Re: [PATCH RFC net v2 2/3] vsock: Fix transport_* TOCTOU
On Sun, Jun 29, 2025 at 11:26:25PM +0200, Michal Luczaj wrote:
On 6/27/25 10:08, Stefano Garzarella wrote:
On Fri, Jun 20, 2025 at 09:52:44PM +0200, Michal Luczaj wrote:
Transport assignment may race with module unload. Protect new_transport
from becoming a stale pointer.
This also takes care of an insecure call in vsock_use_local_transport();
add a lockdep assert.
BUG: unable to handle page fault for address: fbfff8056000
Oops: Oops: [#1] SMP KASAN
RIP: 0010:vsock_assign_transport+0x366/0x600
Call Trace:
vsock_connect+0x59c/0xc40
__sys_connect+0xe8/0x100
__x64_sys_connect+0x6e/0xc0
do_syscall_64+0x92/0x1c0
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Signed-off-by: Michal Luczaj
---
net/vmw_vsock/af_vsock.c | 28 +++-
1 file changed, 23 insertions(+), 5 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index
63a920af5bfe6960306a3e5eeae0cbf30648985e..a1b1073a2c89f865fcdb58b38d8e7feffcf1544f
100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_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);
Thinking back to this patch, could there be a deadlock between call
vsock_deassign_transport(), which call module_put(), now with the
`vsock_register_mutex` held, and the call to vsock_core_unregister()
usually made by modules in the exit function?
I think we're good. module_put() does not call the module cleanup function
(kernel/module/main.c:delete_module() syscall does that), so
vsock_core_unregister() won't happen in this path here. Have I missed
anything else?
Nope, I reached the same conclusion!
Thanks,
Stefano
Re: [PATCH RFC net v2 2/3] vsock: Fix transport_* TOCTOU
On 6/27/25 10:08, Stefano Garzarella wrote:
> On Fri, Jun 20, 2025 at 09:52:44PM +0200, Michal Luczaj wrote:
>> Transport assignment may race with module unload. Protect new_transport
>>from becoming a stale pointer.
>>
>> This also takes care of an insecure call in vsock_use_local_transport();
>> add a lockdep assert.
>>
>> BUG: unable to handle page fault for address: fbfff8056000
>> Oops: Oops: [#1] SMP KASAN
>> RIP: 0010:vsock_assign_transport+0x366/0x600
>> Call Trace:
>> vsock_connect+0x59c/0xc40
>> __sys_connect+0xe8/0x100
>> __x64_sys_connect+0x6e/0xc0
>> do_syscall_64+0x92/0x1c0
>> entry_SYSCALL_64_after_hwframe+0x4b/0x53
>>
>> Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
>> Signed-off-by: Michal Luczaj
>> ---
>> net/vmw_vsock/af_vsock.c | 28 +++-
>> 1 file changed, 23 insertions(+), 5 deletions(-)
>>
>> diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>> index
>> 63a920af5bfe6960306a3e5eeae0cbf30648985e..a1b1073a2c89f865fcdb58b38d8e7feffcf1544f
>> 100644
>> --- a/net/vmw_vsock/af_vsock.c
>> +++ b/net/vmw_vsock/af_vsock.c
>> @@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
>>
>> static bool vsock_use_local_transport(unsigned int remote_cid)
>> {
>> +lockdep_assert_held(&vsock_register_mutex);
>> +
>> if (!transport_local)
>> return false;
>>
>> @@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk,
>> struct vsock_sock *psk)
>>
>> remote_flags = vsk->remote_addr.svm_flags;
>>
>> +mutex_lock(&vsock_register_mutex);
>> +
>> switch (sk->sk_type) {
>> case SOCK_DGRAM:
>> new_transport = transport_dgram;
>> @@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk,
>> struct vsock_sock *psk)
>> new_transport = transport_h2g;
>> break;
>> default:
>> -return -ESOCKTNOSUPPORT;
>> +ret = -ESOCKTNOSUPPORT;
>> +goto err;
>> }
>>
>> if (vsk->transport) {
>> -if (vsk->transport == new_transport)
>> -return 0;
>> +if (vsk->transport == new_transport) {
>> +ret = 0;
>> +goto err;
>> +}
>
> /* transport->release() must be called with sock lock acquired.
>* This path can only be taken during vsock_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);
>
> Thinking back to this patch, could there be a deadlock between call
> vsock_deassign_transport(), which call module_put(), now with the
> `vsock_register_mutex` held, and the call to vsock_core_unregister()
> usually made by modules in the exit function?
I think we're good. module_put() does not call the module cleanup function
(kernel/module/main.c:delete_module() syscall does that), so
vsock_core_unregister() won't happen in this path here. Have I missed
anything else?
Re: [PATCH RFC net v2 2/3] vsock: Fix transport_* TOCTOU
On Fri, Jun 20, 2025 at 09:52:44PM +0200, Michal Luczaj wrote:
Transport assignment may race with module unload. Protect new_transport
from becoming a stale pointer.
This also takes care of an insecure call in vsock_use_local_transport();
add a lockdep assert.
BUG: unable to handle page fault for address: fbfff8056000
Oops: Oops: [#1] SMP KASAN
RIP: 0010:vsock_assign_transport+0x366/0x600
Call Trace:
vsock_connect+0x59c/0xc40
__sys_connect+0xe8/0x100
__x64_sys_connect+0x6e/0xc0
do_syscall_64+0x92/0x1c0
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Signed-off-by: Michal Luczaj
---
net/vmw_vsock/af_vsock.c | 28 +++-
1 file changed, 23 insertions(+), 5 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index
63a920af5bfe6960306a3e5eeae0cbf30648985e..a1b1073a2c89f865fcdb58b38d8e7feffcf1544f
100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_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);
Thinking back to this patch, could there be a deadlock between call
vsock_deassign_transport(), which call module_put(), now with the
`vsock_register_mutex` held, and the call to vsock_core_unregister()
usually made by modules in the exit function?
Thanks,
Stefano
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
/* We increase the module refcnt to prevent the transport unloading
* while there are open sockets assigned to it.
*/
- if (!new_transport || !try_module_get(new_transport->module))
- return -ENODEV;
+ if (!new_transport || !try_module_get(new_transport->module)) {
+ ret = -ENODEV;
+ goto err;
+ }
+
+ /* It's safe to release the mutex after a successful try_module_get().
+* Whichever transport `new_transport` points at, it won't go await
+* until the last module_put() below or in vsock_deassign_transport().
+*/
+ mutex_unlock(&vsock_register_mutex);
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
@@ -528,6 +543,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
vsk->transport = new_transport;
return 0;
+err:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);
--
2.49.0
Re: [PATCH RFC net v2 2/3] vsock: Fix transport_* TOCTOU
On Fri, Jun 20, 2025 at 09:52:44PM +0200, Michal Luczaj wrote:
Transport assignment may race with module unload. Protect new_transport
from becoming a stale pointer.
This also takes care of an insecure call in vsock_use_local_transport();
add a lockdep assert.
BUG: unable to handle page fault for address: fbfff8056000
Oops: Oops: [#1] SMP KASAN
RIP: 0010:vsock_assign_transport+0x366/0x600
Call Trace:
vsock_connect+0x59c/0xc40
__sys_connect+0xe8/0x100
__x64_sys_connect+0x6e/0xc0
do_syscall_64+0x92/0x1c0
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Signed-off-by: Michal Luczaj
---
net/vmw_vsock/af_vsock.c | 28 +++-
1 file changed, 23 insertions(+), 5 deletions(-)
LGTM!
Reviewed-by: Stefano Garzarella
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index
63a920af5bfe6960306a3e5eeae0cbf30648985e..a1b1073a2c89f865fcdb58b38d8e7feffcf1544f
100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
static bool vsock_use_local_transport(unsigned int remote_cid)
{
+ lockdep_assert_held(&vsock_register_mutex);
+
if (!transport_local)
return false;
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
remote_flags = vsk->remote_addr.svm_flags;
+ mutex_lock(&vsock_register_mutex);
+
switch (sk->sk_type) {
case SOCK_DGRAM:
new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
new_transport = transport_h2g;
break;
default:
- return -ESOCKTNOSUPPORT;
+ ret = -ESOCKTNOSUPPORT;
+ goto err;
}
if (vsk->transport) {
- if (vsk->transport == new_transport)
- return 0;
+ if (vsk->transport == new_transport) {
+ ret = 0;
+ goto err;
+ }
/* transport->release() must be called with sock lock acquired.
* This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
/* We increase the module refcnt to prevent the transport unloading
* while there are open sockets assigned to it.
*/
- if (!new_transport || !try_module_get(new_transport->module))
- return -ENODEV;
+ if (!new_transport || !try_module_get(new_transport->module)) {
+ ret = -ENODEV;
+ goto err;
+ }
+
+ /* It's safe to release the mutex after a successful try_module_get().
+* Whichever transport `new_transport` points at, it won't go await
+* until the last module_put() below or in vsock_deassign_transport().
+*/
+ mutex_unlock(&vsock_register_mutex);
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
@@ -528,6 +543,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct
vsock_sock *psk)
vsk->transport = new_transport;
return 0;
+err:
+ mutex_unlock(&vsock_register_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);
--
2.49.0
