Merge branch 'BPF iterator for UNIX domain socket.'

Kuniyuki Iwashima says:

====================

This patch set adds BPF iterator support for UNIX domain socket.  The first
patch implements it, and the second adds "%c" support for BPF_SEQ_PRINTF().

Thanks to Yonghong Song for the fix [0] for the LLVM code gen.  The fix
prevents the LLVM compiler from transforming the loop exit condition '<' to
'!=', where the upper bound is not a constant.  The transformation leads
the verifier to interpret it as an infinite loop.

And thanks to Andrii Nakryiko for its workaround [1].

[0] https://reviews.llvm.org/D107483
[1] https://lore.kernel.org/netdev/CAEf4BzZ3sVx1m1mOCcPcuVPiY6cWEAO=6VGHDiXEs9ZVD-RoLg@mail.gmail.com/

Changelog:
  v6:
  - Align the header "Inde" column
  - Change int vars to __u64 not to break test_progs-no_alu32
  - Move the if statement into the for loop not to depend on the fix [0]
  - Drop the README change
  - Modify "%c" positive test patterns

  v5:
  https://lore.kernel.org/netdev/20210812164557.79046-1-kuniyu@amazon.co.jp/
  - Align header line of bpf_iter_unix.c
  - Add test for "%c"

  v4:
  https://lore.kernel.org/netdev/20210810092807.13190-1-kuniyu@amazon.co.jp/
  - Check IS_BUILTIN(CONFIG_UNIX)
  - Support "%c" in BPF_SEQ_PRINTF()
  - Uncomment the code to print the name of the abstract socket
  - Mention the LLVM fix in README.rst
  - Remove the 'aligned' attribute in bpf_iter.h
  - Keep the format string on a single line

  v3:
  https://lore.kernel.org/netdev/20210804070851.97834-1-kuniyu@amazon.co.jp/
  - Export some functions for CONFIG_UNIX=m

  v2:
  https://lore.kernel.org/netdev/20210803011110.21205-1-kuniyu@amazon.co.jp/
  - Implement bpf_iter specific seq_ops->stop()
  - Add bpf_iter__unix in bpf_iter.h
  - Move common definitions in selftest to bpf_tracing_net.h
  - Include the code for abstract UNIX domain socket as comment in selftest
  - Use ASSERT_OK_PTR() instead of CHECK()
  - Make ternary operators on single line

  v1:
  https://lore.kernel.org/netdev/20210729233645.4869-1-kuniyu@amazon.co.jp/
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

1 files changed, 80 insertions, 0 deletions

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;
+}