From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, duanxiongchun@bytedance.com,
wangdongdong.6@bytedance.com, jiang.wang@bytedance.com,
Cong Wang <cong.wang@bytedance.com>,
John Fastabend <john.fastabend@gmail.com>,
Daniel Borkmann <daniel@iogearbox.net>,
Jakub Sitnicki <jakub@cloudflare.com>,
Lorenz Bauer <lmb@cloudflare.com>
Subject: [Patch bpf-next v2 1/9] sock_map: introduce BPF_SK_SKB_VERDICT
Date: Mon, 1 Mar 2021 18:37:35 -0800 [thread overview]
Message-ID: <20210302023743.24123-2-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210302023743.24123-1-xiyou.wangcong@gmail.com>
From: Cong Wang <cong.wang@bytedance.com>
Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is
confusing and more importantly we still want to distinguish them
from user-space. So 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.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@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 6c09d94be2e9..451530d41af7 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 {
@@ -442,6 +443,7 @@ 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);
@@ -489,5 +491,6 @@ static inline void skb_bpf_redirect_clear(struct sk_buff *skb)
{
skb->_sk_redir = 0;
}
+
#endif /* CONFIG_NET_SOCK_MSG */
#endif /* _LINUX_SKMSG_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b89af20cfa19..1a08ab00a45e 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 c859bc46d06c..afa803a1553e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2941,6 +2941,7 @@ 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 07f54015238a..5efd790f1b47 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -693,7 +693,7 @@ 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);
@@ -1010,6 +1010,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
}
skb_set_owner_r(skb, sk);
prog = READ_ONCE(psock->progs.stream_verdict);
+ if (!prog)
+ prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index dd53a7771d7e..3bddd9dd2da2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -155,6 +155,8 @@ static void sock_map_del_link(struct sock *sk,
strp_stop = true;
if (psock->saved_data_ready && stab->progs.stream_verdict)
verdict_stop = true;
+ if (psock->saved_data_ready && stab->progs.skb_verdict)
+ verdict_stop = true;
list_del(&link->list);
sk_psock_free_link(link);
}
@@ -227,7 +229,7 @@ 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;
@@ -256,6 +258,15 @@ 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);
@@ -265,6 +276,7 @@ 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;
@@ -296,6 +308,9 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
} else if (!stream_parser && stream_verdict && !psock->saved_data_ready) {
psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
sk_psock_start_verdict(sk,psock);
+ } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) {
+ psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+ sk_psock_start_verdict(sk, psock);
}
write_unlock_bh(&sk->sk_callback_lock);
return 0;
@@ -304,6 +319,9 @@ 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:
@@ -1468,6 +1486,9 @@ static 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 f2b915b20546..3f067d2d7584 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 b89af20cfa19..1a08ab00a45e 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
next prev parent reply other threads:[~2021-03-02 8:50 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-02 2:37 [Patch bpf-next v2 0/9] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP Cong Wang
2021-03-02 2:37 ` Cong Wang [this message]
2021-03-02 2:37 ` [Patch bpf-next v2 2/9] sock: introduce sk_prot->update_proto() Cong Wang
2021-03-02 16:22 ` Lorenz Bauer
2021-03-02 18:23 ` Cong Wang
2021-03-03 9:35 ` Lorenz Bauer
2021-03-03 18:20 ` Cong Wang
2021-03-04 9:30 ` Lorenz Bauer
2021-03-04 23:52 ` Cong Wang
2021-03-06 0:27 ` John Fastabend
2021-03-06 0:57 ` Cong Wang
2021-03-06 1:55 ` John Fastabend
2021-03-09 17:53 ` Cong Wang
2021-03-10 6:33 ` John Fastabend
2021-03-02 2:37 ` [Patch bpf-next v2 3/9] udp: implement ->sendmsg_locked() Cong Wang
2021-03-02 2:37 ` [Patch bpf-next v2 4/9] udp: implement ->read_sock() for sockmap Cong Wang
2021-03-03 6:26 ` Yonghong Song
2021-03-02 2:37 ` [Patch bpf-next v2 5/9] udp: add ->read_sock() and ->sendmsg_locked() to ipv6 Cong Wang
2021-03-02 16:23 ` Lorenz Bauer
2021-03-02 17:59 ` Cong Wang
2021-03-02 2:37 ` [Patch bpf-next v2 6/9] skmsg: extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Cong Wang
2021-03-02 2:37 ` [Patch bpf-next v2 7/9] udp: implement udp_bpf_recvmsg() for sockmap Cong Wang
2021-03-02 2:37 ` [Patch bpf-next v2 8/9] sock_map: update sock type checks for UDP Cong Wang
2021-03-03 6:37 ` Yonghong Song
2021-03-03 18:02 ` Cong Wang
2021-03-03 18:50 ` Yonghong Song
2021-03-02 2:37 ` [Patch bpf-next v2 9/9] selftests/bpf: add a test case for udp sockmap Cong Wang
2021-03-02 16:31 ` Lorenz Bauer
2021-03-02 18:05 ` Cong Wang
2021-03-03 10:20 ` Lorenz Bauer
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210302023743.24123-2-xiyou.wangcong@gmail.com \
--to=xiyou.wangcong@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=cong.wang@bytedance.com \
--cc=daniel@iogearbox.net \
--cc=duanxiongchun@bytedance.com \
--cc=jakub@cloudflare.com \
--cc=jiang.wang@bytedance.com \
--cc=john.fastabend@gmail.com \
--cc=lmb@cloudflare.com \
--cc=netdev@vger.kernel.org \
--cc=wangdongdong.6@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).