diff options
| -rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 22 | ||||
| -rw-r--r-- | net/core/filter.c | 6 | ||||
| -rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 41 |
3 files changed, 65 insertions, 4 deletions
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 70f6fd4fa305..d6731c32864e 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -28,6 +28,7 @@ struct bpf_struct_ops_value { struct bpf_struct_ops_map { struct bpf_map map; + struct rcu_head rcu; const struct bpf_struct_ops *st_ops; /* protect map_update */ struct mutex lock; @@ -622,6 +623,14 @@ bool bpf_struct_ops_get(const void *kdata) return refcount_inc_not_zero(&kvalue->refcnt); } +static void bpf_struct_ops_put_rcu(struct rcu_head *head) +{ + struct bpf_struct_ops_map *st_map; + + st_map = container_of(head, struct bpf_struct_ops_map, rcu); + bpf_map_put(&st_map->map); +} + void bpf_struct_ops_put(const void *kdata) { struct bpf_struct_ops_value *kvalue; @@ -632,6 +641,17 @@ void bpf_struct_ops_put(const void *kdata) st_map = container_of(kvalue, struct bpf_struct_ops_map, kvalue); - bpf_map_put(&st_map->map); + /* The struct_ops's function may switch to another struct_ops. + * + * For example, bpf_tcp_cc_x->init() may switch to + * another tcp_cc_y by calling + * setsockopt(TCP_CONGESTION, "tcp_cc_y"). + * During the switch, bpf_struct_ops_put(tcp_cc_x) is called + * and its map->refcnt may reach 0 which then free its + * trampoline image while tcp_cc_x is still running. + * + * Thus, a rcu grace period is needed here. + */ + call_rcu(&st_map->rcu, bpf_struct_ops_put_rcu); } } diff --git a/net/core/filter.c b/net/core/filter.c index cfbd01167eb5..2e32cee2c469 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5051,6 +5051,12 @@ err_clear: BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { + if (level == SOL_TCP && optname == TCP_CONGESTION) { + if (optlen >= sizeof("cdg") - 1 && + !strncmp("cdg", optval, optlen)) + return -ENOTSUPP; + } + return _bpf_setsockopt(sk, level, optname, optval, optlen); } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 9e41eff4a685..0dcee9df1326 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -10,6 +10,9 @@ #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. */ +extern struct bpf_struct_ops bpf_tcp_congestion_ops; + static u32 optional_ops[] = { offsetof(struct tcp_congestion_ops, init), offsetof(struct tcp_congestion_ops, release), @@ -163,6 +166,19 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = { .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 = bpf_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) @@ -174,6 +190,28 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, 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; default: return bpf_base_func_proto(func_id); } @@ -286,9 +324,6 @@ static void bpf_tcp_ca_unreg(void *kdata) tcp_unregister_congestion_control(kdata); } -/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; - struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, |