From: Cong Wang <cong.w...@bytedance.com>
I was planning to reuse BPF_SK_SKB_STREAM_VERDICT but its name is
confusing and more importantly it seems kTLS relies on it to deliver
sk_msg too. To avoid messing up kTLS, we can just reuse the stream
verdict code but introduce a new type of eBPF program, skb_verdict.
Users are not allowed to set stream_verdict and skb_verdict at the
same time.
Cc: John Fastabend <john.fastab...@gmail.com>
Cc: Daniel Borkmann <dan...@iogearbox.net>
Cc: Jakub Sitnicki <ja...@cloudflare.com>
Cc: Lorenz Bauer <l...@cloudflare.com>
Signed-off-by: Cong Wang <cong.w...@bytedance.com>
---
include/linux/skmsg.h | 3 +++
include/uapi/linux/bpf.h | 1 +
kernel/bpf/syscall.c | 1 +
net/core/skmsg.c | 4 +++-
net/core/sock_map.c | 23 ++++++++++++++++++++++-
tools/bpf/bpftool/common.c | 1 +
tools/bpf/bpftool/prog.c | 1 +
tools/include/uapi/linux/bpf.h | 1 +
8 files changed, 33 insertions(+), 2 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 218566ac4fa1..cb79b1afa556 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -58,6 +58,7 @@ struct sk_psock_progs {
struct bpf_prog *msg_parser;
struct bpf_prog *stream_parser;
struct bpf_prog *stream_verdict;
+ struct bpf_prog *skb_verdict;
};
enum sk_psock_state_bits {
@@ -428,6 +429,7 @@ static inline void psock_progs_drop(struct sk_psock_progs
*progs)
psock_set_prog(&progs->msg_parser, NULL);
psock_set_prog(&progs->stream_parser, NULL);
psock_set_prog(&progs->stream_verdict, NULL);
+ psock_set_prog(&progs->skb_verdict, NULL);
}
int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
@@ -482,5 +484,6 @@ void skb_bpf_ext_redirect_clear(struct sk_buff *skb)
ext->flags = 0;
ext->sk_redir = NULL;
}
+
#endif /* CONFIG_NET_SOCK_MSG */
#endif /* _LINUX_SKMSG_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c001766adcbc..c1a412ebfb08 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -247,6 +247,7 @@ enum bpf_attach_type {
BPF_XDP_CPUMAP,
BPF_SK_LOOKUP,
BPF_XDP,
+ BPF_SK_SKB_VERDICT,
__MAX_BPF_ATTACH_TYPE
};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e5999d86c76e..a56549fc2825 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2936,6 +2936,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
return BPF_PROG_TYPE_SK_MSG;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
+ case BPF_SK_SKB_VERDICT:
return BPF_PROG_TYPE_SK_SKB;
case BPF_LIRC_MODE2:
return BPF_PROG_TYPE_LIRC_MODE2;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 51446fe63be5..ecbd6f0d49a5 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -688,7 +688,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
rcu_assign_sk_user_data(sk, NULL);
if (psock->progs.stream_parser)
sk_psock_stop_strp(sk, psock);
- else if (psock->progs.stream_verdict)
+ else if (psock->progs.stream_verdict || psock->progs.skb_verdict)
sk_psock_stop_verdict(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
@@ -966,6 +966,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc,
struct sk_buff *skb,
}
prog = READ_ONCE(psock->progs.stream_verdict);
+ if (!prog)
+ prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
skb_bpf_ext_redirect_clear(skb);
ret = sk_psock_bpf_run(psock, prog, skb);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 521663582982..f827f1ecefcc 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -152,6 +152,8 @@ static void sock_map_del_link(struct sock *sk,
strp_stop = true;
if (psock->bpf_running && stab->progs.stream_verdict)
verdict_stop = true;
+ if (psock->bpf_running && stab->progs.skb_verdict)
+ verdict_stop = true;
list_del(&link->list);
sk_psock_free_link(link);
}
@@ -224,7 +226,7 @@ static struct sk_psock *sock_map_psock_get_checked(struct
sock *sk)
static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
struct sock *sk)
{
- struct bpf_prog *msg_parser, *stream_parser, *stream_verdict;
+ struct bpf_prog *msg_parser, *stream_parser, *stream_verdict,
*skb_verdict;
struct sk_psock *psock;
int ret;
@@ -253,6 +255,15 @@ static int sock_map_link(struct bpf_map *map, struct
sk_psock_progs *progs,
}
}
+ skb_verdict = READ_ONCE(progs->skb_verdict);
+ if (skb_verdict) {
+ skb_verdict = bpf_prog_inc_not_zero(skb_verdict);
+ if (IS_ERR(skb_verdict)) {
+ ret = PTR_ERR(skb_verdict);
+ goto out_put_msg_parser;
+ }
+ }
+
psock = sock_map_psock_get_checked(sk);
if (IS_ERR(psock)) {
ret = PTR_ERR(psock);
@@ -262,6 +273,7 @@ static int sock_map_link(struct bpf_map *map, struct
sk_psock_progs *progs,
if (psock) {
if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
(stream_parser && READ_ONCE(psock->progs.stream_parser)) ||
+ (skb_verdict && READ_ONCE(psock->progs.skb_verdict)) ||
(stream_verdict && READ_ONCE(psock->progs.stream_verdict)))
{
sk_psock_put(sk, psock);
ret = -EBUSY;
@@ -293,6 +305,9 @@ static int sock_map_link(struct bpf_map *map, struct
sk_psock_progs *progs,
} else if (!stream_parser && stream_verdict && !psock->bpf_running) {
psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
sk_psock_start_verdict(sk,psock);
+ } else if (!stream_verdict && skb_verdict && !psock->bpf_running) {
+ psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+ sk_psock_start_verdict(sk, psock);
}
write_unlock_bh(&sk->sk_callback_lock);
return 0;
@@ -301,6 +316,9 @@ static int sock_map_link(struct bpf_map *map, struct
sk_psock_progs *progs,
out_drop:
sk_psock_put(sk, psock);
out_progs:
+ if (skb_verdict)
+ bpf_prog_put(skb_verdict);
+out_put_msg_parser:
if (msg_parser)
bpf_prog_put(msg_parser);
out_put_stream_parser:
@@ -1467,6 +1485,9 @@ int sock_map_prog_update(struct bpf_map *map, struct
bpf_prog *prog,
case BPF_SK_SKB_STREAM_VERDICT:
pprog = &progs->stream_verdict;
break;
+ case BPF_SK_SKB_VERDICT:
+ pprog = &progs->skb_verdict;
+ break;
default:
return -EOPNOTSUPP;
}
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 65303664417e..1828bba19020 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -57,6 +57,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
[BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser",
[BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict",
+ [BPF_SK_SKB_VERDICT] = "sk_skb_verdict",
[BPF_SK_MSG_VERDICT] = "sk_msg_verdict",
[BPF_LIRC_MODE2] = "lirc_mode2",
[BPF_FLOW_DISSECTOR] = "flow_dissector",
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 1fe3ba255bad..a78d8c03b7ea 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -76,6 +76,7 @@ enum dump_mode {
static const char * const attach_type_strings[] = {
[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
+ [BPF_SK_SKB_VERDICT] = "skb_verdict",
[BPF_SK_MSG_VERDICT] = "msg_verdict",
[BPF_FLOW_DISSECTOR] = "flow_dissector",
[__MAX_BPF_ATTACH_TYPE] = NULL,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c001766adcbc..c1a412ebfb08 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -247,6 +247,7 @@ enum bpf_attach_type {
BPF_XDP_CPUMAP,
BPF_SK_LOOKUP,
BPF_XDP,
+ BPF_SK_SKB_VERDICT,
__MAX_BPF_ATTACH_TYPE
};
--
2.25.1
