[PATCH v2 bpf-next 0/2] BPF iterator for UNIX domain socket.

[PATCH v2 bpf-next 0/2] BPF iterator for UNIX domain socket.

[Kuniyuki Iwashima]

This patch set adds BPF iterator support for UNIX domain socket.  The first
patch implements it and the second adds a selftest.


Changelog:
  v2:
  - 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/


Kuniyuki Iwashima (2):
  bpf: af_unix: Implement BPF iterator for UNIX domain socket.
  selftest/bpf: Implement sample UNIX domain socket iterator program.

 include/linux/btf_ids.h                       |  3 +-
 net/unix/af_unix.c                            | 93 +++++++++++++++++++
 .../selftests/bpf/prog_tests/bpf_iter.c       | 16 ++++
 tools/testing/selftests/bpf/progs/bpf_iter.h  |  8 ++
 .../selftests/bpf/progs/bpf_iter_unix.c       | 86 +++++++++++++++++
 .../selftests/bpf/progs/bpf_tracing_net.h     |  4 +
 6 files changed, 209 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_unix.c

-- 
2.30.2

[PATCH v2 bpf-next 1/2] bpf: af_unix: Implement BPF iterator for UNIX domain socket.

[Kuniyuki Iwashima]

This patch implements the BPF iterator for the UNIX domain socket.

Currently, the batch optimization introduced for the TCP iterator in the
commit 04c7820b776f ("bpf: tcp: Bpf iter batching and lock_sock") is not
applied.  It will require replacing the big lock for the hash table with
small locks for each hash list not to block other processes.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
 include/linux/btf_ids.h |  3 +-
 net/unix/af_unix.c      | 93 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+), 1 deletion(-)

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 57890b357f85..bed4b9964581 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -172,7 +172,8 @@ extern struct btf_id_set name;
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)
 
 enum {
 #define BTF_SOCK_TYPE(name, str) name,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 256c4e31132e..675ed1f3107e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -113,6 +113,7 @@
 #include <linux/security.h>
 #include <linux/freezer.h>
 #include <linux/file.h>
+#include <linux/btf_ids.h>
 
 #include "scm.h"
 
@@ -2982,6 +2983,64 @@ static const struct seq_operations unix_seq_ops = {
 	.stop   = unix_seq_stop,
 	.show   = unix_seq_show,
 };
+
+#ifdef CONFIG_BPF_SYSCALL
+struct bpf_iter__unix {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct unix_sock *, unix_sk);
+	uid_t uid __aligned(8);
+};
+
+static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
+			      struct unix_sock *unix_sk, uid_t uid)
+{
+	struct bpf_iter__unix ctx;
+
+	meta->seq_num--;  /* skip SEQ_START_TOKEN */
+	ctx.meta = meta;
+	ctx.unix_sk = unix_sk;
+	ctx.uid = uid;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	struct sock *sk = v;
+	uid_t uid;
+
+	if (v == SEQ_START_TOKEN)
+		return 0;
+
+	uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	return unix_prog_seq_show(prog, &meta, v, uid);
+}
+
+static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)unix_prog_seq_show(prog, &meta, v, 0);
+	}
+
+	unix_seq_stop(seq, v);
+}
+
+static const struct seq_operations bpf_iter_unix_seq_ops = {
+	.start	= unix_seq_start,
+	.next	= unix_seq_next,
+	.stop	= bpf_iter_unix_seq_stop,
+	.show	= bpf_iter_unix_seq_show,
+};
+#endif
 #endif
 
 static const struct net_proto_family unix_family_ops = {
@@ -3022,6 +3081,35 @@ static struct pernet_operations unix_net_ops = {
 	.exit = unix_net_exit,
 };
 
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta,
+		     struct unix_sock *unix_sk, uid_t uid)
+
+static const struct bpf_iter_seq_info unix_seq_info = {
+	.seq_ops		= &bpf_iter_unix_seq_ops,
+	.init_seq_private	= bpf_iter_init_seq_net,
+	.fini_seq_private	= bpf_iter_fini_seq_net,
+	.seq_priv_size		= sizeof(struct seq_net_private),
+};
+
+static struct bpf_iter_reg unix_reg_info = {
+	.target			= "unix",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__unix, unix_sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &unix_seq_info,
+};
+
+static void __init bpf_iter_register(void)
+{
+	unix_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UNIX];
+	if (bpf_iter_reg_target(&unix_reg_info))
+		pr_warn("Warning: could not register bpf iterator unix\n");
+}
+#endif
+
 static int __init af_unix_init(void)
 {
 	int rc = -1;
@@ -3037,6 +3125,11 @@ static int __init af_unix_init(void)
 	sock_register(&unix_family_ops);
 	register_pernet_subsys(&unix_net_ops);
 	unix_bpf_build_proto();
+
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	bpf_iter_register();
+#endif
+
 out:
 	return rc;
 }
-- 
2.30.2

Re: [PATCH v2 bpf-next 1/2] bpf: af_unix: Implement BPF iterator for UNIX domain socket.

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 1773 bytes --]

Hi Kuniyuki,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on bpf-next/master]

url:    https://github.com/0day-ci/linux/commits/Kuniyuki-Iwashima/BPF-iterator-for-UNIX-domain-socket/20210803-091232
base:   https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
config: powerpc64-randconfig-r002-20210803 (attached as .config)
compiler: powerpc-linux-gcc (GCC) 10.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/0day-ci/linux/commit/bba6a9ec76322618d01e32307b865dbbffe05903
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Kuniyuki-Iwashima/BPF-iterator-for-UNIX-domain-socket/20210803-091232
        git checkout bba6a9ec76322618d01e32307b865dbbffe05903
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-10.3.0 make.cross ARCH=powerpc64 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>, old ones prefixed by <<):

>> ERROR: modpost: "bpf_iter_fini_seq_net" [net/unix/unix.ko] undefined!
>> ERROR: modpost: "bpf_iter_run_prog" [net/unix/unix.ko] undefined!
>> ERROR: modpost: "bpf_iter_get_info" [net/unix/unix.ko] undefined!
>> ERROR: modpost: "bpf_iter_reg_target" [net/unix/unix.ko] undefined!
>> ERROR: modpost: "btf_sock_ids" [net/unix/unix.ko] undefined!
>> ERROR: modpost: "bpf_iter_init_seq_net" [net/unix/unix.ko] undefined!

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 38307 bytes --]

[PATCH v2 bpf-next 2/2] selftest/bpf: Implement sample UNIX domain socket iterator program.

[Kuniyuki Iwashima]

If there are no abstract sockets, this prog can output the same result
compared to /proc/net/unix.

  # cat /sys/fs/bpf/unix | head -n 2
  Num       RefCount Protocol Flags    Type St Inode Path
  ffff9ab7122db000: 00000002 00000000 00010000 0001 01 10623 private/defer

  # cat /proc/net/unix | head -n 2
  Num       RefCount Protocol Flags    Type St Inode Path
  ffff9ab7122db000: 00000002 00000000 00010000 0001 01 10623 private/defer

According to the analysis by Yonghong Song (See the link), the BPF verifier
cannot load the code in the comment to print the name of the abstract UNIX
domain socket due to LLVM optimisation.  It can be uncommented once the
LLVM code gen is improved.

Link: https://lore.kernel.org/netdev/1994df05-8f01-371f-3c3b-d33d7836878c@fb.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
 .../selftests/bpf/prog_tests/bpf_iter.c       | 16 ++++
 tools/testing/selftests/bpf/progs/bpf_iter.h  |  8 ++
 .../selftests/bpf/progs/bpf_iter_unix.c       | 86 +++++++++++++++++++
 .../selftests/bpf/progs/bpf_tracing_net.h     |  4 +
 4 files changed, 114 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_unix.c

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 1f1aade56504..77ac24b191d4 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -13,6 +13,7 @@
 #include "bpf_iter_tcp6.skel.h"
 #include "bpf_iter_udp4.skel.h"
 #include "bpf_iter_udp6.skel.h"
+#include "bpf_iter_unix.skel.h"
 #include "bpf_iter_test_kern1.skel.h"
 #include "bpf_iter_test_kern2.skel.h"
 #include "bpf_iter_test_kern3.skel.h"
@@ -313,6 +314,19 @@ static void test_udp6(void)
 	bpf_iter_udp6__destroy(skel);
 }
 
+static void test_unix(void)
+{
+	struct bpf_iter_unix *skel;
+
+	skel = bpf_iter_unix__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_unix__open_and_load"))
+		return;
+
+	do_dummy_read(skel->progs.dump_unix);
+
+	bpf_iter_unix__destroy(skel);
+}
+
 /* The expected string is less than 16 bytes */
 static int do_read_with_fd(int iter_fd, const char *expected,
 			   bool read_one_char)
@@ -1255,6 +1269,8 @@ void test_bpf_iter(void)
 		test_udp4();
 	if (test__start_subtest("udp6"))
 		test_udp6();
+	if (test__start_subtest("unix"))
+		test_unix();
 	if (test__start_subtest("anon"))
 		test_anon_iter(false);
 	if (test__start_subtest("anon-read-one-char"))
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index 3d83b185c4bc..d92648621bcb 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__((aligned(8)));
+} __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..048844ee4f32
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
@@ -0,0 +1,86 @@
+// 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 %5lu",
+		       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 {
+			BPF_SEQ_PRINTF(seq, " @");
+
+			/* 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().
+			 * However, the BPF verifier cannot load the code below
+			 * because of the optimisation by LLVM.  So, print only
+			 * the first escaped byte here for now.  Once LLVM code
+			 * gen is improved, remove the BPF_SEQ_PRINTF() above
+			 * and uncomment the code below.
+			 *
+			 * int i, len;
+			 *
+			 * len = unix_sk->addr->len - sizeof(short);
+			 *
+			 * BPF_SEQ_PRINTF(seq, " @");
+			 *
+			 * // unix_mkname() tests this upper bound.
+			 * if (len < sizeof(struct sockaddr_un))
+			 *	for (i = 1 ; i < len; i++)
+			 *		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
-- 
2.30.2