From: Cong Wang <cong.wang@xxxxxxxxxxxxx>
unix_proto is special, it is very different from INET proto,
which even does not have a ->close(). We have to add a dummy
one to satisfy sockmap.
Cc: John Fastabend <john.fastabend@xxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Cc: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
Cc: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
Signed-off-by: Cong Wang <cong.wang@xxxxxxxxxxxxx>
---
MAINTAINERS | 1 +
include/net/af_unix.h | 10 +++++++++
net/unix/Makefile | 1 +
net/unix/af_unix.c | 12 ++++++++++-
net/unix/unix_bpf.c | 50 +++++++++++++++++++++++++++++++++++++++++++
5 files changed, 73 insertions(+), 1 deletion(-)
create mode 100644 net/unix/unix_bpf.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 1df56a32d2df..1fa3971c45b0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9950,6 +9950,7 @@ F: net/core/skmsg.c
F: net/core/sock_map.c
F: net/ipv4/tcp_bpf.c
F: net/ipv4/udp_bpf.c
+F: net/unix/unix_bpf.c
LANTIQ / INTEL Ethernet drivers
M: Hauke Mehrtens <hauke@xxxxxxxxxx>
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index f42fdddecd41..fa75f899e88a 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -89,4 +89,14 @@ void unix_sysctl_unregister(struct net *net);
static inline int unix_sysctl_register(struct net *net) { return 0; }
static inline void unix_sysctl_unregister(struct net *net) {}
#endif
+
+extern struct proto unix_proto;
+
+#ifdef CONFIG_BPF_SOCK_MAP
+int unix_bpf_update_proto(struct sock *sk, bool restore);
+void __init unix_bpf_build_proto(void);
+#else
+static inline void __init unix_bpf_build_proto(void)
+{}
+#endif
#endif
diff --git a/net/unix/Makefile b/net/unix/Makefile
index 54e58cc4f945..7d2c70c575b6 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_UNIX) += unix.o
unix-y := af_unix.o garbage.o
unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o
+unix-$(CONFIG_BPF_SOCK_MAP) += unix_bpf.o
obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
unix_diag-y := diag.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 9315c4f4c27a..4ce12d3c369e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -773,10 +773,18 @@ static const struct proto_ops unix_seqpacket_ops = {
.show_fdinfo = unix_show_fdinfo,
};
-static struct proto unix_proto = {
+static void unix_close(struct sock *sk, long timeout)
+{
+}
+
+struct proto unix_proto = {
.name = "UNIX",
.owner = THIS_MODULE,
.obj_size = sizeof(struct unix_sock),
+ .close = unix_close,
+#ifdef CONFIG_BPF_SOCK_MAP
+ .update_proto = unix_bpf_update_proto,
+#endif
};
static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
@@ -861,6 +869,7 @@ static int unix_release(struct socket *sock)
return 0;
unix_release_sock(sk, 0);
+ sk->sk_prot->close(sk, 0);
sock->sk = NULL;
return 0;
@@ -2973,6 +2982,7 @@ static int __init af_unix_init(void)
sock_register(&unix_family_ops);
register_pernet_subsys(&unix_net_ops);
+ unix_bpf_build_proto();
out:
return rc;
}
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
new file mode 100644
index 000000000000..2e6a26ec4958
--- /dev/null
+++ b/net/unix/unix_bpf.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Cong Wang <cong.wang@xxxxxxxxxxxxx> */
+
+#include <linux/skmsg.h>
+#include <net/sock.h>
+#include <net/af_unix.h>
+
+static struct proto *unix_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_prot_lock);
+static struct proto unix_bpf_prot;
+
+static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+ *prot = *base;
+ prot->close = sock_map_close;
+}
+
+static void unix_bpf_check_needs_rebuild(struct proto *ops)
+{
+ if (unlikely(ops != smp_load_acquire(&unix_prot_saved))) {
+ spin_lock_bh(&unix_prot_lock);
+ if (likely(ops != unix_prot_saved)) {
+ unix_bpf_rebuild_protos(&unix_bpf_prot, ops);
+ smp_store_release(&unix_prot_saved, ops);
+ }
+ spin_unlock_bh(&unix_prot_lock);
+ }
+}
+
+int unix_bpf_update_proto(struct sock *sk, bool restore)
+{
+ struct sk_psock *psock = sk_psock(sk);
+
+ if (restore) {
+ sk->sk_write_space = psock->saved_write_space;
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ return 0;
+ }
+
+ unix_bpf_check_needs_rebuild(psock->sk_proto);
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, &unix_bpf_prot);
+ return 0;
+}
+
+void __init unix_bpf_build_proto(void)
+{
+ unix_bpf_rebuild_protos(&unix_bpf_prot, &unix_proto);
+}
--
2.25.1
