From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
To: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <kafai@fb.com>,
"Song Liu" <songliubraving@fb.com>, Yonghong Song <yhs@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@kernel.org>
Cc: Benjamin Herrenschmidt <benh@amazon.com>,
Kuniyuki Iwashima <kuniyu@amazon.co.jp>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <bpf@vger.kernel.org>,
<netdev@vger.kernel.org>
Subject: [PATCH v2 bpf-next 1/2] bpf: af_unix: Implement BPF iterator for UNIX domain socket.
Date: Tue, 3 Aug 2021 10:11:09 +0900 [thread overview]
Message-ID: <20210803011110.21205-2-kuniyu@amazon.co.jp> (raw)
In-Reply-To: <20210803011110.21205-1-kuniyu@amazon.co.jp>
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
next prev parent reply other threads:[~2021-08-03 1:11 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-03 1:11 [PATCH v2 bpf-next 0/2] BPF iterator for UNIX domain socket Kuniyuki Iwashima
2021-08-03 1:11 ` Kuniyuki Iwashima [this message]
2021-08-03 10:06 ` [PATCH v2 bpf-next 1/2] bpf: af_unix: Implement " kernel test robot
2021-08-03 1:11 ` [PATCH v2 bpf-next 2/2] selftest/bpf: Implement sample UNIX domain socket iterator program Kuniyuki Iwashima
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210803011110.21205-2-kuniyu@amazon.co.jp \
--to=kuniyu@amazon.co.jp \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=benh@amazon.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).