[PATCH net-next v6 1/9] vsock: a per-net vsock NS mode state

Bobby Eshleman posted 9 patches 2 weeks, 1 day ago
[PATCH net-next v6 1/9] vsock: a per-net vsock NS mode state
Posted by Bobby Eshleman 2 weeks, 1 day ago
From: Bobby Eshleman <bobbyeshleman@meta.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.

Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>

---
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      | 55 +++++++++++++++++++++++++++++++++++++++++++++
 include/net/net_namespace.h |  4 ++++
 include/net/netns/vsock.h   | 20 +++++++++++++++++
 4 files changed, 80 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 47bc35743f22..bc53c67e0926 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26634,6 +26634,7 @@ L:	netdev@vger.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..2857e97699de 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 orig_net_mode;
 
 	/* Protected by lock_sock(sk) */
 	u64 buffer_size;
@@ -256,4 +258,57 @@ 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;
+	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.written) {
+		ret = false;
+		goto skip;
+	}
+
+	net->vsock.mode = mode;
+	net->vsock.written = true;
+	ret = true;
+
+skip:
+	spin_unlock_bh(&net->vsock.lock);
+	return ret;
+}
+
+/* Return true if vsock_sock passes the mode rules for a given net and
+ * orig_net_mode. Otherwise, return false.
+ *
+ * net is the current net namespace of the object being checked. orig_net_mode
+ * is the mode of net when the object was created.
+ *
+ * orig_net_mode is the mode of arg 'net' at the time of creation for the
+ * object being checked. For example, if searching for a vsock_sock then
+ * orig_net_mode is arg net's mode at the time the vsock_sock was created.
+ *
+ * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c.
+ */
+static inline bool vsock_net_check_mode(struct vsock_sock *vsk, struct net *net,
+					enum vsock_net_mode orig_net_mode)
+{
+	struct net *vsk_net = sock_net(sk_vsock(vsk));
+
+	if (net_eq(vsk_net, net))
+		return true;
+
+	return orig_net_mode == VSOCK_NET_MODE_GLOBAL && vsk->orig_net_mode == VSOCK_NET_MODE_GLOBAL;
+}
 #endif /* __AF_VSOCK_H__ */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 025a7574b275..005c0da4fb62 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..d4593c0b8dc4
--- /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 *vsock_hdr;
+	spinlock_t lock;
+
+	/* protected by lock */
+	enum vsock_net_mode mode;
+	bool written;
+};
+#endif /* __NET_NET_NAMESPACE_VSOCK_H */

-- 
2.47.3
Re: [PATCH net-next v6 1/9] vsock: a per-net vsock NS mode state
Posted by Stefano Garzarella 5 days, 19 hours ago
On Tue, Sep 16, 2025 at 04:43:45PM -0700, Bobby Eshleman wrote:
>From: Bobby Eshleman <bobbyeshleman@meta.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.
>
>Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
>
>---
>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      | 55 +++++++++++++++++++++++++++++++++++++++++++++
> include/net/net_namespace.h |  4 ++++
> include/net/netns/vsock.h   | 20 +++++++++++++++++
> 4 files changed, 80 insertions(+)
>
>diff --git a/MAINTAINERS b/MAINTAINERS
>index 47bc35743f22..bc53c67e0926 100644
>--- a/MAINTAINERS
>+++ b/MAINTAINERS
>@@ -26634,6 +26634,7 @@ L:	netdev@vger.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..2857e97699de 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 orig_net_mode;

Why `orig_` prefix?

Maybe I need to review all the series, but it's a bit confusing for now.
I guess it's related to the new behaviour to not change the mode of 
already created sockets (which I like), but IMHO this variable prefix is 
confusing.It seems we will have another field with the "actual_" mode, 
but if it's immutable, I'd avoid that prefix.

>
> 	/* Protected by lock_sock(sk) */
> 	u64 buffer_size;
>@@ -256,4 +258,57 @@ 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;
>+	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.written) {
>+		ret = false;
>+		goto skip;
>+	}
>+
>+	net->vsock.mode = mode;
>+	net->vsock.written = true;
>+	ret = true;
>+
>+skip:
>+	spin_unlock_bh(&net->vsock.lock);
>+	return ret;
>+}
>+
>+/* Return true if vsock_sock passes the mode rules for a given net and
>+ * orig_net_mode. Otherwise, return false.
>+ *
>+ * net is the current net namespace of the object being checked. orig_net_mode
>+ * is the mode of net when the object was created.

`orig_net_mode` is also explained in the next paragraph, should we 
remove from here?

>+ *
>+ * orig_net_mode is the mode of arg 'net' at the time of creation for the
>+ * object being checked. For example, if searching for a vsock_sock then
>+ * orig_net_mode is arg net's mode at the time the vsock_sock was created.
>+ *
>+ * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c.
>+ */
>+static inline bool vsock_net_check_mode(struct vsock_sock *vsk, struct net *net,
>+					enum vsock_net_mode orig_net_mode)
>+{
>+	struct net *vsk_net = sock_net(sk_vsock(vsk));
>+
>+	if (net_eq(vsk_net, net))
>+		return true;
>+
>+	return orig_net_mode == VSOCK_NET_MODE_GLOBAL && vsk->orig_net_mode == VSOCK_NET_MODE_GLOBAL;

nit: I'd rewrite in this way, just because it seems easy to read to me, 
but again not strong opinion, this is fine:

	return orig_net_mode == VSOCK_NET_MODE_GLOBAL &&
	       orig_net_mode == vsk->orig_net_mode;

>+}
> #endif /* __AF_VSOCK_H__ */
>diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
>index 025a7574b275..005c0da4fb62 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..d4593c0b8dc4
>--- /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 *vsock_hdr;

sysctl_header, or sysctl_hdr, or sysctl_ctl ?
I'd remove `vsock_` prefix and make more clear its used for sysctl.

>+	spinlock_t lock;
>+
>+	/* protected by lock */
>+	enum vsock_net_mode mode;
>+	bool written;

I would call this `mode_set` or `mode_locked`, I mean with `mode_` 
prefix to make sure we don't need to rename it when we will add new 
fields in the future.

Thanks
Stefano

>+};
>+#endif /* __NET_NET_NAMESPACE_VSOCK_H */
>
>-- 
>2.47.3
>