diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ae01457ea2cd..2c937a2df83b 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -404,7 +404,8 @@ 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 = {
@@ -460,7 +461,8 @@ 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/net/af_vsock.h b/include/net/af_vsock.h
index 9b5bdd083b6f..59d97a143204 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -145,7 +145,7 @@ struct vsock_transport {
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. */
@@ -218,6 +218,13 @@ 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,
+ enum vsock_net_mode net_mode);
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode);
void vsock_remove_sock(struct vsock_sock *vsk);
void vsock_for_each_connected_socket(struct vsock_transport *transport,
void (*fn)(struct sock *sk));
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 72bb6b7ed386..54373ae101c3 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -83,6 +83,38 @@
* TCP_ESTABLISHED - connected
* TCP_CLOSING - disconnecting
* TCP_LISTEN - listening
+ *
+ * - Namespaces in vsock support two different modes configured
+ * through /proc/sys/net/vsock/ns_mode. The modes are "local" and "global".
+ * Each mode defines how the namespace interacts with CIDs.
+ * /proc/sys/net/vsock/ns_mode is write-once, so that it may be configured
+ * and locked down by a namespace manager. The default is "global". The mode
+ * is set per-namespace.
+ *
+ * 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.
+ * - when a socket or device is initialized in a namespace with mode
+ * global, it will stay in global mode even if the namespace later
+ * changes to local.
*/
#include <linux/compat.h>
@@ -100,6 +132,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/net.h>
+#include <linux/proc_fs.h>
#include <linux/poll.h>
#include <linux/random.h>
#include <linux/skbuff.h>
@@ -111,9 +144,18 @@
#include <linux/workqueue.h>
#include <net/sock.h>
#include <net/af_vsock.h>
+#include <net/netns/vsock.h>
#include <uapi/linux/vm_sockets.h>
#include <uapi/asm-generic/ioctls.h>
+#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 +277,47 @@ 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,
+ enum vsock_net_mode net_mode)
{
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), vsk->net_mode, net,
+ net_mode))
+ 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), vsk->net_mode, net,
+ net_mode))
+ 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,
+ enum vsock_net_mode net_mode)
{
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), vsk->net_mode, net,
+ net_mode)) {
+ return sk;
}
}
@@ -304,12 +360,14 @@ void vsock_remove_connected(struct vsock_sock *vsk)
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);
-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct sock *sk;
spin_lock_bh(&vsock_table_lock);
- sk = __vsock_find_bound_socket(addr);
+ sk = __vsock_find_bound_socket_net(addr, net, net_mode);
if (sk)
sock_hold(sk);
@@ -317,15 +375,23 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm
*addr)
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net);
+
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+{
+ return vsock_find_bound_socket_net(addr, NULL, VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_bound_socket);
-struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
- struct sockaddr_vm *dst)
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
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, net_mode);
if (sk)
sock_hold(sk);
@@ -333,6 +399,14 @@ struct sock *vsock_find_connected_socket(struct
sockaddr_vm *src,
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net);
+
+struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst)
+{
+ return vsock_find_connected_socket_net(src, dst,
+ NULL, VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
@@ -528,7 +602,7 @@ 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;
}
@@ -676,6 +750,7 @@ static void vsock_pending_work(struct work_struct *work)
static int __vsock_bind_connectible(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
+ struct net *net = sock_net(sk_vsock(vsk));
static u32 port;
struct sockaddr_vm new_addr;
@@ -695,7 +770,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
new_addr.svm_port = port++;
- if (!__vsock_find_bound_socket(&new_addr)) {
+ if (!__vsock_find_bound_socket_net(&new_addr, net,
+ vsk->net_mode)) {
found = true;
break;
}
@@ -712,7 +788,8 @@ 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,
+ vsk->net_mode))
return -EADDRINUSE;
}
@@ -836,6 +913,8 @@ static struct sock *__vsock_create(struct net *net,
vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE;
}
+ vsk->net_mode = vsock_net_mode(net);
+
return sk;
}
@@ -2636,6 +2715,142 @@ 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)
+{
+ char data[VSOCK_NET_MODE_STR_MAX] = {0};
+ enum vsock_net_mode mode;
+ struct ctl_table tmp;
+ struct net *net;
+ int ret;
+
+ if (!table->data || !table->maxlen || !*lenp) {
+ *lenp = 0;
+ return 0;
+ }
+
+ net = current->nsproxy->net_ns;
+ tmp = *table;
+ tmp.data = data;
+
+ if (!write) {
+ const char *p;
+
+ mode = vsock_net_mode(net);
+
+ 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)
+ return ret;
+
+ if (!write)
+ return 0;
+
+ if (*lenp >= sizeof(data))
+ return -EINVAL;
+
+ if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_GLOBAL;
+ else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_LOCAL;
+ else
+ return -EINVAL;
+
+ if (!vsock_net_write_mode(net, mode))
+ return -EPERM;
+
+ return 0;
+}
+
+static struct ctl_table vsock_table[] = {
+ {
+ .procname = "ns_mode",
+ .data = &init_net.vsock.mode,
+ .maxlen = VSOCK_NET_MODE_STR_MAX,
+ .mode = 0644,
+ .proc_handler = vsock_net_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;
+ }
+
+ 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)
+{
+ net->vsock.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 __net_initdata = {
+ .init = vsock_sysctl_init_net,
+ .exit = vsock_sysctl_exit_net,
+};
+
static int __init vsock_init(void)
{
int err = 0;
@@ -2663,10 +2878,18 @@ static int __init vsock_init(void)
goto err_unregister_proto;
}
+ if (register_pernet_subsys(&vsock_sysctl_ops)) {
+ err = -ENOMEM;
+ goto err_unregister_sock;
+ }
+
+ vsock_net_init(&init_net);
vsock_bpf_build_proto();
return 0;
+err_unregister_sock:
+ sock_unregister(AF_VSOCK);
err_unregister_proto:
proto_unregister(&vsock_proto);
err_deregister_misc:
@@ -2680,6 +2903,7 @@ 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/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8c867023a2e5..5d379ccf3770 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 = {
@@ -593,7 +594,8 @@ 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;
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index bc2ff918b315..8722337a4f80 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;
@@ -106,7 +107,8 @@ 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;
}
--
2.47.3
