| 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: <iiakzdk7n7onhu5sncjd7poh5sk34nrtvusbiulsel5uswuekv@p2yzmblg6xx7>
Date: Thu, 6 Nov 2025 17:16:29 +0100
From: Stefano Garzarella <sgarzare@...hat.com>
To: Bobby Eshleman <bobbyeshleman@...il.com>
Cc: Shuah Khan <shuah@...nel.org>, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>,
Stefan Hajnoczi <stefanha@...hat.com>, "Michael S. Tsirkin" <mst@...hat.com>,
Jason Wang <jasowang@...hat.com>, Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
Eugenio Pérez <eperezma@...hat.com>, "K. Y. Srinivasan" <kys@...rosoft.com>,
Haiyang Zhang <haiyangz@...rosoft.com>, Wei Liu <wei.liu@...nel.org>, Dexuan Cui <decui@...rosoft.com>,
Bryan Tan <bryan-bt.tan@...adcom.com>, Vishnu Dasa <vishnu.dasa@...adcom.com>,
Broadcom internal kernel review list <bcm-kernel-feedback-list@...adcom.com>, virtualization@...ts.linux.dev, netdev@...r.kernel.org,
linux-kselftest@...r.kernel.org, linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
linux-hyperv@...r.kernel.org, berrange@...hat.com, Bobby Eshleman <bobbyeshleman@...a.com>
Subject: Re: [PATCH net-next v8 01/14] vsock: a per-net vsock NS mode state
On Thu, Oct 23, 2025 at 11:27:40AM -0700, Bobby Eshleman wrote:
>From: Bobby Eshleman <bobbyeshleman@...a.com>
>
>Add the per-net vsock NS mode state. This only adds the structure for
>holding the mode and some of the functions for setting/getting and
>checking the mode, but does not integrate the functionality yet.
>
>A "net_mode" field is added to vsock_sock to store the mode of the
>namespace when the vsock_sock was created. In order to evaluate
>namespace mode rules we need to know both a) which namespace the
>endpoints are in, and b) what mode that namespace had when the endpoints
>were created. This allows us to handle the changing of modes from global
>to local *after* a socket has been created by remembering that the mode
>was global when the socket was created. If we were to use the current
>net's mode instead, then the lookup would fail and the socket would
>break.
>
>Signed-off-by: Bobby Eshleman <bobbyeshleman@...a.com>
>---
>Changes in v7:
>- clarify vsock_net_check_mode() comments
>- change to `orig_net_mode == VSOCK_NET_MODE_GLOBAL && orig_net_mode == vsk->orig_net_mode`
>- remove extraneous explanation of `orig_net_mode`
>- rename `written` to `mode_locked`
>- rename `vsock_hdr` to `sysctl_hdr`
>- change `orig_net_mode` to `net_mode`
>- make vsock_net_check_mode() more generic by taking just net pointers
> and modes, instead of a vsock_sock ptr, for reuse by transports
> (e.g., vhost_vsock)
>
>Changes in v6:
>- add orig_net_mode to store mode at creation time which will be used to
> avoid breakage when namespace changes mode during socket/VM lifespan
>
>Changes in v5:
>- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
>- change from net->vsock.ns_mode to net->vsock.mode
>- change vsock_net_set_mode() to vsock_net_write_mode()
>- vsock_net_write_mode() returns bool for write success to avoid
> need to use vsock_net_mode_can_set()
>- remove vsock_net_mode_can_set()
>---
> MAINTAINERS | 1 +
> include/net/af_vsock.h | 56 +++++++++++++++++++++++++++++++++++++++++++++
> include/net/net_namespace.h | 4 ++++
> include/net/netns/vsock.h | 20 ++++++++++++++++
> 4 files changed, 81 insertions(+)
>
>diff --git a/MAINTAINERS b/MAINTAINERS
>index ea72b3bd2248..dd765bbf79ab 100644
>--- a/MAINTAINERS
>+++ b/MAINTAINERS
>@@ -27070,6 +27070,7 @@ L: netdev@...r.kernel.org
> S: Maintained
> F: drivers/vhost/vsock.c
> F: include/linux/virtio_vsock.h
>+F: include/net/netns/vsock.h
> F: include/uapi/linux/virtio_vsock.h
> F: net/vmw_vsock/virtio_transport.c
> F: net/vmw_vsock/virtio_transport_common.c
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index d40e978126e3..bce5389ef742 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -10,6 +10,7 @@
>
> #include <linux/kernel.h>
> #include <linux/workqueue.h>
>+#include <net/netns/vsock.h>
> #include <net/sock.h>
> #include <uapi/linux/vm_sockets.h>
>
>@@ -65,6 +66,7 @@ struct vsock_sock {
> u32 peer_shutdown;
> bool sent_request;
> bool ignore_connecting_rst;
>+ enum vsock_net_mode net_mode;
>
> /* Protected by lock_sock(sk) */
> u64 buffer_size;
>@@ -256,4 +258,58 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
> {
> return t->msgzerocopy_allow && t->msgzerocopy_allow();
> }
>+
>+static inline enum vsock_net_mode vsock_net_mode(struct net *net)
>+{
>+ enum vsock_net_mode ret;
>+
>+ spin_lock_bh(&net->vsock.lock);
>+ ret = net->vsock.mode;
Do we really need a spin_lock just to set/get a variable?
What about WRITE_ONCE/READ_ONCE and/or atomic ?
Not a strong opinion, just to check if we can do something like this:
static inline enum vsock_net_mode vsock_net_mode(struct net *net)
{
return READ_ONCE(net->vsock.mode);
}
static inline bool vsock_net_write_mode(struct net *net, u8 mode)
{
// Or using test_and_set_bit() if you prefer
if (xchg(&net->vsock.mode_locked, true))
return false;
WRITE_ONCE(net->vsock.mode, mode);
return true;
}
Thanks,
Stefano
>+ spin_unlock_bh(&net->vsock.lock);
>+ return ret;
>+}
>+
>+static inline bool vsock_net_write_mode(struct net *net, u8 mode)
>+{
>+ bool ret;
>+
>+ spin_lock_bh(&net->vsock.lock);
>+
>+ if (net->vsock.mode_locked) {
>+ ret = false;
>+ goto skip;
>+ }
>+
>+ net->vsock.mode = mode;
>+ net->vsock.mode_locked = true;
>+ ret = true;
>+
>+skip:
>+ spin_unlock_bh(&net->vsock.lock);
>+ return ret;
>+}
>+
>+/* Return true if two namespaces and modes pass the mode rules. Otherwise,
>+ * return false.
>+ *
>+ * ns0 and ns1 are the namespaces being checked.
>+ * mode0 and mode1 are the vsock namespace modes of ns0 and ns1.
>+ *
>+ * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c.
>+ */
>+static inline bool vsock_net_check_mode(struct net *ns0, enum vsock_net_mode mode0,
>+ struct net *ns1, enum vsock_net_mode mode1)
>+{
>+ /* Any vsocks within the same network namespace are always reachable,
>+ * regardless of the mode.
>+ */
>+ if (net_eq(ns0, ns1))
>+ return true;
>+
>+ /*
>+ * If the network namespaces differ, vsocks are only reachable if both
>+ * were created in VSOCK_NET_MODE_GLOBAL mode.
>+ */
>+ return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1;
>+}
> #endif /* __AF_VSOCK_H__ */
>diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
>index cb664f6e3558..66d3de1d935f 100644
>--- a/include/net/net_namespace.h
>+++ b/include/net/net_namespace.h
>@@ -37,6 +37,7 @@
> #include <net/netns/smc.h>
> #include <net/netns/bpf.h>
> #include <net/netns/mctp.h>
>+#include <net/netns/vsock.h>
> #include <net/net_trackers.h>
> #include <linux/ns_common.h>
> #include <linux/idr.h>
>@@ -196,6 +197,9 @@ struct net {
> /* Move to a better place when the config guard is removed. */
> struct mutex rtnl_mutex;
> #endif
>+#if IS_ENABLED(CONFIG_VSOCKETS)
>+ struct netns_vsock vsock;
>+#endif
> } __randomize_layout;
>
> #include <linux/seq_file_net.h>
>diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
>new file mode 100644
>index 000000000000..c9a438ad52f2
>--- /dev/null
>+++ b/include/net/netns/vsock.h
>@@ -0,0 +1,20 @@
>+/* SPDX-License-Identifier: GPL-2.0 */
>+#ifndef __NET_NET_NAMESPACE_VSOCK_H
>+#define __NET_NET_NAMESPACE_VSOCK_H
>+
>+#include <linux/types.h>
>+
>+enum vsock_net_mode {
>+ VSOCK_NET_MODE_GLOBAL,
>+ VSOCK_NET_MODE_LOCAL,
>+};
>+
>+struct netns_vsock {
>+ struct ctl_table_header *sysctl_hdr;
>+ spinlock_t lock;
>+
>+ /* protected by lock */
>+ enum vsock_net_mode mode;
>+ bool mode_locked;
>+};
>+#endif /* __NET_NET_NAMESPACE_VSOCK_H */
>
>--
>2.47.3
>
Powered by blists - more mailing lists