selftest/bpf: Implement sample UNIX domain socket iterator program.

The iterator can output almost the same result compared to /proc/net/unix.
The header line is aligned, and the Inode column uses "%8lu" because "%5lu"
can be easily overflown.

  # cat /sys/fs/bpf/unix
  Num               RefCount Protocol Flags    Type St    Inode Path
  ffff963c06689800: 00000002 00000000 00010000 0001 01    18697 private/defer
  ffff963c7c979c00: 00000002 00000000 00000000 0001 01   598245 @Hello@World@

  # cat /proc/net/unix
  Num       RefCount Protocol Flags    Type St Inode Path
  ffff963c06689800: 00000002 00000000 00010000 0001 01 18697 private/defer
  ffff963c7c979c00: 00000002 00000000 00000000 0001 01 598245 @Hello@World@

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210814015718.42704-4-kuniyu@amazon.co.jp

3 files changed, 92 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index 3d83b185c4bc..8cfaeba1ddbf 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -12,6 +12,7 @@
 #define tcp6_sock tcp6_sock___not_used
 #define bpf_iter__udp bpf_iter__udp___not_used
 #define udp6_sock udp6_sock___not_used
+#define bpf_iter__unix bpf_iter__unix___not_used
 #define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used
 #define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used
 #define bpf_iter__sockmap bpf_iter__sockmap___not_used
@@ -32,6 +33,7 @@
 #undef tcp6_sock
 #undef bpf_iter__udp
 #undef udp6_sock
+#undef bpf_iter__unix
 #undef bpf_iter__bpf_map_elem
 #undef bpf_iter__bpf_sk_storage_map
 #undef bpf_iter__sockmap
@@ -103,6 +105,12 @@ struct udp6_sock {
 	struct ipv6_pinfo inet6;
 } __attribute__((preserve_access_index));
 
+struct bpf_iter__unix {
+	struct bpf_iter_meta *meta;
+	struct unix_sock *unix_sk;
+	uid_t uid;
+} __attribute__((preserve_access_index));
+
 struct bpf_iter__bpf_map_elem {
 	struct bpf_iter_meta *meta;
 	struct bpf_map *map;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
new file mode 100644
index 000000000000..94423902685d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+
+static long sock_i_ino(const struct sock *sk)
+{
+	const struct socket *sk_socket = sk->sk_socket;
+	const struct inode *inode;
+	unsigned long ino;
+
+	if (!sk_socket)
+		return 0;
+
+	inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode;
+	bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino);
+	return ino;
+}
+
+SEC("iter/unix")
+int dump_unix(struct bpf_iter__unix *ctx)
+{
+	struct unix_sock *unix_sk = ctx->unix_sk;
+	struct sock *sk = (struct sock *)unix_sk;
+	struct seq_file *seq;
+	__u32 seq_num;
+
+	if (!unix_sk)
+		return 0;
+
+	seq = ctx->meta->seq;
+	seq_num = ctx->meta->seq_num;
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "Num               RefCount Protocol Flags    Type St    Inode Path\n");
+
+	BPF_SEQ_PRINTF(seq, "%pK: %08X %08X %08X %04X %02X %8lu",
+		       unix_sk,
+		       sk->sk_refcnt.refs.counter,
+		       0,
+		       sk->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0,
+		       sk->sk_type,
+		       sk->sk_socket ?
+		       (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTED : SS_UNCONNECTED) :
+		       (sk->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
+		       sock_i_ino(sk));
+
+	if (unix_sk->addr) {
+		if (!UNIX_ABSTRACT(unix_sk)) {
+			BPF_SEQ_PRINTF(seq, " %s", unix_sk->addr->name->sun_path);
+		} else {
+			/* The name of the abstract UNIX domain socket starts
+			 * with '\0' and can contain '\0'.  The null bytes
+			 * should be escaped as done in unix_seq_show().
+			 */
+			__u64 i, len;
+
+			len = unix_sk->addr->len - sizeof(short);
+
+			BPF_SEQ_PRINTF(seq, " @");
+
+			for (i = 1; i < len; i++) {
+				/* unix_mkname() tests this upper bound. */
+				if (i >= sizeof(struct sockaddr_un))
+					break;
+
+				BPF_SEQ_PRINTF(seq, "%c",
+					       unix_sk->addr->name->sun_path[i] ?:
+					       '@');
+			}
+		}
+	}
+
+	BPF_SEQ_PRINTF(seq, "\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 3af0998a0623..eef5646ddb19 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -5,6 +5,10 @@
 #define AF_INET			2
 #define AF_INET6		10
 
+#define __SO_ACCEPTCON		(1 << 16)
+#define UNIX_HASH_SIZE		256
+#define UNIX_ABSTRACT(unix_sk)	(unix_sk->addr->hash < UNIX_HASH_SIZE)
+
 #define SOL_TCP			6
 #define TCP_CONGESTION		13
 #define TCP_CA_NAME_MAX		16