| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210727001252.1287673-3-jiang.wang@bytedance.com>
Date: Tue, 27 Jul 2021 00:12:49 +0000
From: Jiang Wang <jiang.wang@...edance.com>
To: netdev@...r.kernel.org
Cc: cong.wang@...edance.com, duanxiongchun@...edance.com,
xieyongji@...edance.com, chaiwen.cc@...edance.com,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
Daniel Borkmann <daniel@...earbox.net>,
Jakub Sitnicki <jakub@...udflare.com>,
Lorenz Bauer <lmb@...udflare.com>,
Alexei Starovoitov <ast@...nel.org>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
KP Singh <kpsingh@...nel.org>, Shuah Khan <shuah@...nel.org>,
Johan Almbladh <johan.almbladh@...finetworks.com>,
linux-kernel@...r.kernel.org, bpf@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: [PATCH bpf-next v1 2/5] af_unix: add unix_stream_proto for sockmap
unix_stream_proto is similar to unix_dgram_proto.
Also implement stream related sockmap functions.
Add dgram key words to those dgram specific functions.
Signed-off-by: Jiang Wang <jiang.wang@...edance.com>
Reviewed-by: Cong Wang <cong.wang@...edance.com>.
---
include/net/af_unix.h | 8 +++-
net/core/sock_map.c | 8 +++-
net/unix/af_unix.c | 77 ++++++++++++++++++++++++++++++-----
net/unix/unix_bpf.c | 93 +++++++++++++++++++++++++++++++++----------
4 files changed, 151 insertions(+), 35 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 435a2c3d5..5d04fbf8a 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -84,6 +84,8 @@ long unix_outq_len(struct sock *sk);
int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
int flags);
+int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+ int flags);
#ifdef CONFIG_SYSCTL
int unix_sysctl_register(struct net *net);
void unix_sysctl_unregister(struct net *net);
@@ -93,9 +95,11 @@ static inline void unix_sysctl_unregister(struct net *net) {}
#endif
#ifdef CONFIG_BPF_SYSCALL
-extern struct proto unix_proto;
+extern struct proto unix_dgram_proto;
+extern struct proto unix_stream_proto;
-int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
+int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
+int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void __init unix_bpf_build_proto(void);
#else
static inline void __init unix_bpf_build_proto(void)
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ae5fa4338..42f50ea7a 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -517,9 +517,15 @@ static bool sk_is_tcp(const struct sock *sk)
sk->sk_protocol == IPPROTO_TCP;
}
+static bool sk_is_unix_stream(const struct sock *sk)
+{
+ return sk->sk_type == SOCK_STREAM &&
+ sk->sk_protocol == PF_UNIX;
+}
+
static bool sock_map_redirect_allowed(const struct sock *sk)
{
- if (sk_is_tcp(sk))
+ if (sk_is_tcp(sk) || sk_is_unix_stream(sk))
return sk->sk_state != TCP_LISTEN;
else
return sk->sk_state == TCP_ESTABLISHED;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 32eeb4a6a..c68d13f61 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -791,17 +791,35 @@ static void unix_close(struct sock *sk, long timeout)
*/
}
-struct proto unix_proto = {
- .name = "UNIX",
+static void unix_unhash(struct sock *sk)
+{
+ /* Nothing to do here, unix socket does not need a ->unhash().
+ * This is merely for sockmap.
+ */
+}
+
+struct proto unix_dgram_proto = {
+ .name = "UNIX-DGRAM",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct unix_sock),
+ .close = unix_close,
+#ifdef CONFIG_BPF_SYSCALL
+ .psock_update_sk_prot = unix_dgram_bpf_update_proto,
+#endif
+};
+
+struct proto unix_stream_proto = {
+ .name = "UNIX-STREAM",
.owner = THIS_MODULE,
.obj_size = sizeof(struct unix_sock),
.close = unix_close,
+ .unhash = unix_unhash,
#ifdef CONFIG_BPF_SYSCALL
- .psock_update_sk_prot = unix_bpf_update_proto,
+ .psock_update_sk_prot = unix_stream_bpf_update_proto,
#endif
};
-static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
+static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type)
{
struct sock *sk = NULL;
struct unix_sock *u;
@@ -810,7 +828,17 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
goto out;
- sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern);
+ if (type != 0) {
+ if (type == SOCK_STREAM)
+ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
+ else /*for seqpacket */
+ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
+ } else {
+ if (sock->type == SOCK_STREAM)
+ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
+ else
+ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
+ }
if (!sk)
goto out;
@@ -872,7 +900,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
return -ESOCKTNOSUPPORT;
}
- return unix_create1(net, sock, kern) ? 0 : -ENOMEM;
+ return unix_create1(net, sock, kern, 0) ? 0 : -ENOMEM;
}
static int unix_release(struct socket *sock)
@@ -1286,7 +1314,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
err = -ENOMEM;
/* create new sock for complete connection */
- newsk = unix_create1(sock_net(sk), NULL, 0);
+ newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
if (newsk == NULL)
goto out;
@@ -2214,7 +2242,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si
struct sock *sk = sock->sk;
#ifdef CONFIG_BPF_SYSCALL
- if (sk->sk_prot != &unix_proto)
+ if (sk->sk_prot != &unix_dgram_proto)
return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, NULL);
#endif
@@ -2533,6 +2561,21 @@ static int unix_stream_read_actor(struct sk_buff *skb,
return ret ?: chunk;
}
+int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+ size_t size, int flags)
+{
+ struct socket *sock = sk->sk_socket;
+ struct unix_stream_read_state state = {
+ .recv_actor = unix_stream_read_actor,
+ .socket = sock,
+ .msg = msg,
+ .size = size,
+ .flags = flags
+ };
+
+ return unix_stream_read_generic(&state, true);
+}
+
static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
size_t size, int flags)
{
@@ -2544,6 +2587,13 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
.flags = flags
};
+ struct sock *sk = sock->sk;
+
+#ifdef CONFIG_BPF_SYSCALL
+ if (sk->sk_prot != &unix_stream_proto)
+ return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, NULL);
+#endif
return unix_stream_read_generic(&state, true);
}
@@ -2993,7 +3043,13 @@ static int __init af_unix_init(void)
BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb));
- rc = proto_register(&unix_proto, 1);
+ rc = proto_register(&unix_dgram_proto, 1);
+ if (rc != 0) {
+ pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
+ goto out;
+ }
+
+ rc = proto_register(&unix_stream_proto, 1);
if (rc != 0) {
pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
goto out;
@@ -3009,7 +3065,8 @@ static int __init af_unix_init(void)
static void __exit af_unix_exit(void)
{
sock_unregister(PF_UNIX);
- proto_unregister(&unix_proto);
+ proto_unregister(&unix_dgram_proto);
+ proto_unregister(&unix_stream_proto);
unregister_pernet_subsys(&unix_net_ops);
}
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index db0cda29f..9067210d3 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -38,9 +38,18 @@ static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock,
return ret;
}
-static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
- size_t len, int nonblock, int flags,
- int *addr_len)
+static int __unix_recvmsg(struct sock *sk, struct msghdr *msg,
+ size_t len, int flags)
+{
+ if (sk->sk_type == SOCK_DGRAM)
+ return __unix_dgram_recvmsg(sk, msg, len, flags);
+ else
+ return __unix_stream_recvmsg(sk, msg, len, flags);
+}
+
+static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+ size_t len, int nonblock, int flags,
+ int *addr_len)
{
struct unix_sock *u = unix_sk(sk);
struct sk_psock *psock;
@@ -48,12 +57,12 @@ static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
psock = sk_psock_get(sk);
if (unlikely(!psock))
- return __unix_dgram_recvmsg(sk, msg, len, flags);
+ return __unix_recvmsg(sk, msg, len, flags);
mutex_lock(&u->iolock);
if (!skb_queue_empty(&sk->sk_receive_queue) &&
sk_psock_queue_empty(psock)) {
- ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+ ret = __unix_recvmsg(sk, msg, len, flags);
goto out;
}
@@ -68,7 +77,7 @@ static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
if (data) {
if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
- ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+ ret = __unix_recvmsg(sk, msg, len, flags);
goto out;
}
copied = -EAGAIN;
@@ -80,30 +89,55 @@ static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
return ret;
}
-static struct proto *unix_prot_saved __read_mostly;
-static DEFINE_SPINLOCK(unix_prot_lock);
-static struct proto unix_bpf_prot;
+static struct proto *unix_dgram_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_dgram_prot_lock);
+static struct proto unix_dgram_bpf_prot;
+
+static struct proto *unix_stream_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_stream_prot_lock);
+static struct proto unix_stream_bpf_prot;
+
+static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+ *prot = *base;
+ prot->close = sock_map_close;
+ prot->recvmsg = unix_bpf_recvmsg;
+}
-static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+static void unix_stream_bpf_rebuild_protos(struct proto *prot,
+ const struct proto *base)
{
*prot = *base;
prot->close = sock_map_close;
- prot->recvmsg = unix_dgram_bpf_recvmsg;
+ prot->recvmsg = unix_bpf_recvmsg;
+ prot->unhash = sock_map_unhash;
}
-static void unix_bpf_check_needs_rebuild(struct proto *ops)
+static void unix_dgram_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);
+ if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) {
+ spin_lock_bh(&unix_dgram_prot_lock);
+ if (likely(ops != unix_dgram_prot_saved)) {
+ unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops);
+ smp_store_release(&unix_dgram_prot_saved, ops);
}
- spin_unlock_bh(&unix_prot_lock);
+ spin_unlock_bh(&unix_dgram_prot_lock);
}
}
-int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+static void unix_stream_bpf_check_needs_rebuild(struct proto *ops)
+{
+ if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) {
+ spin_lock_bh(&unix_stream_prot_lock);
+ if (likely(ops != unix_stream_prot_saved)) {
+ unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops);
+ smp_store_release(&unix_stream_prot_saved, ops);
+ }
+ spin_unlock_bh(&unix_stream_prot_lock);
+ }
+}
+
+int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
if (restore) {
sk->sk_write_space = psock->saved_write_space;
@@ -111,12 +145,27 @@ int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
return 0;
}
- unix_bpf_check_needs_rebuild(psock->sk_proto);
- WRITE_ONCE(sk->sk_prot, &unix_bpf_prot);
+ unix_dgram_bpf_check_needs_rebuild(psock->sk_proto);
+ WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot);
+ return 0;
+}
+
+int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+{
+ if (restore) {
+ sk->sk_write_space = psock->saved_write_space;
+ WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ return 0;
+ }
+
+ unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
+ WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot);
return 0;
}
void __init unix_bpf_build_proto(void)
{
- unix_bpf_rebuild_protos(&unix_bpf_prot, &unix_proto);
+ unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto);
+ unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto);
+
}
--
2.20.1
Powered by blists - more mailing lists