diff mbox series

[bpf-next,v5,05/11] sock_map: introduce BPF_SK_SKB_VERDICT

Message ID 20210317022219.24934-6-xiyou.wangcong@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series sockmap: introduce BPF_SK_SKB_VERDICT and support UDP | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 15 maintainers not CCed: sdf@google.com joe@cilium.io linux-api@vger.kernel.org yhs@fb.com kpsingh@kernel.org andrii@kernel.org kafai@fb.com ast@kernel.org tklauser@distanz.ch kuba@kernel.org tony.ambardar@gmail.com songliubraving@fb.com davem@davemloft.net quentin@isovalent.com zhuyifei@google.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 12261 this patch: 12261
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 12767 this patch: 12767
netdev/header_inline success Link

Commit Message

Cong Wang March 17, 2021, 2:22 a.m. UTC 
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          |  2 ++
 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, 32 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 0f5e663f6c7f..77e5d890ec4b 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 {
@@ -489,6 +490,7 @@  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);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2d3036e292a9..309a24582b18 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -957,6 +957,7 @@  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 d0a227b0f672..5cba52862334 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -708,7 +708,7 @@  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);
@@ -1035,6 +1035,8 @@  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 7c3589fc13bb..33f8c854db4f 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 2d3036e292a9..309a24582b18 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -957,6 +957,7 @@  enum bpf_attach_type {
 	BPF_XDP_CPUMAP,
 	BPF_SK_LOOKUP,
 	BPF_XDP,
+	BPF_SK_SKB_VERDICT,
 	__MAX_BPF_ATTACH_TYPE
 };