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.
Future patches add the uAPI and transport-specific usage of these structures and helpers.
Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v13: - remove net_mode because net->vsock.mode becomes immutable, no need to save the mode when vsocks are created. - add the new helpers for child_ns_mode to support ns_mode inheriting the mode from child_ns_mode. - because ns_mode is immutable and child_ns_mode can be changed multiple times, remove the write-once lock. - simplify vsock_net_check_mode() to no longer take mode arguments since the mode can be accessed via the net pointers without fear of the mode changing. - add logic in vsock_net_check_mode() to infer VSOCK_NET_MODE_GLOBAL from NULL namespaces in order to allow only net pointers to be passed to vsock_net_check_mode(), while still allowing namespace-unaware transports to force global mode.
Changes in v10: - change mode_locked to int (Stefano)
Changes in v9: - use xchg(), WRITE_ONCE(), READ_ONCE() for mode and mode_locked (Stefano) - clarify mode0/mode1 meaning in vsock_net_check_mode() comment - remove spin lock in net->vsock (not used anymore) - change mode from u8 to enum vsock_net_mode in vsock_net_write_mode()
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 | 42 ++++++++++++++++++++++++++++++++++++++++++ include/net/net_namespace.h | 4 ++++ include/net/netns/vsock.h | 17 +++++++++++++++++ 4 files changed, 64 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS index 454b8ed119e9..38d24e5a957c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -27516,6 +27516,7 @@ 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..6f5bc9dbefa5 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>
@@ -256,4 +257,45 @@ 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) +{ + return READ_ONCE(net->vsock.mode); +} + +static inline void vsock_net_set_child_mode(struct net *net, + enum vsock_net_mode mode) +{ + WRITE_ONCE(net->vsock.child_ns_mode, mode); +} + +static inline enum vsock_net_mode vsock_net_child_mode(struct net *net) +{ + return READ_ONCE(net->vsock.child_ns_mode); +} + +/* Return true if two namespaces pass the mode rules. Otherwise, return false. + * + * A NULL namespace is treated as VSOCK_NET_MODE_GLOBAL. + * + * 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, struct net *ns1) +{ + enum vsock_net_mode mode0, mode1; + + /* Any vsocks within the same network namespace are always reachable, + * regardless of the mode. + */ + if (net_eq(ns0, ns1)) + return true; + + mode0 = ns0 ? vsock_net_mode(ns0) : VSOCK_NET_MODE_GLOBAL; + mode1 = ns1 ? vsock_net_mode(ns1) : VSOCK_NET_MODE_GLOBAL; + + /* Different namespaces are only reachable if they are both + * 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..e2325e2d6ec5 --- /dev/null +++ b/include/net/netns/vsock.h @@ -0,0 +1,17 @@ +/* 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; + enum vsock_net_mode mode; + enum vsock_net_mode child_ns_mode; +}; +#endif /* __NET_NET_NAMESPACE_VSOCK_H */