Some transports (hyperv, virtio) acquire the sock lock during the
.release() callback.
In the vsock_stream_connect() we call vsock_assign_transport(); if
the socket was previously assigned to another transport, the
vsk->transport->release() is called, but the sock lock is already
held in the vsock_stream_connect(), causing a deadlock reported by
syzbot:
INFO: task syz-executor280:9768 blocked for more than 143 seconds.
Not tainted 5.6.0-rc1-syzkaller #0
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
syz-executor280 D27912 9768 9766 0x00000000
Call Trace:
context_switch kernel/sched/core.c:3386 [inline]
__schedule+0x934/0x1f90 kernel/sched/core.c:4082
schedule+0xdc/0x2b0 kernel/sched/core.c:4156
__lock_sock+0x165/0x290 net/core/sock.c:2413
lock_sock_nested+0xfe/0x120 net/core/sock.c:2938
virtio_transport_release+0xc4/0xd60 net/vmw_vsock/virtio_transport_common.c:832
vsock_assign_transport+0xf3/0x3b0 net/vmw_vsock/af_vsock.c:454
vsock_stream_connect+0x2b3/0xc70 net/vmw_vsock/af_vsock.c:1288
__sys_connect_file+0x161/0x1c0 net/socket.c:1857
__sys_connect+0x174/0x1b0 net/socket.c:1874
__do_sys_connect net/socket.c:1885 [inline]
__se_sys_connect net/socket.c:1882 [inline]
__x64_sys_connect+0x73/0xb0 net/socket.c:1882
do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
entry_SYSCALL_64_after_hwframe+0x49/0xbe
To avoid this issue, this patch remove the lock acquiring in the
.release() callback of hyperv and virtio transports, and it holds
the lock when we call vsk->transport->release() in the vsock core.
Reported-by: [email protected]
Fixes: 408624af4c89 ("vsock: use local transport when it is loaded")
Signed-off-by: Stefano Garzarella <[email protected]>
---
net/vmw_vsock/af_vsock.c | 20 ++++++++++++--------
net/vmw_vsock/hyperv_transport.c | 3 ---
net/vmw_vsock/virtio_transport_common.c | 2 --
3 files changed, 12 insertions(+), 13 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9c5b2a91baad..a5f28708e0e7 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -451,6 +451,12 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
if (vsk->transport == new_transport)
return 0;
+ /* transport->release() must be called with sock lock acquired.
+ * This path can only be taken during vsock_stream_connect(),
+ * where we have already held the sock lock.
+ * In the other cases, this function is called on a new socket
+ * which is not assigned to any transport.
+ */
vsk->transport->release(vsk);
vsock_deassign_transport(vsk);
}
@@ -753,20 +759,18 @@ static void __vsock_release(struct sock *sk, int level)
vsk = vsock_sk(sk);
pending = NULL; /* Compiler warning. */
- /* The release call is supposed to use lock_sock_nested()
- * rather than lock_sock(), if a sock lock should be acquired.
- */
- if (vsk->transport)
- vsk->transport->release(vsk);
- else if (sk->sk_type == SOCK_STREAM)
- vsock_remove_sock(vsk);
-
/* When "level" is SINGLE_DEPTH_NESTING, use the nested
* version to avoid the warning "possible recursive locking
* detected". When "level" is 0, lock_sock_nested(sk, level)
* is the same as lock_sock(sk).
*/
lock_sock_nested(sk, level);
+
+ if (vsk->transport)
+ vsk->transport->release(vsk);
+ else if (sk->sk_type == SOCK_STREAM)
+ vsock_remove_sock(vsk);
+
sock_orphan(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 3492c021925f..630b851f8150 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -526,12 +526,9 @@ static bool hvs_close_lock_held(struct vsock_sock *vsk)
static void hvs_release(struct vsock_sock *vsk)
{
- struct sock *sk = sk_vsock(vsk);
bool remove_sock;
- lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
remove_sock = hvs_close_lock_held(vsk);
- release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
}
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index d9f0c9c5425a..f3c4bab2f737 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -829,7 +829,6 @@ void virtio_transport_release(struct vsock_sock *vsk)
struct sock *sk = &vsk->sk;
bool remove_sock = true;
- lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
if (sk->sk_type == SOCK_STREAM)
remove_sock = virtio_transport_close(vsk);
@@ -837,7 +836,6 @@ void virtio_transport_release(struct vsock_sock *vsk)
list_del(&pkt->list);
virtio_transport_free_pkt(pkt);
}
- release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
--
2.24.1
On Wed, Feb 26, 2020 at 11:58:18AM +0100, Stefano Garzarella wrote:
> Some transports (hyperv, virtio) acquire the sock lock during the
> .release() callback.
>
> In the vsock_stream_connect() we call vsock_assign_transport(); if
> the socket was previously assigned to another transport, the
> vsk->transport->release() is called, but the sock lock is already
> held in the vsock_stream_connect(), causing a deadlock reported by
> syzbot:
>
> INFO: task syz-executor280:9768 blocked for more than 143 seconds.
> Not tainted 5.6.0-rc1-syzkaller #0
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> syz-executor280 D27912 9768 9766 0x00000000
> Call Trace:
> context_switch kernel/sched/core.c:3386 [inline]
> __schedule+0x934/0x1f90 kernel/sched/core.c:4082
> schedule+0xdc/0x2b0 kernel/sched/core.c:4156
> __lock_sock+0x165/0x290 net/core/sock.c:2413
> lock_sock_nested+0xfe/0x120 net/core/sock.c:2938
> virtio_transport_release+0xc4/0xd60 net/vmw_vsock/virtio_transport_common.c:832
> vsock_assign_transport+0xf3/0x3b0 net/vmw_vsock/af_vsock.c:454
> vsock_stream_connect+0x2b3/0xc70 net/vmw_vsock/af_vsock.c:1288
> __sys_connect_file+0x161/0x1c0 net/socket.c:1857
> __sys_connect+0x174/0x1b0 net/socket.c:1874
> __do_sys_connect net/socket.c:1885 [inline]
> __se_sys_connect net/socket.c:1882 [inline]
> __x64_sys_connect+0x73/0xb0 net/socket.c:1882
> do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
> entry_SYSCALL_64_after_hwframe+0x49/0xbe
>
> To avoid this issue, this patch remove the lock acquiring in the
> .release() callback of hyperv and virtio transports, and it holds
> the lock when we call vsk->transport->release() in the vsock core.
>
> Reported-by: [email protected]
> Fixes: 408624af4c89 ("vsock: use local transport when it is loaded")
> Signed-off-by: Stefano Garzarella <[email protected]>
> ---
> net/vmw_vsock/af_vsock.c | 20 ++++++++++++--------
> net/vmw_vsock/hyperv_transport.c | 3 ---
> net/vmw_vsock/virtio_transport_common.c | 2 --
> 3 files changed, 12 insertions(+), 13 deletions(-)
Reviewed-by: Stefan Hajnoczi <[email protected]>
From: Stefano Garzarella <[email protected]>
Date: Wed, 26 Feb 2020 11:58:18 +0100
> Some transports (hyperv, virtio) acquire the sock lock during the
> .release() callback.
>
> In the vsock_stream_connect() we call vsock_assign_transport(); if
> the socket was previously assigned to another transport, the
> vsk->transport->release() is called, but the sock lock is already
> held in the vsock_stream_connect(), causing a deadlock reported by
> syzbot:
...
> To avoid this issue, this patch remove the lock acquiring in the
> .release() callback of hyperv and virtio transports, and it holds
> the lock when we call vsk->transport->release() in the vsock core.
>
> Reported-by: [email protected]
> Fixes: 408624af4c89 ("vsock: use local transport when it is loaded")
> Signed-off-by: Stefano Garzarella <[email protected]>
Applied, thank you.