From eafb64f40ca49c79f0769aab25d0fae5c9d3becb Mon Sep 17 00:00:00 2001 From: Bobby Eshleman Date: Wed, 21 Jan 2026 14:11:41 -0800 Subject: [PATCH] vsock: add netns to vsock core Add netns logic to vsock core. Additionally, modify transport hook prototypes to be used by later transport-specific patches (e.g., *_seqpacket_allow()). Namespaces are supported primarily by changing socket lookup functions (e.g., vsock_find_connected_socket()) to take into account the socket namespace and the namespace mode before considering a candidate socket a "match". This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode to report the mode and /proc/sys/net/vsock/child_ns_mode to set the mode for new namespaces. Add netns functionality (initialization, passing to transports, procfs, etc...) to the af_vsock socket layer. Later patches that add netns support to transports depend on this patch. This patch changes the allocation of random ports for connectible vsocks in order to avoid leaking the random port range starting point to other namespaces. dgram_allow(), stream_allow(), and seqpacket_allow() callbacks are modified to take a vsk in order to perform logic on namespace modes. In future patches, the net will also be used for socket lookups in these functions. Reviewed-by: Stefano Garzarella Signed-off-by: Bobby Eshleman Link: https://patch.msgid.link/20260121-vsock-vmtest-v16-1-2859a7512097@meta.com Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- MAINTAINERS | 1 + drivers/vhost/vsock.c | 6 +- include/linux/virtio_vsock.h | 4 +- include/net/af_vsock.h | 61 ++++- include/net/net_namespace.h | 4 + include/net/netns/vsock.h | 21 ++ net/vmw_vsock/af_vsock.c | 335 ++++++++++++++++++++++-- net/vmw_vsock/hyperv_transport.c | 7 +- net/vmw_vsock/virtio_transport.c | 9 +- net/vmw_vsock/virtio_transport_common.c | 6 +- net/vmw_vsock/vmci_transport.c | 26 +- net/vmw_vsock/vsock_loopback.c | 8 +- 12 files changed, 437 insertions(+), 51 deletions(-) create mode 100644 include/net/netns/vsock.h diff --git a/MAINTAINERS b/MAINTAINERS index 62392b61a52fc..c3df85fd5acde 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -27556,6 +27556,7 @@ 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/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 552cfb53498ad..647ded6f6ea5c 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -407,7 +407,8 @@ static bool vhost_transport_msgzerocopy_allow(void) return true; } -static bool vhost_transport_seqpacket_allow(u32 remote_cid); +static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, + u32 remote_cid); static struct virtio_transport vhost_transport = { .transport = { @@ -463,7 +464,8 @@ static struct virtio_transport vhost_transport = { .send_pkt = vhost_transport_send_pkt, }; -static bool vhost_transport_seqpacket_allow(u32 remote_cid) +static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, + u32 remote_cid) { struct vhost_vsock *vsock; bool seqpacket_allow = false; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 0c67543a45c8a..1845e8d4f78d8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -256,10 +256,10 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); -bool virtio_transport_stream_allow(u32 cid, u32 port); +bool virtio_transport_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port); int virtio_transport_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr); -bool virtio_transport_dgram_allow(u32 cid, u32 port); +bool virtio_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port); int virtio_transport_connect(struct vsock_sock *vsk); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d40e978126e33..d3ff48a2fbe06 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -10,6 +10,7 @@ #include #include +#include #include #include @@ -124,7 +125,7 @@ struct vsock_transport { size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); - bool (*dgram_allow)(u32 cid, u32 port); + bool (*dgram_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* STREAM. */ /* TODO: stream_bind() */ @@ -136,14 +137,14 @@ struct vsock_transport { s64 (*stream_has_space)(struct vsock_sock *); u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); - bool (*stream_allow)(u32 cid, u32 port); + bool (*stream_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* SEQ_PACKET. */ ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, int flags); int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len); - bool (*seqpacket_allow)(u32 remote_cid); + bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid); u32 (*seqpacket_has_data)(struct vsock_sock *vsk); /* Notification. */ @@ -216,6 +217,11 @@ void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net); +struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + struct net *net); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); @@ -256,4 +262,53 @@ 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) +{ + if (!net) + return VSOCK_NET_MODE_GLOBAL; + + return READ_ONCE(net->vsock.mode); +} + +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, + 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 = vsock_net_mode(ns0); + mode1 = vsock_net_mode(ns1); + + /* 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 cb664f6e35580..66d3de1d935fd 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -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 diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h new file mode 100644 index 0000000000000..b34d69a22fa86 --- /dev/null +++ b/include/net/netns/vsock.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NET_NAMESPACE_VSOCK_H +#define __NET_NET_NAMESPACE_VSOCK_H + +#include + +enum vsock_net_mode { + VSOCK_NET_MODE_GLOBAL, + VSOCK_NET_MODE_LOCAL, +}; + +struct netns_vsock { + struct ctl_table_header *sysctl_hdr; + + /* protected by the vsock_table_lock in af_vsock.c */ + u32 port; + + enum vsock_net_mode mode; + enum vsock_net_mode 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 a3505a4dcee0b..20ad2b2dc17bc 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -83,6 +83,50 @@ * TCP_ESTABLISHED - connected * TCP_CLOSING - disconnecting * TCP_LISTEN - listening + * + * - Namespaces in vsock support two different modes: "local" and "global". + * Each mode defines how the namespace interacts with CIDs. + * Each namespace exposes two sysctl files: + * + * - /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 + * child namespaces will inherit when created. The default is "global". + * + * Changing child_ns_mode only affects newly created namespaces, not the + * current namespace or existing children. 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 modes affect the allocation and accessibility of CIDs as follows: + * + * - global - access and allocation are all system-wide + * - all CID allocation from global namespaces draw from the same + * system-wide pool. + * - if one global namespace has already allocated some CID, another + * global namespace will not be able to allocate the same CID. + * - global mode AF_VSOCK sockets can reach any VM or socket in any global + * namespace, they are not contained to only their own namespace. + * - AF_VSOCK sockets in a global mode namespace cannot reach VMs or + * sockets in any local mode namespace. + * - local - access and allocation are contained within the namespace + * - CID allocation draws only from a private pool local only to the + * namespace, and does not affect the CIDs available for allocation in any + * other namespace (global or local). + * - VMs in a local namespace do not collide with CIDs in any other local + * namespace or any global namespace. For example, if a VM in a local mode + * namespace is given CID 10, then CID 10 is still available for + * allocation in any other namespace, but not in the same namespace. + * - AF_VSOCK sockets in a local mode namespace can connect only to VMs or + * other sockets within their own namespace. + * - sockets bound to VMADDR_CID_ANY in local namespaces will never resolve + * to any transport that is not compatible with local mode. There is no + * error that propagates to the user (as there is for connection attempts) + * because it is possible for some packet to reach this socket from + * a different transport that *does* support local mode. For + * example, virtio-vsock may not support local mode, but the socket + * may still accept a connection from vhost-vsock which does. */ #include @@ -100,20 +144,31 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include #include #include #include #include +#include #include #include +#define VSOCK_NET_MODE_STR_GLOBAL "global" +#define VSOCK_NET_MODE_STR_LOCAL "local" + +/* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'. + * The newline is added by proc_dostring() for read operations. + */ +#define VSOCK_NET_MODE_STR_MAX 8 + static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); @@ -235,33 +290,42 @@ static void __vsock_remove_connected(struct vsock_sock *vsk) sock_put(&vsk->sk); } -static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) +static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { - if (vsock_addr_equals_addr(addr, &vsk->local_addr)) - return sk_vsock(vsk); + struct sock *sk = sk_vsock(vsk); + + if (vsock_addr_equals_addr(addr, &vsk->local_addr) && + vsock_net_check_mode(sock_net(sk), net)) + return sk; if (addr->svm_port == vsk->local_addr.svm_port && (vsk->local_addr.svm_cid == VMADDR_CID_ANY || - addr->svm_cid == VMADDR_CID_ANY)) - return sk_vsock(vsk); + addr->svm_cid == VMADDR_CID_ANY) && + vsock_net_check_mode(sock_net(sk), net)) + return sk; } return NULL; } -static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst) +static struct sock * +__vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, struct net *net) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { + struct sock *sk = sk_vsock(vsk); + if (vsock_addr_equals_addr(src, &vsk->remote_addr) && - dst->svm_port == vsk->local_addr.svm_port) { - return sk_vsock(vsk); + dst->svm_port == vsk->local_addr.svm_port && + vsock_net_check_mode(sock_net(sk), net)) { + return sk; } } @@ -304,12 +368,18 @@ void vsock_remove_connected(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_remove_connected); -struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) +/* Find a bound socket, filtering by namespace and namespace mode. + * + * Use this in transports that are namespace-aware and can provide the + * network namespace context. + */ +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net) { struct sock *sk; spin_lock_bh(&vsock_table_lock); - sk = __vsock_find_bound_socket(addr); + sk = __vsock_find_bound_socket_net(addr, net); if (sk) sock_hold(sk); @@ -317,15 +387,32 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) return sk; } +EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net); + +/* Find a bound socket without namespace filtering. + * + * Use this in transports that lack namespace context. All sockets are + * treated as if in global mode. + */ +struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) +{ + return vsock_find_bound_socket_net(addr, NULL); +} EXPORT_SYMBOL_GPL(vsock_find_bound_socket); -struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, - struct sockaddr_vm *dst) +/* Find a connected socket, filtering by namespace and namespace mode. + * + * Use this in transports that are namespace-aware and can provide the + * network namespace context. + */ +struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + struct net *net) { struct sock *sk; spin_lock_bh(&vsock_table_lock); - sk = __vsock_find_connected_socket(src, dst); + sk = __vsock_find_connected_socket_net(src, dst, net); if (sk) sock_hold(sk); @@ -333,6 +420,18 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, return sk; } +EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net); + +/* Find a connected socket without namespace filtering. + * + * Use this in transports that lack namespace context. All sockets are + * treated as if in global mode. + */ +struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, + struct sockaddr_vm *dst) +{ + return vsock_find_connected_socket_net(src, dst, NULL); +} EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) @@ -528,7 +627,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || - !new_transport->seqpacket_allow(remote_cid)) { + !new_transport->seqpacket_allow(vsk, remote_cid)) { module_put(new_transport->module); return -ESOCKTNOSUPPORT; } @@ -676,11 +775,11 @@ out: static int __vsock_bind_connectible(struct vsock_sock *vsk, struct sockaddr_vm *addr) { - static u32 port; + struct net *net = sock_net(sk_vsock(vsk)); struct sockaddr_vm new_addr; - if (!port) - port = get_random_u32_above(LAST_RESERVED_PORT); + if (!net->vsock.port) + net->vsock.port = get_random_u32_above(LAST_RESERVED_PORT); vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); @@ -689,13 +788,13 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port == VMADDR_PORT_ANY || - port <= LAST_RESERVED_PORT) - port = LAST_RESERVED_PORT + 1; + if (net->vsock.port == VMADDR_PORT_ANY || + net->vsock.port <= LAST_RESERVED_PORT) + net->vsock.port = LAST_RESERVED_PORT + 1; - new_addr.svm_port = port++; + new_addr.svm_port = net->vsock.port++; - if (!__vsock_find_bound_socket(&new_addr)) { + if (!__vsock_find_bound_socket_net(&new_addr, net)) { found = true; break; } @@ -712,7 +811,7 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, return -EACCES; } - if (__vsock_find_bound_socket(&new_addr)) + if (__vsock_find_bound_socket_net(&new_addr, net)) return -EADDRINUSE; } @@ -1314,7 +1413,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - if (!transport->dgram_allow(remote_addr->svm_cid, + if (!transport->dgram_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; @@ -1355,7 +1454,7 @@ static int vsock_dgram_connect(struct socket *sock, if (err) goto out; - if (!vsk->transport->dgram_allow(remote_addr->svm_cid, + if (!vsk->transport->dgram_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; @@ -1585,7 +1684,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr, * endpoints. */ if (!transport || - !transport->stream_allow(remote_addr->svm_cid, + !transport->stream_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -ENETUNREACH; goto out; @@ -2662,6 +2761,180 @@ static struct miscdevice vsock_device = { .fops = &vsock_device_ops, }; +static int __vsock_net_mode_string(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + enum vsock_net_mode mode, + enum vsock_net_mode *new_mode) +{ + char data[VSOCK_NET_MODE_STR_MAX] = {0}; + struct ctl_table tmp; + int ret; + + if (!table->data || !table->maxlen || !*lenp) { + *lenp = 0; + return 0; + } + + tmp = *table; + tmp.data = data; + + if (!write) { + const char *p; + + switch (mode) { + case VSOCK_NET_MODE_GLOBAL: + p = VSOCK_NET_MODE_STR_GLOBAL; + break; + case VSOCK_NET_MODE_LOCAL: + p = VSOCK_NET_MODE_STR_LOCAL; + break; + default: + WARN_ONCE(true, "netns has invalid vsock mode"); + *lenp = 0; + return 0; + } + + strscpy(data, p, sizeof(data)); + tmp.maxlen = strlen(p); + } + + ret = proc_dostring(&tmp, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + + if (*lenp >= sizeof(data)) + return -EINVAL; + + if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data))) + *new_mode = VSOCK_NET_MODE_GLOBAL; + else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data))) + *new_mode = VSOCK_NET_MODE_LOCAL; + else + return -EINVAL; + + return 0; +} + +static int vsock_net_mode_string(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net; + + if (write) + return -EPERM; + + net = current->nsproxy->net_ns; + + return __vsock_net_mode_string(table, write, buffer, lenp, ppos, + vsock_net_mode(net), NULL); +} + +static int vsock_net_child_mode_string(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + enum vsock_net_mode new_mode; + struct net *net; + int ret; + + net = current->nsproxy->net_ns; + + ret = __vsock_net_mode_string(table, write, buffer, lenp, ppos, + vsock_net_child_mode(net), &new_mode); + if (ret) + return ret; + + if (write) + vsock_net_set_child_mode(net, new_mode); + + return 0; +} + +static struct ctl_table vsock_table[] = { + { + .procname = "ns_mode", + .data = &init_net.vsock.mode, + .maxlen = VSOCK_NET_MODE_STR_MAX, + .mode = 0444, + .proc_handler = vsock_net_mode_string + }, + { + .procname = "child_ns_mode", + .data = &init_net.vsock.child_ns_mode, + .maxlen = VSOCK_NET_MODE_STR_MAX, + .mode = 0644, + .proc_handler = vsock_net_child_mode_string + }, +}; + +static int __net_init vsock_sysctl_register(struct net *net) +{ + struct ctl_table *table; + + if (net_eq(net, &init_net)) { + table = vsock_table; + } else { + table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->vsock.mode; + table[1].data = &net->vsock.child_ns_mode; + } + + net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table, + ARRAY_SIZE(vsock_table)); + if (!net->vsock.sysctl_hdr) + goto err_reg; + + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void vsock_sysctl_unregister(struct net *net) +{ + const struct ctl_table *table; + + table = net->vsock.sysctl_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->vsock.sysctl_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static void vsock_net_init(struct net *net) +{ + if (net_eq(net, &init_net)) + net->vsock.mode = VSOCK_NET_MODE_GLOBAL; + else + net->vsock.mode = vsock_net_child_mode(current->nsproxy->net_ns); + + net->vsock.child_ns_mode = VSOCK_NET_MODE_GLOBAL; +} + +static __net_init int vsock_sysctl_init_net(struct net *net) +{ + vsock_net_init(net); + + if (vsock_sysctl_register(net)) + return -ENOMEM; + + return 0; +} + +static __net_exit void vsock_sysctl_exit_net(struct net *net) +{ + vsock_sysctl_unregister(net); +} + +static struct pernet_operations vsock_sysctl_ops = { + .init = vsock_sysctl_init_net, + .exit = vsock_sysctl_exit_net, +}; + static int __init vsock_init(void) { int err = 0; @@ -2689,10 +2962,17 @@ static int __init vsock_init(void) goto err_unregister_proto; } + if (register_pernet_subsys(&vsock_sysctl_ops)) { + err = -ENOMEM; + goto err_unregister_sock; + } + vsock_bpf_build_proto(); return 0; +err_unregister_sock: + sock_unregister(AF_VSOCK); err_unregister_proto: proto_unregister(&vsock_proto); err_deregister_misc: @@ -2706,6 +2986,7 @@ static void __exit vsock_exit(void) misc_deregister(&vsock_device); sock_unregister(AF_VSOCK); proto_unregister(&vsock_proto); + unregister_pernet_subsys(&vsock_sysctl_ops); } const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk) diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 432fcbbd14d4f..c3010c8743081 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -570,7 +570,7 @@ static int hvs_dgram_enqueue(struct vsock_sock *vsk, return -EOPNOTSUPP; } -static bool hvs_dgram_allow(u32 cid, u32 port) +static bool hvs_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port) { return false; } @@ -745,8 +745,11 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk) return hvs->chan != NULL; } -static bool hvs_stream_allow(u32 cid, u32 port) +static bool hvs_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port) { + if (!vsock_net_mode_global(vsk)) + return false; + if (cid == VMADDR_CID_HOST) return true; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 8c867023a2e52..f0a9e51118f34 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -536,7 +536,8 @@ static bool virtio_transport_msgzerocopy_allow(void) return true; } -static bool virtio_transport_seqpacket_allow(u32 remote_cid); +static bool virtio_transport_seqpacket_allow(struct vsock_sock *vsk, + u32 remote_cid); static struct virtio_transport virtio_transport = { .transport = { @@ -593,11 +594,15 @@ static struct virtio_transport virtio_transport = { .can_msgzerocopy = virtio_transport_can_msgzerocopy, }; -static bool virtio_transport_seqpacket_allow(u32 remote_cid) +static bool +virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid) { struct virtio_vsock *vsock; bool seqpacket_allow; + if (!vsock_net_mode_global(vsk)) + return false; + seqpacket_allow = false; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index d3e26025ef589..d57e7af6a68d2 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1055,9 +1055,9 @@ bool virtio_transport_stream_is_active(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active); -bool virtio_transport_stream_allow(u32 cid, u32 port) +bool virtio_transport_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port) { - return true; + return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; } EXPORT_SYMBOL_GPL(virtio_transport_stream_allow); @@ -1068,7 +1068,7 @@ int virtio_transport_dgram_bind(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind); -bool virtio_transport_dgram_allow(u32 cid, u32 port) +bool virtio_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port) { return false; } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 7eccd6708d664..00f6bbdb035a5 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -646,13 +646,17 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg) return VMCI_SUCCESS; } -static bool vmci_transport_stream_allow(u32 cid, u32 port) +static bool vmci_transport_stream_allow(struct vsock_sock *vsk, u32 cid, + u32 port) { static const u32 non_socket_contexts[] = { VMADDR_CID_LOCAL, }; int i; + if (!vsock_net_mode_global(vsk)) + return false; + BUILD_BUG_ON(sizeof(cid) != sizeof(*non_socket_contexts)); for (i = 0; i < ARRAY_SIZE(non_socket_contexts); i++) { @@ -682,12 +686,10 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) err = VMCI_SUCCESS; bh_process_pkt = false; - /* Ignore incoming packets from contexts without sockets, or resources - * that aren't vsock implementations. + /* Ignore incoming packets from resources that aren't vsock + * implementations. */ - - if (!vmci_transport_stream_allow(dg->src.context, -1) - || vmci_transport_peer_rid(dg->src.context) != dg->src.resource) + if (vmci_transport_peer_rid(dg->src.context) != dg->src.resource) return VMCI_ERROR_NO_ACCESS; if (VMCI_DG_SIZE(dg) < sizeof(*pkt)) @@ -749,6 +751,12 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) goto out; } + /* Ignore incoming packets from contexts without sockets. */ + if (!vmci_transport_stream_allow(vsk, dg->src.context, -1)) { + err = VMCI_ERROR_NO_ACCESS; + goto out; + } + /* We do most everything in a work queue, but let's fast path the * notification of reads and writes to help data transfer performance. * We can only do this if there is no process context code executing @@ -1784,8 +1792,12 @@ out: return err; } -static bool vmci_transport_dgram_allow(u32 cid, u32 port) +static bool vmci_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, + u32 port) { + if (!vsock_net_mode_global(vsk)) + return false; + if (cid == VMADDR_CID_HYPERVISOR) { /* Registrations of PBRPC Servers do not modify VMX/Hypervisor * state and are allowed. diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index bc2ff918b315e..deff68c64a091 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -46,7 +46,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) return 0; } -static bool vsock_loopback_seqpacket_allow(u32 remote_cid); +static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, + u32 remote_cid); static bool vsock_loopback_msgzerocopy_allow(void) { return true; @@ -106,9 +107,10 @@ static struct virtio_transport loopback_transport = { .send_pkt = vsock_loopback_send_pkt, }; -static bool vsock_loopback_seqpacket_allow(u32 remote_cid) +static bool +vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid) { - return true; + return vsock_net_mode_global(vsk); } static void vsock_loopback_work(struct work_struct *work) -- 2.47.3