On Thu, Feb 19, 2026 at 11:35:52AM +0100, Stefano Garzarella wrote:
On Wed, Feb 18, 2026 at 10:10:37AM -0800, Bobby Eshleman wrote:
> From: Bobby Eshleman <[email protected]>
>
> Two administrator processes may race when setting child_ns_mode as one
> process sets child_ns_mode to "local" and then creates a namespace, but
> another process changes child_ns_mode to "global" between the write and
> the namespace creation. The first process ends up with a namespace in
> "global" mode instead of "local". While this can be detected after the
> fact by reading ns_mode and retrying, it is fragile and error-prone.
>
> Make child_ns_mode write-once so that a namespace manager can set it
> once and be sure it won't change. Writing a different value after the
> first write returns -EBUSY. This applies to all namespaces, including
> init_net, where an init process can write "local" to lock all future
> namespaces into local mode.
>
> Fixes: eafb64f40ca4 ("vsock: add netns to vsock core")
> Signed-off-by: Bobby Eshleman <[email protected]>
> Suggested-by: Daan De Meyer <[email protected]>
> Suggested-by: Stefano Garzarella <[email protected]>
nit: usually the S-o-b of the author is the last when sending a patch.
Ah good to know, thanks. Will change.
> ---
> include/net/af_vsock.h | 20 +++++++++++++++++---
> include/net/netns/vsock.h | 9 ++++++++-
> net/vmw_vsock/af_vsock.c | 15 ++++++++++-----
> 3 files changed, 35 insertions(+), 9 deletions(-)
>
> diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
> index d3ff48a2fbe0..9bd42147626d 100644
> --- a/include/net/af_vsock.h
> +++ b/include/net/af_vsock.h
> @@ -276,15 +276,29 @@ static inline bool vsock_net_mode_global(struct
vsock_sock *vsk)
> return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL;
> }
>
> -static inline void vsock_net_set_child_mode(struct net *net,
> +static inline bool vsock_net_set_child_mode(struct net *net,
> enum vsock_net_mode mode)
> {
> - WRITE_ONCE(net->vsock.child_ns_mode, mode);
> + int locked = mode + VSOCK_NET_MODE_LOCKED;
> + int cur;
> +
> + cur = READ_ONCE(net->vsock.child_ns_mode);
> + if (cur == locked)
> + return true;
> + if (cur >= VSOCK_NET_MODE_LOCKED)
> + return false;
> +
> + if (try_cmpxchg(&net->vsock.child_ns_mode, &cur, locked))
> + return true;
> +
> + return cur == locked;
Sorry, it took me a while to get it entirely :-(
This overcomplication is exactly what I wanted to avoid when I proposed the
change in v1:
https://lore.kernel.org/netdev/aZWUmbiH11Eh3Y4v@sgarzare-redhat/
Glad you thought so too, because I actually think your original proposed
snippet in that thread is the best/simplest so far.
> }
>
> static inline enum vsock_net_mode vsock_net_child_mode(struct net *net)
> {
> - return READ_ONCE(net->vsock.child_ns_mode);
> + int mode = READ_ONCE(net->vsock.child_ns_mode);
> +
> + return mode & (VSOCK_NET_MODE_LOCKED - 1);
This is working just because VSOCK_NET_MODE_LOCKED == 2, so IMO this should
at least set as value in the enum and documented on top of vsock_net_mode.
> }
>
> /* Return true if two namespaces pass the mode rules. Otherwise, return false.
> diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
> index b34d69a22fa8..d20ab6269342 100644
> --- a/include/net/netns/vsock.h
> +++ b/include/net/netns/vsock.h
> @@ -7,6 +7,7 @@
> enum vsock_net_mode {
> VSOCK_NET_MODE_GLOBAL,
> VSOCK_NET_MODE_LOCAL,
> + VSOCK_NET_MODE_LOCKED,
This is not really a mode, so IMO should not be part of `enum
vsock_net_mode`. If you really want it, maybe we can add both
VSOCK_NET_MODE_GLOBAL_LOCKED and VSOCK_NET_MODE_LOCAL_LOCKED, which can be
less error prone if we will touch this enum one day.
> };
>
> struct netns_vsock {
> @@ -16,6 +17,12 @@ struct netns_vsock {
> u32 port;
>
> enum vsock_net_mode mode;
> - enum vsock_net_mode child_ns_mode;
> +
> + /* 0 (GLOBAL)
> + * 1 (LOCAL)
> + * 2 (GLOBAL + LOCKED)
> + * 3 (LOCAL + LOCKED)
> + */
> + int child_ns_mode;
Sorry, I don't like this too much, since it seems too complicated to read
and to maintain, If we really want to use just one variable, maybe we can
use -1 as UNSET for child_ns_mode. If it is UNSET, vsock_net_child_mode()
can just return `mode` since it's the default that we also documented, if
it's set, it means that is locked with the value specified.
Maybe with code is easier, I mean something like this:
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d3ff48a2fbe0..fcd5b538df35 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -276,15 +276,25 @@ static inline bool vsock_net_mode_global(struct
vsock_sock *vsk)
return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL;
}
-static inline void vsock_net_set_child_mode(struct net *net,
+static inline bool vsock_net_set_child_mode(struct net *net,
enum vsock_net_mode mode)
{
- WRITE_ONCE(net->vsock.child_ns_mode, mode);
+ int old = VSOCK_NET_CHILD_NS_UNSET;
+
+ if (try_cmpxchg(&net->vsock.child_ns_mode, &old, mode))
+ return true;
+
+ return old == mode;
}
static inline enum vsock_net_mode vsock_net_child_mode(struct net *net)
{
- return READ_ONCE(net->vsock.child_ns_mode);
+ int mode = READ_ONCE(net->vsock.child_ns_mode);
+
+ if (mode == VSOCK_NET_CHILD_NS_UNSET)
+ return net->vsock.mode;
+
+ return mode;
}
/* Return true if two namespaces pass the mode rules. Otherwise, return false.
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
index b34d69a22fa8..bf52baf7d7a7 100644
--- a/include/net/netns/vsock.h
+++ b/include/net/netns/vsock.h
@@ -9,6 +9,8 @@ enum vsock_net_mode {
VSOCK_NET_MODE_LOCAL,
};
+#define VSOCK_NET_CHILD_NS_UNSET (-1)
+
struct netns_vsock {
struct ctl_table_header *sysctl_hdr;
@@ -16,6 +18,13 @@ struct netns_vsock {
u32 port;
enum vsock_net_mode mode;
- enum vsock_net_mode child_ns_mode;
+
+ /* Write-once child namespace mode, must be initialized to
+ * VSOCK_NET_CHILD_NS_UNSET. Transitions once from UNSET to a
+ * vsock_net_mode value via try_cmpxchg on first sysctl write.
+ * While UNSET, vsock_net_child_mode() returns the namespace's
+ * own mode since it's the default.
+ */
+ int child_ns_mode;
};
#endif /* __NET_NET_NAMESPACE_VSOCK_H */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9880756d9eff..f0cb7c6a8212 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2853,7 +2853,8 @@ static int vsock_net_child_mode_string(const struct
ctl_table *table, int write,
new_mode == VSOCK_NET_MODE_GLOBAL)
return -EPERM;
- vsock_net_set_child_mode(net, new_mode);
+ if (!vsock_net_set_child_mode(net, new_mode))
+ return -EBUSY;
}
return 0;
@@ -2922,7 +2923,7 @@ static void vsock_net_init(struct net *net)
else
net->vsock.mode =
vsock_net_child_mode(current->nsproxy->net_ns);
- net->vsock.child_ns_mode = net->vsock.mode;
+ net->vsock.child_ns_mode = VSOCK_NET_CHILD_NS_UNSET;
}
static __net_init int vsock_sysctl_init_net(struct net *net)
If you like it, please add my Co-developed-by and S-o-b.
Will do!
BTW, let's discuss here more about it and agree before sending a new
version, so this should also allow other to comment eventually.
Thanks,
Stefano
Tbh, I like your original proposal from v1 best (copied below). I like
that the whole locking mechanism is self-contained there in one place,
and doesn't ripple out elsewhere into the code (e.g.,
vsock_net_child_mode() carrying logic around UNSET). Wdyt?
if (try_cmpxchg(&net->vsock.child_ns_mode_locked,
&old_locked, new_locked)) {
WRITE_ONCE(net->vsock.child_ns_mode, mode);
return true;
}
return old_locked == new_locked;
}
Best,
Bobby
> };
> #endif /* __NET_NET_NAMESPACE_VSOCK_H */
> diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
> index 9880756d9eff..50044a838c89 100644
> --- a/net/vmw_vsock/af_vsock.c
> +++ b/net/vmw_vsock/af_vsock.c
> @@ -90,16 +90,20 @@
> *
> * - /proc/sys/net/vsock/ns_mode (read-only) reports the current namespace's
> * mode, which is set at namespace creation and immutable thereafter.
> - * - /proc/sys/net/vsock/child_ns_mode (writable) controls what mode future
> + * - /proc/sys/net/vsock/child_ns_mode (write-once) controls what mode
future
> * child namespaces will inherit when created. The initial value matches
> * the namespace's own ns_mode.
> *
> * Changing child_ns_mode only affects newly created namespaces, not the
> * current namespace or existing children. A "local" namespace cannot set
> - * child_ns_mode to "global". At namespace creation, ns_mode is inherited
> - * from the parent's child_ns_mode.
> + * child_ns_mode to "global". child_ns_mode is write-once, so that it may
be
> + * configured and locked down by a namespace manager. Writing a different
> + * value after the first write returns -EBUSY. At namespace creation,
ns_mode
> + * is inherited from the parent's child_ns_mode.
> *
> - * The init_net mode is "global" and cannot be modified.
> + * The init_net mode is "global" and cannot be modified. The init_net
> + * child_ns_mode is also write-once, so an init process (e.g. systemd) can
> + * set it to "local" to ensure all new namespaces inherit local mode.
> *
> * The modes affect the allocation and accessibility of CIDs as follows:
> *
> @@ -2853,7 +2857,8 @@ static int vsock_net_child_mode_string(const struct
ctl_table *table, int write,
> new_mode == VSOCK_NET_MODE_GLOBAL)
> return -EPERM;
>
> - vsock_net_set_child_mode(net, new_mode);
> + if (!vsock_net_set_child_mode(net, new_mode))
> + return -EBUSY;
> }
>
> return 0;
>
> --
> 2.47.3
>
