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.
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@meta.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 | 64 +++++++++++++++++++++++++++++++++++++++++++++ include/net/net_namespace.h | 4 +++ include/net/netns/vsock.h | 20 ++++++++++++++ 4 files changed, 89 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS index 4faa7719bf86..c58f9e38898a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -27062,6 +27062,7 @@ 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..a1053d3668cf 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 +258,66 @@ 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.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. + * + * The vsock namespace mode is write-once, and the default is + * VSOCK_NET_MODE_GLOBAL. Once set to VSOCK_NET_MODE_LOCAL, it cannot + * revert to GLOBAL. It is not possible to have a case where a socket + * was created in LOCAL mode, and then the mode switched to GLOBAL. + * + * As a result, we only need to check if the modes were global at + * creation time. + */ + 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 */