Merge branch 'bug fixes for sockmap'

Xu Kuohai says:

====================
bug fixes and a new test case for sockmap.

v3:
fix bpf ci failure

v2: https://lore.kernel.org/bpf/20230803064838.108784-1-xukuohai@huaweicloud.com
add a test case

v1:
https://lore.kernel.org/bpf/20230728105649.3978774-1-xukuohai@huaweicloud.com
https://lore.kernel.org/bpf/20230728105717.3978849-1-xukuohai@huaweicloud.com
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

Author: Martin KaFai Lau

include/linux/skmsg.h

@@ -62,6 +62,7 @@ struct sk_psock_progs {
 
 enum sk_psock_state_bits {
 	SK_PSOCK_TX_ENABLED,
+	SK_PSOCK_RX_STRP_ENABLED,
 };
 
 struct sk_psock_link {

net/core/skmsg.c

@@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 {
+	int ret;
+
 	static const struct strp_callbacks cb = {
 		.rcv_msg	= sk_psock_strp_read,
 		.read_sock_done	= sk_psock_strp_read_done,
 		.parse_msg	= sk_psock_strp_parse,
 	};
 
-	return strp_init(&psock->strp, sk, &cb);
+	ret = strp_init(&psock->strp, sk, &cb);
+	if (!ret)
+		sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
+
+	return ret;
 }
 
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
@@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 static void sk_psock_done_strp(struct sk_psock *psock)
 {
 	/* Parser has been stopped */
-	if (psock->progs.stream_parser)
+	if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED))
 		strp_done(&psock->strp);
 }
 #else

net/core/sock_map.c

@@ -146,13 +146,13 @@ static void sock_map_del_link(struct sock *sk,
 	list_for_each_entry_safe(link, tmp, &psock->link, list) {
 		if (link->link_raw == link_raw) {
 			struct bpf_map *map = link->map;
-			struct bpf_stab *stab = container_of(map, struct bpf_stab,
-							     map);
-			if (psock->saved_data_ready && stab->progs.stream_parser)
+			struct sk_psock_progs *progs = sock_map_progs(map);
+
+			if (psock->saved_data_ready && progs->stream_parser)
 				strp_stop = true;
-			if (psock->saved_data_ready && stab->progs.stream_verdict)
+			if (psock->saved_data_ready && progs->stream_verdict)
 				verdict_stop = true;
-			if (psock->saved_data_ready && stab->progs.skb_verdict)
+			if (psock->saved_data_ready && progs->skb_verdict)
 				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);

tools/testing/selftests/bpf/prog_tests/sockmap_listen.c

@@ -869,6 +869,77 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT);
 }
 
+static void redir_partial(int family, int sotype, int sock_map, int parser_map)
+{
+	int s, c0, c1, p0, p1;
+	int err, n, key, value;
+	char buf[] = "abc";
+
+	key = 0;
+	value = sizeof(buf) - 1;
+	err = xbpf_map_update_elem(parser_map, &key, &value, 0);
+	if (err)
+		return;
+
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
+	if (s < 0)
+		goto clean_parser_map;
+
+	err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1);
+	if (err)
+		goto close_srv;
+
+	err = add_to_sockmap(sock_map, p0, p1);
+	if (err)
+		goto close;
+
+	n = xsend(c1, buf, sizeof(buf), 0);
+	if (n < sizeof(buf))
+		FAIL("incomplete write");
+
+	n = xrecv_nonblock(c0, buf, sizeof(buf), 0);
+	if (n != sizeof(buf) - 1)
+		FAIL("expect %zu, received %d", sizeof(buf) - 1, n);
+
+close:
+	xclose(c0);
+	xclose(p0);
+	xclose(c1);
+	xclose(p1);
+close_srv:
+	xclose(s);
+
+clean_parser_map:
+	key = 0;
+	value = 0;
+	xbpf_map_update_elem(parser_map, &key, &value, 0);
+}
+
+static void test_skb_redir_partial(struct test_sockmap_listen *skel,
+				   struct bpf_map *inner_map, int family,
+				   int sotype)
+{
+	int verdict = bpf_program__fd(skel->progs.prog_stream_verdict);
+	int parser = bpf_program__fd(skel->progs.prog_stream_parser);
+	int parser_map = bpf_map__fd(skel->maps.parser_map);
+	int sock_map = bpf_map__fd(inner_map);
+	int err;
+
+	err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (err)
+		return;
+
+	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (err)
+		goto detach;
+
+	redir_partial(family, sotype, sock_map, parser_map);
+
+	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT);
+detach:
+	xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER);
+}
+
 static void test_reuseport_select_listening(int family, int sotype,
 					    int sock_map, int verd_map,
 					    int reuseport_prog)
@@ -1243,6 +1314,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 	} tests[] = {
 		TEST(test_skb_redir_to_connected),
 		TEST(test_skb_redir_to_listening),
+		TEST(test_skb_redir_partial),
 		TEST(test_msg_redir_to_connected),
 		TEST(test_msg_redir_to_listening),
 	};
@@ -1432,7 +1504,7 @@ static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd,
 	if (n < 1)
 		goto out;
 
-	n = recv(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), MSG_DONTWAIT);
+	n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0);
 	if (n < 0)
 		FAIL("%s: recv() err, errno=%d", log_prefix, errno);
 	if (n == 0)

tools/testing/selftests/bpf/progs/test_sockmap_listen.c

@@ -28,12 +28,26 @@ struct {
 	__type(value, unsigned int);
 } verdict_map SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} parser_map SEC(".maps");
+
 bool test_sockmap = false; /* toggled by user-space */
 bool test_ingress = false; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
 int prog_stream_parser(struct __sk_buff *skb)
 {
+	int *value;
+	__u32 key = 0;
+
+	value = bpf_map_lookup_elem(&parser_map, &key);
+	if (value && *value)
+		return *value;
+
 	return skb->len;
 }