57 insertions(+)net/mptcp/bpf.c +0
-0@@ -204,10 +204,59 @@ static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = { .set = &bpf_mptcp_fmodret_ids, };
net/mptcp/bpf.c static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = { · line 211
Quoted 5 lines
net/mptcp/bpf.c +5
-0+struct bpf_iter__mptcp_subflow { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct mptcp_sock *, msk); + __bpf_md_ptr(struct list_head *, pos); +};
This bpf_iter__mptcp_subflow struct should be dropped too.
Quoted 10 lines
net/mptcp/bpf.c +10
-0+ +struct bpf_iter_mptcp_subflow { +__u64 __opaque[2 ]; +} __attribute__((aligned (8 ))); + +struct bpf_iter_mptcp_subflow_kern { +struct mptcp_sock *msk; +struct list_head *pos; +} __attribute__((aligned (8 ))); +
Quoted 3 lines
__diag_push(); __diag_ignore_all("-Wmissing-prototypes",
"kfuncs which will be used in BPF programs");
Duplicate with __bpf_kfunc_start_defs/__bpf_kfunc_end_defs, __diag_push, __diag_pop and __diag_ignore_all should be dropped.
Quoted 59 lines
net/mptcp/bpf.c +3
-0+__bpf_kfunc_start_defs (); + +__bpf_kfunc int bpf_iter_mptcp_subflow_new(struct
bpf_iter_mptcp_subflow*it,net/mptcp/bpf.c +20
-0+ struct mptcp_sock *msk) +{ +struct bpf_iter_mptcp_subflow_kern *kit = (void *)it; + +if (!msk) +return -EINVAL ; + + kit->msk = msk; + kit->pos = &msk->conn_list; +return 0 ; +} + +__bpf_kfunc struct mptcp_subflow_context * +bpf_iter_mptcp_subflow_next (struct bpf_iter_mptcp_subflow *it) +{ +struct bpf_iter_mptcp_subflow_kern *kit = (void *)it; +struct mptcp_subflow_context *subflow; +struct mptcp_sock *msk = kit->msk; + + subflow = list_entry((kit->pos)->next, struct
mptcp_subflow_context, node);net/mptcp/bpf.c +1
-0+ if (!msk || list_entry_is_head(subflow, &msk->conn_list,node))
net/mptcp/bpf.c +7
-0+return NULL ; + + kit->pos = &subflow->node; +return subflow; +} + +__bpf_kfunc void bpf_iter_mptcp_subflow_destroy(struct
bpf_iter_mptcp_subflow*it)net/mptcp/bpf.c +3
-0+{ +} +__bpf_kfunc struct
mptcp_subflow_context*bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos)
{net/mptcp/bpf.c +0
-0@@ -221,6 +270,8 @@ __bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk) return tcp_rtx_queue_empty(sk); }net/mptcp/bpf.c +2
-0+__bpf_kfunc_end_defs (); +__diag_pop();
BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)net/mptcp/protocol.h +0
-0@@ -715,6 +715,12 @@ void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
net/mptcp/protocol.h void mptcp_subflow_queue_clean(struct sock *sk, · line 725
Quoted 10 lines
net/mptcp/protocol.h +6
-0void 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 bpf_iter_mptcp_subflow ; +int bpf_iter_mptcp_subflow_new (struct bpf_iter_mptcp_subflow *it, + struct mptcp_sock *msk); +struct mptcp_subflow_context * +bpf_iter_mptcp_subflow_next (struct bpf_iter_mptcp_subflow *it); +void bpf_iter_mptcp_subflow_destroy (struct bpf_iter_mptcp_subflow *it);
No need to add these declarations, since "-Wmissing-declarations" is ignored in __bpf_kfunc_start_defs.
Will update in v3.
Thanks,
-Geliang
Quoted 4 lines
net/mptcp/protocol.h +0
-0bool bpf_mptcp_subflow_queues_empty(struct sock *sk);struct
mptcp_subflow_context*bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos);
Geliang Tang
reviewerPATCH v2 2/4 bpf: Register mptcp tracing kfunc set
In reply to Geliang TangFrom: Geliang Tang <[email protected]>
Since the kfuncs mptcp_subflow_active() and mptcp_subflow_set_scheduled() are invoked in the mptcp_subflow bpf_iter test in a ftrace hook for mptcp_sched_get_send(), it's necessary to register them into a BPF_PROG_TYPE_TRACING type kfunc set together with the bpf_iter mptcp_subflow helpers bpf_iter_mptcp_subflow_new()/_next()/_destroy().
--- net/mptcp/bpf.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
net/mptcp/bpf.c +6 -1
@@ -275,9 +275,12 @@ __bpf_kfunc_end_defs();__diag_pop (); BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids) +BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_new) +BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_next) +BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_destroy) +BTF_ID_FLAGS(func, mptcp_subflow_active) 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)
@@ -295,6 +298,8 @@ static int __init bpf_mptcp_kfunc_init(void)int ret; ret =register_btf_fmodret_id_set (&bpf_mptcp_fmodret_set); + ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_TRACING , + &bpf_mptcp_sched_kfunc_set); ret = ret ?:register_btf_kfunc_id_set (BPF_PROG_TYPE_STRUCT_OPS , &bpf_mptcp_sched_kfunc_set);#ifdef CONFIG_BPF_JIT
Signature · 1 line
2.43.0
Geliang Tang
reviewerPATCH v2 3/4 selftests/bpf: Add mptcp_subflow bpf_iter test prog
In reply to Geliang TangFrom: Geliang Tang <[email protected]>
This patch adds a new mptcp bpf selftest program for the newly added mptcp_subflow bpf_iter.
Export bpf_iter_mptcp_subflow_new/_next/_destroy into bpf_experimental.h then use bpf_for_each(mptcp_subflow, subflow, msk) to walk the mptcp subflow list.
Add a ftrace hook for mptcp_sched_get_send() to do this test and invoke kfuncs mptcp_subflow_active() and mptcp_subflow_set_scheduled() in the loops.
--- .../testing/selftests/bpf/bpf_experimental.h | 7 ++++ tools/testing/selftests/bpf/progs/mptcp_bpf.h | 4 ++ .../selftests/bpf/progs/mptcp_bpf_iter.c | 38 +++++++++++++++++++ 3 files changed, 49 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_iter.c
tools/testing/selftests/bpf/bpf_experimental.h +7 -0
@@ -549,6 +549,13 @@ extern int bpf_iter_css_new(struct bpf_iter_css *it,extern struct cgroup_subsys_state *bpf_iter_css_next (struct bpf_iter_css *it)__weak __ksym; extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym; +struct bpf_iter_mptcp_subflow ; +extern int bpf_iter_mptcp_subflow_new(struct bpf_iter_mptcp_subflow *it, + struct mptcp_sock *msk) __weak __ksym; +extern struct mptcp_subflow_context * +bpf_iter_mptcp_subflow_next (struct bpf_iter_mptcp_subflow *it)__weak __ksym; +extern void bpf_iter_mptcp_subflow_destroy(struct bpf_iter_mptcp_subflow *it) __weak __ksym; + extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym; extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym; extern int bpf_wq_set_callback_impl(struct bpf_wq *wq,
tools/testing/selftests/bpf/progs/mptcp_bpf.h +4 -0
@@ -43,9 +43,13 @@ mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) }/* ksym */ +extern bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) __ksym; extern void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow, bool scheduled) __ksym; +extern void bpf_rcu_read_lock(void) __ksym; +extern void bpf_rcu_read_unlock(void) __ksym; +extern struct mptcp_subflow_context *bpf_mptcp_subflow_ctx_by_pos (const struct mptcp_sched_data *data,unsigned int pos) __ksym;
tools/testing/selftests/bpf/progs/mptcp_bpf_iter.c new file +38 -0
@@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Kylin Software */ + +/* vmlinux.h, bpf_helpers.h and other 'define' */ +#include "bpf_tracing_net.h" +#include "mptcp_bpf.h" + +char _license[] SEC("license") = "GPL"; +int iter =0 ; +int pid; + +SEC("fentry/mptcp_sched_get_send") +int BPF_PROG (trace_mptcp_sched_get_send ,struct mptcp_sock *msk) +{ +struct mptcp_subflow_context *subflow; +int i =0 ; + +if (bpf_get_current_pid_tgid () >>32 != pid) +return 0 ; + +bpf_rcu_read_lock (); +bpf_for_each (mptcp_subflow, subflow, msk) { +if (i++ >=MPTCP_SUBFLOWS_MAX ) +break ; + +if (subflow->token != msk->token) +break ; + +if (!mptcp_subflow_active (subflow)) +continue ; + +mptcp_subflow_set_scheduled (subflow, false); + } +bpf_rcu_read_unlock (); + + iter = i; +return 0 ; +}
Signature · 1 line
2.43.0
Geliang Tang
reviewerPATCH v2 4/4 selftests/bpf: Add mptcp_subflow bpf_iter subtest
In reply to Geliang TangFrom: Geliang Tang <[email protected]>
This patch adds a subtest named test_bpf_iter to load and verify the newly added mptcp_subflow type bpf_iter example in test_mptcp. Use endpoint_init() to add a new subflow endpoint. A new helper recv_send() is invoked to trigger the ftrace hook for mptcp_sched_get_send() after wait_for_new_subflows(). Check if skel->bss->iter equals 2 to verify whether the ftrace program loops twice as expected.
--- .../testing/selftests/bpf/prog_tests/mptcp.c | 85 +++++++++++++++++++ 1 file changed, 85 insertions(+)
tools/testing/selftests/bpf/prog_tests/mptcp.c +85 -0
@@ -10,6 +10,7 @@#include "mptcp_sock.skel.h" #include "mptcpify.skel.h" #include "mptcp_subflow.skel.h" +#include "mptcp_bpf_iter.skel.h" #include "mptcp_bpf_first.skel.h" #include "mptcp_bpf_bkup.skel.h" #include "mptcp_bpf_rr.skel.h"
@@ -258,6 +259,34 @@ static void send_byte(int fd)ASSERT_EQ (write (fd, &b,sizeof (b)),1 ,"send single byte" ); } +static int recv_send (int server_fd) +{ +char buf[1 ]; +int ret, fd; +ssize_t n; + + fd =accept (server_fd,NULL ,NULL ); +if (!ASSERT_OK_FD (fd,"accept" )) +return -1 ; + + n =recv (fd, buf,sizeof (buf),0 ); +if (!ASSERT_GT (n,0 ,"recv" )) { + ret =-1 ; + goto close; + } + + n =send (fd, buf, n,0 ); +if (!ASSERT_GT (n,0 ,"send" )) { + ret =-1 ; + goto close; + } + + ret =0 ; +close: +close (fd); +return ret; +} +static int verify_mptcpify (int server_fd,int client_fd) {struct __mptcp_info info;
@@ -470,6 +499,60 @@ static void test_subflow(void)close (cgroup_fd); } +static void run_bpf_iter (void ) +{ +int server_fd, client_fd; + + server_fd =start_mptcp_server (AF_INET ,ADDR_1 ,PORT_1 ,0 ); +if (!ASSERT_OK_FD (server_fd,"start_mptcp_server" )) +return ; + + client_fd =connect_to_fd (server_fd,0 ); +if (!ASSERT_OK_FD (client_fd,"connect_to_fd" )) + goto close_server; + +send_byte (client_fd); +wait_for_new_subflows (client_fd); +recv_send (server_fd); + +close (client_fd); +close_server: +close (server_fd); +} + +static void test_bpf_iter (void ) +{ +struct mptcp_bpf_iter *skel; +struct nstoken *nstoken; +int err; + + skel =mptcp_bpf_iter__open_and_load (); +if (!ASSERT_OK_PTR (skel,"skel_open_load: mptcp_iter" )) +return ; + + skel->bss->pid =getpid (); + + err =mptcp_bpf_iter__attach (skel); +if (!ASSERT_OK (err,"skel_attach: mptcp_iter" )) + goto skel_destroy; + + nstoken =create_netns (); +if (!ASSERT_OK_PTR (nstoken,"create_netns: mptcp_iter" )) + goto skel_destroy; + +if (endpoint_init ("subflow" ) <0 ) + goto close_netns; + +run_bpf_iter (); + +ASSERT_EQ (skel->bss->iter,2 ,"iter" ); + +close_netns: +cleanup_netns (nstoken); +skel_destroy: +mptcp_bpf_iter__destroy (skel); +} +static struct nstoken *sched_init (char *flags,char *sched) {struct nstoken *nstoken;
@@ -651,6 +734,8 @@ void test_mptcp(void)test_mptcpify ();if (test__start_subtest ("subflow" ))test_subflow (); +if (test__start_subtest ("bpf_iter" )) +test_bpf_iter ();if (test__start_subtest ("default" ))test_default ();if (test__start_subtest ("first" ))
Signature · 1 line
2.43.0
Hi Geliang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- KVM Validation: normal: Success! ✅
- KVM Validation: debug: Success! ✅
- KVM Validation: btf (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/10765143216
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/47ba4265c94f
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=888193
If there are some issues, you can reproduce them using the same environment as the one used by the CI thanks to a docker image, e.g.:
$ cd [kernel source code]
$ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
--pull always mptcp/mptcp-upstream-virtme-docker:latest \
auto-normalFor more details:
https://github.com/multipath-tcp/mptcp-upstream-virtme-docker
Please note that despite all the efforts that have been already done to have a stable tests suite when executed on a public CI like here, it is possible some reported issues are not due to your modifications. Still, do not hesitate to help us improve that ;-)
Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (NGI0 Core)