bpf: af_unix: Implement BPF iterator for UNIX domain socket.

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

Currently, the batch optimisation introduced for the TCP iterator in the
commit 04c7820 ("bpf: tcp: Bpf iter batching and lock_sock") is not
used for the UNIX domain socket.  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 <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Acked-by: Yonghong Song <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

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,

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"
 
@@ -3143,6 +3144,64 @@ static const struct seq_operations unix_seq_ops = {
 	.stop   = unix_seq_stop,
 	.show   = unix_seq_show,
 };
+
+#if IS_BUILTIN(CONFIG_UNIX) && defined(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 = {
@@ -3183,6 +3242,35 @@ static struct pernet_operations unix_net_ops = {
 	.exit = unix_net_exit,
 };
 
+#if IS_BUILTIN(CONFIG_UNIX) && 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;
@@ -3198,6 +3286,11 @@ static int __init af_unix_init(void)
 	sock_register(&unix_family_ops);
 	register_pernet_subsys(&unix_net_ops);
 	unix_bpf_build_proto();
+
+#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	bpf_iter_register();
+#endif
+
 out:
 	return rc;
 }