BPF packet scheduler
Subsystems (6)
v9 cover BPF packet scheduler
v9:
- patch 2: add the missing mptcp_sched_init() invoking in mptcp_proto_init().
- patch 5: set last_snd after invoking get_subflow().
- patch 7: merge the squash-to patch.
base-commit: export/20220402T105856
v8:
- use global sched_list instead of pernet sched_list.
- drop synchronize_rcu() in mptcp_unregister_scheduler().
- update mptcp_init_sched and mptcp_release_sched as Mat and Florian suggested.
- fix the build break in patch 8.
- depends on: "add skc_to_mptcp_sock" v14.
- export/20220325T055307
v7:
- add bpf_try_module_get in mptcp_init_sched.
- add bpf_module_put in mptcp_release_sched.
- rename bpf_first to mptcp_bpf_first.
- update commit logs.
v6:
- still use pernet sched_list, use current->nsproxy->net_ns in BPF context instead of using init_net.
- patch 1:
- use rcu_read_lock instead of spin_lock in mptcp_sched_find as Florian suggested.
- drop synchronize_rcu in sched_exit_net as Florian suggested.
- keep synchronize_rcu in mptcp_unregister_scheduler, otherwise, got a workqueue lockup in my test.
- update Makefile as Mat suggested.
- patch 2:
- add mptcp_sched_data_init to register default sched, instead of registering it in init_net.
- patch 5:
- move mptcp_sched_get_subflow to protocol.h as Mat suggested.
- patch 6:
- use current->nsproxy->net_ns instead of init_net.
- patch 8:
- add send_data to send more data, instead of send_byte.
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.
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.
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 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 | 17 ++- net/mptcp/protocol.h | 19 +++ net/mptcp/sched.c | 104 ++++++++++++++++ .../testing/selftests/bpf/bpf_mptcp_helpers.h | 12 ++ .../testing/selftests/bpf/prog_tests/mptcp.c | 114 ++++++++++++++++++ .../selftests/bpf/progs/mptcp_bpf_first.c | 30 +++++ 12 files changed, 433 insertions(+), 6 deletions(-) create mode 100644 net/mptcp/sched.c create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
Signature · 1 line
2.34.1
PATCH v9 1/8 mptcp: add struct mptcp_sched_ops
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 or delete or find a packet scheduler on mptcp_sched_list.
--- 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
include/net/mptcp.h +13 -0
@@ -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;
net/mptcp/Makefile +1 -1
@@ -2,7 +2,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o + mib.o pm_netlink.o sockopt.o sched.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
net/mptcp/protocol.h +3 -0
@@ -608,6 +608,9 @@ 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) {
net/mptcp/sched.c new file +56 -0
56 lines not on this page · raw message
Signature · 1 line
2.34.1
PATCH v9 2/8 mptcp: register default scheduler
In reply to Geliang TangThis patch defines the default packet scheduler mptcp_sched_default, register it in mptcp_sched_init(), which is invoked in mptcp_proto_init(). Skip deleting this default scheduler in mptcp_unregister_scheduler().
--- net/mptcp/protocol.c | 3 ++- net/mptcp/protocol.h | 2 ++ net/mptcp/sched.c | 14 ++++++++++++++ 3 files changed, 18 insertions(+), 1 deletion(-)
net/mptcp/protocol.c +2 -1
@@ -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;
@@ -3804,6 +3804,7 @@ 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 )
net/mptcp/protocol.h +2 -0
@@ -611,6 +611,8 @@ 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) {
net/mptcp/sched.c +14 -0
@@ -13,6 +13,12 @@#include <linux/spinlock.h> #include "protocol.h" +static struct mptcp_sched_ops mptcp_sched_default = { + .get_subflow = mptcp_subflow_get_send, + .name ="default" , + .owner =THIS_MODULE , +}; +static DEFINE_SPINLOCK (mptcp_sched_list_lock);static LIST_HEAD (mptcp_sched_list);
@@ -50,7 +56,15 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched)void mptcp_unregister_scheduler (struct mptcp_sched_ops *sched) { +if (sched == &mptcp_sched_default) +return ; +spin_lock (&mptcp_sched_list_lock);list_del_rcu (&sched->list);spin_unlock (&mptcp_sched_list_lock); } + +void mptcp_sched_init (void ) +{ +mptcp_register_scheduler (&mptcp_sched_default); +}
Signature · 1 line
2.34.1
PATCH v9 3/8 mptcp: add a new sysctl scheduler
In reply to Geliang TangThis patch adds a new sysctl, named scheduler, to support for selection of different schedulers. Export mptcp_get_scheduler helper to get this sysctl.
--- Documentation/networking/mptcp-sysctl.rst | 8 ++++++++ net/mptcp/ctrl.c | 14 ++++++++++++++ net/mptcp/protocol.h | 1 + 3 files changed, 23 insertions(+)
Documentation/networking/mptcp-sysctl.rst +8 -0
@@ -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"
net/mptcp/ctrl.c +14 -0
@@ -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)
net/mptcp/protocol.h +1 -0
@@ -586,6 +586,7 @@ 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);
Signature · 1 line
2.34.1
PATCH v9 4/8 mptcp: add sched in mptcp_sock
In reply to Geliang TangThis patch adds 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().
--- net/mptcp/protocol.c | 7 +++++++ net/mptcp/protocol.h | 4 ++++ net/mptcp/sched.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+)
net/mptcp/protocol.c +7 -0
@@ -2657,6 +2657,11 @@ static int mptcp_init_sock(struct sock *sk)if (ret)return ret; + ret =mptcp_init_sched (mptcp_sk (sk), +mptcp_sched_find (mptcp_get_scheduler (net))); +if (ret) +return ret; +/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */
@@ -2816,6 +2821,7 @@ static void __mptcp_destroy_sock(struct sock *sk)sk_stop_timer (sk, &sk->sk_timer);mptcp_data_unlock (sk); msk->pm.status =0 ; +mptcp_release_sched (msk);/* clears msk->subflow, allowing the following loop to close * even the initial subflow
@@ -2993,6 +2999,7 @@ 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;
net/mptcp/protocol.h +4 -0
@@ -288,6 +288,7 @@ 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 */
@@ -614,6 +615,9 @@ 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 ); +int 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) {
net/mptcp/sched.c +34 -0
@@ -68,3 +68,37 @@ void mptcp_sched_init(void) {mptcp_register_scheduler (&mptcp_sched_default); } + +int mptcp_init_sched (struct mptcp_sock *msk, +struct mptcp_sched_ops *sched) +{ +struct mptcp_sched_ops *sched_init = &mptcp_sched_default; + +if (sched) + sched_init = sched; + +if (!bpf_try_module_get (sched_init, sched_init->owner)) +return -EBUSY ; + + msk->sched = sched_init; +if (msk->sched->init) + msk->sched->init (msk); + +pr_debug ("sched=%s" , msk->sched->name); + +return 0 ; +} + +void mptcp_release_sched (struct mptcp_sock *msk) +{ +struct mptcp_sched_ops *sched = msk->sched; + +if (!sched) +return ; + + msk->sched =NULL ; +if (sched->release) + sched->release (msk); + +bpf_module_put (sched, sched->owner); +}
Signature · 1 line
2.34.1
PATCH v9 5/8 mptcp: add get_subflow wrapper
In reply to Geliang TangThis patch defines a new wrapper mptcp_sched_get_subflow(), invoke get_subflow() of msk->sched in it. Use the wrapper instead of using mptcp_subflow_get_send() directly.
Move the msk->last_snd setting out of get_subflow() of msk->sched, set it after invoking get_subflow() as the return value of it.
--- net/mptcp/protocol.c | 7 +++---- net/mptcp/protocol.h | 9 +++++++++ 2 files changed, 12 insertions(+), 4 deletions(-)
net/mptcp/protocol.c +3 -4
@@ -1507,7 +1507,6 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) subflow->avg_pacing_rate =div_u64 ((u64 )subflow->avg_pacing_rate * wmem +READ_ONCE (ssk->sk_pacing_rate) * burst, burst + wmem); - msk->last_snd = ssk; msk->snd_burst = burst;return ssk; }
@@ -1567,7 +1566,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)int ret =0 ; prev_ssk = ssk; - ssk =mptcp_subflow_get_send (msk); + ssk =mptcp_sched_get_subflow (msk);/* First check. If the ssk has changed since * the last round, release prev_ssk
@@ -1636,7 +1635,7 @@ 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_sched_get_subflow (mptcp_sk (sk));if (!xmit_ssk) goto out;if (xmit_ssk != ssk) {
@@ -3137,7 +3136,7 @@ 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_sched_get_subflow (mptcp_sk (sk));if (xmit_ssk == ssk)__mptcp_subflow_push_pending (sk, ssk);
net/mptcp/protocol.h +9 -0
@@ -619,6 +619,15 @@ int mptcp_init_sched(struct mptcp_sock *msk, struct mptcp_sched_ops *sched);void mptcp_release_sched (struct mptcp_sock *msk); +static inline struct sock *mptcp_sched_get_subflow (struct mptcp_sock *msk) +{ +struct sock *ssk =INDIRECT_CALL_INET_1 (msk->sched->get_subflow, + mptcp_subflow_get_send, msk); + + msk->last_snd = ssk; +return ssk; +} +static inline bool __mptcp_subflow_active (struct mptcp_subflow_context *subflow) {struct sock *ssk =mptcp_subflow_tcp_sock (subflow);
Signature · 1 line
2.34.1
PATCH v9 6/8 mptcp: add bpf_mptcp_sched_ops
In reply to Geliang TangThis patch implements a new struct bpf_struct_ops, bpf_mptcp_sched_ops. Register and unregister the bpf scheduler in .reg and .unreg.
This implementation is similar to BPF TCP CC. And some code in this patch is from bpf_tcp_ca.c
--- kernel/bpf/bpf_struct_ops_types.h | 4 ++ net/mptcp/bpf.c | 102 ++++++++++++++++++++++++++++++ 2 files changed, 106 insertions(+)
kernel/bpf/bpf_struct_ops_types.h +4 -0
@@ -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
net/mptcp/bpf.c +102 -0
110 lines not on this page · raw message
Signature · 1 line
2.34.1
PATCH v9 7/8 selftests: bpf: add bpf_first scheduler
In reply to Geliang TangThis patch implements the simplest MPTCP scheduler, named bpf_first, which always picks the first subflow to send data. It's a sample of MPTCP BPF scheduler implementations.
--- .../testing/selftests/bpf/bpf_mptcp_helpers.h | 12 ++++++++ .../selftests/bpf/progs/mptcp_bpf_first.c | 30 +++++++++++++++++++ 2 files changed, 42 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
tools/testing/selftests/bpf/bpf_mptcp_helpers.h +12 -0
@@ -14,4 +14,16 @@ struct mptcp_sock {char ca_name[TCP_CA_NAME_MAX ]; } __attribute__((preserve_access_index)); +#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; +}; +#endif
tools/testing/selftests/bpf/progs/mptcp_bpf_first.c new file +30 -0
@@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022, SUSE. */ + +#include <linux/bpf.h> +#include "bpf_mptcp_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" , +};
Signature · 1 line
2.34.1
PATCH v9 8/8 selftests: bpf: add bpf_first test
In reply to Geliang TangThis patch expends the MPTCP test base to support MPTCP packet scheduler tests. Add the bpf_first scheduler test in it. Use sysctl to set net.mptcp.scheduler to use this sched.
Some code in send_data() is from bpf_tcp_ca.c.
--- .../testing/selftests/bpf/prog_tests/mptcp.c | 114 ++++++++++++++++++ 1 file changed, 114 insertions(+)
tools/testing/selftests/bpf/prog_tests/mptcp.c +114 -0
@@ -4,6 +4,9 @@#include <test_progs.h> #include "cgroup_helpers.h" #include "network_helpers.h" +#include "mptcp_bpf_first.skel.h" + +#define min (a, b) ((a) < (b) ? (a) : (b))#ifndef TCP_CA_NAME_MAX #define TCP_CA_NAME_MAX 16
@@ -19,6 +22,8 @@ struct mptcp_storage { };static char monitor_log_path[64 ]; +static const unsigned int total_bytes =10 *1024 *1024 ; +static int stop, duration;static int verify_tsk (int map_fd,int client_fd) {
@@ -251,8 +256,117 @@ void test_base(void)close (cgroup_fd); } +static void *server (void *arg) +{ +int lfd = (int )(long )arg, err =0 , fd; +ssize_t nr_sent =0 , bytes =0 ; +char batch[1500 ]; + + fd =accept (lfd,NULL ,NULL ); +while (fd ==-1 ) { +if (errno ==EINTR ) +continue ; + err = -errno; + goto done; + } + +if (settimeo (fd,0 )) { + err = -errno; + goto done; + } + +while (bytes < total_bytes && !READ_ONCE (stop)) { + nr_sent =send (fd, &batch, +min (total_bytes - bytes,sizeof (batch)),0 ); +if (nr_sent ==-1 && errno ==EINTR ) +continue ; +if (nr_sent ==-1 ) { + err = -errno; +break ; + } + bytes += nr_sent; + } + +CHECK (bytes != total_bytes,"send" ,"%zd != %u nr_sent:%zd errno:%d\n" , + bytes, total_bytes, nr_sent, errno); + +done: +if (fd >=0 ) +close (fd); +if (err) { +WRITE_ONCE (stop,1 ); +return ERR_PTR (err); + } +return NULL ; +} + +static void send_data (int lfd,int fd) +{ +ssize_t nr_recv =0 , bytes =0 ; +pthread_t srv_thread; +void *thread_ret; +char batch[1500 ]; +int err; + +WRITE_ONCE (stop,0 ); + + err =pthread_create (&srv_thread,NULL , server, (void *)(long )lfd); +if (CHECK (err !=0 ,"pthread_create" ,"err:%d errno:%d\n" , err, errno)) +return ; + +/* recv total_bytes */ +while (bytes < total_bytes && !READ_ONCE (stop)) { + nr_recv =recv (fd, &batch, +min (total_bytes - bytes,sizeof (batch)),0 ); +if (nr_recv ==-1 && errno ==EINTR ) +continue ; +if (nr_recv ==-1 ) +break ; + bytes += nr_recv; + } + +CHECK (bytes != total_bytes,"recv" ,"%zd != %u nr_recv:%zd errno:%d\n" , + bytes, total_bytes, nr_recv, errno); + +WRITE_ONCE (stop,1 ); + +pthread_join (srv_thread, &thread_ret); +CHECK (IS_ERR (thread_ret),"pthread_join" ,"thread_ret:%ld" , +PTR_ERR (thread_ret)); +} + +static void test_first (void ) +{ +struct mptcp_bpf_first *first_skel; +int server_fd, client_fd; +struct bpf_link *link; + + first_skel =mptcp_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" )) { +mptcp_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_data (server_fd, client_fd); + +close (client_fd); +close (server_fd); +bpf_link__destroy (link); +mptcp_bpf_first__destroy (first_skel); +} +void test_mptcp (void ) {if (test__start_subtest ("base" ))test_base (); +if (test__start_subtest ("first" )) +test_first (); }
Signature · 1 line
2.34.1
Re: [PATCH mptcp-next v9 6/8] mptcp: add bpf_mptcp_sched_ops
In reply to Geliang TangQuoted 48 lines · Geliang Tang
This patch implements a new struct
bpf_struct_ops,bpf_mptcp_sched_ops. Register and unregister the bpf scheduler in .reg and .unreg.This implementation is similar to BPF TCP CC. And some code in this patch is from
bpf_tcp_ca.cSigned-off-by Geliang Tang <[email protected]>---
kernel/bpf/bpf_struct_ops_types.h| 4 ++net/mptcp/bpf.c| 102 ++++++++++++++++++++++++++++++2 files changed, 106 insertions(+)kernel/bpf/bpf_struct_ops_types.h +4
-0@@ -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 net/mptcp/bpf.c +12
-0@@ -10,8 +10,110 @@#define pr_fmt (fmt) "MPTCP: " fmt#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), +}; +
net/mptcp/bpf.c line 36
Quoted 10 lines
net/mptcp/bpf.c +10
-0+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,
Hi Geliang -
I'm mostly comparing this code to bpf_tcp_ca.c to try to get a frame of reference for how BPF works.
Using 'btf_ctx_access' here seems like a less strict check than what the CA code uses. bpf_tracing_btf_ctx_access() has more constraints like only allowing READs. What's the reasoning behind the difference? I want to be sure access is not more open than it needs to be.
net/mptcp/bpf.c line 37
Quoted 1 line
net/mptcp/bpf.c +1
-0+ .btf_struct_access = btf_struct_access,
Similar question here - bpf_tcp_ca.c has more strict checking.
- Mat
Quoted 87 lines
net/mptcp/bpf.c +79
-0+}; + +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))Signature · 1 line
2.34.1
--
Mat Martineau
Intel
Re: selftests: bpf: add bpf_first test: Tests Results
In reply to Geliang TangHi Geliang,
Thank you for your modifications, that's great!
Our CI did some validations and here is its report:
- KVM Validation: normal:
- Success! ✅:
- Task: https://cirrus-ci.com/task/6452376256118784
- Summary: https://api.cirrus-ci.com/v1/artifact/task/6452376256118784/summary/summary.txt
- KVM Validation: debug:
- Success! ✅:
- Task: https://cirrus-ci.com/task/5045001372565504
- Summary: https://api.cirrus-ci.com/v1/artifact/task/5045001372565504/summary/summary.txt
Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/1a4b8dbb4120
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 (Tessares)
Re: [PATCH mptcp-next v9 6/8] mptcp: add bpf_mptcp_sched_ops
In reply to Mat MartineauHi Mat,
Quoted 63 lines · Mat Martineau
Quoted 48 lines · Geliang Tang
This patch implements a new struct
bpf_struct_ops,bpf_mptcp_sched_ops. Register and unregister the bpf scheduler in .reg and .unreg.This implementation is similar to BPF TCP CC. And some code in this patch is from
bpf_tcp_ca.cSigned-off-by Geliang Tang <[email protected]>---
kernel/bpf/bpf_struct_ops_types.h| 4 ++net/mptcp/bpf.c| 102 ++++++++++++++++++++++++++++++2 files changed, 106 insertions(+)kernel/bpf/bpf_struct_ops_types.h +4
-0@@ -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 net/mptcp/bpf.c +12
-0@@ -10,8 +10,110 @@#define pr_fmt (fmt) "MPTCP: " fmt#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), +}; +net/mptcp/bpf.c line 36
Quoted 10 lines
net/mptcp/bpf.c +10
-0+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,Hi Geliang -
Quoted 7 lines
I'm mostly comparing this code to
bpf_tcp_ca.cto try to get a frame of reference for how BPF works.Using '
btf_ctx_access' here seems like a less strict check than what the CA code uses.bpf_tracing_btf_ctx_access()has more constraints like only allowing READs. What's the reasoning behind the difference? I want to be sure access is not more open than it needs to be.
I agree, bpf_tracing_btf_ctx_access() is much better. I sent a squash-to patch to fix this. I want to keep the accesses more generic, not do specific, additional checks unless we need them in the future. So I uesd btf_ctx_access and btf_struct_access.
Thanks,
-Geliang
Quoted 99 lines
net/mptcp/bpf.c line 37
Quoted 2 lines
net/mptcp/bpf.c +1
-0+ .btf_struct_access = btf_struct_access,Similar question here -
bpf_tcp_ca.chas more strict checking.- Mat
Quoted 87 lines
net/mptcp/bpf.c +79
-0+}; + +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))Signature · 1 line
2.34.1--
Mat Martineau
Intel
Re: [PATCH mptcp-next v9 6/8] mptcp: add bpf_mptcp_sched_ops
Quoted 74 lines · Geliang Tang
Hi Mat,
Quoted 63 lines · Mat Martineau
Quoted 48 lines · Geliang Tang
This patch implements a new struct
bpf_struct_ops,bpf_mptcp_sched_ops. Register and unregister the bpf scheduler in .reg and .unreg.This implementation is similar to BPF TCP CC. And some code in this patch is from
bpf_tcp_ca.cSigned-off-by Geliang Tang <[email protected]>---
kernel/bpf/bpf_struct_ops_types.h| 4 ++net/mptcp/bpf.c| 102 ++++++++++++++++++++++++++++++2 files changed, 106 insertions(+)kernel/bpf/bpf_struct_ops_types.h +4
-0@@ -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 net/mptcp/bpf.c +12
-0@@ -10,8 +10,110 @@#define pr_fmt (fmt) "MPTCP: " fmt#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), +}; +net/mptcp/bpf.c line 36
Quoted 10 lines
net/mptcp/bpf.c +10
-0+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,Hi Geliang -
Quoted 7 lines
I'm mostly comparing this code to
bpf_tcp_ca.cto try to get a frame of reference for how BPF works.Using '
btf_ctx_access' here seems like a less strict check than what the CA code uses.bpf_tracing_btf_ctx_access()has more constraints like only allowing READs. What's the reasoning behind the difference? I want to be sure access is not more open than it needs to be.
Quoted 5 lines
I agree,
bpf_tracing_btf_ctx_access()is much better. I sent a squash-to patch to fix this. I want to keep the accesses more generic, not do specific, additional checks unless we need them in the future. So I uesdbtf_ctx_accessandbtf_struct_access.
Ok, thanks for the squash-to patch.
Quoted 2 lines
Quoted 2 lines
net/mptcp/bpf.c line 37
Quoted 2 lines
net/mptcp/bpf.c +1
-0+ .btf_struct_access = btf_struct_access,
While I realize it's simpler to refer to the existing function, I think it's safer to add the BPF_READ check similar to what the BPF CA code does.
- Mat
Quoted 89 lines
Quoted 89 lines
Similar question here -
bpf_tcp_ca.chas more strict checking.- Mat
Quoted 84 lines
net/mptcp/bpf.c +79
-1+}; + +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
Quoted 10 lines
Quoted 8 lines
Quoted 3 lines
--
Mat Martineau
Intel
--
Mat Martineau
Intel