Contributors: 22
| Author |
Tokens |
Token Proportion |
Commits |
Commit Proportion |
| Martin KaFai Lau |
895 |
61.13% |
9 |
15.25% |
| Peter Zijlstra |
225 |
15.37% |
1 |
1.69% |
| Kui-Feng Lee |
92 |
6.28% |
5 |
8.47% |
| Kumar Kartikeya Dwivedi |
61 |
4.17% |
5 |
8.47% |
| John Fastabend |
37 |
2.53% |
2 |
3.39% |
| Alexei Starovoitov |
24 |
1.64% |
8 |
13.56% |
| Daniel Borkmann |
23 |
1.57% |
5 |
8.47% |
| Jörn-Thorben Hinz |
19 |
1.30% |
1 |
1.69% |
| David Vernet |
11 |
0.75% |
1 |
1.69% |
| Linus Torvalds (pre-git) |
11 |
0.75% |
5 |
8.47% |
| Yixin Shen |
11 |
0.75% |
1 |
1.69% |
| Miao Xu |
10 |
0.68% |
2 |
3.39% |
| Lawrence Brakmo |
8 |
0.55% |
1 |
1.69% |
| Dmitrii Banshchikov |
6 |
0.41% |
1 |
1.69% |
| Andrii Nakryiko |
6 |
0.41% |
3 |
5.08% |
| Craig Gallek |
6 |
0.41% |
1 |
1.69% |
| Lorenz Bauer |
5 |
0.34% |
1 |
1.69% |
| Andrey Ignatov |
4 |
0.27% |
1 |
1.69% |
| Yonghong Song |
4 |
0.27% |
2 |
3.39% |
| Daniel Xu |
3 |
0.20% |
2 |
3.39% |
| Brenden Blanco |
2 |
0.14% |
1 |
1.69% |
| Hou Tao |
1 |
0.07% |
1 |
1.69% |
| Total |
1464 |
|
59 |
|
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/init.h>
#include <linux/types.h>
#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/filter.h>
#include <net/tcp.h>
#include <net/bpf_sk_storage.h>
/* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */
static struct bpf_struct_ops bpf_tcp_congestion_ops;
static const struct btf_type *tcp_sock_type;
static u32 tcp_sock_id, sock_id;
static const struct btf_type *tcp_congestion_ops_type;
static int bpf_tcp_ca_init(struct btf *btf)
{
s32 type_id;
type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT);
if (type_id < 0)
return -EINVAL;
sock_id = type_id;
type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT);
if (type_id < 0)
return -EINVAL;
tcp_sock_id = type_id;
tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT);
if (type_id < 0)
return -EINVAL;
tcp_congestion_ops_type = btf_type_by_id(btf, type_id);
return 0;
}
static bool bpf_tcp_ca_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info))
return false;
if (base_type(info->reg_type) == PTR_TO_BTF_ID &&
!bpf_type_has_unsafe_modifiers(info->reg_type) &&
info->btf_id == sock_id)
/* promote it to tcp_sock */
info->btf_id = tcp_sock_id;
return true;
}
static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
const struct bpf_reg_state *reg,
int off, int size)
{
const struct btf_type *t;
size_t end;
t = btf_type_by_id(reg->btf, reg->btf_id);
if (t != tcp_sock_type) {
bpf_log(log, "only read is supported\n");
return -EACCES;
}
switch (off) {
case offsetof(struct sock, sk_pacing_rate):
end = offsetofend(struct sock, sk_pacing_rate);
break;
case offsetof(struct sock, sk_pacing_status):
end = offsetofend(struct sock, sk_pacing_status);
break;
case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv):
end = offsetofend(struct inet_connection_sock, icsk_ca_priv);
break;
case offsetof(struct inet_connection_sock, icsk_ack.pending):
end = offsetofend(struct inet_connection_sock,
icsk_ack.pending);
break;
case offsetof(struct tcp_sock, snd_cwnd):
end = offsetofend(struct tcp_sock, snd_cwnd);
break;
case offsetof(struct tcp_sock, snd_cwnd_cnt):
end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
break;
case offsetof(struct tcp_sock, snd_cwnd_stamp):
end = offsetofend(struct tcp_sock, snd_cwnd_stamp);
break;
case offsetof(struct tcp_sock, snd_ssthresh):
end = offsetofend(struct tcp_sock, snd_ssthresh);
break;
case offsetof(struct tcp_sock, ecn_flags):
end = offsetofend(struct tcp_sock, ecn_flags);
break;
case offsetof(struct tcp_sock, app_limited):
end = offsetofend(struct tcp_sock, app_limited);
break;
default:
bpf_log(log, "no write support to tcp_sock at off %d\n", off);
return -EACCES;
}
if (off + size > end) {
bpf_log(log,
"write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n",
off, size, end);
return -EACCES;
}
return 0;
}
BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
{
/* bpf_tcp_ca prog cannot have NULL tp */
__tcp_send_ack((struct sock *)tp, rcv_nxt);
return 0;
}
static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
.func = bpf_tcp_send_ack,
.gpl_only = false,
/* In case we want to report error later */
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &tcp_sock_id,
.arg2_type = ARG_ANYTHING,
};
static u32 prog_ops_moff(const struct bpf_prog *prog)
{
const struct btf_member *m;
const struct btf_type *t;
u32 midx;
midx = prog->expected_attach_type;
t = tcp_congestion_ops_type;
m = &btf_type_member(t)[midx];
return __btf_member_bit_offset(t, m) / 8;
}
static const struct bpf_func_proto *
bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_tcp_send_ack:
return &bpf_tcp_send_ack_proto;
case BPF_FUNC_sk_storage_get:
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
case BPF_FUNC_setsockopt:
/* Does not allow release() to call setsockopt.
* release() is called when the current bpf-tcp-cc
* is retiring. It is not allowed to call
* setsockopt() to make further changes which
* may potentially allocate new resources.
*/
if (prog_ops_moff(prog) !=
offsetof(struct tcp_congestion_ops, release))
return &bpf_sk_setsockopt_proto;
return NULL;
case BPF_FUNC_getsockopt:
/* Since get/setsockopt is usually expected to
* be available together, disable getsockopt for
* release also to avoid usage surprise.
* The bpf-tcp-cc already has a more powerful way
* to read tcp_sock from the PTR_TO_BTF_ID.
*/
if (prog_ops_moff(prog) !=
offsetof(struct tcp_congestion_ops, release))
return &bpf_sk_getsockopt_proto;
return NULL;
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id, prog);
}
}
BTF_KFUNCS_START(bpf_tcp_ca_check_kfunc_ids)
BTF_ID_FLAGS(func, tcp_reno_ssthresh)
BTF_ID_FLAGS(func, tcp_reno_cong_avoid)
BTF_ID_FLAGS(func, tcp_reno_undo_cwnd)
BTF_ID_FLAGS(func, tcp_slow_start)
BTF_ID_FLAGS(func, tcp_cong_avoid_ai)
BTF_KFUNCS_END(bpf_tcp_ca_check_kfunc_ids)
static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = {
.owner = THIS_MODULE,
.set = &bpf_tcp_ca_check_kfunc_ids,
};
static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
.get_func_proto = bpf_tcp_ca_get_func_proto,
.is_valid_access = bpf_tcp_ca_is_valid_access,
.btf_struct_access = bpf_tcp_ca_btf_struct_access,
};
static int bpf_tcp_ca_init_member(const struct btf_type *t,
const struct btf_member *member,
void *kdata, const void *udata)
{
const struct tcp_congestion_ops *utcp_ca;
struct tcp_congestion_ops *tcp_ca;
u32 moff;
utcp_ca = (const struct tcp_congestion_ops *)udata;
tcp_ca = (struct tcp_congestion_ops *)kdata;
moff = __btf_member_bit_offset(t, member) / 8;
switch (moff) {
case offsetof(struct tcp_congestion_ops, flags):
if (utcp_ca->flags & ~TCP_CONG_MASK)
return -EINVAL;
tcp_ca->flags = utcp_ca->flags;
return 1;
case offsetof(struct tcp_congestion_ops, name):
if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name,
sizeof(tcp_ca->name)) <= 0)
return -EINVAL;
return 1;
}
return 0;
}
static int bpf_tcp_ca_reg(void *kdata, struct bpf_link *link)
{
return tcp_register_congestion_control(kdata);
}
static void bpf_tcp_ca_unreg(void *kdata, struct bpf_link *link)
{
tcp_unregister_congestion_control(kdata);
}
static int bpf_tcp_ca_update(void *kdata, void *old_kdata, struct bpf_link *link)
{
return tcp_update_congestion_control(kdata, old_kdata);
}
static int bpf_tcp_ca_validate(void *kdata)
{
return tcp_validate_congestion_control(kdata);
}
static u32 bpf_tcp_ca_ssthresh(struct sock *sk)
{
return 0;
}
static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
}
static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state)
{
}
static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
}
static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags)
{
}
static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample)
{
}
static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
{
return 0;
}
static void bpf_tcp_ca_cong_control(struct sock *sk, u32 ack, int flag,
const struct rate_sample *rs)
{
}
static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk)
{
return 0;
}
static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk)
{
return 0;
}
static void __bpf_tcp_ca_init(struct sock *sk)
{
}
static void __bpf_tcp_ca_release(struct sock *sk)
{
}
static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
.ssthresh = bpf_tcp_ca_ssthresh,
.cong_avoid = bpf_tcp_ca_cong_avoid,
.set_state = bpf_tcp_ca_set_state,
.cwnd_event = bpf_tcp_ca_cwnd_event,
.in_ack_event = bpf_tcp_ca_in_ack_event,
.pkts_acked = bpf_tcp_ca_pkts_acked,
.min_tso_segs = bpf_tcp_ca_min_tso_segs,
.cong_control = bpf_tcp_ca_cong_control,
.undo_cwnd = bpf_tcp_ca_undo_cwnd,
.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
.init = __bpf_tcp_ca_init,
.release = __bpf_tcp_ca_release,
};
static struct bpf_struct_ops bpf_tcp_congestion_ops = {
.verifier_ops = &bpf_tcp_ca_verifier_ops,
.reg = bpf_tcp_ca_reg,
.unreg = bpf_tcp_ca_unreg,
.update = bpf_tcp_ca_update,
.init_member = bpf_tcp_ca_init_member,
.init = bpf_tcp_ca_init,
.validate = bpf_tcp_ca_validate,
.name = "tcp_congestion_ops",
.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
.owner = THIS_MODULE,
};
static int __init bpf_tcp_ca_kfunc_init(void)
{
int ret;
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set);
ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops);
return ret;
}
late_initcall(bpf_tcp_ca_kfunc_init);