From: Bobby Eshleman bobbyeshleman@meta.com

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.

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.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v14: - include linux/sysctl.h in af_vsock.c - squash patch 'vsock: add per-net vsock NS mode state' into this patch (prior version can be found here): https://lore.kernel.org/all/20251223-vsock-vmtest-v13-1-9d6db8e7c80b@meta.co...)

Changes in v13: - remove net_mode and replace with direct accesses to net->vsock.mode, since this is now immutable. - update comments about mode behavior and mutability, and sysctl API - only pass NULL for net when wanting global, instead of net_mode == VSOCK_NET_MODE_GLOBAL. This reflects the new logic of vsock_net_check_mode() that only requires net pointers (not net_mode). - refactor sysctl string code into a re-usable function, because child_ns_mode and ns_mode both handle the same strings. - remove redundant vsock_net_init(&init_net) call in module init because pernet registration calls the callback on the init_net too

Changes in v12: - return true in dgram_allow(), stream_allow(), and seqpacket_allow() only if net_mode == VSOCK_NET_MODE_GLOBAL (Stefano) - document bind(VMADDR_CID_ANY) case in af_vsock.c (Stefano) - change order of stream_allow() call in vmci so we can pass vsk to it

Changes in v10: - add file-level comment about what happens to sockets/devices when the namespace mode changes (Stefano) - change the 'if (write)' boolean in vsock_net_mode_string() to if (!write), this simplifies a later patch which adds "goto" for mutex unlocking on function exit.

Changes in v9: - remove virtio_vsock_alloc_rx_skb() (Stefano) - remove vsock_global_dummy_net, not needed as net=NULL + net_mode=VSOCK_NET_MODE_GLOBAL achieves identical result

Changes in v7: - hv_sock: fix hyperv build error - explain why vhost does not use the dummy - explain usage of __vsock_global_dummy_net - explain why VSOCK_NET_MODE_STR_MAX is 8 characters - use switch-case in vsock_net_mode_string() - avoid changing transports as much as possible - add vsock_find_{bound,connected}_socket_net() - rename `vsock_hdr` to `sysctl_hdr` - add virtio_vsock_alloc_linear_skb() wrapper for setting dummy net and global mode for virtio-vsock, move skb->cb zero-ing into wrapper - explain seqpacket_allow() change - move net setting to __vsock_create() instead of vsock_create() so that child sockets also have their net assigned upon accept()

Changes in v6: - unregister sysctl ops in vsock_exit() - af_vsock: clarify description of CID behavior - af_vsock: fix buf vs buffer naming, and length checking - af_vsock: fix length checking w/ correct ctl_table->maxlen

Changes in v5: - vsock_global_net() -> vsock_global_dummy_net() - update comments for new uAPI - use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode - add prototype changes so patch remains compilable --- MAINTAINERS | 1 + drivers/vhost/vsock.c | 6 +- include/linux/virtio_vsock.h | 4 +- include/net/af_vsock.h | 53 +++++- include/net/net_namespace.h | 4 + include/net/netns/vsock.h | 17 ++ net/vmw_vsock/af_vsock.c | 297 +++++++++++++++++++++++++++++--- 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, 394 insertions(+), 44 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS index 6737aad729d6..f4aa476427c8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -27522,6 +27522,7 @@ 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 552cfb53498a..647ded6f6ea5 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 0c67543a45c8..1845e8d4f78d 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 d40e978126e3..10c2846fcc58 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>

@@ -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 +262,45 @@ 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 */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a3505a4dcee0..9d614e4a4fa5 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -83,6 +83,42 @@ * 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 read-only and inherited from the + * parent namespace's /proc/sys/net/vsock/child_ns_mode at creation + * time and is immutable thereafter. The default is "global". + * + * 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 <linux/compat.h> @@ -100,20 +136,31 @@ #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> #include <linux/smp.h> #include <linux/socket.h> #include <linux/stddef.h> +#include <linux/sysctl.h> #include <linux/unistd.h> #include <linux/wait.h> #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 +282,42 @@ 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 +360,13 @@ 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) { 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 +374,22 @@ 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); +} 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) { 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 +397,13 @@ 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); +} EXPORT_SYMBOL_GPL(vsock_find_connected_socket);

void vsock_remove_sock(struct vsock_sock *vsk) @@ -528,7 +599,7 @@ 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 +747,7 @@ 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 +767,7 @@ 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)) { found = true; break; } @@ -712,7 +784,7 @@ 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 +1386,7 @@ 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 +1427,7 @@ 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 +1657,7 @@ 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 +2734,183 @@ 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) + return ret; + + if (!write) + return 0; + + 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 __net_initdata = { + .init = vsock_sysctl_init_net, + .exit = vsock_sysctl_exit_net, +}; + static int __init vsock_init(void) { int err = 0; @@ -2689,10 +2938,17 @@ 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 +2962,7 @@ 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 432fcbbd14d4..4d6d7807f152 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(sock_net(sk_vsock(vsk))) != VSOCK_NET_MODE_GLOBAL) + 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 8c867023a2e5..37eeefddb48c 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(sock_net(sk_vsock(vsk))) != VSOCK_NET_MODE_GLOBAL) + 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 dcc8a1d5851e..fdb8f5b3fa60 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1043,9 +1043,9 @@ 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);

@@ -1056,7 +1056,7 @@ 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 7eccd6708d66..d5ce39ea5a1b 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(sock_net(sk_vsock(vsk))) != VSOCK_NET_MODE_GLOBAL) + 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 @@ static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk, 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(sock_net(sk_vsock(vsk))) != VSOCK_NET_MODE_GLOBAL) + 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 bc2ff918b315..378a96dcb666 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(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; }

static void vsock_loopback_work(struct work_struct *work)

From: Bobby Eshleman bobbyeshleman@meta.com

Associate reply packets with the sending socket. When vsock must reply with an RST packet and there exists a sending socket (e.g., for loopback), setting the skb owner to the socket correctly handles reference counting between the skb and sk (i.e., the sk stays alive until the skb is freed).

This allows the net namespace to be used for socket lookups for the duration of the reply skb's lifetime, preventing race conditions between the namespace lifecycle and vsock socket search using the namespace pointer.

Reviewed-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v11: - move before adding to netns support (Stefano)

Changes in v10: - break this out into its own patch for easy revert (Stefano) --- net/vmw_vsock/virtio_transport_common.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index fdb8f5b3fa60..718be9f33274 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1165,6 +1165,12 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, .op = VIRTIO_VSOCK_OP_RST, .type = le16_to_cpu(hdr->type), .reply = true, + + /* Set sk owner to socket we are replying to (may be NULL for + * non-loopback). This keeps a reference to the sock and + * sock_net(sk) until the reply skb is freed. + */ + .vsk = vsock_sk(skb->sk), }; struct sk_buff *reply;

From: Bobby Eshleman bobbyeshleman@meta.com

Increase the timeout from 300s to 1200s. On a modern bare metal server my last run showed the new set of tests taking ~400s. Multiply by an (arbitrary) factor of three to account for slower/nested runners.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/settings | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vsock/settings b/tools/testing/selftests/vsock/settings index 694d70710ff0..79b65bdf05db 100644 --- a/tools/testing/selftests/vsock/settings +++ b/tools/testing/selftests/vsock/settings @@ -1 +1 @@ -timeout=300 +timeout=1200

From: Bobby Eshleman bobbyeshleman@meta.com

Add namespace support to vm management, ssh helpers, and vsock_test wrapper functions. This enables running VMs and test helpers in specific namespaces, which is required for upcoming namespace isolation tests.

The functions still work correctly within the init ns, though the caller must now pass "init_ns" explicitly.

No functional changes for existing tests. All have been updated to pass "init_ns" explicitly.

Affected functions (such as vm_start() and vm_ssh()) now wrap their commands with 'ip netns exec' when executing commands in non-init namespaces.

Reviewed-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 93 +++++++++++++++++++++++---------- 1 file changed, 65 insertions(+), 28 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index c2bdc293b94c..1d03acb62347 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -135,7 +135,18 @@ del_namespaces() { }

vm_ssh() { - ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@" + local ns_exec + + if [[ "${1}" == init_ns ]]; then + ns_exec="" + else + ns_exec="ip netns exec ${1}" + fi + + shift + + ${ns_exec} ssh -q -o UserKnownHostsFile=/dev/null -p "${SSH_HOST_PORT}" localhost "$@" + return $? }

@@ -258,10 +269,12 @@ terminate_pidfiles() {

vm_start() { local pidfile=$1 + local ns=$2 local logfile=/dev/null local verbose_opt="" local kernel_opt="" local qemu_opts="" + local ns_exec="" local qemu

qemu=$(command -v "${QEMU}") @@ -282,7 +295,11 @@ vm_start() { kernel_opt="${KERNEL_CHECKOUT}" fi

- vng \ + if [[ "${ns}" != "init_ns" ]]; then + ns_exec="ip netns exec ${ns}" + fi + + ${ns_exec} vng \ --run \ ${kernel_opt} \ ${verbose_opt} \ @@ -297,6 +314,7 @@ vm_start() { }

vm_wait_for_ssh() { + local ns=$1 local i

i=0 @@ -304,7 +322,8 @@ vm_wait_for_ssh() { if [[ ${i} -gt ${WAIT_PERIOD_MAX} ]]; then die "Timed out waiting for guest ssh" fi - if vm_ssh -- true; then + + if vm_ssh "${ns}" -- true; then break fi i=$(( i + 1 )) @@ -338,30 +357,41 @@ wait_for_listener() }

vm_wait_for_listener() { - local port=$1 + local ns=$1 + local port=$2

- vm_ssh <<EOF + vm_ssh "${ns}" <<EOF $(declare -f wait_for_listener) wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} EOF }

host_wait_for_listener() { - local port=$1 + local ns=$1 + local port=$2

- wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + if [[ "${ns}" == "init_ns" ]]; then + wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + else + ip netns exec "${ns}" bash <<-EOF + $(declare -f wait_for_listener) + wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} + EOF + fi }

+ vm_vsock_test() { - local host=$1 - local cid=$2 - local port=$3 + local ns=$1 + local host=$2 + local cid=$3 + local port=$4 local rc

# log output and use pipefail to respect vsock_test errors set -o pipefail if [[ "${host}" != server ]]; then - vm_ssh -- "${VSOCK_TEST}" \ + vm_ssh "${ns}" -- "${VSOCK_TEST}" \ --mode=client \ --control-host="${host}" \ --peer-cid="${cid}" \ @@ -369,7 +399,7 @@ vm_vsock_test() { 2>&1 | log_guest rc=$? else - vm_ssh -- "${VSOCK_TEST}" \ + vm_ssh "${ns}" -- "${VSOCK_TEST}" \ --mode=server \ --peer-cid="${cid}" \ --control-port="${port}" \ @@ -381,7 +411,7 @@ vm_vsock_test() { return $rc fi

- vm_wait_for_listener "${port}" + vm_wait_for_listener "${ns}" "${port}" rc=$? fi set +o pipefail @@ -390,22 +420,28 @@ vm_vsock_test() { }

host_vsock_test() { - local host=$1 - local cid=$2 - local port=$3 + local ns=$1 + local host=$2 + local cid=$3 + local port=$4 local rc

+ local cmd="${VSOCK_TEST}" + if [[ "${ns}" != "init_ns" ]]; then + cmd="ip netns exec ${ns} ${cmd}" + fi + # log output and use pipefail to respect vsock_test errors set -o pipefail if [[ "${host}" != server ]]; then - ${VSOCK_TEST} \ + ${cmd} \ --mode=client \ --peer-cid="${cid}" \ --control-host="${host}" \ --control-port="${port}" 2>&1 | log_host rc=$? else - ${VSOCK_TEST} \ + ${cmd} \ --mode=server \ --peer-cid="${cid}" \ --control-port="${port}" 2>&1 | log_host & @@ -416,7 +452,7 @@ host_vsock_test() { return $rc fi

- host_wait_for_listener "${port}" + host_wait_for_listener "${ns}" "${port}" rc=$? fi set +o pipefail @@ -460,11 +496,11 @@ log_guest() { }

test_vm_server_host_client() { - if ! vm_vsock_test "server" 2 "${TEST_GUEST_PORT}"; then + if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then return "${KSFT_FAIL}" fi

- if ! host_vsock_test "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then + if ! host_vsock_test "init_ns" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then return "${KSFT_FAIL}" fi

@@ -472,11 +508,11 @@ test_vm_server_host_client() { }

test_vm_client_host_server() { - if ! host_vsock_test "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then + if ! host_vsock_test "init_ns" "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then return "${KSFT_FAIL}" fi

- if ! vm_vsock_test "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then + if ! vm_vsock_test "init_ns" "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then return "${KSFT_FAIL}" fi

@@ -486,13 +522,14 @@ test_vm_client_host_server() { test_vm_loopback() { local port=60000 # non-forwarded local port

- vm_ssh -- modprobe vsock_loopback &> /dev/null || : + vm_ssh "init_ns" -- modprobe vsock_loopback &> /dev/null || :

- if ! vm_vsock_test "server" 1 "${port}"; then + if ! vm_vsock_test "init_ns" "server" 1 "${port}"; then return "${KSFT_FAIL}" fi

- if ! vm_vsock_test "127.0.0.1" 1 "${port}"; then + + if ! vm_vsock_test "init_ns" "127.0.0.1" 1 "${port}"; then return "${KSFT_FAIL}" fi

@@ -621,8 +658,8 @@ cnt_total=0 if shared_vm_tests_requested "${ARGS[@]}"; then log_host "Booting up VM" pidfile="$(create_pidfile)" - vm_start "${pidfile}" - vm_wait_for_ssh + vm_start "${pidfile}" "init_ns" + vm_wait_for_ssh "init_ns" log_host "VM booted up"

run_shared_vm_tests "${ARGS[@]}"

From: Bobby Eshleman bobbyeshleman@meta.com

Replace /proc/net parsing with ss(8) for detecting listening sockets in wait_for_listener() functions and add support for TCP, VSOCK, and Unix socket protocols.

The previous implementation parsed /proc/net/tcp using awk to detect listening sockets, but this approach could not support vsock because vsock does not export socket information to /proc/net/.

Instead, use ss so that we can detect listeners on tcp, vsock, and unix.

The protocol parameter is now required for all wait_for_listener family functions (wait_for_listener, vm_wait_for_listener, host_wait_for_listener) to explicitly specify which socket type to wait for.

ss is added to the dependency check in check_deps().

Reviewed-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- tools/testing/selftests/vsock/vmtest.sh | 47 +++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 4b5929ffc9eb..0e681d4c3a15 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -182,7 +182,7 @@ check_args() { }

check_deps() { - for dep in vng ${QEMU} busybox pkill ssh; do + for dep in vng ${QEMU} busybox pkill ssh ss; do if [[ ! -x $(command -v "${dep}") ]]; then echo -e "skip: dependency ${dep} not found!\n" exit "${KSFT_SKIP}" @@ -337,21 +337,32 @@ wait_for_listener() local port=$1 local interval=$2 local max_intervals=$3 - local protocol=tcp - local pattern + local protocol=$4 local i

- pattern=":$(printf "%04X" "${port}") " - - # for tcp protocol additionally check the socket state - [ "${protocol}" = "tcp" ] && pattern="${pattern}0A" - for i in $(seq "${max_intervals}"); do - if awk -v pattern="${pattern}" \ - 'BEGIN {rc=1} $2" "$4 ~ pattern {rc=0} END {exit rc}' \ - /proc/net/"${protocol}"*; then + case "${protocol}" in + tcp) + if ss --listening --tcp --numeric | grep -q ":${port} "; then + break + fi + ;; + vsock) + if ss --listening --vsock --numeric | grep -q ":${port} "; then + break + fi + ;; + unix) + # For unix sockets, port is actually the socket path + if ss --listening --unix | grep -q "${port}"; then + break + fi + ;; + *) + echo "Unknown protocol: ${protocol}" >&2 break - fi + ;; + esac sleep "${interval}" done } @@ -359,23 +370,25 @@ wait_for_listener() vm_wait_for_listener() { local ns=$1 local port=$2 + local protocol=$3

vm_ssh "${ns}" <<EOF $(declare -f wait_for_listener) -wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} +wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} ${protocol} EOF }

host_wait_for_listener() { local ns=$1 local port=$2 + local protocol=$3

if [[ "${ns}" == "init_ns" ]]; then - wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" "${protocol}" else ip netns exec "${ns}" bash <<-EOF $(declare -f wait_for_listener) - wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} + wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} ${protocol} EOF fi } @@ -422,7 +435,7 @@ vm_vsock_test() { return $rc fi

- vm_wait_for_listener "${ns}" "${port}" + vm_wait_for_listener "${ns}" "${port}" "tcp" rc=$? fi set +o pipefail @@ -463,7 +476,7 @@ host_vsock_test() { return $rc fi

- host_wait_for_listener "${ns}" "${port}" + host_wait_for_listener "${ns}" "${port}" "tcp" rc=$? fi set +o pipefail

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests to verify CID collision rules across different vsock namespace modes.

1. Two VMs with the same CID cannot start in different global namespaces (ns_global_same_cid_fails) 2. Two VMs with the same CID can start in different local namespaces (ns_local_same_cid_ok) 3. VMs with the same CID can coexist when one is in a global namespace and another is in a local namespace (ns_global_local_same_cid_ok and ns_local_global_same_cid_ok)

The tests ns_global_local_same_cid_ok and ns_local_global_same_cid_ok make sure that ordering does not matter.

The tests use a shared helper function namespaces_can_boot_same_cid() that attempts to start two VMs with identical CIDs in the specified namespaces and verifies whether VM initialization failed or succeeded.

Reviewed-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v11: - check vm_start() rc in namespaces_can_boot_same_cid() (Stefano) - fix ns_local_same_cid_ok() to use local0 and local1 instead of reusing local0 twice. This check should pass, ensuring local namespaces do not collide (Stefano) --- tools/testing/selftests/vsock/vmtest.sh | 78 +++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 38785a102236..1bf537410ea6 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -50,6 +50,10 @@ readonly TEST_NAMES=( vm_loopback ns_host_vsock_ns_mode_ok ns_host_vsock_child_ns_mode_ok + ns_global_same_cid_fails + ns_local_same_cid_ok + ns_global_local_same_cid_ok + ns_local_global_same_cid_ok ) readonly TEST_DESCS=( # vm_server_host_client @@ -66,6 +70,18 @@ readonly TEST_DESCS=(

# ns_host_vsock_child_ns_mode_ok "Check /proc/sys/net/vsock/ns_mode is read-only and child_ns_mode is writable." + + # ns_global_same_cid_fails + "Check QEMU fails to start two VMs with same CID in two different global namespaces." + + # ns_local_same_cid_ok + "Check QEMU successfully starts two VMs with same CID in two different local namespaces." + + # ns_global_local_same_cid_ok + "Check QEMU successfully starts one VM in a global ns and then another VM in a local ns with the same CID." + + # ns_local_global_same_cid_ok + "Check QEMU successfully starts one VM in a local ns and then another VM in a global ns with the same CID." )

readonly USE_SHARED_VM=( @@ -577,6 +593,68 @@ test_ns_host_vsock_ns_mode_ok() { return "${KSFT_PASS}" }

+namespaces_can_boot_same_cid() { + local ns0=$1 + local ns1=$2 + local pidfile1 pidfile2 + local rc + + pidfile1="$(create_pidfile)" + + # The first VM should be able to start. If it can't then we have + # problems and need to return non-zero. + if ! vm_start "${pidfile1}" "${ns0}"; then + return 1 + fi + + pidfile2="$(create_pidfile)" + vm_start "${pidfile2}" "${ns1}" + rc=$? + terminate_pidfiles "${pidfile1}" "${pidfile2}" + + return "${rc}" +} + +test_ns_global_same_cid_fails() { + init_namespaces + + if namespaces_can_boot_same_cid "global0" "global1"; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" +} + +test_ns_local_global_same_cid_ok() { + init_namespaces + + if namespaces_can_boot_same_cid "local0" "global0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_global_local_same_cid_ok() { + init_namespaces + + if namespaces_can_boot_same_cid "global0" "local0"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + +test_ns_local_same_cid_ok() { + init_namespaces + + if namespaces_can_boot_same_cid "local0" "local1"; then + return "${KSFT_PASS}" + fi + + return "${KSFT_FAIL}" +} + test_ns_host_vsock_child_ns_mode_ok() { local orig_mode local rc

From: Bobby Eshleman bobbyeshleman@meta.com

Add tests that validate vsock sockets are resilient to deleting namespaces. The vsock sockets should still function normally.

The function check_ns_delete_doesnt_break_connection() is added to re-use the step-by-step logic of 1) setup connections, 2) delete ns, 3) check that the connections are still ok.

Signed-off-by: Bobby Eshleman bobbyeshleman@meta.com --- Changes in v13: - remove tests that change the mode after socket creation (this is not supported behavior now and the immutability property is tested in other tests) - remove "change_mode" behavior of check_ns_changes_dont_break_connection() and rename to check_ns_delete_doesnt_break_connection() because we only need to test namespace deletion (other tests confirm that the mode cannot change)

Changes in v11: - remove pipefile (Stefano)

Changes in v9: - more consistent shell style - clarify -u usage comment for pipefile --- tools/testing/selftests/vsock/vmtest.sh | 84 +++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index a9eaf37bc31b..dc8dbe74a6d0 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -68,6 +68,9 @@ readonly TEST_NAMES=( ns_same_local_loopback_ok ns_same_local_host_connect_to_local_vm_ok ns_same_local_vm_connect_to_local_host_ok + ns_delete_vm_ok + ns_delete_host_ok + ns_delete_both_ok ) readonly TEST_DESCS=( # vm_server_host_client @@ -135,6 +138,15 @@ readonly TEST_DESCS=(

# ns_same_local_vm_connect_to_local_host_ok "Run vsock_test client in VM in a local ns with server in same ns." + + # ns_delete_vm_ok + "Check that deleting the VM's namespace does not break the socket connection" + + # ns_delete_host_ok + "Check that deleting the host's namespace does not break the socket connection" + + # ns_delete_both_ok + "Check that deleting the VM and host's namespaces does not break the socket connection" )

readonly USE_SHARED_VM=( @@ -1287,6 +1299,78 @@ test_vm_loopback() { return "${KSFT_PASS}" }

+check_ns_delete_doesnt_break_connection() { + local pipefile pidfile outfile + local ns0="global0" + local ns1="global1" + local port=12345 + local pids=() + local rc=0 + + init_namespaces + + pidfile="$(create_pidfile)" + if ! vm_start "${pidfile}" "${ns0}"; then + return "${KSFT_FAIL}" + fi + vm_wait_for_ssh "${ns0}" + + outfile=$(mktemp) + vm_ssh "${ns0}" -- \ + socat VSOCK-LISTEN:"${port}",fork STDOUT > "${outfile}" 2>/dev/null & + pids+=($!) + vm_wait_for_listener "${ns0}" "${port}" "vsock" + + # We use a pipe here so that we can echo into the pipe instead of using + # socat and a unix socket file. We just need a name for the pipe (not a + # regular file) so use -u. + pipefile=$(mktemp -u /tmp/vmtest_pipe_XXXX) + ip netns exec "${ns1}" \ + socat PIPE:"${pipefile}" VSOCK-CONNECT:"${VSOCK_CID}":"${port}" & + pids+=($!) + + timeout "${WAIT_PERIOD}" \ + bash -c 'while [[ ! -e '"${pipefile}"' ]]; do sleep 1; done; exit 0' + + if [[ "$1" == "vm" ]]; then + ip netns del "${ns0}" + elif [[ "$1" == "host" ]]; then + ip netns del "${ns1}" + elif [[ "$1" == "both" ]]; then + ip netns del "${ns0}" + ip netns del "${ns1}" + fi + + echo "TEST" > "${pipefile}" + + timeout "${WAIT_PERIOD}" \ + bash -c 'while [[ ! -s '"${outfile}"' ]]; do sleep 1; done; exit 0' + + if grep -q "TEST" "${outfile}"; then + rc="${KSFT_PASS}" + else + rc="${KSFT_FAIL}" + fi + + terminate_pidfiles "${pidfile}" + terminate_pids "${pids[@]}" + rm -f "${outfile}" "${pipefile}" + + return "${rc}" +} + +test_ns_delete_vm_ok() { + check_ns_delete_doesnt_break_connection "vm" +} + +test_ns_delete_host_ok() { + check_ns_delete_doesnt_break_connection "host" +} + +test_ns_delete_both_ok() { + check_ns_delete_doesnt_break_connection "both" +} + shared_vm_test() { local tname